From 35ef8c0707b68f7cbd10b14dc031932b25d361d4 Mon Sep 17 00:00:00 2001 From: Jose Santos Date: Thu, 7 Mar 2024 15:19:48 -0600 Subject: [PATCH] update workloads] Signed-off-by: Jose Santos --- .../device_filter/MI100/SQ_IFETCH_LEVEL.csv | 6 +++--- .../device_filter/MI100/SQ_INST_LEVEL_LDS.csv | 6 +++--- .../device_filter/MI100/SQ_INST_LEVEL_SMEM.csv | 6 +++--- .../device_filter/MI100/SQ_INST_LEVEL_VMEM.csv | 6 +++--- .../device_filter/MI100/SQ_LEVEL_WAVES.csv | 6 +++--- .../workloads/device_filter/MI100/pmc_perf.csv | 8 ++++---- tests/workloads/device_filter/MI100/sysinfo.csv | 2 +- .../device_filter/MI100/timestamps.csv | 6 +++--- .../device_filter/MI200/SQ_IFETCH_LEVEL.csv | 4 ++++ .../device_filter/MI200/SQ_INST_LEVEL_LDS.csv | 4 ++++ .../device_filter/MI200/SQ_INST_LEVEL_SMEM.csv | 4 ++++ .../device_filter/MI200/SQ_INST_LEVEL_VMEM.csv | 4 ++++ .../device_filter/MI200/SQ_LEVEL_WAVES.csv | 4 ++++ .../MI200/perfmon/SQ_IFETCH_LEVEL.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_LDS.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_SMEM.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_VMEM.txt | 5 +++++ .../MI200/perfmon/SQ_LEVEL_WAVES.txt | 5 +++++ .../device_filter/MI200/perfmon/pmc_perf_0.txt | 5 +++++ .../device_filter/MI200/perfmon/pmc_perf_1.txt | 5 +++++ .../device_filter/MI200/perfmon/pmc_perf_10.txt | 5 +++++ .../device_filter/MI200/perfmon/pmc_perf_11.txt | 5 +++++ .../device_filter/MI200/perfmon/pmc_perf_12.txt | 5 +++++ .../device_filter/MI200/perfmon/pmc_perf_13.txt | 5 +++++ .../device_filter/MI200/perfmon/pmc_perf_14.txt | 5 +++++ .../device_filter/MI200/perfmon/pmc_perf_15.txt | 5 +++++ .../device_filter/MI200/perfmon/pmc_perf_16.txt | 5 +++++ .../device_filter/MI200/perfmon/pmc_perf_17.txt | 5 +++++ .../device_filter/MI200/perfmon/pmc_perf_18.txt | 5 +++++ .../device_filter/MI200/perfmon/pmc_perf_2.txt | 5 +++++ .../device_filter/MI200/perfmon/pmc_perf_3.txt | 5 +++++ .../device_filter/MI200/perfmon/pmc_perf_4.txt | 5 +++++ .../device_filter/MI200/perfmon/pmc_perf_5.txt | 5 +++++ .../device_filter/MI200/perfmon/pmc_perf_6.txt | 5 +++++ .../device_filter/MI200/perfmon/pmc_perf_7.txt | 5 +++++ .../device_filter/MI200/perfmon/pmc_perf_8.txt | 5 +++++ .../device_filter/MI200/perfmon/pmc_perf_9.txt | 5 +++++ .../device_filter/MI200/perfmon/timestamps.txt | 5 +++++ .../workloads/device_filter/MI200/pmc_perf.csv | 4 ++++ .../workloads/device_filter/MI200/roofline.csv | 2 ++ tests/workloads/device_filter/MI200/sysinfo.csv | 2 ++ .../device_filter/MI200/timestamps.csv | 4 ++++ .../device_inv_int/MI100/SQ_IFETCH_LEVEL.csv | 6 +++--- .../device_inv_int/MI100/SQ_INST_LEVEL_LDS.csv | 6 +++--- .../device_inv_int/MI100/SQ_INST_LEVEL_SMEM.csv | 6 +++--- .../device_inv_int/MI100/SQ_INST_LEVEL_VMEM.csv | 6 +++--- .../device_inv_int/MI100/SQ_LEVEL_WAVES.csv | 6 +++--- .../device_inv_int/MI100/pmc_dispatch_info.csv | 4 ++++ .../workloads/device_inv_int/MI100/pmc_perf.csv | 8 ++++---- .../workloads/device_inv_int/MI100/sysinfo.csv | 2 +- .../device_inv_int/MI100/timestamps.csv | 6 +++--- .../device_inv_int/MI200/SQ_IFETCH_LEVEL.csv | 4 ++++ .../device_inv_int/MI200/SQ_INST_LEVEL_LDS.csv | 4 ++++ .../device_inv_int/MI200/SQ_INST_LEVEL_SMEM.csv | 4 ++++ .../device_inv_int/MI200/SQ_INST_LEVEL_VMEM.csv | 4 ++++ .../device_inv_int/MI200/SQ_LEVEL_WAVES.csv | 4 ++++ .../MI200/perfmon/SQ_IFETCH_LEVEL.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_LDS.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_SMEM.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_VMEM.txt | 5 +++++ .../MI200/perfmon/SQ_LEVEL_WAVES.txt | 5 +++++ .../device_inv_int/MI200/perfmon/pmc_perf_0.txt | 5 +++++ .../device_inv_int/MI200/perfmon/pmc_perf_1.txt | 5 +++++ .../MI200/perfmon/pmc_perf_10.txt | 5 +++++ .../MI200/perfmon/pmc_perf_11.txt | 5 +++++ .../MI200/perfmon/pmc_perf_12.txt | 5 +++++ .../MI200/perfmon/pmc_perf_13.txt | 5 +++++ .../MI200/perfmon/pmc_perf_14.txt | 5 +++++ .../MI200/perfmon/pmc_perf_15.txt | 5 +++++ .../MI200/perfmon/pmc_perf_16.txt | 5 +++++ .../MI200/perfmon/pmc_perf_17.txt | 5 +++++ .../MI200/perfmon/pmc_perf_18.txt | 5 +++++ .../device_inv_int/MI200/perfmon/pmc_perf_2.txt | 5 +++++ .../device_inv_int/MI200/perfmon/pmc_perf_3.txt | 5 +++++ .../device_inv_int/MI200/perfmon/pmc_perf_4.txt | 5 +++++ .../device_inv_int/MI200/perfmon/pmc_perf_5.txt | 5 +++++ .../device_inv_int/MI200/perfmon/pmc_perf_6.txt | 5 +++++ .../device_inv_int/MI200/perfmon/pmc_perf_7.txt | 5 +++++ .../device_inv_int/MI200/perfmon/pmc_perf_8.txt | 5 +++++ .../device_inv_int/MI200/perfmon/pmc_perf_9.txt | 5 +++++ .../device_inv_int/MI200/perfmon/timestamps.txt | 5 +++++ .../workloads/device_inv_int/MI200/pmc_perf.csv | 4 ++++ .../workloads/device_inv_int/MI200/roofline.csv | 5 +++++ .../workloads/device_inv_int/MI200/sysinfo.csv | 2 ++ .../device_inv_int/MI200/timestamps.csv | 4 ++++ .../dispatch_0/MI100/SQ_IFETCH_LEVEL.csv | 2 +- .../dispatch_0/MI100/SQ_INST_LEVEL_LDS.csv | 2 +- .../dispatch_0/MI100/SQ_INST_LEVEL_SMEM.csv | 2 +- .../dispatch_0/MI100/SQ_INST_LEVEL_VMEM.csv | 2 +- .../dispatch_0/MI100/SQ_LEVEL_WAVES.csv | 2 +- .../dispatch_0/MI100/pmc_dispatch_info.csv | 2 ++ tests/workloads/dispatch_0/MI100/pmc_perf.csv | 4 ++-- tests/workloads/dispatch_0/MI100/sysinfo.csv | 2 +- tests/workloads/dispatch_0/MI100/timestamps.csv | 2 +- .../dispatch_0/MI200/SQ_IFETCH_LEVEL.csv | 2 ++ .../dispatch_0/MI200/SQ_INST_LEVEL_LDS.csv | 2 ++ .../dispatch_0/MI200/SQ_INST_LEVEL_SMEM.csv | 2 ++ .../dispatch_0/MI200/SQ_INST_LEVEL_VMEM.csv | 2 ++ .../dispatch_0/MI200/SQ_LEVEL_WAVES.csv | 2 ++ .../MI200/perfmon/SQ_IFETCH_LEVEL.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_LDS.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_SMEM.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_VMEM.txt | 5 +++++ .../dispatch_0/MI200/perfmon/SQ_LEVEL_WAVES.txt | 5 +++++ .../dispatch_0/MI200/perfmon/pmc_perf_0.txt | 5 +++++ .../dispatch_0/MI200/perfmon/pmc_perf_1.txt | 5 +++++ .../dispatch_0/MI200/perfmon/pmc_perf_10.txt | 5 +++++ .../dispatch_0/MI200/perfmon/pmc_perf_11.txt | 5 +++++ .../dispatch_0/MI200/perfmon/pmc_perf_12.txt | 5 +++++ .../dispatch_0/MI200/perfmon/pmc_perf_13.txt | 5 +++++ .../dispatch_0/MI200/perfmon/pmc_perf_14.txt | 5 +++++ .../dispatch_0/MI200/perfmon/pmc_perf_15.txt | 5 +++++ .../dispatch_0/MI200/perfmon/pmc_perf_16.txt | 5 +++++ .../dispatch_0/MI200/perfmon/pmc_perf_17.txt | 5 +++++ .../dispatch_0/MI200/perfmon/pmc_perf_18.txt | 5 +++++ .../dispatch_0/MI200/perfmon/pmc_perf_2.txt | 5 +++++ .../dispatch_0/MI200/perfmon/pmc_perf_3.txt | 5 +++++ .../dispatch_0/MI200/perfmon/pmc_perf_4.txt | 5 +++++ .../dispatch_0/MI200/perfmon/pmc_perf_5.txt | 5 +++++ .../dispatch_0/MI200/perfmon/pmc_perf_6.txt | 5 +++++ .../dispatch_0/MI200/perfmon/pmc_perf_7.txt | 5 +++++ .../dispatch_0/MI200/perfmon/pmc_perf_8.txt | 5 +++++ .../dispatch_0/MI200/perfmon/pmc_perf_9.txt | 5 +++++ .../dispatch_0/MI200/perfmon/timestamps.txt | 5 +++++ tests/workloads/dispatch_0/MI200/pmc_perf.csv | 2 ++ tests/workloads/dispatch_0/MI200/roofline.csv | 5 +++++ tests/workloads/dispatch_0/MI200/sysinfo.csv | 2 ++ tests/workloads/dispatch_0/MI200/timestamps.csv | 2 ++ .../dispatch_0_1/MI100/SQ_IFETCH_LEVEL.csv | 4 ++-- .../dispatch_0_1/MI100/SQ_INST_LEVEL_LDS.csv | 4 ++-- .../dispatch_0_1/MI100/SQ_INST_LEVEL_SMEM.csv | 4 ++-- .../dispatch_0_1/MI100/SQ_INST_LEVEL_VMEM.csv | 4 ++-- .../dispatch_0_1/MI100/SQ_LEVEL_WAVES.csv | 4 ++-- .../dispatch_0_1/MI100/pmc_dispatch_info.csv | 3 +++ tests/workloads/dispatch_0_1/MI100/pmc_perf.csv | 6 +++--- tests/workloads/dispatch_0_1/MI100/sysinfo.csv | 2 +- .../workloads/dispatch_0_1/MI100/timestamps.csv | 4 ++-- .../dispatch_0_1/MI200/SQ_IFETCH_LEVEL.csv | 3 +++ .../dispatch_0_1/MI200/SQ_INST_LEVEL_LDS.csv | 3 +++ .../dispatch_0_1/MI200/SQ_INST_LEVEL_SMEM.csv | 3 +++ .../dispatch_0_1/MI200/SQ_INST_LEVEL_VMEM.csv | 3 +++ .../dispatch_0_1/MI200/SQ_LEVEL_WAVES.csv | 3 +++ .../MI200/perfmon/SQ_IFETCH_LEVEL.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_LDS.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_SMEM.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_VMEM.txt | 5 +++++ .../MI200/perfmon/SQ_LEVEL_WAVES.txt | 5 +++++ .../dispatch_0_1/MI200/perfmon/pmc_perf_0.txt | 5 +++++ .../dispatch_0_1/MI200/perfmon/pmc_perf_1.txt | 5 +++++ .../dispatch_0_1/MI200/perfmon/pmc_perf_10.txt | 5 +++++ .../dispatch_0_1/MI200/perfmon/pmc_perf_11.txt | 5 +++++ .../dispatch_0_1/MI200/perfmon/pmc_perf_12.txt | 5 +++++ .../dispatch_0_1/MI200/perfmon/pmc_perf_13.txt | 5 +++++ .../dispatch_0_1/MI200/perfmon/pmc_perf_14.txt | 5 +++++ .../dispatch_0_1/MI200/perfmon/pmc_perf_15.txt | 5 +++++ .../dispatch_0_1/MI200/perfmon/pmc_perf_16.txt | 5 +++++ .../dispatch_0_1/MI200/perfmon/pmc_perf_17.txt | 5 +++++ .../dispatch_0_1/MI200/perfmon/pmc_perf_18.txt | 5 +++++ .../dispatch_0_1/MI200/perfmon/pmc_perf_2.txt | 5 +++++ .../dispatch_0_1/MI200/perfmon/pmc_perf_3.txt | 5 +++++ .../dispatch_0_1/MI200/perfmon/pmc_perf_4.txt | 5 +++++ .../dispatch_0_1/MI200/perfmon/pmc_perf_5.txt | 5 +++++ .../dispatch_0_1/MI200/perfmon/pmc_perf_6.txt | 5 +++++ .../dispatch_0_1/MI200/perfmon/pmc_perf_7.txt | 5 +++++ .../dispatch_0_1/MI200/perfmon/pmc_perf_8.txt | 5 +++++ .../dispatch_0_1/MI200/perfmon/pmc_perf_9.txt | 5 +++++ .../dispatch_0_1/MI200/perfmon/timestamps.txt | 5 +++++ tests/workloads/dispatch_0_1/MI200/pmc_perf.csv | 3 +++ tests/workloads/dispatch_0_1/MI200/roofline.csv | 5 +++++ tests/workloads/dispatch_0_1/MI200/sysinfo.csv | 2 ++ .../workloads/dispatch_0_1/MI200/timestamps.csv | 3 +++ .../dispatch_2/MI100/SQ_IFETCH_LEVEL.csv | 2 +- .../dispatch_2/MI100/SQ_INST_LEVEL_LDS.csv | 2 +- .../dispatch_2/MI100/SQ_INST_LEVEL_SMEM.csv | 2 +- .../dispatch_2/MI100/SQ_INST_LEVEL_VMEM.csv | 2 +- .../dispatch_2/MI100/SQ_LEVEL_WAVES.csv | 2 +- .../dispatch_2/MI100/pmc_dispatch_info.csv | 2 ++ tests/workloads/dispatch_2/MI100/pmc_perf.csv | 4 ++-- tests/workloads/dispatch_2/MI100/sysinfo.csv | 2 +- tests/workloads/dispatch_2/MI100/timestamps.csv | 2 +- .../dispatch_2/MI200/SQ_IFETCH_LEVEL.csv | 2 ++ .../dispatch_2/MI200/SQ_INST_LEVEL_LDS.csv | 2 ++ .../dispatch_2/MI200/SQ_INST_LEVEL_SMEM.csv | 2 ++ .../dispatch_2/MI200/SQ_INST_LEVEL_VMEM.csv | 2 ++ .../dispatch_2/MI200/SQ_LEVEL_WAVES.csv | 2 ++ .../MI200/perfmon/SQ_IFETCH_LEVEL.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_LDS.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_SMEM.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_VMEM.txt | 5 +++++ .../dispatch_2/MI200/perfmon/SQ_LEVEL_WAVES.txt | 5 +++++ .../dispatch_2/MI200/perfmon/pmc_perf_0.txt | 5 +++++ .../dispatch_2/MI200/perfmon/pmc_perf_1.txt | 5 +++++ .../dispatch_2/MI200/perfmon/pmc_perf_10.txt | 5 +++++ .../dispatch_2/MI200/perfmon/pmc_perf_11.txt | 5 +++++ .../dispatch_2/MI200/perfmon/pmc_perf_12.txt | 5 +++++ .../dispatch_2/MI200/perfmon/pmc_perf_13.txt | 5 +++++ .../dispatch_2/MI200/perfmon/pmc_perf_14.txt | 5 +++++ .../dispatch_2/MI200/perfmon/pmc_perf_15.txt | 5 +++++ .../dispatch_2/MI200/perfmon/pmc_perf_16.txt | 5 +++++ .../dispatch_2/MI200/perfmon/pmc_perf_17.txt | 5 +++++ .../dispatch_2/MI200/perfmon/pmc_perf_18.txt | 5 +++++ .../dispatch_2/MI200/perfmon/pmc_perf_2.txt | 5 +++++ .../dispatch_2/MI200/perfmon/pmc_perf_3.txt | 5 +++++ .../dispatch_2/MI200/perfmon/pmc_perf_4.txt | 5 +++++ .../dispatch_2/MI200/perfmon/pmc_perf_5.txt | 5 +++++ .../dispatch_2/MI200/perfmon/pmc_perf_6.txt | 5 +++++ .../dispatch_2/MI200/perfmon/pmc_perf_7.txt | 5 +++++ .../dispatch_2/MI200/perfmon/pmc_perf_8.txt | 5 +++++ .../dispatch_2/MI200/perfmon/pmc_perf_9.txt | 5 +++++ .../dispatch_2/MI200/perfmon/timestamps.txt | 5 +++++ tests/workloads/dispatch_2/MI200/pmc_perf.csv | 2 ++ tests/workloads/dispatch_2/MI200/roofline.csv | 5 +++++ tests/workloads/dispatch_2/MI200/sysinfo.csv | 2 ++ tests/workloads/dispatch_2/MI200/timestamps.csv | 2 ++ tests/workloads/dispatch_6_8/MI100/sysinfo.csv | 2 +- .../dispatch_6_8/MI200/SQ_IFETCH_LEVEL.csv | 1 + .../dispatch_6_8/MI200/SQ_INST_LEVEL_LDS.csv | 1 + .../dispatch_6_8/MI200/SQ_INST_LEVEL_SMEM.csv | 1 + .../dispatch_6_8/MI200/SQ_INST_LEVEL_VMEM.csv | 1 + .../dispatch_6_8/MI200/SQ_LEVEL_WAVES.csv | 1 + .../MI200/perfmon/SQ_IFETCH_LEVEL.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_LDS.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_SMEM.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_VMEM.txt | 5 +++++ .../MI200/perfmon/SQ_LEVEL_WAVES.txt | 5 +++++ .../dispatch_6_8/MI200/perfmon/pmc_perf_0.txt | 5 +++++ .../dispatch_6_8/MI200/perfmon/pmc_perf_1.txt | 5 +++++ .../dispatch_6_8/MI200/perfmon/pmc_perf_10.txt | 5 +++++ .../dispatch_6_8/MI200/perfmon/pmc_perf_11.txt | 5 +++++ .../dispatch_6_8/MI200/perfmon/pmc_perf_12.txt | 5 +++++ .../dispatch_6_8/MI200/perfmon/pmc_perf_13.txt | 5 +++++ .../dispatch_6_8/MI200/perfmon/pmc_perf_14.txt | 5 +++++ .../dispatch_6_8/MI200/perfmon/pmc_perf_15.txt | 5 +++++ .../dispatch_6_8/MI200/perfmon/pmc_perf_16.txt | 5 +++++ .../dispatch_6_8/MI200/perfmon/pmc_perf_17.txt | 5 +++++ .../dispatch_6_8/MI200/perfmon/pmc_perf_18.txt | 5 +++++ .../dispatch_6_8/MI200/perfmon/pmc_perf_2.txt | 5 +++++ .../dispatch_6_8/MI200/perfmon/pmc_perf_3.txt | 5 +++++ .../dispatch_6_8/MI200/perfmon/pmc_perf_4.txt | 5 +++++ .../dispatch_6_8/MI200/perfmon/pmc_perf_5.txt | 5 +++++ .../dispatch_6_8/MI200/perfmon/pmc_perf_6.txt | 5 +++++ .../dispatch_6_8/MI200/perfmon/pmc_perf_7.txt | 5 +++++ .../dispatch_6_8/MI200/perfmon/pmc_perf_8.txt | 5 +++++ .../dispatch_6_8/MI200/perfmon/pmc_perf_9.txt | 5 +++++ .../dispatch_6_8/MI200/perfmon/timestamps.txt | 5 +++++ .../workloads/dispatch_6_8/MI200/pmc_perf_0.csv | 1 + .../workloads/dispatch_6_8/MI200/pmc_perf_1.csv | 1 + .../dispatch_6_8/MI200/pmc_perf_10.csv | 1 + .../dispatch_6_8/MI200/pmc_perf_11.csv | 1 + .../dispatch_6_8/MI200/pmc_perf_12.csv | 1 + .../dispatch_6_8/MI200/pmc_perf_13.csv | 1 + .../dispatch_6_8/MI200/pmc_perf_14.csv | 1 + .../dispatch_6_8/MI200/pmc_perf_15.csv | 1 + .../dispatch_6_8/MI200/pmc_perf_16.csv | 1 + .../dispatch_6_8/MI200/pmc_perf_17.csv | 1 + .../dispatch_6_8/MI200/pmc_perf_18.csv | 1 + .../workloads/dispatch_6_8/MI200/pmc_perf_2.csv | 1 + .../workloads/dispatch_6_8/MI200/pmc_perf_3.csv | 1 + .../workloads/dispatch_6_8/MI200/pmc_perf_4.csv | 1 + .../workloads/dispatch_6_8/MI200/pmc_perf_5.csv | 1 + .../workloads/dispatch_6_8/MI200/pmc_perf_6.csv | 1 + .../workloads/dispatch_6_8/MI200/pmc_perf_7.csv | 1 + .../workloads/dispatch_6_8/MI200/pmc_perf_8.csv | 1 + .../workloads/dispatch_6_8/MI200/pmc_perf_9.csv | 1 + tests/workloads/dispatch_6_8/MI200/sysinfo.csv | 2 ++ .../workloads/dispatch_6_8/MI200/timestamps.csv | 1 + tests/workloads/dispatch_7/MI100/sysinfo.csv | 2 +- .../dispatch_7/MI200/SQ_IFETCH_LEVEL.csv | 1 + .../dispatch_7/MI200/SQ_INST_LEVEL_LDS.csv | 1 + .../dispatch_7/MI200/SQ_INST_LEVEL_SMEM.csv | 1 + .../dispatch_7/MI200/SQ_INST_LEVEL_VMEM.csv | 1 + .../dispatch_7/MI200/SQ_LEVEL_WAVES.csv | 1 + .../MI200/perfmon/SQ_IFETCH_LEVEL.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_LDS.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_SMEM.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_VMEM.txt | 5 +++++ .../dispatch_7/MI200/perfmon/SQ_LEVEL_WAVES.txt | 5 +++++ .../dispatch_7/MI200/perfmon/pmc_perf_0.txt | 5 +++++ .../dispatch_7/MI200/perfmon/pmc_perf_1.txt | 5 +++++ .../dispatch_7/MI200/perfmon/pmc_perf_10.txt | 5 +++++ .../dispatch_7/MI200/perfmon/pmc_perf_11.txt | 5 +++++ .../dispatch_7/MI200/perfmon/pmc_perf_12.txt | 5 +++++ .../dispatch_7/MI200/perfmon/pmc_perf_13.txt | 5 +++++ .../dispatch_7/MI200/perfmon/pmc_perf_14.txt | 5 +++++ .../dispatch_7/MI200/perfmon/pmc_perf_15.txt | 5 +++++ .../dispatch_7/MI200/perfmon/pmc_perf_16.txt | 5 +++++ .../dispatch_7/MI200/perfmon/pmc_perf_17.txt | 5 +++++ .../dispatch_7/MI200/perfmon/pmc_perf_18.txt | 5 +++++ .../dispatch_7/MI200/perfmon/pmc_perf_2.txt | 5 +++++ .../dispatch_7/MI200/perfmon/pmc_perf_3.txt | 5 +++++ .../dispatch_7/MI200/perfmon/pmc_perf_4.txt | 5 +++++ .../dispatch_7/MI200/perfmon/pmc_perf_5.txt | 5 +++++ .../dispatch_7/MI200/perfmon/pmc_perf_6.txt | 5 +++++ .../dispatch_7/MI200/perfmon/pmc_perf_7.txt | 5 +++++ .../dispatch_7/MI200/perfmon/pmc_perf_8.txt | 5 +++++ .../dispatch_7/MI200/perfmon/pmc_perf_9.txt | 5 +++++ .../dispatch_7/MI200/perfmon/timestamps.txt | 5 +++++ tests/workloads/dispatch_7/MI200/pmc_perf_0.csv | 1 + tests/workloads/dispatch_7/MI200/pmc_perf_1.csv | 1 + .../workloads/dispatch_7/MI200/pmc_perf_10.csv | 1 + .../workloads/dispatch_7/MI200/pmc_perf_11.csv | 1 + .../workloads/dispatch_7/MI200/pmc_perf_12.csv | 1 + .../workloads/dispatch_7/MI200/pmc_perf_13.csv | 1 + .../workloads/dispatch_7/MI200/pmc_perf_14.csv | 1 + .../workloads/dispatch_7/MI200/pmc_perf_15.csv | 1 + .../workloads/dispatch_7/MI200/pmc_perf_16.csv | 1 + .../workloads/dispatch_7/MI200/pmc_perf_17.csv | 1 + .../workloads/dispatch_7/MI200/pmc_perf_18.csv | 1 + tests/workloads/dispatch_7/MI200/pmc_perf_2.csv | 1 + tests/workloads/dispatch_7/MI200/pmc_perf_3.csv | 1 + tests/workloads/dispatch_7/MI200/pmc_perf_4.csv | 1 + tests/workloads/dispatch_7/MI200/pmc_perf_5.csv | 1 + tests/workloads/dispatch_7/MI200/pmc_perf_6.csv | 1 + tests/workloads/dispatch_7/MI200/pmc_perf_7.csv | 1 + tests/workloads/dispatch_7/MI200/pmc_perf_8.csv | 1 + tests/workloads/dispatch_7/MI200/pmc_perf_9.csv | 1 + tests/workloads/dispatch_7/MI200/sysinfo.csv | 2 ++ tests/workloads/dispatch_7/MI200/timestamps.csv | 1 + .../dispatch_inv/MI100/SQ_IFETCH_LEVEL.csv | 2 +- .../dispatch_inv/MI100/SQ_INST_LEVEL_LDS.csv | 2 +- .../dispatch_inv/MI100/SQ_INST_LEVEL_SMEM.csv | 2 +- .../dispatch_inv/MI100/SQ_INST_LEVEL_VMEM.csv | 2 +- .../dispatch_inv/MI100/SQ_LEVEL_WAVES.csv | 2 +- tests/workloads/dispatch_inv/MI100/pmc_perf.csv | 4 ++-- tests/workloads/dispatch_inv/MI100/sysinfo.csv | 2 +- .../workloads/dispatch_inv/MI100/timestamps.csv | 2 +- .../dispatch_inv/MI200/SQ_IFETCH_LEVEL.csv | 2 ++ .../dispatch_inv/MI200/SQ_INST_LEVEL_LDS.csv | 2 ++ .../dispatch_inv/MI200/SQ_INST_LEVEL_SMEM.csv | 2 ++ .../dispatch_inv/MI200/SQ_INST_LEVEL_VMEM.csv | 2 ++ .../dispatch_inv/MI200/SQ_LEVEL_WAVES.csv | 2 ++ .../MI200/perfmon/SQ_IFETCH_LEVEL.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_LDS.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_SMEM.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_VMEM.txt | 5 +++++ .../MI200/perfmon/SQ_LEVEL_WAVES.txt | 5 +++++ .../dispatch_inv/MI200/perfmon/pmc_perf_0.txt | 5 +++++ .../dispatch_inv/MI200/perfmon/pmc_perf_1.txt | 5 +++++ .../dispatch_inv/MI200/perfmon/pmc_perf_10.txt | 5 +++++ .../dispatch_inv/MI200/perfmon/pmc_perf_11.txt | 5 +++++ .../dispatch_inv/MI200/perfmon/pmc_perf_12.txt | 5 +++++ .../dispatch_inv/MI200/perfmon/pmc_perf_13.txt | 5 +++++ .../dispatch_inv/MI200/perfmon/pmc_perf_14.txt | 5 +++++ .../dispatch_inv/MI200/perfmon/pmc_perf_15.txt | 5 +++++ .../dispatch_inv/MI200/perfmon/pmc_perf_16.txt | 5 +++++ .../dispatch_inv/MI200/perfmon/pmc_perf_17.txt | 5 +++++ .../dispatch_inv/MI200/perfmon/pmc_perf_18.txt | 5 +++++ .../dispatch_inv/MI200/perfmon/pmc_perf_2.txt | 5 +++++ .../dispatch_inv/MI200/perfmon/pmc_perf_3.txt | 5 +++++ .../dispatch_inv/MI200/perfmon/pmc_perf_4.txt | 5 +++++ .../dispatch_inv/MI200/perfmon/pmc_perf_5.txt | 5 +++++ .../dispatch_inv/MI200/perfmon/pmc_perf_6.txt | 5 +++++ .../dispatch_inv/MI200/perfmon/pmc_perf_7.txt | 5 +++++ .../dispatch_inv/MI200/perfmon/pmc_perf_8.txt | 5 +++++ .../dispatch_inv/MI200/perfmon/pmc_perf_9.txt | 5 +++++ .../dispatch_inv/MI200/perfmon/timestamps.txt | 5 +++++ tests/workloads/dispatch_inv/MI200/pmc_perf.csv | 2 ++ tests/workloads/dispatch_inv/MI200/roofline.csv | 5 +++++ tests/workloads/dispatch_inv/MI200/sysinfo.csv | 2 ++ .../workloads/dispatch_inv/MI200/timestamps.csv | 2 ++ .../dispatch_invalid/MI100/SQ_IFETCH_LEVEL.csv | 2 ++ .../MI100/SQ_INST_LEVEL_LDS.csv | 2 ++ .../MI100/SQ_INST_LEVEL_SMEM.csv | 2 ++ .../MI100/SQ_INST_LEVEL_VMEM.csv | 2 ++ .../dispatch_invalid/MI100/SQ_LEVEL_WAVES.csv | 2 ++ .../MI100/perfmon/SQ_IFETCH_LEVEL.txt | 5 +++++ .../MI100/perfmon/SQ_INST_LEVEL_LDS.txt | 5 +++++ .../MI100/perfmon/SQ_INST_LEVEL_SMEM.txt | 5 +++++ .../MI100/perfmon/SQ_INST_LEVEL_VMEM.txt | 5 +++++ .../MI100/perfmon/SQ_LEVEL_WAVES.txt | 5 +++++ .../MI100/perfmon/pmc_perf_0.txt | 5 +++++ .../MI100/perfmon/pmc_perf_1.txt | 5 +++++ .../MI100/perfmon/pmc_perf_10.txt | 5 +++++ .../MI100/perfmon/pmc_perf_11.txt | 5 +++++ .../MI100/perfmon/pmc_perf_12.txt | 5 +++++ .../MI100/perfmon/pmc_perf_13.txt | 5 +++++ .../MI100/perfmon/pmc_perf_14.txt | 5 +++++ .../MI100/perfmon/pmc_perf_15.txt | 5 +++++ .../MI100/perfmon/pmc_perf_16.txt | 5 +++++ .../MI100/perfmon/pmc_perf_2.txt | 5 +++++ .../MI100/perfmon/pmc_perf_3.txt | 5 +++++ .../MI100/perfmon/pmc_perf_4.txt | 5 +++++ .../MI100/perfmon/pmc_perf_5.txt | 5 +++++ .../MI100/perfmon/pmc_perf_6.txt | 5 +++++ .../MI100/perfmon/pmc_perf_7.txt | 5 +++++ .../MI100/perfmon/pmc_perf_8.txt | 5 +++++ .../MI100/perfmon/pmc_perf_9.txt | 5 +++++ .../MI100/perfmon/timestamps.txt | 5 +++++ .../MI100/pmc_dispatch_info.csv | 2 ++ .../dispatch_invalid/MI100/pmc_perf.csv | 2 ++ .../dispatch_invalid/MI100/sysinfo.csv | 2 ++ .../dispatch_invalid/MI100/timestamps.csv | 2 ++ .../ipblocks_CPC/MI100/pmc_dispatch_info.csv | 4 ++++ tests/workloads/ipblocks_CPC/MI100/pmc_perf.csv | 8 ++++---- tests/workloads/ipblocks_CPC/MI100/sysinfo.csv | 2 +- .../workloads/ipblocks_CPC/MI100/timestamps.csv | 6 +++--- .../ipblocks_CPC/MI200/perfmon/pmc_perf_0.txt | 5 +++++ .../ipblocks_CPC/MI200/perfmon/pmc_perf_1.txt | 5 +++++ .../ipblocks_CPC/MI200/perfmon/pmc_perf_2.txt | 5 +++++ .../ipblocks_CPC/MI200/perfmon/pmc_perf_3.txt | 5 +++++ .../ipblocks_CPC/MI200/perfmon/pmc_perf_4.txt | 5 +++++ .../ipblocks_CPC/MI200/perfmon/pmc_perf_5.txt | 5 +++++ .../ipblocks_CPC/MI200/perfmon/timestamps.txt | 5 +++++ tests/workloads/ipblocks_CPC/MI200/pmc_perf.csv | 4 ++++ tests/workloads/ipblocks_CPC/MI200/roofline.csv | 5 +++++ tests/workloads/ipblocks_CPC/MI200/sysinfo.csv | 2 ++ .../workloads/ipblocks_CPC/MI200/timestamps.csv | 4 ++++ .../ipblocks_CPF/MI100/pmc_dispatch_info.csv | 4 ++++ tests/workloads/ipblocks_CPF/MI100/pmc_perf.csv | 8 ++++---- tests/workloads/ipblocks_CPF/MI100/sysinfo.csv | 2 +- .../workloads/ipblocks_CPF/MI100/timestamps.csv | 6 +++--- .../ipblocks_CPF/MI200/perfmon/pmc_perf_0.txt | 5 +++++ .../ipblocks_CPF/MI200/perfmon/pmc_perf_1.txt | 5 +++++ .../ipblocks_CPF/MI200/perfmon/pmc_perf_2.txt | 5 +++++ .../ipblocks_CPF/MI200/perfmon/pmc_perf_3.txt | 5 +++++ .../ipblocks_CPF/MI200/perfmon/timestamps.txt | 5 +++++ tests/workloads/ipblocks_CPF/MI200/pmc_perf.csv | 4 ++++ tests/workloads/ipblocks_CPF/MI200/roofline.csv | 5 +++++ tests/workloads/ipblocks_CPF/MI200/sysinfo.csv | 2 ++ .../workloads/ipblocks_CPF/MI200/timestamps.csv | 4 ++++ .../ipblocks_SPI/MI100/pmc_dispatch_info.csv | 4 ++++ tests/workloads/ipblocks_SPI/MI100/pmc_perf.csv | 8 ++++---- tests/workloads/ipblocks_SPI/MI100/sysinfo.csv | 2 +- .../workloads/ipblocks_SPI/MI100/timestamps.csv | 6 +++--- .../ipblocks_SQ/MI100/SQ_IFETCH_LEVEL.csv | 6 +++--- .../ipblocks_SQ/MI100/SQ_INST_LEVEL_LDS.csv | 6 +++--- .../ipblocks_SQ/MI100/SQ_INST_LEVEL_SMEM.csv | 6 +++--- .../ipblocks_SQ/MI100/SQ_INST_LEVEL_VMEM.csv | 6 +++--- .../ipblocks_SQ/MI100/SQ_LEVEL_WAVES.csv | 6 +++--- .../ipblocks_SQ/MI100/pmc_dispatch_info.csv | 4 ++++ tests/workloads/ipblocks_SQ/MI100/pmc_perf.csv | 8 ++++---- tests/workloads/ipblocks_SQ/MI100/sysinfo.csv | 2 +- .../workloads/ipblocks_SQ/MI100/timestamps.csv | 6 +++--- .../ipblocks_SQ/MI200/SQ_IFETCH_LEVEL.csv | 4 ++++ .../ipblocks_SQ/MI200/SQ_INST_LEVEL_LDS.csv | 4 ++++ .../ipblocks_SQ/MI200/SQ_INST_LEVEL_SMEM.csv | 4 ++++ .../ipblocks_SQ/MI200/SQ_INST_LEVEL_VMEM.csv | 4 ++++ .../ipblocks_SQ/MI200/SQ_LEVEL_WAVES.csv | 4 ++++ .../MI200/perfmon/SQ_IFETCH_LEVEL.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_LDS.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_SMEM.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_VMEM.txt | 5 +++++ .../MI200/perfmon/SQ_LEVEL_WAVES.txt | 5 +++++ .../ipblocks_SQ/MI200/perfmon/pmc_perf_0.txt | 5 +++++ .../ipblocks_SQ/MI200/perfmon/pmc_perf_1.txt | 5 +++++ .../ipblocks_SQ/MI200/perfmon/pmc_perf_10.txt | 5 +++++ .../ipblocks_SQ/MI200/perfmon/pmc_perf_11.txt | 5 +++++ .../ipblocks_SQ/MI200/perfmon/pmc_perf_12.txt | 5 +++++ .../ipblocks_SQ/MI200/perfmon/pmc_perf_2.txt | 5 +++++ .../ipblocks_SQ/MI200/perfmon/pmc_perf_3.txt | 5 +++++ .../ipblocks_SQ/MI200/perfmon/pmc_perf_4.txt | 5 +++++ .../ipblocks_SQ/MI200/perfmon/pmc_perf_5.txt | 5 +++++ .../ipblocks_SQ/MI200/perfmon/pmc_perf_6.txt | 5 +++++ .../ipblocks_SQ/MI200/perfmon/pmc_perf_7.txt | 5 +++++ .../ipblocks_SQ/MI200/perfmon/pmc_perf_8.txt | 5 +++++ .../ipblocks_SQ/MI200/perfmon/pmc_perf_9.txt | 5 +++++ .../ipblocks_SQ/MI200/perfmon/timestamps.txt | 5 +++++ tests/workloads/ipblocks_SQ/MI200/pmc_perf.csv | 4 ++++ tests/workloads/ipblocks_SQ/MI200/roofline.csv | 5 +++++ tests/workloads/ipblocks_SQ/MI200/sysinfo.csv | 2 ++ .../workloads/ipblocks_SQ/MI200/timestamps.csv | 4 ++++ .../ipblocks_SQC/MI100/pmc_dispatch_info.csv | 4 ++++ tests/workloads/ipblocks_SQC/MI100/pmc_perf.csv | 8 ++++---- tests/workloads/ipblocks_SQC/MI100/sysinfo.csv | 2 +- .../workloads/ipblocks_SQC/MI100/timestamps.csv | 6 +++--- .../ipblocks_SQC/MI200/perfmon/pmc_perf_0.txt | 5 +++++ .../ipblocks_SQC/MI200/perfmon/pmc_perf_1.txt | 5 +++++ .../ipblocks_SQC/MI200/perfmon/pmc_perf_2.txt | 5 +++++ .../ipblocks_SQC/MI200/perfmon/pmc_perf_3.txt | 5 +++++ .../ipblocks_SQC/MI200/perfmon/timestamps.txt | 5 +++++ tests/workloads/ipblocks_SQC/MI200/pmc_perf.csv | 4 ++++ tests/workloads/ipblocks_SQC/MI200/roofline.csv | 5 +++++ tests/workloads/ipblocks_SQC/MI200/sysinfo.csv | 2 ++ .../workloads/ipblocks_SQC/MI200/timestamps.csv | 4 ++++ .../ipblocks_SQ_CPC/MI100/SQ_IFETCH_LEVEL.csv | 6 +++--- .../ipblocks_SQ_CPC/MI100/SQ_INST_LEVEL_LDS.csv | 6 +++--- .../MI100/SQ_INST_LEVEL_SMEM.csv | 6 +++--- .../MI100/SQ_INST_LEVEL_VMEM.csv | 6 +++--- .../ipblocks_SQ_CPC/MI100/SQ_LEVEL_WAVES.csv | 6 +++--- .../ipblocks_SQ_CPC/MI100/pmc_dispatch_info.csv | 4 ++++ .../ipblocks_SQ_CPC/MI100/pmc_perf.csv | 8 ++++---- .../workloads/ipblocks_SQ_CPC/MI100/sysinfo.csv | 2 +- .../ipblocks_SQ_CPC/MI100/timestamps.csv | 6 +++--- .../ipblocks_SQ_CPC/MI200/SQ_IFETCH_LEVEL.csv | 4 ++++ .../ipblocks_SQ_CPC/MI200/SQ_INST_LEVEL_LDS.csv | 4 ++++ .../MI200/SQ_INST_LEVEL_SMEM.csv | 4 ++++ .../MI200/SQ_INST_LEVEL_VMEM.csv | 4 ++++ .../ipblocks_SQ_CPC/MI200/SQ_LEVEL_WAVES.csv | 4 ++++ .../MI200/perfmon/SQ_IFETCH_LEVEL.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_LDS.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_SMEM.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_VMEM.txt | 5 +++++ .../MI200/perfmon/SQ_LEVEL_WAVES.txt | 5 +++++ .../MI200/perfmon/pmc_perf_0.txt | 5 +++++ .../MI200/perfmon/pmc_perf_1.txt | 5 +++++ .../MI200/perfmon/pmc_perf_10.txt | 5 +++++ .../MI200/perfmon/pmc_perf_11.txt | 5 +++++ .../MI200/perfmon/pmc_perf_12.txt | 5 +++++ .../MI200/perfmon/pmc_perf_2.txt | 5 +++++ .../MI200/perfmon/pmc_perf_3.txt | 5 +++++ .../MI200/perfmon/pmc_perf_4.txt | 5 +++++ .../MI200/perfmon/pmc_perf_5.txt | 5 +++++ .../MI200/perfmon/pmc_perf_6.txt | 5 +++++ .../MI200/perfmon/pmc_perf_7.txt | 5 +++++ .../MI200/perfmon/pmc_perf_8.txt | 5 +++++ .../MI200/perfmon/pmc_perf_9.txt | 5 +++++ .../MI200/perfmon/timestamps.txt | 5 +++++ .../ipblocks_SQ_CPC/MI200/pmc_perf.csv | 4 ++++ .../ipblocks_SQ_CPC/MI200/roofline.csv | 5 +++++ .../workloads/ipblocks_SQ_CPC/MI200/sysinfo.csv | 2 ++ .../ipblocks_SQ_CPC/MI200/timestamps.csv | 4 ++++ .../ipblocks_SQ_SPI/MI100/SQ_IFETCH_LEVEL.csv | 6 +++--- .../ipblocks_SQ_SPI/MI100/SQ_INST_LEVEL_LDS.csv | 6 +++--- .../MI100/SQ_INST_LEVEL_SMEM.csv | 6 +++--- .../MI100/SQ_INST_LEVEL_VMEM.csv | 6 +++--- .../ipblocks_SQ_SPI/MI100/SQ_LEVEL_WAVES.csv | 6 +++--- .../ipblocks_SQ_SPI/MI100/pmc_dispatch_info.csv | 4 ++++ .../ipblocks_SQ_SPI/MI100/pmc_perf.csv | 8 ++++---- .../workloads/ipblocks_SQ_SPI/MI100/sysinfo.csv | 2 +- .../ipblocks_SQ_SPI/MI100/timestamps.csv | 6 +++--- .../ipblocks_SQ_SPI/MI200/SQ_IFETCH_LEVEL.csv | 4 ++++ .../ipblocks_SQ_SPI/MI200/SQ_INST_LEVEL_LDS.csv | 4 ++++ .../MI200/SQ_INST_LEVEL_SMEM.csv | 4 ++++ .../MI200/SQ_INST_LEVEL_VMEM.csv | 4 ++++ .../ipblocks_SQ_SPI/MI200/SQ_LEVEL_WAVES.csv | 4 ++++ .../MI200/perfmon/SQ_IFETCH_LEVEL.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_LDS.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_SMEM.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_VMEM.txt | 5 +++++ .../MI200/perfmon/SQ_LEVEL_WAVES.txt | 5 +++++ .../MI200/perfmon/pmc_perf_0.txt | 5 +++++ .../MI200/perfmon/pmc_perf_1.txt | 5 +++++ .../MI200/perfmon/pmc_perf_10.txt | 5 +++++ .../MI200/perfmon/pmc_perf_11.txt | 5 +++++ .../MI200/perfmon/pmc_perf_12.txt | 5 +++++ .../MI200/perfmon/pmc_perf_2.txt | 5 +++++ .../MI200/perfmon/pmc_perf_3.txt | 5 +++++ .../MI200/perfmon/pmc_perf_4.txt | 5 +++++ .../MI200/perfmon/pmc_perf_5.txt | 5 +++++ .../MI200/perfmon/pmc_perf_6.txt | 5 +++++ .../MI200/perfmon/pmc_perf_7.txt | 5 +++++ .../MI200/perfmon/pmc_perf_8.txt | 5 +++++ .../MI200/perfmon/pmc_perf_9.txt | 5 +++++ .../MI200/perfmon/timestamps.txt | 5 +++++ .../ipblocks_SQ_SPI/MI200/pmc_perf.csv | 4 ++++ .../ipblocks_SQ_SPI/MI200/roofline.csv | 5 +++++ .../workloads/ipblocks_SQ_SPI/MI200/sysinfo.csv | 2 ++ .../ipblocks_SQ_SPI/MI200/timestamps.csv | 4 ++++ .../MI100/SQ_IFETCH_LEVEL.csv | 6 +++--- .../MI100/SQ_INST_LEVEL_LDS.csv | 6 +++--- .../MI100/SQ_INST_LEVEL_SMEM.csv | 6 +++--- .../MI100/SQ_INST_LEVEL_VMEM.csv | 6 +++--- .../MI100/SQ_LEVEL_WAVES.csv | 6 +++--- .../MI100/perfmon/pmc_perf_0.txt | 2 +- .../MI100/pmc_dispatch_info.csv | 4 ++++ .../MI100/pmc_perf.csv | 8 ++++---- .../MI100/sysinfo.csv | 2 +- .../MI100/timestamps.csv | 6 +++--- .../MI200/SQ_IFETCH_LEVEL.csv | 4 ++++ .../MI200/SQ_INST_LEVEL_LDS.csv | 4 ++++ .../MI200/SQ_INST_LEVEL_SMEM.csv | 4 ++++ .../MI200/SQ_INST_LEVEL_VMEM.csv | 4 ++++ .../MI200/SQ_LEVEL_WAVES.csv | 4 ++++ .../MI200/perfmon/SQ_IFETCH_LEVEL.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_LDS.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_SMEM.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_VMEM.txt | 5 +++++ .../MI200/perfmon/SQ_LEVEL_WAVES.txt | 5 +++++ .../MI200/perfmon/pmc_perf_0.txt | 5 +++++ .../MI200/perfmon/pmc_perf_1.txt | 5 +++++ .../MI200/perfmon/pmc_perf_10.txt | 5 +++++ .../MI200/perfmon/pmc_perf_11.txt | 5 +++++ .../MI200/perfmon/pmc_perf_12.txt | 5 +++++ .../MI200/perfmon/pmc_perf_2.txt | 5 +++++ .../MI200/perfmon/pmc_perf_3.txt | 5 +++++ .../MI200/perfmon/pmc_perf_4.txt | 5 +++++ .../MI200/perfmon/pmc_perf_5.txt | 5 +++++ .../MI200/perfmon/pmc_perf_6.txt | 5 +++++ .../MI200/perfmon/pmc_perf_7.txt | 5 +++++ .../MI200/perfmon/pmc_perf_8.txt | 5 +++++ .../MI200/perfmon/pmc_perf_9.txt | 5 +++++ .../MI200/perfmon/timestamps.txt | 5 +++++ .../MI200/pmc_perf.csv | 4 ++++ .../MI200/roofline.csv | 5 +++++ .../MI200/sysinfo.csv | 2 ++ .../MI200/timestamps.csv | 4 ++++ .../MI100/SQ_IFETCH_LEVEL.csv | 6 +++--- .../MI100/SQ_INST_LEVEL_LDS.csv | 6 +++--- .../MI100/SQ_INST_LEVEL_SMEM.csv | 6 +++--- .../MI100/SQ_INST_LEVEL_VMEM.csv | 6 +++--- .../MI100/SQ_LEVEL_WAVES.csv | 6 +++--- .../MI100/perfmon/pmc_perf_0.txt | 2 +- .../MI100/pmc_dispatch_info.csv | 4 ++++ .../ipblocks_SQ_SQC_TCP_CPC/MI100/pmc_perf.csv | 8 ++++---- .../ipblocks_SQ_SQC_TCP_CPC/MI100/sysinfo.csv | 2 +- .../MI100/timestamps.csv | 6 +++--- .../MI200/SQ_IFETCH_LEVEL.csv | 4 ++++ .../MI200/SQ_INST_LEVEL_LDS.csv | 4 ++++ .../MI200/SQ_INST_LEVEL_SMEM.csv | 4 ++++ .../MI200/SQ_INST_LEVEL_VMEM.csv | 4 ++++ .../MI200/SQ_LEVEL_WAVES.csv | 4 ++++ .../MI200/perfmon/SQ_IFETCH_LEVEL.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_LDS.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_SMEM.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_VMEM.txt | 5 +++++ .../MI200/perfmon/SQ_LEVEL_WAVES.txt | 5 +++++ .../MI200/perfmon/pmc_perf_0.txt | 5 +++++ .../MI200/perfmon/pmc_perf_1.txt | 5 +++++ .../MI200/perfmon/pmc_perf_10.txt | 5 +++++ .../MI200/perfmon/pmc_perf_11.txt | 5 +++++ .../MI200/perfmon/pmc_perf_12.txt | 5 +++++ .../MI200/perfmon/pmc_perf_2.txt | 5 +++++ .../MI200/perfmon/pmc_perf_3.txt | 5 +++++ .../MI200/perfmon/pmc_perf_4.txt | 5 +++++ .../MI200/perfmon/pmc_perf_5.txt | 5 +++++ .../MI200/perfmon/pmc_perf_6.txt | 5 +++++ .../MI200/perfmon/pmc_perf_7.txt | 5 +++++ .../MI200/perfmon/pmc_perf_8.txt | 5 +++++ .../MI200/perfmon/pmc_perf_9.txt | 5 +++++ .../MI200/perfmon/timestamps.txt | 5 +++++ .../ipblocks_SQ_SQC_TCP_CPC/MI200/pmc_perf.csv | 4 ++++ .../ipblocks_SQ_SQC_TCP_CPC/MI200/roofline.csv | 5 +++++ .../ipblocks_SQ_SQC_TCP_CPC/MI200/sysinfo.csv | 2 ++ .../MI200/timestamps.csv | 4 ++++ .../ipblocks_SQ_TA/MI100/SQ_IFETCH_LEVEL.csv | 6 +++--- .../ipblocks_SQ_TA/MI100/SQ_INST_LEVEL_LDS.csv | 6 +++--- .../ipblocks_SQ_TA/MI100/SQ_INST_LEVEL_SMEM.csv | 6 +++--- .../ipblocks_SQ_TA/MI100/SQ_INST_LEVEL_VMEM.csv | 6 +++--- .../ipblocks_SQ_TA/MI100/SQ_LEVEL_WAVES.csv | 6 +++--- .../ipblocks_SQ_TA/MI100/pmc_dispatch_info.csv | 4 ++++ .../workloads/ipblocks_SQ_TA/MI100/pmc_perf.csv | 8 ++++---- .../workloads/ipblocks_SQ_TA/MI100/sysinfo.csv | 2 +- .../ipblocks_SQ_TA/MI100/timestamps.csv | 6 +++--- .../ipblocks_SQ_TA/MI200/SQ_IFETCH_LEVEL.csv | 4 ++++ .../ipblocks_SQ_TA/MI200/SQ_INST_LEVEL_LDS.csv | 4 ++++ .../ipblocks_SQ_TA/MI200/SQ_INST_LEVEL_SMEM.csv | 4 ++++ .../ipblocks_SQ_TA/MI200/SQ_INST_LEVEL_VMEM.csv | 4 ++++ .../ipblocks_SQ_TA/MI200/SQ_LEVEL_WAVES.csv | 4 ++++ .../MI200/perfmon/SQ_IFETCH_LEVEL.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_LDS.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_SMEM.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_VMEM.txt | 5 +++++ .../MI200/perfmon/SQ_LEVEL_WAVES.txt | 5 +++++ .../ipblocks_SQ_TA/MI200/perfmon/pmc_perf_0.txt | 5 +++++ .../ipblocks_SQ_TA/MI200/perfmon/pmc_perf_1.txt | 5 +++++ .../MI200/perfmon/pmc_perf_10.txt | 5 +++++ .../MI200/perfmon/pmc_perf_11.txt | 5 +++++ .../MI200/perfmon/pmc_perf_12.txt | 5 +++++ .../ipblocks_SQ_TA/MI200/perfmon/pmc_perf_2.txt | 5 +++++ .../ipblocks_SQ_TA/MI200/perfmon/pmc_perf_3.txt | 5 +++++ .../ipblocks_SQ_TA/MI200/perfmon/pmc_perf_4.txt | 5 +++++ .../ipblocks_SQ_TA/MI200/perfmon/pmc_perf_5.txt | 5 +++++ .../ipblocks_SQ_TA/MI200/perfmon/pmc_perf_6.txt | 5 +++++ .../ipblocks_SQ_TA/MI200/perfmon/pmc_perf_7.txt | 5 +++++ .../ipblocks_SQ_TA/MI200/perfmon/pmc_perf_8.txt | 5 +++++ .../ipblocks_SQ_TA/MI200/perfmon/pmc_perf_9.txt | 5 +++++ .../ipblocks_SQ_TA/MI200/perfmon/timestamps.txt | 5 +++++ .../workloads/ipblocks_SQ_TA/MI200/pmc_perf.csv | 4 ++++ .../workloads/ipblocks_SQ_TA/MI200/roofline.csv | 5 +++++ .../workloads/ipblocks_SQ_TA/MI200/sysinfo.csv | 2 ++ .../ipblocks_SQ_TA/MI200/timestamps.csv | 4 ++++ .../ipblocks_TA/MI100/pmc_dispatch_info.csv | 4 ++++ tests/workloads/ipblocks_TA/MI100/pmc_perf.csv | 8 ++++---- tests/workloads/ipblocks_TA/MI100/sysinfo.csv | 2 +- .../workloads/ipblocks_TA/MI100/timestamps.csv | 6 +++--- .../ipblocks_TA/MI200/perfmon/pmc_perf_0.txt | 5 +++++ .../ipblocks_TA/MI200/perfmon/pmc_perf_1.txt | 5 +++++ .../ipblocks_TA/MI200/perfmon/pmc_perf_2.txt | 5 +++++ .../ipblocks_TA/MI200/perfmon/pmc_perf_3.txt | 5 +++++ .../ipblocks_TA/MI200/perfmon/pmc_perf_4.txt | 5 +++++ .../ipblocks_TA/MI200/perfmon/pmc_perf_5.txt | 5 +++++ .../ipblocks_TA/MI200/perfmon/pmc_perf_6.txt | 5 +++++ .../ipblocks_TA/MI200/perfmon/pmc_perf_7.txt | 5 +++++ .../ipblocks_TA/MI200/perfmon/timestamps.txt | 5 +++++ tests/workloads/ipblocks_TA/MI200/pmc_perf.csv | 4 ++++ tests/workloads/ipblocks_TA/MI200/roofline.csv | 5 +++++ tests/workloads/ipblocks_TA/MI200/sysinfo.csv | 2 ++ .../workloads/ipblocks_TA/MI200/timestamps.csv | 4 ++++ .../ipblocks_TCC/MI100/pmc_dispatch_info.csv | 4 ++++ tests/workloads/ipblocks_TCC/MI100/pmc_perf.csv | 8 ++++---- tests/workloads/ipblocks_TCC/MI100/sysinfo.csv | 2 +- .../workloads/ipblocks_TCC/MI100/timestamps.csv | 6 +++--- .../ipblocks_TCC/MI200/perfmon/pmc_perf_0.txt | 5 +++++ .../ipblocks_TCC/MI200/perfmon/pmc_perf_1.txt | 5 +++++ .../ipblocks_TCC/MI200/perfmon/pmc_perf_2.txt | 5 +++++ .../ipblocks_TCC/MI200/perfmon/pmc_perf_3.txt | 5 +++++ .../ipblocks_TCC/MI200/perfmon/pmc_perf_4.txt | 5 +++++ .../ipblocks_TCC/MI200/perfmon/pmc_perf_5.txt | 5 +++++ .../ipblocks_TCC/MI200/perfmon/pmc_perf_6.txt | 5 +++++ .../ipblocks_TCC/MI200/perfmon/pmc_perf_7.txt | 5 +++++ .../ipblocks_TCC/MI200/perfmon/pmc_perf_8.txt | 5 +++++ .../ipblocks_TCC/MI200/perfmon/timestamps.txt | 5 +++++ tests/workloads/ipblocks_TCC/MI200/pmc_perf.csv | 4 ++++ tests/workloads/ipblocks_TCC/MI200/roofline.csv | 5 +++++ tests/workloads/ipblocks_TCC/MI200/sysinfo.csv | 2 ++ .../workloads/ipblocks_TCC/MI200/timestamps.csv | 4 ++++ .../ipblocks_TCP/MI100/pmc_dispatch_info.csv | 4 ++++ tests/workloads/ipblocks_TCP/MI100/pmc_perf.csv | 8 ++++---- tests/workloads/ipblocks_TCP/MI100/sysinfo.csv | 2 +- .../workloads/ipblocks_TCP/MI100/timestamps.csv | 6 +++--- .../ipblocks_TCP/MI200/perfmon/pmc_perf_0.txt | 5 +++++ .../ipblocks_TCP/MI200/perfmon/pmc_perf_1.txt | 5 +++++ .../ipblocks_TCP/MI200/perfmon/pmc_perf_2.txt | 5 +++++ .../ipblocks_TCP/MI200/perfmon/pmc_perf_3.txt | 5 +++++ .../ipblocks_TCP/MI200/perfmon/pmc_perf_4.txt | 5 +++++ .../ipblocks_TCP/MI200/perfmon/pmc_perf_5.txt | 5 +++++ .../ipblocks_TCP/MI200/perfmon/pmc_perf_6.txt | 5 +++++ .../ipblocks_TCP/MI200/perfmon/pmc_perf_7.txt | 5 +++++ .../ipblocks_TCP/MI200/perfmon/pmc_perf_8.txt | 5 +++++ .../ipblocks_TCP/MI200/perfmon/pmc_perf_9.txt | 5 +++++ .../ipblocks_TCP/MI200/perfmon/timestamps.txt | 5 +++++ tests/workloads/ipblocks_TCP/MI200/pmc_perf.csv | 4 ++++ tests/workloads/ipblocks_TCP/MI200/roofline.csv | 5 +++++ tests/workloads/ipblocks_TCP/MI200/sysinfo.csv | 2 ++ .../workloads/ipblocks_TCP/MI200/timestamps.csv | 4 ++++ .../ipblocks_TD/MI100/pmc_dispatch_info.csv | 4 ++++ tests/workloads/ipblocks_TD/MI100/pmc_perf.csv | 8 ++++---- tests/workloads/ipblocks_TD/MI100/sysinfo.csv | 2 +- .../workloads/ipblocks_TD/MI100/timestamps.csv | 6 +++--- .../ipblocks_TD/MI200/perfmon/pmc_perf_0.txt | 5 +++++ .../ipblocks_TD/MI200/perfmon/pmc_perf_1.txt | 5 +++++ .../ipblocks_TD/MI200/perfmon/pmc_perf_2.txt | 5 +++++ .../ipblocks_TD/MI200/perfmon/pmc_perf_3.txt | 5 +++++ .../ipblocks_TD/MI200/perfmon/timestamps.txt | 5 +++++ tests/workloads/ipblocks_TD/MI200/pmc_perf.csv | 4 ++++ tests/workloads/ipblocks_TD/MI200/roofline.csv | 5 +++++ tests/workloads/ipblocks_TD/MI200/sysinfo.csv | 2 ++ .../workloads/ipblocks_TD/MI200/timestamps.csv | 4 ++++ .../join_type_grid/MI100/SQ_IFETCH_LEVEL.csv | 6 +++--- .../join_type_grid/MI100/SQ_INST_LEVEL_LDS.csv | 6 +++--- .../join_type_grid/MI100/SQ_INST_LEVEL_SMEM.csv | 6 +++--- .../join_type_grid/MI100/SQ_INST_LEVEL_VMEM.csv | 6 +++--- .../join_type_grid/MI100/SQ_LEVEL_WAVES.csv | 6 +++--- .../join_type_grid/MI100/pmc_dispatch_info.csv | 4 ++++ .../workloads/join_type_grid/MI100/pmc_perf.csv | 8 ++++---- .../workloads/join_type_grid/MI100/sysinfo.csv | 2 +- .../join_type_grid/MI100/timestamps.csv | 6 +++--- .../join_type_grid/MI200/SQ_IFETCH_LEVEL.csv | 4 ++++ .../join_type_grid/MI200/SQ_INST_LEVEL_LDS.csv | 4 ++++ .../join_type_grid/MI200/SQ_INST_LEVEL_SMEM.csv | 4 ++++ .../join_type_grid/MI200/SQ_INST_LEVEL_VMEM.csv | 4 ++++ .../join_type_grid/MI200/SQ_LEVEL_WAVES.csv | 4 ++++ .../MI200/perfmon/SQ_IFETCH_LEVEL.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_LDS.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_SMEM.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_VMEM.txt | 5 +++++ .../MI200/perfmon/SQ_LEVEL_WAVES.txt | 5 +++++ .../join_type_grid/MI200/perfmon/pmc_perf_0.txt | 5 +++++ .../join_type_grid/MI200/perfmon/pmc_perf_1.txt | 5 +++++ .../MI200/perfmon/pmc_perf_10.txt | 5 +++++ .../MI200/perfmon/pmc_perf_11.txt | 5 +++++ .../MI200/perfmon/pmc_perf_12.txt | 5 +++++ .../MI200/perfmon/pmc_perf_13.txt | 5 +++++ .../MI200/perfmon/pmc_perf_14.txt | 5 +++++ .../MI200/perfmon/pmc_perf_15.txt | 5 +++++ .../MI200/perfmon/pmc_perf_16.txt | 5 +++++ .../MI200/perfmon/pmc_perf_17.txt | 5 +++++ .../MI200/perfmon/pmc_perf_18.txt | 5 +++++ .../join_type_grid/MI200/perfmon/pmc_perf_2.txt | 5 +++++ .../join_type_grid/MI200/perfmon/pmc_perf_3.txt | 5 +++++ .../join_type_grid/MI200/perfmon/pmc_perf_4.txt | 5 +++++ .../join_type_grid/MI200/perfmon/pmc_perf_5.txt | 5 +++++ .../join_type_grid/MI200/perfmon/pmc_perf_6.txt | 5 +++++ .../join_type_grid/MI200/perfmon/pmc_perf_7.txt | 5 +++++ .../join_type_grid/MI200/perfmon/pmc_perf_8.txt | 5 +++++ .../join_type_grid/MI200/perfmon/pmc_perf_9.txt | 5 +++++ .../join_type_grid/MI200/perfmon/timestamps.txt | 5 +++++ .../workloads/join_type_grid/MI200/pmc_perf.csv | 4 ++++ .../workloads/join_type_grid/MI200/roofline.csv | 5 +++++ .../workloads/join_type_grid/MI200/sysinfo.csv | 2 ++ .../join_type_grid/MI200/timestamps.csv | 4 ++++ .../join_type_kernel/MI100/SQ_IFETCH_LEVEL.csv | 6 +++--- .../MI100/SQ_INST_LEVEL_LDS.csv | 6 +++--- .../MI100/SQ_INST_LEVEL_SMEM.csv | 6 +++--- .../MI100/SQ_INST_LEVEL_VMEM.csv | 6 +++--- .../join_type_kernel/MI100/SQ_LEVEL_WAVES.csv | 6 +++--- .../MI100/pmc_dispatch_info.csv | 4 ++++ .../join_type_kernel/MI100/pmc_perf.csv | 8 ++++---- .../join_type_kernel/MI100/sysinfo.csv | 2 +- .../join_type_kernel/MI100/timestamps.csv | 6 +++--- .../join_type_kernel/MI200/SQ_IFETCH_LEVEL.csv | 4 ++++ .../MI200/SQ_INST_LEVEL_LDS.csv | 4 ++++ .../MI200/SQ_INST_LEVEL_SMEM.csv | 4 ++++ .../MI200/SQ_INST_LEVEL_VMEM.csv | 4 ++++ .../join_type_kernel/MI200/SQ_LEVEL_WAVES.csv | 4 ++++ .../MI200/perfmon/SQ_IFETCH_LEVEL.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_LDS.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_SMEM.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_VMEM.txt | 5 +++++ .../MI200/perfmon/SQ_LEVEL_WAVES.txt | 5 +++++ .../MI200/perfmon/pmc_perf_0.txt | 5 +++++ .../MI200/perfmon/pmc_perf_1.txt | 5 +++++ .../MI200/perfmon/pmc_perf_10.txt | 5 +++++ .../MI200/perfmon/pmc_perf_11.txt | 5 +++++ .../MI200/perfmon/pmc_perf_12.txt | 5 +++++ .../MI200/perfmon/pmc_perf_13.txt | 5 +++++ .../MI200/perfmon/pmc_perf_14.txt | 5 +++++ .../MI200/perfmon/pmc_perf_15.txt | 5 +++++ .../MI200/perfmon/pmc_perf_16.txt | 5 +++++ .../MI200/perfmon/pmc_perf_17.txt | 5 +++++ .../MI200/perfmon/pmc_perf_18.txt | 5 +++++ .../MI200/perfmon/pmc_perf_2.txt | 5 +++++ .../MI200/perfmon/pmc_perf_3.txt | 5 +++++ .../MI200/perfmon/pmc_perf_4.txt | 5 +++++ .../MI200/perfmon/pmc_perf_5.txt | 5 +++++ .../MI200/perfmon/pmc_perf_6.txt | 5 +++++ .../MI200/perfmon/pmc_perf_7.txt | 5 +++++ .../MI200/perfmon/pmc_perf_8.txt | 5 +++++ .../MI200/perfmon/pmc_perf_9.txt | 5 +++++ .../MI200/perfmon/timestamps.txt | 5 +++++ .../join_type_kernel/MI200/pmc_perf.csv | 4 ++++ .../join_type_kernel/MI200/roofline.csv | 5 +++++ .../join_type_kernel/MI200/sysinfo.csv | 2 ++ .../join_type_kernel/MI200/timestamps.csv | 4 ++++ .../{pmc_perf_16.csv => SQ_IFETCH_LEVEL.csv} | 0 .../kernel/MI100/perfmon/SQ_IFETCH_LEVEL.txt | 2 +- .../kernel/MI100/perfmon/pmc_perf_16.txt | 2 +- .../workloads/kernel/MI200/SQ_IFETCH_LEVEL.csv | 1 + .../kernel/MI200/perfmon/SQ_IFETCH_LEVEL.txt | 5 +++++ .../kernel/MI200/perfmon/SQ_INST_LEVEL_LDS.txt | 5 +++++ .../kernel/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt | 5 +++++ .../kernel/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt | 5 +++++ .../kernel/MI200/perfmon/SQ_LEVEL_WAVES.txt | 5 +++++ .../kernel/MI200/perfmon/pmc_perf_0.txt | 5 +++++ .../kernel/MI200/perfmon/pmc_perf_1.txt | 5 +++++ .../kernel/MI200/perfmon/pmc_perf_10.txt | 5 +++++ .../kernel/MI200/perfmon/pmc_perf_11.txt | 5 +++++ .../kernel/MI200/perfmon/pmc_perf_12.txt | 5 +++++ .../kernel/MI200/perfmon/pmc_perf_13.txt | 5 +++++ .../kernel/MI200/perfmon/pmc_perf_14.txt | 5 +++++ .../kernel/MI200/perfmon/pmc_perf_15.txt | 5 +++++ .../kernel/MI200/perfmon/pmc_perf_16.txt | 5 +++++ .../kernel/MI200/perfmon/pmc_perf_17.txt | 5 +++++ .../kernel/MI200/perfmon/pmc_perf_18.txt | 5 +++++ .../kernel/MI200/perfmon/pmc_perf_2.txt | 5 +++++ .../kernel/MI200/perfmon/pmc_perf_3.txt | 5 +++++ .../kernel/MI200/perfmon/pmc_perf_4.txt | 5 +++++ .../kernel/MI200/perfmon/pmc_perf_5.txt | 5 +++++ .../kernel/MI200/perfmon/pmc_perf_6.txt | 5 +++++ .../kernel/MI200/perfmon/pmc_perf_7.txt | 5 +++++ .../kernel/MI200/perfmon/pmc_perf_8.txt | 5 +++++ .../kernel/MI200/perfmon/pmc_perf_9.txt | 5 +++++ .../kernel/MI200/perfmon/timestamps.txt | 5 +++++ .../workloads/kernel_inv_int/MI100/sysinfo.csv | 2 +- .../kernel_inv_int/MI200/SQ_IFETCH_LEVEL.csv | 1 + .../kernel_inv_int/MI200/SQ_INST_LEVEL_LDS.csv | 1 + .../kernel_inv_int/MI200/SQ_INST_LEVEL_SMEM.csv | 1 + .../kernel_inv_int/MI200/SQ_INST_LEVEL_VMEM.csv | 1 + .../kernel_inv_int/MI200/SQ_LEVEL_WAVES.csv | 1 + .../MI200/perfmon/SQ_IFETCH_LEVEL.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_LDS.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_SMEM.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_VMEM.txt | 5 +++++ .../MI200/perfmon/SQ_LEVEL_WAVES.txt | 5 +++++ .../kernel_inv_int/MI200/perfmon/pmc_perf_0.txt | 5 +++++ .../kernel_inv_int/MI200/perfmon/pmc_perf_1.txt | 5 +++++ .../MI200/perfmon/pmc_perf_10.txt | 5 +++++ .../MI200/perfmon/pmc_perf_11.txt | 5 +++++ .../MI200/perfmon/pmc_perf_12.txt | 5 +++++ .../MI200/perfmon/pmc_perf_13.txt | 5 +++++ .../MI200/perfmon/pmc_perf_14.txt | 5 +++++ .../MI200/perfmon/pmc_perf_15.txt | 5 +++++ .../MI200/perfmon/pmc_perf_16.txt | 5 +++++ .../MI200/perfmon/pmc_perf_17.txt | 5 +++++ .../MI200/perfmon/pmc_perf_18.txt | 5 +++++ .../kernel_inv_int/MI200/perfmon/pmc_perf_2.txt | 5 +++++ .../kernel_inv_int/MI200/perfmon/pmc_perf_3.txt | 5 +++++ .../kernel_inv_int/MI200/perfmon/pmc_perf_4.txt | 5 +++++ .../kernel_inv_int/MI200/perfmon/pmc_perf_5.txt | 5 +++++ .../kernel_inv_int/MI200/perfmon/pmc_perf_6.txt | 5 +++++ .../kernel_inv_int/MI200/perfmon/pmc_perf_7.txt | 5 +++++ .../kernel_inv_int/MI200/perfmon/pmc_perf_8.txt | 5 +++++ .../kernel_inv_int/MI200/perfmon/pmc_perf_9.txt | 5 +++++ .../kernel_inv_int/MI200/perfmon/timestamps.txt | 5 +++++ .../kernel_inv_int/MI200/pmc_perf_0.csv | 1 + .../kernel_inv_int/MI200/pmc_perf_1.csv | 1 + .../kernel_inv_int/MI200/pmc_perf_10.csv | 1 + .../kernel_inv_int/MI200/pmc_perf_11.csv | 1 + .../kernel_inv_int/MI200/pmc_perf_12.csv | 1 + .../kernel_inv_int/MI200/pmc_perf_13.csv | 1 + .../kernel_inv_int/MI200/pmc_perf_14.csv | 1 + .../kernel_inv_int/MI200/pmc_perf_15.csv | 1 + .../kernel_inv_int/MI200/pmc_perf_16.csv | 1 + .../kernel_inv_int/MI200/pmc_perf_17.csv | 1 + .../kernel_inv_int/MI200/pmc_perf_18.csv | 1 + .../kernel_inv_int/MI200/pmc_perf_2.csv | 1 + .../kernel_inv_int/MI200/pmc_perf_3.csv | 1 + .../kernel_inv_int/MI200/pmc_perf_4.csv | 1 + .../kernel_inv_int/MI200/pmc_perf_5.csv | 1 + .../kernel_inv_int/MI200/pmc_perf_6.csv | 1 + .../kernel_inv_int/MI200/pmc_perf_7.csv | 1 + .../kernel_inv_int/MI200/pmc_perf_8.csv | 1 + .../kernel_inv_int/MI200/pmc_perf_9.csv | 1 + .../workloads/kernel_inv_int/MI200/sysinfo.csv | 2 ++ .../kernel_inv_int/MI200/timestamps.csv | 1 + .../workloads/kernel_inv_str/MI100/sysinfo.csv | 2 +- .../kernel_inv_str/MI200/SQ_IFETCH_LEVEL.csv | 1 + .../kernel_inv_str/MI200/SQ_INST_LEVEL_LDS.csv | 1 + .../kernel_inv_str/MI200/SQ_INST_LEVEL_SMEM.csv | 1 + .../kernel_inv_str/MI200/SQ_INST_LEVEL_VMEM.csv | 1 + .../kernel_inv_str/MI200/SQ_LEVEL_WAVES.csv | 1 + .../MI200/perfmon/SQ_IFETCH_LEVEL.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_LDS.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_SMEM.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_VMEM.txt | 5 +++++ .../MI200/perfmon/SQ_LEVEL_WAVES.txt | 5 +++++ .../kernel_inv_str/MI200/perfmon/pmc_perf_0.txt | 5 +++++ .../kernel_inv_str/MI200/perfmon/pmc_perf_1.txt | 5 +++++ .../MI200/perfmon/pmc_perf_10.txt | 5 +++++ .../MI200/perfmon/pmc_perf_11.txt | 5 +++++ .../MI200/perfmon/pmc_perf_12.txt | 5 +++++ .../MI200/perfmon/pmc_perf_13.txt | 5 +++++ .../MI200/perfmon/pmc_perf_14.txt | 5 +++++ .../MI200/perfmon/pmc_perf_15.txt | 5 +++++ .../MI200/perfmon/pmc_perf_16.txt | 5 +++++ .../MI200/perfmon/pmc_perf_17.txt | 5 +++++ .../MI200/perfmon/pmc_perf_18.txt | 5 +++++ .../kernel_inv_str/MI200/perfmon/pmc_perf_2.txt | 5 +++++ .../kernel_inv_str/MI200/perfmon/pmc_perf_3.txt | 5 +++++ .../kernel_inv_str/MI200/perfmon/pmc_perf_4.txt | 5 +++++ .../kernel_inv_str/MI200/perfmon/pmc_perf_5.txt | 5 +++++ .../kernel_inv_str/MI200/perfmon/pmc_perf_6.txt | 5 +++++ .../kernel_inv_str/MI200/perfmon/pmc_perf_7.txt | 5 +++++ .../kernel_inv_str/MI200/perfmon/pmc_perf_8.txt | 5 +++++ .../kernel_inv_str/MI200/perfmon/pmc_perf_9.txt | 5 +++++ .../kernel_inv_str/MI200/perfmon/timestamps.txt | 5 +++++ .../kernel_inv_str/MI200/pmc_perf_0.csv | 1 + .../kernel_inv_str/MI200/pmc_perf_1.csv | 1 + .../kernel_inv_str/MI200/pmc_perf_10.csv | 1 + .../kernel_inv_str/MI200/pmc_perf_11.csv | 1 + .../kernel_inv_str/MI200/pmc_perf_12.csv | 1 + .../kernel_inv_str/MI200/pmc_perf_13.csv | 1 + .../kernel_inv_str/MI200/pmc_perf_14.csv | 1 + .../kernel_inv_str/MI200/pmc_perf_15.csv | 1 + .../kernel_inv_str/MI200/pmc_perf_16.csv | 1 + .../kernel_inv_str/MI200/pmc_perf_17.csv | 1 + .../kernel_inv_str/MI200/pmc_perf_18.csv | 1 + .../kernel_inv_str/MI200/pmc_perf_2.csv | 1 + .../kernel_inv_str/MI200/pmc_perf_3.csv | 1 + .../kernel_inv_str/MI200/pmc_perf_4.csv | 1 + .../kernel_inv_str/MI200/pmc_perf_5.csv | 1 + .../kernel_inv_str/MI200/pmc_perf_6.csv | 1 + .../kernel_inv_str/MI200/pmc_perf_7.csv | 1 + .../kernel_inv_str/MI200/pmc_perf_8.csv | 1 + .../kernel_inv_str/MI200/pmc_perf_9.csv | 1 + .../workloads/kernel_inv_str/MI200/sysinfo.csv | 2 ++ .../kernel_inv_str/MI200/timestamps.csv | 1 + .../kernel_names/MI200/empirRoof_gpu-0_fp32.pdf | Bin 0 -> 13328 bytes .../MI200/empirRoof_gpu-0_int8_fp16.pdf | Bin 0 -> 13142 bytes .../kernel_names/MI200/kernelName_legend.pdf | Bin 0 -> 10637 bytes .../kernel_names/MI200/perfmon/pmc_perf_0.txt | 5 +++++ .../kernel_names/MI200/perfmon/pmc_perf_1.txt | 5 +++++ .../kernel_names/MI200/perfmon/pmc_perf_2.txt | 5 +++++ .../kernel_names/MI200/perfmon/timestamps.txt | 5 +++++ tests/workloads/kernel_names/MI200/pmc_perf.csv | 4 ++++ tests/workloads/kernel_names/MI200/roofline.csv | 5 +++++ tests/workloads/kernel_names/MI200/sysinfo.csv | 2 ++ .../workloads/kernel_names/MI200/timestamps.csv | 4 ++++ .../kernel_substr/MI100/SQ_IFETCH_LEVEL.csv | 6 +++--- .../kernel_substr/MI100/SQ_INST_LEVEL_LDS.csv | 6 +++--- .../kernel_substr/MI100/SQ_INST_LEVEL_SMEM.csv | 6 +++--- .../kernel_substr/MI100/SQ_INST_LEVEL_VMEM.csv | 6 +++--- .../kernel_substr/MI100/SQ_LEVEL_WAVES.csv | 6 +++--- .../kernel_substr/MI100/pmc_dispatch_info.csv | 4 ++++ .../workloads/kernel_substr/MI100/pmc_perf.csv | 8 ++++---- tests/workloads/kernel_substr/MI100/sysinfo.csv | 2 +- .../kernel_substr/MI100/timestamps.csv | 6 +++--- .../kernel_substr/MI200/SQ_IFETCH_LEVEL.csv | 4 ++++ .../kernel_substr/MI200/SQ_INST_LEVEL_LDS.csv | 4 ++++ .../kernel_substr/MI200/SQ_INST_LEVEL_SMEM.csv | 4 ++++ .../kernel_substr/MI200/SQ_INST_LEVEL_VMEM.csv | 4 ++++ .../kernel_substr/MI200/SQ_LEVEL_WAVES.csv | 4 ++++ .../MI200/perfmon/SQ_IFETCH_LEVEL.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_LDS.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_SMEM.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_VMEM.txt | 5 +++++ .../MI200/perfmon/SQ_LEVEL_WAVES.txt | 5 +++++ .../kernel_substr/MI200/perfmon/pmc_perf_0.txt | 5 +++++ .../kernel_substr/MI200/perfmon/pmc_perf_1.txt | 5 +++++ .../kernel_substr/MI200/perfmon/pmc_perf_10.txt | 5 +++++ .../kernel_substr/MI200/perfmon/pmc_perf_11.txt | 5 +++++ .../kernel_substr/MI200/perfmon/pmc_perf_12.txt | 5 +++++ .../kernel_substr/MI200/perfmon/pmc_perf_13.txt | 5 +++++ .../kernel_substr/MI200/perfmon/pmc_perf_14.txt | 5 +++++ .../kernel_substr/MI200/perfmon/pmc_perf_15.txt | 5 +++++ .../kernel_substr/MI200/perfmon/pmc_perf_16.txt | 5 +++++ .../kernel_substr/MI200/perfmon/pmc_perf_17.txt | 5 +++++ .../kernel_substr/MI200/perfmon/pmc_perf_18.txt | 5 +++++ .../kernel_substr/MI200/perfmon/pmc_perf_2.txt | 5 +++++ .../kernel_substr/MI200/perfmon/pmc_perf_3.txt | 5 +++++ .../kernel_substr/MI200/perfmon/pmc_perf_4.txt | 5 +++++ .../kernel_substr/MI200/perfmon/pmc_perf_5.txt | 5 +++++ .../kernel_substr/MI200/perfmon/pmc_perf_6.txt | 5 +++++ .../kernel_substr/MI200/perfmon/pmc_perf_7.txt | 5 +++++ .../kernel_substr/MI200/perfmon/pmc_perf_8.txt | 5 +++++ .../kernel_substr/MI200/perfmon/pmc_perf_9.txt | 5 +++++ .../kernel_substr/MI200/perfmon/timestamps.txt | 5 +++++ .../workloads/kernel_substr/MI200/pmc_perf.csv | 4 ++++ .../workloads/kernel_substr/MI200/roofline.csv | 5 +++++ tests/workloads/kernel_substr/MI200/sysinfo.csv | 2 ++ .../kernel_substr/MI200/timestamps.csv | 4 ++++ .../kernel_summaries/MI100/SQ_IFETCH_LEVEL.csv | 6 +++--- .../MI100/SQ_INST_LEVEL_LDS.csv | 6 +++--- .../MI100/SQ_INST_LEVEL_SMEM.csv | 6 +++--- .../MI100/SQ_INST_LEVEL_VMEM.csv | 6 +++--- .../kernel_summaries/MI100/SQ_LEVEL_WAVES.csv | 6 +++--- .../MI100/pmc_dispatch_info.csv | 4 ++++ .../kernel_summaries/MI100/pmc_perf.csv | 8 ++++---- .../kernel_summaries/MI100/sysinfo.csv | 2 +- .../kernel_summaries/MI100/timestamps.csv | 6 +++--- .../kernel_summaries/MI200/SQ_IFETCH_LEVEL.csv | 4 ++++ .../MI200/SQ_INST_LEVEL_LDS.csv | 4 ++++ .../MI200/SQ_INST_LEVEL_SMEM.csv | 4 ++++ .../MI200/SQ_INST_LEVEL_VMEM.csv | 4 ++++ .../kernel_summaries/MI200/SQ_LEVEL_WAVES.csv | 4 ++++ .../MI200/perfmon/SQ_IFETCH_LEVEL.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_LDS.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_SMEM.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_VMEM.txt | 5 +++++ .../MI200/perfmon/SQ_LEVEL_WAVES.txt | 5 +++++ .../MI200/perfmon/pmc_perf_0.txt | 5 +++++ .../MI200/perfmon/pmc_perf_1.txt | 5 +++++ .../MI200/perfmon/pmc_perf_10.txt | 5 +++++ .../MI200/perfmon/pmc_perf_11.txt | 5 +++++ .../MI200/perfmon/pmc_perf_12.txt | 5 +++++ .../MI200/perfmon/pmc_perf_13.txt | 5 +++++ .../MI200/perfmon/pmc_perf_14.txt | 5 +++++ .../MI200/perfmon/pmc_perf_15.txt | 5 +++++ .../MI200/perfmon/pmc_perf_16.txt | 5 +++++ .../MI200/perfmon/pmc_perf_17.txt | 5 +++++ .../MI200/perfmon/pmc_perf_18.txt | 5 +++++ .../MI200/perfmon/pmc_perf_2.txt | 5 +++++ .../MI200/perfmon/pmc_perf_3.txt | 5 +++++ .../MI200/perfmon/pmc_perf_4.txt | 5 +++++ .../MI200/perfmon/pmc_perf_5.txt | 5 +++++ .../MI200/perfmon/pmc_perf_6.txt | 5 +++++ .../MI200/perfmon/pmc_perf_7.txt | 5 +++++ .../MI200/perfmon/pmc_perf_8.txt | 5 +++++ .../MI200/perfmon/pmc_perf_9.txt | 5 +++++ .../MI200/perfmon/timestamps.txt | 5 +++++ .../kernel_summaries/MI200/pmc_perf.csv | 4 ++++ .../kernel_summaries/MI200/roofline.csv | 0 .../kernel_summaries/MI200/sysinfo.csv | 2 ++ .../kernel_summaries/MI200/timestamps.csv | 4 ++++ .../kernel_verbose_0/MI100/SQ_IFETCH_LEVEL.csv | 6 +++--- .../MI100/SQ_INST_LEVEL_LDS.csv | 6 +++--- .../MI100/SQ_INST_LEVEL_SMEM.csv | 6 +++--- .../MI100/SQ_INST_LEVEL_VMEM.csv | 6 +++--- .../kernel_verbose_0/MI100/SQ_LEVEL_WAVES.csv | 6 +++--- .../MI100/pmc_dispatch_info.csv | 4 ++++ .../kernel_verbose_0/MI100/pmc_perf.csv | 8 ++++---- .../kernel_verbose_0/MI100/sysinfo.csv | 2 +- .../kernel_verbose_0/MI100/timestamps.csv | 6 +++--- .../kernel_verbose_0/MI200/SQ_IFETCH_LEVEL.csv | 4 ++++ .../MI200/SQ_INST_LEVEL_LDS.csv | 4 ++++ .../MI200/SQ_INST_LEVEL_SMEM.csv | 4 ++++ .../MI200/SQ_INST_LEVEL_VMEM.csv | 4 ++++ .../kernel_verbose_0/MI200/SQ_LEVEL_WAVES.csv | 4 ++++ .../MI200/perfmon/SQ_IFETCH_LEVEL.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_LDS.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_SMEM.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_VMEM.txt | 5 +++++ .../MI200/perfmon/SQ_LEVEL_WAVES.txt | 5 +++++ .../MI200/perfmon/pmc_perf_0.txt | 5 +++++ .../MI200/perfmon/pmc_perf_1.txt | 5 +++++ .../MI200/perfmon/pmc_perf_10.txt | 5 +++++ .../MI200/perfmon/pmc_perf_11.txt | 5 +++++ .../MI200/perfmon/pmc_perf_12.txt | 5 +++++ .../MI200/perfmon/pmc_perf_13.txt | 5 +++++ .../MI200/perfmon/pmc_perf_14.txt | 5 +++++ .../MI200/perfmon/pmc_perf_15.txt | 5 +++++ .../MI200/perfmon/pmc_perf_16.txt | 5 +++++ .../MI200/perfmon/pmc_perf_17.txt | 5 +++++ .../MI200/perfmon/pmc_perf_18.txt | 5 +++++ .../MI200/perfmon/pmc_perf_2.txt | 5 +++++ .../MI200/perfmon/pmc_perf_3.txt | 5 +++++ .../MI200/perfmon/pmc_perf_4.txt | 5 +++++ .../MI200/perfmon/pmc_perf_5.txt | 5 +++++ .../MI200/perfmon/pmc_perf_6.txt | 5 +++++ .../MI200/perfmon/pmc_perf_7.txt | 5 +++++ .../MI200/perfmon/pmc_perf_8.txt | 5 +++++ .../MI200/perfmon/pmc_perf_9.txt | 5 +++++ .../MI200/perfmon/timestamps.txt | 5 +++++ .../kernel_verbose_0/MI200/pmc_perf.csv | 4 ++++ .../kernel_verbose_0/MI200/roofline.csv | 5 +++++ .../kernel_verbose_0/MI200/sysinfo.csv | 2 ++ .../kernel_verbose_0/MI200/timestamps.csv | 4 ++++ .../kernel_verbose_1/MI100/SQ_IFETCH_LEVEL.csv | 6 +++--- .../MI100/SQ_INST_LEVEL_LDS.csv | 6 +++--- .../MI100/SQ_INST_LEVEL_SMEM.csv | 6 +++--- .../MI100/SQ_INST_LEVEL_VMEM.csv | 6 +++--- .../kernel_verbose_1/MI100/SQ_LEVEL_WAVES.csv | 6 +++--- .../MI100/pmc_dispatch_info.csv | 4 ++++ .../kernel_verbose_1/MI100/pmc_perf.csv | 8 ++++---- .../kernel_verbose_1/MI100/sysinfo.csv | 2 +- .../kernel_verbose_1/MI100/timestamps.csv | 6 +++--- .../kernel_verbose_1/MI200/SQ_IFETCH_LEVEL.csv | 4 ++++ .../MI200/SQ_INST_LEVEL_LDS.csv | 4 ++++ .../MI200/SQ_INST_LEVEL_SMEM.csv | 4 ++++ .../MI200/SQ_INST_LEVEL_VMEM.csv | 4 ++++ .../kernel_verbose_1/MI200/SQ_LEVEL_WAVES.csv | 4 ++++ .../MI200/perfmon/SQ_IFETCH_LEVEL.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_LDS.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_SMEM.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_VMEM.txt | 5 +++++ .../MI200/perfmon/SQ_LEVEL_WAVES.txt | 5 +++++ .../MI200/perfmon/pmc_perf_0.txt | 5 +++++ .../MI200/perfmon/pmc_perf_1.txt | 5 +++++ .../MI200/perfmon/pmc_perf_10.txt | 5 +++++ .../MI200/perfmon/pmc_perf_11.txt | 5 +++++ .../MI200/perfmon/pmc_perf_12.txt | 5 +++++ .../MI200/perfmon/pmc_perf_13.txt | 5 +++++ .../MI200/perfmon/pmc_perf_14.txt | 5 +++++ .../MI200/perfmon/pmc_perf_15.txt | 5 +++++ .../MI200/perfmon/pmc_perf_16.txt | 5 +++++ .../MI200/perfmon/pmc_perf_17.txt | 5 +++++ .../MI200/perfmon/pmc_perf_18.txt | 5 +++++ .../MI200/perfmon/pmc_perf_2.txt | 5 +++++ .../MI200/perfmon/pmc_perf_3.txt | 5 +++++ .../MI200/perfmon/pmc_perf_4.txt | 5 +++++ .../MI200/perfmon/pmc_perf_5.txt | 5 +++++ .../MI200/perfmon/pmc_perf_6.txt | 5 +++++ .../MI200/perfmon/pmc_perf_7.txt | 5 +++++ .../MI200/perfmon/pmc_perf_8.txt | 5 +++++ .../MI200/perfmon/pmc_perf_9.txt | 5 +++++ .../MI200/perfmon/timestamps.txt | 5 +++++ .../kernel_verbose_1/MI200/pmc_perf.csv | 4 ++++ .../kernel_verbose_1/MI200/roofline.csv | 5 +++++ .../kernel_verbose_1/MI200/sysinfo.csv | 2 ++ .../kernel_verbose_1/MI200/timestamps.csv | 4 ++++ .../kernel_verbose_2/MI100/SQ_IFETCH_LEVEL.csv | 6 +++--- .../MI100/SQ_INST_LEVEL_LDS.csv | 6 +++--- .../MI100/SQ_INST_LEVEL_SMEM.csv | 6 +++--- .../MI100/SQ_INST_LEVEL_VMEM.csv | 6 +++--- .../kernel_verbose_2/MI100/SQ_LEVEL_WAVES.csv | 6 +++--- .../MI100/pmc_dispatch_info.csv | 4 ++++ .../kernel_verbose_2/MI100/pmc_perf.csv | 8 ++++---- .../kernel_verbose_2/MI100/sysinfo.csv | 2 +- .../kernel_verbose_2/MI100/timestamps.csv | 6 +++--- .../kernel_verbose_2/MI200/SQ_IFETCH_LEVEL.csv | 4 ++++ .../MI200/SQ_INST_LEVEL_LDS.csv | 4 ++++ .../MI200/SQ_INST_LEVEL_SMEM.csv | 4 ++++ .../MI200/SQ_INST_LEVEL_VMEM.csv | 4 ++++ .../kernel_verbose_2/MI200/SQ_LEVEL_WAVES.csv | 4 ++++ .../MI200/perfmon/SQ_IFETCH_LEVEL.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_LDS.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_SMEM.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_VMEM.txt | 5 +++++ .../MI200/perfmon/SQ_LEVEL_WAVES.txt | 5 +++++ .../MI200/perfmon/pmc_perf_0.txt | 5 +++++ .../MI200/perfmon/pmc_perf_1.txt | 5 +++++ .../MI200/perfmon/pmc_perf_10.txt | 5 +++++ .../MI200/perfmon/pmc_perf_11.txt | 5 +++++ .../MI200/perfmon/pmc_perf_12.txt | 5 +++++ .../MI200/perfmon/pmc_perf_13.txt | 5 +++++ .../MI200/perfmon/pmc_perf_14.txt | 5 +++++ .../MI200/perfmon/pmc_perf_15.txt | 5 +++++ .../MI200/perfmon/pmc_perf_16.txt | 5 +++++ .../MI200/perfmon/pmc_perf_17.txt | 5 +++++ .../MI200/perfmon/pmc_perf_18.txt | 5 +++++ .../MI200/perfmon/pmc_perf_2.txt | 5 +++++ .../MI200/perfmon/pmc_perf_3.txt | 5 +++++ .../MI200/perfmon/pmc_perf_4.txt | 5 +++++ .../MI200/perfmon/pmc_perf_5.txt | 5 +++++ .../MI200/perfmon/pmc_perf_6.txt | 5 +++++ .../MI200/perfmon/pmc_perf_7.txt | 5 +++++ .../MI200/perfmon/pmc_perf_8.txt | 5 +++++ .../MI200/perfmon/pmc_perf_9.txt | 5 +++++ .../MI200/perfmon/timestamps.txt | 5 +++++ .../kernel_verbose_2/MI200/pmc_perf.csv | 4 ++++ .../kernel_verbose_2/MI200/roofline.csv | 5 +++++ .../kernel_verbose_2/MI200/sysinfo.csv | 2 ++ .../kernel_verbose_2/MI200/timestamps.csv | 4 ++++ .../kernel_verbose_3/MI100/SQ_IFETCH_LEVEL.csv | 6 +++--- .../MI100/SQ_INST_LEVEL_LDS.csv | 6 +++--- .../MI100/SQ_INST_LEVEL_SMEM.csv | 6 +++--- .../MI100/SQ_INST_LEVEL_VMEM.csv | 6 +++--- .../kernel_verbose_3/MI100/SQ_LEVEL_WAVES.csv | 6 +++--- .../MI100/pmc_dispatch_info.csv | 4 ++++ .../kernel_verbose_3/MI100/pmc_perf.csv | 8 ++++---- .../kernel_verbose_3/MI100/sysinfo.csv | 2 +- .../kernel_verbose_3/MI100/timestamps.csv | 6 +++--- .../kernel_verbose_3/MI200/SQ_IFETCH_LEVEL.csv | 4 ++++ .../MI200/SQ_INST_LEVEL_LDS.csv | 4 ++++ .../MI200/SQ_INST_LEVEL_SMEM.csv | 4 ++++ .../MI200/SQ_INST_LEVEL_VMEM.csv | 4 ++++ .../kernel_verbose_3/MI200/SQ_LEVEL_WAVES.csv | 4 ++++ .../MI200/perfmon/SQ_IFETCH_LEVEL.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_LDS.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_SMEM.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_VMEM.txt | 5 +++++ .../MI200/perfmon/SQ_LEVEL_WAVES.txt | 5 +++++ .../MI200/perfmon/pmc_perf_0.txt | 5 +++++ .../MI200/perfmon/pmc_perf_1.txt | 5 +++++ .../MI200/perfmon/pmc_perf_10.txt | 5 +++++ .../MI200/perfmon/pmc_perf_11.txt | 5 +++++ .../MI200/perfmon/pmc_perf_12.txt | 5 +++++ .../MI200/perfmon/pmc_perf_13.txt | 5 +++++ .../MI200/perfmon/pmc_perf_14.txt | 5 +++++ .../MI200/perfmon/pmc_perf_15.txt | 5 +++++ .../MI200/perfmon/pmc_perf_16.txt | 5 +++++ .../MI200/perfmon/pmc_perf_17.txt | 5 +++++ .../MI200/perfmon/pmc_perf_18.txt | 5 +++++ .../MI200/perfmon/pmc_perf_2.txt | 5 +++++ .../MI200/perfmon/pmc_perf_3.txt | 5 +++++ .../MI200/perfmon/pmc_perf_4.txt | 5 +++++ .../MI200/perfmon/pmc_perf_5.txt | 5 +++++ .../MI200/perfmon/pmc_perf_6.txt | 5 +++++ .../MI200/perfmon/pmc_perf_7.txt | 5 +++++ .../MI200/perfmon/pmc_perf_8.txt | 5 +++++ .../MI200/perfmon/pmc_perf_9.txt | 5 +++++ .../MI200/perfmon/timestamps.txt | 5 +++++ .../kernel_verbose_3/MI200/pmc_perf.csv | 4 ++++ .../kernel_verbose_3/MI200/roofline.csv | 5 +++++ .../kernel_verbose_3/MI200/sysinfo.csv | 2 ++ .../kernel_verbose_3/MI200/timestamps.csv | 4 ++++ .../kernel_verbose_4/MI100/SQ_IFETCH_LEVEL.csv | 6 +++--- .../MI100/SQ_INST_LEVEL_LDS.csv | 6 +++--- .../MI100/SQ_INST_LEVEL_SMEM.csv | 6 +++--- .../MI100/SQ_INST_LEVEL_VMEM.csv | 6 +++--- .../kernel_verbose_4/MI100/SQ_LEVEL_WAVES.csv | 6 +++--- .../MI100/pmc_dispatch_info.csv | 4 ++++ .../kernel_verbose_4/MI100/pmc_perf.csv | 8 ++++---- .../kernel_verbose_4/MI100/sysinfo.csv | 2 +- .../kernel_verbose_4/MI100/timestamps.csv | 6 +++--- .../kernel_verbose_4/MI200/SQ_IFETCH_LEVEL.csv | 4 ++++ .../MI200/SQ_INST_LEVEL_LDS.csv | 4 ++++ .../MI200/SQ_INST_LEVEL_SMEM.csv | 4 ++++ .../MI200/SQ_INST_LEVEL_VMEM.csv | 4 ++++ .../kernel_verbose_4/MI200/SQ_LEVEL_WAVES.csv | 4 ++++ .../MI200/perfmon/SQ_IFETCH_LEVEL.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_LDS.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_SMEM.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_VMEM.txt | 5 +++++ .../MI200/perfmon/SQ_LEVEL_WAVES.txt | 5 +++++ .../MI200/perfmon/pmc_perf_0.txt | 5 +++++ .../MI200/perfmon/pmc_perf_1.txt | 5 +++++ .../MI200/perfmon/pmc_perf_10.txt | 5 +++++ .../MI200/perfmon/pmc_perf_11.txt | 5 +++++ .../MI200/perfmon/pmc_perf_12.txt | 5 +++++ .../MI200/perfmon/pmc_perf_13.txt | 5 +++++ .../MI200/perfmon/pmc_perf_14.txt | 5 +++++ .../MI200/perfmon/pmc_perf_15.txt | 5 +++++ .../MI200/perfmon/pmc_perf_16.txt | 5 +++++ .../MI200/perfmon/pmc_perf_17.txt | 5 +++++ .../MI200/perfmon/pmc_perf_18.txt | 5 +++++ .../MI200/perfmon/pmc_perf_2.txt | 5 +++++ .../MI200/perfmon/pmc_perf_3.txt | 5 +++++ .../MI200/perfmon/pmc_perf_4.txt | 5 +++++ .../MI200/perfmon/pmc_perf_5.txt | 5 +++++ .../MI200/perfmon/pmc_perf_6.txt | 5 +++++ .../MI200/perfmon/pmc_perf_7.txt | 5 +++++ .../MI200/perfmon/pmc_perf_8.txt | 5 +++++ .../MI200/perfmon/pmc_perf_9.txt | 5 +++++ .../MI200/perfmon/timestamps.txt | 5 +++++ .../kernel_verbose_4/MI200/pmc_perf.csv | 4 ++++ .../kernel_verbose_4/MI200/roofline.csv | 5 +++++ .../kernel_verbose_4/MI200/sysinfo.csv | 2 ++ .../kernel_verbose_4/MI200/timestamps.csv | 4 ++++ .../kernel_verbose_5/MI100/SQ_IFETCH_LEVEL.csv | 6 +++--- .../MI100/SQ_INST_LEVEL_LDS.csv | 6 +++--- .../MI100/SQ_INST_LEVEL_SMEM.csv | 6 +++--- .../MI100/SQ_INST_LEVEL_VMEM.csv | 6 +++--- .../kernel_verbose_5/MI100/SQ_LEVEL_WAVES.csv | 6 +++--- .../MI100/pmc_dispatch_info.csv | 4 ++++ .../kernel_verbose_5/MI100/pmc_perf.csv | 8 ++++---- .../kernel_verbose_5/MI100/sysinfo.csv | 2 +- .../kernel_verbose_5/MI100/timestamps.csv | 6 +++--- .../kernel_verbose_5/MI200/SQ_IFETCH_LEVEL.csv | 4 ++++ .../MI200/SQ_INST_LEVEL_LDS.csv | 4 ++++ .../MI200/SQ_INST_LEVEL_SMEM.csv | 4 ++++ .../MI200/SQ_INST_LEVEL_VMEM.csv | 4 ++++ .../kernel_verbose_5/MI200/SQ_LEVEL_WAVES.csv | 4 ++++ .../MI200/perfmon/SQ_IFETCH_LEVEL.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_LDS.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_SMEM.txt | 5 +++++ .../MI200/perfmon/SQ_INST_LEVEL_VMEM.txt | 5 +++++ .../MI200/perfmon/SQ_LEVEL_WAVES.txt | 5 +++++ .../MI200/perfmon/pmc_perf_0.txt | 5 +++++ .../MI200/perfmon/pmc_perf_1.txt | 5 +++++ .../MI200/perfmon/pmc_perf_10.txt | 5 +++++ .../MI200/perfmon/pmc_perf_11.txt | 5 +++++ .../MI200/perfmon/pmc_perf_12.txt | 5 +++++ .../MI200/perfmon/pmc_perf_13.txt | 5 +++++ .../MI200/perfmon/pmc_perf_14.txt | 5 +++++ .../MI200/perfmon/pmc_perf_15.txt | 5 +++++ .../MI200/perfmon/pmc_perf_16.txt | 5 +++++ .../MI200/perfmon/pmc_perf_17.txt | 5 +++++ .../MI200/perfmon/pmc_perf_18.txt | 5 +++++ .../MI200/perfmon/pmc_perf_2.txt | 5 +++++ .../MI200/perfmon/pmc_perf_3.txt | 5 +++++ .../MI200/perfmon/pmc_perf_4.txt | 5 +++++ .../MI200/perfmon/pmc_perf_5.txt | 5 +++++ .../MI200/perfmon/pmc_perf_6.txt | 5 +++++ .../MI200/perfmon/pmc_perf_7.txt | 5 +++++ .../MI200/perfmon/pmc_perf_8.txt | 5 +++++ .../MI200/perfmon/pmc_perf_9.txt | 5 +++++ .../MI200/perfmon/timestamps.txt | 5 +++++ .../kernel_verbose_5/MI200/pmc_perf.csv | 4 ++++ .../kernel_verbose_5/MI200/roofline.csv | 5 +++++ .../kernel_verbose_5/MI200/sysinfo.csv | 2 ++ .../kernel_verbose_5/MI200/timestamps.csv | 4 ++++ .../MI200/empirRoof_gpu-0_fp32.pdf | Bin 0 -> 12635 bytes .../MI200/empirRoof_gpu-0_int8_fp16.pdf | Bin 0 -> 12378 bytes .../mem_levels_HBM/MI200/perfmon/pmc_perf_0.txt | 5 +++++ .../mem_levels_HBM/MI200/perfmon/pmc_perf_1.txt | 5 +++++ .../mem_levels_HBM/MI200/perfmon/pmc_perf_2.txt | 5 +++++ .../mem_levels_HBM/MI200/perfmon/timestamps.txt | 5 +++++ .../workloads/mem_levels_HBM/MI200/pmc_perf.csv | 4 ++++ .../workloads/mem_levels_HBM/MI200/roofline.csv | 5 +++++ .../workloads/mem_levels_HBM/MI200/sysinfo.csv | 2 ++ .../mem_levels_HBM/MI200/timestamps.csv | 4 ++++ .../MI100/perfmon/pmc_perf_0.txt | 5 +++++ .../MI100/perfmon/pmc_perf_1.txt | 5 +++++ .../MI100/perfmon/pmc_perf_2.txt | 5 +++++ .../MI100/perfmon/timestamps.txt | 5 +++++ .../MI200/empirRoof_gpu-0_fp32.pdf | Bin 0 -> 13222 bytes .../MI200/empirRoof_gpu-0_int8_fp16.pdf | Bin 0 -> 12857 bytes .../MI200/perfmon/pmc_perf_0.txt | 5 +++++ .../MI200/perfmon/pmc_perf_1.txt | 5 +++++ .../MI200/perfmon/pmc_perf_2.txt | 5 +++++ .../MI200/perfmon/timestamps.txt | 5 +++++ .../mem_levels_HBM_LDS/MI200/pmc_perf.csv | 4 ++++ .../mem_levels_HBM_LDS/MI200/roofline.csv | 5 +++++ .../mem_levels_HBM_LDS/MI200/sysinfo.csv | 2 ++ .../mem_levels_HBM_LDS/MI200/timestamps.csv | 4 ++++ .../MI200/empirRoof_gpu-0_fp32.pdf | Bin 0 -> 12510 bytes .../MI200/empirRoof_gpu-0_int8_fp16.pdf | Bin 0 -> 12295 bytes .../mem_levels_L2/MI200/perfmon/pmc_perf_0.txt | 5 +++++ .../mem_levels_L2/MI200/perfmon/pmc_perf_1.txt | 5 +++++ .../mem_levels_L2/MI200/perfmon/pmc_perf_2.txt | 5 +++++ .../mem_levels_L2/MI200/perfmon/timestamps.txt | 5 +++++ .../workloads/mem_levels_L2/MI200/pmc_perf.csv | 4 ++++ .../workloads/mem_levels_L2/MI200/roofline.csv | 5 +++++ tests/workloads/mem_levels_L2/MI200/sysinfo.csv | 2 ++ .../mem_levels_L2/MI200/timestamps.csv | 4 ++++ .../MI200/empirRoof_gpu-0_fp32.pdf | Bin 0 -> 13043 bytes .../MI200/empirRoof_gpu-0_int8_fp16.pdf | Bin 0 -> 12852 bytes .../MI200/perfmon/pmc_perf_0.txt | 5 +++++ .../MI200/perfmon/pmc_perf_1.txt | 5 +++++ .../MI200/perfmon/pmc_perf_2.txt | 5 +++++ .../MI200/perfmon/timestamps.txt | 5 +++++ .../mem_levels_L2_vL1d_LDS/MI200/pmc_perf.csv | 4 ++++ .../mem_levels_L2_vL1d_LDS/MI200/roofline.csv | 5 +++++ .../mem_levels_L2_vL1d_LDS/MI200/sysinfo.csv | 2 ++ .../mem_levels_L2_vL1d_LDS/MI200/timestamps.csv | 4 ++++ .../MI200/empirRoof_gpu-0_fp32.pdf | Bin 0 -> 13249 bytes .../MI200/empirRoof_gpu-0_int8_fp16.pdf | Bin 0 -> 12563 bytes .../mem_levels_LDS/MI200/perfmon/pmc_perf_0.txt | 5 +++++ .../mem_levels_LDS/MI200/perfmon/pmc_perf_1.txt | 5 +++++ .../mem_levels_LDS/MI200/perfmon/pmc_perf_2.txt | 5 +++++ .../mem_levels_LDS/MI200/perfmon/timestamps.txt | 5 +++++ .../workloads/mem_levels_LDS/MI200/pmc_perf.csv | 4 ++++ .../workloads/mem_levels_LDS/MI200/roofline.csv | 5 +++++ .../workloads/mem_levels_LDS/MI200/sysinfo.csv | 2 ++ .../mem_levels_LDS/MI200/timestamps.csv | 4 ++++ .../MI200/empirRoof_gpu-0_fp32.pdf | Bin 0 -> 12981 bytes .../MI200/empirRoof_gpu-0_int8_fp16.pdf | Bin 0 -> 12513 bytes .../MI200/perfmon/pmc_perf_0.txt | 5 +++++ .../MI200/perfmon/pmc_perf_1.txt | 5 +++++ .../MI200/perfmon/pmc_perf_2.txt | 5 +++++ .../MI200/perfmon/timestamps.txt | 5 +++++ .../mem_levels_vL1D/MI200/pmc_perf.csv | 4 ++++ .../mem_levels_vL1D/MI200/roofline.csv | 5 +++++ .../workloads/mem_levels_vL1D/MI200/sysinfo.csv | 2 ++ .../mem_levels_vL1D/MI200/timestamps.csv | 4 ++++ .../MI200/empirRoof_gpu-0_fp32.pdf | Bin 0 -> 13350 bytes .../MI200/empirRoof_gpu-0_int8_fp16.pdf | Bin 0 -> 12907 bytes .../MI200/perfmon/pmc_perf_0.txt | 5 +++++ .../MI200/perfmon/pmc_perf_1.txt | 5 +++++ .../MI200/perfmon/pmc_perf_2.txt | 5 +++++ .../MI200/perfmon/timestamps.txt | 5 +++++ .../mem_levels_vL1d_LDS/MI200/pmc_perf.csv | 4 ++++ .../mem_levels_vL1d_LDS/MI200/roofline.csv | 5 +++++ .../mem_levels_vL1d_LDS/MI200/sysinfo.csv | 2 ++ .../mem_levels_vL1d_LDS/MI200/timestamps.csv | 4 ++++ .../workloads/no_roof/MI100/SQ_IFETCH_LEVEL.csv | 6 +++--- .../no_roof/MI100/SQ_INST_LEVEL_LDS.csv | 6 +++--- .../no_roof/MI100/SQ_INST_LEVEL_SMEM.csv | 6 +++--- .../no_roof/MI100/SQ_INST_LEVEL_VMEM.csv | 6 +++--- .../workloads/no_roof/MI100/SQ_LEVEL_WAVES.csv | 6 +++--- .../no_roof/MI100/pmc_dispatch_info.csv | 4 ++++ tests/workloads/no_roof/MI100/pmc_perf.csv | 8 ++++---- tests/workloads/no_roof/MI100/sysinfo.csv | 2 +- tests/workloads/no_roof/MI100/timestamps.csv | 6 +++--- tests/workloads/path/MI100/SQ_IFETCH_LEVEL.csv | 6 +++--- .../workloads/path/MI100/SQ_INST_LEVEL_LDS.csv | 6 +++--- .../workloads/path/MI100/SQ_INST_LEVEL_SMEM.csv | 6 +++--- .../workloads/path/MI100/SQ_INST_LEVEL_VMEM.csv | 6 +++--- tests/workloads/path/MI100/SQ_LEVEL_WAVES.csv | 6 +++--- .../workloads/path/MI100/pmc_dispatch_info.csv | 4 ++++ tests/workloads/path/MI100/pmc_perf.csv | 8 ++++---- tests/workloads/path/MI100/sysinfo.csv | 2 +- tests/workloads/path/MI100/timestamps.csv | 6 +++--- tests/workloads/path/MI200/SQ_IFETCH_LEVEL.csv | 4 ++++ .../workloads/path/MI200/SQ_INST_LEVEL_LDS.csv | 4 ++++ .../workloads/path/MI200/SQ_INST_LEVEL_SMEM.csv | 4 ++++ .../workloads/path/MI200/SQ_INST_LEVEL_VMEM.csv | 4 ++++ tests/workloads/path/MI200/SQ_LEVEL_WAVES.csv | 4 ++++ .../path/MI200/perfmon/SQ_IFETCH_LEVEL.txt | 5 +++++ .../path/MI200/perfmon/SQ_INST_LEVEL_LDS.txt | 5 +++++ .../path/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt | 5 +++++ .../path/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt | 5 +++++ .../path/MI200/perfmon/SQ_LEVEL_WAVES.txt | 5 +++++ .../workloads/path/MI200/perfmon/pmc_perf_0.txt | 5 +++++ .../workloads/path/MI200/perfmon/pmc_perf_1.txt | 5 +++++ .../path/MI200/perfmon/pmc_perf_10.txt | 5 +++++ .../path/MI200/perfmon/pmc_perf_11.txt | 5 +++++ .../path/MI200/perfmon/pmc_perf_12.txt | 5 +++++ .../path/MI200/perfmon/pmc_perf_13.txt | 5 +++++ .../path/MI200/perfmon/pmc_perf_14.txt | 5 +++++ .../path/MI200/perfmon/pmc_perf_15.txt | 5 +++++ .../path/MI200/perfmon/pmc_perf_16.txt | 5 +++++ .../path/MI200/perfmon/pmc_perf_17.txt | 5 +++++ .../path/MI200/perfmon/pmc_perf_18.txt | 5 +++++ .../workloads/path/MI200/perfmon/pmc_perf_2.txt | 5 +++++ .../workloads/path/MI200/perfmon/pmc_perf_3.txt | 5 +++++ .../workloads/path/MI200/perfmon/pmc_perf_4.txt | 5 +++++ .../workloads/path/MI200/perfmon/pmc_perf_5.txt | 5 +++++ .../workloads/path/MI200/perfmon/pmc_perf_6.txt | 5 +++++ .../workloads/path/MI200/perfmon/pmc_perf_7.txt | 5 +++++ .../workloads/path/MI200/perfmon/pmc_perf_8.txt | 5 +++++ .../workloads/path/MI200/perfmon/pmc_perf_9.txt | 5 +++++ .../workloads/path/MI200/perfmon/timestamps.txt | 5 +++++ tests/workloads/path/MI200/pmc_perf.csv | 4 ++++ tests/workloads/path/MI200/roofline.csv | 5 +++++ tests/workloads/path/MI200/sysinfo.csv | 2 ++ tests/workloads/path/MI200/timestamps.csv | 4 ++++ .../MI200/empirRoof_gpu-0_fp32.pdf | Bin 0 -> 13327 bytes .../MI200/empirRoof_gpu-0_int8_fp16.pdf | Bin 0 -> 13153 bytes .../MI200/perfmon/pmc_perf_0.txt | 5 +++++ .../MI200/perfmon/pmc_perf_1.txt | 5 +++++ .../MI200/perfmon/pmc_perf_2.txt | 5 +++++ .../MI200/perfmon/timestamps.txt | 5 +++++ .../sort_dispatches/MI200/pmc_perf.csv | 4 ++++ .../sort_dispatches/MI200/roofline.csv | 5 +++++ .../workloads/sort_dispatches/MI200/sysinfo.csv | 2 ++ .../sort_dispatches/MI200/timestamps.csv | 4 ++++ .../sort_kernels/MI200/empirRoof_gpu-0_fp32.pdf | Bin 0 -> 13105 bytes .../MI200/empirRoof_gpu-0_int8_fp16.pdf | Bin 0 -> 13142 bytes .../sort_kernels/MI200/perfmon/pmc_perf_0.txt | 5 +++++ .../sort_kernels/MI200/perfmon/pmc_perf_1.txt | 5 +++++ .../sort_kernels/MI200/perfmon/pmc_perf_2.txt | 5 +++++ .../sort_kernels/MI200/perfmon/timestamps.txt | 5 +++++ tests/workloads/sort_kernels/MI200/pmc_perf.csv | 4 ++++ tests/workloads/sort_kernels/MI200/roofline.csv | 5 +++++ tests/workloads/sort_kernels/MI200/sysinfo.csv | 2 ++ .../workloads/sort_kernels/MI200/timestamps.csv | 4 ++++ tests/workloads/vcopy/MI100/SQ_IFETCH_LEVEL.csv | 6 +++--- .../workloads/vcopy/MI100/SQ_INST_LEVEL_LDS.csv | 6 +++--- .../vcopy/MI100/SQ_INST_LEVEL_SMEM.csv | 6 +++--- .../vcopy/MI100/SQ_INST_LEVEL_VMEM.csv | 6 +++--- tests/workloads/vcopy/MI100/SQ_LEVEL_WAVES.csv | 6 +++--- .../workloads/vcopy/MI100/pmc_dispatch_info.csv | 4 ++++ tests/workloads/vcopy/MI100/pmc_perf.csv | 8 ++++---- tests/workloads/vcopy/MI100/sysinfo.csv | 2 +- tests/workloads/vcopy/MI100/timestamps.csv | 6 +++--- tests/workloads/vcopy/MI200/SQ_IFETCH_LEVEL.csv | 6 +++--- .../workloads/vcopy/MI200/SQ_INST_LEVEL_LDS.csv | 6 +++--- .../vcopy/MI200/SQ_INST_LEVEL_SMEM.csv | 6 +++--- .../vcopy/MI200/SQ_INST_LEVEL_VMEM.csv | 6 +++--- tests/workloads/vcopy/MI200/SQ_LEVEL_WAVES.csv | 6 +++--- .../vcopy/MI200/perfmon/pmc_perf_0.txt | 2 +- .../vcopy/MI200/perfmon/pmc_perf_1.txt | 2 +- .../vcopy/MI200/perfmon/pmc_perf_2.txt | 2 +- .../vcopy/MI200/perfmon/pmc_perf_3.txt | 2 +- .../vcopy/MI200/perfmon/pmc_perf_4.txt | 2 +- .../workloads/vcopy/MI200/pmc_dispatch_info.csv | 4 ++++ tests/workloads/vcopy/MI200/pmc_perf.csv | 8 ++++---- tests/workloads/vcopy/MI200/roofline.csv | 8 ++++---- tests/workloads/vcopy/MI200/sysinfo.csv | 2 +- tests/workloads/vcopy/MI200/timestamps.csv | 6 +++--- 1472 files changed, 5798 insertions(+), 630 deletions(-) create mode 100644 tests/workloads/device_filter/MI200/SQ_IFETCH_LEVEL.csv create mode 100644 tests/workloads/device_filter/MI200/SQ_INST_LEVEL_LDS.csv create mode 100644 tests/workloads/device_filter/MI200/SQ_INST_LEVEL_SMEM.csv create mode 100644 tests/workloads/device_filter/MI200/SQ_INST_LEVEL_VMEM.csv create mode 100644 tests/workloads/device_filter/MI200/SQ_LEVEL_WAVES.csv create mode 100644 tests/workloads/device_filter/MI200/perfmon/SQ_IFETCH_LEVEL.txt create mode 100644 tests/workloads/device_filter/MI200/perfmon/SQ_INST_LEVEL_LDS.txt create mode 100644 tests/workloads/device_filter/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt create mode 100644 tests/workloads/device_filter/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt create mode 100644 tests/workloads/device_filter/MI200/perfmon/SQ_LEVEL_WAVES.txt create mode 100644 tests/workloads/device_filter/MI200/perfmon/pmc_perf_0.txt create mode 100644 tests/workloads/device_filter/MI200/perfmon/pmc_perf_1.txt create mode 100644 tests/workloads/device_filter/MI200/perfmon/pmc_perf_10.txt create mode 100644 tests/workloads/device_filter/MI200/perfmon/pmc_perf_11.txt create mode 100644 tests/workloads/device_filter/MI200/perfmon/pmc_perf_12.txt create mode 100644 tests/workloads/device_filter/MI200/perfmon/pmc_perf_13.txt create mode 100644 tests/workloads/device_filter/MI200/perfmon/pmc_perf_14.txt create mode 100644 tests/workloads/device_filter/MI200/perfmon/pmc_perf_15.txt create mode 100644 tests/workloads/device_filter/MI200/perfmon/pmc_perf_16.txt create mode 100644 tests/workloads/device_filter/MI200/perfmon/pmc_perf_17.txt create mode 100644 tests/workloads/device_filter/MI200/perfmon/pmc_perf_18.txt create mode 100644 tests/workloads/device_filter/MI200/perfmon/pmc_perf_2.txt create mode 100644 tests/workloads/device_filter/MI200/perfmon/pmc_perf_3.txt create mode 100644 tests/workloads/device_filter/MI200/perfmon/pmc_perf_4.txt create mode 100644 tests/workloads/device_filter/MI200/perfmon/pmc_perf_5.txt create mode 100644 tests/workloads/device_filter/MI200/perfmon/pmc_perf_6.txt create mode 100644 tests/workloads/device_filter/MI200/perfmon/pmc_perf_7.txt create mode 100644 tests/workloads/device_filter/MI200/perfmon/pmc_perf_8.txt create mode 100644 tests/workloads/device_filter/MI200/perfmon/pmc_perf_9.txt create mode 100644 tests/workloads/device_filter/MI200/perfmon/timestamps.txt create mode 100644 tests/workloads/device_filter/MI200/pmc_perf.csv create mode 100644 tests/workloads/device_filter/MI200/roofline.csv create mode 100644 tests/workloads/device_filter/MI200/sysinfo.csv create mode 100644 tests/workloads/device_filter/MI200/timestamps.csv create mode 100644 tests/workloads/device_inv_int/MI100/pmc_dispatch_info.csv create mode 100644 tests/workloads/device_inv_int/MI200/SQ_IFETCH_LEVEL.csv create mode 100644 tests/workloads/device_inv_int/MI200/SQ_INST_LEVEL_LDS.csv create mode 100644 tests/workloads/device_inv_int/MI200/SQ_INST_LEVEL_SMEM.csv create mode 100644 tests/workloads/device_inv_int/MI200/SQ_INST_LEVEL_VMEM.csv create mode 100644 tests/workloads/device_inv_int/MI200/SQ_LEVEL_WAVES.csv create mode 100644 tests/workloads/device_inv_int/MI200/perfmon/SQ_IFETCH_LEVEL.txt create mode 100644 tests/workloads/device_inv_int/MI200/perfmon/SQ_INST_LEVEL_LDS.txt create mode 100644 tests/workloads/device_inv_int/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt create mode 100644 tests/workloads/device_inv_int/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt create mode 100644 tests/workloads/device_inv_int/MI200/perfmon/SQ_LEVEL_WAVES.txt create mode 100644 tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_0.txt create mode 100644 tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_1.txt create mode 100644 tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_10.txt create mode 100644 tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_11.txt create mode 100644 tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_12.txt create mode 100644 tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_13.txt create mode 100644 tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_14.txt create mode 100644 tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_15.txt create mode 100644 tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_16.txt create mode 100644 tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_17.txt create mode 100644 tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_18.txt create mode 100644 tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_2.txt create mode 100644 tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_3.txt create mode 100644 tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_4.txt create mode 100644 tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_5.txt create mode 100644 tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_6.txt create mode 100644 tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_7.txt create mode 100644 tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_8.txt create mode 100644 tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_9.txt create mode 100644 tests/workloads/device_inv_int/MI200/perfmon/timestamps.txt create mode 100644 tests/workloads/device_inv_int/MI200/pmc_perf.csv create mode 100644 tests/workloads/device_inv_int/MI200/roofline.csv create mode 100644 tests/workloads/device_inv_int/MI200/sysinfo.csv create mode 100644 tests/workloads/device_inv_int/MI200/timestamps.csv create mode 100644 tests/workloads/dispatch_0/MI100/pmc_dispatch_info.csv create mode 100644 tests/workloads/dispatch_0/MI200/SQ_IFETCH_LEVEL.csv create mode 100644 tests/workloads/dispatch_0/MI200/SQ_INST_LEVEL_LDS.csv create mode 100644 tests/workloads/dispatch_0/MI200/SQ_INST_LEVEL_SMEM.csv create mode 100644 tests/workloads/dispatch_0/MI200/SQ_INST_LEVEL_VMEM.csv create mode 100644 tests/workloads/dispatch_0/MI200/SQ_LEVEL_WAVES.csv create mode 100644 tests/workloads/dispatch_0/MI200/perfmon/SQ_IFETCH_LEVEL.txt create mode 100644 tests/workloads/dispatch_0/MI200/perfmon/SQ_INST_LEVEL_LDS.txt create mode 100644 tests/workloads/dispatch_0/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt create mode 100644 tests/workloads/dispatch_0/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt create mode 100644 tests/workloads/dispatch_0/MI200/perfmon/SQ_LEVEL_WAVES.txt create mode 100644 tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_0.txt create mode 100644 tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_1.txt create mode 100644 tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_10.txt create mode 100644 tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_11.txt create mode 100644 tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_12.txt create mode 100644 tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_13.txt create mode 100644 tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_14.txt create mode 100644 tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_15.txt create mode 100644 tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_16.txt create mode 100644 tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_17.txt create mode 100644 tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_18.txt create mode 100644 tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_2.txt create mode 100644 tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_3.txt create mode 100644 tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_4.txt create mode 100644 tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_5.txt create mode 100644 tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_6.txt create mode 100644 tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_7.txt create mode 100644 tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_8.txt create mode 100644 tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_9.txt create mode 100644 tests/workloads/dispatch_0/MI200/perfmon/timestamps.txt create mode 100644 tests/workloads/dispatch_0/MI200/pmc_perf.csv create mode 100644 tests/workloads/dispatch_0/MI200/roofline.csv create mode 100644 tests/workloads/dispatch_0/MI200/sysinfo.csv create mode 100644 tests/workloads/dispatch_0/MI200/timestamps.csv create mode 100644 tests/workloads/dispatch_0_1/MI100/pmc_dispatch_info.csv create mode 100644 tests/workloads/dispatch_0_1/MI200/SQ_IFETCH_LEVEL.csv create mode 100644 tests/workloads/dispatch_0_1/MI200/SQ_INST_LEVEL_LDS.csv create mode 100644 tests/workloads/dispatch_0_1/MI200/SQ_INST_LEVEL_SMEM.csv create mode 100644 tests/workloads/dispatch_0_1/MI200/SQ_INST_LEVEL_VMEM.csv create mode 100644 tests/workloads/dispatch_0_1/MI200/SQ_LEVEL_WAVES.csv create mode 100644 tests/workloads/dispatch_0_1/MI200/perfmon/SQ_IFETCH_LEVEL.txt create mode 100644 tests/workloads/dispatch_0_1/MI200/perfmon/SQ_INST_LEVEL_LDS.txt create mode 100644 tests/workloads/dispatch_0_1/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt create mode 100644 tests/workloads/dispatch_0_1/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt create mode 100644 tests/workloads/dispatch_0_1/MI200/perfmon/SQ_LEVEL_WAVES.txt create mode 100644 tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_0.txt create mode 100644 tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_1.txt create mode 100644 tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_10.txt create mode 100644 tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_11.txt create mode 100644 tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_12.txt create mode 100644 tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_13.txt create mode 100644 tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_14.txt create mode 100644 tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_15.txt create mode 100644 tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_16.txt create mode 100644 tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_17.txt create mode 100644 tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_18.txt create mode 100644 tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_2.txt create mode 100644 tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_3.txt create mode 100644 tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_4.txt create mode 100644 tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_5.txt create mode 100644 tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_6.txt create mode 100644 tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_7.txt create mode 100644 tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_8.txt create mode 100644 tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_9.txt create mode 100644 tests/workloads/dispatch_0_1/MI200/perfmon/timestamps.txt create mode 100644 tests/workloads/dispatch_0_1/MI200/pmc_perf.csv create mode 100644 tests/workloads/dispatch_0_1/MI200/roofline.csv create mode 100644 tests/workloads/dispatch_0_1/MI200/sysinfo.csv create mode 100644 tests/workloads/dispatch_0_1/MI200/timestamps.csv create mode 100644 tests/workloads/dispatch_2/MI100/pmc_dispatch_info.csv create mode 100644 tests/workloads/dispatch_2/MI200/SQ_IFETCH_LEVEL.csv create mode 100644 tests/workloads/dispatch_2/MI200/SQ_INST_LEVEL_LDS.csv create mode 100644 tests/workloads/dispatch_2/MI200/SQ_INST_LEVEL_SMEM.csv create mode 100644 tests/workloads/dispatch_2/MI200/SQ_INST_LEVEL_VMEM.csv create mode 100644 tests/workloads/dispatch_2/MI200/SQ_LEVEL_WAVES.csv create mode 100644 tests/workloads/dispatch_2/MI200/perfmon/SQ_IFETCH_LEVEL.txt create mode 100644 tests/workloads/dispatch_2/MI200/perfmon/SQ_INST_LEVEL_LDS.txt create mode 100644 tests/workloads/dispatch_2/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt create mode 100644 tests/workloads/dispatch_2/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt create mode 100644 tests/workloads/dispatch_2/MI200/perfmon/SQ_LEVEL_WAVES.txt create mode 100644 tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_0.txt create mode 100644 tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_1.txt create mode 100644 tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_10.txt create mode 100644 tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_11.txt create mode 100644 tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_12.txt create mode 100644 tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_13.txt create mode 100644 tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_14.txt create mode 100644 tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_15.txt create mode 100644 tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_16.txt create mode 100644 tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_17.txt create mode 100644 tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_18.txt create mode 100644 tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_2.txt create mode 100644 tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_3.txt create mode 100644 tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_4.txt create mode 100644 tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_5.txt create mode 100644 tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_6.txt create mode 100644 tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_7.txt create mode 100644 tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_8.txt create mode 100644 tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_9.txt create mode 100644 tests/workloads/dispatch_2/MI200/perfmon/timestamps.txt create mode 100644 tests/workloads/dispatch_2/MI200/pmc_perf.csv create mode 100644 tests/workloads/dispatch_2/MI200/roofline.csv create mode 100644 tests/workloads/dispatch_2/MI200/sysinfo.csv create mode 100644 tests/workloads/dispatch_2/MI200/timestamps.csv create mode 100644 tests/workloads/dispatch_6_8/MI200/SQ_IFETCH_LEVEL.csv create mode 100644 tests/workloads/dispatch_6_8/MI200/SQ_INST_LEVEL_LDS.csv create mode 100644 tests/workloads/dispatch_6_8/MI200/SQ_INST_LEVEL_SMEM.csv create mode 100644 tests/workloads/dispatch_6_8/MI200/SQ_INST_LEVEL_VMEM.csv create mode 100644 tests/workloads/dispatch_6_8/MI200/SQ_LEVEL_WAVES.csv create mode 100644 tests/workloads/dispatch_6_8/MI200/perfmon/SQ_IFETCH_LEVEL.txt create mode 100644 tests/workloads/dispatch_6_8/MI200/perfmon/SQ_INST_LEVEL_LDS.txt create mode 100644 tests/workloads/dispatch_6_8/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt create mode 100644 tests/workloads/dispatch_6_8/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt create mode 100644 tests/workloads/dispatch_6_8/MI200/perfmon/SQ_LEVEL_WAVES.txt create mode 100644 tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_0.txt create mode 100644 tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_1.txt create mode 100644 tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_10.txt create mode 100644 tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_11.txt create mode 100644 tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_12.txt create mode 100644 tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_13.txt create mode 100644 tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_14.txt create mode 100644 tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_15.txt create mode 100644 tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_16.txt create mode 100644 tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_17.txt create mode 100644 tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_18.txt create mode 100644 tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_2.txt create mode 100644 tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_3.txt create mode 100644 tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_4.txt create mode 100644 tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_5.txt create mode 100644 tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_6.txt create mode 100644 tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_7.txt create mode 100644 tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_8.txt create mode 100644 tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_9.txt create mode 100644 tests/workloads/dispatch_6_8/MI200/perfmon/timestamps.txt create mode 100644 tests/workloads/dispatch_6_8/MI200/pmc_perf_0.csv create mode 100644 tests/workloads/dispatch_6_8/MI200/pmc_perf_1.csv create mode 100644 tests/workloads/dispatch_6_8/MI200/pmc_perf_10.csv create mode 100644 tests/workloads/dispatch_6_8/MI200/pmc_perf_11.csv create mode 100644 tests/workloads/dispatch_6_8/MI200/pmc_perf_12.csv create mode 100644 tests/workloads/dispatch_6_8/MI200/pmc_perf_13.csv create mode 100644 tests/workloads/dispatch_6_8/MI200/pmc_perf_14.csv create mode 100644 tests/workloads/dispatch_6_8/MI200/pmc_perf_15.csv create mode 100644 tests/workloads/dispatch_6_8/MI200/pmc_perf_16.csv create mode 100644 tests/workloads/dispatch_6_8/MI200/pmc_perf_17.csv create mode 100644 tests/workloads/dispatch_6_8/MI200/pmc_perf_18.csv create mode 100644 tests/workloads/dispatch_6_8/MI200/pmc_perf_2.csv create mode 100644 tests/workloads/dispatch_6_8/MI200/pmc_perf_3.csv create mode 100644 tests/workloads/dispatch_6_8/MI200/pmc_perf_4.csv create mode 100644 tests/workloads/dispatch_6_8/MI200/pmc_perf_5.csv create mode 100644 tests/workloads/dispatch_6_8/MI200/pmc_perf_6.csv create mode 100644 tests/workloads/dispatch_6_8/MI200/pmc_perf_7.csv create mode 100644 tests/workloads/dispatch_6_8/MI200/pmc_perf_8.csv create mode 100644 tests/workloads/dispatch_6_8/MI200/pmc_perf_9.csv create mode 100644 tests/workloads/dispatch_6_8/MI200/sysinfo.csv create mode 100644 tests/workloads/dispatch_6_8/MI200/timestamps.csv create mode 100644 tests/workloads/dispatch_7/MI200/SQ_IFETCH_LEVEL.csv create mode 100644 tests/workloads/dispatch_7/MI200/SQ_INST_LEVEL_LDS.csv create mode 100644 tests/workloads/dispatch_7/MI200/SQ_INST_LEVEL_SMEM.csv create mode 100644 tests/workloads/dispatch_7/MI200/SQ_INST_LEVEL_VMEM.csv create mode 100644 tests/workloads/dispatch_7/MI200/SQ_LEVEL_WAVES.csv create mode 100644 tests/workloads/dispatch_7/MI200/perfmon/SQ_IFETCH_LEVEL.txt create mode 100644 tests/workloads/dispatch_7/MI200/perfmon/SQ_INST_LEVEL_LDS.txt create mode 100644 tests/workloads/dispatch_7/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt create mode 100644 tests/workloads/dispatch_7/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt create mode 100644 tests/workloads/dispatch_7/MI200/perfmon/SQ_LEVEL_WAVES.txt create mode 100644 tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_0.txt create mode 100644 tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_1.txt create mode 100644 tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_10.txt create mode 100644 tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_11.txt create mode 100644 tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_12.txt create mode 100644 tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_13.txt create mode 100644 tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_14.txt create mode 100644 tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_15.txt create mode 100644 tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_16.txt create mode 100644 tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_17.txt create mode 100644 tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_18.txt create mode 100644 tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_2.txt create mode 100644 tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_3.txt create mode 100644 tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_4.txt create mode 100644 tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_5.txt create mode 100644 tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_6.txt create mode 100644 tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_7.txt create mode 100644 tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_8.txt create mode 100644 tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_9.txt create mode 100644 tests/workloads/dispatch_7/MI200/perfmon/timestamps.txt create mode 100644 tests/workloads/dispatch_7/MI200/pmc_perf_0.csv create mode 100644 tests/workloads/dispatch_7/MI200/pmc_perf_1.csv create mode 100644 tests/workloads/dispatch_7/MI200/pmc_perf_10.csv create mode 100644 tests/workloads/dispatch_7/MI200/pmc_perf_11.csv create mode 100644 tests/workloads/dispatch_7/MI200/pmc_perf_12.csv create mode 100644 tests/workloads/dispatch_7/MI200/pmc_perf_13.csv create mode 100644 tests/workloads/dispatch_7/MI200/pmc_perf_14.csv create mode 100644 tests/workloads/dispatch_7/MI200/pmc_perf_15.csv create mode 100644 tests/workloads/dispatch_7/MI200/pmc_perf_16.csv create mode 100644 tests/workloads/dispatch_7/MI200/pmc_perf_17.csv create mode 100644 tests/workloads/dispatch_7/MI200/pmc_perf_18.csv create mode 100644 tests/workloads/dispatch_7/MI200/pmc_perf_2.csv create mode 100644 tests/workloads/dispatch_7/MI200/pmc_perf_3.csv create mode 100644 tests/workloads/dispatch_7/MI200/pmc_perf_4.csv create mode 100644 tests/workloads/dispatch_7/MI200/pmc_perf_5.csv create mode 100644 tests/workloads/dispatch_7/MI200/pmc_perf_6.csv create mode 100644 tests/workloads/dispatch_7/MI200/pmc_perf_7.csv create mode 100644 tests/workloads/dispatch_7/MI200/pmc_perf_8.csv create mode 100644 tests/workloads/dispatch_7/MI200/pmc_perf_9.csv create mode 100644 tests/workloads/dispatch_7/MI200/sysinfo.csv create mode 100644 tests/workloads/dispatch_7/MI200/timestamps.csv create mode 100644 tests/workloads/dispatch_inv/MI200/SQ_IFETCH_LEVEL.csv create mode 100644 tests/workloads/dispatch_inv/MI200/SQ_INST_LEVEL_LDS.csv create mode 100644 tests/workloads/dispatch_inv/MI200/SQ_INST_LEVEL_SMEM.csv create mode 100644 tests/workloads/dispatch_inv/MI200/SQ_INST_LEVEL_VMEM.csv create mode 100644 tests/workloads/dispatch_inv/MI200/SQ_LEVEL_WAVES.csv create mode 100644 tests/workloads/dispatch_inv/MI200/perfmon/SQ_IFETCH_LEVEL.txt create mode 100644 tests/workloads/dispatch_inv/MI200/perfmon/SQ_INST_LEVEL_LDS.txt create mode 100644 tests/workloads/dispatch_inv/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt create mode 100644 tests/workloads/dispatch_inv/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt create mode 100644 tests/workloads/dispatch_inv/MI200/perfmon/SQ_LEVEL_WAVES.txt create mode 100644 tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_0.txt create mode 100644 tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_1.txt create mode 100644 tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_10.txt create mode 100644 tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_11.txt create mode 100644 tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_12.txt create mode 100644 tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_13.txt create mode 100644 tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_14.txt create mode 100644 tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_15.txt create mode 100644 tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_16.txt create mode 100644 tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_17.txt create mode 100644 tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_18.txt create mode 100644 tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_2.txt create mode 100644 tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_3.txt create mode 100644 tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_4.txt create mode 100644 tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_5.txt create mode 100644 tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_6.txt create mode 100644 tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_7.txt create mode 100644 tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_8.txt create mode 100644 tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_9.txt create mode 100644 tests/workloads/dispatch_inv/MI200/perfmon/timestamps.txt create mode 100644 tests/workloads/dispatch_inv/MI200/pmc_perf.csv create mode 100644 tests/workloads/dispatch_inv/MI200/roofline.csv create mode 100644 tests/workloads/dispatch_inv/MI200/sysinfo.csv create mode 100644 tests/workloads/dispatch_inv/MI200/timestamps.csv create mode 100644 tests/workloads/dispatch_invalid/MI100/SQ_IFETCH_LEVEL.csv create mode 100644 tests/workloads/dispatch_invalid/MI100/SQ_INST_LEVEL_LDS.csv create mode 100644 tests/workloads/dispatch_invalid/MI100/SQ_INST_LEVEL_SMEM.csv create mode 100644 tests/workloads/dispatch_invalid/MI100/SQ_INST_LEVEL_VMEM.csv create mode 100644 tests/workloads/dispatch_invalid/MI100/SQ_LEVEL_WAVES.csv create mode 100644 tests/workloads/dispatch_invalid/MI100/perfmon/SQ_IFETCH_LEVEL.txt create mode 100644 tests/workloads/dispatch_invalid/MI100/perfmon/SQ_INST_LEVEL_LDS.txt create mode 100644 tests/workloads/dispatch_invalid/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt create mode 100644 tests/workloads/dispatch_invalid/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt create mode 100644 tests/workloads/dispatch_invalid/MI100/perfmon/SQ_LEVEL_WAVES.txt create mode 100644 tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_0.txt create mode 100644 tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_1.txt create mode 100644 tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_10.txt create mode 100644 tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_11.txt create mode 100644 tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_12.txt create mode 100644 tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_13.txt create mode 100644 tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_14.txt create mode 100644 tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_15.txt create mode 100644 tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_16.txt create mode 100644 tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_2.txt create mode 100644 tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_3.txt create mode 100644 tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_4.txt create mode 100644 tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_5.txt create mode 100644 tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_6.txt create mode 100644 tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_7.txt create mode 100644 tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_8.txt create mode 100644 tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_9.txt create mode 100644 tests/workloads/dispatch_invalid/MI100/perfmon/timestamps.txt create mode 100644 tests/workloads/dispatch_invalid/MI100/pmc_dispatch_info.csv create mode 100644 tests/workloads/dispatch_invalid/MI100/pmc_perf.csv create mode 100644 tests/workloads/dispatch_invalid/MI100/sysinfo.csv create mode 100644 tests/workloads/dispatch_invalid/MI100/timestamps.csv create mode 100644 tests/workloads/ipblocks_CPC/MI100/pmc_dispatch_info.csv create mode 100644 tests/workloads/ipblocks_CPC/MI200/perfmon/pmc_perf_0.txt create mode 100644 tests/workloads/ipblocks_CPC/MI200/perfmon/pmc_perf_1.txt create mode 100644 tests/workloads/ipblocks_CPC/MI200/perfmon/pmc_perf_2.txt create mode 100644 tests/workloads/ipblocks_CPC/MI200/perfmon/pmc_perf_3.txt create mode 100644 tests/workloads/ipblocks_CPC/MI200/perfmon/pmc_perf_4.txt create mode 100644 tests/workloads/ipblocks_CPC/MI200/perfmon/pmc_perf_5.txt create mode 100644 tests/workloads/ipblocks_CPC/MI200/perfmon/timestamps.txt create mode 100644 tests/workloads/ipblocks_CPC/MI200/pmc_perf.csv create mode 100644 tests/workloads/ipblocks_CPC/MI200/roofline.csv create mode 100644 tests/workloads/ipblocks_CPC/MI200/sysinfo.csv create mode 100644 tests/workloads/ipblocks_CPC/MI200/timestamps.csv create mode 100644 tests/workloads/ipblocks_CPF/MI100/pmc_dispatch_info.csv create mode 100644 tests/workloads/ipblocks_CPF/MI200/perfmon/pmc_perf_0.txt create mode 100644 tests/workloads/ipblocks_CPF/MI200/perfmon/pmc_perf_1.txt create mode 100644 tests/workloads/ipblocks_CPF/MI200/perfmon/pmc_perf_2.txt create mode 100644 tests/workloads/ipblocks_CPF/MI200/perfmon/pmc_perf_3.txt create mode 100644 tests/workloads/ipblocks_CPF/MI200/perfmon/timestamps.txt create mode 100644 tests/workloads/ipblocks_CPF/MI200/pmc_perf.csv create mode 100644 tests/workloads/ipblocks_CPF/MI200/roofline.csv create mode 100644 tests/workloads/ipblocks_CPF/MI200/sysinfo.csv create mode 100644 tests/workloads/ipblocks_CPF/MI200/timestamps.csv create mode 100644 tests/workloads/ipblocks_SPI/MI100/pmc_dispatch_info.csv create mode 100644 tests/workloads/ipblocks_SQ/MI100/pmc_dispatch_info.csv create mode 100644 tests/workloads/ipblocks_SQ/MI200/SQ_IFETCH_LEVEL.csv create mode 100644 tests/workloads/ipblocks_SQ/MI200/SQ_INST_LEVEL_LDS.csv create mode 100644 tests/workloads/ipblocks_SQ/MI200/SQ_INST_LEVEL_SMEM.csv create mode 100644 tests/workloads/ipblocks_SQ/MI200/SQ_INST_LEVEL_VMEM.csv create mode 100644 tests/workloads/ipblocks_SQ/MI200/SQ_LEVEL_WAVES.csv create mode 100644 tests/workloads/ipblocks_SQ/MI200/perfmon/SQ_IFETCH_LEVEL.txt create mode 100644 tests/workloads/ipblocks_SQ/MI200/perfmon/SQ_INST_LEVEL_LDS.txt create mode 100644 tests/workloads/ipblocks_SQ/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt create mode 100644 tests/workloads/ipblocks_SQ/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt create mode 100644 tests/workloads/ipblocks_SQ/MI200/perfmon/SQ_LEVEL_WAVES.txt create mode 100644 tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_0.txt create mode 100644 tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_1.txt create mode 100644 tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_10.txt create mode 100644 tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_11.txt create mode 100644 tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_12.txt create mode 100644 tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_2.txt create mode 100644 tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_3.txt create mode 100644 tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_4.txt create mode 100644 tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_5.txt create mode 100644 tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_6.txt create mode 100644 tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_7.txt create mode 100644 tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_8.txt create mode 100644 tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_9.txt create mode 100644 tests/workloads/ipblocks_SQ/MI200/perfmon/timestamps.txt create mode 100644 tests/workloads/ipblocks_SQ/MI200/pmc_perf.csv create mode 100644 tests/workloads/ipblocks_SQ/MI200/roofline.csv create mode 100644 tests/workloads/ipblocks_SQ/MI200/sysinfo.csv create mode 100644 tests/workloads/ipblocks_SQ/MI200/timestamps.csv create mode 100644 tests/workloads/ipblocks_SQC/MI100/pmc_dispatch_info.csv create mode 100644 tests/workloads/ipblocks_SQC/MI200/perfmon/pmc_perf_0.txt create mode 100644 tests/workloads/ipblocks_SQC/MI200/perfmon/pmc_perf_1.txt create mode 100644 tests/workloads/ipblocks_SQC/MI200/perfmon/pmc_perf_2.txt create mode 100644 tests/workloads/ipblocks_SQC/MI200/perfmon/pmc_perf_3.txt create mode 100644 tests/workloads/ipblocks_SQC/MI200/perfmon/timestamps.txt create mode 100644 tests/workloads/ipblocks_SQC/MI200/pmc_perf.csv create mode 100644 tests/workloads/ipblocks_SQC/MI200/roofline.csv create mode 100644 tests/workloads/ipblocks_SQC/MI200/sysinfo.csv create mode 100644 tests/workloads/ipblocks_SQC/MI200/timestamps.csv create mode 100644 tests/workloads/ipblocks_SQ_CPC/MI100/pmc_dispatch_info.csv create mode 100644 tests/workloads/ipblocks_SQ_CPC/MI200/SQ_IFETCH_LEVEL.csv create mode 100644 tests/workloads/ipblocks_SQ_CPC/MI200/SQ_INST_LEVEL_LDS.csv create mode 100644 tests/workloads/ipblocks_SQ_CPC/MI200/SQ_INST_LEVEL_SMEM.csv create mode 100644 tests/workloads/ipblocks_SQ_CPC/MI200/SQ_INST_LEVEL_VMEM.csv create mode 100644 tests/workloads/ipblocks_SQ_CPC/MI200/SQ_LEVEL_WAVES.csv create mode 100644 tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/SQ_IFETCH_LEVEL.txt create mode 100644 tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/SQ_INST_LEVEL_LDS.txt create mode 100644 tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt create mode 100644 tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt create mode 100644 tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/SQ_LEVEL_WAVES.txt create mode 100644 tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_0.txt create mode 100644 tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_1.txt create mode 100644 tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_10.txt create mode 100644 tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_11.txt create mode 100644 tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_12.txt create mode 100644 tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_2.txt create mode 100644 tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_3.txt create mode 100644 tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_4.txt create mode 100644 tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_5.txt create mode 100644 tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_6.txt create mode 100644 tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_7.txt create mode 100644 tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_8.txt create mode 100644 tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_9.txt create mode 100644 tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/timestamps.txt create mode 100644 tests/workloads/ipblocks_SQ_CPC/MI200/pmc_perf.csv create mode 100644 tests/workloads/ipblocks_SQ_CPC/MI200/roofline.csv create mode 100644 tests/workloads/ipblocks_SQ_CPC/MI200/sysinfo.csv create mode 100644 tests/workloads/ipblocks_SQ_CPC/MI200/timestamps.csv create mode 100644 tests/workloads/ipblocks_SQ_SPI/MI100/pmc_dispatch_info.csv create mode 100644 tests/workloads/ipblocks_SQ_SPI/MI200/SQ_IFETCH_LEVEL.csv create mode 100644 tests/workloads/ipblocks_SQ_SPI/MI200/SQ_INST_LEVEL_LDS.csv create mode 100644 tests/workloads/ipblocks_SQ_SPI/MI200/SQ_INST_LEVEL_SMEM.csv create mode 100644 tests/workloads/ipblocks_SQ_SPI/MI200/SQ_INST_LEVEL_VMEM.csv create mode 100644 tests/workloads/ipblocks_SQ_SPI/MI200/SQ_LEVEL_WAVES.csv create mode 100644 tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/SQ_IFETCH_LEVEL.txt create mode 100644 tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/SQ_INST_LEVEL_LDS.txt create mode 100644 tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt create mode 100644 tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt create mode 100644 tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/SQ_LEVEL_WAVES.txt create mode 100644 tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_0.txt create mode 100644 tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_1.txt create mode 100644 tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_10.txt create mode 100644 tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_11.txt create mode 100644 tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_12.txt create mode 100644 tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_2.txt create mode 100644 tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_3.txt create mode 100644 tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_4.txt create mode 100644 tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_5.txt create mode 100644 tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_6.txt create mode 100644 tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_7.txt create mode 100644 tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_8.txt create mode 100644 tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_9.txt create mode 100644 tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/timestamps.txt create mode 100644 tests/workloads/ipblocks_SQ_SPI/MI200/pmc_perf.csv create mode 100644 tests/workloads/ipblocks_SQ_SPI/MI200/roofline.csv create mode 100644 tests/workloads/ipblocks_SQ_SPI/MI200/sysinfo.csv create mode 100644 tests/workloads/ipblocks_SQ_SPI/MI200/timestamps.csv create mode 100644 tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/pmc_dispatch_info.csv create mode 100644 tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/SQ_IFETCH_LEVEL.csv create mode 100644 tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/SQ_INST_LEVEL_LDS.csv create mode 100644 tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/SQ_INST_LEVEL_SMEM.csv create mode 100644 tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/SQ_INST_LEVEL_VMEM.csv create mode 100644 tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/SQ_LEVEL_WAVES.csv create mode 100644 tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/SQ_IFETCH_LEVEL.txt create mode 100644 tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/SQ_INST_LEVEL_LDS.txt create mode 100644 tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt create mode 100644 tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt create mode 100644 tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/SQ_LEVEL_WAVES.txt create mode 100644 tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_0.txt create mode 100644 tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_1.txt create mode 100644 tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_10.txt create mode 100644 tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_11.txt create mode 100644 tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_12.txt create mode 100644 tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_2.txt create mode 100644 tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_3.txt create mode 100644 tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_4.txt create mode 100644 tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_5.txt create mode 100644 tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_6.txt create mode 100644 tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_7.txt create mode 100644 tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_8.txt create mode 100644 tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_9.txt create mode 100644 tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/timestamps.txt create mode 100644 tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/pmc_perf.csv create mode 100644 tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/roofline.csv create mode 100644 tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/sysinfo.csv create mode 100644 tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/timestamps.csv create mode 100644 tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/pmc_dispatch_info.csv create mode 100644 tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/SQ_IFETCH_LEVEL.csv create mode 100644 tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/SQ_INST_LEVEL_LDS.csv create mode 100644 tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/SQ_INST_LEVEL_SMEM.csv create mode 100644 tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/SQ_INST_LEVEL_VMEM.csv create mode 100644 tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/SQ_LEVEL_WAVES.csv create mode 100644 tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/SQ_IFETCH_LEVEL.txt create mode 100644 tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/SQ_INST_LEVEL_LDS.txt create mode 100644 tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt create mode 100644 tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt create mode 100644 tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/SQ_LEVEL_WAVES.txt create mode 100644 tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_0.txt create mode 100644 tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_1.txt create mode 100644 tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_10.txt create mode 100644 tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_11.txt create mode 100644 tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_12.txt create mode 100644 tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_2.txt create mode 100644 tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_3.txt create mode 100644 tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_4.txt create mode 100644 tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_5.txt create mode 100644 tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_6.txt create mode 100644 tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_7.txt create mode 100644 tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_8.txt create mode 100644 tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_9.txt create mode 100644 tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/timestamps.txt create mode 100644 tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/pmc_perf.csv create mode 100644 tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/roofline.csv create mode 100644 tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/sysinfo.csv create mode 100644 tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/timestamps.csv create mode 100644 tests/workloads/ipblocks_SQ_TA/MI100/pmc_dispatch_info.csv create mode 100644 tests/workloads/ipblocks_SQ_TA/MI200/SQ_IFETCH_LEVEL.csv create mode 100644 tests/workloads/ipblocks_SQ_TA/MI200/SQ_INST_LEVEL_LDS.csv create mode 100644 tests/workloads/ipblocks_SQ_TA/MI200/SQ_INST_LEVEL_SMEM.csv create mode 100644 tests/workloads/ipblocks_SQ_TA/MI200/SQ_INST_LEVEL_VMEM.csv create mode 100644 tests/workloads/ipblocks_SQ_TA/MI200/SQ_LEVEL_WAVES.csv create mode 100644 tests/workloads/ipblocks_SQ_TA/MI200/perfmon/SQ_IFETCH_LEVEL.txt create mode 100644 tests/workloads/ipblocks_SQ_TA/MI200/perfmon/SQ_INST_LEVEL_LDS.txt create mode 100644 tests/workloads/ipblocks_SQ_TA/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt create mode 100644 tests/workloads/ipblocks_SQ_TA/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt create mode 100644 tests/workloads/ipblocks_SQ_TA/MI200/perfmon/SQ_LEVEL_WAVES.txt create mode 100644 tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_0.txt create mode 100644 tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_1.txt create mode 100644 tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_10.txt create mode 100644 tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_11.txt create mode 100644 tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_12.txt create mode 100644 tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_2.txt create mode 100644 tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_3.txt create mode 100644 tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_4.txt create mode 100644 tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_5.txt create mode 100644 tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_6.txt create mode 100644 tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_7.txt create mode 100644 tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_8.txt create mode 100644 tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_9.txt create mode 100644 tests/workloads/ipblocks_SQ_TA/MI200/perfmon/timestamps.txt create mode 100644 tests/workloads/ipblocks_SQ_TA/MI200/pmc_perf.csv create mode 100644 tests/workloads/ipblocks_SQ_TA/MI200/roofline.csv create mode 100644 tests/workloads/ipblocks_SQ_TA/MI200/sysinfo.csv create mode 100644 tests/workloads/ipblocks_SQ_TA/MI200/timestamps.csv create mode 100644 tests/workloads/ipblocks_TA/MI100/pmc_dispatch_info.csv create mode 100644 tests/workloads/ipblocks_TA/MI200/perfmon/pmc_perf_0.txt create mode 100644 tests/workloads/ipblocks_TA/MI200/perfmon/pmc_perf_1.txt create mode 100644 tests/workloads/ipblocks_TA/MI200/perfmon/pmc_perf_2.txt create mode 100644 tests/workloads/ipblocks_TA/MI200/perfmon/pmc_perf_3.txt create mode 100644 tests/workloads/ipblocks_TA/MI200/perfmon/pmc_perf_4.txt create mode 100644 tests/workloads/ipblocks_TA/MI200/perfmon/pmc_perf_5.txt create mode 100644 tests/workloads/ipblocks_TA/MI200/perfmon/pmc_perf_6.txt create mode 100644 tests/workloads/ipblocks_TA/MI200/perfmon/pmc_perf_7.txt create mode 100644 tests/workloads/ipblocks_TA/MI200/perfmon/timestamps.txt create mode 100644 tests/workloads/ipblocks_TA/MI200/pmc_perf.csv create mode 100644 tests/workloads/ipblocks_TA/MI200/roofline.csv create mode 100644 tests/workloads/ipblocks_TA/MI200/sysinfo.csv create mode 100644 tests/workloads/ipblocks_TA/MI200/timestamps.csv create mode 100644 tests/workloads/ipblocks_TCC/MI100/pmc_dispatch_info.csv create mode 100644 tests/workloads/ipblocks_TCC/MI200/perfmon/pmc_perf_0.txt create mode 100644 tests/workloads/ipblocks_TCC/MI200/perfmon/pmc_perf_1.txt create mode 100644 tests/workloads/ipblocks_TCC/MI200/perfmon/pmc_perf_2.txt create mode 100644 tests/workloads/ipblocks_TCC/MI200/perfmon/pmc_perf_3.txt create mode 100644 tests/workloads/ipblocks_TCC/MI200/perfmon/pmc_perf_4.txt create mode 100644 tests/workloads/ipblocks_TCC/MI200/perfmon/pmc_perf_5.txt create mode 100644 tests/workloads/ipblocks_TCC/MI200/perfmon/pmc_perf_6.txt create mode 100644 tests/workloads/ipblocks_TCC/MI200/perfmon/pmc_perf_7.txt create mode 100644 tests/workloads/ipblocks_TCC/MI200/perfmon/pmc_perf_8.txt create mode 100644 tests/workloads/ipblocks_TCC/MI200/perfmon/timestamps.txt create mode 100644 tests/workloads/ipblocks_TCC/MI200/pmc_perf.csv create mode 100644 tests/workloads/ipblocks_TCC/MI200/roofline.csv create mode 100644 tests/workloads/ipblocks_TCC/MI200/sysinfo.csv create mode 100644 tests/workloads/ipblocks_TCC/MI200/timestamps.csv create mode 100644 tests/workloads/ipblocks_TCP/MI100/pmc_dispatch_info.csv create mode 100644 tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_0.txt create mode 100644 tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_1.txt create mode 100644 tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_2.txt create mode 100644 tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_3.txt create mode 100644 tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_4.txt create mode 100644 tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_5.txt create mode 100644 tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_6.txt create mode 100644 tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_7.txt create mode 100644 tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_8.txt create mode 100644 tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_9.txt create mode 100644 tests/workloads/ipblocks_TCP/MI200/perfmon/timestamps.txt create mode 100644 tests/workloads/ipblocks_TCP/MI200/pmc_perf.csv create mode 100644 tests/workloads/ipblocks_TCP/MI200/roofline.csv create mode 100644 tests/workloads/ipblocks_TCP/MI200/sysinfo.csv create mode 100644 tests/workloads/ipblocks_TCP/MI200/timestamps.csv create mode 100644 tests/workloads/ipblocks_TD/MI100/pmc_dispatch_info.csv create mode 100644 tests/workloads/ipblocks_TD/MI200/perfmon/pmc_perf_0.txt create mode 100644 tests/workloads/ipblocks_TD/MI200/perfmon/pmc_perf_1.txt create mode 100644 tests/workloads/ipblocks_TD/MI200/perfmon/pmc_perf_2.txt create mode 100644 tests/workloads/ipblocks_TD/MI200/perfmon/pmc_perf_3.txt create mode 100644 tests/workloads/ipblocks_TD/MI200/perfmon/timestamps.txt create mode 100644 tests/workloads/ipblocks_TD/MI200/pmc_perf.csv create mode 100644 tests/workloads/ipblocks_TD/MI200/roofline.csv create mode 100644 tests/workloads/ipblocks_TD/MI200/sysinfo.csv create mode 100644 tests/workloads/ipblocks_TD/MI200/timestamps.csv create mode 100644 tests/workloads/join_type_grid/MI100/pmc_dispatch_info.csv create mode 100644 tests/workloads/join_type_grid/MI200/SQ_IFETCH_LEVEL.csv create mode 100644 tests/workloads/join_type_grid/MI200/SQ_INST_LEVEL_LDS.csv create mode 100644 tests/workloads/join_type_grid/MI200/SQ_INST_LEVEL_SMEM.csv create mode 100644 tests/workloads/join_type_grid/MI200/SQ_INST_LEVEL_VMEM.csv create mode 100644 tests/workloads/join_type_grid/MI200/SQ_LEVEL_WAVES.csv create mode 100644 tests/workloads/join_type_grid/MI200/perfmon/SQ_IFETCH_LEVEL.txt create mode 100644 tests/workloads/join_type_grid/MI200/perfmon/SQ_INST_LEVEL_LDS.txt create mode 100644 tests/workloads/join_type_grid/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt create mode 100644 tests/workloads/join_type_grid/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt create mode 100644 tests/workloads/join_type_grid/MI200/perfmon/SQ_LEVEL_WAVES.txt create mode 100644 tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_0.txt create mode 100644 tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_1.txt create mode 100644 tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_10.txt create mode 100644 tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_11.txt create mode 100644 tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_12.txt create mode 100644 tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_13.txt create mode 100644 tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_14.txt create mode 100644 tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_15.txt create mode 100644 tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_16.txt create mode 100644 tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_17.txt create mode 100644 tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_18.txt create mode 100644 tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_2.txt create mode 100644 tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_3.txt create mode 100644 tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_4.txt create mode 100644 tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_5.txt create mode 100644 tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_6.txt create mode 100644 tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_7.txt create mode 100644 tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_8.txt create mode 100644 tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_9.txt create mode 100644 tests/workloads/join_type_grid/MI200/perfmon/timestamps.txt create mode 100644 tests/workloads/join_type_grid/MI200/pmc_perf.csv create mode 100644 tests/workloads/join_type_grid/MI200/roofline.csv create mode 100644 tests/workloads/join_type_grid/MI200/sysinfo.csv create mode 100644 tests/workloads/join_type_grid/MI200/timestamps.csv create mode 100644 tests/workloads/join_type_kernel/MI100/pmc_dispatch_info.csv create mode 100644 tests/workloads/join_type_kernel/MI200/SQ_IFETCH_LEVEL.csv create mode 100644 tests/workloads/join_type_kernel/MI200/SQ_INST_LEVEL_LDS.csv create mode 100644 tests/workloads/join_type_kernel/MI200/SQ_INST_LEVEL_SMEM.csv create mode 100644 tests/workloads/join_type_kernel/MI200/SQ_INST_LEVEL_VMEM.csv create mode 100644 tests/workloads/join_type_kernel/MI200/SQ_LEVEL_WAVES.csv create mode 100644 tests/workloads/join_type_kernel/MI200/perfmon/SQ_IFETCH_LEVEL.txt create mode 100644 tests/workloads/join_type_kernel/MI200/perfmon/SQ_INST_LEVEL_LDS.txt create mode 100644 tests/workloads/join_type_kernel/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt create mode 100644 tests/workloads/join_type_kernel/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt create mode 100644 tests/workloads/join_type_kernel/MI200/perfmon/SQ_LEVEL_WAVES.txt create mode 100644 tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_0.txt create mode 100644 tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_1.txt create mode 100644 tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_10.txt create mode 100644 tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_11.txt create mode 100644 tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_12.txt create mode 100644 tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_13.txt create mode 100644 tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_14.txt create mode 100644 tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_15.txt create mode 100644 tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_16.txt create mode 100644 tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_17.txt create mode 100644 tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_18.txt create mode 100644 tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_2.txt create mode 100644 tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_3.txt create mode 100644 tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_4.txt create mode 100644 tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_5.txt create mode 100644 tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_6.txt create mode 100644 tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_7.txt create mode 100644 tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_8.txt create mode 100644 tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_9.txt create mode 100644 tests/workloads/join_type_kernel/MI200/perfmon/timestamps.txt create mode 100644 tests/workloads/join_type_kernel/MI200/pmc_perf.csv create mode 100644 tests/workloads/join_type_kernel/MI200/roofline.csv create mode 100644 tests/workloads/join_type_kernel/MI200/sysinfo.csv create mode 100644 tests/workloads/join_type_kernel/MI200/timestamps.csv rename tests/workloads/kernel/MI100/{pmc_perf_16.csv => SQ_IFETCH_LEVEL.csv} (100%) create mode 100644 tests/workloads/kernel/MI200/SQ_IFETCH_LEVEL.csv create mode 100644 tests/workloads/kernel/MI200/perfmon/SQ_IFETCH_LEVEL.txt create mode 100644 tests/workloads/kernel/MI200/perfmon/SQ_INST_LEVEL_LDS.txt create mode 100644 tests/workloads/kernel/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt create mode 100644 tests/workloads/kernel/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt create mode 100644 tests/workloads/kernel/MI200/perfmon/SQ_LEVEL_WAVES.txt create mode 100644 tests/workloads/kernel/MI200/perfmon/pmc_perf_0.txt create mode 100644 tests/workloads/kernel/MI200/perfmon/pmc_perf_1.txt create mode 100644 tests/workloads/kernel/MI200/perfmon/pmc_perf_10.txt create mode 100644 tests/workloads/kernel/MI200/perfmon/pmc_perf_11.txt create mode 100644 tests/workloads/kernel/MI200/perfmon/pmc_perf_12.txt create mode 100644 tests/workloads/kernel/MI200/perfmon/pmc_perf_13.txt create mode 100644 tests/workloads/kernel/MI200/perfmon/pmc_perf_14.txt create mode 100644 tests/workloads/kernel/MI200/perfmon/pmc_perf_15.txt create mode 100644 tests/workloads/kernel/MI200/perfmon/pmc_perf_16.txt create mode 100644 tests/workloads/kernel/MI200/perfmon/pmc_perf_17.txt create mode 100644 tests/workloads/kernel/MI200/perfmon/pmc_perf_18.txt create mode 100644 tests/workloads/kernel/MI200/perfmon/pmc_perf_2.txt create mode 100644 tests/workloads/kernel/MI200/perfmon/pmc_perf_3.txt create mode 100644 tests/workloads/kernel/MI200/perfmon/pmc_perf_4.txt create mode 100644 tests/workloads/kernel/MI200/perfmon/pmc_perf_5.txt create mode 100644 tests/workloads/kernel/MI200/perfmon/pmc_perf_6.txt create mode 100644 tests/workloads/kernel/MI200/perfmon/pmc_perf_7.txt create mode 100644 tests/workloads/kernel/MI200/perfmon/pmc_perf_8.txt create mode 100644 tests/workloads/kernel/MI200/perfmon/pmc_perf_9.txt create mode 100644 tests/workloads/kernel/MI200/perfmon/timestamps.txt create mode 100644 tests/workloads/kernel_inv_int/MI200/SQ_IFETCH_LEVEL.csv create mode 100644 tests/workloads/kernel_inv_int/MI200/SQ_INST_LEVEL_LDS.csv create mode 100644 tests/workloads/kernel_inv_int/MI200/SQ_INST_LEVEL_SMEM.csv create mode 100644 tests/workloads/kernel_inv_int/MI200/SQ_INST_LEVEL_VMEM.csv create mode 100644 tests/workloads/kernel_inv_int/MI200/SQ_LEVEL_WAVES.csv create mode 100644 tests/workloads/kernel_inv_int/MI200/perfmon/SQ_IFETCH_LEVEL.txt create mode 100644 tests/workloads/kernel_inv_int/MI200/perfmon/SQ_INST_LEVEL_LDS.txt create mode 100644 tests/workloads/kernel_inv_int/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt create mode 100644 tests/workloads/kernel_inv_int/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt create mode 100644 tests/workloads/kernel_inv_int/MI200/perfmon/SQ_LEVEL_WAVES.txt create mode 100644 tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_0.txt create mode 100644 tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_1.txt create mode 100644 tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_10.txt create mode 100644 tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_11.txt create mode 100644 tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_12.txt create mode 100644 tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_13.txt create mode 100644 tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_14.txt create mode 100644 tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_15.txt create mode 100644 tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_16.txt create mode 100644 tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_17.txt create mode 100644 tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_18.txt create mode 100644 tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_2.txt create mode 100644 tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_3.txt create mode 100644 tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_4.txt create mode 100644 tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_5.txt create mode 100644 tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_6.txt create mode 100644 tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_7.txt create mode 100644 tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_8.txt create mode 100644 tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_9.txt create mode 100644 tests/workloads/kernel_inv_int/MI200/perfmon/timestamps.txt create mode 100644 tests/workloads/kernel_inv_int/MI200/pmc_perf_0.csv create mode 100644 tests/workloads/kernel_inv_int/MI200/pmc_perf_1.csv create mode 100644 tests/workloads/kernel_inv_int/MI200/pmc_perf_10.csv create mode 100644 tests/workloads/kernel_inv_int/MI200/pmc_perf_11.csv create mode 100644 tests/workloads/kernel_inv_int/MI200/pmc_perf_12.csv create mode 100644 tests/workloads/kernel_inv_int/MI200/pmc_perf_13.csv create mode 100644 tests/workloads/kernel_inv_int/MI200/pmc_perf_14.csv create mode 100644 tests/workloads/kernel_inv_int/MI200/pmc_perf_15.csv create mode 100644 tests/workloads/kernel_inv_int/MI200/pmc_perf_16.csv create mode 100644 tests/workloads/kernel_inv_int/MI200/pmc_perf_17.csv create mode 100644 tests/workloads/kernel_inv_int/MI200/pmc_perf_18.csv create mode 100644 tests/workloads/kernel_inv_int/MI200/pmc_perf_2.csv create mode 100644 tests/workloads/kernel_inv_int/MI200/pmc_perf_3.csv create mode 100644 tests/workloads/kernel_inv_int/MI200/pmc_perf_4.csv create mode 100644 tests/workloads/kernel_inv_int/MI200/pmc_perf_5.csv create mode 100644 tests/workloads/kernel_inv_int/MI200/pmc_perf_6.csv create mode 100644 tests/workloads/kernel_inv_int/MI200/pmc_perf_7.csv create mode 100644 tests/workloads/kernel_inv_int/MI200/pmc_perf_8.csv create mode 100644 tests/workloads/kernel_inv_int/MI200/pmc_perf_9.csv create mode 100644 tests/workloads/kernel_inv_int/MI200/sysinfo.csv create mode 100644 tests/workloads/kernel_inv_int/MI200/timestamps.csv create mode 100644 tests/workloads/kernel_inv_str/MI200/SQ_IFETCH_LEVEL.csv create mode 100644 tests/workloads/kernel_inv_str/MI200/SQ_INST_LEVEL_LDS.csv create mode 100644 tests/workloads/kernel_inv_str/MI200/SQ_INST_LEVEL_SMEM.csv create mode 100644 tests/workloads/kernel_inv_str/MI200/SQ_INST_LEVEL_VMEM.csv create mode 100644 tests/workloads/kernel_inv_str/MI200/SQ_LEVEL_WAVES.csv create mode 100644 tests/workloads/kernel_inv_str/MI200/perfmon/SQ_IFETCH_LEVEL.txt create mode 100644 tests/workloads/kernel_inv_str/MI200/perfmon/SQ_INST_LEVEL_LDS.txt create mode 100644 tests/workloads/kernel_inv_str/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt create mode 100644 tests/workloads/kernel_inv_str/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt create mode 100644 tests/workloads/kernel_inv_str/MI200/perfmon/SQ_LEVEL_WAVES.txt create mode 100644 tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_0.txt create mode 100644 tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_1.txt create mode 100644 tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_10.txt create mode 100644 tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_11.txt create mode 100644 tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_12.txt create mode 100644 tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_13.txt create mode 100644 tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_14.txt create mode 100644 tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_15.txt create mode 100644 tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_16.txt create mode 100644 tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_17.txt create mode 100644 tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_18.txt create mode 100644 tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_2.txt create mode 100644 tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_3.txt create mode 100644 tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_4.txt create mode 100644 tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_5.txt create mode 100644 tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_6.txt create mode 100644 tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_7.txt create mode 100644 tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_8.txt create mode 100644 tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_9.txt create mode 100644 tests/workloads/kernel_inv_str/MI200/perfmon/timestamps.txt create mode 100644 tests/workloads/kernel_inv_str/MI200/pmc_perf_0.csv create mode 100644 tests/workloads/kernel_inv_str/MI200/pmc_perf_1.csv create mode 100644 tests/workloads/kernel_inv_str/MI200/pmc_perf_10.csv create mode 100644 tests/workloads/kernel_inv_str/MI200/pmc_perf_11.csv create mode 100644 tests/workloads/kernel_inv_str/MI200/pmc_perf_12.csv create mode 100644 tests/workloads/kernel_inv_str/MI200/pmc_perf_13.csv create mode 100644 tests/workloads/kernel_inv_str/MI200/pmc_perf_14.csv create mode 100644 tests/workloads/kernel_inv_str/MI200/pmc_perf_15.csv create mode 100644 tests/workloads/kernel_inv_str/MI200/pmc_perf_16.csv create mode 100644 tests/workloads/kernel_inv_str/MI200/pmc_perf_17.csv create mode 100644 tests/workloads/kernel_inv_str/MI200/pmc_perf_18.csv create mode 100644 tests/workloads/kernel_inv_str/MI200/pmc_perf_2.csv create mode 100644 tests/workloads/kernel_inv_str/MI200/pmc_perf_3.csv create mode 100644 tests/workloads/kernel_inv_str/MI200/pmc_perf_4.csv create mode 100644 tests/workloads/kernel_inv_str/MI200/pmc_perf_5.csv create mode 100644 tests/workloads/kernel_inv_str/MI200/pmc_perf_6.csv create mode 100644 tests/workloads/kernel_inv_str/MI200/pmc_perf_7.csv create mode 100644 tests/workloads/kernel_inv_str/MI200/pmc_perf_8.csv create mode 100644 tests/workloads/kernel_inv_str/MI200/pmc_perf_9.csv create mode 100644 tests/workloads/kernel_inv_str/MI200/sysinfo.csv create mode 100644 tests/workloads/kernel_inv_str/MI200/timestamps.csv create mode 100644 tests/workloads/kernel_names/MI200/empirRoof_gpu-0_fp32.pdf create mode 100644 tests/workloads/kernel_names/MI200/empirRoof_gpu-0_int8_fp16.pdf create mode 100644 tests/workloads/kernel_names/MI200/kernelName_legend.pdf create mode 100644 tests/workloads/kernel_names/MI200/perfmon/pmc_perf_0.txt create mode 100644 tests/workloads/kernel_names/MI200/perfmon/pmc_perf_1.txt create mode 100644 tests/workloads/kernel_names/MI200/perfmon/pmc_perf_2.txt create mode 100644 tests/workloads/kernel_names/MI200/perfmon/timestamps.txt create mode 100644 tests/workloads/kernel_names/MI200/pmc_perf.csv create mode 100644 tests/workloads/kernel_names/MI200/roofline.csv create mode 100644 tests/workloads/kernel_names/MI200/sysinfo.csv create mode 100644 tests/workloads/kernel_names/MI200/timestamps.csv create mode 100644 tests/workloads/kernel_substr/MI100/pmc_dispatch_info.csv create mode 100644 tests/workloads/kernel_substr/MI200/SQ_IFETCH_LEVEL.csv create mode 100644 tests/workloads/kernel_substr/MI200/SQ_INST_LEVEL_LDS.csv create mode 100644 tests/workloads/kernel_substr/MI200/SQ_INST_LEVEL_SMEM.csv create mode 100644 tests/workloads/kernel_substr/MI200/SQ_INST_LEVEL_VMEM.csv create mode 100644 tests/workloads/kernel_substr/MI200/SQ_LEVEL_WAVES.csv create mode 100644 tests/workloads/kernel_substr/MI200/perfmon/SQ_IFETCH_LEVEL.txt create mode 100644 tests/workloads/kernel_substr/MI200/perfmon/SQ_INST_LEVEL_LDS.txt create mode 100644 tests/workloads/kernel_substr/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt create mode 100644 tests/workloads/kernel_substr/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt create mode 100644 tests/workloads/kernel_substr/MI200/perfmon/SQ_LEVEL_WAVES.txt create mode 100644 tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_0.txt create mode 100644 tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_1.txt create mode 100644 tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_10.txt create mode 100644 tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_11.txt create mode 100644 tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_12.txt create mode 100644 tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_13.txt create mode 100644 tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_14.txt create mode 100644 tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_15.txt create mode 100644 tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_16.txt create mode 100644 tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_17.txt create mode 100644 tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_18.txt create mode 100644 tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_2.txt create mode 100644 tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_3.txt create mode 100644 tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_4.txt create mode 100644 tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_5.txt create mode 100644 tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_6.txt create mode 100644 tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_7.txt create mode 100644 tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_8.txt create mode 100644 tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_9.txt create mode 100644 tests/workloads/kernel_substr/MI200/perfmon/timestamps.txt create mode 100644 tests/workloads/kernel_substr/MI200/pmc_perf.csv create mode 100644 tests/workloads/kernel_substr/MI200/roofline.csv create mode 100644 tests/workloads/kernel_substr/MI200/sysinfo.csv create mode 100644 tests/workloads/kernel_substr/MI200/timestamps.csv create mode 100644 tests/workloads/kernel_summaries/MI100/pmc_dispatch_info.csv create mode 100644 tests/workloads/kernel_summaries/MI200/SQ_IFETCH_LEVEL.csv create mode 100644 tests/workloads/kernel_summaries/MI200/SQ_INST_LEVEL_LDS.csv create mode 100644 tests/workloads/kernel_summaries/MI200/SQ_INST_LEVEL_SMEM.csv create mode 100644 tests/workloads/kernel_summaries/MI200/SQ_INST_LEVEL_VMEM.csv create mode 100644 tests/workloads/kernel_summaries/MI200/SQ_LEVEL_WAVES.csv create mode 100644 tests/workloads/kernel_summaries/MI200/perfmon/SQ_IFETCH_LEVEL.txt create mode 100644 tests/workloads/kernel_summaries/MI200/perfmon/SQ_INST_LEVEL_LDS.txt create mode 100644 tests/workloads/kernel_summaries/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt create mode 100644 tests/workloads/kernel_summaries/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt create mode 100644 tests/workloads/kernel_summaries/MI200/perfmon/SQ_LEVEL_WAVES.txt create mode 100644 tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_0.txt create mode 100644 tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_1.txt create mode 100644 tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_10.txt create mode 100644 tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_11.txt create mode 100644 tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_12.txt create mode 100644 tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_13.txt create mode 100644 tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_14.txt create mode 100644 tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_15.txt create mode 100644 tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_16.txt create mode 100644 tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_17.txt create mode 100644 tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_18.txt create mode 100644 tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_2.txt create mode 100644 tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_3.txt create mode 100644 tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_4.txt create mode 100644 tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_5.txt create mode 100644 tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_6.txt create mode 100644 tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_7.txt create mode 100644 tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_8.txt create mode 100644 tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_9.txt create mode 100644 tests/workloads/kernel_summaries/MI200/perfmon/timestamps.txt create mode 100644 tests/workloads/kernel_summaries/MI200/pmc_perf.csv create mode 100644 tests/workloads/kernel_summaries/MI200/roofline.csv create mode 100644 tests/workloads/kernel_summaries/MI200/sysinfo.csv create mode 100644 tests/workloads/kernel_summaries/MI200/timestamps.csv create mode 100644 tests/workloads/kernel_verbose_0/MI100/pmc_dispatch_info.csv create mode 100644 tests/workloads/kernel_verbose_0/MI200/SQ_IFETCH_LEVEL.csv create mode 100644 tests/workloads/kernel_verbose_0/MI200/SQ_INST_LEVEL_LDS.csv create mode 100644 tests/workloads/kernel_verbose_0/MI200/SQ_INST_LEVEL_SMEM.csv create mode 100644 tests/workloads/kernel_verbose_0/MI200/SQ_INST_LEVEL_VMEM.csv create mode 100644 tests/workloads/kernel_verbose_0/MI200/SQ_LEVEL_WAVES.csv create mode 100644 tests/workloads/kernel_verbose_0/MI200/perfmon/SQ_IFETCH_LEVEL.txt create mode 100644 tests/workloads/kernel_verbose_0/MI200/perfmon/SQ_INST_LEVEL_LDS.txt create mode 100644 tests/workloads/kernel_verbose_0/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt create mode 100644 tests/workloads/kernel_verbose_0/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt create mode 100644 tests/workloads/kernel_verbose_0/MI200/perfmon/SQ_LEVEL_WAVES.txt create mode 100644 tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_0.txt create mode 100644 tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_1.txt create mode 100644 tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_10.txt create mode 100644 tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_11.txt create mode 100644 tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_12.txt create mode 100644 tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_13.txt create mode 100644 tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_14.txt create mode 100644 tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_15.txt create mode 100644 tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_16.txt create mode 100644 tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_17.txt create mode 100644 tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_18.txt create mode 100644 tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_2.txt create mode 100644 tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_3.txt create mode 100644 tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_4.txt create mode 100644 tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_5.txt create mode 100644 tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_6.txt create mode 100644 tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_7.txt create mode 100644 tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_8.txt create mode 100644 tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_9.txt create mode 100644 tests/workloads/kernel_verbose_0/MI200/perfmon/timestamps.txt create mode 100644 tests/workloads/kernel_verbose_0/MI200/pmc_perf.csv create mode 100644 tests/workloads/kernel_verbose_0/MI200/roofline.csv create mode 100644 tests/workloads/kernel_verbose_0/MI200/sysinfo.csv create mode 100644 tests/workloads/kernel_verbose_0/MI200/timestamps.csv create mode 100644 tests/workloads/kernel_verbose_1/MI100/pmc_dispatch_info.csv create mode 100644 tests/workloads/kernel_verbose_1/MI200/SQ_IFETCH_LEVEL.csv create mode 100644 tests/workloads/kernel_verbose_1/MI200/SQ_INST_LEVEL_LDS.csv create mode 100644 tests/workloads/kernel_verbose_1/MI200/SQ_INST_LEVEL_SMEM.csv create mode 100644 tests/workloads/kernel_verbose_1/MI200/SQ_INST_LEVEL_VMEM.csv create mode 100644 tests/workloads/kernel_verbose_1/MI200/SQ_LEVEL_WAVES.csv create mode 100644 tests/workloads/kernel_verbose_1/MI200/perfmon/SQ_IFETCH_LEVEL.txt create mode 100644 tests/workloads/kernel_verbose_1/MI200/perfmon/SQ_INST_LEVEL_LDS.txt create mode 100644 tests/workloads/kernel_verbose_1/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt create mode 100644 tests/workloads/kernel_verbose_1/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt create mode 100644 tests/workloads/kernel_verbose_1/MI200/perfmon/SQ_LEVEL_WAVES.txt create mode 100644 tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_0.txt create mode 100644 tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_1.txt create mode 100644 tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_10.txt create mode 100644 tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_11.txt create mode 100644 tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_12.txt create mode 100644 tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_13.txt create mode 100644 tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_14.txt create mode 100644 tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_15.txt create mode 100644 tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_16.txt create mode 100644 tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_17.txt create mode 100644 tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_18.txt create mode 100644 tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_2.txt create mode 100644 tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_3.txt create mode 100644 tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_4.txt create mode 100644 tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_5.txt create mode 100644 tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_6.txt create mode 100644 tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_7.txt create mode 100644 tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_8.txt create mode 100644 tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_9.txt create mode 100644 tests/workloads/kernel_verbose_1/MI200/perfmon/timestamps.txt create mode 100644 tests/workloads/kernel_verbose_1/MI200/pmc_perf.csv create mode 100644 tests/workloads/kernel_verbose_1/MI200/roofline.csv create mode 100644 tests/workloads/kernel_verbose_1/MI200/sysinfo.csv create mode 100644 tests/workloads/kernel_verbose_1/MI200/timestamps.csv create mode 100644 tests/workloads/kernel_verbose_2/MI100/pmc_dispatch_info.csv create mode 100644 tests/workloads/kernel_verbose_2/MI200/SQ_IFETCH_LEVEL.csv create mode 100644 tests/workloads/kernel_verbose_2/MI200/SQ_INST_LEVEL_LDS.csv create mode 100644 tests/workloads/kernel_verbose_2/MI200/SQ_INST_LEVEL_SMEM.csv create mode 100644 tests/workloads/kernel_verbose_2/MI200/SQ_INST_LEVEL_VMEM.csv create mode 100644 tests/workloads/kernel_verbose_2/MI200/SQ_LEVEL_WAVES.csv create mode 100644 tests/workloads/kernel_verbose_2/MI200/perfmon/SQ_IFETCH_LEVEL.txt create mode 100644 tests/workloads/kernel_verbose_2/MI200/perfmon/SQ_INST_LEVEL_LDS.txt create mode 100644 tests/workloads/kernel_verbose_2/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt create mode 100644 tests/workloads/kernel_verbose_2/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt create mode 100644 tests/workloads/kernel_verbose_2/MI200/perfmon/SQ_LEVEL_WAVES.txt create mode 100644 tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_0.txt create mode 100644 tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_1.txt create mode 100644 tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_10.txt create mode 100644 tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_11.txt create mode 100644 tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_12.txt create mode 100644 tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_13.txt create mode 100644 tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_14.txt create mode 100644 tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_15.txt create mode 100644 tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_16.txt create mode 100644 tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_17.txt create mode 100644 tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_18.txt create mode 100644 tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_2.txt create mode 100644 tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_3.txt create mode 100644 tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_4.txt create mode 100644 tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_5.txt create mode 100644 tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_6.txt create mode 100644 tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_7.txt create mode 100644 tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_8.txt create mode 100644 tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_9.txt create mode 100644 tests/workloads/kernel_verbose_2/MI200/perfmon/timestamps.txt create mode 100644 tests/workloads/kernel_verbose_2/MI200/pmc_perf.csv create mode 100644 tests/workloads/kernel_verbose_2/MI200/roofline.csv create mode 100644 tests/workloads/kernel_verbose_2/MI200/sysinfo.csv create mode 100644 tests/workloads/kernel_verbose_2/MI200/timestamps.csv create mode 100644 tests/workloads/kernel_verbose_3/MI100/pmc_dispatch_info.csv create mode 100644 tests/workloads/kernel_verbose_3/MI200/SQ_IFETCH_LEVEL.csv create mode 100644 tests/workloads/kernel_verbose_3/MI200/SQ_INST_LEVEL_LDS.csv create mode 100644 tests/workloads/kernel_verbose_3/MI200/SQ_INST_LEVEL_SMEM.csv create mode 100644 tests/workloads/kernel_verbose_3/MI200/SQ_INST_LEVEL_VMEM.csv create mode 100644 tests/workloads/kernel_verbose_3/MI200/SQ_LEVEL_WAVES.csv create mode 100644 tests/workloads/kernel_verbose_3/MI200/perfmon/SQ_IFETCH_LEVEL.txt create mode 100644 tests/workloads/kernel_verbose_3/MI200/perfmon/SQ_INST_LEVEL_LDS.txt create mode 100644 tests/workloads/kernel_verbose_3/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt create mode 100644 tests/workloads/kernel_verbose_3/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt create mode 100644 tests/workloads/kernel_verbose_3/MI200/perfmon/SQ_LEVEL_WAVES.txt create mode 100644 tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_0.txt create mode 100644 tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_1.txt create mode 100644 tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_10.txt create mode 100644 tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_11.txt create mode 100644 tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_12.txt create mode 100644 tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_13.txt create mode 100644 tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_14.txt create mode 100644 tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_15.txt create mode 100644 tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_16.txt create mode 100644 tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_17.txt create mode 100644 tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_18.txt create mode 100644 tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_2.txt create mode 100644 tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_3.txt create mode 100644 tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_4.txt create mode 100644 tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_5.txt create mode 100644 tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_6.txt create mode 100644 tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_7.txt create mode 100644 tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_8.txt create mode 100644 tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_9.txt create mode 100644 tests/workloads/kernel_verbose_3/MI200/perfmon/timestamps.txt create mode 100644 tests/workloads/kernel_verbose_3/MI200/pmc_perf.csv create mode 100644 tests/workloads/kernel_verbose_3/MI200/roofline.csv create mode 100644 tests/workloads/kernel_verbose_3/MI200/sysinfo.csv create mode 100644 tests/workloads/kernel_verbose_3/MI200/timestamps.csv create mode 100644 tests/workloads/kernel_verbose_4/MI100/pmc_dispatch_info.csv create mode 100644 tests/workloads/kernel_verbose_4/MI200/SQ_IFETCH_LEVEL.csv create mode 100644 tests/workloads/kernel_verbose_4/MI200/SQ_INST_LEVEL_LDS.csv create mode 100644 tests/workloads/kernel_verbose_4/MI200/SQ_INST_LEVEL_SMEM.csv create mode 100644 tests/workloads/kernel_verbose_4/MI200/SQ_INST_LEVEL_VMEM.csv create mode 100644 tests/workloads/kernel_verbose_4/MI200/SQ_LEVEL_WAVES.csv create mode 100644 tests/workloads/kernel_verbose_4/MI200/perfmon/SQ_IFETCH_LEVEL.txt create mode 100644 tests/workloads/kernel_verbose_4/MI200/perfmon/SQ_INST_LEVEL_LDS.txt create mode 100644 tests/workloads/kernel_verbose_4/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt create mode 100644 tests/workloads/kernel_verbose_4/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt create mode 100644 tests/workloads/kernel_verbose_4/MI200/perfmon/SQ_LEVEL_WAVES.txt create mode 100644 tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_0.txt create mode 100644 tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_1.txt create mode 100644 tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_10.txt create mode 100644 tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_11.txt create mode 100644 tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_12.txt create mode 100644 tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_13.txt create mode 100644 tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_14.txt create mode 100644 tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_15.txt create mode 100644 tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_16.txt create mode 100644 tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_17.txt create mode 100644 tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_18.txt create mode 100644 tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_2.txt create mode 100644 tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_3.txt create mode 100644 tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_4.txt create mode 100644 tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_5.txt create mode 100644 tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_6.txt create mode 100644 tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_7.txt create mode 100644 tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_8.txt create mode 100644 tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_9.txt create mode 100644 tests/workloads/kernel_verbose_4/MI200/perfmon/timestamps.txt create mode 100644 tests/workloads/kernel_verbose_4/MI200/pmc_perf.csv create mode 100644 tests/workloads/kernel_verbose_4/MI200/roofline.csv create mode 100644 tests/workloads/kernel_verbose_4/MI200/sysinfo.csv create mode 100644 tests/workloads/kernel_verbose_4/MI200/timestamps.csv create mode 100644 tests/workloads/kernel_verbose_5/MI100/pmc_dispatch_info.csv create mode 100644 tests/workloads/kernel_verbose_5/MI200/SQ_IFETCH_LEVEL.csv create mode 100644 tests/workloads/kernel_verbose_5/MI200/SQ_INST_LEVEL_LDS.csv create mode 100644 tests/workloads/kernel_verbose_5/MI200/SQ_INST_LEVEL_SMEM.csv create mode 100644 tests/workloads/kernel_verbose_5/MI200/SQ_INST_LEVEL_VMEM.csv create mode 100644 tests/workloads/kernel_verbose_5/MI200/SQ_LEVEL_WAVES.csv create mode 100644 tests/workloads/kernel_verbose_5/MI200/perfmon/SQ_IFETCH_LEVEL.txt create mode 100644 tests/workloads/kernel_verbose_5/MI200/perfmon/SQ_INST_LEVEL_LDS.txt create mode 100644 tests/workloads/kernel_verbose_5/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt create mode 100644 tests/workloads/kernel_verbose_5/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt create mode 100644 tests/workloads/kernel_verbose_5/MI200/perfmon/SQ_LEVEL_WAVES.txt create mode 100644 tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_0.txt create mode 100644 tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_1.txt create mode 100644 tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_10.txt create mode 100644 tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_11.txt create mode 100644 tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_12.txt create mode 100644 tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_13.txt create mode 100644 tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_14.txt create mode 100644 tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_15.txt create mode 100644 tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_16.txt create mode 100644 tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_17.txt create mode 100644 tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_18.txt create mode 100644 tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_2.txt create mode 100644 tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_3.txt create mode 100644 tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_4.txt create mode 100644 tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_5.txt create mode 100644 tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_6.txt create mode 100644 tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_7.txt create mode 100644 tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_8.txt create mode 100644 tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_9.txt create mode 100644 tests/workloads/kernel_verbose_5/MI200/perfmon/timestamps.txt create mode 100644 tests/workloads/kernel_verbose_5/MI200/pmc_perf.csv create mode 100644 tests/workloads/kernel_verbose_5/MI200/roofline.csv create mode 100644 tests/workloads/kernel_verbose_5/MI200/sysinfo.csv create mode 100644 tests/workloads/kernel_verbose_5/MI200/timestamps.csv create mode 100644 tests/workloads/mem_levels_HBM/MI200/empirRoof_gpu-0_fp32.pdf create mode 100644 tests/workloads/mem_levels_HBM/MI200/empirRoof_gpu-0_int8_fp16.pdf create mode 100644 tests/workloads/mem_levels_HBM/MI200/perfmon/pmc_perf_0.txt create mode 100644 tests/workloads/mem_levels_HBM/MI200/perfmon/pmc_perf_1.txt create mode 100644 tests/workloads/mem_levels_HBM/MI200/perfmon/pmc_perf_2.txt create mode 100644 tests/workloads/mem_levels_HBM/MI200/perfmon/timestamps.txt create mode 100644 tests/workloads/mem_levels_HBM/MI200/pmc_perf.csv create mode 100644 tests/workloads/mem_levels_HBM/MI200/roofline.csv create mode 100644 tests/workloads/mem_levels_HBM/MI200/sysinfo.csv create mode 100644 tests/workloads/mem_levels_HBM/MI200/timestamps.csv create mode 100644 tests/workloads/mem_levels_HBM_LDS/MI100/perfmon/pmc_perf_0.txt create mode 100644 tests/workloads/mem_levels_HBM_LDS/MI100/perfmon/pmc_perf_1.txt create mode 100644 tests/workloads/mem_levels_HBM_LDS/MI100/perfmon/pmc_perf_2.txt create mode 100644 tests/workloads/mem_levels_HBM_LDS/MI100/perfmon/timestamps.txt create mode 100644 tests/workloads/mem_levels_HBM_LDS/MI200/empirRoof_gpu-0_fp32.pdf create mode 100644 tests/workloads/mem_levels_HBM_LDS/MI200/empirRoof_gpu-0_int8_fp16.pdf create mode 100644 tests/workloads/mem_levels_HBM_LDS/MI200/perfmon/pmc_perf_0.txt create mode 100644 tests/workloads/mem_levels_HBM_LDS/MI200/perfmon/pmc_perf_1.txt create mode 100644 tests/workloads/mem_levels_HBM_LDS/MI200/perfmon/pmc_perf_2.txt create mode 100644 tests/workloads/mem_levels_HBM_LDS/MI200/perfmon/timestamps.txt create mode 100644 tests/workloads/mem_levels_HBM_LDS/MI200/pmc_perf.csv create mode 100644 tests/workloads/mem_levels_HBM_LDS/MI200/roofline.csv create mode 100644 tests/workloads/mem_levels_HBM_LDS/MI200/sysinfo.csv create mode 100644 tests/workloads/mem_levels_HBM_LDS/MI200/timestamps.csv create mode 100644 tests/workloads/mem_levels_L2/MI200/empirRoof_gpu-0_fp32.pdf create mode 100644 tests/workloads/mem_levels_L2/MI200/empirRoof_gpu-0_int8_fp16.pdf create mode 100644 tests/workloads/mem_levels_L2/MI200/perfmon/pmc_perf_0.txt create mode 100644 tests/workloads/mem_levels_L2/MI200/perfmon/pmc_perf_1.txt create mode 100644 tests/workloads/mem_levels_L2/MI200/perfmon/pmc_perf_2.txt create mode 100644 tests/workloads/mem_levels_L2/MI200/perfmon/timestamps.txt create mode 100644 tests/workloads/mem_levels_L2/MI200/pmc_perf.csv create mode 100644 tests/workloads/mem_levels_L2/MI200/roofline.csv create mode 100644 tests/workloads/mem_levels_L2/MI200/sysinfo.csv create mode 100644 tests/workloads/mem_levels_L2/MI200/timestamps.csv create mode 100644 tests/workloads/mem_levels_L2_vL1d_LDS/MI200/empirRoof_gpu-0_fp32.pdf create mode 100644 tests/workloads/mem_levels_L2_vL1d_LDS/MI200/empirRoof_gpu-0_int8_fp16.pdf create mode 100644 tests/workloads/mem_levels_L2_vL1d_LDS/MI200/perfmon/pmc_perf_0.txt create mode 100644 tests/workloads/mem_levels_L2_vL1d_LDS/MI200/perfmon/pmc_perf_1.txt create mode 100644 tests/workloads/mem_levels_L2_vL1d_LDS/MI200/perfmon/pmc_perf_2.txt create mode 100644 tests/workloads/mem_levels_L2_vL1d_LDS/MI200/perfmon/timestamps.txt create mode 100644 tests/workloads/mem_levels_L2_vL1d_LDS/MI200/pmc_perf.csv create mode 100644 tests/workloads/mem_levels_L2_vL1d_LDS/MI200/roofline.csv create mode 100644 tests/workloads/mem_levels_L2_vL1d_LDS/MI200/sysinfo.csv create mode 100644 tests/workloads/mem_levels_L2_vL1d_LDS/MI200/timestamps.csv create mode 100644 tests/workloads/mem_levels_LDS/MI200/empirRoof_gpu-0_fp32.pdf create mode 100644 tests/workloads/mem_levels_LDS/MI200/empirRoof_gpu-0_int8_fp16.pdf create mode 100644 tests/workloads/mem_levels_LDS/MI200/perfmon/pmc_perf_0.txt create mode 100644 tests/workloads/mem_levels_LDS/MI200/perfmon/pmc_perf_1.txt create mode 100644 tests/workloads/mem_levels_LDS/MI200/perfmon/pmc_perf_2.txt create mode 100644 tests/workloads/mem_levels_LDS/MI200/perfmon/timestamps.txt create mode 100644 tests/workloads/mem_levels_LDS/MI200/pmc_perf.csv create mode 100644 tests/workloads/mem_levels_LDS/MI200/roofline.csv create mode 100644 tests/workloads/mem_levels_LDS/MI200/sysinfo.csv create mode 100644 tests/workloads/mem_levels_LDS/MI200/timestamps.csv create mode 100644 tests/workloads/mem_levels_vL1D/MI200/empirRoof_gpu-0_fp32.pdf create mode 100644 tests/workloads/mem_levels_vL1D/MI200/empirRoof_gpu-0_int8_fp16.pdf create mode 100644 tests/workloads/mem_levels_vL1D/MI200/perfmon/pmc_perf_0.txt create mode 100644 tests/workloads/mem_levels_vL1D/MI200/perfmon/pmc_perf_1.txt create mode 100644 tests/workloads/mem_levels_vL1D/MI200/perfmon/pmc_perf_2.txt create mode 100644 tests/workloads/mem_levels_vL1D/MI200/perfmon/timestamps.txt create mode 100644 tests/workloads/mem_levels_vL1D/MI200/pmc_perf.csv create mode 100644 tests/workloads/mem_levels_vL1D/MI200/roofline.csv create mode 100644 tests/workloads/mem_levels_vL1D/MI200/sysinfo.csv create mode 100644 tests/workloads/mem_levels_vL1D/MI200/timestamps.csv create mode 100644 tests/workloads/mem_levels_vL1d_LDS/MI200/empirRoof_gpu-0_fp32.pdf create mode 100644 tests/workloads/mem_levels_vL1d_LDS/MI200/empirRoof_gpu-0_int8_fp16.pdf create mode 100644 tests/workloads/mem_levels_vL1d_LDS/MI200/perfmon/pmc_perf_0.txt create mode 100644 tests/workloads/mem_levels_vL1d_LDS/MI200/perfmon/pmc_perf_1.txt create mode 100644 tests/workloads/mem_levels_vL1d_LDS/MI200/perfmon/pmc_perf_2.txt create mode 100644 tests/workloads/mem_levels_vL1d_LDS/MI200/perfmon/timestamps.txt create mode 100644 tests/workloads/mem_levels_vL1d_LDS/MI200/pmc_perf.csv create mode 100644 tests/workloads/mem_levels_vL1d_LDS/MI200/roofline.csv create mode 100644 tests/workloads/mem_levels_vL1d_LDS/MI200/sysinfo.csv create mode 100644 tests/workloads/mem_levels_vL1d_LDS/MI200/timestamps.csv create mode 100644 tests/workloads/no_roof/MI100/pmc_dispatch_info.csv create mode 100644 tests/workloads/path/MI100/pmc_dispatch_info.csv create mode 100644 tests/workloads/path/MI200/SQ_IFETCH_LEVEL.csv create mode 100644 tests/workloads/path/MI200/SQ_INST_LEVEL_LDS.csv create mode 100644 tests/workloads/path/MI200/SQ_INST_LEVEL_SMEM.csv create mode 100644 tests/workloads/path/MI200/SQ_INST_LEVEL_VMEM.csv create mode 100644 tests/workloads/path/MI200/SQ_LEVEL_WAVES.csv create mode 100644 tests/workloads/path/MI200/perfmon/SQ_IFETCH_LEVEL.txt create mode 100644 tests/workloads/path/MI200/perfmon/SQ_INST_LEVEL_LDS.txt create mode 100644 tests/workloads/path/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt create mode 100644 tests/workloads/path/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt create mode 100644 tests/workloads/path/MI200/perfmon/SQ_LEVEL_WAVES.txt create mode 100644 tests/workloads/path/MI200/perfmon/pmc_perf_0.txt create mode 100644 tests/workloads/path/MI200/perfmon/pmc_perf_1.txt create mode 100644 tests/workloads/path/MI200/perfmon/pmc_perf_10.txt create mode 100644 tests/workloads/path/MI200/perfmon/pmc_perf_11.txt create mode 100644 tests/workloads/path/MI200/perfmon/pmc_perf_12.txt create mode 100644 tests/workloads/path/MI200/perfmon/pmc_perf_13.txt create mode 100644 tests/workloads/path/MI200/perfmon/pmc_perf_14.txt create mode 100644 tests/workloads/path/MI200/perfmon/pmc_perf_15.txt create mode 100644 tests/workloads/path/MI200/perfmon/pmc_perf_16.txt create mode 100644 tests/workloads/path/MI200/perfmon/pmc_perf_17.txt create mode 100644 tests/workloads/path/MI200/perfmon/pmc_perf_18.txt create mode 100644 tests/workloads/path/MI200/perfmon/pmc_perf_2.txt create mode 100644 tests/workloads/path/MI200/perfmon/pmc_perf_3.txt create mode 100644 tests/workloads/path/MI200/perfmon/pmc_perf_4.txt create mode 100644 tests/workloads/path/MI200/perfmon/pmc_perf_5.txt create mode 100644 tests/workloads/path/MI200/perfmon/pmc_perf_6.txt create mode 100644 tests/workloads/path/MI200/perfmon/pmc_perf_7.txt create mode 100644 tests/workloads/path/MI200/perfmon/pmc_perf_8.txt create mode 100644 tests/workloads/path/MI200/perfmon/pmc_perf_9.txt create mode 100644 tests/workloads/path/MI200/perfmon/timestamps.txt create mode 100644 tests/workloads/path/MI200/pmc_perf.csv create mode 100644 tests/workloads/path/MI200/roofline.csv create mode 100644 tests/workloads/path/MI200/sysinfo.csv create mode 100644 tests/workloads/path/MI200/timestamps.csv create mode 100644 tests/workloads/sort_dispatches/MI200/empirRoof_gpu-0_fp32.pdf create mode 100644 tests/workloads/sort_dispatches/MI200/empirRoof_gpu-0_int8_fp16.pdf create mode 100644 tests/workloads/sort_dispatches/MI200/perfmon/pmc_perf_0.txt create mode 100644 tests/workloads/sort_dispatches/MI200/perfmon/pmc_perf_1.txt create mode 100644 tests/workloads/sort_dispatches/MI200/perfmon/pmc_perf_2.txt create mode 100644 tests/workloads/sort_dispatches/MI200/perfmon/timestamps.txt create mode 100644 tests/workloads/sort_dispatches/MI200/pmc_perf.csv create mode 100644 tests/workloads/sort_dispatches/MI200/roofline.csv create mode 100644 tests/workloads/sort_dispatches/MI200/sysinfo.csv create mode 100644 tests/workloads/sort_dispatches/MI200/timestamps.csv create mode 100644 tests/workloads/sort_kernels/MI200/empirRoof_gpu-0_fp32.pdf create mode 100644 tests/workloads/sort_kernels/MI200/empirRoof_gpu-0_int8_fp16.pdf create mode 100644 tests/workloads/sort_kernels/MI200/perfmon/pmc_perf_0.txt create mode 100644 tests/workloads/sort_kernels/MI200/perfmon/pmc_perf_1.txt create mode 100644 tests/workloads/sort_kernels/MI200/perfmon/pmc_perf_2.txt create mode 100644 tests/workloads/sort_kernels/MI200/perfmon/timestamps.txt create mode 100644 tests/workloads/sort_kernels/MI200/pmc_perf.csv create mode 100644 tests/workloads/sort_kernels/MI200/roofline.csv create mode 100644 tests/workloads/sort_kernels/MI200/sysinfo.csv create mode 100644 tests/workloads/sort_kernels/MI200/timestamps.csv create mode 100644 tests/workloads/vcopy/MI100/pmc_dispatch_info.csv create mode 100644 tests/workloads/vcopy/MI200/pmc_dispatch_info.csv diff --git a/tests/workloads/device_filter/MI100/SQ_IFETCH_LEVEL.csv b/tests/workloads/device_filter/MI100/SQ_IFETCH_LEVEL.csv index df28c8c9fc..5dfa84e3bc 100644 --- a/tests/workloads/device_filter/MI100/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/device_filter/MI100/SQ_IFETCH_LEVEL.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2869770,2869770,1048576,256,0,0,8,8,16,64,0x0,0x7eff6a3d2e80,48732,48732,16384,65536,12984,1684952,2187869534755189,2187863086843344,2187863086866864,2187869542260328 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2869770,2869770,1048576,256,0,0,8,8,16,64,0x0,0x7eff6a3d2e80,43698,43698,16384,65536,8101,1048580,2187869542283442,2187863086979504,2187863086998544,2187869542602320 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2869770,2869770,1048576,256,0,0,8,8,16,64,0x0,0x7eff6a3d2e80,42890,42890,16384,65536,8070,1048588,2187869542634450,2187863087020944,2187863087039824,2187869542818836 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,171832,171832,1048576,256,0,0,8,8,16,64,0x0,0x7f261105ce80,48069,48069,16384,65536,12763,1638700,194272922419343,194285066464535,194285066489175,194272930391948 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,171832,171832,1048576,256,0,0,8,8,16,64,0x0,0x7f261105ce80,43546,43546,16384,65536,8369,1048580,194272930413559,194285066682455,194285066701335,194272930732383 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,171832,171832,1048576,256,0,0,8,8,16,64,0x0,0x7f261105ce80,43715,43715,16384,65536,8176,1048580,194272930764153,194285066722455,194285066741335,194272930942791 diff --git a/tests/workloads/device_filter/MI100/SQ_INST_LEVEL_LDS.csv b/tests/workloads/device_filter/MI100/SQ_INST_LEVEL_LDS.csv index 99cea428b0..d912fc3108 100644 --- a/tests/workloads/device_filter/MI100/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/device_filter/MI100/SQ_INST_LEVEL_LDS.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2869952,2869952,1048576,256,0,0,8,8,16,64,0x0,0x7f72072bae80,0,0,0,2187869977668644,2187863086843344,2187863086866864,2187869985176257 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2869952,2869952,1048576,256,0,0,8,8,16,64,0x0,0x7f72072bae80,0,0,0,2187869985195062,2187863086979504,2187863086998544,2187869985509663 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2869952,2869952,1048576,256,0,0,8,8,16,64,0x0,0x7f72072bae80,0,0,0,2187869985538427,2187863087020944,2187863087039824,2187869985711863 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,172017,172017,1048576,256,0,0,8,8,16,64,0x0,0x7ff6bfca6e80,0,0,0,194273420605668,194285066464535,194285066489175,194273428330044 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,172017,172017,1048576,256,0,0,8,8,16,64,0x0,0x7ff6bfca6e80,0,0,0,194273428350383,194285066682455,194285066701335,194273428660279 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,172017,172017,1048576,256,0,0,8,8,16,64,0x0,0x7ff6bfca6e80,0,0,0,194273428688593,194285066722455,194285066741335,194273428860549 diff --git a/tests/workloads/device_filter/MI100/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/device_filter/MI100/SQ_INST_LEVEL_SMEM.csv index 7496167640..714649e733 100644 --- a/tests/workloads/device_filter/MI100/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/device_filter/MI100/SQ_INST_LEVEL_SMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2867946,2867946,1048576,256,0,0,8,8,16,64,0x0,0x7fde64f1ae80,65536,193254,24880920,2187864659556927,2187863086843344,2187863086866864,2187864667075622 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2867946,2867946,1048576,256,0,0,8,8,16,64,0x0,0x7fde64f1ae80,65536,177776,22778168,2187864667094427,2187863086979504,2187863086998544,2187864667403628 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2867946,2867946,1048576,256,0,0,8,8,16,64,0x0,0x7fde64f1ae80,65536,177040,22689848,2187864667432131,2187863087020944,2187863087039824,2187864667600928 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,172202,172202,1048576,256,0,0,8,8,16,64,0x0,0x7f80dbc10e80,65536,198372,25466512,194273910775706,194285066464535,194285066489175,194273918668841 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,172202,172202,1048576,256,0,0,8,8,16,64,0x0,0x7f80dbc10e80,65536,178410,22861520,194273918687927,194285066682455,194285066701335,194273919011510 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,172202,172202,1048576,256,0,0,8,8,16,64,0x0,0x7f80dbc10e80,65536,178762,22853312,194273919039884,194285066722455,194285066741335,194273919232939 diff --git a/tests/workloads/device_filter/MI100/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/device_filter/MI100/SQ_INST_LEVEL_VMEM.csv index 0f35052d39..5f0f862060 100644 --- a/tests/workloads/device_filter/MI100/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/device_filter/MI100/SQ_INST_LEVEL_VMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2870680,2870680,1048576,256,0,0,8,8,16,64,0x0,0x7f9a920b2e80,32768,646946,82808524,2187872008481374,2187863086843344,2187863086866864,2187872016007002 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2870680,2870680,1048576,256,0,0,8,8,16,64,0x0,0x7f9a920b2e80,32768,665028,85108136,2187872016024845,2187863086979504,2187863086998544,2187872016349314 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2870680,2870680,1048576,256,0,0,8,8,16,64,0x0,0x7f9a920b2e80,32768,662924,84848200,2187872016378269,2187863087020944,2187863087039824,2187872016554119 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,172388,172388,1048576,256,0,0,8,8,16,64,0x0,0x7f91b7fd6e80,32768,645046,82562784,194274390775457,194285066464535,194285066489175,194274398576077 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,172388,172388,1048576,256,0,0,8,8,16,64,0x0,0x7f91b7fd6e80,32768,656009,83967432,194274398595203,194285066682455,194285066701335,194274398895572 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,172388,172388,1048576,256,0,0,8,8,16,64,0x0,0x7f91b7fd6e80,32768,654851,83819532,194274398924006,194285066722455,194285066741335,194274399099017 diff --git a/tests/workloads/device_filter/MI100/SQ_LEVEL_WAVES.csv b/tests/workloads/device_filter/MI100/SQ_LEVEL_WAVES.csv index cc51865684..fe78976967 100644 --- a/tests/workloads/device_filter/MI100/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/device_filter/MI100/SQ_LEVEL_WAVES.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2870862,2870862,1048576,256,0,0,8,8,16,64,0x0,0x7febf83ace80,49355,49355,18227,394848,16384,25114743,232859,0,100948108,2187872453712459,2187863086843344,2187863086866864,2187872461243888 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2870862,2870862,1048576,256,0,0,8,8,16,64,0x0,0x7febf83ace80,44034,44034,15357,352280,16384,24796619,227952,0,99683264,2187872461273072,2187863086979504,2187863086998544,2187872461597281 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2870862,2870862,1048576,256,0,0,8,8,16,64,0x0,0x7febf83ace80,44730,44730,15579,357848,16384,24297029,232090,0,97687376,2187872461636034,2187863087020944,2187863087039824,2187872461826611 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,172574,172574,1048576,256,0,0,8,8,16,64,0x0,0x7f63ef9aae80,48374,48374,16676,387000,16384,25449189,235661,0,102288864,194274879224637,194285066464535,194285066489175,194274887852072 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,172574,172574,1048576,256,0,0,8,8,16,64,0x0,0x7f63ef9aae80,42333,42333,13500,338672,16384,24694478,228632,0,99275804,194274887882279,194285066682455,194285066701335,194274888171918 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,172574,172574,1048576,256,0,0,8,8,16,64,0x0,0x7f63ef9aae80,42877,42877,13541,343024,16384,24621688,230950,0,98996648,194274888210190,194285066722455,194285066741335,194274888401232 diff --git a/tests/workloads/device_filter/MI100/pmc_perf.csv b/tests/workloads/device_filter/MI100/pmc_perf.csv index c99d4b9e81..686bbd8b36 100644 --- a/tests/workloads/device_filter/MI100/pmc_perf.csv +++ b/tests/workloads/device_filter/MI100/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_1,obj_1,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_2,obj_2,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_3,obj_3,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_4,obj_4,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_5,obj_5,TCC_EA_ATOMIC_LEVEL_sum,wave_size_6,obj_6,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_7,obj_7,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_8,obj_8,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_9,obj_9,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_10,obj_10,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_11,obj_11,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_12,obj_12,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_13,obj_13,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_14,obj_14,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_15,obj_15,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_16,obj_16,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f4e659bce80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86630.0,44442.0,131112.0,0.0,64,0x7f8dad7cee80,0,0,192,0,65536,64397,48,1372,31201,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,539,47235,1720,0,48.0,339.0,0.0,262288.0,64,0x7f48ded7ce80,386640,236475,3450540,16384,25581398,144,48,0,48329,48329,3899682.0,2989415.0,5268.0,966859.0,2049533.0,0.0,2980362.0,2669526.0,385183,246412,48329,0,48329,0,1546528.0,957726.0,0.0,0.0,64,0x7f5e2cfc4e80,8192,0,4096,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fb21fe58e80,32768,0,0,0,16384,16384,393216,23050929,960.0,513890.0,0.0,524288.0,1114083.0,32768.0,0,0,0,17041,131072.0,131072.0,0.0,131072.0,64,0x7fea92c9ae80,0.0,64,0x7fd78d976e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131292.0,0.0,432.0,131291.0,64,0x7f0dce858e80,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,0,47559,0,0,64,0x7f468f6d0e80,2579,0,0,1919912,2736,0,0,1925348,2713,0,0,1871657,2342,0,0,1815952,3200,0,0,1867731,2494,0,0,1888385,2355,0,0,1880021,4336,0,0,2231068,2637,0,0,1900127,643,0,0,1579931,5744,0,0,2192760,932,0,0,1738650,2822,0,0,1918072,886,0,0,1651251,1530,0,0,1787081,2331,0,0,1934359,4040,0,0,1980397,953,0,0,1635180,5421,0,0,2152545,1559,0,0,1702324,4295,0,0,2038417,971,0,0,1652548,1670,0,0,1746359,2173,0,0,1790259,3036,0,0,1840325,950,0,0,1642207,2200,0,0,1869283,2869,0,0,1988779,7566,0,0,2332139,2406,0,0,1842139,1570,0,0,1740592,2650,0,0,1965375,64,0x7f06f910ee80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,63224.0,129223.0,64,0x7fdfc3e88e80,194569,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13202,29586,9853,550,0,47728,262720.0,0.0,188.0,262532.0,64,0x7fe55b430e80,131072.0,131072.0,0.0,2560155.0,0.0,0.0,129583622.0,60018628.0,64,0x7fc701a42e80,2216157,360448,163840,0,0,180224,114688,0,71312939.0,171827287.0,70038535.0,131072.0,0.0,610894.0,0,0,26910,72105.0,0.0,0.0,72105.0,64,0x7f3119578e80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,141,8363,4408,8504,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8198,4102,8198,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f842d1bae80,0,3235050,4096,4096,0,3276819,4096,4096,0,3119192,4096,4096,0,2748450,4096,4096,0,2837173,4096,4096,0,3204393,4096,4096,0,3105910,4096,4096,0,3581114,4096,4096,0,3291469,4096,4096,0,4130633,4096,4096,0,3274382,4096,4096,0,3109424,4096,4096,0,3301210,4096,4096,0,2510362,4096,4096,0,3025633,4096,4096,0,3488333,4096,4096,0,3366075,4096,4096,0,2752798,4096,4096,0,3408785,4096,4096,0,3633022,4096,4096,0,3261018,4096,4096,0,2938563,4096,4096,0,3023265,4096,4096,0,3217978,4096,4096,0,2815878,4096,4096,0,3226586,4096,4096,0,3196368,4096,4096,0,3067972,4096,4096,0,2942037,4096,4096,0,2640435,4096,4096,0,3070656,4096,4096,0,3194085,4096,4096,64,0x7f8530110e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,47510,0,131530.0,131072.0,0.0,131104.0,64,0x7f940eb4ae80,4096,0,1551,0,4096,0,2605,0,4096,0,1531,0,4099,0,227,0,4096,0,1913,0,4096,0,573,0,4144,0,421,0,4096,0,2924,0,4096,0,894,0,4096,0,1838,0,4096,0,5705,0,4096,0,737,0,4096,0,1327,0,4096,0,228,0,4097,0,783,0,4096,0,782,0,4096,0,3317,0,4096,0,3382,0,4096,0,4238,0,4096,0,711,0,4096,0,629,0,4096,0,691,0,4096,0,1601,0,4264,0,2346,0,4096,0,1461,0,4096,0,2043,0,4096,0,3213,0,4144,0,1322,0,4096,0,308,0,4096,0,0,0,4096,0,4828,0,4096,0,455,0,2187863086843344,2187863086866864 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f4e659bce80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86558.0,0.0,131112.0,0.0,64,0x7f8dad7cee80,0,0,48,0,65536,65536,0,0,31297,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,458,43077,1676,0,48.0,372.0,0.0,262144.0,64,0x7f48ded7ce80,901152,232843,3386282,16384,25149701,0,48,0,112643,112643,4128378.0,2996471.0,7750.0,1188195.0,2036416.0,0.0,2987786.0,2676363.0,901144,254595,52202,60441,112643,158,3604576.0,820977.0,0.0,0.0,64,0x7f5e2cfc4e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fb21fe58e80,32768,0,0,0,16384,16384,393216,25318453,1079.0,512633.0,0.0,524288.0,1143932.0,32768.0,0,0,0,17461,87038.0,87038.0,0.0,87038.0,64,0x7fea92c9ae80,0.0,64,0x7fd78d976e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131310.0,0.0,474.0,131309.0,64,0x7f0dce858e80,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,0,42799,0,0,64,0x7f468f6d0e80,1182,0,0,1356396,3701,0,0,1596032,719,0,0,1363877,1959,0,0,1508187,1531,0,0,1334922,1554,0,0,1382105,1382,0,0,1404342,4702,0,0,1711766,1503,0,0,1356199,1384,0,0,1337753,2625,0,0,1604973,1633,0,0,1482760,1437,0,0,1444568,1679,0,0,1467442,722,0,0,1252792,930,0,0,1460653,1315,0,0,1418333,1815,0,0,1385305,2646,0,0,1554377,1690,0,0,1431662,1870,0,0,1523971,2878,0,0,1520985,812,0,0,1319095,770,0,0,1260467,1579,0,0,1352077,1798,0,0,1501544,648,0,0,1246394,1739,0,0,1457116,1271,0,0,1284429,2548,0,0,1531659,1142,0,0,1432715,3454,0,0,1680022,64,0x7f06f910ee80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,60649.0,129018.0,64,0x7fdfc3e88e80,190714,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,14464,30848,8598,2398,0,41285,262578.0,0.0,47.0,262531.0,64,0x7fe55b430e80,131072.0,131072.0,0.0,2585772.0,0.0,0.0,98644666.0,35097245.0,64,0x7fc701a42e80,251293,360448,163840,0,0,180224,114688,0,74325709.0,208450256.0,81919876.0,131072.0,0.0,598233.0,0,0,23838,75387.0,0.0,0.0,75387.0,64,0x7f3119578e80,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8360,4264,8360,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8203,4107,8203,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f842d1bae80,0,3296762,2700,2700,0,2800131,2754,2754,0,3014128,2680,2680,0,3125592,2738,2738,0,3162929,2696,2696,0,3159611,2740,2740,0,2986529,2712,2712,0,3138461,2723,2723,0,3140239,2678,2678,0,4016201,2760,2760,0,2859019,2726,2726,0,4060789,2756,2756,0,2946893,2690,2690,0,3346125,2736,2736,0,3003604,2688,2688,0,3295432,2726,2726,0,3259249,2692,2692,0,4757243,2736,2736,0,3115366,2660,2660,0,3808340,2730,2730,0,2797113,2690,2690,0,3251511,2780,2780,0,3001038,2681,2681,0,2791354,2702,2702,0,2991406,2688,2688,0,3162125,2756,2756,0,3109257,2703,2703,0,2505988,2728,2728,0,2660814,2692,2692,0,2884983,2756,2756,0,2901429,2684,2684,0,3219141,2726,2726,64,0x7f8530110e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,240.0,524288.0,0.0,0.0,0,0,6401,44248,1576,131861.0,131072.0,0.0,87933.0,64,0x7f940eb4ae80,4096,0,1490,0,4096,0,604,0,4096,0,1885,0,4096,0,253,0,4096,0,11,0,4096,0,869,0,4144,0,572,0,4096,0,8461,0,4096,0,2547,0,4096,0,2849,0,4096,0,2097,0,4096,0,2679,0,4097,0,648,0,4096,0,0,0,4097,0,1673,0,4096,0,0,0,4096,0,2256,0,4096,0,3270,0,4096,0,561,0,4096,0,2688,0,4096,0,1516,0,4096,0,2349,0,4096,0,239,0,4264,0,1410,0,4096,0,551,0,4096,0,2397,0,4096,0,310,0,4144,0,76,0,4099,0,0,0,4096,0,959,0,4098,0,766,0,4096,0,452,0,2187863086979504,2187863086998544 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f4e659bce80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86351.0,0.0,131112.0,0.0,64,0x7f8dad7cee80,0,0,48,0,65536,65536,0,0,30268,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,458,41565,1700,0,48.0,359.0,0.0,262144.0,64,0x7f48ded7ce80,367752,229861,3352454,16384,24242363,0,48,0,45968,45968,3738176.0,3006931.0,5264.0,1128558.0,2115342.0,0.0,2997268.0,2685623.0,367744,239661,45968,0,45968,0,1470976.0,799772.0,0.0,0.0,64,0x7f5e2cfc4e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fb21fe58e80,32768,0,0,0,16384,16384,393216,22727205,960.0,513893.0,0.0,524288.0,1049491.0,32768.0,0,0,0,13567,86780.0,86780.0,0.0,86780.0,64,0x7fea92c9ae80,0.0,64,0x7fd78d976e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131295.0,0.0,444.0,131294.0,64,0x7f0dce858e80,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,64,0x7f468f6d0e80,1310,0,0,1408633,2314,0,0,1474929,2181,0,0,1515275,2009,0,0,1469597,997,0,0,1294023,1589,0,0,1423479,1853,0,0,1451504,1918,0,0,1499084,774,0,0,1320407,1766,0,0,1448322,3102,0,0,1572650,2095,0,0,1502786,1685,0,0,1395911,1787,0,0,1440739,1678,0,0,1413744,2752,0,0,1609026,2849,0,0,1533368,1237,0,0,1342248,2846,0,0,1558478,3207,0,0,1569433,2892,0,0,1556941,2277,0,0,1494411,2814,0,0,1564909,4039,0,0,1640045,1338,0,0,1299289,1110,0,0,1324259,1953,0,0,1439185,3874,0,0,1621768,1617,0,0,1497262,4515,0,0,1719101,1570,0,0,1447537,4077,0,0,1658063,64,0x7f06f910ee80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,70782.0,142056.0,64,0x7fdfc3e88e80,192865,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13718,30102,8437,2402,0,41253,262582.0,0.0,47.0,262535.0,64,0x7fe55b430e80,131072.0,131072.0,0.0,2540173.0,0.0,0.0,129657272.0,46319629.0,64,0x7fc701a42e80,1191650,360448,163840,0,0,180224,114688,0,70322285.0,193567953.0,75673930.0,131072.0,0.0,584751.0,0,0,25130,75046.0,0.0,0.0,75046.0,64,0x7f3119578e80,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8360,4264,8360,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8194,4098,8194,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f842d1bae80,0,4001358,2730,2730,0,2376511,2714,2714,0,3561771,2708,2708,0,3491281,2757,2757,0,3341479,2692,2692,0,2875055,2744,2744,0,2758286,2732,2732,0,3132213,2712,2712,0,2992028,2714,2714,0,4159175,2700,2700,0,3014378,2748,2748,0,4094375,2752,2752,0,2742996,2706,2706,0,2910611,2728,2728,0,3206642,2710,2710,0,3351558,2720,2720,0,2941077,2690,2690,0,3805700,2688,2688,0,3421874,2718,2718,0,4447243,2720,2720,0,2885785,2711,2711,0,3003164,2753,2753,0,3667575,2706,2706,0,2949001,2726,2726,0,2603147,2700,2700,0,2978629,2738,2738,0,2644933,2734,2734,0,2719145,2728,2728,0,3299129,2697,2697,0,2829861,2699,2699,0,3928716,2740,2740,0,2778257,2708,2708,64,0x7f8530110e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,3296,39481,0,131412.0,131072.0,0.0,86838.0,64,0x7f940eb4ae80,4096,0,4211,0,4096,0,790,0,4096,0,1715,0,4096,0,1732,0,4096,0,3056,0,4096,0,6473,0,4144,0,871,0,4096,0,628,0,4096,0,141,0,4096,0,3897,0,4096,0,853,0,4096,0,4587,0,4097,0,2237,0,4096,0,1784,0,4097,0,5499,0,4096,0,2290,0,4096,0,2588,0,4096,0,2954,0,4096,0,5043,0,4096,0,3383,0,4096,0,1282,0,4096,0,2519,0,4096,0,688,0,4264,0,210,0,4096,0,5,0,4096,0,968,0,4096,0,4673,0,4144,0,160,0,4099,0,567,0,4096,0,349,0,4098,0,5281,0,4096,0,4220,0,2187863087020944,2187863087039824 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_1,obj_1,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_2,obj_2,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_3,obj_3,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_4,obj_4,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_5,obj_5,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_6,obj_6,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_7,obj_7,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_8,obj_8,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_9,obj_9,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_10,obj_10,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_11,obj_11,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_12,obj_12,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_13,obj_13,TCC_EA_ATOMIC_LEVEL_sum,wave_size_14,obj_14,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_15,obj_15,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_16,obj_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fde441d4e80,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,64,0x7f3e60c9ce80,4096,0,453,0,4096,0,0,0,4099,0,908,0,4096,0,1984,0,4096,0,1437,0,4096,0,5277,0,4144,0,109,0,4096,0,2814,0,4096,0,39,0,4096,0,320,0,4144,0,718,0,4221,0,6748,0,4096,0,0,0,4096,0,363,0,4096,0,1005,0,4096,0,2756,0,4096,0,1901,0,4096,0,7287,0,4096,0,2210,0,4096,0,1396,0,4096,0,82,0,4096,0,2754,0,4096,0,2030,0,4096,0,0,0,4096,0,0,0,4096,0,1252,0,4216,0,1075,0,4096,0,519,0,4096,0,0,0,4097,0,0,0,4096,0,4,0,4096,0,2134,0,64,0x7fe4f1e68e80,4244,0,0,1981534,2935,0,0,1915945,6476,0,0,2194672,1496,0,0,1810650,773,0,0,1656548,3877,0,0,2039141,1667,0,0,1818115,3418,0,0,1978226,1674,0,0,1761786,3443,0,0,1997252,4503,0,0,2076072,2624,0,0,1864141,2435,0,0,1883999,2427,0,0,1893825,2845,0,0,1868957,2662,0,0,1994085,3963,0,0,1987695,927,0,0,1650137,3746,0,0,1940536,1848,0,0,1864568,2467,0,0,1931672,3663,0,0,2002468,2027,0,0,1796257,2969,0,0,2007956,1753,0,0,1772645,932,0,0,1700905,2090,0,0,1857306,3957,0,0,1980981,1934,0,0,1711472,4658,0,0,2137910,5217,0,0,2098477,1353,0,0,1725857,64,0x7f32df54ce80,0,3592917,4096,4096,0,4430480,4096,4096,0,3199046,4096,4096,0,3658465,4096,4096,0,3671226,4096,4096,0,3925206,4096,4096,0,3772613,4096,4096,0,3982183,4096,4096,0,4035872,4096,4096,0,4135655,4096,4096,0,4638037,4096,4096,0,5053819,4096,4096,0,4269725,4096,4096,0,4446952,4096,4096,0,3268689,4096,4096,0,3934704,4096,4096,0,3519363,4096,4096,0,4842876,4096,4096,0,3475510,4096,4096,0,3847119,4096,4096,0,3944591,4096,4096,0,3556276,4096,4096,0,3878967,4096,4096,0,2942631,4096,4096,0,3391567,4096,4096,0,4281734,4096,4096,0,3812897,4096,4096,0,3039482,4096,4096,0,3695822,4096,4096,0,3897657,4096,4096,0,4030661,4096,4096,0,3898185,4096,4096,64,0x7f2b358f0e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,46952,0,131533.0,131072.0,0.0,131104.0,64,0x7f52539fae80,381872,230810,3375249,16384,25068515,144,48,0,47733,47733,3815066.0,3002055.0,6762.0,737874.0,2091981.0,0.0,2993208.0,2681308.0,380159,240748,47733,0,47733,0,1527456.0,947059.0,0.0,0.0,64,0x7f956bba8e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131292.0,0.0,432.0,131291.0,64,0x7f44161ece80,1807606,360448,163840,0,0,180224,114688,0,71907270.0,197035886.0,76549948.0,131072.0,0.0,588330.0,0,0,26287,71046.0,0.0,0.0,71046.0,64,0x7fa4391cce80,32768,0,0,0,16384,16384,393216,23605514,960.0,513937.0,0.0,524288.0,965398.0,32768.0,0,0,0,15914,131072.0,131072.0,0.0,131072.0,64,0x7feded874e80,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fdc4fd40e80,0,8192,4096,8192,0,8240,4144,8240,141,8319,4364,8460,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7feb2fd38e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,44679.0,116229.0,64,0x7faffaee2e80,0,0,192,0,65536,64469,48,1347,32092,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,539,48072,1718,0,48.0,316.0,0.0,262288.0,64,0x7f982e7dce80,0.0,64,0x7ff858716e80,131072.0,131072.0,0.0,2551695.0,0.0,0.0,129760322.0,61651014.0,64,0x7f4b37d50e80,190372,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13555,29939,9879,550,0,46722,262648.0,0.0,188.0,262460.0,64,0x7f1f51b16e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86606.0,44466.0,131111.0,0.0,194285066464535,194285066489175 +1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fde441d4e80,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,64,0x7f3e60c9ce80,4096,0,1212,0,4098,0,0,0,4096,0,1633,0,4096,0,1163,0,4096,0,1422,0,4097,0,805,0,4144,0,166,0,4096,0,2379,0,4096,0,1508,0,4096,0,2819,0,4144,0,6281,0,4217,0,5813,0,4096,0,424,0,4096,0,2156,0,4096,0,5119,0,4096,0,1399,0,4096,0,2260,0,4096,0,3382,0,4096,0,7487,0,4096,0,1729,0,4096,0,1724,0,4096,0,2043,0,4096,0,1342,0,4097,0,0,0,4096,0,322,0,4096,0,4802,0,4216,0,42,0,4096,0,180,0,4096,0,0,0,4097,0,1958,0,4096,0,184,0,4096,0,3918,0,64,0x7fe4f1e68e80,3219,0,0,1562312,731,0,0,1285276,2423,0,0,1538043,1536,0,0,1405284,1684,0,0,1543199,1748,0,0,1404916,3554,0,0,1680074,2221,0,0,1586501,1093,0,0,1325850,1472,0,0,1398736,3112,0,0,1632394,1228,0,0,1380641,2389,0,0,1460729,3115,0,0,1628789,1555,0,0,1374840,3935,0,0,1709254,2255,0,0,1465568,834,0,0,1344720,4213,0,0,1671870,1297,0,0,1420662,2362,0,0,1525225,1424,0,0,1408994,3211,0,0,1639511,2683,0,0,1647393,1365,0,0,1322748,1782,0,0,1420327,2550,0,0,1557342,5391,0,0,1727912,1442,0,0,1421847,2240,0,0,1541356,4576,0,0,1735518,1507,0,0,1459347,64,0x7f32df54ce80,0,5658087,2748,2748,0,3619563,2714,2714,0,2418594,2712,2712,0,2572533,2697,2697,0,2843853,2716,2716,0,2984112,2712,2712,0,2359649,2712,2712,0,2871855,2710,2710,0,3014279,2730,2730,0,4360044,2684,2684,0,2709665,2724,2724,0,4494899,2734,2734,0,2432485,2712,2712,0,3153878,2672,2672,0,3039553,2744,2744,0,2359250,2700,2700,0,2898959,2736,2736,0,3840021,2710,2710,0,3053562,2714,2714,0,3500255,2716,2716,0,2561979,2713,2713,0,2935477,2733,2733,0,3563788,2703,2703,0,2625817,2705,2705,0,3077528,2723,2723,0,3574562,2694,2694,0,3570602,2744,2744,0,3482203,2718,2718,0,3428227,2726,2726,0,2963549,2712,2712,0,2918923,2724,2724,0,2596552,2676,2676,64,0x7f2b358f0e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,240.0,524288.0,0.0,0.0,0,0,6570,44835,1079,131879.0,131072.0,0.0,107520.0,64,0x7f52539fae80,340616,229944,3361732,16384,24531568,0,48,0,42576,42576,3739316.0,3078645.0,6342.0,882161.0,2135594.0,0.0,3069429.0,2758188.0,340608,239737,42576,0,42576,0,1362432.0,813711.0,0.0,0.0,64,0x7f956bba8e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131306.0,0.0,466.0,131305.0,64,0x7f44161ece80,1494893,360448,163840,0,0,180224,114688,0,72343460.0,201193433.0,71593158.0,131072.0,0.0,657177.0,0,0,25423,55539.0,0.0,0.0,55539.0,64,0x7fa4391cce80,32768,0,0,0,16384,16384,393216,23307083,960.0,513877.0,0.0,524288.0,1054076.0,32768.0,0,0,0,13905,86557.0,86557.0,0.0,86557.0,64,0x7feded874e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fdc4fd40e80,0,8192,4096,8192,0,8240,4144,8240,0,8343,4247,8343,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8240,4144,8240,0,8193,4097,8193,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7feb2fd38e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,70762.0,140151.0,64,0x7faffaee2e80,0,0,48,0,65536,65536,0,0,31164,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,457,42484,1791,0,48.0,222.0,0.0,262144.0,64,0x7f982e7dce80,0.0,64,0x7ff858716e80,131072.0,131072.0,0.0,2553450.0,0.0,0.0,89599350.0,33108575.0,64,0x7f4b37d50e80,188542,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13935,30319,8715,2900,0,42027,262518.0,0.0,47.0,262471.0,64,0x7f1f51b16e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86610.0,0.0,131112.0,0.0,194285066682455,194285066701335 +2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fde441d4e80,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,64,0x7f3e60c9ce80,4096,0,2330,0,4098,0,2325,0,4096,0,851,0,4096,0,956,0,4096,0,1646,0,4097,0,3487,0,4144,0,696,0,4096,0,592,0,4096,0,821,0,4096,0,4368,0,4144,0,3674,0,4218,0,3889,0,4096,0,4219,0,4096,0,5031,0,4096,0,1526,0,4096,0,551,0,4096,0,1891,0,4096,0,5222,0,4096,0,2262,0,4096,0,1781,0,4096,0,4366,0,4096,0,1546,0,4096,0,1776,0,4097,0,336,0,4096,0,2299,0,4096,0,2151,0,4216,0,873,0,4096,0,65,0,4096,0,2418,0,4097,0,1235,0,4096,0,44,0,4096,0,5028,0,64,0x7fe4f1e68e80,2581,0,0,1511750,452,0,0,1256508,1323,0,0,1390576,1776,0,0,1462619,187,0,0,1248769,407,0,0,1202378,4877,0,0,1770431,732,0,0,1350563,384,0,0,1297308,611,0,0,1409649,734,0,0,1316694,472,0,0,1211940,5044,0,0,1732488,925,0,0,1354968,973,0,0,1354973,1379,0,0,1405363,838,0,0,1299353,304,0,0,1218957,1817,0,0,1490833,1160,0,0,1372320,6271,0,0,1857282,1787,0,0,1506243,2092,0,0,1549318,1143,0,0,1276492,1402,0,0,1413228,407,0,0,1247513,1429,0,0,1415070,2561,0,0,1523401,1592,0,0,1438727,3126,0,0,1579821,509,0,0,1259292,433,0,0,1265277,64,0x7f32df54ce80,0,4973079,2711,2711,0,4058889,2720,2720,0,4493430,2668,2668,0,2681406,2721,2721,0,3890042,2680,2680,0,3429252,2728,2728,0,3641605,2720,2720,0,2647654,2696,2696,0,4801850,2670,2670,0,4146136,2716,2716,0,3501863,2708,2708,0,5478603,2720,2720,0,3272465,2690,2690,0,4965405,2694,2694,0,3568915,2680,2680,0,2650896,2684,2684,0,5242056,2690,2690,0,5388472,2732,2732,0,3438659,2672,2672,0,3025780,2719,2719,0,3314562,2688,2688,0,4226397,2740,2740,0,2854399,2688,2688,0,2504232,2702,2702,0,2846498,2696,2696,0,3364195,2692,2692,0,3733085,2720,2720,0,2430030,2696,2696,0,3363474,2706,2706,0,3242097,2718,2718,0,3867473,2704,2704,0,3004985,2680,2680,64,0x7f2b358f0e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,3379,38734,0,131355.0,131072.0,0.0,86412.0,64,0x7f52539fae80,344136,228164,3344197,16384,24508735,0,48,0,43016,43016,3712661.0,3062302.0,5248.0,790272.0,2158126.0,0.0,3052498.0,2741055.0,344128,237955,43016,0,43016,0,1376512.0,799393.0,0.0,0.0,64,0x7f956bba8e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131294.0,0.0,442.0,131293.0,64,0x7f44161ece80,1534560,360448,163840,0,0,180224,114688,0,69519286.0,194844419.0,72720170.0,131072.0,0.0,599441.0,0,0,25599,60145.0,0.0,0.0,60145.0,64,0x7fa4391cce80,32768,0,0,0,16384,16384,393216,22493453,960.0,513854.0,0.0,524288.0,884676.0,32768.0,0,0,0,13233,86402.0,86402.0,0.0,86402.0,64,0x7feded874e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fdc4fd40e80,0,8192,4096,8192,0,8240,4144,8240,0,8323,4227,8323,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8240,4144,8240,0,8193,4097,8193,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7feb2fd38e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,72097.0,143327.0,64,0x7faffaee2e80,0,0,48,0,65536,65536,0,0,29889,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,457,41786,1792,0,48.0,215.0,0.0,262144.0,64,0x7f982e7dce80,0.0,64,0x7ff858716e80,131072.0,131072.0,0.0,2561361.0,0.0,0.0,92664244.0,36722243.0,64,0x7f4b37d50e80,189261,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,14630,31014,8640,2891,0,40712,262480.0,0.0,47.0,262433.0,64,0x7f1f51b16e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86404.0,0.0,131112.0,0.0,194285066722455,194285066741335 diff --git a/tests/workloads/device_filter/MI100/sysinfo.csv b/tests/workloads/device_filter/MI100/sysinfo.csv index b17df905b2..3b3294c9b8 100644 --- a/tests/workloads/device_filter/MI100/sysinfo.csv +++ b/tests/workloads/device_filter/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -device_filter,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Fri Mar 1 16:46:13 2024 (CST),1,t006-003.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651240,,5.7.1-98,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +device_filter,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 07 Mar 2024 01:08:57 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/device_filter/MI100/timestamps.csv b/tests/workloads/device_filter/MI100/timestamps.csv index 6a362fa2dc..37942f7a55 100644 --- a/tests/workloads/device_filter/MI100/timestamps.csv +++ b/tests/workloads/device_filter/MI100/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,2867400,2867400,1048576,256,0,0,8,8,16,64,0x0,0x7f1016c04e80,2187863086818021,2187863086843344,2187863086866864,2187863086880578 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,2867400,2867400,1048576,256,0,0,8,8,16,64,0x0,0x7f1016c04e80,2187863086879366,2187863086979504,2187863086998544,2187863086999782 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,2867400,2867400,1048576,256,0,0,8,8,16,64,0x0,0x7f1016c04e80,2187863087011163,2187863087020944,2187863087039824,2187863087040899 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,175921,175921,1048576,256,0,0,8,8,16,64,0x0,0x7ff832f9ae80,194285066439120,194285066464535,194285066489175,194285066502310 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,175921,175921,1048576,256,0,0,8,8,16,64,0x0,0x7ff832f9ae80,194285066502350,194285066682455,194285066701335,194285066702839 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,175921,175921,1048576,256,0,0,8,8,16,64,0x0,0x7ff832f9ae80,194285066713930,194285066722455,194285066741335,194285066742634 diff --git a/tests/workloads/device_filter/MI200/SQ_IFETCH_LEVEL.csv b/tests/workloads/device_filter/MI200/SQ_IFETCH_LEVEL.csv new file mode 100644 index 0000000000..ca02cd7a40 --- /dev/null +++ b/tests/workloads/device_filter/MI200/SQ_IFETCH_LEVEL.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,330344,330344,1048576,256,0,0,8,0,16,64,0x0,0x7fe6cf348ec0,27379,27379,16384,65536,13546,1530804,199109067732799,199121780771567,199121780791247,199109083780798 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,330344,330344,1048576,256,0,0,8,0,16,64,0x0,0x7fe6cf348ec0,40641,40641,16384,65536,9422,1048620,199109083800004,199121780810127,199121780825807,199109084104139 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,330344,330344,1048576,256,0,0,8,0,16,64,0x0,0x7fe6cf348ec0,40214,40214,16384,65536,9321,1048756,199109084143764,199121780890127,199121780906607,199109084308516 diff --git a/tests/workloads/device_filter/MI200/SQ_INST_LEVEL_LDS.csv b/tests/workloads/device_filter/MI200/SQ_INST_LEVEL_LDS.csv new file mode 100644 index 0000000000..242baf8ff9 --- /dev/null +++ b/tests/workloads/device_filter/MI200/SQ_INST_LEVEL_LDS.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,330545,330545,1048576,256,0,0,8,0,16,64,0x0,0x7f3c42f94ec0,0,0,0,199109550821338,199121780771567,199121780791247,199109566789335 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,330545,330545,1048576,256,0,0,8,0,16,64,0x0,0x7f3c42f94ec0,0,0,0,199109566805174,199121780810127,199121780825807,199109567096836 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,330545,330545,1048576,256,0,0,8,0,16,64,0x0,0x7f3c42f94ec0,0,0,0,199109567123557,199121780890127,199121780906607,199109567286696 diff --git a/tests/workloads/device_filter/MI200/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/device_filter/MI200/SQ_INST_LEVEL_SMEM.csv new file mode 100644 index 0000000000..07b2c32d82 --- /dev/null +++ b/tests/workloads/device_filter/MI200/SQ_INST_LEVEL_SMEM.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,330728,330728,1048576,256,0,0,8,0,16,64,0x0,0x7fc8f8a6cec0,65536,211460,23579520,199110030597901,199121780771567,199121780791247,199110046727484 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,330728,330728,1048576,256,0,0,8,0,16,64,0x0,0x7fc8f8a6cec0,65536,254912,28465096,199110046748423,199121780810127,199121780825807,199110047009096 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,330728,330728,1048576,256,0,0,8,0,16,64,0x0,0x7fc8f8a6cec0,65536,258838,28871464,199110047035506,199121780890127,199121780906607,199110047184308 diff --git a/tests/workloads/device_filter/MI200/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/device_filter/MI200/SQ_INST_LEVEL_VMEM.csv new file mode 100644 index 0000000000..82f95e25a3 --- /dev/null +++ b/tests/workloads/device_filter/MI200/SQ_INST_LEVEL_VMEM.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,330929,330929,1048576,256,0,0,8,0,16,64,0x0,0x7fd12bbd8ec0,32768,288902,32346476,199110514009110,199121780771567,199121780791247,199110529778261 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,330929,330929,1048576,256,0,0,8,0,16,64,0x0,0x7fd12bbd8ec0,32768,593947,66524552,199110529795433,199121780810127,199121780825807,199110530092144 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,330929,330929,1048576,256,0,0,8,0,16,64,0x0,0x7fd12bbd8ec0,32768,602236,67452520,199110530118254,199121780890127,199121780906607,199110530290219 diff --git a/tests/workloads/device_filter/MI200/SQ_LEVEL_WAVES.csv b/tests/workloads/device_filter/MI200/SQ_LEVEL_WAVES.csv new file mode 100644 index 0000000000..88fc5ecb4c --- /dev/null +++ b/tests/workloads/device_filter/MI200/SQ_LEVEL_WAVES.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,331115,331115,1048576,256,0,0,8,0,16,64,0x0,0x7f16a9730ec0,27492,27492,10876,219944,16384,10773590,127834,0,43600528,199110993347043,199121780771567,199121780791247,199111009505921 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,331115,331115,1048576,256,0,0,8,0,16,64,0x0,0x7f16a9730ec0,41046,41046,13175,328376,16384,19783221,224811,0,79611516,199111009533263,199121780810127,199121780825807,199111009819264 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,331115,331115,1048576,256,0,0,8,0,16,64,0x0,0x7f16a9730ec0,40621,40621,11924,324976,16384,19553416,225262,0,78707700,199111009854681,199121780890127,199121780906607,199111010019924 diff --git a/tests/workloads/device_filter/MI200/perfmon/SQ_IFETCH_LEVEL.txt b/tests/workloads/device_filter/MI200/perfmon/SQ_IFETCH_LEVEL.txt new file mode 100644 index 0000000000..293092f641 --- /dev/null +++ b/tests/workloads/device_filter/MI200/perfmon/SQ_IFETCH_LEVEL.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/device_filter/MI200/perfmon/SQ_INST_LEVEL_LDS.txt b/tests/workloads/device_filter/MI200/perfmon/SQ_INST_LEVEL_LDS.txt new file mode 100644 index 0000000000..08439eedce --- /dev/null +++ b/tests/workloads/device_filter/MI200/perfmon/SQ_INST_LEVEL_LDS.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/device_filter/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt b/tests/workloads/device_filter/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt new file mode 100644 index 0000000000..6cca322d4e --- /dev/null +++ b/tests/workloads/device_filter/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/device_filter/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt b/tests/workloads/device_filter/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt new file mode 100644 index 0000000000..e527ad31ba --- /dev/null +++ b/tests/workloads/device_filter/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/device_filter/MI200/perfmon/SQ_LEVEL_WAVES.txt b/tests/workloads/device_filter/MI200/perfmon/SQ_LEVEL_WAVES.txt new file mode 100644 index 0000000000..3f8e04adb3 --- /dev/null +++ b/tests/workloads/device_filter/MI200/perfmon/SQ_LEVEL_WAVES.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/device_filter/MI200/perfmon/pmc_perf_0.txt b/tests/workloads/device_filter/MI200/perfmon/pmc_perf_0.txt new file mode 100644 index 0000000000..4ffdc32149 --- /dev/null +++ b/tests/workloads/device_filter/MI200/perfmon/pmc_perf_0.txt @@ -0,0 +1,5 @@ +pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES SQ_INSTS_VALU_CVT SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU GRBM_COUNT GRBM_GUI_ACTIVE TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum TA_TA_BUSY_sum TA_BUFFER_WAVEFRONTS_sum TD_TD_BUSY_sum TD_TC_STALL_sum SPI_CSN_WINDOW_VALID SPI_CSN_BUSY CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/device_filter/MI200/perfmon/pmc_perf_1.txt b/tests/workloads/device_filter/MI200/perfmon/pmc_perf_1.txt new file mode 100644 index 0000000000..6c277f4a37 --- /dev/null +++ b/tests/workloads/device_filter/MI200/perfmon/pmc_perf_1.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VSKIPPED SQ_INSTS SQ_INSTS_VALU SQ_INSTS_VALU_ADD_F16 SQ_INSTS_VALU_MUL_F16 SQ_INSTS_VALU_FMA_F16 SQ_INSTS_VALU_TRANS_F16 SQ_INSTS_VALU_ADD_F32 GRBM_SPI_BUSY TCP_READ_TAGCONFLICT_STALL_CYCLES_sum TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum TCP_TA_TCP_STATE_READ_sum TA_BUFFER_READ_WAVEFRONTS_sum TA_BUFFER_WRITE_WAVEFRONTS_sum TD_SPI_STALL_sum TD_LOAD_WAVEFRONT_sum SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/device_filter/MI200/perfmon/pmc_perf_10.txt b/tests/workloads/device_filter/MI200/perfmon/pmc_perf_10.txt new file mode 100644 index 0000000000..7053d4dce6 --- /dev/null +++ b/tests/workloads/device_filter/MI200/perfmon/pmc_perf_10.txt @@ -0,0 +1,5 @@ +pmc: SQC_TC_DATA_WRITE_REQ SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES + +gpu: +range: +kernel: diff --git a/tests/workloads/device_filter/MI200/perfmon/pmc_perf_11.txt b/tests/workloads/device_filter/MI200/perfmon/pmc_perf_11.txt new file mode 100644 index 0000000000..77ae8b461f --- /dev/null +++ b/tests/workloads/device_filter/MI200/perfmon/pmc_perf_11.txt @@ -0,0 +1,5 @@ +pmc: SQC_ICACHE_MISSES_DUPLICATE SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE + +gpu: +range: +kernel: diff --git a/tests/workloads/device_filter/MI200/perfmon/pmc_perf_12.txt b/tests/workloads/device_filter/MI200/perfmon/pmc_perf_12.txt new file mode 100644 index 0000000000..dfb2cf65e5 --- /dev/null +++ b/tests/workloads/device_filter/MI200/perfmon/pmc_perf_12.txt @@ -0,0 +1,5 @@ +pmc: SQC_DCACHE_REQ_READ_1 SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 + +gpu: +range: +kernel: diff --git a/tests/workloads/device_filter/MI200/perfmon/pmc_perf_13.txt b/tests/workloads/device_filter/MI200/perfmon/pmc_perf_13.txt new file mode 100644 index 0000000000..062fc9644a --- /dev/null +++ b/tests/workloads/device_filter/MI200/perfmon/pmc_perf_13.txt @@ -0,0 +1,5 @@ +pmc: TCC_ATOMIC[0] TCC_CYCLE[0] TCC_EA_ATOMIC[0] TCC_EA_ATOMIC_LEVEL[0] TCC_ATOMIC[1] TCC_CYCLE[1] TCC_EA_ATOMIC[1] TCC_EA_ATOMIC_LEVEL[1] TCC_ATOMIC[2] TCC_CYCLE[2] TCC_EA_ATOMIC[2] TCC_EA_ATOMIC_LEVEL[2] TCC_ATOMIC[3] TCC_CYCLE[3] TCC_EA_ATOMIC[3] TCC_EA_ATOMIC_LEVEL[3] TCC_ATOMIC[4] TCC_CYCLE[4] TCC_EA_ATOMIC[4] TCC_EA_ATOMIC_LEVEL[4] TCC_ATOMIC[5] TCC_CYCLE[5] TCC_EA_ATOMIC[5] TCC_EA_ATOMIC_LEVEL[5] TCC_ATOMIC[6] TCC_CYCLE[6] TCC_EA_ATOMIC[6] TCC_EA_ATOMIC_LEVEL[6] TCC_ATOMIC[7] TCC_CYCLE[7] TCC_EA_ATOMIC[7] TCC_EA_ATOMIC_LEVEL[7] TCC_ATOMIC[8] TCC_CYCLE[8] TCC_EA_ATOMIC[8] TCC_EA_ATOMIC_LEVEL[8] TCC_ATOMIC[9] TCC_CYCLE[9] TCC_EA_ATOMIC[9] TCC_EA_ATOMIC_LEVEL[9] TCC_ATOMIC[10] TCC_CYCLE[10] TCC_EA_ATOMIC[10] TCC_EA_ATOMIC_LEVEL[10] TCC_ATOMIC[11] TCC_CYCLE[11] TCC_EA_ATOMIC[11] TCC_EA_ATOMIC_LEVEL[11] TCC_ATOMIC[12] TCC_CYCLE[12] TCC_EA_ATOMIC[12] TCC_EA_ATOMIC_LEVEL[12] TCC_ATOMIC[13] TCC_CYCLE[13] TCC_EA_ATOMIC[13] TCC_EA_ATOMIC_LEVEL[13] TCC_ATOMIC[14] TCC_CYCLE[14] TCC_EA_ATOMIC[14] TCC_EA_ATOMIC_LEVEL[14] TCC_ATOMIC[15] TCC_CYCLE[15] TCC_EA_ATOMIC[15] TCC_EA_ATOMIC_LEVEL[15] TCC_ATOMIC[16] TCC_CYCLE[16] TCC_EA_ATOMIC[16] TCC_EA_ATOMIC_LEVEL[16] TCC_ATOMIC[17] TCC_CYCLE[17] TCC_EA_ATOMIC[17] TCC_EA_ATOMIC_LEVEL[17] TCC_ATOMIC[18] TCC_CYCLE[18] TCC_EA_ATOMIC[18] TCC_EA_ATOMIC_LEVEL[18] TCC_ATOMIC[19] TCC_CYCLE[19] TCC_EA_ATOMIC[19] TCC_EA_ATOMIC_LEVEL[19] TCC_ATOMIC[20] TCC_CYCLE[20] TCC_EA_ATOMIC[20] TCC_EA_ATOMIC_LEVEL[20] TCC_ATOMIC[21] TCC_CYCLE[21] TCC_EA_ATOMIC[21] TCC_EA_ATOMIC_LEVEL[21] TCC_ATOMIC[22] TCC_CYCLE[22] TCC_EA_ATOMIC[22] TCC_EA_ATOMIC_LEVEL[22] TCC_ATOMIC[23] TCC_CYCLE[23] TCC_EA_ATOMIC[23] TCC_EA_ATOMIC_LEVEL[23] TCC_ATOMIC[24] TCC_CYCLE[24] TCC_EA_ATOMIC[24] TCC_EA_ATOMIC_LEVEL[24] TCC_ATOMIC[25] TCC_CYCLE[25] TCC_EA_ATOMIC[25] TCC_EA_ATOMIC_LEVEL[25] TCC_ATOMIC[26] TCC_CYCLE[26] TCC_EA_ATOMIC[26] TCC_EA_ATOMIC_LEVEL[26] TCC_ATOMIC[27] TCC_CYCLE[27] TCC_EA_ATOMIC[27] TCC_EA_ATOMIC_LEVEL[27] TCC_ATOMIC[28] TCC_CYCLE[28] TCC_EA_ATOMIC[28] TCC_EA_ATOMIC_LEVEL[28] TCC_ATOMIC[29] TCC_CYCLE[29] TCC_EA_ATOMIC[29] TCC_EA_ATOMIC_LEVEL[29] TCC_ATOMIC[30] TCC_CYCLE[30] TCC_EA_ATOMIC[30] TCC_EA_ATOMIC_LEVEL[30] TCC_ATOMIC[31] TCC_CYCLE[31] TCC_EA_ATOMIC[31] TCC_EA_ATOMIC_LEVEL[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/device_filter/MI200/perfmon/pmc_perf_14.txt b/tests/workloads/device_filter/MI200/perfmon/pmc_perf_14.txt new file mode 100644 index 0000000000..e0698dbf57 --- /dev/null +++ b/tests/workloads/device_filter/MI200/perfmon/pmc_perf_14.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_EA_RDREQ_GMI_CREDIT_STALL[0] TCC_EA_RDREQ[1] TCC_EA_RDREQ_32B[1] TCC_EA_RDREQ_DRAM_CREDIT_STALL[1] TCC_EA_RDREQ_GMI_CREDIT_STALL[1] TCC_EA_RDREQ[2] TCC_EA_RDREQ_32B[2] TCC_EA_RDREQ_DRAM_CREDIT_STALL[2] TCC_EA_RDREQ_GMI_CREDIT_STALL[2] TCC_EA_RDREQ[3] TCC_EA_RDREQ_32B[3] TCC_EA_RDREQ_DRAM_CREDIT_STALL[3] TCC_EA_RDREQ_GMI_CREDIT_STALL[3] TCC_EA_RDREQ[4] TCC_EA_RDREQ_32B[4] TCC_EA_RDREQ_DRAM_CREDIT_STALL[4] TCC_EA_RDREQ_GMI_CREDIT_STALL[4] TCC_EA_RDREQ[5] TCC_EA_RDREQ_32B[5] TCC_EA_RDREQ_DRAM_CREDIT_STALL[5] TCC_EA_RDREQ_GMI_CREDIT_STALL[5] TCC_EA_RDREQ[6] TCC_EA_RDREQ_32B[6] TCC_EA_RDREQ_DRAM_CREDIT_STALL[6] TCC_EA_RDREQ_GMI_CREDIT_STALL[6] TCC_EA_RDREQ[7] TCC_EA_RDREQ_32B[7] TCC_EA_RDREQ_DRAM_CREDIT_STALL[7] TCC_EA_RDREQ_GMI_CREDIT_STALL[7] TCC_EA_RDREQ[8] TCC_EA_RDREQ_32B[8] TCC_EA_RDREQ_DRAM_CREDIT_STALL[8] TCC_EA_RDREQ_GMI_CREDIT_STALL[8] TCC_EA_RDREQ[9] TCC_EA_RDREQ_32B[9] TCC_EA_RDREQ_DRAM_CREDIT_STALL[9] TCC_EA_RDREQ_GMI_CREDIT_STALL[9] TCC_EA_RDREQ[10] TCC_EA_RDREQ_32B[10] TCC_EA_RDREQ_DRAM_CREDIT_STALL[10] TCC_EA_RDREQ_GMI_CREDIT_STALL[10] TCC_EA_RDREQ[11] TCC_EA_RDREQ_32B[11] TCC_EA_RDREQ_DRAM_CREDIT_STALL[11] TCC_EA_RDREQ_GMI_CREDIT_STALL[11] TCC_EA_RDREQ[12] TCC_EA_RDREQ_32B[12] TCC_EA_RDREQ_DRAM_CREDIT_STALL[12] TCC_EA_RDREQ_GMI_CREDIT_STALL[12] TCC_EA_RDREQ[13] TCC_EA_RDREQ_32B[13] TCC_EA_RDREQ_DRAM_CREDIT_STALL[13] TCC_EA_RDREQ_GMI_CREDIT_STALL[13] TCC_EA_RDREQ[14] TCC_EA_RDREQ_32B[14] TCC_EA_RDREQ_DRAM_CREDIT_STALL[14] TCC_EA_RDREQ_GMI_CREDIT_STALL[14] TCC_EA_RDREQ[15] TCC_EA_RDREQ_32B[15] TCC_EA_RDREQ_DRAM_CREDIT_STALL[15] TCC_EA_RDREQ_GMI_CREDIT_STALL[15] TCC_EA_RDREQ[16] TCC_EA_RDREQ_32B[16] TCC_EA_RDREQ_DRAM_CREDIT_STALL[16] TCC_EA_RDREQ_GMI_CREDIT_STALL[16] TCC_EA_RDREQ[17] TCC_EA_RDREQ_32B[17] TCC_EA_RDREQ_DRAM_CREDIT_STALL[17] TCC_EA_RDREQ_GMI_CREDIT_STALL[17] TCC_EA_RDREQ[18] TCC_EA_RDREQ_32B[18] TCC_EA_RDREQ_DRAM_CREDIT_STALL[18] TCC_EA_RDREQ_GMI_CREDIT_STALL[18] TCC_EA_RDREQ[19] TCC_EA_RDREQ_32B[19] TCC_EA_RDREQ_DRAM_CREDIT_STALL[19] TCC_EA_RDREQ_GMI_CREDIT_STALL[19] TCC_EA_RDREQ[20] TCC_EA_RDREQ_32B[20] TCC_EA_RDREQ_DRAM_CREDIT_STALL[20] TCC_EA_RDREQ_GMI_CREDIT_STALL[20] TCC_EA_RDREQ[21] TCC_EA_RDREQ_32B[21] TCC_EA_RDREQ_DRAM_CREDIT_STALL[21] TCC_EA_RDREQ_GMI_CREDIT_STALL[21] TCC_EA_RDREQ[22] TCC_EA_RDREQ_32B[22] TCC_EA_RDREQ_DRAM_CREDIT_STALL[22] TCC_EA_RDREQ_GMI_CREDIT_STALL[22] TCC_EA_RDREQ[23] TCC_EA_RDREQ_32B[23] TCC_EA_RDREQ_DRAM_CREDIT_STALL[23] TCC_EA_RDREQ_GMI_CREDIT_STALL[23] TCC_EA_RDREQ[24] TCC_EA_RDREQ_32B[24] TCC_EA_RDREQ_DRAM_CREDIT_STALL[24] TCC_EA_RDREQ_GMI_CREDIT_STALL[24] TCC_EA_RDREQ[25] TCC_EA_RDREQ_32B[25] TCC_EA_RDREQ_DRAM_CREDIT_STALL[25] TCC_EA_RDREQ_GMI_CREDIT_STALL[25] TCC_EA_RDREQ[26] TCC_EA_RDREQ_32B[26] TCC_EA_RDREQ_DRAM_CREDIT_STALL[26] TCC_EA_RDREQ_GMI_CREDIT_STALL[26] TCC_EA_RDREQ[27] TCC_EA_RDREQ_32B[27] TCC_EA_RDREQ_DRAM_CREDIT_STALL[27] TCC_EA_RDREQ_GMI_CREDIT_STALL[27] TCC_EA_RDREQ[28] TCC_EA_RDREQ_32B[28] TCC_EA_RDREQ_DRAM_CREDIT_STALL[28] TCC_EA_RDREQ_GMI_CREDIT_STALL[28] TCC_EA_RDREQ[29] TCC_EA_RDREQ_32B[29] TCC_EA_RDREQ_DRAM_CREDIT_STALL[29] TCC_EA_RDREQ_GMI_CREDIT_STALL[29] TCC_EA_RDREQ[30] TCC_EA_RDREQ_32B[30] TCC_EA_RDREQ_DRAM_CREDIT_STALL[30] TCC_EA_RDREQ_GMI_CREDIT_STALL[30] TCC_EA_RDREQ[31] TCC_EA_RDREQ_32B[31] TCC_EA_RDREQ_DRAM_CREDIT_STALL[31] TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/device_filter/MI200/perfmon/pmc_perf_15.txt b/tests/workloads/device_filter/MI200/perfmon/pmc_perf_15.txt new file mode 100644 index 0000000000..77ad088669 --- /dev/null +++ b/tests/workloads/device_filter/MI200/perfmon/pmc_perf_15.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ[0] TCC_EA_WRREQ_64B[0] TCC_EA_RDREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_LEVEL[1] TCC_EA_WRREQ[1] TCC_EA_WRREQ_64B[1] TCC_EA_RDREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_LEVEL[2] TCC_EA_WRREQ[2] TCC_EA_WRREQ_64B[2] TCC_EA_RDREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_LEVEL[3] TCC_EA_WRREQ[3] TCC_EA_WRREQ_64B[3] TCC_EA_RDREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_LEVEL[4] TCC_EA_WRREQ[4] TCC_EA_WRREQ_64B[4] TCC_EA_RDREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_LEVEL[5] TCC_EA_WRREQ[5] TCC_EA_WRREQ_64B[5] TCC_EA_RDREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_LEVEL[6] TCC_EA_WRREQ[6] TCC_EA_WRREQ_64B[6] TCC_EA_RDREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_LEVEL[7] TCC_EA_WRREQ[7] TCC_EA_WRREQ_64B[7] TCC_EA_RDREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_LEVEL[8] TCC_EA_WRREQ[8] TCC_EA_WRREQ_64B[8] TCC_EA_RDREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_LEVEL[9] TCC_EA_WRREQ[9] TCC_EA_WRREQ_64B[9] TCC_EA_RDREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_LEVEL[10] TCC_EA_WRREQ[10] TCC_EA_WRREQ_64B[10] TCC_EA_RDREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_LEVEL[11] TCC_EA_WRREQ[11] TCC_EA_WRREQ_64B[11] TCC_EA_RDREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_LEVEL[12] TCC_EA_WRREQ[12] TCC_EA_WRREQ_64B[12] TCC_EA_RDREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_LEVEL[13] TCC_EA_WRREQ[13] TCC_EA_WRREQ_64B[13] TCC_EA_RDREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_LEVEL[14] TCC_EA_WRREQ[14] TCC_EA_WRREQ_64B[14] TCC_EA_RDREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_LEVEL[15] TCC_EA_WRREQ[15] TCC_EA_WRREQ_64B[15] TCC_EA_RDREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_LEVEL[16] TCC_EA_WRREQ[16] TCC_EA_WRREQ_64B[16] TCC_EA_RDREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_LEVEL[17] TCC_EA_WRREQ[17] TCC_EA_WRREQ_64B[17] TCC_EA_RDREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_LEVEL[18] TCC_EA_WRREQ[18] TCC_EA_WRREQ_64B[18] TCC_EA_RDREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_LEVEL[19] TCC_EA_WRREQ[19] TCC_EA_WRREQ_64B[19] TCC_EA_RDREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_LEVEL[20] TCC_EA_WRREQ[20] TCC_EA_WRREQ_64B[20] TCC_EA_RDREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_LEVEL[21] TCC_EA_WRREQ[21] TCC_EA_WRREQ_64B[21] TCC_EA_RDREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_LEVEL[22] TCC_EA_WRREQ[22] TCC_EA_WRREQ_64B[22] TCC_EA_RDREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_LEVEL[23] TCC_EA_WRREQ[23] TCC_EA_WRREQ_64B[23] TCC_EA_RDREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_LEVEL[24] TCC_EA_WRREQ[24] TCC_EA_WRREQ_64B[24] TCC_EA_RDREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_LEVEL[25] TCC_EA_WRREQ[25] TCC_EA_WRREQ_64B[25] TCC_EA_RDREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_LEVEL[26] TCC_EA_WRREQ[26] TCC_EA_WRREQ_64B[26] TCC_EA_RDREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_LEVEL[27] TCC_EA_WRREQ[27] TCC_EA_WRREQ_64B[27] TCC_EA_RDREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_LEVEL[28] TCC_EA_WRREQ[28] TCC_EA_WRREQ_64B[28] TCC_EA_RDREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_LEVEL[29] TCC_EA_WRREQ[29] TCC_EA_WRREQ_64B[29] TCC_EA_RDREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_LEVEL[30] TCC_EA_WRREQ[30] TCC_EA_WRREQ_64B[30] TCC_EA_RDREQ_IO_CREDIT_STALL[31] TCC_EA_RDREQ_LEVEL[31] TCC_EA_WRREQ[31] TCC_EA_WRREQ_64B[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/device_filter/MI200/perfmon/pmc_perf_16.txt b/tests/workloads/device_filter/MI200/perfmon/pmc_perf_16.txt new file mode 100644 index 0000000000..d0628bb948 --- /dev/null +++ b/tests/workloads/device_filter/MI200/perfmon/pmc_perf_16.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_WRREQ_IO_CREDIT_STALL[0] TCC_EA_WRREQ_LEVEL[0] TCC_EA_WRREQ_DRAM_CREDIT_STALL[1] TCC_EA_WRREQ_GMI_CREDIT_STALL[1] TCC_EA_WRREQ_IO_CREDIT_STALL[1] TCC_EA_WRREQ_LEVEL[1] TCC_EA_WRREQ_DRAM_CREDIT_STALL[2] TCC_EA_WRREQ_GMI_CREDIT_STALL[2] TCC_EA_WRREQ_IO_CREDIT_STALL[2] TCC_EA_WRREQ_LEVEL[2] TCC_EA_WRREQ_DRAM_CREDIT_STALL[3] TCC_EA_WRREQ_GMI_CREDIT_STALL[3] TCC_EA_WRREQ_IO_CREDIT_STALL[3] TCC_EA_WRREQ_LEVEL[3] TCC_EA_WRREQ_DRAM_CREDIT_STALL[4] TCC_EA_WRREQ_GMI_CREDIT_STALL[4] TCC_EA_WRREQ_IO_CREDIT_STALL[4] TCC_EA_WRREQ_LEVEL[4] TCC_EA_WRREQ_DRAM_CREDIT_STALL[5] TCC_EA_WRREQ_GMI_CREDIT_STALL[5] TCC_EA_WRREQ_IO_CREDIT_STALL[5] TCC_EA_WRREQ_LEVEL[5] TCC_EA_WRREQ_DRAM_CREDIT_STALL[6] TCC_EA_WRREQ_GMI_CREDIT_STALL[6] TCC_EA_WRREQ_IO_CREDIT_STALL[6] TCC_EA_WRREQ_LEVEL[6] TCC_EA_WRREQ_DRAM_CREDIT_STALL[7] TCC_EA_WRREQ_GMI_CREDIT_STALL[7] TCC_EA_WRREQ_IO_CREDIT_STALL[7] TCC_EA_WRREQ_LEVEL[7] TCC_EA_WRREQ_DRAM_CREDIT_STALL[8] TCC_EA_WRREQ_GMI_CREDIT_STALL[8] TCC_EA_WRREQ_IO_CREDIT_STALL[8] TCC_EA_WRREQ_LEVEL[8] TCC_EA_WRREQ_DRAM_CREDIT_STALL[9] TCC_EA_WRREQ_GMI_CREDIT_STALL[9] TCC_EA_WRREQ_IO_CREDIT_STALL[9] TCC_EA_WRREQ_LEVEL[9] TCC_EA_WRREQ_DRAM_CREDIT_STALL[10] TCC_EA_WRREQ_GMI_CREDIT_STALL[10] TCC_EA_WRREQ_IO_CREDIT_STALL[10] TCC_EA_WRREQ_LEVEL[10] TCC_EA_WRREQ_DRAM_CREDIT_STALL[11] TCC_EA_WRREQ_GMI_CREDIT_STALL[11] TCC_EA_WRREQ_IO_CREDIT_STALL[11] TCC_EA_WRREQ_LEVEL[11] TCC_EA_WRREQ_DRAM_CREDIT_STALL[12] TCC_EA_WRREQ_GMI_CREDIT_STALL[12] TCC_EA_WRREQ_IO_CREDIT_STALL[12] TCC_EA_WRREQ_LEVEL[12] TCC_EA_WRREQ_DRAM_CREDIT_STALL[13] TCC_EA_WRREQ_GMI_CREDIT_STALL[13] TCC_EA_WRREQ_IO_CREDIT_STALL[13] TCC_EA_WRREQ_LEVEL[13] TCC_EA_WRREQ_DRAM_CREDIT_STALL[14] TCC_EA_WRREQ_GMI_CREDIT_STALL[14] TCC_EA_WRREQ_IO_CREDIT_STALL[14] TCC_EA_WRREQ_LEVEL[14] TCC_EA_WRREQ_DRAM_CREDIT_STALL[15] TCC_EA_WRREQ_GMI_CREDIT_STALL[15] TCC_EA_WRREQ_IO_CREDIT_STALL[15] TCC_EA_WRREQ_LEVEL[15] TCC_EA_WRREQ_DRAM_CREDIT_STALL[16] TCC_EA_WRREQ_GMI_CREDIT_STALL[16] TCC_EA_WRREQ_IO_CREDIT_STALL[16] TCC_EA_WRREQ_LEVEL[16] TCC_EA_WRREQ_DRAM_CREDIT_STALL[17] TCC_EA_WRREQ_GMI_CREDIT_STALL[17] TCC_EA_WRREQ_IO_CREDIT_STALL[17] TCC_EA_WRREQ_LEVEL[17] TCC_EA_WRREQ_DRAM_CREDIT_STALL[18] TCC_EA_WRREQ_GMI_CREDIT_STALL[18] TCC_EA_WRREQ_IO_CREDIT_STALL[18] TCC_EA_WRREQ_LEVEL[18] TCC_EA_WRREQ_DRAM_CREDIT_STALL[19] TCC_EA_WRREQ_GMI_CREDIT_STALL[19] TCC_EA_WRREQ_IO_CREDIT_STALL[19] TCC_EA_WRREQ_LEVEL[19] TCC_EA_WRREQ_DRAM_CREDIT_STALL[20] TCC_EA_WRREQ_GMI_CREDIT_STALL[20] TCC_EA_WRREQ_IO_CREDIT_STALL[20] TCC_EA_WRREQ_LEVEL[20] TCC_EA_WRREQ_DRAM_CREDIT_STALL[21] TCC_EA_WRREQ_GMI_CREDIT_STALL[21] TCC_EA_WRREQ_IO_CREDIT_STALL[21] TCC_EA_WRREQ_LEVEL[21] TCC_EA_WRREQ_DRAM_CREDIT_STALL[22] TCC_EA_WRREQ_GMI_CREDIT_STALL[22] TCC_EA_WRREQ_IO_CREDIT_STALL[22] TCC_EA_WRREQ_LEVEL[22] TCC_EA_WRREQ_DRAM_CREDIT_STALL[23] TCC_EA_WRREQ_GMI_CREDIT_STALL[23] TCC_EA_WRREQ_IO_CREDIT_STALL[23] TCC_EA_WRREQ_LEVEL[23] TCC_EA_WRREQ_DRAM_CREDIT_STALL[24] TCC_EA_WRREQ_GMI_CREDIT_STALL[24] TCC_EA_WRREQ_IO_CREDIT_STALL[24] TCC_EA_WRREQ_LEVEL[24] TCC_EA_WRREQ_DRAM_CREDIT_STALL[25] TCC_EA_WRREQ_GMI_CREDIT_STALL[25] TCC_EA_WRREQ_IO_CREDIT_STALL[25] TCC_EA_WRREQ_LEVEL[25] TCC_EA_WRREQ_DRAM_CREDIT_STALL[26] TCC_EA_WRREQ_GMI_CREDIT_STALL[26] TCC_EA_WRREQ_IO_CREDIT_STALL[26] TCC_EA_WRREQ_LEVEL[26] TCC_EA_WRREQ_DRAM_CREDIT_STALL[27] TCC_EA_WRREQ_GMI_CREDIT_STALL[27] TCC_EA_WRREQ_IO_CREDIT_STALL[27] TCC_EA_WRREQ_LEVEL[27] TCC_EA_WRREQ_DRAM_CREDIT_STALL[28] TCC_EA_WRREQ_GMI_CREDIT_STALL[28] TCC_EA_WRREQ_IO_CREDIT_STALL[28] TCC_EA_WRREQ_LEVEL[28] TCC_EA_WRREQ_DRAM_CREDIT_STALL[29] TCC_EA_WRREQ_GMI_CREDIT_STALL[29] TCC_EA_WRREQ_IO_CREDIT_STALL[29] TCC_EA_WRREQ_LEVEL[29] TCC_EA_WRREQ_DRAM_CREDIT_STALL[30] TCC_EA_WRREQ_GMI_CREDIT_STALL[30] TCC_EA_WRREQ_IO_CREDIT_STALL[30] TCC_EA_WRREQ_LEVEL[30] TCC_EA_WRREQ_DRAM_CREDIT_STALL[31] TCC_EA_WRREQ_GMI_CREDIT_STALL[31] TCC_EA_WRREQ_IO_CREDIT_STALL[31] TCC_EA_WRREQ_LEVEL[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/device_filter/MI200/perfmon/pmc_perf_17.txt b/tests/workloads/device_filter/MI200/perfmon/pmc_perf_17.txt new file mode 100644 index 0000000000..343869c5f1 --- /dev/null +++ b/tests/workloads/device_filter/MI200/perfmon/pmc_perf_17.txt @@ -0,0 +1,5 @@ +pmc: TCC_HIT[0] TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_HIT[1] TCC_MISS[1] TCC_READ[1] TCC_REQ[1] TCC_HIT[2] TCC_MISS[2] TCC_READ[2] TCC_REQ[2] TCC_HIT[3] TCC_MISS[3] TCC_READ[3] TCC_REQ[3] TCC_HIT[4] TCC_MISS[4] TCC_READ[4] TCC_REQ[4] TCC_HIT[5] TCC_MISS[5] TCC_READ[5] TCC_REQ[5] TCC_HIT[6] TCC_MISS[6] TCC_READ[6] TCC_REQ[6] TCC_HIT[7] TCC_MISS[7] TCC_READ[7] TCC_REQ[7] TCC_HIT[8] TCC_MISS[8] TCC_READ[8] TCC_REQ[8] TCC_HIT[9] TCC_MISS[9] TCC_READ[9] TCC_REQ[9] TCC_HIT[10] TCC_MISS[10] TCC_READ[10] TCC_REQ[10] TCC_HIT[11] TCC_MISS[11] TCC_READ[11] TCC_REQ[11] TCC_HIT[12] TCC_MISS[12] TCC_READ[12] TCC_REQ[12] TCC_HIT[13] TCC_MISS[13] TCC_READ[13] TCC_REQ[13] TCC_HIT[14] TCC_MISS[14] TCC_READ[14] TCC_REQ[14] TCC_HIT[15] TCC_MISS[15] TCC_READ[15] TCC_REQ[15] TCC_HIT[16] TCC_MISS[16] TCC_READ[16] TCC_REQ[16] TCC_HIT[17] TCC_MISS[17] TCC_READ[17] TCC_REQ[17] TCC_HIT[18] TCC_MISS[18] TCC_READ[18] TCC_REQ[18] TCC_HIT[19] TCC_MISS[19] TCC_READ[19] TCC_REQ[19] TCC_HIT[20] TCC_MISS[20] TCC_READ[20] TCC_REQ[20] TCC_HIT[21] TCC_MISS[21] TCC_READ[21] TCC_REQ[21] TCC_HIT[22] TCC_MISS[22] TCC_READ[22] TCC_REQ[22] TCC_HIT[23] TCC_MISS[23] TCC_READ[23] TCC_REQ[23] TCC_HIT[24] TCC_MISS[24] TCC_READ[24] TCC_REQ[24] TCC_HIT[25] TCC_MISS[25] TCC_READ[25] TCC_REQ[25] TCC_HIT[26] TCC_MISS[26] TCC_READ[26] TCC_REQ[26] TCC_HIT[27] TCC_MISS[27] TCC_READ[27] TCC_REQ[27] TCC_HIT[28] TCC_MISS[28] TCC_READ[28] TCC_REQ[28] TCC_HIT[29] TCC_MISS[29] TCC_READ[29] TCC_REQ[29] TCC_HIT[30] TCC_MISS[30] TCC_READ[30] TCC_REQ[30] TCC_HIT[31] TCC_MISS[31] TCC_READ[31] TCC_REQ[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/device_filter/MI200/perfmon/pmc_perf_18.txt b/tests/workloads/device_filter/MI200/perfmon/pmc_perf_18.txt new file mode 100644 index 0000000000..a74cefd281 --- /dev/null +++ b/tests/workloads/device_filter/MI200/perfmon/pmc_perf_18.txt @@ -0,0 +1,5 @@ +pmc: TCC_RW_REQ[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_RW_REQ[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_WRITE[1] TCC_RW_REQ[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_WRITE[2] TCC_RW_REQ[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_WRITE[3] TCC_RW_REQ[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_WRITE[4] TCC_RW_REQ[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_WRITE[5] TCC_RW_REQ[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_WRITE[6] TCC_RW_REQ[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_WRITE[7] TCC_RW_REQ[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_WRITE[8] TCC_RW_REQ[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_WRITE[9] TCC_RW_REQ[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_WRITE[10] TCC_RW_REQ[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_WRITE[11] TCC_RW_REQ[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_WRITE[12] TCC_RW_REQ[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_WRITE[13] TCC_RW_REQ[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_WRITE[14] TCC_RW_REQ[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_WRITE[15] TCC_RW_REQ[16] TCC_TOO_MANY_EA_WRREQS_STALL[16] TCC_WRITE[16] TCC_RW_REQ[17] TCC_TOO_MANY_EA_WRREQS_STALL[17] TCC_WRITE[17] TCC_RW_REQ[18] TCC_TOO_MANY_EA_WRREQS_STALL[18] TCC_WRITE[18] TCC_RW_REQ[19] TCC_TOO_MANY_EA_WRREQS_STALL[19] TCC_WRITE[19] TCC_RW_REQ[20] TCC_TOO_MANY_EA_WRREQS_STALL[20] TCC_WRITE[20] TCC_RW_REQ[21] TCC_TOO_MANY_EA_WRREQS_STALL[21] TCC_WRITE[21] TCC_RW_REQ[22] TCC_TOO_MANY_EA_WRREQS_STALL[22] TCC_WRITE[22] TCC_RW_REQ[23] TCC_TOO_MANY_EA_WRREQS_STALL[23] TCC_WRITE[23] TCC_RW_REQ[24] TCC_TOO_MANY_EA_WRREQS_STALL[24] TCC_WRITE[24] TCC_RW_REQ[25] TCC_TOO_MANY_EA_WRREQS_STALL[25] TCC_WRITE[25] TCC_RW_REQ[26] TCC_TOO_MANY_EA_WRREQS_STALL[26] TCC_WRITE[26] TCC_RW_REQ[27] TCC_TOO_MANY_EA_WRREQS_STALL[27] TCC_WRITE[27] TCC_RW_REQ[28] TCC_TOO_MANY_EA_WRREQS_STALL[28] TCC_WRITE[28] TCC_RW_REQ[29] TCC_TOO_MANY_EA_WRREQS_STALL[29] TCC_WRITE[29] TCC_RW_REQ[30] TCC_TOO_MANY_EA_WRREQS_STALL[30] TCC_WRITE[30] TCC_RW_REQ[31] TCC_TOO_MANY_EA_WRREQS_STALL[31] TCC_WRITE[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/device_filter/MI200/perfmon/pmc_perf_2.txt b/tests/workloads/device_filter/MI200/perfmon/pmc_perf_2.txt new file mode 100644 index 0000000000..70b69f8928 --- /dev/null +++ b/tests/workloads/device_filter/MI200/perfmon/pmc_perf_2.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_MUL_F32 SQ_INSTS_VALU_FMA_F32 SQ_INSTS_VALU_TRANS_F32 SQ_INSTS_VALU_ADD_F64 SQ_INSTS_VALU_MUL_F64 SQ_INSTS_VALU_FMA_F64 SQ_INSTS_VALU_TRANS_F64 SQ_INSTS_VALU_INT32 TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum TA_BUFFER_ATOMIC_WAVEFRONTS_sum TA_BUFFER_TOTAL_CYCLES_sum TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/device_filter/MI200/perfmon/pmc_perf_3.txt b/tests/workloads/device_filter/MI200/perfmon/pmc_perf_3.txt new file mode 100644 index 0000000000..e47f8e33c9 --- /dev/null +++ b/tests/workloads/device_filter/MI200/perfmon/pmc_perf_3.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_INT64 SQ_INSTS_SMEM SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum TD_COALESCABLE_WAVEFRONT_sum SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE CPF_CMP_UTCL1_STALL_ON_TRANSLATION TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/device_filter/MI200/perfmon/pmc_perf_4.txt b/tests/workloads/device_filter/MI200/perfmon/pmc_perf_4.txt new file mode 100644 index 0000000000..2d96f365a9 --- /dev/null +++ b/tests/workloads/device_filter/MI200/perfmon/pmc_perf_4.txt @@ -0,0 +1,5 @@ +pmc: SQ_WAVE_CYCLES SQ_WAIT_ANY SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_BUSY_CU_CYCLES SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE TCC_EA_WRREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WR_UNCACHED_32B_sum TCC_EA_WRREQ_DRAM_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/device_filter/MI200/perfmon/pmc_perf_5.txt b/tests/workloads/device_filter/MI200/perfmon/pmc_perf_5.txt new file mode 100644 index 0000000000..e50beed390 --- /dev/null +++ b/tests/workloads/device_filter/MI200/perfmon/pmc_perf_5.txt @@ -0,0 +1,5 @@ +pmc: SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU TCP_TCP_LATENCY_sum TCP_TCC_READ_REQ_LATENCY_sum TCP_TCC_WRITE_REQ_LATENCY_sum TCP_TCC_READ_REQ_sum TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN CPC_ME1_DC0_SPI_BUSY TCC_EA_WRREQ_STALL_sum TCC_EA_RDREQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RD_UNCACHED_32B_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/device_filter/MI200/perfmon/pmc_perf_6.txt b/tests/workloads/device_filter/MI200/perfmon/pmc_perf_6.txt new file mode 100644 index 0000000000..15a2277c1b --- /dev/null +++ b/tests/workloads/device_filter/MI200/perfmon/pmc_perf_6.txt @@ -0,0 +1,5 @@ +pmc: SQ_THREAD_CYCLES_VALU SQ_IFETCH SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TCP_TCC_NC_READ_REQ_sum TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN TCC_EA_RDREQ_DRAM_sum TCC_TAG_STALL_sum TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/device_filter/MI200/perfmon/pmc_perf_7.txt b/tests/workloads/device_filter/MI200/perfmon/pmc_perf_7.txt new file mode 100644 index 0000000000..b42ce91618 --- /dev/null +++ b/tests/workloads/device_filter/MI200/perfmon/pmc_perf_7.txt @@ -0,0 +1,5 @@ +pmc: SQ_WAVES_LT_32 SQ_WAVES_LT_16 SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TCP_TCC_UC_WRITE_REQ_sum TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR TCC_NORMAL_EVICT_sum TCC_ALL_TC_OP_INV_EVICT_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA_ATOMIC_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/device_filter/MI200/perfmon/pmc_perf_8.txt b/tests/workloads/device_filter/MI200/perfmon/pmc_perf_8.txt new file mode 100644 index 0000000000..21d4c7a998 --- /dev/null +++ b/tests/workloads/device_filter/MI200/perfmon/pmc_perf_8.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM_NORM SQ_INSTS_MFMA SQ_INSTS_VALU_MFMA_I8 SQ_INSTS_VALU_MFMA_F16 SQ_INSTS_VALU_MFMA_BF16 SQ_INSTS_VALU_MFMA_F32 SQ_INSTS_VALU_MFMA_F64 SQ_VALU_MFMA_BUSY_CYCLES TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TCP_TCC_CC_ATOMIC_REQ_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN TCC_EA_RDREQ_LEVEL_sum TCC_EA_WRREQ_LEVEL_sum TCC_EA_ATOMIC_LEVEL_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/device_filter/MI200/perfmon/pmc_perf_9.txt b/tests/workloads/device_filter/MI200/perfmon/pmc_perf_9.txt new file mode 100644 index 0000000000..9ffe5778c3 --- /dev/null +++ b/tests/workloads/device_filter/MI200/perfmon/pmc_perf_9.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_FLAT_LDS_ONLY SQ_INSTS_VALU_MFMA_MOPS_I8 SQ_INSTS_VALU_MFMA_MOPS_F16 SQ_INSTS_VALU_MFMA_MOPS_BF16 SQ_INSTS_VALU_MFMA_MOPS_F32 SQ_INSTS_VALU_MFMA_MOPS_F64 SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum TCP_PENDING_STALL_CYCLES_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/device_filter/MI200/perfmon/timestamps.txt b/tests/workloads/device_filter/MI200/perfmon/timestamps.txt new file mode 100644 index 0000000000..676cca1b80 --- /dev/null +++ b/tests/workloads/device_filter/MI200/perfmon/timestamps.txt @@ -0,0 +1,5 @@ +pmc: + +gpu: +range: +kernel: diff --git a/tests/workloads/device_filter/MI200/pmc_perf.csv b/tests/workloads/device_filter/MI200/pmc_perf.csv new file mode 100644 index 0000000000..c5ff376c7a --- /dev/null +++ b/tests/workloads/device_filter/MI200/pmc_perf.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_1,obj_1,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_2,obj_2,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,TCC_EA_ATOMIC_LEVEL_sum,wave_size_3,obj_3,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_4,obj_4,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_5,obj_5,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_6,obj_6,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_7,obj_7,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,wave_size_8,obj_8,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_9,obj_9,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,TD_COALESCABLE_WAVEFRONT_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_10,obj_10,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_11,obj_11,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_12,obj_12,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_DRAM_sum,TCC_TAG_STALL_sum,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,wave_size_13,obj_13,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,wave_size_14,obj_14,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_15,obj_15,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_16,obj_16,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_17,obj_17,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_18,obj_18,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f9a8d118ec0,0,393216,163840,0,0,0,0,0,18192,0.0,0.0,0.0,32768.0,0.0,0.0,404.0,32768.0,4096,16384,352,28648,1959,0,56.0,6.0,0.0,204115.0,64,0x7fc01fea8ec0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,64,0x7f7dbc560ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,41566892.0,35963380.0,0.0,64,0x7f1e9c334ec0,2266,4098,2268,6364,2304,4096,2304,6400,2258,4096,2258,6354,2293,4096,2293,6389,2294,4097,2295,6391,2296,4096,2296,6392,2265,4096,2265,6361,2259,4096,2259,6355,2264,4096,2264,6360,2268,4096,2268,6364,2307,4096,2307,6403,2259,4096,2259,6355,2296,4096,2296,6392,2241,4096,2241,6337,2295,4096,2295,6391,2265,4096,2265,6361,2296,4096,2296,6392,2289,4096,2289,6385,2272,4098,2274,6370,2285,4096,2285,6381,2273,4096,2273,6369,2261,4096,2261,6357,2284,4096,2284,6380,2481,4098,2483,6579,2310,4096,2310,6406,2299,4096,2299,6395,2290,4096,2290,6386,2270,4096,2270,6366,2284,4096,2284,6380,2274,4096,2274,6370,2263,4096,2263,6359,2285,4096,2285,6381,64,0x7f61a3950ec0,232256,129710,16384,0,16384,16384,32768,49152,29031,29031,1963928.0,1376026.0,3395.0,177094.0,1080961.0,0.0,1367746.0,1069337.0,230545,137846,29031,0,29031,0,928992.0,489441.0,0.0,0.0,64,0x7f85d9680ec0,0,1222161,4096,4096,0,1294970,4096,4096,0,1055300,4096,4096,0,1352829,4096,4096,0,1415575,4096,4096,0,1355138,4096,4096,0,1217705,4096,4096,0,1445989,4096,4096,0,1143331,4096,4096,0,1058640,4096,4096,0,1085347,4096,4096,0,1450439,4096,4096,0,1391096,4096,4096,0,1303465,4096,4096,0,1164874,4096,4096,0,1264499,4096,4096,0,1245139,4096,4096,0,1586344,4096,4096,0,1067662,4096,4096,0,1645609,4096,4096,0,1179812,4096,4096,0,1473415,4096,4096,0,1531899,4096,4096,0,1149818,4096,4096,0,1272169,4096,4096,0,1059596,4096,4096,0,1204653,4096,4096,0,1266661,4096,4096,0,1397846,4096,4096,0,1155763,4096,4096,0,1270045,4096,4096,0,1393299,4096,4096,64,0x7f89fa890ec0,1270,116237,0,0,65536,63800,56,1680,64,0x7fd0d2be8ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65551.0,0.0,0.0,0.0,64,0x7f08643d4ec0,6309,0,4096,6323,0,4096,6411,0,4096,6397,0,4096,6331,0,4096,6323,0,4096,6388,0,4096,6485,0,4096,6486,0,4096,6311,0,4096,6326,0,4096,6414,0,4096,6396,0,4096,6332,0,4096,6328,0,4096,6389,0,4096,6395,0,4096,6402,0,4096,6292,0,4096,6337,0,4096,6385,0,4096,6347,0,4096,6351,0,4096,6499,0,4096,6337,0,4096,6395,0,4096,6404,0,4096,6288,0,4096,6339,0,4096,6386,0,4096,6351,0,4096,6354,0,4096,64,0x7ff854f58ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,10145,0,814,27538,0,73243.0,131072.0,0.0,65568.0,64,0x7f4126794ec0,0,0,0,224,0,65536,64169,56,64,0x7fd0b879cec0,10377321,9384630,648627,344064,1565336,0,0,163840,832.0,515136.0,0.0,524288.0,252802.0,32768.0,441329,0,0,11202,131072.0,131072.0,0.0,131072.0,64,0x7fc6d5a1cec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131082.0,34350.0,46165.0,19371.0,64,0x7fd0d002cec0,114688,0,32768,32768,16384,16384,65536,49152,28333967.0,87418890.0,38825053.0,131072.0,0.0,214467.0,0,0,15472,301.0,131080.0,0.0,8.0,64,0x7ff4297c4ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,12322,18857,7191,545,0,26141,204027.0,0.0,72944.0,131083.0,64,0x7f0b2a81cec0,32768,32768,0,64,0x7fda70128ec0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,197,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,362,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4097,0,0,0,4100,0,0,0,4096,0,0,0,4096,0,0,0,4099,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,64,0x7f3c3f648ec0,0,0,0,1001867,0,0,0,1034501,0,0,0,1039801,0,0,0,1149913,16,0,0,1127038,0,0,0,1061247,0,0,0,1102693,18,0,0,1303069,0,0,0,1109414,0,0,0,1002710,0,0,0,1023850,0,0,0,1088630,0,0,0,1100645,0,0,0,1135139,0,0,0,981449,7,0,0,1207898,0,0,0,1037454,61,0,0,1205959,0,0,0,954309,0,0,0,1088841,0,0,0,1094129,0,0,0,1084983,0,0,0,1109150,0,0,0,1086548,0,0,0,972888,0,0,0,1066849,0,0,0,1000714,0,0,0,1127056,43,0,0,1104743,0,0,0,1069381,0,0,0,1101394,0,0,0,1160834,64,0x7f53b09e8ec0,0,0,0,0,0,0,168,56,131072.0,131072.0,0.0,951355.0,199121780771567,199121780791247 +1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f9a8d118ec0,0,393216,163840,0,0,0,0,0,27713,0.0,0.0,0.0,32768.0,0.0,0.0,179.0,32768.0,4096,16384,302,36962,1920,0,56.0,0.0,0.0,200346.0,64,0x7fc01fea8ec0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,64,0x7f7dbc560ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,118471975.0,66267208.0,0.0,64,0x7f1e9c334ec0,2161,4099,2164,6260,2151,4098,2153,6249,2178,4096,2178,6274,2142,4096,2142,6238,2189,4097,2190,6286,2136,4096,2136,6232,2178,4096,2178,6274,2169,4096,2169,6265,2175,4096,2175,6271,2165,4096,2165,6261,2156,4096,2156,6252,2178,4096,2178,6274,2145,4096,2145,6241,2130,4096,2130,6226,2141,4096,2141,6237,2186,4096,2186,6282,2159,4097,2160,6256,2172,4096,2172,6268,2168,4098,2170,6266,2182,4096,2182,6278,2164,4096,2164,6260,2162,4096,2162,6258,2147,4096,2147,6243,2141,4096,2141,6237,2148,4096,2148,6244,2166,4096,2166,6262,2176,4096,2176,6272,2172,4096,2172,6268,2177,4097,2178,6274,2167,4096,2167,6263,2165,4096,2165,6261,2149,4096,2149,6245,64,0x7f61a3950ec0,328560,221627,16384,0,16384,16384,32768,49152,41069,41069,3158598.0,2460968.0,5037.0,337420.0,1680863.0,0.0,2448414.0,2138415.0,328552,231375,41069,0,41069,0,1314208.0,766352.0,0.0,0.0,64,0x7f85d9680ec0,0,3232678,2856,2856,0,3335659,2888,2888,0,3761389,2866,2866,0,3639512,2880,2880,0,4397834,2868,2868,0,4507952,2844,2844,0,3066646,2852,2852,0,4327187,2824,2824,0,3471679,2824,2824,0,3920499,2852,2852,0,3591748,2890,2890,0,3687937,2864,2864,0,3014193,2880,2880,0,3520333,2864,2864,0,3856037,2840,2840,0,4205632,2852,2852,0,3989474,2816,2816,0,3539459,2852,2852,0,3836590,2880,2880,0,3720161,2872,2872,0,4301203,2840,2840,0,4296486,2892,2892,0,3771862,2820,2820,0,5227377,2848,2848,0,3937104,2848,2848,0,4223077,2816,2816,0,3659150,2852,2852,0,4100095,2878,2878,0,3498362,2864,2864,0,3425720,2840,2840,0,3595413,2892,2892,0,4396528,2820,2820,64,0x7f89fa890ec0,0,184365,0,0,65536,63800,56,1680,64,0x7fd0d2be8ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65554.0,0.0,0.0,0.0,64,0x7f08643d4ec0,6270,0,4096,6284,0,4096,6261,0,4096,6270,0,4096,6274,0,4096,6308,0,4096,6257,0,4096,6261,0,4096,6260,0,4096,6269,0,4096,6286,0,4096,6259,0,4096,6276,0,4096,6276,0,4096,6312,0,4096,6256,0,4096,6271,0,4096,6242,0,4096,6266,0,4096,6291,0,4096,6262,0,4096,6266,0,4096,6279,0,4096,6318,0,4096,6319,0,4096,6270,0,4096,6246,0,4096,6267,0,4096,6289,0,4096,6258,0,4096,6268,0,4096,6283,0,4096,64,0x7ff854f58ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,21157,0,3388,39296,0,69259.0,131072.0,0.0,45450.0,64,0x7f4126794ec0,0,0,0,56,0,65536,65536,0,64,0x7fd0b879cec0,19081381,17928759,808558,344064,2721065,0,0,163840,832.0,515144.0,0.0,524288.0,663743.0,32768.0,958763,0,0,13853,90744.0,90744.0,0.0,90744.0,64,0x7fc6d5a1cec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131074.0,89223.0,45570.0,0.0,64,0x7fd0d002cec0,114688,0,32768,32768,16384,16384,65536,49152,57664325.0,203725507.0,46739559.0,131072.0,0.0,538226.0,0,0,25176,5889.0,131084.0,0.0,22.0,64,0x7ff4297c4ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,27800,27794,8751,550,0,35684,200707.0,0.0,69632.0,131075.0,64,0x7f0b2a81cec0,32768,32768,0,64,0x7fda70128ec0,4096,0,121,0,4096,0,39,0,4097,0,368,0,4096,0,521,0,4096,0,41,0,4096,0,573,0,4096,0,419,0,4096,0,260,0,4096,0,1208,0,4096,0,113,0,4096,0,386,0,4096,0,1155,0,4096,0,865,0,4096,0,0,0,4096,0,1421,0,4097,0,370,0,4097,0,1191,0,4096,0,1103,0,4097,0,312,0,4097,0,1088,0,4100,0,151,0,4096,0,1553,0,4096,0,1450,0,4096,0,422,0,4096,0,165,0,4096,0,313,0,4096,0,42,0,4096,0,48,0,4097,0,1560,0,4096,0,26,0,4098,0,30,0,4096,0,155,0,64,0x7f3c3f648ec0,595,0,0,1975494,231,0,0,1999416,266,0,0,1962958,486,0,0,1859654,452,0,0,2029586,2134,0,0,2497031,259,0,0,1914490,679,0,0,2226582,1021,0,0,2186328,310,0,0,1754375,448,0,0,2277055,512,0,0,1972859,452,0,0,1747124,669,0,0,2298676,1081,0,0,2352290,844,0,0,2150303,270,0,0,2217530,1097,0,0,2314692,744,0,0,2035454,982,0,0,2335155,341,0,0,1930718,2722,0,0,2599638,0,0,0,1731854,163,0,0,2117254,170,0,0,2182808,871,0,0,2212921,400,0,0,2010053,375,0,0,1878286,1125,0,0,2240574,68,0,0,1744642,1513,0,0,2182432,336,0,0,2284276,64,0x7f53b09e8ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2043679.0,199121780810127,199121780825807 +2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f9a8d118ec0,0,393216,163840,0,0,0,0,0,29721,0.0,0.0,0.0,32768.0,0.0,0.0,272.0,32768.0,4096,16384,302,40740,1956,0,56.0,9.0,0.0,201143.0,64,0x7fc01fea8ec0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,64,0x7f7dbc560ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,119995005.0,71157945.0,0.0,64,0x7f1e9c334ec0,2174,4099,2177,6273,2198,4098,2200,6296,2164,4096,2164,6260,2183,4096,2183,6279,2219,4097,2220,6316,2182,4096,2182,6278,2161,4096,2161,6257,2165,4096,2165,6261,2162,4096,2162,6258,2174,4096,2174,6270,2197,4096,2197,6293,2161,4096,2161,6257,2184,4096,2184,6280,2164,4096,2164,6260,2176,4096,2176,6272,2158,4096,2158,6254,2165,4097,2166,6262,2180,4096,2180,6276,2174,4098,2176,6272,2158,4096,2158,6254,2204,4096,2204,6300,2171,4096,2171,6267,2170,4096,2170,6266,2173,4096,2173,6269,2175,4096,2175,6271,2169,4096,2169,6265,2183,4096,2183,6279,2177,4096,2177,6273,2161,4097,2162,6258,2207,4096,2207,6303,2173,4096,2173,6269,2172,4096,2172,6268,64,0x7f61a3950ec0,331976,223954,16384,0,16384,16384,32768,49152,41496,41496,3188123.0,2487009.0,4110.0,395442.0,1802846.0,0.0,2474216.0,2164747.0,331968,233067,41496,0,41496,0,1327872.0,773543.0,0.0,0.0,64,0x7f85d9680ec0,0,3174388,2828,2828,0,3079431,2872,2872,0,4333494,2860,2860,0,3418129,2868,2868,0,4391738,2888,2888,0,3919640,2856,2856,0,2924396,2856,2856,0,3585551,2812,2812,0,3542793,2812,2812,0,3521330,2828,2828,0,3163722,2872,2872,0,4322369,2864,2864,0,2595513,2870,2870,0,3097719,2888,2888,0,3966381,2856,2856,0,3072174,2856,2856,0,3254967,2808,2808,0,5016060,2850,2850,0,3044454,2842,2842,0,4084529,2852,2852,0,3183913,2844,2844,0,4116338,2896,2896,0,4476701,2824,2824,0,3439648,2824,2824,0,4469803,2824,2824,0,3515651,2804,2804,0,3608618,2844,2844,0,3926221,2836,2836,0,3799220,2856,2856,0,4531322,2840,2840,0,3175626,2896,2896,0,2960598,2824,2824,64,0x7f89fa890ec0,0,185461,0,0,65536,63800,56,1680,64,0x7fd0d2be8ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65552.0,0.0,0.0,0.0,64,0x7f08643d4ec0,6230,0,4096,6247,0,4096,6271,0,4096,6262,0,4096,6268,0,4096,6297,0,4096,6260,0,4096,6261,0,4096,6263,0,4096,6231,0,4096,6249,0,4096,6272,0,4096,6262,0,4096,6271,0,4096,6296,0,4096,6258,0,4096,6252,0,4096,6279,0,4096,6258,0,4096,6249,0,4096,6248,0,4096,6278,0,4096,6256,0,4096,6282,0,4096,6284,0,4096,6253,0,4096,6283,0,4096,6263,0,4096,6251,0,4096,6246,0,4096,6279,0,4096,6256,0,4096,64,0x7ff854f58ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,21726,0,2836,38956,0,69585.0,131072.0,0.0,45457.0,64,0x7f4126794ec0,0,0,0,56,0,65536,65536,0,64,0x7fd0b879cec0,18992598,17897611,750923,344064,2740347,0,0,163840,832.0,515158.0,0.0,524288.0,568711.0,32768.0,952685,0,0,13344,91058.0,91058.0,0.0,91058.0,64,0x7fc6d5a1cec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131084.0,103025.0,45587.0,0.0,64,0x7fd0d002cec0,114688,0,32768,32768,16384,16384,65536,49152,57005676.0,199044416.0,48768208.0,131072.0,0.0,508170.0,0,0,25041,4173.0,131082.0,0.0,18.0,64,0x7ff4297c4ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,32824,28015,9582,2832,0,39458,200837.0,0.0,69750.0,131087.0,64,0x7f0b2a81cec0,32768,32768,0,64,0x7fda70128ec0,4096,0,238,0,4096,0,85,0,4097,0,0,0,4096,0,122,0,4096,0,18,0,4096,0,437,0,4096,0,120,0,4096,0,1206,0,4096,0,532,0,4096,0,127,0,4096,0,287,0,4096,0,0,0,4096,0,318,0,4096,0,241,0,4096,0,145,0,4097,0,8,0,4097,0,24,0,4096,0,1914,0,4097,0,57,0,4097,0,1065,0,4101,0,113,0,4096,0,852,0,4096,0,222,0,4096,0,1719,0,4096,0,988,0,4096,0,43,0,4096,0,0,0,4096,0,750,0,4097,0,248,0,4096,0,14,0,4098,0,1554,0,4096,0,69,0,64,0x7f3c3f648ec0,554,0,0,2261820,1209,0,0,2575791,0,0,0,1621827,74,0,0,2037275,1180,0,0,2524103,404,0,0,2022422,0,0,0,1430425,0,0,0,1570629,0,0,0,1436278,0,0,0,1816981,0,0,0,2176448,0,0,0,1730391,0,0,0,1903018,514,0,0,2162762,284,0,0,2032468,0,0,0,1676391,0,0,0,1652474,0,0,0,1749102,92,0,0,1948161,0,0,0,1995391,0,0,0,1534929,69,0,0,2085733,332,0,0,2008735,201,0,0,2284680,0,0,0,2025651,0,0,0,1369773,0,0,0,1833494,0,0,0,1956247,0,0,0,1711645,0,0,0,1547265,0,0,0,1706631,322,0,0,2191072,64,0x7f53b09e8ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2033587.0,199121780890127,199121780906607 diff --git a/tests/workloads/device_filter/MI200/roofline.csv b/tests/workloads/device_filter/MI200/roofline.csv new file mode 100644 index 0000000000..f9b85b413e --- /dev/null +++ b/tests/workloads/device_filter/MI200/roofline.csv @@ -0,0 +1,2 @@ +device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh +0,1388.6548,1388.108,1389.2015,5015.9297,5012.8184,5019.041,9223.8145,9223.0537,9224.5752,18052.502,18051.623,18053.381,20935.658,20875.303,20996.014,20266.73,20266.039,20267.422,170456.62,170450.44,170462.81,164889.83,164885.14,164894.52,41426.273,41425.676,41426.871,41480.551,41480.051,41481.051,166346.09,165855.02,166837.17 diff --git a/tests/workloads/device_filter/MI200/sysinfo.csv b/tests/workloads/device_filter/MI200/sysinfo.csv new file mode 100644 index 0000000000..2819017c4f --- /dev/null +++ b/tests/workloads/device_filter/MI200/sysinfo.csv @@ -0,0 +1,2 @@ +workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd +device_filter,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 02:29:36 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/device_filter/MI200/timestamps.csv b/tests/workloads/device_filter/MI200/timestamps.csv new file mode 100644 index 0000000000..fa4e99ac33 --- /dev/null +++ b/tests/workloads/device_filter/MI200/timestamps.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,334902,334902,1048576,256,0,0,8,0,16,64,0x0,0x7fc789a84ec0,199121780746738,199121780771567,199121780791247,199121780807012 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,334902,334902,1048576,256,0,0,8,0,16,64,0x0,0x7fc789a84ec0,199121780801932,199121780810127,199121780825807,199121780887234 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,334902,334902,1048576,256,0,0,8,0,16,64,0x0,0x7fc789a84ec0,199121780836327,199121780890127,199121780906607,199121780907502 diff --git a/tests/workloads/device_inv_int/MI100/SQ_IFETCH_LEVEL.csv b/tests/workloads/device_inv_int/MI100/SQ_IFETCH_LEVEL.csv index 2a38d4c577..9336186cbd 100644 --- a/tests/workloads/device_inv_int/MI100/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/device_inv_int/MI100/SQ_IFETCH_LEVEL.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2858631,2858631,1048576,256,0,0,8,8,16,64,0x0,0x7f306d022e80,48693,48693,16384,65536,14587,1861268,2187837651454006,2187843682406959,2187843682431279,2187837659153650 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2858631,2858631,1048576,256,0,0,8,8,16,64,0x0,0x7f306d022e80,43450,43450,16384,65536,8185,1048576,2187837659175581,2187843682524719,2187843682543599,2187837659498637 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2858631,2858631,1048576,256,0,0,8,8,16,64,0x0,0x7f306d022e80,42429,42429,16384,65536,8118,1048580,2187837659530768,2187843682565519,2187843682585039,2187837659713381 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,163106,163106,1048576,256,0,0,8,8,16,64,0x0,0x7fd0d59ece80,47824,47824,16384,65536,14415,1841604,194245701996654,194257894802798,194257894826478,194245709757699 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,163106,163106,1048576,256,0,0,8,8,16,64,0x0,0x7fd0d59ece80,42607,42607,16384,65536,8172,1048580,194245709780272,194257894909678,194257894929198,194245710148639 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,163106,163106,1048576,256,0,0,8,8,16,64,0x0,0x7fd0d59ece80,42359,42359,16384,65536,8301,1048580,194245710180850,194257894949838,194257894968558,194245710367043 diff --git a/tests/workloads/device_inv_int/MI100/SQ_INST_LEVEL_LDS.csv b/tests/workloads/device_inv_int/MI100/SQ_INST_LEVEL_LDS.csv index 0c4f5c5d42..ee64ae70f6 100644 --- a/tests/workloads/device_inv_int/MI100/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/device_inv_int/MI100/SQ_INST_LEVEL_LDS.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2862637,2862637,1048576,256,0,0,8,8,16,64,0x0,0x7f5be8850e80,0,0,0,2187848852549207,2187843682406959,2187843682431279,2187848859975488 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2862637,2862637,1048576,256,0,0,8,8,16,64,0x0,0x7f5be8850e80,0,0,0,2187848859994684,2187843682524719,2187843682543599,2187848860303414 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2862637,2862637,1048576,256,0,0,8,8,16,64,0x0,0x7f5be8850e80,0,0,0,2187848860332038,2187843682565519,2187843682585039,2187848860506154 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,163295,163295,1048576,256,0,0,8,8,16,64,0x0,0x7f1c0fd10e80,0,0,0,194246201989340,194257894802798,194257894826478,194246209682066 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,163295,163295,1048576,256,0,0,8,8,16,64,0x0,0x7f1c0fd10e80,0,0,0,194246209701843,194257894909678,194257894929198,194246209982224 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,163295,163295,1048576,256,0,0,8,8,16,64,0x0,0x7f1c0fd10e80,0,0,0,194246210010568,194257894949838,194257894968558,194246210167986 diff --git a/tests/workloads/device_inv_int/MI100/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/device_inv_int/MI100/SQ_INST_LEVEL_SMEM.csv index 52248b7375..4ac1a5e172 100644 --- a/tests/workloads/device_inv_int/MI100/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/device_inv_int/MI100/SQ_INST_LEVEL_SMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2861181,2861181,1048576,256,0,0,8,8,16,64,0x0,0x7f4afbf56e80,65536,210560,26916328,2187844811633072,2187843682406959,2187843682431279,2187844819158530 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2861181,2861181,1048576,256,0,0,8,8,16,64,0x0,0x7f4afbf56e80,65536,180192,23099952,2187844819178597,2187843682524719,2187843682543599,2187844819476596 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2861181,2861181,1048576,256,0,0,8,8,16,64,0x0,0x7f4afbf56e80,65536,192032,24611128,2187844819505521,2187843682565519,2187843682585039,2187844819677133 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,163481,163481,1048576,256,0,0,8,8,16,64,0x0,0x7f41294aee80,65536,202308,25952544,194246693370130,194257894802798,194257894826478,194246701328779 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,163481,163481,1048576,256,0,0,8,8,16,64,0x0,0x7f41294aee80,65536,182670,23344896,194246701348828,194257894909678,194257894929198,194246701641622 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,163481,163481,1048576,256,0,0,8,8,16,64,0x0,0x7f41294aee80,65536,181360,23270400,194246701670366,194257894949838,194257894968558,194246701840689 diff --git a/tests/workloads/device_inv_int/MI100/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/device_inv_int/MI100/SQ_INST_LEVEL_VMEM.csv index 945cb9c526..5df6e22d20 100644 --- a/tests/workloads/device_inv_int/MI100/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/device_inv_int/MI100/SQ_INST_LEVEL_VMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2859725,2859725,1048576,256,0,0,8,8,16,64,0x0,0x7f77365b0e80,32768,648628,83041940,2187840584839972,2187843682406959,2187843682431279,2187840592444006 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2859725,2859725,1048576,256,0,0,8,8,16,64,0x0,0x7f77365b0e80,32768,665455,85189652,2187840592464465,2187843682524719,2187843682543599,2187840592804623 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2859725,2859725,1048576,256,0,0,8,8,16,64,0x0,0x7f77365b0e80,32768,630264,80689312,2187840592833738,2187843682565519,2187843682585039,2187840593022011 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,163664,163664,1048576,256,0,0,8,8,16,64,0x0,0x7f0703804e80,32768,645357,82598164,194247183554014,194257894802798,194257894826478,194247191243955 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,163664,163664,1048576,256,0,0,8,8,16,64,0x0,0x7f0703804e80,32768,670028,85765020,194247191265515,194257894909678,194257894929198,194247191518214 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,163664,163664,1048576,256,0,0,8,8,16,64,0x0,0x7f0703804e80,32768,644220,82464252,194247191549022,194257894949838,194257894968558,194247191732850 diff --git a/tests/workloads/device_inv_int/MI100/SQ_LEVEL_WAVES.csv b/tests/workloads/device_inv_int/MI100/SQ_LEVEL_WAVES.csv index 30971937d6..91bf93a983 100644 --- a/tests/workloads/device_inv_int/MI100/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/device_inv_int/MI100/SQ_LEVEL_WAVES.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2861545,2861545,1048576,256,0,0,8,8,16,64,0x0,0x7f66b3458e80,49547,49547,16868,396384,16384,26740947,242792,0,107460160,2187845706739501,2187843682406959,2187843682431279,2187845714403057 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2861545,2861545,1048576,256,0,0,8,8,16,64,0x0,0x7f66b3458e80,43543,43543,13929,348352,16384,25132807,235648,0,101028984,2187845714431621,2187843682524719,2187843682543599,2187845714748586 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2861545,2861545,1048576,256,0,0,8,8,16,64,0x0,0x7f66b3458e80,43359,43359,14054,346880,16384,24431177,229443,0,98220436,2187845714786918,2187843682565519,2187843682585039,2187845714981864 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,163849,163849,1048576,256,0,0,8,8,16,64,0x0,0x7f24c9b52e80,48152,48152,17278,385224,16384,24999057,233984,0,100494368,194247678463586,194257894802798,194257894826478,194247686158065 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,163849,163849,1048576,256,0,0,8,8,16,64,0x0,0x7f24c9b52e80,42999,42999,13485,344000,16384,25054375,233600,0,100720288,194247686185978,194257894909678,194257894929198,194247686516484 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,163849,163849,1048576,256,0,0,8,8,16,64,0x0,0x7f24c9b52e80,43151,43151,13780,345216,16384,23923902,232092,0,96192684,194247686554565,194257894949838,194257894968558,194247686738744 diff --git a/tests/workloads/device_inv_int/MI100/pmc_dispatch_info.csv b/tests/workloads/device_inv_int/MI100/pmc_dispatch_info.csv new file mode 100644 index 0000000000..17300ae9af --- /dev/null +++ b/tests/workloads/device_inv_int/MI100/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) ",2 +1,"vecCopy(double*, double*, double*, int, int) ",2 +2,"vecCopy(double*, double*, double*, int, int) ",2 diff --git a/tests/workloads/device_inv_int/MI100/pmc_perf.csv b/tests/workloads/device_inv_int/MI100/pmc_perf.csv index 521f7284b4..630c08cd36 100644 --- a/tests/workloads/device_inv_int/MI100/pmc_perf.csv +++ b/tests/workloads/device_inv_int/MI100/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_1,obj_1,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_2,obj_2,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_3,obj_3,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_4,obj_4,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_5,obj_5,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_6,obj_6,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_7,obj_7,TCC_EA_ATOMIC_LEVEL_sum,wave_size_8,obj_8,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_9,obj_9,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_10,obj_10,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_11,obj_11,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_12,obj_12,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_13,obj_13,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_14,obj_14,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_15,obj_15,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_16,obj_16,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f0f15e9ce80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,83850.0,157724.0,64,0x7f78aacc2e80,4096,0,1809,0,4096,0,1486,0,4096,0,10,0,4099,0,0,0,4096,0,2430,0,4096,0,2858,0,4096,0,14,0,4096,0,213,0,4096,0,1805,0,4096,0,1016,0,4096,0,2282,0,4096,0,424,0,4096,0,1546,0,4096,0,2367,0,4097,0,3039,0,4096,0,222,0,4096,0,603,0,4096,0,2979,0,4096,0,0,0,4096,0,851,0,4096,0,0,0,4368,0,5823,0,4096,0,756,0,4096,0,470,0,4096,0,2239,0,4144,0,1429,0,4096,0,117,0,4144,0,16,0,4096,0,793,0,4096,0,1569,0,4096,0,0,0,4096,0,106,0,64,0x7f3e903f6e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131447.0,0.0,742.0,131446.0,64,0x7f5207bbae80,383472,230437,3361985,16384,24810359,144,48,0,47933,47933,3808992.0,2988866.0,7672.0,1199121.0,2121014.0,0.0,2979905.0,2668348.0,382015,240366,47933,0,47933,0,1533856.0,952676.0,0.0,0.0,64,0x7fe3613dce80,1993346,360448,163840,0,0,180224,114688,0,72137845.0,204245558.0,80040364.0,131072.0,0.0,600159.0,0,0,26531,76707.0,0.0,0.0,76707.0,64,0x7fdc9c4a8e80,0,3604738,4096,4096,0,4585940,4096,4096,0,4267033,4096,4096,0,3446747,4096,4096,0,3793604,4096,4096,0,3120752,4096,4096,0,4865543,4096,4096,0,4041474,4096,4096,0,3471550,4096,4096,0,3791145,4096,4096,0,3977519,4096,4096,0,4599172,4096,4096,0,3296690,4096,4096,0,3568287,4096,4096,0,4574830,4096,4096,0,3915129,4096,4096,0,3511945,4096,4096,0,4098794,4096,4096,0,4971185,4096,4096,0,4701434,4096,4096,0,3999737,4096,4096,0,4198270,4096,4096,0,4453092,4096,4096,0,3251912,4096,4096,0,3352648,4096,4096,0,3256301,4096,4096,0,4508553,4096,4096,0,3473699,4096,4096,0,4743581,4096,4096,0,3297993,4096,4096,0,3332103,4096,4096,0,4891791,4096,4096,64,0x7fc1c877ce80,131072.0,131072.0,0.0,2540052.0,0.0,0.0,122645628.0,58889530.0,64,0x7ff6a8160e80,0.0,64,0x7fbf7ebc0e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86702.0,44370.0,131112.0,0.0,64,0x7f4ea442ce80,4693,0,0,2160231,3989,0,0,2077401,5526,0,0,2200155,3383,0,0,1904609,2545,0,0,1888302,728,0,0,1576011,2322,0,0,1910602,2010,0,0,1851259,5416,0,0,2299593,2128,0,0,1792462,4163,0,0,2034097,565,0,0,1589958,5431,0,0,2229071,2950,0,0,1928414,1016,0,0,1660636,4404,0,0,2088951,2304,0,0,1867755,702,0,0,1561880,5809,0,0,2158254,1529,0,0,1659923,2766,0,0,1874448,843,0,0,1607340,4223,0,0,2034999,4053,0,0,2079986,1251,0,0,1782637,1027,0,0,1645981,3675,0,0,1962876,2300,0,0,1772139,6370,0,0,2185656,1696,0,0,1745224,3911,0,0,1965501,1878,0,0,1773081,64,0x7fc40ea66e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,64,0x7f54e5e90e80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,141,8195,4240,8336,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8360,4264,8360,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8196,4100,8196,64,0x7facf8386e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,46766,0,131517.0,131072.0,0.0,131104.0,64,0x7f79b459ee80,32768,0,0,0,16384,16384,393216,22590402,960.0,513877.0,0.0,524288.0,1064724.0,32768.0,0,0,0,17622,131072.0,131072.0,0.0,131072.0,64,0x7f5e4f946e80,0,0,192,0,65536,64514,48,1331,32988,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,539,49360,1742,0,48.0,533.0,0.0,262288.0,64,0x7f0e7a4a8e80,190320,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,14382,30766,10004,550,0,46610,262603.0,0.0,188.0,262415.0,64,0x7f191a560e80,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,0,49179,0,0,2187843682406959,2187843682431279 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f0f15e9ce80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,64351.0,133143.0,64,0x7f78aacc2e80,4096,0,995,0,4096,0,778,0,4096,0,1730,0,4096,0,463,0,4096,0,1002,0,4096,0,1325,0,4096,0,1025,0,4096,0,2145,0,4098,0,1434,0,4096,0,1246,0,4097,0,295,0,4096,0,2005,0,4096,0,1368,0,4096,0,2235,0,4100,0,1892,0,4096,0,588,0,4096,0,2598,0,4096,0,3120,0,4096,0,7199,0,4096,0,1483,0,4096,0,402,0,4338,0,1599,0,4096,0,2888,0,4096,0,773,0,4096,0,982,0,4144,0,515,0,4096,0,2914,0,4144,0,929,0,4096,0,932,0,4096,0,4289,0,4096,0,433,0,4096,0,653,0,64,0x7f3e903f6e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131476.0,0.0,804.0,131474.0,64,0x7f5207bbae80,404752,260382,3813812,16384,28132994,0,96,0,50593,50593,4195766.0,3408194.0,3545.0,1276530.0,2465194.0,0.0,3389534.0,3074838.0,404744,270167,50593,0,50593,1091,1618976.0,906683.0,1.0,0.0,64,0x7fe3613dce80,1594799,360448,163840,0,0,180224,114688,0,73990968.0,195542709.0,78183566.0,131072.0,0.0,604206.0,0,0,26382,65878.0,0.0,0.0,65878.0,64,0x7fdc9c4a8e80,0,4051112,2676,2676,0,4041108,2720,2720,0,3478570,2688,2688,0,5111679,2720,2720,0,3644707,2669,2669,0,3532686,2728,2728,0,4622818,2716,2716,0,4395017,2718,2718,0,3081633,2676,2676,0,4668825,2676,2676,0,4266747,2732,2732,0,4015397,2744,2744,0,3736606,2686,2686,0,3321874,2693,2693,0,4316212,2696,2696,0,4227796,2728,2728,0,2983811,2676,2676,0,4197024,2714,2714,0,4567990,2688,2688,0,4184753,2728,2728,0,2870532,2676,2676,0,3761157,2734,2734,0,3584429,2671,2671,0,3420079,2702,2702,0,2788547,2668,2668,0,4223034,2708,2708,0,3967979,2718,2718,0,4150394,2724,2724,0,3602395,2668,2668,0,3457494,2706,2706,0,3468765,2720,2720,0,5519755,2698,2698,64,0x7fc1c877ce80,131072.0,131072.0,0.0,2631333.0,0.0,0.0,103319261.0,57890611.0,64,0x7ff6a8160e80,0.0,64,0x7fbf7ebc0e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86718.0,0.0,131113.0,0.0,64,0x7f4ea442ce80,1453,0,0,1403646,2083,0,0,1462053,2678,0,0,1501103,4270,0,0,1738551,1047,0,0,1327384,2483,0,0,1572061,1484,0,0,1422490,3218,0,0,1744533,1559,0,0,1377158,2524,0,0,1553708,312,0,0,1188208,2184,0,0,1637447,771,0,0,1267928,5124,0,0,1805083,515,0,0,1216849,4619,0,0,1736502,1825,0,0,1450823,1039,0,0,1353757,2896,0,0,1554454,948,0,0,1319921,197,0,0,1220378,2809,0,0,1583533,1614,0,0,1463415,4330,0,0,1700620,617,0,0,1320511,1222,0,0,1415643,3199,0,0,1641414,5535,0,0,1728794,1740,0,0,1400839,4621,0,0,1681592,1056,0,0,1245423,2705,0,0,1608985,64,0x7fc40ea66e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f54e5e90e80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8194,4098,8194,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8360,4264,8360,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,64,0x7facf8386e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,3678,39227,0,131385.0,131072.0,0.0,86647.0,64,0x7f79b459ee80,32768,0,0,0,16384,16384,393216,22546290,960.0,513895.0,0.0,524288.0,951731.0,32768.0,0,0,0,13296,86618.0,86618.0,0.0,86618.0,64,0x7f5e4f946e80,0,0,48,0,65536,65536,0,0,32447,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,458,45684,1736,0,48.0,549.0,0.0,262144.0,64,0x7f0e7a4a8e80,595845,0,0,65536,62560,96,2880,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,14097,30481,26786,6313,0,43963,262913.0,0.0,94.0,262819.0,64,0x7f191a560e80,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,0,43792,0,0,2187843682524719,2187843682543599 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f0f15e9ce80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,36142.0,100417.0,64,0x7f78aacc2e80,4096,0,2887,0,4096,0,1896,0,4096,0,1355,0,4096,0,674,0,4096,0,2332,0,4096,0,756,0,4096,0,1178,0,4096,0,62,0,4098,0,2595,0,4096,0,771,0,4097,0,1955,0,4096,0,1779,0,4096,0,1285,0,4096,0,1329,0,4100,0,950,0,4096,0,28,0,4096,0,1568,0,4096,0,1955,0,4096,0,3226,0,4096,0,898,0,4096,0,783,0,4366,0,5550,0,4096,0,621,0,4096,0,23,0,4096,0,1117,0,4144,0,2705,0,4096,0,957,0,4144,0,568,0,4096,0,1023,0,4096,0,652,0,4096,0,2869,0,4096,0,1687,0,64,0x7f3e903f6e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131392.0,0.0,638.0,131391.0,64,0x7f5207bbae80,336416,226914,3317645,16384,24684994,0,48,0,42051,42051,3693612.0,3036934.0,5739.0,963065.0,2103864.0,0.0,3027948.0,2716876.0,336408,236451,42051,0,42051,0,1345632.0,791443.0,0.0,0.0,64,0x7fe3613dce80,1365751,360448,163840,0,0,180224,114688,0,72176233.0,198948855.0,75443586.0,131072.0,0.0,645324.0,0,0,25546,63900.0,0.0,0.0,63900.0,64,0x7fdc9c4a8e80,0,2869900,2702,2702,0,2984662,2700,2700,0,3143822,2700,2700,0,3199680,2726,2726,0,2477745,2712,2712,0,3062864,2696,2696,0,3282513,2760,2760,0,3338896,2728,2728,0,2819761,2688,2688,0,2685114,2666,2666,0,3462555,2732,2732,0,3651008,2726,2726,0,2720493,2712,2712,0,2861909,2680,2680,0,2899788,2718,2718,0,3190254,2722,2722,0,2731290,2727,2727,0,3244031,2672,2672,0,4624944,2717,2717,0,3659512,2734,2734,0,2756363,2736,2736,0,4379239,2722,2722,0,5480708,2697,2697,0,2889464,2714,2714,0,2832733,2706,2706,0,3000202,2682,2682,0,4560562,2740,2740,0,2804984,2712,2712,0,2573922,2708,2708,0,2666828,2700,2700,0,3099584,2716,2716,0,4687973,2722,2722,64,0x7fc1c877ce80,131072.0,131072.0,0.0,2608383.0,0.0,0.0,129833075.0,46556315.0,64,0x7ff6a8160e80,0.0,64,0x7fbf7ebc0e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86733.0,0.0,131113.0,0.0,64,0x7f4ea442ce80,164,0,0,1066949,321,0,0,1130244,2027,0,0,1341051,400,0,0,1174658,228,0,0,1133467,557,0,0,1019064,1184,0,0,1284703,1458,0,0,1354504,449,0,0,1216061,333,0,0,1185097,2153,0,0,1405812,1424,0,0,1378677,112,0,0,1120892,194,0,0,1113229,23,0,0,995380,740,0,0,1236552,429,0,0,1247984,5289,0,0,1836573,1630,0,0,1340395,484,0,0,1179542,368,0,0,1250834,923,0,0,1185399,547,0,0,1223846,716,0,0,1213368,895,0,0,1317959,0,0,0,1081893,3451,0,0,1673173,247,0,0,1163334,52,0,0,1117875,142,0,0,1109344,498,0,0,1245936,524,0,0,1132521,64,0x7fc40ea66e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f54e5e90e80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8194,4098,8194,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8360,4264,8360,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8200,4104,8200,64,0x7facf8386e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,3793,38142,0,131374.0,131072.0,0.0,86597.0,64,0x7f79b459ee80,32768,0,0,0,16384,16384,393216,21289704,960.0,513860.0,0.0,524288.0,1248083.0,32768.0,0,0,0,14119,87763.0,87763.0,0.0,87763.0,64,0x7f5e4f946e80,0,0,48,0,65536,65536,0,0,31679,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,457,43126,1692,0,48.0,465.0,0.0,262144.0,64,0x7f0e7a4a8e80,176261,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13445,29829,8488,2558,0,41725,262523.0,0.0,47.0,262476.0,64,0x7f191a560e80,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,0,44231,0,0,2187843682565519,2187843682585039 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_1,obj_1,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_2,obj_2,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_3,obj_3,TCC_EA_ATOMIC_LEVEL_sum,wave_size_4,obj_4,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_5,obj_5,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_6,obj_6,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_7,obj_7,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_8,obj_8,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_9,obj_9,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_10,obj_10,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_11,obj_11,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_12,obj_12,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_13,obj_13,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_14,obj_14,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_15,obj_15,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_16,obj_16,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fcf0932ee80,131072.0,131072.0,0.0,2566886.0,0.0,0.0,121840349.0,58445288.0,64,0x7ff44e090e80,0,4527760,4096,4096,0,3555075,4096,4096,0,2775410,4096,4096,0,3418968,4096,4096,0,4238708,4096,4096,0,2987453,4096,4096,0,3716834,4096,4096,0,4981364,4096,4096,0,3278531,4096,4096,0,3073029,4096,4096,0,3931357,4096,4096,0,4760082,4096,4096,0,2991096,4096,4096,0,4375993,4096,4096,0,4199466,4096,4096,0,3009560,4096,4096,0,3287903,4096,4096,0,3971461,4096,4096,0,4254037,4096,4096,0,4627029,4096,4096,0,3949698,4096,4096,0,4293693,4096,4096,0,4053840,4096,4096,0,3067426,4096,4096,0,3522697,4096,4096,0,3575519,4096,4096,0,5577921,4096,4096,0,3023500,4096,4096,0,4493256,4096,4096,0,3531987,4096,4096,0,3123815,4096,4096,0,2809669,4096,4096,64,0x7f5c6c79ee80,2197,0,0,1825758,3688,0,0,1993202,1773,0,0,1767972,6611,0,0,2229155,1848,0,0,1799238,964,0,0,1727628,3278,0,0,1973798,2685,0,0,1887535,1931,0,0,1888618,1815,0,0,1857040,1007,0,0,1755433,1417,0,0,1761046,2480,0,0,1921293,5265,0,0,2122584,1286,0,0,1761950,6088,0,0,2184448,3078,0,0,1963396,593,0,0,1645137,4360,0,0,2094990,3224,0,0,1923765,2123,0,0,1986131,4211,0,0,2047900,722,0,0,1619918,6858,0,0,2157641,2635,0,0,1899838,1951,0,0,1856611,3161,0,0,1952531,4438,0,0,2024809,2658,0,0,1902416,2845,0,0,1885019,2557,0,0,1994981,3414,0,0,2025850,64,0x7f45b1126e80,0.0,64,0x7fce2156ae80,0,8192,4096,8192,0,8192,4096,8192,141,8195,4240,8336,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8469,4373,8469,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7fcddb37ae80,187897,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13344,29728,9915,550,0,45970,262612.0,0.0,188.0,262424.0,64,0x7f1f422b4e80,1833987,360448,163840,0,0,180224,114688,0,67918409.0,194039889.0,69898979.0,131072.0,0.0,683023.0,0,0,26884,85053.0,0.0,0.0,85053.0,64,0x7f0aeb206e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86526.0,44546.0,131111.0,0.0,64,0x7f0a32744e80,0,0,192,0,65536,64413,48,1376,31580,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,538,47664,1753,0,48.0,263.0,0.0,262288.0,64,0x7ff35b1e8e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,48080,0,131680.0,131072.0,0.0,131104.0,64,0x7f7b58daae80,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,64,0x7f36ddc8ae80,32768,0,0,0,16384,16384,393216,23005499,960.0,513903.0,0.0,524288.0,889072.0,32768.0,0,0,0,16742,131072.0,131072.0,0.0,131072.0,64,0x7f2f61292e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,46844.0,117046.0,64,0x7fcaef4e6e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131345.0,0.0,538.0,131344.0,64,0x7f64f24f6e80,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f6a2c826e80,4096,0,5848,0,4229,0,5984,0,4099,0,3303,0,4096,0,3660,0,4096,0,1999,0,4096,0,5546,0,4096,0,139,0,4096,0,3715,0,4144,0,416,0,4096,0,904,0,4144,0,1979,0,4096,0,2160,0,4096,0,0,0,4096,0,0,0,4096,0,2882,0,4096,0,0,0,4097,0,234,0,4096,0,3518,0,4096,0,4635,0,4096,0,356,0,4096,0,5351,0,4096,0,0,0,4096,0,3151,0,4144,0,88,0,4096,0,0,0,4096,0,174,0,4096,0,711,0,4096,0,557,0,4096,0,742,0,4096,0,353,0,4096,0,5158,0,4096,0,488,0,64,0x7f621b26ee80,380000,230046,3335699,16384,24097627,144,48,0,47499,47499,3803607.0,2960470.0,6886.0,1090442.0,2081779.0,0.0,2949969.0,2640041.0,378543,240004,47499,0,47499,0,1519968.0,970987.0,0.0,0.0,194257894802798,194257894826478 +1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fcf0932ee80,131072.0,131072.0,0.0,2611149.0,0.0,0.0,113086249.0,45751167.0,64,0x7ff44e090e80,0,3365818,2708,2708,0,4226863,2718,2718,0,3622979,2678,2678,0,3211610,2726,2726,0,4633233,2696,2696,0,3700931,2717,2717,0,4413258,2686,2686,0,3805762,2716,2716,0,3549104,2678,2678,0,4663676,2686,2686,0,4215530,2684,2684,0,4818752,2728,2728,0,3003802,2726,2726,0,3212344,2666,2666,0,3408405,2678,2678,0,3409004,2700,2700,0,4631889,2694,2694,0,5387890,2684,2684,0,3501197,2660,2660,0,4252721,2704,2704,0,4940336,2710,2710,0,4423994,2734,2734,0,4513618,2672,2672,0,3806442,2700,2700,0,3168336,2706,2706,0,3137423,2717,2717,0,3735098,2712,2712,0,3082439,2704,2704,0,3313063,2694,2694,0,2985552,2712,2712,0,3723447,2708,2708,0,4554880,2716,2716,64,0x7f5c6c79ee80,3477,0,0,1677901,2673,0,0,1543497,1180,0,0,1282168,2236,0,0,1399042,1649,0,0,1385229,325,0,0,1231987,4929,0,0,1784217,2176,0,0,1445048,1069,0,0,1387247,820,0,0,1291456,3516,0,0,1656123,1911,0,0,1511916,2515,0,0,1575273,2180,0,0,1418914,7771,0,0,2010820,5681,0,0,1707998,746,0,0,1329781,216,0,0,1255758,3485,0,0,1668061,3640,0,0,1657957,2850,0,0,1456156,973,0,0,1447484,2838,0,0,1510469,2073,0,0,1419852,394,0,0,1231310,2176,0,0,1495991,1637,0,0,1358263,3335,0,0,1573230,2517,0,0,1459606,2698,0,0,1458964,4793,0,0,1701931,1749,0,0,1319873,64,0x7f45b1126e80,0.0,64,0x7fce2156ae80,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8193,4097,8193,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8445,4349,8445,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7fcddb37ae80,186426,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,11130,27514,8753,2874,0,41283,262414.0,0.0,47.0,262367.0,64,0x7f1f422b4e80,1309158,360448,163840,0,0,180224,114688,0,69824744.0,186221412.0,69391074.0,131072.0,0.0,591139.0,0,0,25286,66142.0,0.0,0.0,66142.0,64,0x7f0aeb206e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86455.0,44617.0,131110.0,0.0,64,0x7f0a32744e80,0,0,48,0,65536,65536,0,0,30644,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,482,45503,4141,0,48.0,222.0,0.0,262144.0,64,0x7ff35b1e8e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,2757,40308,0,131579.0,131072.0,0.0,86936.0,64,0x7f7b58daae80,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,64,0x7f36ddc8ae80,32768,0,0,0,16384,16384,393216,22341817,960.0,514039.0,0.0,524288.0,1021354.0,32768.0,0,0,0,13651,86557.0,86557.0,0.0,86557.0,64,0x7f2f61292e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,53083.0,120688.0,64,0x7fcaef4e6e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131770.0,0.0,1390.0,131767.0,64,0x7f64f24f6e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f6a2c826e80,4096,0,3298,0,4247,0,698,0,4096,0,0,0,4097,0,521,0,4096,0,3129,0,4096,0,1065,0,4096,0,344,0,4096,0,1864,0,4144,0,916,0,4096,0,1289,0,4144,0,1859,0,4096,0,4737,0,4096,0,6859,0,4097,0,203,0,4096,0,12,0,4096,0,242,0,4097,0,836,0,4098,0,1802,0,4096,0,382,0,4096,0,635,0,4096,0,1750,0,4096,0,5598,0,4096,0,0,0,4144,0,0,0,4096,0,2506,0,4096,0,2897,0,4096,0,0,0,4096,0,2951,0,4096,0,1501,0,4096,0,0,0,4096,0,610,0,4096,0,478,0,64,0x7f621b26ee80,383976,255497,3751630,16384,24605329,0,48,0,47996,47996,4121567.0,3589567.0,6010.0,1253940.0,2487457.0,0.0,3580777.0,3272539.0,383968,264629,47996,0,47996,1068,1535872.0,953280.0,3.0,0.0,194257894909678,194257894929198 +2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fcf0932ee80,131072.0,131072.0,0.0,2555628.0,0.0,0.0,116932893.0,46914420.0,64,0x7ff44e090e80,0,2825135,2720,2720,0,2686487,2711,2711,0,5260778,2696,2696,0,3193974,2746,2746,0,2909188,2682,2682,0,2633911,2761,2761,0,2131598,2706,2706,0,3632339,2748,2748,0,2695958,2664,2664,0,4889651,2732,2732,0,2469835,2709,2709,0,3587606,2758,2758,0,2843456,2696,2696,0,2612871,2714,2714,0,3059147,2700,2700,0,3021221,2733,2733,0,2716164,2684,2684,0,5232311,2738,2738,0,2529687,2716,2716,0,3210409,2726,2726,0,2943608,2670,2670,0,2491290,2786,2786,0,2593772,2706,2706,0,4393415,2702,2702,0,3411270,2692,2692,0,2517710,2756,2756,0,2051713,2714,2714,0,2861911,2728,2728,0,2619552,2690,2690,0,2610323,2727,2727,0,2385440,2724,2724,0,2800681,2716,2716,64,0x7f5c6c79ee80,1749,0,0,1435090,2262,0,0,1508459,1448,0,0,1416248,2213,0,0,1468240,2423,0,0,1596292,1450,0,0,1425724,596,0,0,1344216,1438,0,0,1431695,2907,0,0,1582506,1107,0,0,1412589,961,0,0,1355688,2393,0,0,1481766,4053,0,0,1690528,581,0,0,1297654,3106,0,0,1604022,2362,0,0,1450864,3135,0,0,1591297,1217,0,0,1324008,4426,0,0,1749904,1458,0,0,1382650,3663,0,0,1661357,1557,0,0,1463431,1532,0,0,1532500,1089,0,0,1324656,3061,0,0,1538480,482,0,0,1246056,1437,0,0,1424126,4059,0,0,1569945,2145,0,0,1553308,1849,0,0,1448343,1742,0,0,1469827,2632,0,0,1543838,64,0x7f45b1126e80,0.0,64,0x7fce2156ae80,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8193,4097,8193,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8357,4261,8357,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7fcddb37ae80,152832,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,12642,29026,8362,2338,0,40237,262413.0,0.0,47.0,262366.0,64,0x7f1f422b4e80,1573989,360448,163840,0,0,180224,114688,0,69279840.0,196075939.0,71851195.0,131072.0,0.0,680636.0,0,0,26233,83217.0,0.0,0.0,83217.0,64,0x7f0aeb206e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86617.0,0.0,131112.0,0.0,64,0x7f0a32744e80,0,0,48,0,65536,65536,0,0,30132,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,458,41885,1692,0,48.0,217.0,0.0,262144.0,64,0x7ff35b1e8e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,3195,111310,158,131593.0,131072.0,0.0,86970.0,64,0x7f7b58daae80,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,64,0x7f36ddc8ae80,32768,0,0,0,16384,16384,393216,22373479,960.0,513995.0,0.0,524288.0,901334.0,32768.0,0,0,0,13147,86574.0,86574.0,0.0,86574.0,64,0x7f2f61292e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,30492.0,96863.0,64,0x7fcaef4e6e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131347.0,0.0,548.0,131346.0,64,0x7f64f24f6e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f6a2c826e80,4096,0,2857,0,4237,0,1585,0,4096,0,1240,0,4097,0,0,0,4096,0,1583,0,4096,0,4907,0,4096,0,2012,0,4096,0,3220,0,4144,0,5275,0,4096,0,4725,0,4144,0,3382,0,4096,0,3280,0,4096,0,4613,0,4097,0,4372,0,4096,0,911,0,4096,0,0,0,4097,0,1525,0,4098,0,5923,0,4096,0,2246,0,4096,0,235,0,4096,0,5127,0,4096,0,3832,0,4096,0,1806,0,4144,0,0,0,4096,0,682,0,4096,0,4944,0,4096,0,2321,0,4096,0,94,0,4096,0,1560,0,4096,0,1020,0,4096,0,559,0,4096,0,633,0,64,0x7f621b26ee80,327464,228650,3346779,16384,23991293,0,48,0,40932,40932,3726932.0,3060657.0,5116.0,1064756.0,2179351.0,0.0,3051600.0,2742254.0,327456,237771,40932,0,40932,0,1309824.0,829271.0,0.0,0.0,194257894949838,194257894968558 diff --git a/tests/workloads/device_inv_int/MI100/sysinfo.csv b/tests/workloads/device_inv_int/MI100/sysinfo.csv index 14ea498dca..7bbeb8f319 100644 --- a/tests/workloads/device_inv_int/MI100/sysinfo.csv +++ b/tests/workloads/device_inv_int/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -device_inv_int,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Fri Mar 1 16:45:48 2024 (CST),1,t006-003.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651240,,5.7.1-98,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +device_inv_int,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 07 Mar 2024 01:08:30 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/device_inv_int/MI100/timestamps.csv b/tests/workloads/device_inv_int/MI100/timestamps.csv index 508e2fe72d..0ddc84a6d7 100644 --- a/tests/workloads/device_inv_int/MI100/timestamps.csv +++ b/tests/workloads/device_inv_int/MI100/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,2860817,2860817,1048576,256,0,0,8,8,16,64,0x0,0x7fd32b2cce80,2187843682380846,2187843682406959,2187843682431279,2187843682443404 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,2860817,2860817,1048576,256,0,0,8,8,16,64,0x0,0x7fd32b2cce80,2187843682444325,2187843682524719,2187843682543599,2187843682544844 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,2860817,2860817,1048576,256,0,0,8,8,16,64,0x0,0x7fd32b2cce80,2187843682556025,2187843682565519,2187843682585039,2187843682586092 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,167187,167187,1048576,256,0,0,8,8,16,64,0x0,0x7f75a08c8e80,194257894775994,194257894802798,194257894826478,194257894838072 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,167187,167187,1048576,256,0,0,8,8,16,64,0x0,0x7f75a08c8e80,194257894839254,194257894909678,194257894929198,194257894930367 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,167187,167187,1048576,256,0,0,8,8,16,64,0x0,0x7f75a08c8e80,194257894941187,194257894949838,194257894968558,194257894969812 diff --git a/tests/workloads/device_inv_int/MI200/SQ_IFETCH_LEVEL.csv b/tests/workloads/device_inv_int/MI200/SQ_IFETCH_LEVEL.csv new file mode 100644 index 0000000000..eabfc56e56 --- /dev/null +++ b/tests/workloads/device_inv_int/MI200/SQ_IFETCH_LEVEL.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,320367,320367,1048576,256,0,0,8,0,16,64,0x0,0x7fc46ea24ec0,27912,27912,16384,65536,13514,1516880,198989177854165,199001894935363,199001894955843,198989193725590 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,320367,320367,1048576,256,0,0,8,0,16,64,0x0,0x7fc46ea24ec0,41103,41103,16384,65536,9163,1048712,198989193746269,199001895045923,199001895062403,198989194045705 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,320367,320367,1048576,256,0,0,8,0,16,64,0x0,0x7fc46ea24ec0,42248,42248,16384,65536,9321,1048688,198989194074961,199001895083363,199001895098883,198989194247106 diff --git a/tests/workloads/device_inv_int/MI200/SQ_INST_LEVEL_LDS.csv b/tests/workloads/device_inv_int/MI200/SQ_INST_LEVEL_LDS.csv new file mode 100644 index 0000000000..aca17b9215 --- /dev/null +++ b/tests/workloads/device_inv_int/MI200/SQ_INST_LEVEL_LDS.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,320552,320552,1048576,256,0,0,8,0,16,64,0x0,0x7fd2d0168ec0,0,0,0,198989659429121,199001894935363,199001894955843,198989675029403 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,320552,320552,1048576,256,0,0,8,0,16,64,0x0,0x7fd2d0168ec0,0,0,0,198989675045944,199001895045923,199001895062403,198989675468113 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,320552,320552,1048576,256,0,0,8,0,16,64,0x0,0x7fd2d0168ec0,0,0,0,198989675494523,199001895083363,199001895098883,198989675627705 diff --git a/tests/workloads/device_inv_int/MI200/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/device_inv_int/MI200/SQ_INST_LEVEL_SMEM.csv new file mode 100644 index 0000000000..148ad78395 --- /dev/null +++ b/tests/workloads/device_inv_int/MI200/SQ_INST_LEVEL_SMEM.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,320753,320753,1048576,256,0,0,8,0,16,64,0x0,0x7f4cb8e90ec0,65536,170884,19184888,198990137856562,199001894935363,199001894955843,198990153574507 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,320753,320753,1048576,256,0,0,8,0,16,64,0x0,0x7f4cb8e90ec0,65536,270394,30243744,198990153590808,199001895045923,199001895062403,198990153897729 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,320753,320753,1048576,256,0,0,8,0,16,64,0x0,0x7f4cb8e90ec0,65536,259860,29229728,198990153924269,199001895083363,199001895098883,198990154075054 diff --git a/tests/workloads/device_inv_int/MI200/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/device_inv_int/MI200/SQ_INST_LEVEL_VMEM.csv new file mode 100644 index 0000000000..b0ad335a3a --- /dev/null +++ b/tests/workloads/device_inv_int/MI200/SQ_INST_LEVEL_VMEM.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,320954,320954,1048576,256,0,0,8,0,16,64,0x0,0x7f40f4f68ec0,32768,278475,31173412,198990619125670,199001894935363,199001894955843,198990634836722 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,320954,320954,1048576,256,0,0,8,0,16,64,0x0,0x7f40f4f68ec0,32768,559977,62717076,198990634856980,199001895045923,199001895062403,198990635121510 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,320954,320954,1048576,256,0,0,8,0,16,64,0x0,0x7f40f4f68ec0,32768,569028,63722036,198990635147840,199001895083363,199001895098883,198990635324454 diff --git a/tests/workloads/device_inv_int/MI200/SQ_LEVEL_WAVES.csv b/tests/workloads/device_inv_int/MI200/SQ_LEVEL_WAVES.csv new file mode 100644 index 0000000000..f11c4d6e02 --- /dev/null +++ b/tests/workloads/device_inv_int/MI200/SQ_LEVEL_WAVES.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,321157,321157,1048576,256,0,0,8,0,16,64,0x0,0x7f6e1b100ec0,29013,29013,11176,232112,16384,11736679,138268,0,47442548,198991099206579,199001894935363,199001894955843,198991115265029 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,321157,321157,1048576,256,0,0,8,0,16,64,0x0,0x7f6e1b100ec0,40851,40851,13491,326816,16384,18989824,219727,0,76441744,198991115292040,199001895045923,199001895062403,198991115577520 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,321157,321157,1048576,256,0,0,8,0,16,64,0x0,0x7f6e1b100ec0,41371,41371,13947,330976,16384,19441122,223986,0,78257552,198991115612746,199001895083363,199001895098883,198991115779131 diff --git a/tests/workloads/device_inv_int/MI200/perfmon/SQ_IFETCH_LEVEL.txt b/tests/workloads/device_inv_int/MI200/perfmon/SQ_IFETCH_LEVEL.txt new file mode 100644 index 0000000000..293092f641 --- /dev/null +++ b/tests/workloads/device_inv_int/MI200/perfmon/SQ_IFETCH_LEVEL.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/device_inv_int/MI200/perfmon/SQ_INST_LEVEL_LDS.txt b/tests/workloads/device_inv_int/MI200/perfmon/SQ_INST_LEVEL_LDS.txt new file mode 100644 index 0000000000..08439eedce --- /dev/null +++ b/tests/workloads/device_inv_int/MI200/perfmon/SQ_INST_LEVEL_LDS.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/device_inv_int/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt b/tests/workloads/device_inv_int/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt new file mode 100644 index 0000000000..6cca322d4e --- /dev/null +++ b/tests/workloads/device_inv_int/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/device_inv_int/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt b/tests/workloads/device_inv_int/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt new file mode 100644 index 0000000000..e527ad31ba --- /dev/null +++ b/tests/workloads/device_inv_int/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/device_inv_int/MI200/perfmon/SQ_LEVEL_WAVES.txt b/tests/workloads/device_inv_int/MI200/perfmon/SQ_LEVEL_WAVES.txt new file mode 100644 index 0000000000..3f8e04adb3 --- /dev/null +++ b/tests/workloads/device_inv_int/MI200/perfmon/SQ_LEVEL_WAVES.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_0.txt b/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_0.txt new file mode 100644 index 0000000000..4ffdc32149 --- /dev/null +++ b/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_0.txt @@ -0,0 +1,5 @@ +pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES SQ_INSTS_VALU_CVT SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU GRBM_COUNT GRBM_GUI_ACTIVE TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum TA_TA_BUSY_sum TA_BUFFER_WAVEFRONTS_sum TD_TD_BUSY_sum TD_TC_STALL_sum SPI_CSN_WINDOW_VALID SPI_CSN_BUSY CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_1.txt b/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_1.txt new file mode 100644 index 0000000000..6c277f4a37 --- /dev/null +++ b/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_1.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VSKIPPED SQ_INSTS SQ_INSTS_VALU SQ_INSTS_VALU_ADD_F16 SQ_INSTS_VALU_MUL_F16 SQ_INSTS_VALU_FMA_F16 SQ_INSTS_VALU_TRANS_F16 SQ_INSTS_VALU_ADD_F32 GRBM_SPI_BUSY TCP_READ_TAGCONFLICT_STALL_CYCLES_sum TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum TCP_TA_TCP_STATE_READ_sum TA_BUFFER_READ_WAVEFRONTS_sum TA_BUFFER_WRITE_WAVEFRONTS_sum TD_SPI_STALL_sum TD_LOAD_WAVEFRONT_sum SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_10.txt b/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_10.txt new file mode 100644 index 0000000000..7053d4dce6 --- /dev/null +++ b/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_10.txt @@ -0,0 +1,5 @@ +pmc: SQC_TC_DATA_WRITE_REQ SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES + +gpu: +range: +kernel: diff --git a/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_11.txt b/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_11.txt new file mode 100644 index 0000000000..77ae8b461f --- /dev/null +++ b/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_11.txt @@ -0,0 +1,5 @@ +pmc: SQC_ICACHE_MISSES_DUPLICATE SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE + +gpu: +range: +kernel: diff --git a/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_12.txt b/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_12.txt new file mode 100644 index 0000000000..dfb2cf65e5 --- /dev/null +++ b/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_12.txt @@ -0,0 +1,5 @@ +pmc: SQC_DCACHE_REQ_READ_1 SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 + +gpu: +range: +kernel: diff --git a/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_13.txt b/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_13.txt new file mode 100644 index 0000000000..062fc9644a --- /dev/null +++ b/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_13.txt @@ -0,0 +1,5 @@ +pmc: TCC_ATOMIC[0] TCC_CYCLE[0] TCC_EA_ATOMIC[0] TCC_EA_ATOMIC_LEVEL[0] TCC_ATOMIC[1] TCC_CYCLE[1] TCC_EA_ATOMIC[1] TCC_EA_ATOMIC_LEVEL[1] TCC_ATOMIC[2] TCC_CYCLE[2] TCC_EA_ATOMIC[2] TCC_EA_ATOMIC_LEVEL[2] TCC_ATOMIC[3] TCC_CYCLE[3] TCC_EA_ATOMIC[3] TCC_EA_ATOMIC_LEVEL[3] TCC_ATOMIC[4] TCC_CYCLE[4] TCC_EA_ATOMIC[4] TCC_EA_ATOMIC_LEVEL[4] TCC_ATOMIC[5] TCC_CYCLE[5] TCC_EA_ATOMIC[5] TCC_EA_ATOMIC_LEVEL[5] TCC_ATOMIC[6] TCC_CYCLE[6] TCC_EA_ATOMIC[6] TCC_EA_ATOMIC_LEVEL[6] TCC_ATOMIC[7] TCC_CYCLE[7] TCC_EA_ATOMIC[7] TCC_EA_ATOMIC_LEVEL[7] TCC_ATOMIC[8] TCC_CYCLE[8] TCC_EA_ATOMIC[8] TCC_EA_ATOMIC_LEVEL[8] TCC_ATOMIC[9] TCC_CYCLE[9] TCC_EA_ATOMIC[9] TCC_EA_ATOMIC_LEVEL[9] TCC_ATOMIC[10] TCC_CYCLE[10] TCC_EA_ATOMIC[10] TCC_EA_ATOMIC_LEVEL[10] TCC_ATOMIC[11] TCC_CYCLE[11] TCC_EA_ATOMIC[11] TCC_EA_ATOMIC_LEVEL[11] TCC_ATOMIC[12] TCC_CYCLE[12] TCC_EA_ATOMIC[12] TCC_EA_ATOMIC_LEVEL[12] TCC_ATOMIC[13] TCC_CYCLE[13] TCC_EA_ATOMIC[13] TCC_EA_ATOMIC_LEVEL[13] TCC_ATOMIC[14] TCC_CYCLE[14] TCC_EA_ATOMIC[14] TCC_EA_ATOMIC_LEVEL[14] TCC_ATOMIC[15] TCC_CYCLE[15] TCC_EA_ATOMIC[15] TCC_EA_ATOMIC_LEVEL[15] TCC_ATOMIC[16] TCC_CYCLE[16] TCC_EA_ATOMIC[16] TCC_EA_ATOMIC_LEVEL[16] TCC_ATOMIC[17] TCC_CYCLE[17] TCC_EA_ATOMIC[17] TCC_EA_ATOMIC_LEVEL[17] TCC_ATOMIC[18] TCC_CYCLE[18] TCC_EA_ATOMIC[18] TCC_EA_ATOMIC_LEVEL[18] TCC_ATOMIC[19] TCC_CYCLE[19] TCC_EA_ATOMIC[19] TCC_EA_ATOMIC_LEVEL[19] TCC_ATOMIC[20] TCC_CYCLE[20] TCC_EA_ATOMIC[20] TCC_EA_ATOMIC_LEVEL[20] TCC_ATOMIC[21] TCC_CYCLE[21] TCC_EA_ATOMIC[21] TCC_EA_ATOMIC_LEVEL[21] TCC_ATOMIC[22] TCC_CYCLE[22] TCC_EA_ATOMIC[22] TCC_EA_ATOMIC_LEVEL[22] TCC_ATOMIC[23] TCC_CYCLE[23] TCC_EA_ATOMIC[23] TCC_EA_ATOMIC_LEVEL[23] TCC_ATOMIC[24] TCC_CYCLE[24] TCC_EA_ATOMIC[24] TCC_EA_ATOMIC_LEVEL[24] TCC_ATOMIC[25] TCC_CYCLE[25] TCC_EA_ATOMIC[25] TCC_EA_ATOMIC_LEVEL[25] TCC_ATOMIC[26] TCC_CYCLE[26] TCC_EA_ATOMIC[26] TCC_EA_ATOMIC_LEVEL[26] TCC_ATOMIC[27] TCC_CYCLE[27] TCC_EA_ATOMIC[27] TCC_EA_ATOMIC_LEVEL[27] TCC_ATOMIC[28] TCC_CYCLE[28] TCC_EA_ATOMIC[28] TCC_EA_ATOMIC_LEVEL[28] TCC_ATOMIC[29] TCC_CYCLE[29] TCC_EA_ATOMIC[29] TCC_EA_ATOMIC_LEVEL[29] TCC_ATOMIC[30] TCC_CYCLE[30] TCC_EA_ATOMIC[30] TCC_EA_ATOMIC_LEVEL[30] TCC_ATOMIC[31] TCC_CYCLE[31] TCC_EA_ATOMIC[31] TCC_EA_ATOMIC_LEVEL[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_14.txt b/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_14.txt new file mode 100644 index 0000000000..e0698dbf57 --- /dev/null +++ b/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_14.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_EA_RDREQ_GMI_CREDIT_STALL[0] TCC_EA_RDREQ[1] TCC_EA_RDREQ_32B[1] TCC_EA_RDREQ_DRAM_CREDIT_STALL[1] TCC_EA_RDREQ_GMI_CREDIT_STALL[1] TCC_EA_RDREQ[2] TCC_EA_RDREQ_32B[2] TCC_EA_RDREQ_DRAM_CREDIT_STALL[2] TCC_EA_RDREQ_GMI_CREDIT_STALL[2] TCC_EA_RDREQ[3] TCC_EA_RDREQ_32B[3] TCC_EA_RDREQ_DRAM_CREDIT_STALL[3] TCC_EA_RDREQ_GMI_CREDIT_STALL[3] TCC_EA_RDREQ[4] TCC_EA_RDREQ_32B[4] TCC_EA_RDREQ_DRAM_CREDIT_STALL[4] TCC_EA_RDREQ_GMI_CREDIT_STALL[4] TCC_EA_RDREQ[5] TCC_EA_RDREQ_32B[5] TCC_EA_RDREQ_DRAM_CREDIT_STALL[5] TCC_EA_RDREQ_GMI_CREDIT_STALL[5] TCC_EA_RDREQ[6] TCC_EA_RDREQ_32B[6] TCC_EA_RDREQ_DRAM_CREDIT_STALL[6] TCC_EA_RDREQ_GMI_CREDIT_STALL[6] TCC_EA_RDREQ[7] TCC_EA_RDREQ_32B[7] TCC_EA_RDREQ_DRAM_CREDIT_STALL[7] TCC_EA_RDREQ_GMI_CREDIT_STALL[7] TCC_EA_RDREQ[8] TCC_EA_RDREQ_32B[8] TCC_EA_RDREQ_DRAM_CREDIT_STALL[8] TCC_EA_RDREQ_GMI_CREDIT_STALL[8] TCC_EA_RDREQ[9] TCC_EA_RDREQ_32B[9] TCC_EA_RDREQ_DRAM_CREDIT_STALL[9] TCC_EA_RDREQ_GMI_CREDIT_STALL[9] TCC_EA_RDREQ[10] TCC_EA_RDREQ_32B[10] TCC_EA_RDREQ_DRAM_CREDIT_STALL[10] TCC_EA_RDREQ_GMI_CREDIT_STALL[10] TCC_EA_RDREQ[11] TCC_EA_RDREQ_32B[11] TCC_EA_RDREQ_DRAM_CREDIT_STALL[11] TCC_EA_RDREQ_GMI_CREDIT_STALL[11] TCC_EA_RDREQ[12] TCC_EA_RDREQ_32B[12] TCC_EA_RDREQ_DRAM_CREDIT_STALL[12] TCC_EA_RDREQ_GMI_CREDIT_STALL[12] TCC_EA_RDREQ[13] TCC_EA_RDREQ_32B[13] TCC_EA_RDREQ_DRAM_CREDIT_STALL[13] TCC_EA_RDREQ_GMI_CREDIT_STALL[13] TCC_EA_RDREQ[14] TCC_EA_RDREQ_32B[14] TCC_EA_RDREQ_DRAM_CREDIT_STALL[14] TCC_EA_RDREQ_GMI_CREDIT_STALL[14] TCC_EA_RDREQ[15] TCC_EA_RDREQ_32B[15] TCC_EA_RDREQ_DRAM_CREDIT_STALL[15] TCC_EA_RDREQ_GMI_CREDIT_STALL[15] TCC_EA_RDREQ[16] TCC_EA_RDREQ_32B[16] TCC_EA_RDREQ_DRAM_CREDIT_STALL[16] TCC_EA_RDREQ_GMI_CREDIT_STALL[16] TCC_EA_RDREQ[17] TCC_EA_RDREQ_32B[17] TCC_EA_RDREQ_DRAM_CREDIT_STALL[17] TCC_EA_RDREQ_GMI_CREDIT_STALL[17] TCC_EA_RDREQ[18] TCC_EA_RDREQ_32B[18] TCC_EA_RDREQ_DRAM_CREDIT_STALL[18] TCC_EA_RDREQ_GMI_CREDIT_STALL[18] TCC_EA_RDREQ[19] TCC_EA_RDREQ_32B[19] TCC_EA_RDREQ_DRAM_CREDIT_STALL[19] TCC_EA_RDREQ_GMI_CREDIT_STALL[19] TCC_EA_RDREQ[20] TCC_EA_RDREQ_32B[20] TCC_EA_RDREQ_DRAM_CREDIT_STALL[20] TCC_EA_RDREQ_GMI_CREDIT_STALL[20] TCC_EA_RDREQ[21] TCC_EA_RDREQ_32B[21] TCC_EA_RDREQ_DRAM_CREDIT_STALL[21] TCC_EA_RDREQ_GMI_CREDIT_STALL[21] TCC_EA_RDREQ[22] TCC_EA_RDREQ_32B[22] TCC_EA_RDREQ_DRAM_CREDIT_STALL[22] TCC_EA_RDREQ_GMI_CREDIT_STALL[22] TCC_EA_RDREQ[23] TCC_EA_RDREQ_32B[23] TCC_EA_RDREQ_DRAM_CREDIT_STALL[23] TCC_EA_RDREQ_GMI_CREDIT_STALL[23] TCC_EA_RDREQ[24] TCC_EA_RDREQ_32B[24] TCC_EA_RDREQ_DRAM_CREDIT_STALL[24] TCC_EA_RDREQ_GMI_CREDIT_STALL[24] TCC_EA_RDREQ[25] TCC_EA_RDREQ_32B[25] TCC_EA_RDREQ_DRAM_CREDIT_STALL[25] TCC_EA_RDREQ_GMI_CREDIT_STALL[25] TCC_EA_RDREQ[26] TCC_EA_RDREQ_32B[26] TCC_EA_RDREQ_DRAM_CREDIT_STALL[26] TCC_EA_RDREQ_GMI_CREDIT_STALL[26] TCC_EA_RDREQ[27] TCC_EA_RDREQ_32B[27] TCC_EA_RDREQ_DRAM_CREDIT_STALL[27] TCC_EA_RDREQ_GMI_CREDIT_STALL[27] TCC_EA_RDREQ[28] TCC_EA_RDREQ_32B[28] TCC_EA_RDREQ_DRAM_CREDIT_STALL[28] TCC_EA_RDREQ_GMI_CREDIT_STALL[28] TCC_EA_RDREQ[29] TCC_EA_RDREQ_32B[29] TCC_EA_RDREQ_DRAM_CREDIT_STALL[29] TCC_EA_RDREQ_GMI_CREDIT_STALL[29] TCC_EA_RDREQ[30] TCC_EA_RDREQ_32B[30] TCC_EA_RDREQ_DRAM_CREDIT_STALL[30] TCC_EA_RDREQ_GMI_CREDIT_STALL[30] TCC_EA_RDREQ[31] TCC_EA_RDREQ_32B[31] TCC_EA_RDREQ_DRAM_CREDIT_STALL[31] TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_15.txt b/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_15.txt new file mode 100644 index 0000000000..77ad088669 --- /dev/null +++ b/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_15.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ[0] TCC_EA_WRREQ_64B[0] TCC_EA_RDREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_LEVEL[1] TCC_EA_WRREQ[1] TCC_EA_WRREQ_64B[1] TCC_EA_RDREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_LEVEL[2] TCC_EA_WRREQ[2] TCC_EA_WRREQ_64B[2] TCC_EA_RDREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_LEVEL[3] TCC_EA_WRREQ[3] TCC_EA_WRREQ_64B[3] TCC_EA_RDREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_LEVEL[4] TCC_EA_WRREQ[4] TCC_EA_WRREQ_64B[4] TCC_EA_RDREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_LEVEL[5] TCC_EA_WRREQ[5] TCC_EA_WRREQ_64B[5] TCC_EA_RDREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_LEVEL[6] TCC_EA_WRREQ[6] TCC_EA_WRREQ_64B[6] TCC_EA_RDREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_LEVEL[7] TCC_EA_WRREQ[7] TCC_EA_WRREQ_64B[7] TCC_EA_RDREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_LEVEL[8] TCC_EA_WRREQ[8] TCC_EA_WRREQ_64B[8] TCC_EA_RDREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_LEVEL[9] TCC_EA_WRREQ[9] TCC_EA_WRREQ_64B[9] TCC_EA_RDREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_LEVEL[10] TCC_EA_WRREQ[10] TCC_EA_WRREQ_64B[10] TCC_EA_RDREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_LEVEL[11] TCC_EA_WRREQ[11] TCC_EA_WRREQ_64B[11] TCC_EA_RDREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_LEVEL[12] TCC_EA_WRREQ[12] TCC_EA_WRREQ_64B[12] TCC_EA_RDREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_LEVEL[13] TCC_EA_WRREQ[13] TCC_EA_WRREQ_64B[13] TCC_EA_RDREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_LEVEL[14] TCC_EA_WRREQ[14] TCC_EA_WRREQ_64B[14] TCC_EA_RDREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_LEVEL[15] TCC_EA_WRREQ[15] TCC_EA_WRREQ_64B[15] TCC_EA_RDREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_LEVEL[16] TCC_EA_WRREQ[16] TCC_EA_WRREQ_64B[16] TCC_EA_RDREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_LEVEL[17] TCC_EA_WRREQ[17] TCC_EA_WRREQ_64B[17] TCC_EA_RDREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_LEVEL[18] TCC_EA_WRREQ[18] TCC_EA_WRREQ_64B[18] TCC_EA_RDREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_LEVEL[19] TCC_EA_WRREQ[19] TCC_EA_WRREQ_64B[19] TCC_EA_RDREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_LEVEL[20] TCC_EA_WRREQ[20] TCC_EA_WRREQ_64B[20] TCC_EA_RDREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_LEVEL[21] TCC_EA_WRREQ[21] TCC_EA_WRREQ_64B[21] TCC_EA_RDREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_LEVEL[22] TCC_EA_WRREQ[22] TCC_EA_WRREQ_64B[22] TCC_EA_RDREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_LEVEL[23] TCC_EA_WRREQ[23] TCC_EA_WRREQ_64B[23] TCC_EA_RDREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_LEVEL[24] TCC_EA_WRREQ[24] TCC_EA_WRREQ_64B[24] TCC_EA_RDREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_LEVEL[25] TCC_EA_WRREQ[25] TCC_EA_WRREQ_64B[25] TCC_EA_RDREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_LEVEL[26] TCC_EA_WRREQ[26] TCC_EA_WRREQ_64B[26] TCC_EA_RDREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_LEVEL[27] TCC_EA_WRREQ[27] TCC_EA_WRREQ_64B[27] TCC_EA_RDREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_LEVEL[28] TCC_EA_WRREQ[28] TCC_EA_WRREQ_64B[28] TCC_EA_RDREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_LEVEL[29] TCC_EA_WRREQ[29] TCC_EA_WRREQ_64B[29] TCC_EA_RDREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_LEVEL[30] TCC_EA_WRREQ[30] TCC_EA_WRREQ_64B[30] TCC_EA_RDREQ_IO_CREDIT_STALL[31] TCC_EA_RDREQ_LEVEL[31] TCC_EA_WRREQ[31] TCC_EA_WRREQ_64B[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_16.txt b/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_16.txt new file mode 100644 index 0000000000..d0628bb948 --- /dev/null +++ b/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_16.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_WRREQ_IO_CREDIT_STALL[0] TCC_EA_WRREQ_LEVEL[0] TCC_EA_WRREQ_DRAM_CREDIT_STALL[1] TCC_EA_WRREQ_GMI_CREDIT_STALL[1] TCC_EA_WRREQ_IO_CREDIT_STALL[1] TCC_EA_WRREQ_LEVEL[1] TCC_EA_WRREQ_DRAM_CREDIT_STALL[2] TCC_EA_WRREQ_GMI_CREDIT_STALL[2] TCC_EA_WRREQ_IO_CREDIT_STALL[2] TCC_EA_WRREQ_LEVEL[2] TCC_EA_WRREQ_DRAM_CREDIT_STALL[3] TCC_EA_WRREQ_GMI_CREDIT_STALL[3] TCC_EA_WRREQ_IO_CREDIT_STALL[3] TCC_EA_WRREQ_LEVEL[3] TCC_EA_WRREQ_DRAM_CREDIT_STALL[4] TCC_EA_WRREQ_GMI_CREDIT_STALL[4] TCC_EA_WRREQ_IO_CREDIT_STALL[4] TCC_EA_WRREQ_LEVEL[4] TCC_EA_WRREQ_DRAM_CREDIT_STALL[5] TCC_EA_WRREQ_GMI_CREDIT_STALL[5] TCC_EA_WRREQ_IO_CREDIT_STALL[5] TCC_EA_WRREQ_LEVEL[5] TCC_EA_WRREQ_DRAM_CREDIT_STALL[6] TCC_EA_WRREQ_GMI_CREDIT_STALL[6] TCC_EA_WRREQ_IO_CREDIT_STALL[6] TCC_EA_WRREQ_LEVEL[6] TCC_EA_WRREQ_DRAM_CREDIT_STALL[7] TCC_EA_WRREQ_GMI_CREDIT_STALL[7] TCC_EA_WRREQ_IO_CREDIT_STALL[7] TCC_EA_WRREQ_LEVEL[7] TCC_EA_WRREQ_DRAM_CREDIT_STALL[8] TCC_EA_WRREQ_GMI_CREDIT_STALL[8] TCC_EA_WRREQ_IO_CREDIT_STALL[8] TCC_EA_WRREQ_LEVEL[8] TCC_EA_WRREQ_DRAM_CREDIT_STALL[9] TCC_EA_WRREQ_GMI_CREDIT_STALL[9] TCC_EA_WRREQ_IO_CREDIT_STALL[9] TCC_EA_WRREQ_LEVEL[9] TCC_EA_WRREQ_DRAM_CREDIT_STALL[10] TCC_EA_WRREQ_GMI_CREDIT_STALL[10] TCC_EA_WRREQ_IO_CREDIT_STALL[10] TCC_EA_WRREQ_LEVEL[10] TCC_EA_WRREQ_DRAM_CREDIT_STALL[11] TCC_EA_WRREQ_GMI_CREDIT_STALL[11] TCC_EA_WRREQ_IO_CREDIT_STALL[11] TCC_EA_WRREQ_LEVEL[11] TCC_EA_WRREQ_DRAM_CREDIT_STALL[12] TCC_EA_WRREQ_GMI_CREDIT_STALL[12] TCC_EA_WRREQ_IO_CREDIT_STALL[12] TCC_EA_WRREQ_LEVEL[12] TCC_EA_WRREQ_DRAM_CREDIT_STALL[13] TCC_EA_WRREQ_GMI_CREDIT_STALL[13] TCC_EA_WRREQ_IO_CREDIT_STALL[13] TCC_EA_WRREQ_LEVEL[13] TCC_EA_WRREQ_DRAM_CREDIT_STALL[14] TCC_EA_WRREQ_GMI_CREDIT_STALL[14] TCC_EA_WRREQ_IO_CREDIT_STALL[14] TCC_EA_WRREQ_LEVEL[14] TCC_EA_WRREQ_DRAM_CREDIT_STALL[15] TCC_EA_WRREQ_GMI_CREDIT_STALL[15] TCC_EA_WRREQ_IO_CREDIT_STALL[15] TCC_EA_WRREQ_LEVEL[15] TCC_EA_WRREQ_DRAM_CREDIT_STALL[16] TCC_EA_WRREQ_GMI_CREDIT_STALL[16] TCC_EA_WRREQ_IO_CREDIT_STALL[16] TCC_EA_WRREQ_LEVEL[16] TCC_EA_WRREQ_DRAM_CREDIT_STALL[17] TCC_EA_WRREQ_GMI_CREDIT_STALL[17] TCC_EA_WRREQ_IO_CREDIT_STALL[17] TCC_EA_WRREQ_LEVEL[17] TCC_EA_WRREQ_DRAM_CREDIT_STALL[18] TCC_EA_WRREQ_GMI_CREDIT_STALL[18] TCC_EA_WRREQ_IO_CREDIT_STALL[18] TCC_EA_WRREQ_LEVEL[18] TCC_EA_WRREQ_DRAM_CREDIT_STALL[19] TCC_EA_WRREQ_GMI_CREDIT_STALL[19] TCC_EA_WRREQ_IO_CREDIT_STALL[19] TCC_EA_WRREQ_LEVEL[19] TCC_EA_WRREQ_DRAM_CREDIT_STALL[20] TCC_EA_WRREQ_GMI_CREDIT_STALL[20] TCC_EA_WRREQ_IO_CREDIT_STALL[20] TCC_EA_WRREQ_LEVEL[20] TCC_EA_WRREQ_DRAM_CREDIT_STALL[21] TCC_EA_WRREQ_GMI_CREDIT_STALL[21] TCC_EA_WRREQ_IO_CREDIT_STALL[21] TCC_EA_WRREQ_LEVEL[21] TCC_EA_WRREQ_DRAM_CREDIT_STALL[22] TCC_EA_WRREQ_GMI_CREDIT_STALL[22] TCC_EA_WRREQ_IO_CREDIT_STALL[22] TCC_EA_WRREQ_LEVEL[22] TCC_EA_WRREQ_DRAM_CREDIT_STALL[23] TCC_EA_WRREQ_GMI_CREDIT_STALL[23] TCC_EA_WRREQ_IO_CREDIT_STALL[23] TCC_EA_WRREQ_LEVEL[23] TCC_EA_WRREQ_DRAM_CREDIT_STALL[24] TCC_EA_WRREQ_GMI_CREDIT_STALL[24] TCC_EA_WRREQ_IO_CREDIT_STALL[24] TCC_EA_WRREQ_LEVEL[24] TCC_EA_WRREQ_DRAM_CREDIT_STALL[25] TCC_EA_WRREQ_GMI_CREDIT_STALL[25] TCC_EA_WRREQ_IO_CREDIT_STALL[25] TCC_EA_WRREQ_LEVEL[25] TCC_EA_WRREQ_DRAM_CREDIT_STALL[26] TCC_EA_WRREQ_GMI_CREDIT_STALL[26] TCC_EA_WRREQ_IO_CREDIT_STALL[26] TCC_EA_WRREQ_LEVEL[26] TCC_EA_WRREQ_DRAM_CREDIT_STALL[27] TCC_EA_WRREQ_GMI_CREDIT_STALL[27] TCC_EA_WRREQ_IO_CREDIT_STALL[27] TCC_EA_WRREQ_LEVEL[27] TCC_EA_WRREQ_DRAM_CREDIT_STALL[28] TCC_EA_WRREQ_GMI_CREDIT_STALL[28] TCC_EA_WRREQ_IO_CREDIT_STALL[28] TCC_EA_WRREQ_LEVEL[28] TCC_EA_WRREQ_DRAM_CREDIT_STALL[29] TCC_EA_WRREQ_GMI_CREDIT_STALL[29] TCC_EA_WRREQ_IO_CREDIT_STALL[29] TCC_EA_WRREQ_LEVEL[29] TCC_EA_WRREQ_DRAM_CREDIT_STALL[30] TCC_EA_WRREQ_GMI_CREDIT_STALL[30] TCC_EA_WRREQ_IO_CREDIT_STALL[30] TCC_EA_WRREQ_LEVEL[30] TCC_EA_WRREQ_DRAM_CREDIT_STALL[31] TCC_EA_WRREQ_GMI_CREDIT_STALL[31] TCC_EA_WRREQ_IO_CREDIT_STALL[31] TCC_EA_WRREQ_LEVEL[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_17.txt b/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_17.txt new file mode 100644 index 0000000000..343869c5f1 --- /dev/null +++ b/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_17.txt @@ -0,0 +1,5 @@ +pmc: TCC_HIT[0] TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_HIT[1] TCC_MISS[1] TCC_READ[1] TCC_REQ[1] TCC_HIT[2] TCC_MISS[2] TCC_READ[2] TCC_REQ[2] TCC_HIT[3] TCC_MISS[3] TCC_READ[3] TCC_REQ[3] TCC_HIT[4] TCC_MISS[4] TCC_READ[4] TCC_REQ[4] TCC_HIT[5] TCC_MISS[5] TCC_READ[5] TCC_REQ[5] TCC_HIT[6] TCC_MISS[6] TCC_READ[6] TCC_REQ[6] TCC_HIT[7] TCC_MISS[7] TCC_READ[7] TCC_REQ[7] TCC_HIT[8] TCC_MISS[8] TCC_READ[8] TCC_REQ[8] TCC_HIT[9] TCC_MISS[9] TCC_READ[9] TCC_REQ[9] TCC_HIT[10] TCC_MISS[10] TCC_READ[10] TCC_REQ[10] TCC_HIT[11] TCC_MISS[11] TCC_READ[11] TCC_REQ[11] TCC_HIT[12] TCC_MISS[12] TCC_READ[12] TCC_REQ[12] TCC_HIT[13] TCC_MISS[13] TCC_READ[13] TCC_REQ[13] TCC_HIT[14] TCC_MISS[14] TCC_READ[14] TCC_REQ[14] TCC_HIT[15] TCC_MISS[15] TCC_READ[15] TCC_REQ[15] TCC_HIT[16] TCC_MISS[16] TCC_READ[16] TCC_REQ[16] TCC_HIT[17] TCC_MISS[17] TCC_READ[17] TCC_REQ[17] TCC_HIT[18] TCC_MISS[18] TCC_READ[18] TCC_REQ[18] TCC_HIT[19] TCC_MISS[19] TCC_READ[19] TCC_REQ[19] TCC_HIT[20] TCC_MISS[20] TCC_READ[20] TCC_REQ[20] TCC_HIT[21] TCC_MISS[21] TCC_READ[21] TCC_REQ[21] TCC_HIT[22] TCC_MISS[22] TCC_READ[22] TCC_REQ[22] TCC_HIT[23] TCC_MISS[23] TCC_READ[23] TCC_REQ[23] TCC_HIT[24] TCC_MISS[24] TCC_READ[24] TCC_REQ[24] TCC_HIT[25] TCC_MISS[25] TCC_READ[25] TCC_REQ[25] TCC_HIT[26] TCC_MISS[26] TCC_READ[26] TCC_REQ[26] TCC_HIT[27] TCC_MISS[27] TCC_READ[27] TCC_REQ[27] TCC_HIT[28] TCC_MISS[28] TCC_READ[28] TCC_REQ[28] TCC_HIT[29] TCC_MISS[29] TCC_READ[29] TCC_REQ[29] TCC_HIT[30] TCC_MISS[30] TCC_READ[30] TCC_REQ[30] TCC_HIT[31] TCC_MISS[31] TCC_READ[31] TCC_REQ[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_18.txt b/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_18.txt new file mode 100644 index 0000000000..a74cefd281 --- /dev/null +++ b/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_18.txt @@ -0,0 +1,5 @@ +pmc: TCC_RW_REQ[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_RW_REQ[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_WRITE[1] TCC_RW_REQ[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_WRITE[2] TCC_RW_REQ[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_WRITE[3] TCC_RW_REQ[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_WRITE[4] TCC_RW_REQ[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_WRITE[5] TCC_RW_REQ[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_WRITE[6] TCC_RW_REQ[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_WRITE[7] TCC_RW_REQ[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_WRITE[8] TCC_RW_REQ[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_WRITE[9] TCC_RW_REQ[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_WRITE[10] TCC_RW_REQ[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_WRITE[11] TCC_RW_REQ[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_WRITE[12] TCC_RW_REQ[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_WRITE[13] TCC_RW_REQ[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_WRITE[14] TCC_RW_REQ[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_WRITE[15] TCC_RW_REQ[16] TCC_TOO_MANY_EA_WRREQS_STALL[16] TCC_WRITE[16] TCC_RW_REQ[17] TCC_TOO_MANY_EA_WRREQS_STALL[17] TCC_WRITE[17] TCC_RW_REQ[18] TCC_TOO_MANY_EA_WRREQS_STALL[18] TCC_WRITE[18] TCC_RW_REQ[19] TCC_TOO_MANY_EA_WRREQS_STALL[19] TCC_WRITE[19] TCC_RW_REQ[20] TCC_TOO_MANY_EA_WRREQS_STALL[20] TCC_WRITE[20] TCC_RW_REQ[21] TCC_TOO_MANY_EA_WRREQS_STALL[21] TCC_WRITE[21] TCC_RW_REQ[22] TCC_TOO_MANY_EA_WRREQS_STALL[22] TCC_WRITE[22] TCC_RW_REQ[23] TCC_TOO_MANY_EA_WRREQS_STALL[23] TCC_WRITE[23] TCC_RW_REQ[24] TCC_TOO_MANY_EA_WRREQS_STALL[24] TCC_WRITE[24] TCC_RW_REQ[25] TCC_TOO_MANY_EA_WRREQS_STALL[25] TCC_WRITE[25] TCC_RW_REQ[26] TCC_TOO_MANY_EA_WRREQS_STALL[26] TCC_WRITE[26] TCC_RW_REQ[27] TCC_TOO_MANY_EA_WRREQS_STALL[27] TCC_WRITE[27] TCC_RW_REQ[28] TCC_TOO_MANY_EA_WRREQS_STALL[28] TCC_WRITE[28] TCC_RW_REQ[29] TCC_TOO_MANY_EA_WRREQS_STALL[29] TCC_WRITE[29] TCC_RW_REQ[30] TCC_TOO_MANY_EA_WRREQS_STALL[30] TCC_WRITE[30] TCC_RW_REQ[31] TCC_TOO_MANY_EA_WRREQS_STALL[31] TCC_WRITE[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_2.txt b/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_2.txt new file mode 100644 index 0000000000..70b69f8928 --- /dev/null +++ b/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_2.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_MUL_F32 SQ_INSTS_VALU_FMA_F32 SQ_INSTS_VALU_TRANS_F32 SQ_INSTS_VALU_ADD_F64 SQ_INSTS_VALU_MUL_F64 SQ_INSTS_VALU_FMA_F64 SQ_INSTS_VALU_TRANS_F64 SQ_INSTS_VALU_INT32 TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum TA_BUFFER_ATOMIC_WAVEFRONTS_sum TA_BUFFER_TOTAL_CYCLES_sum TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_3.txt b/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_3.txt new file mode 100644 index 0000000000..e47f8e33c9 --- /dev/null +++ b/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_3.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_INT64 SQ_INSTS_SMEM SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum TD_COALESCABLE_WAVEFRONT_sum SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE CPF_CMP_UTCL1_STALL_ON_TRANSLATION TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_4.txt b/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_4.txt new file mode 100644 index 0000000000..2d96f365a9 --- /dev/null +++ b/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_4.txt @@ -0,0 +1,5 @@ +pmc: SQ_WAVE_CYCLES SQ_WAIT_ANY SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_BUSY_CU_CYCLES SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE TCC_EA_WRREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WR_UNCACHED_32B_sum TCC_EA_WRREQ_DRAM_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_5.txt b/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_5.txt new file mode 100644 index 0000000000..e50beed390 --- /dev/null +++ b/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_5.txt @@ -0,0 +1,5 @@ +pmc: SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU TCP_TCP_LATENCY_sum TCP_TCC_READ_REQ_LATENCY_sum TCP_TCC_WRITE_REQ_LATENCY_sum TCP_TCC_READ_REQ_sum TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN CPC_ME1_DC0_SPI_BUSY TCC_EA_WRREQ_STALL_sum TCC_EA_RDREQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RD_UNCACHED_32B_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_6.txt b/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_6.txt new file mode 100644 index 0000000000..15a2277c1b --- /dev/null +++ b/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_6.txt @@ -0,0 +1,5 @@ +pmc: SQ_THREAD_CYCLES_VALU SQ_IFETCH SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TCP_TCC_NC_READ_REQ_sum TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN TCC_EA_RDREQ_DRAM_sum TCC_TAG_STALL_sum TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_7.txt b/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_7.txt new file mode 100644 index 0000000000..b42ce91618 --- /dev/null +++ b/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_7.txt @@ -0,0 +1,5 @@ +pmc: SQ_WAVES_LT_32 SQ_WAVES_LT_16 SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TCP_TCC_UC_WRITE_REQ_sum TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR TCC_NORMAL_EVICT_sum TCC_ALL_TC_OP_INV_EVICT_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA_ATOMIC_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_8.txt b/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_8.txt new file mode 100644 index 0000000000..21d4c7a998 --- /dev/null +++ b/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_8.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM_NORM SQ_INSTS_MFMA SQ_INSTS_VALU_MFMA_I8 SQ_INSTS_VALU_MFMA_F16 SQ_INSTS_VALU_MFMA_BF16 SQ_INSTS_VALU_MFMA_F32 SQ_INSTS_VALU_MFMA_F64 SQ_VALU_MFMA_BUSY_CYCLES TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TCP_TCC_CC_ATOMIC_REQ_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN TCC_EA_RDREQ_LEVEL_sum TCC_EA_WRREQ_LEVEL_sum TCC_EA_ATOMIC_LEVEL_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_9.txt b/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_9.txt new file mode 100644 index 0000000000..9ffe5778c3 --- /dev/null +++ b/tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_9.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_FLAT_LDS_ONLY SQ_INSTS_VALU_MFMA_MOPS_I8 SQ_INSTS_VALU_MFMA_MOPS_F16 SQ_INSTS_VALU_MFMA_MOPS_BF16 SQ_INSTS_VALU_MFMA_MOPS_F32 SQ_INSTS_VALU_MFMA_MOPS_F64 SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum TCP_PENDING_STALL_CYCLES_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/device_inv_int/MI200/perfmon/timestamps.txt b/tests/workloads/device_inv_int/MI200/perfmon/timestamps.txt new file mode 100644 index 0000000000..676cca1b80 --- /dev/null +++ b/tests/workloads/device_inv_int/MI200/perfmon/timestamps.txt @@ -0,0 +1,5 @@ +pmc: + +gpu: +range: +kernel: diff --git a/tests/workloads/device_inv_int/MI200/pmc_perf.csv b/tests/workloads/device_inv_int/MI200/pmc_perf.csv new file mode 100644 index 0000000000..61f39cd23c --- /dev/null +++ b/tests/workloads/device_inv_int/MI200/pmc_perf.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_1,obj_1,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_2,obj_2,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,wave_size_3,obj_3,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_4,obj_4,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_5,obj_5,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_6,obj_6,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_7,obj_7,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_8,obj_8,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,TCC_EA_ATOMIC_LEVEL_sum,wave_size_9,obj_9,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_10,obj_10,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_11,obj_11,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_DRAM_sum,TCC_TAG_STALL_sum,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,wave_size_12,obj_12,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_13,obj_13,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_14,obj_14,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_15,obj_15,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_16,obj_16,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_17,obj_17,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,TD_COALESCABLE_WAVEFRONT_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_18,obj_18,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f9a6c228ec0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4097,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,216,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4099,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,90,0,4098,0,0,0,4096,0,0,0,4096,0,0,0,64,0x7f2937a68ec0,11006002,9848553,813385,344064,1688971,0,0,163840,832.0,515136.0,0.0,524288.0,261212.0,32768.0,508615,0,0,10959,131072.0,131072.0,0.0,131072.0,64,0x7f94aab9cec0,114688,0,32768,32768,16384,16384,65536,49152,27239232.0,85502204.0,39234167.0,131072.0,0.0,214329.0,0,0,14836,985.0,131081.0,0.0,10.0,64,0x7f8ec991cec0,0,1179824,4096,4096,0,1184747,4096,4096,0,1095241,4096,4096,0,1312053,4096,4096,0,1119705,4096,4096,0,1279152,4096,4096,0,1146894,4096,4096,0,1419418,4096,4096,0,1059357,4096,4096,0,955392,4096,4096,0,1177723,4096,4096,0,1147610,4096,4096,0,1142555,4096,4096,0,1295423,4096,4096,0,1244614,4096,4096,0,1176565,4096,4096,0,1307790,4096,4096,0,1099403,4096,4096,0,1255268,4096,4096,0,1441413,4096,4096,0,1096315,4096,4096,0,1313792,4096,4096,0,1070022,4096,4096,0,1165463,4096,4096,0,1269843,4096,4096,0,1221566,4096,4096,0,960162,4096,4096,0,1209517,4096,4096,0,1356484,4096,4096,0,1216090,4096,4096,0,1005949,4096,4096,0,1352581,4096,4096,64,0x7f29664d0ec0,230544,129864,16384,0,16384,16384,32768,49152,28817,28817,1966047.0,1356490.0,3655.0,143485.0,1055507.0,0.0,1348383.0,1050292.0,228833,137984,28817,0,28817,0,922144.0,489395.0,0.0,0.0,64,0x7f2a5913cec0,0,0,0,224,0,65536,64214,56,64,0x7fb169968ec0,0,0,0,0,0,0,168,56,131072.0,131072.0,0.0,936867.0,64,0x7f5b58528ec0,6358,0,4096,6390,0,4096,6365,0,4096,6363,0,4096,6359,0,4096,6377,0,4096,6327,0,4096,6330,0,4096,6335,0,4096,6361,0,4096,6392,0,4096,6371,0,4096,6365,0,4096,6363,0,4096,6376,0,4096,6329,0,4096,6343,0,4096,6323,0,4096,6337,0,4096,6394,0,4096,6391,0,4096,6355,0,4096,6374,0,4096,6604,0,4096,6440,0,4096,6346,0,4096,6323,0,4096,6339,0,4096,6395,0,4096,6386,0,4096,6352,0,4096,6380,0,4096,64,0x7ffbde45cec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,36964499.0,33819093.0,0.0,64,0x7f4f6bc44ec0,0,393216,163840,0,0,0,0,0,18192,0.0,0.0,0.0,32768.0,0.0,0.0,384.0,32768.0,4096,16384,352,28917,2240,0,56.0,8.0,0.0,204076.0,64,0x7f45efd94ec0,32768,32768,0,64,0x7f0432dc4ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131081.0,34583.0,46155.0,19381.0,64,0x7f3368474ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13656,18873,8498,545,0,27677,203868.0,0.0,72787.0,131081.0,64,0x7fd115474ec0,0,0,0,1079720,0,0,0,1134252,0,0,0,1045421,0,0,0,1022469,0,0,0,1142703,0,0,0,1146218,0,0,0,1128724,0,0,0,1111887,0,0,0,955800,0,0,0,1049019,0,0,0,1027599,0,0,0,1083365,0,0,0,973437,0,0,0,1124813,0,0,0,1061835,0,0,0,1168236,0,0,0,963833,0,0,0,1046292,0,0,0,1106744,0,0,0,1096318,0,0,0,1033391,0,0,0,1060045,0,0,0,1015723,0,0,0,1103195,0,0,0,1117196,0,0,0,1023077,0,0,0,1041474,0,0,0,1183148,0,0,0,1102262,0,0,0,1044954,0,0,0,983585,0,0,0,1135988,64,0x7f6344c98ec0,2241,4096,2241,6337,2302,4096,2302,6398,2261,4096,2261,6357,2315,4096,2315,6411,2245,4096,2245,6341,2255,4096,2255,6351,2283,4097,2284,6380,2260,4096,2260,6356,2259,4101,2264,6360,2241,4096,2241,6337,2304,4096,2304,6400,2264,4096,2264,6360,2318,4096,2318,6414,2248,4096,2248,6344,2258,4096,2258,6354,2282,4096,2282,6378,2312,4096,2312,6408,2269,4096,2269,6365,2305,4097,2306,6402,2260,4096,2260,6356,2289,4096,2289,6385,2257,4096,2257,6353,2265,4096,2265,6361,2397,4098,2399,6495,2234,4096,2234,6330,2315,4096,2315,6411,2271,4096,2271,6367,2354,4097,2355,6451,2261,4096,2261,6357,2290,4096,2290,6386,2256,4096,2256,6352,2266,4097,2267,6363,64,0x7fb37110cec0,1219,116932,0,0,65536,63800,56,1680,64,0x7f2bf1eb4ec0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,64,0x7fe24d508ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,11265,0,820,28544,0,73265.0,131072.0,0.0,65568.0,64,0x7fd2fe7f8ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65551.0,0.0,0.0,0.0,199001894935363,199001894955843 +1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f9a6c228ec0,4096,0,8,0,4096,0,1480,0,4099,0,749,0,4096,0,973,0,4096,0,28,0,4096,0,18,0,4096,0,504,0,4096,0,681,0,4096,0,0,0,4096,0,529,0,4097,0,423,0,4097,0,171,0,4096,0,123,0,4097,0,14,0,4096,0,361,0,4096,0,333,0,4096,0,859,0,4096,0,277,0,4098,0,0,0,4096,0,34,0,4096,0,917,0,4096,0,482,0,4096,0,149,0,4096,0,1642,0,4096,0,2497,0,4096,0,296,0,4096,0,610,0,4096,0,0,0,4096,0,80,0,4099,0,896,0,4096,0,223,0,4096,0,155,0,64,0x7f2937a68ec0,17442109,16824138,273907,344064,2559829,0,0,163840,0.0,524288.0,0.0,524288.0,473755.0,32768.0,744023,0,0,12076,91469.0,91469.0,0.0,91469.0,64,0x7f94aab9cec0,114688,0,32768,32768,16384,16384,65536,49152,58684283.0,202252507.0,50068835.0,131072.0,0.0,528959.0,0,0,25234,5071.0,131085.0,0.0,24.0,64,0x7f8ec991cec0,0,4053298,2812,2812,0,5308663,2868,2868,0,3454808,2848,2848,0,4348769,2864,2864,0,4297579,2884,2884,0,3439406,2852,2852,0,3286148,2876,2876,0,5347469,2796,2796,0,3999171,2800,2800,0,3171519,2812,2812,0,4247777,2862,2862,0,3552601,2846,2846,0,3383726,2864,2864,0,3929474,2884,2884,0,3974256,2852,2852,0,3298457,2876,2876,0,3671812,2830,2830,0,3699796,2848,2848,0,4266571,2850,2850,0,4211648,2844,2844,0,3904572,2840,2840,0,4286664,2860,2860,0,3192445,2840,2840,0,4691568,2832,2832,0,4205176,2832,2832,0,3857193,2824,2824,0,3382754,2848,2848,0,3428950,2844,2844,0,3600961,2840,2840,0,2908010,2836,2836,0,3081597,2864,2864,0,4344951,2840,2840,64,0x7f29664d0ec0,333392,226065,16384,0,16384,16384,32768,49152,41673,41673,3215463.0,2486094.0,4544.0,386757.0,1698384.0,0.0,2473902.0,2167306.0,333384,235179,41673,0,41673,0,1333536.0,789257.0,0.0,0.0,64,0x7f2a5913cec0,0,0,0,56,0,65536,65536,0,64,0x7fb169968ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2034549.0,64,0x7f5b58528ec0,6274,0,4096,6281,0,4096,6274,0,4096,6273,0,4096,6296,0,4096,6257,0,4096,6300,0,4096,6304,0,4096,6299,0,4096,6275,0,4096,6281,0,4096,6275,0,4096,6273,0,4096,6296,0,4096,6263,0,4096,6300,0,4096,6278,0,4096,6312,0,4096,6295,0,4096,6277,0,4096,6247,0,4096,6291,0,4096,6264,0,4096,6305,0,4096,6309,0,4096,6281,0,4096,6312,0,4096,6293,0,4096,6277,0,4096,6245,0,4096,6295,0,4096,6260,0,4096,64,0x7ffbde45cec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,114993725.0,54736282.0,0.0,64,0x7f4f6bc44ec0,0,393216,163840,0,0,0,0,0,30625,0.0,0.0,0.0,32768.0,0.0,0.0,226.0,32768.0,4096,16384,302,42149,2062,0,56.0,12.0,0.0,201132.0,64,0x7f45efd94ec0,32768,32768,0,64,0x7f0432dc4ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131083.0,113320.0,45613.0,0.0,64,0x7f3368474ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,33476,27568,9679,3091,0,40813,200853.0,0.0,69770.0,131083.0,64,0x7fd115474ec0,0,0,0,1902501,0,0,0,1773219,0,0,0,1828587,125,0,0,1959593,44,0,0,1743737,191,0,0,1928450,0,0,0,1491817,306,0,0,2171414,235,0,0,1964093,0,0,0,1516128,0,0,0,1648016,0,0,0,1666965,117,0,0,1903701,217,0,0,1832230,70,0,0,1665619,0,0,0,1537253,0,0,0,1869651,0,0,0,1490493,0,0,0,2132873,0,0,0,2322381,0,0,0,1982215,0,0,0,1837909,0,0,0,1394897,0,0,0,1823369,0,0,0,1621199,0,0,0,1617817,0,0,0,1515019,0,0,0,1799969,1145,0,0,2655551,0,0,0,1675597,47,0,0,1837476,21,0,0,1871388,64,0x7f6344c98ec0,2177,4096,2177,6273,2186,4096,2186,6282,2154,4096,2154,6250,2177,4097,2178,6274,2227,4096,2227,6323,2216,4096,2216,6312,2165,4097,2166,6262,2157,4096,2157,6253,2160,4100,2164,6260,2180,4096,2180,6276,2186,4096,2186,6282,2152,4096,2152,6248,2180,4096,2180,6276,2232,4096,2232,6328,2224,4096,2224,6320,2165,4096,2165,6261,2163,4096,2163,6259,2188,4096,2188,6284,2204,4099,2207,6303,2172,4096,2172,6268,2165,4096,2165,6261,2195,4096,2195,6291,2204,4096,2204,6300,2197,4096,2197,6293,2190,4096,2190,6286,2160,4096,2160,6256,2191,4096,2191,6287,2265,4097,2266,6362,2177,4097,2178,6274,2166,4096,2166,6262,2197,4096,2197,6293,2211,4097,2212,6308,64,0x7fb37110cec0,0,189319,0,0,65536,63800,56,1680,64,0x7f2bf1eb4ec0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,64,0x7fe24d508ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,21917,0,3200,38716,0,70007.0,131072.0,0.0,45614.0,64,0x7fd2fe7f8ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65554.0,0.0,0.0,0.0,199001895045923,199001895062403 +2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f9a6c228ec0,4096,0,0,0,4096,0,61,0,4099,0,39,0,4096,0,598,0,4096,0,0,0,4096,0,603,0,4096,0,1572,0,4096,0,1491,0,4096,0,767,0,4096,0,4,0,4097,0,506,0,4097,0,623,0,4096,0,0,0,4097,0,492,0,4096,0,45,0,4096,0,971,0,4096,0,1309,0,4096,0,689,0,4098,0,104,0,4096,0,110,0,4096,0,0,0,4096,0,26,0,4096,0,642,0,4096,0,969,0,4096,0,753,0,4096,0,285,0,4096,0,180,0,4096,0,294,0,4096,0,124,0,4099,0,316,0,4096,0,0,0,4096,0,277,0,64,0x7f2937a68ec0,19212072,17889234,978774,344064,2828431,0,0,163840,832.0,515156.0,0.0,524288.0,651940.0,32768.0,962483,0,0,14247,91258.0,91258.0,0.0,91258.0,64,0x7f94aab9cec0,114688,0,32768,32768,16384,16384,65536,49152,59012238.0,203962207.0,49799072.0,131072.0,0.0,613464.0,0,0,25520,25605.0,131085.0,0.0,24.0,64,0x7f8ec991cec0,0,3500985,2810,2810,0,4465598,2856,2856,0,3139145,2876,2876,0,4828031,2866,2866,0,4272524,2868,2868,0,4639315,2828,2828,0,3168068,2864,2864,0,3509805,2824,2824,0,4089463,2824,2824,0,2984079,2812,2812,0,3969660,2856,2856,0,2815232,2880,2880,0,3730141,2866,2866,0,3945959,2864,2864,0,4215769,2828,2828,0,3595329,2864,2864,0,3573539,2808,2808,0,4453356,2836,2836,0,3262638,2844,2844,0,4107953,2828,2828,0,3955268,2856,2856,0,3741482,2884,2884,0,4475161,2830,2830,0,4123623,2824,2824,0,3853112,2824,2824,0,2678326,2804,2804,0,3157757,2836,2836,0,3570615,2844,2844,0,3788053,2828,2828,0,3648549,2856,2856,0,3216476,2884,2884,0,4553292,2832,2832,64,0x7f29664d0ec0,332968,225188,16384,0,16384,16384,32768,49152,41620,41620,3204620.0,2435646.0,4679.0,336921.0,1612536.0,0.0,2423654.0,2115789.0,332960,234475,41620,0,41620,0,1331840.0,769041.0,0.0,0.0,64,0x7f2a5913cec0,0,0,0,56,0,65536,65536,0,64,0x7fb169968ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2078739.0,64,0x7f5b58528ec0,6272,0,4096,6271,0,4096,6273,0,4096,6267,0,4096,6265,0,4096,6291,0,4096,6305,0,4096,6259,0,4096,6258,0,4096,6276,0,4096,6275,0,4096,6273,0,4096,6266,0,4096,6268,0,4096,6294,0,4096,6307,0,4096,6317,0,4096,6336,0,4096,6276,0,4096,6264,0,4096,6285,0,4096,6304,0,4096,6270,0,4096,6323,0,4096,6327,0,4096,6317,0,4096,6337,0,4096,6274,0,4096,6265,0,4096,6279,0,4096,6303,0,4096,6270,0,4096,64,0x7ffbde45cec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,122720872.0,59508672.0,0.0,64,0x7f4f6bc44ec0,0,393216,163840,0,0,0,0,0,29950,0.0,0.0,0.0,32768.0,0.0,0.0,183.0,32768.0,4096,16384,302,41324,2064,0,56.0,11.0,0.0,200699.0,64,0x7f45efd94ec0,32768,32768,0,64,0x7f0432dc4ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131083.0,94142.0,45588.0,0.0,64,0x7f3368474ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,33548,28329,9681,2572,0,40307,201246.0,0.0,70161.0,131085.0,64,0x7fd115474ec0,0,0,0,1672867,0,0,0,1772478,0,0,0,1793173,0,0,0,1756705,0,0,0,1692171,16,0,0,2001859,0,0,0,1516869,0,0,0,1582399,0,0,0,1495708,1,0,0,1835980,192,0,0,2154216,0,0,0,1590847,310,0,0,1732891,0,0,0,1537215,0,0,0,1741083,0,0,0,1462858,0,0,0,1421382,51,0,0,1543396,10,0,0,1987202,62,0,0,2046958,0,0,0,1835595,0,0,0,1775664,0,0,0,1532975,0,0,0,1767950,970,0,0,2553432,0,0,0,1723931,0,0,0,1312116,577,0,0,2382098,80,0,0,1948886,0,0,0,1869305,0,0,0,1467726,103,0,0,1725884,64,0x7f6344c98ec0,2170,4096,2170,6266,2190,4096,2190,6286,2146,4096,2146,6242,2170,4097,2171,6267,2205,4096,2205,6301,2174,4096,2174,6270,2155,4097,2156,6252,2164,4096,2164,6260,2169,4101,2174,6270,2170,4096,2170,6266,2192,4096,2192,6288,2144,4096,2144,6240,2168,4096,2168,6264,2207,4096,2207,6303,2177,4096,2177,6273,2157,4096,2157,6253,2153,4096,2153,6249,2199,4096,2199,6295,2163,4099,2166,6262,2180,4096,2180,6276,2154,4096,2154,6250,2161,4096,2161,6257,2222,4096,2222,6318,2200,4096,2200,6296,2198,4096,2198,6294,2156,4096,2156,6252,2194,4096,2194,6290,2222,4097,2223,6319,2183,4097,2184,6280,2159,4096,2159,6255,2160,4096,2160,6256,2227,4097,2228,6324,64,0x7fb37110cec0,0,187457,0,0,65536,63800,56,1680,64,0x7f2bf1eb4ec0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,64,0x7fe24d508ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,21559,0,3201,38687,0,69886.0,131072.0,0.0,45669.0,64,0x7fd2fe7f8ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65554.0,0.0,0.0,0.0,199001895083363,199001895098883 diff --git a/tests/workloads/device_inv_int/MI200/roofline.csv b/tests/workloads/device_inv_int/MI200/roofline.csv new file mode 100644 index 0000000000..d8d5915d2f --- /dev/null +++ b/tests/workloads/device_inv_int/MI200/roofline.csv @@ -0,0 +1,5 @@ +device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh +0,1388.4407,1387.9556,1388.9258,5012.3818,5009.4272,5015.3364,9220.9736,9220.4082,9221.5391,18048.867,18047.982,18049.752,20929.025,20868.734,20989.316,20262.105,20261.408,20262.803,170368.28,170364.62,170371.94,164833.34,164829.61,164837.08,41411.355,41410.75,41411.961,41471.086,41470.277,41471.895,166320.92,165829.64,166812.2 +1,1388.9957,1388.3947,1389.5968,5027.0874,5024.9897,5029.1851,9231.418,9230.6963,9232.1396,18088.484,18084.846,18092.123,20968.271,20901.262,21035.281,20286.959,20286.332,20287.586,170792.02,170786.41,170797.62,165064.95,165061.06,165068.84,41475.48,41474.453,41476.508,41528.645,41527.684,41529.605,166824.89,166821.84,166827.94 +2,1388.7762,1388.223,1389.3295,5033.8354,5031.5078,5036.1631,9260.0098,9259.3555,9260.6641,18109.824,18108.805,18110.844,21048.404,21047.924,21048.885,20354.592,20354.098,20355.086,171145.12,171140.94,171149.31,165515.59,165511.66,165519.53,41583.41,41582.383,41584.438,41643.316,41641.996,41644.637,166962.69,166359.5,167565.88 +3,1389.2411,1388.7584,1389.7238,5030.2002,5028.9575,5031.4429,9239.7422,9239.1396,9240.3447,18027.953,18024.689,18031.217,21032.553,21032.098,21033.008,20313.242,20312.57,20313.914,171017.05,171013.84,171020.25,165231.08,165227.28,165234.88,41521.387,41520.555,41522.219,41580.211,41579.453,41580.969,167016.34,167014.17,167018.52 diff --git a/tests/workloads/device_inv_int/MI200/sysinfo.csv b/tests/workloads/device_inv_int/MI200/sysinfo.csv new file mode 100644 index 0000000000..29a3cdacbe --- /dev/null +++ b/tests/workloads/device_inv_int/MI200/sysinfo.csv @@ -0,0 +1,2 @@ +workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd +device_inv_int,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 02:27:36 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/device_inv_int/MI200/timestamps.csv b/tests/workloads/device_inv_int/MI200/timestamps.csv new file mode 100644 index 0000000000..e0b15ace6a --- /dev/null +++ b/tests/workloads/device_inv_int/MI200/timestamps.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,325033,325033,1048576,256,0,0,8,0,16,64,0x0,0x7f31a7fccec0,199001894911168,199001894935363,199001894955843,199001894968617 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,325033,325033,1048576,256,0,0,8,0,16,64,0x0,0x7f31a7fccec0,199001894966613,199001895045923,199001895062403,199001895063647 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,325033,325033,1048576,256,0,0,8,0,16,64,0x0,0x7f31a7fccec0,199001895073536,199001895083363,199001895098883,199001895100126 diff --git a/tests/workloads/dispatch_0/MI100/SQ_IFETCH_LEVEL.csv b/tests/workloads/dispatch_0/MI100/SQ_IFETCH_LEVEL.csv index d6996ad777..abd79556f9 100644 --- a/tests/workloads/dispatch_0/MI100/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/dispatch_0/MI100/SQ_IFETCH_LEVEL.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2847318,2847318,1048576,256,0,0,8,8,16,64,0x0,0x7f6648898e80,47274,47274,16384,65536,13112,1663272,2187803528527851,2187803983015672,2187803983039992,2187803536033431 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,150756,150756,1048576,256,0,0,8,8,16,64,0x0,0x7f820df66e80,47744,47744,16384,65536,12856,1674844,194204807313230,194218184431477,194218184455957,194204815275476 diff --git a/tests/workloads/dispatch_0/MI100/SQ_INST_LEVEL_LDS.csv b/tests/workloads/dispatch_0/MI100/SQ_INST_LEVEL_LDS.csv index 5c59b31fdd..61b0e93dcb 100644 --- a/tests/workloads/dispatch_0/MI100/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/dispatch_0/MI100/SQ_INST_LEVEL_LDS.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2846769,2846769,1048576,256,0,0,8,8,16,64,0x0,0x7fe51c612e80,0,0,0,2187801917565820,2187803983015672,2187803983039992,2187801925224307 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,150941,150941,1048576,256,0,0,8,8,16,64,0x0,0x7fb5db332e80,0,0,0,194205315685723,194218184431477,194218184455957,194205323317172 diff --git a/tests/workloads/dispatch_0/MI100/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/dispatch_0/MI100/SQ_INST_LEVEL_SMEM.csv index 573b6fc04d..972eec206c 100644 --- a/tests/workloads/dispatch_0/MI100/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/dispatch_0/MI100/SQ_INST_LEVEL_SMEM.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2849331,2849331,1048576,256,0,0,8,8,16,64,0x0,0x7f6f424dce80,65536,205200,26259424,2187809164143107,2187803983015672,2187803983039992,2187809171645862 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,151125,151125,1048576,256,0,0,8,8,16,64,0x0,0x7f690a0c0e80,65536,205956,26258976,194205816966838,194218184431477,194218184455957,194205824797164 diff --git a/tests/workloads/dispatch_0/MI100/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/dispatch_0/MI100/SQ_INST_LEVEL_VMEM.csv index 48e35dea98..9d543ed6ad 100644 --- a/tests/workloads/dispatch_0/MI100/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/dispatch_0/MI100/SQ_INST_LEVEL_VMEM.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2849148,2849148,1048576,256,0,0,8,8,16,64,0x0,0x7f37e6006e80,32768,652733,83542268,2187808723799978,2187803983015672,2187803983039992,2187808731263349 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,151312,151312,1048576,256,0,0,8,8,16,64,0x0,0x7fa9adb0ce80,32768,667106,85389576,194206315490934,194218184431477,194218184455957,194206323400790 diff --git a/tests/workloads/dispatch_0/MI100/SQ_LEVEL_WAVES.csv b/tests/workloads/dispatch_0/MI100/SQ_LEVEL_WAVES.csv index d8a2887ac3..790b97edc7 100644 --- a/tests/workloads/dispatch_0/MI100/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/dispatch_0/MI100/SQ_LEVEL_WAVES.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2847684,2847684,1048576,256,0,0,8,8,16,64,0x0,0x7f54e0f84e80,47118,47118,17095,376952,16384,24302477,224867,0,97701064,2187804428513108,2187803983015672,2187803983039992,2187804436177596 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,151497,151497,1048576,256,0,0,8,8,16,64,0x0,0x7fd5b2e38e80,48008,48008,17263,384072,16384,24600233,232757,0,98897844,194207844573840,194218184431477,194218184455957,194207852970067 diff --git a/tests/workloads/dispatch_0/MI100/pmc_dispatch_info.csv b/tests/workloads/dispatch_0/MI100/pmc_dispatch_info.csv new file mode 100644 index 0000000000..e90d72a8cf --- /dev/null +++ b/tests/workloads/dispatch_0/MI100/pmc_dispatch_info.csv @@ -0,0 +1,2 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) ",2 diff --git a/tests/workloads/dispatch_0/MI100/pmc_perf.csv b/tests/workloads/dispatch_0/MI100/pmc_perf.csv index faf7fa7a69..312389d032 100644 --- a/tests/workloads/dispatch_0/MI100/pmc_perf.csv +++ b/tests/workloads/dispatch_0/MI100/pmc_perf.csv @@ -1,2 +1,2 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_1,obj_1,TCC_EA_ATOMIC_LEVEL_sum,wave_size_2,obj_2,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_3,obj_3,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_4,obj_4,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_5,obj_5,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_6,obj_6,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_7,obj_7,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_8,obj_8,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_9,obj_9,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_10,obj_10,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_11,obj_11,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_12,obj_12,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_13,obj_13,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_14,obj_14,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_15,obj_15,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_16,obj_16,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f3220ad8e80,5194,0,0,2068203,1563,0,0,1843585,3890,0,0,2073188,2357,0,0,1838800,2906,0,0,1964866,4123,0,0,2083082,3019,0,0,1980401,1126,0,0,1739217,2116,0,0,1962610,1504,0,0,1795225,1893,0,0,1830723,1209,0,0,1785576,4221,0,0,2003673,1084,0,0,1758536,2170,0,0,1839537,3071,0,0,1989820,2776,0,0,1985830,959,0,0,1670065,2681,0,0,1964489,967,0,0,1717976,4012,0,0,1999840,1581,0,0,1835655,3739,0,0,2092282,4524,0,0,2054051,2952,0,0,1918369,1198,0,0,1720286,5344,0,0,2211346,2601,0,0,1880845,6753,0,0,2217821,1776,0,0,1831363,2655,0,0,1983750,1120,0,0,1715153,64,0x7fb31e25ae80,0.0,64,0x7f9f45336e80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8359,4263,8359,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8293,4197,8293,0,8192,4096,8192,141,8195,4240,8336,0,8192,4096,8192,0,8192,4096,8192,64,0x7fc45c54ae80,0,0,192,0,65536,64497,48,1259,31452,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,538,47535,1729,0,48.0,272.0,0.0,262288.0,64,0x7f579ad28e80,2189028,360448,163840,0,0,180224,114688,0,70558815.0,206983996.0,80339137.0,131072.0,0.0,642414.0,0,0,26760,102589.0,0.0,0.0,102589.0,64,0x7f7261662e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,47698,0,131602.0,131072.0,0.0,131104.0,64,0x7f088cfe6e80,131072.0,131072.0,0.0,2625172.0,0.0,0.0,131872564.0,62296285.0,64,0x7efc40a26e80,0,2748501,4096,4096,0,3840100,4096,4096,0,4108452,4096,4096,0,2947343,4096,4096,0,3040477,4096,4096,0,3944044,4096,4096,0,2476802,4096,4096,0,5514695,4096,4096,0,2654547,4096,4096,0,3100262,4096,4096,0,2543709,4096,4096,0,3048461,4096,4096,0,2748338,4096,4096,0,3115526,4096,4096,0,2817235,4096,4096,0,2910248,4096,4096,0,3715184,4096,4096,0,2711504,4096,4096,0,5531972,4096,4096,0,3330972,4096,4096,0,2426014,4096,4096,0,2979586,4096,4096,0,2771918,4096,4096,0,4178575,4096,4096,0,2722573,4096,4096,0,2557628,4096,4096,0,3670745,4096,4096,0,2622149,4096,4096,0,2973558,4096,4096,0,2932333,4096,4096,0,3170785,4096,4096,0,3767901,4096,4096,64,0x7f55fbb72e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,62758.0,127852.0,64,0x7f912d192e80,8192,0,4096,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fbaf9664e80,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,0,47999,0,0,64,0x7f8b1336ae80,388104,236742,3433945,16384,24696797,144,48,0,48512,48512,3903956.0,3037429.0,5449.0,1090465.0,2229924.0,0.0,3027940.0,2718747.0,386391,246680,48512,0,48512,0,1552384.0,960412.0,0.0,0.0,64,0x7f4751190e80,32768,0,0,0,16384,16384,393216,22877477,960.0,513951.0,0.0,524288.0,845849.0,32768.0,0,0,0,16973,131072.0,131072.0,0.0,131072.0,64,0x7f151fa60e80,4096,0,36,0,4096,0,243,0,4096,0,2302,0,4099,0,2066,0,4096,0,0,0,4096,0,216,0,4096,0,1178,0,4096,0,3427,0,4096,0,419,0,4096,0,197,0,4096,0,1296,0,4096,0,2326,0,4096,0,0,0,4096,0,119,0,4096,0,1419,0,4096,0,518,0,4096,0,455,0,4096,0,3745,0,4096,0,1585,0,4096,0,1758,0,4096,0,0,0,4096,0,771,0,4096,0,808,0,4096,0,1202,0,4096,0,312,0,4096,0,368,0,4096,0,1749,0,4144,0,1214,0,4096,0,0,0,4096,0,0,0,4096,0,186,0,4383,0,4023,0,64,0x7fc36170ee80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86453.0,44619.0,131111.0,0.0,64,0x7f9891c60e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131343.0,0.0,534.0,131342.0,64,0x7f7894b7ce80,201258,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13158,29542,9936,550,0,46514,262665.0,0.0,188.0,262477.0,2187803983015672,2187803983039992 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCC_EA_ATOMIC_LEVEL_sum,wave_size_1,obj_1,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_2,obj_2,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_3,obj_3,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_4,obj_4,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_5,obj_5,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_6,obj_6,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_7,obj_7,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_8,obj_8,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_9,obj_9,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_10,obj_10,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_11,obj_11,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_12,obj_12,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_13,obj_13,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_14,obj_14,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_15,obj_15,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_16,obj_16,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f9b7aa06e80,0.0,64,0x7f5584210e80,4096,0,1935,0,4096,0,4,0,4099,0,673,0,4096,0,289,0,4096,0,431,0,4264,0,2540,0,4096,0,200,0,4096,0,6850,0,4096,0,2220,0,4098,0,155,0,4144,0,3511,0,4096,0,4462,0,4096,0,657,0,4096,0,280,0,4096,0,4755,0,4096,0,1052,0,4096,0,1770,0,4096,0,1068,0,4096,0,1662,0,4096,0,676,0,4096,0,2234,0,4096,0,1260,0,4096,0,853,0,4096,0,1203,0,4096,0,1029,0,4096,0,785,0,4096,0,4254,0,4097,0,614,0,4144,0,154,0,4096,0,1122,0,4096,0,2872,0,4096,0,3055,0,64,0x7f2d132cce80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86608.0,44464.0,131112.0,0.0,64,0x7f49e98cee80,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,64,0x7f9fb07dce80,131072.0,131072.0,0.0,2605084.0,0.0,0.0,91634054.0,56016744.0,64,0x7f8a5d196e80,1222,0,0,1672592,4137,0,0,2116484,2098,0,0,1855201,2630,0,0,1863877,1290,0,0,1755336,1301,0,0,1712227,1631,0,0,1809381,3344,0,0,1987834,1339,0,0,1790962,5144,0,0,2057655,1010,0,0,1740292,3317,0,0,1921560,4433,0,0,2139790,1177,0,0,1759290,845,0,0,1730331,4724,0,0,2113318,1217,0,0,1798941,1304,0,0,1734767,1490,0,0,1725463,2798,0,0,1882071,986,0,0,1737550,5807,0,0,2258275,2334,0,0,1863442,7724,0,0,2306468,3065,0,0,1909158,1358,0,0,1774221,1211,0,0,1748337,4580,0,0,2026474,977,0,0,1619259,6715,0,0,2261394,679,0,0,1669914,2749,0,0,1841898,64,0x7f7855560e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,48592,0,131613.0,131072.0,0.0,131104.0,64,0x7fbcc9bf8e80,0,3744845,4096,4096,0,2419114,4096,4096,0,3527926,4096,4096,0,2991557,4096,4096,0,5028313,4096,4096,0,3041846,4096,4096,0,3725318,4096,4096,0,5222933,4096,4096,0,2765341,4096,4096,0,2604617,4096,4096,0,5094887,4096,4096,0,4430574,4096,4096,0,2585796,4096,4096,0,2774314,4096,4096,0,3775925,4096,4096,0,2776109,4096,4096,0,3241025,4096,4096,0,3624424,4096,4096,0,4396971,4096,4096,0,3841404,4096,4096,0,2863297,4096,4096,0,4437948,4096,4096,0,3158849,4096,4096,0,4356441,4096,4096,0,2607802,4096,4096,0,2700884,4096,4096,0,4086063,4096,4096,0,3906988,4096,4096,0,2954270,4096,4096,0,2865625,4096,4096,0,3464833,4096,4096,0,3219484,4096,4096,64,0x7fc5fb9dce80,385384,235430,3434307,16384,25114810,144,48,0,48172,48172,3883841.0,3057301.0,5938.0,928736.0,2103263.0,0.0,3048047.0,2736387.0,384063,245364,48172,0,48172,0,1541504.0,959387.0,0.0,0.0,64,0x7fe1aa3dce80,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f0c9b118e80,0,0,192,0,65536,64468,48,1376,31964,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,538,48151,1769,0,48.0,439.0,0.0,262288.0,64,0x7f1ebae36e80,0,8192,4096,8192,0,8192,4096,8192,141,8195,4240,8336,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8355,4259,8355,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f7c145dae80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,57167.0,122935.0,64,0x7fb464ddae80,191328,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13331,29715,9995,550,0,46439,262620.0,0.0,188.0,262432.0,64,0x7fc82ce98e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131309.0,0.0,466.0,131308.0,64,0x7f93c8fd2e80,2137191,360448,163840,0,0,180224,114688,0,70122419.0,194516738.0,77228435.0,131072.0,0.0,734493.0,0,0,27069,67406.0,0.0,0.0,67406.0,64,0x7f72bbc4ae80,32768,0,0,0,16384,16384,393216,22509426,960.0,513968.0,0.0,524288.0,1033477.0,32768.0,0,0,0,17038,131072.0,131072.0,0.0,131072.0,194218184431477,194218184455957 diff --git a/tests/workloads/dispatch_0/MI100/sysinfo.csv b/tests/workloads/dispatch_0/MI100/sysinfo.csv index 7afbba2bb7..54e879b37d 100644 --- a/tests/workloads/dispatch_0/MI100/sysinfo.csv +++ b/tests/workloads/dispatch_0/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -dispatch_0,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Fri Mar 1 16:45:11 2024 (CST),1,t006-003.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651240,,5.7.1-98,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +dispatch_0,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 07 Mar 2024 01:07:49 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/dispatch_0/MI100/timestamps.csv b/tests/workloads/dispatch_0/MI100/timestamps.csv index 3b34558213..fbc023c1d0 100644 --- a/tests/workloads/dispatch_0/MI100/timestamps.csv +++ b/tests/workloads/dispatch_0/MI100/timestamps.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,2847501,2847501,1048576,256,0,0,8,8,16,64,0x0,0x7face032ee80,2187803982990937,2187803983015672,2187803983039992,2187803983054696 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,154895,154895,1048576,256,0,0,8,8,16,64,0x0,0x7f26e5422e80,194218184405603,194218184431477,194218184455957,194218184468662 diff --git a/tests/workloads/dispatch_0/MI200/SQ_IFETCH_LEVEL.csv b/tests/workloads/dispatch_0/MI200/SQ_IFETCH_LEVEL.csv new file mode 100644 index 0000000000..dda5e22f08 --- /dev/null +++ b/tests/workloads/dispatch_0/MI200/SQ_IFETCH_LEVEL.csv @@ -0,0 +1,2 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,306015,306015,1048576,256,0,0,8,0,16,64,0x0,0x7fd36d3a0ec0,27553,27553,16384,65536,14040,1568448,198487811862509,198500539781025,198500539801025,198487828148739 diff --git a/tests/workloads/dispatch_0/MI200/SQ_INST_LEVEL_LDS.csv b/tests/workloads/dispatch_0/MI200/SQ_INST_LEVEL_LDS.csv new file mode 100644 index 0000000000..bb1e96b729 --- /dev/null +++ b/tests/workloads/dispatch_0/MI200/SQ_INST_LEVEL_LDS.csv @@ -0,0 +1,2 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,306217,306217,1048576,256,0,0,8,0,16,64,0x0,0x7f1d6cb44ec0,0,0,0,198488296151539,198500539781025,198500539801025,198488312049765 diff --git a/tests/workloads/dispatch_0/MI200/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/dispatch_0/MI200/SQ_INST_LEVEL_SMEM.csv new file mode 100644 index 0000000000..7de8913869 --- /dev/null +++ b/tests/workloads/dispatch_0/MI200/SQ_INST_LEVEL_SMEM.csv @@ -0,0 +1,2 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,306419,306419,1048576,256,0,0,8,0,16,64,0x0,0x7efbf7208ec0,65536,172952,19460368,198488779287609,198500539781025,198500539801025,198488795365134 diff --git a/tests/workloads/dispatch_0/MI200/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/dispatch_0/MI200/SQ_INST_LEVEL_VMEM.csv new file mode 100644 index 0000000000..d9ca2ff134 --- /dev/null +++ b/tests/workloads/dispatch_0/MI200/SQ_INST_LEVEL_VMEM.csv @@ -0,0 +1,2 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,306621,306621,1048576,256,0,0,8,0,16,64,0x0,0x7f5805234ec0,32768,291597,32660248,198489259151227,198500539781025,198500539801025,198489275062158 diff --git a/tests/workloads/dispatch_0/MI200/SQ_LEVEL_WAVES.csv b/tests/workloads/dispatch_0/MI200/SQ_LEVEL_WAVES.csv new file mode 100644 index 0000000000..bfc0e93d5e --- /dev/null +++ b/tests/workloads/dispatch_0/MI200/SQ_LEVEL_WAVES.csv @@ -0,0 +1,2 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,306807,306807,1048576,256,0,0,8,0,16,64,0x0,0x7fe505304ec0,28097,28097,10788,224784,16384,11140767,132548,0,45073020,198489738658391,198500539781025,198500539801025,198489754777786 diff --git a/tests/workloads/dispatch_0/MI200/perfmon/SQ_IFETCH_LEVEL.txt b/tests/workloads/dispatch_0/MI200/perfmon/SQ_IFETCH_LEVEL.txt new file mode 100644 index 0000000000..ad08a34f3f --- /dev/null +++ b/tests/workloads/dispatch_0/MI200/perfmon/SQ_IFETCH_LEVEL.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES + +gpu: +range: 0 +kernel: diff --git a/tests/workloads/dispatch_0/MI200/perfmon/SQ_INST_LEVEL_LDS.txt b/tests/workloads/dispatch_0/MI200/perfmon/SQ_INST_LEVEL_LDS.txt new file mode 100644 index 0000000000..1ea4fc1fd5 --- /dev/null +++ b/tests/workloads/dispatch_0/MI200/perfmon/SQ_INST_LEVEL_LDS.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES + +gpu: +range: 0 +kernel: diff --git a/tests/workloads/dispatch_0/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt b/tests/workloads/dispatch_0/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt new file mode 100644 index 0000000000..9c8a738a40 --- /dev/null +++ b/tests/workloads/dispatch_0/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: 0 +kernel: diff --git a/tests/workloads/dispatch_0/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt b/tests/workloads/dispatch_0/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt new file mode 100644 index 0000000000..aacd4c0da0 --- /dev/null +++ b/tests/workloads/dispatch_0/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: 0 +kernel: diff --git a/tests/workloads/dispatch_0/MI200/perfmon/SQ_LEVEL_WAVES.txt b/tests/workloads/dispatch_0/MI200/perfmon/SQ_LEVEL_WAVES.txt new file mode 100644 index 0000000000..f2c3fa3aeb --- /dev/null +++ b/tests/workloads/dispatch_0/MI200/perfmon/SQ_LEVEL_WAVES.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES + +gpu: +range: 0 +kernel: diff --git a/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_0.txt b/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_0.txt new file mode 100644 index 0000000000..8b34e00101 --- /dev/null +++ b/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_0.txt @@ -0,0 +1,5 @@ +pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES SQ_INSTS_VALU_CVT SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU GRBM_COUNT GRBM_GUI_ACTIVE TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum TA_TA_BUSY_sum TA_BUFFER_WAVEFRONTS_sum TD_TD_BUSY_sum TD_TC_STALL_sum SPI_CSN_WINDOW_VALID SPI_CSN_BUSY CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum + +gpu: +range: 0 +kernel: diff --git a/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_1.txt b/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_1.txt new file mode 100644 index 0000000000..d7a693bccc --- /dev/null +++ b/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_1.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VSKIPPED SQ_INSTS SQ_INSTS_VALU SQ_INSTS_VALU_ADD_F16 SQ_INSTS_VALU_MUL_F16 SQ_INSTS_VALU_FMA_F16 SQ_INSTS_VALU_TRANS_F16 SQ_INSTS_VALU_ADD_F32 GRBM_SPI_BUSY TCP_READ_TAGCONFLICT_STALL_CYCLES_sum TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum TCP_TA_TCP_STATE_READ_sum TA_BUFFER_READ_WAVEFRONTS_sum TA_BUFFER_WRITE_WAVEFRONTS_sum TD_SPI_STALL_sum TD_LOAD_WAVEFRONT_sum SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum + +gpu: +range: 0 +kernel: diff --git a/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_10.txt b/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_10.txt new file mode 100644 index 0000000000..9e6300392b --- /dev/null +++ b/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_10.txt @@ -0,0 +1,5 @@ +pmc: SQC_TC_DATA_WRITE_REQ SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES + +gpu: +range: 0 +kernel: diff --git a/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_11.txt b/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_11.txt new file mode 100644 index 0000000000..f5ed8c59b9 --- /dev/null +++ b/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_11.txt @@ -0,0 +1,5 @@ +pmc: SQC_ICACHE_MISSES_DUPLICATE SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE + +gpu: +range: 0 +kernel: diff --git a/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_12.txt b/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_12.txt new file mode 100644 index 0000000000..2b973739c5 --- /dev/null +++ b/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_12.txt @@ -0,0 +1,5 @@ +pmc: SQC_DCACHE_REQ_READ_1 SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 + +gpu: +range: 0 +kernel: diff --git a/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_13.txt b/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_13.txt new file mode 100644 index 0000000000..823fd3dc83 --- /dev/null +++ b/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_13.txt @@ -0,0 +1,5 @@ +pmc: TCC_ATOMIC[0] TCC_CYCLE[0] TCC_EA_ATOMIC[0] TCC_EA_ATOMIC_LEVEL[0] TCC_ATOMIC[1] TCC_CYCLE[1] TCC_EA_ATOMIC[1] TCC_EA_ATOMIC_LEVEL[1] TCC_ATOMIC[2] TCC_CYCLE[2] TCC_EA_ATOMIC[2] TCC_EA_ATOMIC_LEVEL[2] TCC_ATOMIC[3] TCC_CYCLE[3] TCC_EA_ATOMIC[3] TCC_EA_ATOMIC_LEVEL[3] TCC_ATOMIC[4] TCC_CYCLE[4] TCC_EA_ATOMIC[4] TCC_EA_ATOMIC_LEVEL[4] TCC_ATOMIC[5] TCC_CYCLE[5] TCC_EA_ATOMIC[5] TCC_EA_ATOMIC_LEVEL[5] TCC_ATOMIC[6] TCC_CYCLE[6] TCC_EA_ATOMIC[6] TCC_EA_ATOMIC_LEVEL[6] TCC_ATOMIC[7] TCC_CYCLE[7] TCC_EA_ATOMIC[7] TCC_EA_ATOMIC_LEVEL[7] TCC_ATOMIC[8] TCC_CYCLE[8] TCC_EA_ATOMIC[8] TCC_EA_ATOMIC_LEVEL[8] TCC_ATOMIC[9] TCC_CYCLE[9] TCC_EA_ATOMIC[9] TCC_EA_ATOMIC_LEVEL[9] TCC_ATOMIC[10] TCC_CYCLE[10] TCC_EA_ATOMIC[10] TCC_EA_ATOMIC_LEVEL[10] TCC_ATOMIC[11] TCC_CYCLE[11] TCC_EA_ATOMIC[11] TCC_EA_ATOMIC_LEVEL[11] TCC_ATOMIC[12] TCC_CYCLE[12] TCC_EA_ATOMIC[12] TCC_EA_ATOMIC_LEVEL[12] TCC_ATOMIC[13] TCC_CYCLE[13] TCC_EA_ATOMIC[13] TCC_EA_ATOMIC_LEVEL[13] TCC_ATOMIC[14] TCC_CYCLE[14] TCC_EA_ATOMIC[14] TCC_EA_ATOMIC_LEVEL[14] TCC_ATOMIC[15] TCC_CYCLE[15] TCC_EA_ATOMIC[15] TCC_EA_ATOMIC_LEVEL[15] TCC_ATOMIC[16] TCC_CYCLE[16] TCC_EA_ATOMIC[16] TCC_EA_ATOMIC_LEVEL[16] TCC_ATOMIC[17] TCC_CYCLE[17] TCC_EA_ATOMIC[17] TCC_EA_ATOMIC_LEVEL[17] TCC_ATOMIC[18] TCC_CYCLE[18] TCC_EA_ATOMIC[18] TCC_EA_ATOMIC_LEVEL[18] TCC_ATOMIC[19] TCC_CYCLE[19] TCC_EA_ATOMIC[19] TCC_EA_ATOMIC_LEVEL[19] TCC_ATOMIC[20] TCC_CYCLE[20] TCC_EA_ATOMIC[20] TCC_EA_ATOMIC_LEVEL[20] TCC_ATOMIC[21] TCC_CYCLE[21] TCC_EA_ATOMIC[21] TCC_EA_ATOMIC_LEVEL[21] TCC_ATOMIC[22] TCC_CYCLE[22] TCC_EA_ATOMIC[22] TCC_EA_ATOMIC_LEVEL[22] TCC_ATOMIC[23] TCC_CYCLE[23] TCC_EA_ATOMIC[23] TCC_EA_ATOMIC_LEVEL[23] TCC_ATOMIC[24] TCC_CYCLE[24] TCC_EA_ATOMIC[24] TCC_EA_ATOMIC_LEVEL[24] TCC_ATOMIC[25] TCC_CYCLE[25] TCC_EA_ATOMIC[25] TCC_EA_ATOMIC_LEVEL[25] TCC_ATOMIC[26] TCC_CYCLE[26] TCC_EA_ATOMIC[26] TCC_EA_ATOMIC_LEVEL[26] TCC_ATOMIC[27] TCC_CYCLE[27] TCC_EA_ATOMIC[27] TCC_EA_ATOMIC_LEVEL[27] TCC_ATOMIC[28] TCC_CYCLE[28] TCC_EA_ATOMIC[28] TCC_EA_ATOMIC_LEVEL[28] TCC_ATOMIC[29] TCC_CYCLE[29] TCC_EA_ATOMIC[29] TCC_EA_ATOMIC_LEVEL[29] TCC_ATOMIC[30] TCC_CYCLE[30] TCC_EA_ATOMIC[30] TCC_EA_ATOMIC_LEVEL[30] TCC_ATOMIC[31] TCC_CYCLE[31] TCC_EA_ATOMIC[31] TCC_EA_ATOMIC_LEVEL[31] + +gpu: +range: 0 +kernel: diff --git a/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_14.txt b/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_14.txt new file mode 100644 index 0000000000..2c16868c9a --- /dev/null +++ b/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_14.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_EA_RDREQ_GMI_CREDIT_STALL[0] TCC_EA_RDREQ[1] TCC_EA_RDREQ_32B[1] TCC_EA_RDREQ_DRAM_CREDIT_STALL[1] TCC_EA_RDREQ_GMI_CREDIT_STALL[1] TCC_EA_RDREQ[2] TCC_EA_RDREQ_32B[2] TCC_EA_RDREQ_DRAM_CREDIT_STALL[2] TCC_EA_RDREQ_GMI_CREDIT_STALL[2] TCC_EA_RDREQ[3] TCC_EA_RDREQ_32B[3] TCC_EA_RDREQ_DRAM_CREDIT_STALL[3] TCC_EA_RDREQ_GMI_CREDIT_STALL[3] TCC_EA_RDREQ[4] TCC_EA_RDREQ_32B[4] TCC_EA_RDREQ_DRAM_CREDIT_STALL[4] TCC_EA_RDREQ_GMI_CREDIT_STALL[4] TCC_EA_RDREQ[5] TCC_EA_RDREQ_32B[5] TCC_EA_RDREQ_DRAM_CREDIT_STALL[5] TCC_EA_RDREQ_GMI_CREDIT_STALL[5] TCC_EA_RDREQ[6] TCC_EA_RDREQ_32B[6] TCC_EA_RDREQ_DRAM_CREDIT_STALL[6] TCC_EA_RDREQ_GMI_CREDIT_STALL[6] TCC_EA_RDREQ[7] TCC_EA_RDREQ_32B[7] TCC_EA_RDREQ_DRAM_CREDIT_STALL[7] TCC_EA_RDREQ_GMI_CREDIT_STALL[7] TCC_EA_RDREQ[8] TCC_EA_RDREQ_32B[8] TCC_EA_RDREQ_DRAM_CREDIT_STALL[8] TCC_EA_RDREQ_GMI_CREDIT_STALL[8] TCC_EA_RDREQ[9] TCC_EA_RDREQ_32B[9] TCC_EA_RDREQ_DRAM_CREDIT_STALL[9] TCC_EA_RDREQ_GMI_CREDIT_STALL[9] TCC_EA_RDREQ[10] TCC_EA_RDREQ_32B[10] TCC_EA_RDREQ_DRAM_CREDIT_STALL[10] TCC_EA_RDREQ_GMI_CREDIT_STALL[10] TCC_EA_RDREQ[11] TCC_EA_RDREQ_32B[11] TCC_EA_RDREQ_DRAM_CREDIT_STALL[11] TCC_EA_RDREQ_GMI_CREDIT_STALL[11] TCC_EA_RDREQ[12] TCC_EA_RDREQ_32B[12] TCC_EA_RDREQ_DRAM_CREDIT_STALL[12] TCC_EA_RDREQ_GMI_CREDIT_STALL[12] TCC_EA_RDREQ[13] TCC_EA_RDREQ_32B[13] TCC_EA_RDREQ_DRAM_CREDIT_STALL[13] TCC_EA_RDREQ_GMI_CREDIT_STALL[13] TCC_EA_RDREQ[14] TCC_EA_RDREQ_32B[14] TCC_EA_RDREQ_DRAM_CREDIT_STALL[14] TCC_EA_RDREQ_GMI_CREDIT_STALL[14] TCC_EA_RDREQ[15] TCC_EA_RDREQ_32B[15] TCC_EA_RDREQ_DRAM_CREDIT_STALL[15] TCC_EA_RDREQ_GMI_CREDIT_STALL[15] TCC_EA_RDREQ[16] TCC_EA_RDREQ_32B[16] TCC_EA_RDREQ_DRAM_CREDIT_STALL[16] TCC_EA_RDREQ_GMI_CREDIT_STALL[16] TCC_EA_RDREQ[17] TCC_EA_RDREQ_32B[17] TCC_EA_RDREQ_DRAM_CREDIT_STALL[17] TCC_EA_RDREQ_GMI_CREDIT_STALL[17] TCC_EA_RDREQ[18] TCC_EA_RDREQ_32B[18] TCC_EA_RDREQ_DRAM_CREDIT_STALL[18] TCC_EA_RDREQ_GMI_CREDIT_STALL[18] TCC_EA_RDREQ[19] TCC_EA_RDREQ_32B[19] TCC_EA_RDREQ_DRAM_CREDIT_STALL[19] TCC_EA_RDREQ_GMI_CREDIT_STALL[19] TCC_EA_RDREQ[20] TCC_EA_RDREQ_32B[20] TCC_EA_RDREQ_DRAM_CREDIT_STALL[20] TCC_EA_RDREQ_GMI_CREDIT_STALL[20] TCC_EA_RDREQ[21] TCC_EA_RDREQ_32B[21] TCC_EA_RDREQ_DRAM_CREDIT_STALL[21] TCC_EA_RDREQ_GMI_CREDIT_STALL[21] TCC_EA_RDREQ[22] TCC_EA_RDREQ_32B[22] TCC_EA_RDREQ_DRAM_CREDIT_STALL[22] TCC_EA_RDREQ_GMI_CREDIT_STALL[22] TCC_EA_RDREQ[23] TCC_EA_RDREQ_32B[23] TCC_EA_RDREQ_DRAM_CREDIT_STALL[23] TCC_EA_RDREQ_GMI_CREDIT_STALL[23] TCC_EA_RDREQ[24] TCC_EA_RDREQ_32B[24] TCC_EA_RDREQ_DRAM_CREDIT_STALL[24] TCC_EA_RDREQ_GMI_CREDIT_STALL[24] TCC_EA_RDREQ[25] TCC_EA_RDREQ_32B[25] TCC_EA_RDREQ_DRAM_CREDIT_STALL[25] TCC_EA_RDREQ_GMI_CREDIT_STALL[25] TCC_EA_RDREQ[26] TCC_EA_RDREQ_32B[26] TCC_EA_RDREQ_DRAM_CREDIT_STALL[26] TCC_EA_RDREQ_GMI_CREDIT_STALL[26] TCC_EA_RDREQ[27] TCC_EA_RDREQ_32B[27] TCC_EA_RDREQ_DRAM_CREDIT_STALL[27] TCC_EA_RDREQ_GMI_CREDIT_STALL[27] TCC_EA_RDREQ[28] TCC_EA_RDREQ_32B[28] TCC_EA_RDREQ_DRAM_CREDIT_STALL[28] TCC_EA_RDREQ_GMI_CREDIT_STALL[28] TCC_EA_RDREQ[29] TCC_EA_RDREQ_32B[29] TCC_EA_RDREQ_DRAM_CREDIT_STALL[29] TCC_EA_RDREQ_GMI_CREDIT_STALL[29] TCC_EA_RDREQ[30] TCC_EA_RDREQ_32B[30] TCC_EA_RDREQ_DRAM_CREDIT_STALL[30] TCC_EA_RDREQ_GMI_CREDIT_STALL[30] TCC_EA_RDREQ[31] TCC_EA_RDREQ_32B[31] TCC_EA_RDREQ_DRAM_CREDIT_STALL[31] TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + +gpu: +range: 0 +kernel: diff --git a/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_15.txt b/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_15.txt new file mode 100644 index 0000000000..9456bc15f7 --- /dev/null +++ b/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_15.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ[0] TCC_EA_WRREQ_64B[0] TCC_EA_RDREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_LEVEL[1] TCC_EA_WRREQ[1] TCC_EA_WRREQ_64B[1] TCC_EA_RDREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_LEVEL[2] TCC_EA_WRREQ[2] TCC_EA_WRREQ_64B[2] TCC_EA_RDREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_LEVEL[3] TCC_EA_WRREQ[3] TCC_EA_WRREQ_64B[3] TCC_EA_RDREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_LEVEL[4] TCC_EA_WRREQ[4] TCC_EA_WRREQ_64B[4] TCC_EA_RDREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_LEVEL[5] TCC_EA_WRREQ[5] TCC_EA_WRREQ_64B[5] TCC_EA_RDREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_LEVEL[6] TCC_EA_WRREQ[6] TCC_EA_WRREQ_64B[6] TCC_EA_RDREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_LEVEL[7] TCC_EA_WRREQ[7] TCC_EA_WRREQ_64B[7] TCC_EA_RDREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_LEVEL[8] TCC_EA_WRREQ[8] TCC_EA_WRREQ_64B[8] TCC_EA_RDREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_LEVEL[9] TCC_EA_WRREQ[9] TCC_EA_WRREQ_64B[9] TCC_EA_RDREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_LEVEL[10] TCC_EA_WRREQ[10] TCC_EA_WRREQ_64B[10] TCC_EA_RDREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_LEVEL[11] TCC_EA_WRREQ[11] TCC_EA_WRREQ_64B[11] TCC_EA_RDREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_LEVEL[12] TCC_EA_WRREQ[12] TCC_EA_WRREQ_64B[12] TCC_EA_RDREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_LEVEL[13] TCC_EA_WRREQ[13] TCC_EA_WRREQ_64B[13] TCC_EA_RDREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_LEVEL[14] TCC_EA_WRREQ[14] TCC_EA_WRREQ_64B[14] TCC_EA_RDREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_LEVEL[15] TCC_EA_WRREQ[15] TCC_EA_WRREQ_64B[15] TCC_EA_RDREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_LEVEL[16] TCC_EA_WRREQ[16] TCC_EA_WRREQ_64B[16] TCC_EA_RDREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_LEVEL[17] TCC_EA_WRREQ[17] TCC_EA_WRREQ_64B[17] TCC_EA_RDREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_LEVEL[18] TCC_EA_WRREQ[18] TCC_EA_WRREQ_64B[18] TCC_EA_RDREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_LEVEL[19] TCC_EA_WRREQ[19] TCC_EA_WRREQ_64B[19] TCC_EA_RDREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_LEVEL[20] TCC_EA_WRREQ[20] TCC_EA_WRREQ_64B[20] TCC_EA_RDREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_LEVEL[21] TCC_EA_WRREQ[21] TCC_EA_WRREQ_64B[21] TCC_EA_RDREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_LEVEL[22] TCC_EA_WRREQ[22] TCC_EA_WRREQ_64B[22] TCC_EA_RDREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_LEVEL[23] TCC_EA_WRREQ[23] TCC_EA_WRREQ_64B[23] TCC_EA_RDREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_LEVEL[24] TCC_EA_WRREQ[24] TCC_EA_WRREQ_64B[24] TCC_EA_RDREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_LEVEL[25] TCC_EA_WRREQ[25] TCC_EA_WRREQ_64B[25] TCC_EA_RDREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_LEVEL[26] TCC_EA_WRREQ[26] TCC_EA_WRREQ_64B[26] TCC_EA_RDREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_LEVEL[27] TCC_EA_WRREQ[27] TCC_EA_WRREQ_64B[27] TCC_EA_RDREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_LEVEL[28] TCC_EA_WRREQ[28] TCC_EA_WRREQ_64B[28] TCC_EA_RDREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_LEVEL[29] TCC_EA_WRREQ[29] TCC_EA_WRREQ_64B[29] TCC_EA_RDREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_LEVEL[30] TCC_EA_WRREQ[30] TCC_EA_WRREQ_64B[30] TCC_EA_RDREQ_IO_CREDIT_STALL[31] TCC_EA_RDREQ_LEVEL[31] TCC_EA_WRREQ[31] TCC_EA_WRREQ_64B[31] + +gpu: +range: 0 +kernel: diff --git a/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_16.txt b/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_16.txt new file mode 100644 index 0000000000..e87dcd91ab --- /dev/null +++ b/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_16.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_WRREQ_IO_CREDIT_STALL[0] TCC_EA_WRREQ_LEVEL[0] TCC_EA_WRREQ_DRAM_CREDIT_STALL[1] TCC_EA_WRREQ_GMI_CREDIT_STALL[1] TCC_EA_WRREQ_IO_CREDIT_STALL[1] TCC_EA_WRREQ_LEVEL[1] TCC_EA_WRREQ_DRAM_CREDIT_STALL[2] TCC_EA_WRREQ_GMI_CREDIT_STALL[2] TCC_EA_WRREQ_IO_CREDIT_STALL[2] TCC_EA_WRREQ_LEVEL[2] TCC_EA_WRREQ_DRAM_CREDIT_STALL[3] TCC_EA_WRREQ_GMI_CREDIT_STALL[3] TCC_EA_WRREQ_IO_CREDIT_STALL[3] TCC_EA_WRREQ_LEVEL[3] TCC_EA_WRREQ_DRAM_CREDIT_STALL[4] TCC_EA_WRREQ_GMI_CREDIT_STALL[4] TCC_EA_WRREQ_IO_CREDIT_STALL[4] TCC_EA_WRREQ_LEVEL[4] TCC_EA_WRREQ_DRAM_CREDIT_STALL[5] TCC_EA_WRREQ_GMI_CREDIT_STALL[5] TCC_EA_WRREQ_IO_CREDIT_STALL[5] TCC_EA_WRREQ_LEVEL[5] TCC_EA_WRREQ_DRAM_CREDIT_STALL[6] TCC_EA_WRREQ_GMI_CREDIT_STALL[6] TCC_EA_WRREQ_IO_CREDIT_STALL[6] TCC_EA_WRREQ_LEVEL[6] TCC_EA_WRREQ_DRAM_CREDIT_STALL[7] TCC_EA_WRREQ_GMI_CREDIT_STALL[7] TCC_EA_WRREQ_IO_CREDIT_STALL[7] TCC_EA_WRREQ_LEVEL[7] TCC_EA_WRREQ_DRAM_CREDIT_STALL[8] TCC_EA_WRREQ_GMI_CREDIT_STALL[8] TCC_EA_WRREQ_IO_CREDIT_STALL[8] TCC_EA_WRREQ_LEVEL[8] TCC_EA_WRREQ_DRAM_CREDIT_STALL[9] TCC_EA_WRREQ_GMI_CREDIT_STALL[9] TCC_EA_WRREQ_IO_CREDIT_STALL[9] TCC_EA_WRREQ_LEVEL[9] TCC_EA_WRREQ_DRAM_CREDIT_STALL[10] TCC_EA_WRREQ_GMI_CREDIT_STALL[10] TCC_EA_WRREQ_IO_CREDIT_STALL[10] TCC_EA_WRREQ_LEVEL[10] TCC_EA_WRREQ_DRAM_CREDIT_STALL[11] TCC_EA_WRREQ_GMI_CREDIT_STALL[11] TCC_EA_WRREQ_IO_CREDIT_STALL[11] TCC_EA_WRREQ_LEVEL[11] TCC_EA_WRREQ_DRAM_CREDIT_STALL[12] TCC_EA_WRREQ_GMI_CREDIT_STALL[12] TCC_EA_WRREQ_IO_CREDIT_STALL[12] TCC_EA_WRREQ_LEVEL[12] TCC_EA_WRREQ_DRAM_CREDIT_STALL[13] TCC_EA_WRREQ_GMI_CREDIT_STALL[13] TCC_EA_WRREQ_IO_CREDIT_STALL[13] TCC_EA_WRREQ_LEVEL[13] TCC_EA_WRREQ_DRAM_CREDIT_STALL[14] TCC_EA_WRREQ_GMI_CREDIT_STALL[14] TCC_EA_WRREQ_IO_CREDIT_STALL[14] TCC_EA_WRREQ_LEVEL[14] TCC_EA_WRREQ_DRAM_CREDIT_STALL[15] TCC_EA_WRREQ_GMI_CREDIT_STALL[15] TCC_EA_WRREQ_IO_CREDIT_STALL[15] TCC_EA_WRREQ_LEVEL[15] TCC_EA_WRREQ_DRAM_CREDIT_STALL[16] TCC_EA_WRREQ_GMI_CREDIT_STALL[16] TCC_EA_WRREQ_IO_CREDIT_STALL[16] TCC_EA_WRREQ_LEVEL[16] TCC_EA_WRREQ_DRAM_CREDIT_STALL[17] TCC_EA_WRREQ_GMI_CREDIT_STALL[17] TCC_EA_WRREQ_IO_CREDIT_STALL[17] TCC_EA_WRREQ_LEVEL[17] TCC_EA_WRREQ_DRAM_CREDIT_STALL[18] TCC_EA_WRREQ_GMI_CREDIT_STALL[18] TCC_EA_WRREQ_IO_CREDIT_STALL[18] TCC_EA_WRREQ_LEVEL[18] TCC_EA_WRREQ_DRAM_CREDIT_STALL[19] TCC_EA_WRREQ_GMI_CREDIT_STALL[19] TCC_EA_WRREQ_IO_CREDIT_STALL[19] TCC_EA_WRREQ_LEVEL[19] TCC_EA_WRREQ_DRAM_CREDIT_STALL[20] TCC_EA_WRREQ_GMI_CREDIT_STALL[20] TCC_EA_WRREQ_IO_CREDIT_STALL[20] TCC_EA_WRREQ_LEVEL[20] TCC_EA_WRREQ_DRAM_CREDIT_STALL[21] TCC_EA_WRREQ_GMI_CREDIT_STALL[21] TCC_EA_WRREQ_IO_CREDIT_STALL[21] TCC_EA_WRREQ_LEVEL[21] TCC_EA_WRREQ_DRAM_CREDIT_STALL[22] TCC_EA_WRREQ_GMI_CREDIT_STALL[22] TCC_EA_WRREQ_IO_CREDIT_STALL[22] TCC_EA_WRREQ_LEVEL[22] TCC_EA_WRREQ_DRAM_CREDIT_STALL[23] TCC_EA_WRREQ_GMI_CREDIT_STALL[23] TCC_EA_WRREQ_IO_CREDIT_STALL[23] TCC_EA_WRREQ_LEVEL[23] TCC_EA_WRREQ_DRAM_CREDIT_STALL[24] TCC_EA_WRREQ_GMI_CREDIT_STALL[24] TCC_EA_WRREQ_IO_CREDIT_STALL[24] TCC_EA_WRREQ_LEVEL[24] TCC_EA_WRREQ_DRAM_CREDIT_STALL[25] TCC_EA_WRREQ_GMI_CREDIT_STALL[25] TCC_EA_WRREQ_IO_CREDIT_STALL[25] TCC_EA_WRREQ_LEVEL[25] TCC_EA_WRREQ_DRAM_CREDIT_STALL[26] TCC_EA_WRREQ_GMI_CREDIT_STALL[26] TCC_EA_WRREQ_IO_CREDIT_STALL[26] TCC_EA_WRREQ_LEVEL[26] TCC_EA_WRREQ_DRAM_CREDIT_STALL[27] TCC_EA_WRREQ_GMI_CREDIT_STALL[27] TCC_EA_WRREQ_IO_CREDIT_STALL[27] TCC_EA_WRREQ_LEVEL[27] TCC_EA_WRREQ_DRAM_CREDIT_STALL[28] TCC_EA_WRREQ_GMI_CREDIT_STALL[28] TCC_EA_WRREQ_IO_CREDIT_STALL[28] TCC_EA_WRREQ_LEVEL[28] TCC_EA_WRREQ_DRAM_CREDIT_STALL[29] TCC_EA_WRREQ_GMI_CREDIT_STALL[29] TCC_EA_WRREQ_IO_CREDIT_STALL[29] TCC_EA_WRREQ_LEVEL[29] TCC_EA_WRREQ_DRAM_CREDIT_STALL[30] TCC_EA_WRREQ_GMI_CREDIT_STALL[30] TCC_EA_WRREQ_IO_CREDIT_STALL[30] TCC_EA_WRREQ_LEVEL[30] TCC_EA_WRREQ_DRAM_CREDIT_STALL[31] TCC_EA_WRREQ_GMI_CREDIT_STALL[31] TCC_EA_WRREQ_IO_CREDIT_STALL[31] TCC_EA_WRREQ_LEVEL[31] + +gpu: +range: 0 +kernel: diff --git a/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_17.txt b/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_17.txt new file mode 100644 index 0000000000..ca34b877cc --- /dev/null +++ b/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_17.txt @@ -0,0 +1,5 @@ +pmc: TCC_HIT[0] TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_HIT[1] TCC_MISS[1] TCC_READ[1] TCC_REQ[1] TCC_HIT[2] TCC_MISS[2] TCC_READ[2] TCC_REQ[2] TCC_HIT[3] TCC_MISS[3] TCC_READ[3] TCC_REQ[3] TCC_HIT[4] TCC_MISS[4] TCC_READ[4] TCC_REQ[4] TCC_HIT[5] TCC_MISS[5] TCC_READ[5] TCC_REQ[5] TCC_HIT[6] TCC_MISS[6] TCC_READ[6] TCC_REQ[6] TCC_HIT[7] TCC_MISS[7] TCC_READ[7] TCC_REQ[7] TCC_HIT[8] TCC_MISS[8] TCC_READ[8] TCC_REQ[8] TCC_HIT[9] TCC_MISS[9] TCC_READ[9] TCC_REQ[9] TCC_HIT[10] TCC_MISS[10] TCC_READ[10] TCC_REQ[10] TCC_HIT[11] TCC_MISS[11] TCC_READ[11] TCC_REQ[11] TCC_HIT[12] TCC_MISS[12] TCC_READ[12] TCC_REQ[12] TCC_HIT[13] TCC_MISS[13] TCC_READ[13] TCC_REQ[13] TCC_HIT[14] TCC_MISS[14] TCC_READ[14] TCC_REQ[14] TCC_HIT[15] TCC_MISS[15] TCC_READ[15] TCC_REQ[15] TCC_HIT[16] TCC_MISS[16] TCC_READ[16] TCC_REQ[16] TCC_HIT[17] TCC_MISS[17] TCC_READ[17] TCC_REQ[17] TCC_HIT[18] TCC_MISS[18] TCC_READ[18] TCC_REQ[18] TCC_HIT[19] TCC_MISS[19] TCC_READ[19] TCC_REQ[19] TCC_HIT[20] TCC_MISS[20] TCC_READ[20] TCC_REQ[20] TCC_HIT[21] TCC_MISS[21] TCC_READ[21] TCC_REQ[21] TCC_HIT[22] TCC_MISS[22] TCC_READ[22] TCC_REQ[22] TCC_HIT[23] TCC_MISS[23] TCC_READ[23] TCC_REQ[23] TCC_HIT[24] TCC_MISS[24] TCC_READ[24] TCC_REQ[24] TCC_HIT[25] TCC_MISS[25] TCC_READ[25] TCC_REQ[25] TCC_HIT[26] TCC_MISS[26] TCC_READ[26] TCC_REQ[26] TCC_HIT[27] TCC_MISS[27] TCC_READ[27] TCC_REQ[27] TCC_HIT[28] TCC_MISS[28] TCC_READ[28] TCC_REQ[28] TCC_HIT[29] TCC_MISS[29] TCC_READ[29] TCC_REQ[29] TCC_HIT[30] TCC_MISS[30] TCC_READ[30] TCC_REQ[30] TCC_HIT[31] TCC_MISS[31] TCC_READ[31] TCC_REQ[31] + +gpu: +range: 0 +kernel: diff --git a/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_18.txt b/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_18.txt new file mode 100644 index 0000000000..67ea85d563 --- /dev/null +++ b/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_18.txt @@ -0,0 +1,5 @@ +pmc: TCC_RW_REQ[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_RW_REQ[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_WRITE[1] TCC_RW_REQ[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_WRITE[2] TCC_RW_REQ[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_WRITE[3] TCC_RW_REQ[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_WRITE[4] TCC_RW_REQ[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_WRITE[5] TCC_RW_REQ[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_WRITE[6] TCC_RW_REQ[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_WRITE[7] TCC_RW_REQ[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_WRITE[8] TCC_RW_REQ[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_WRITE[9] TCC_RW_REQ[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_WRITE[10] TCC_RW_REQ[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_WRITE[11] TCC_RW_REQ[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_WRITE[12] TCC_RW_REQ[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_WRITE[13] TCC_RW_REQ[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_WRITE[14] TCC_RW_REQ[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_WRITE[15] TCC_RW_REQ[16] TCC_TOO_MANY_EA_WRREQS_STALL[16] TCC_WRITE[16] TCC_RW_REQ[17] TCC_TOO_MANY_EA_WRREQS_STALL[17] TCC_WRITE[17] TCC_RW_REQ[18] TCC_TOO_MANY_EA_WRREQS_STALL[18] TCC_WRITE[18] TCC_RW_REQ[19] TCC_TOO_MANY_EA_WRREQS_STALL[19] TCC_WRITE[19] TCC_RW_REQ[20] TCC_TOO_MANY_EA_WRREQS_STALL[20] TCC_WRITE[20] TCC_RW_REQ[21] TCC_TOO_MANY_EA_WRREQS_STALL[21] TCC_WRITE[21] TCC_RW_REQ[22] TCC_TOO_MANY_EA_WRREQS_STALL[22] TCC_WRITE[22] TCC_RW_REQ[23] TCC_TOO_MANY_EA_WRREQS_STALL[23] TCC_WRITE[23] TCC_RW_REQ[24] TCC_TOO_MANY_EA_WRREQS_STALL[24] TCC_WRITE[24] TCC_RW_REQ[25] TCC_TOO_MANY_EA_WRREQS_STALL[25] TCC_WRITE[25] TCC_RW_REQ[26] TCC_TOO_MANY_EA_WRREQS_STALL[26] TCC_WRITE[26] TCC_RW_REQ[27] TCC_TOO_MANY_EA_WRREQS_STALL[27] TCC_WRITE[27] TCC_RW_REQ[28] TCC_TOO_MANY_EA_WRREQS_STALL[28] TCC_WRITE[28] TCC_RW_REQ[29] TCC_TOO_MANY_EA_WRREQS_STALL[29] TCC_WRITE[29] TCC_RW_REQ[30] TCC_TOO_MANY_EA_WRREQS_STALL[30] TCC_WRITE[30] TCC_RW_REQ[31] TCC_TOO_MANY_EA_WRREQS_STALL[31] TCC_WRITE[31] + +gpu: +range: 0 +kernel: diff --git a/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_2.txt b/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_2.txt new file mode 100644 index 0000000000..d204fe101c --- /dev/null +++ b/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_2.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_MUL_F32 SQ_INSTS_VALU_FMA_F32 SQ_INSTS_VALU_TRANS_F32 SQ_INSTS_VALU_ADD_F64 SQ_INSTS_VALU_MUL_F64 SQ_INSTS_VALU_FMA_F64 SQ_INSTS_VALU_TRANS_F64 SQ_INSTS_VALU_INT32 TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum TA_BUFFER_ATOMIC_WAVEFRONTS_sum TA_BUFFER_TOTAL_CYCLES_sum TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum + +gpu: +range: 0 +kernel: diff --git a/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_3.txt b/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_3.txt new file mode 100644 index 0000000000..8820faa7c5 --- /dev/null +++ b/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_3.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_INT64 SQ_INSTS_SMEM SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum TD_COALESCABLE_WAVEFRONT_sum SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE CPF_CMP_UTCL1_STALL_ON_TRANSLATION TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum + +gpu: +range: 0 +kernel: diff --git a/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_4.txt b/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_4.txt new file mode 100644 index 0000000000..07006fde4c --- /dev/null +++ b/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_4.txt @@ -0,0 +1,5 @@ +pmc: SQ_WAVE_CYCLES SQ_WAIT_ANY SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_BUSY_CU_CYCLES SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE TCC_EA_WRREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WR_UNCACHED_32B_sum TCC_EA_WRREQ_DRAM_sum + +gpu: +range: 0 +kernel: diff --git a/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_5.txt b/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_5.txt new file mode 100644 index 0000000000..7a3ae18a02 --- /dev/null +++ b/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_5.txt @@ -0,0 +1,5 @@ +pmc: SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU TCP_TCP_LATENCY_sum TCP_TCC_READ_REQ_LATENCY_sum TCP_TCC_WRITE_REQ_LATENCY_sum TCP_TCC_READ_REQ_sum TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN CPC_ME1_DC0_SPI_BUSY TCC_EA_WRREQ_STALL_sum TCC_EA_RDREQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RD_UNCACHED_32B_sum + +gpu: +range: 0 +kernel: diff --git a/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_6.txt b/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_6.txt new file mode 100644 index 0000000000..3f982dc008 --- /dev/null +++ b/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_6.txt @@ -0,0 +1,5 @@ +pmc: SQ_THREAD_CYCLES_VALU SQ_IFETCH SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TCP_TCC_NC_READ_REQ_sum TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN TCC_EA_RDREQ_DRAM_sum TCC_TAG_STALL_sum TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum + +gpu: +range: 0 +kernel: diff --git a/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_7.txt b/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_7.txt new file mode 100644 index 0000000000..94073a0a3c --- /dev/null +++ b/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_7.txt @@ -0,0 +1,5 @@ +pmc: SQ_WAVES_LT_32 SQ_WAVES_LT_16 SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TCP_TCC_UC_WRITE_REQ_sum TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR TCC_NORMAL_EVICT_sum TCC_ALL_TC_OP_INV_EVICT_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA_ATOMIC_sum + +gpu: +range: 0 +kernel: diff --git a/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_8.txt b/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_8.txt new file mode 100644 index 0000000000..0b3b79f046 --- /dev/null +++ b/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_8.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM_NORM SQ_INSTS_MFMA SQ_INSTS_VALU_MFMA_I8 SQ_INSTS_VALU_MFMA_F16 SQ_INSTS_VALU_MFMA_BF16 SQ_INSTS_VALU_MFMA_F32 SQ_INSTS_VALU_MFMA_F64 SQ_VALU_MFMA_BUSY_CYCLES TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TCP_TCC_CC_ATOMIC_REQ_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN TCC_EA_RDREQ_LEVEL_sum TCC_EA_WRREQ_LEVEL_sum TCC_EA_ATOMIC_LEVEL_sum + +gpu: +range: 0 +kernel: diff --git a/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_9.txt b/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_9.txt new file mode 100644 index 0000000000..57fbbff186 --- /dev/null +++ b/tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_9.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_FLAT_LDS_ONLY SQ_INSTS_VALU_MFMA_MOPS_I8 SQ_INSTS_VALU_MFMA_MOPS_F16 SQ_INSTS_VALU_MFMA_MOPS_BF16 SQ_INSTS_VALU_MFMA_MOPS_F32 SQ_INSTS_VALU_MFMA_MOPS_F64 SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum TCP_PENDING_STALL_CYCLES_sum + +gpu: +range: 0 +kernel: diff --git a/tests/workloads/dispatch_0/MI200/perfmon/timestamps.txt b/tests/workloads/dispatch_0/MI200/perfmon/timestamps.txt new file mode 100644 index 0000000000..24911467fe --- /dev/null +++ b/tests/workloads/dispatch_0/MI200/perfmon/timestamps.txt @@ -0,0 +1,5 @@ +pmc: + +gpu: +range: 0 +kernel: diff --git a/tests/workloads/dispatch_0/MI200/pmc_perf.csv b/tests/workloads/dispatch_0/MI200/pmc_perf.csv new file mode 100644 index 0000000000..961b0ab948 --- /dev/null +++ b/tests/workloads/dispatch_0/MI200/pmc_perf.csv @@ -0,0 +1,2 @@ +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,TCC_EA_ATOMIC_LEVEL_sum,wave_size_1,obj_1,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_2,obj_2,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_3,obj_3,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,TD_COALESCABLE_WAVEFRONT_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_4,obj_4,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_5,obj_5,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_6,obj_6,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_7,obj_7,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_8,obj_8,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_9,obj_9,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_10,obj_10,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_11,obj_11,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_DRAM_sum,TCC_TAG_STALL_sum,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,wave_size_12,obj_12,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_13,obj_13,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,wave_size_14,obj_14,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_15,obj_15,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_16,obj_16,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_17,obj_17,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_18,obj_18,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f93cfdd4ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,43336787.0,35077708.0,0.0,64,0x7f851a7d8ec0,6368,0,4096,6395,0,4096,6376,0,4096,6370,0,4096,6377,0,4096,6414,0,4096,6318,0,4096,6373,0,4096,6372,0,4096,6369,0,4096,6399,0,4096,6369,0,4096,6371,0,4096,6379,0,4096,6419,0,4096,6322,0,4096,6400,0,4096,6361,0,4096,6378,0,4096,6400,0,4096,6363,0,4096,6407,0,4096,6380,0,4096,6571,0,4096,6405,0,4096,6408,0,4096,6362,0,4096,6379,0,4096,6397,0,4096,6363,0,4096,6411,0,4096,6380,0,4096,64,0x7f30ca774ec0,2278,4096,2278,6374,2298,4096,2298,6394,2251,4096,2251,6347,2335,4096,2335,6431,2283,4096,2283,6379,2300,4096,2300,6396,2254,4096,2254,6350,2312,4096,2312,6408,2368,4097,2369,6465,2279,4096,2279,6375,2300,4096,2300,6396,2254,4096,2254,6350,2337,4096,2337,6433,2285,4096,2285,6381,2306,4096,2306,6402,2254,4096,2254,6350,2291,4096,2291,6387,2252,4096,2252,6348,2300,4097,2301,6397,2289,4096,2289,6385,2276,4096,2276,6372,2276,4096,2276,6372,2303,4096,2303,6399,2487,4099,2490,6586,2325,4096,2325,6421,2298,4096,2298,6394,2255,4096,2255,6351,2303,4096,2303,6399,2292,4096,2292,6388,2275,4096,2275,6371,2279,4096,2279,6375,2308,4098,2310,6406,64,0x7f1fd64d0ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,10545,0,817,28162,0,73375.0,131072.0,0.0,65568.0,64,0x7f6eae674ec0,1289,124666,0,0,65536,63800,56,1680,64,0x7ffbeae70ec0,0,0,0,0,0,0,168,56,131072.0,131072.0,0.0,943442.0,64,0x7f742fbbcec0,32768,32768,0,64,0x7fca046d4ec0,0,0,0,1026393,0,0,0,1204489,0,0,0,1050426,0,0,0,1202217,0,0,0,1153510,134,0,0,1242105,0,0,0,1084146,0,0,0,1175538,0,0,0,1125487,0,0,0,1052972,0,0,0,1044219,26,0,0,1160051,0,0,0,1118212,1,0,0,1094801,620,0,0,1347439,0,0,0,1172086,0,0,0,1114829,0,0,0,1071247,0,0,0,1102993,0,0,0,1209273,0,0,0,1120733,0,0,0,1088024,25,0,0,1138228,0,0,0,1072997,0,0,0,1018992,0,0,0,1122267,0,0,0,1102180,0,0,0,1155008,0,0,0,1095474,0,0,0,1048708,0,0,0,1136110,0,0,0,1133187,64,0x7fae6c0c0ec0,0,1062044,4096,4096,0,1407413,4096,4096,0,1209912,4096,4096,0,1354247,4096,4096,0,1300941,4096,4096,0,1380593,4096,4096,0,1183905,4096,4096,0,1504136,4096,4096,0,1202625,4096,4096,0,981032,4096,4096,0,1186111,4096,4096,0,1305893,4096,4096,0,1205538,4096,4096,0,1240714,4096,4096,0,1135766,4096,4096,0,1154158,4096,4096,0,1472010,4096,4096,0,1271905,4096,4096,0,1299419,4096,4096,0,1268868,4096,4096,0,1184696,4096,4096,0,1250092,4096,4096,0,1338418,4096,4096,0,1111864,4096,4096,0,1364313,4096,4096,0,1186114,4096,4096,0,1577678,4096,4096,0,1287611,4096,4096,0,1225532,4096,4096,0,1076946,4096,4096,0,1010342,4096,4096,0,1542983,4096,4096,64,0x7f7bb8440ec0,4096,0,0,0,4096,0,372,0,4099,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,439,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4097,0,0,0,4099,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,64,0x7f88d8c48ec0,0,393216,163840,0,0,0,0,0,18192,0.0,0.0,0.0,32768.0,0.0,0.0,418.0,32768.0,4096,16384,352,28238,1933,0,56.0,7.0,0.0,204299.0,64,0x7fb940cecec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131084.0,34210.0,46115.0,19421.0,64,0x7f7efb9c8ec0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,64,0x7f8939398ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65551.0,0.0,0.0,0.0,64,0x7f02c9d00ec0,237056,132824,16384,0,16384,16384,32768,49152,29631,29631,2004384.0,1430992.0,3646.0,211725.0,1132729.0,0.0,1423412.0,1125171.0,235345,140962,29631,0,29631,0,948192.0,500665.0,0.0,0.0,64,0x7ff55a6b4ec0,0,0,0,224,0,65536,63760,56,64,0x7f00e95a8ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13240,19683,8487,549,0,27107,204650.0,0.0,73567.0,131083.0,64,0x7f4b21dd0ec0,11035356,9890398,800894,344064,1665326,0,0,163840,832.0,515136.0,0.0,524288.0,275956.0,32768.0,529651,0,0,10877,131072.0,131072.0,0.0,131072.0,64,0x7f258fa24ec0,114688,0,32768,32768,16384,16384,65536,49152,29054970.0,90445211.0,39684969.0,131072.0,0.0,248878.0,0,0,15521,1027.0,131082.0,0.0,12.0,198500539781025,198500539801025 diff --git a/tests/workloads/dispatch_0/MI200/roofline.csv b/tests/workloads/dispatch_0/MI200/roofline.csv new file mode 100644 index 0000000000..1737f5f365 --- /dev/null +++ b/tests/workloads/dispatch_0/MI200/roofline.csv @@ -0,0 +1,5 @@ +device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh +0,1388.2593,1387.6742,1388.8444,5015.6343,5012.4912,5018.7773,9223.3535,9222.6689,9224.0381,18050.238,18049.146,18051.33,20933.475,20873.053,20993.896,20262.736,20262.088,20263.385,170396.28,170393.2,170399.36,164844.48,164840.03,164848.94,41410.918,41410.391,41411.445,41466.852,41465.879,41467.824,166299.94,165807.45,166792.42 +1,1389.0791,1388.4865,1389.6718,5026.2217,5024.4121,5028.0312,9233.2822,9232.6641,9233.9004,18090.092,18086.539,18093.645,20971.795,20904.992,21038.598,20290.67,20290.035,20291.305,170824.69,170820.02,170829.36,165107.66,165105.09,165110.22,41487.414,41486.652,41488.176,41542.918,41542,41543.836,166879.25,166876.3,166882.2 +2,1388.9591,1388.4004,1389.5178,5035.1958,5033.0864,5037.3052,9261.5215,9260.8203,9262.2227,18107.543,18106.791,18108.295,21047.707,21047.246,21048.168,20351.348,20350.775,20351.92,171110.19,171106.17,171114.2,165507.5,165502.62,165512.38,41583.355,41582.031,41584.68,41637.441,41636.102,41638.781,166941.58,166351.8,167531.36 +3,1389.1071,1388.4954,1389.7188,5030.6714,5029.2788,5032.064,9241.2998,9240.582,9242.0176,18023.967,18020.326,18027.607,21036.178,21035.668,21036.688,20311.578,20310.953,20312.203,171023.28,171018.56,171028,165224.14,165220.2,165228.08,41439.121,41285.898,41592.344,41578.496,41577.977,41579.016,166999.5,166997.89,167001.11 diff --git a/tests/workloads/dispatch_0/MI200/sysinfo.csv b/tests/workloads/dispatch_0/MI200/sysinfo.csv new file mode 100644 index 0000000000..0bead8f0b0 --- /dev/null +++ b/tests/workloads/dispatch_0/MI200/sysinfo.csv @@ -0,0 +1,2 @@ +workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd +dispatch_0,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 02:19:14 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/dispatch_0/MI200/timestamps.csv b/tests/workloads/dispatch_0/MI200/timestamps.csv new file mode 100644 index 0000000000..e1869601c3 --- /dev/null +++ b/tests/workloads/dispatch_0/MI200/timestamps.csv @@ -0,0 +1,2 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,310582,310582,1048576,256,0,0,8,0,16,64,0x0,0x7f0fb9e1cec0,198500539756684,198500539781025,198500539801025,198500539812330 diff --git a/tests/workloads/dispatch_0_1/MI100/SQ_IFETCH_LEVEL.csv b/tests/workloads/dispatch_0_1/MI100/SQ_IFETCH_LEVEL.csv index 6bbefac1f1..41b9a35a9c 100644 --- a/tests/workloads/dispatch_0_1/MI100/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/dispatch_0_1/MI100/SQ_IFETCH_LEVEL.csv @@ -1,3 +1,3 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2854821,2854821,1048576,256,0,0,8,8,16,64,0x0,0x7fd201bc8e80,48587,48587,16384,65536,13335,1699196,2187825353651312,2187817997797403,2187817997821723,2187825361131083 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2854821,2854821,1048576,256,0,0,8,8,16,64,0x0,0x7fd201bc8e80,43788,43788,16384,65536,8358,1048576,2187825361154758,2187817997919963,2187817997938843,2187825361465401 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,155261,155261,1048576,256,0,0,8,8,16,64,0x0,0x7fdace5aee80,48843,48843,16384,65536,14557,1859980,194220648419385,194232901432521,194232901456681,194220656370350 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,155261,155261,1048576,256,0,0,8,8,16,64,0x0,0x7fdace5aee80,42042,42042,16384,65536,8064,1048588,194220656392682,194232901551561,194232901570601,194220656709111 diff --git a/tests/workloads/dispatch_0_1/MI100/SQ_INST_LEVEL_LDS.csv b/tests/workloads/dispatch_0_1/MI100/SQ_INST_LEVEL_LDS.csv index e70c97b263..f0dd1bf8e3 100644 --- a/tests/workloads/dispatch_0_1/MI100/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/dispatch_0_1/MI100/SQ_INST_LEVEL_LDS.csv @@ -1,3 +1,3 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2852254,2852254,1048576,256,0,0,8,8,16,64,0x0,0x7fdce63b0e80,0,0,0,2187818435420620,2187817997797403,2187817997821723,2187818443006390 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2852254,2852254,1048576,256,0,0,8,8,16,64,0x0,0x7fdce63b0e80,0,0,0,2187818443027440,2187817997919963,2187817997938843,2187818443325199 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,155449,155449,1048576,256,0,0,8,8,16,64,0x0,0x7f0144e1ee80,0,0,0,194221143127145,194232901432521,194232901456681,194221150750408 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,155449,155449,1048576,256,0,0,8,8,16,64,0x0,0x7f0144e1ee80,0,0,0,194221150769896,194232901551561,194232901570601,194221151079862 diff --git a/tests/workloads/dispatch_0_1/MI100/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/dispatch_0_1/MI100/SQ_INST_LEVEL_SMEM.csv index bb50c7bdfc..264df07706 100644 --- a/tests/workloads/dispatch_0_1/MI100/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/dispatch_0_1/MI100/SQ_INST_LEVEL_SMEM.csv @@ -1,3 +1,3 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2853357,2853357,1048576,256,0,0,8,8,16,64,0x0,0x7fece8768e80,65536,177888,22849344,2187821117349071,2187817997797403,2187817997821723,2187821124970508 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2853357,2853357,1048576,256,0,0,8,8,16,64,0x0,0x7fece8768e80,65536,167696,21526976,2187821124989614,2187817997919963,2187817997938843,2187821125313562 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,155638,155638,1048576,256,0,0,8,8,16,64,0x0,0x7fd3082b2e80,65536,220822,28203128,194221637472508,194232901432521,194232901456681,194221645453088 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,155638,155638,1048576,256,0,0,8,8,16,64,0x0,0x7fd3082b2e80,65536,199286,25574192,194221645471273,194232901551561,194232901570601,194221645910755 diff --git a/tests/workloads/dispatch_0_1/MI100/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/dispatch_0_1/MI100/SQ_INST_LEVEL_VMEM.csv index 366ab07684..7518891d3e 100644 --- a/tests/workloads/dispatch_0_1/MI100/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/dispatch_0_1/MI100/SQ_INST_LEVEL_VMEM.csv @@ -1,3 +1,3 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2852991,2852991,1048576,256,0,0,8,8,16,64,0x0,0x7f100dc28e80,32768,657746,84179812,2187820219055599,2187817997797403,2187817997821723,2187820226818161 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2852991,2852991,1048576,256,0,0,8,8,16,64,0x0,0x7f100dc28e80,32768,678033,86771904,2187820226837949,2187817997919963,2187817997938843,2187820227160915 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,155824,155824,1048576,256,0,0,8,8,16,64,0x0,0x7ff8d92c4e80,32768,651728,83429440,194222135704660,194232901432521,194232901456681,194222143498788 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,155824,155824,1048576,256,0,0,8,8,16,64,0x0,0x7ff8d92c4e80,32768,664228,85004888,194222143519427,194232901551561,194232901570601,194222143811741 diff --git a/tests/workloads/dispatch_0_1/MI100/SQ_LEVEL_WAVES.csv b/tests/workloads/dispatch_0_1/MI100/SQ_LEVEL_WAVES.csv index aa6a3b1643..3059357307 100644 --- a/tests/workloads/dispatch_0_1/MI100/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/dispatch_0_1/MI100/SQ_LEVEL_WAVES.csv @@ -1,3 +1,3 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2851521,2851521,1048576,256,0,0,8,8,16,64,0x0,0x7fa106240e80,47947,47947,16547,383584,16384,24538596,231412,0,98657844,2187816647872285,2187817997797403,2187817997821723,2187816655447195 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2851521,2851521,1048576,256,0,0,8,8,16,64,0x0,0x7fa106240e80,42133,42133,13660,337072,16384,24431973,228800,0,98212048,2187816655475638,2187817997919963,2187817997938843,2187816655805868 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,156011,156011,1048576,256,0,0,8,8,16,64,0x0,0x7f6b448cee80,48616,48616,17826,388936,16384,25474846,236631,0,102389564,194222631809706,194232901432521,194232901456681,194222639570670 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,156011,156011,1048576,256,0,0,8,8,16,64,0x0,0x7f6b448cee80,42631,42631,13289,341056,16384,25728907,236499,0,103400652,194222639598924,194232901551561,194232901570601,194222639909191 diff --git a/tests/workloads/dispatch_0_1/MI100/pmc_dispatch_info.csv b/tests/workloads/dispatch_0_1/MI100/pmc_dispatch_info.csv new file mode 100644 index 0000000000..aef03adc37 --- /dev/null +++ b/tests/workloads/dispatch_0_1/MI100/pmc_dispatch_info.csv @@ -0,0 +1,3 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) ",2 +1,"vecCopy(double*, double*, double*, int, int) ",2 diff --git a/tests/workloads/dispatch_0_1/MI100/pmc_perf.csv b/tests/workloads/dispatch_0_1/MI100/pmc_perf.csv index ee639aa449..0b11068099 100644 --- a/tests/workloads/dispatch_0_1/MI100/pmc_perf.csv +++ b/tests/workloads/dispatch_0_1/MI100/pmc_perf.csv @@ -1,3 +1,3 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_1,obj_1,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_2,obj_2,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_3,obj_3,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_4,obj_4,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_5,obj_5,TCC_EA_ATOMIC_LEVEL_sum,wave_size_6,obj_6,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_7,obj_7,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_8,obj_8,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_9,obj_9,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_10,obj_10,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_11,obj_11,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_12,obj_12,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_13,obj_13,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_14,obj_14,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_15,obj_15,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_16,obj_16,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f59c6672e80,4096,0,884,0,4096,0,7241,0,4096,0,4793,0,4099,0,2599,0,4096,0,2154,0,4096,0,3136,0,4096,0,288,0,4096,0,2872,0,4096,0,1687,0,4096,0,949,0,4096,0,1226,0,4096,0,3572,0,4096,0,1760,0,4264,0,1550,0,4144,0,8,0,4096,0,641,0,4096,0,1339,0,4096,0,2508,0,4096,0,2977,0,4096,0,974,0,4096,0,4167,0,4096,0,1373,0,4096,0,2383,0,4096,0,0,0,4096,0,499,0,4096,0,891,0,4096,0,1060,0,4144,0,1403,0,4096,0,2641,0,4097,0,0,0,4096,0,0,0,4096,0,6711,0,64,0x7fe07ee12e80,0,0,192,0,65536,64511,48,1360,32092,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,538,48249,1718,0,48.0,383.0,0.0,262288.0,64,0x7fc7d7c6ce80,190381,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,14504,30888,9876,550,0,45781,262590.0,0.0,188.0,262402.0,64,0x7f5e935ece80,32768,0,0,0,16384,16384,393216,22024101,960.0,513884.0,0.0,524288.0,1173274.0,32768.0,0,0,0,17442,131072.0,131072.0,0.0,131072.0,64,0x7fe12d8fae80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,65337.0,130872.0,64,0x7f0dea7dce80,0.0,64,0x7f724c9fae80,0,3709730,4096,4096,0,2691727,4096,4096,0,4860451,4096,4096,0,4011195,4096,4096,0,4212142,4096,4096,0,2952521,4096,4096,0,4952643,4096,4096,0,3402094,4096,4096,0,3520868,4096,4096,0,4159150,4096,4096,0,3244782,4096,4096,0,4056625,4096,4096,0,2809991,4096,4096,0,4073468,4096,4096,0,3922681,4096,4096,0,3382407,4096,4096,0,3898405,4096,4096,0,4153605,4096,4096,0,4804191,4096,4096,0,3690606,4096,4096,0,4343774,4096,4096,0,4594981,4096,4096,0,3438943,4096,4096,0,3358847,4096,4096,0,3120617,4096,4096,0,3779821,4096,4096,0,3553386,4096,4096,0,5160416,4096,4096,0,3020076,4096,4096,0,3555842,4096,4096,0,3008008,4096,4096,0,3193964,4096,4096,64,0x7f95e557ae80,392048,239379,3510014,16384,25645719,144,48,0,49005,49005,3943561.0,3022659.0,6796.0,1099135.0,2040815.0,0.0,3013743.0,2702139.0,390527,249332,49005,0,49005,0,1568160.0,960866.0,0.0,0.0,64,0x7ff258422e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131360.0,0.0,568.0,131359.0,64,0x7fad94a7ce80,1904378,360448,163840,0,0,180224,114688,0,69629443.0,202401778.0,73612921.0,131072.0,0.0,599486.0,0,0,26515,80321.0,0.0,0.0,80321.0,64,0x7f349a4bae80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,141,8332,4377,8473,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f225df1ae80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86607.0,44465.0,131111.0,0.0,64,0x7f2f5a676e80,8192,0,4096,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f16d41c6e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,48272,0,131631.0,131072.0,0.0,131104.0,64,0x7f6626f04e80,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,0,48651,0,0,64,0x7f403d11ee80,131072.0,131072.0,0.0,2607526.0,0.0,0.0,117494719.0,62120706.0,64,0x7f62ac1dce80,2344,0,0,1827024,744,0,0,1622330,596,0,0,1601570,2730,0,0,1879982,1372,0,0,1719760,302,0,0,1550459,3955,0,0,2126722,2605,0,0,1967050,2520,0,0,1824609,1726,0,0,1798330,554,0,0,1591286,1066,0,0,1633560,5563,0,0,2234365,950,0,0,1624899,978,0,0,1619574,3124,0,0,1872210,1763,0,0,1751192,703,0,0,1703906,937,0,0,1694279,2940,0,0,1954814,6163,0,0,2145181,4104,0,0,2013477,701,0,0,1529111,2101,0,0,1854014,3225,0,0,1869353,984,0,0,1656245,2325,0,0,1881285,3066,0,0,1901849,2960,0,0,2008550,2402,0,0,1895693,3255,0,0,2062674,2492,0,0,1953049,2187817997797403,2187817997821723 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f59c6672e80,4096,0,2641,0,4096,0,0,0,4096,0,1336,0,4096,0,2701,0,4096,0,1401,0,4096,0,0,0,4096,0,6719,0,4096,0,0,0,4096,0,1190,0,4096,0,89,0,4096,0,309,0,4096,0,2630,0,4096,0,4,0,4264,0,706,0,4144,0,811,0,4096,0,1362,0,4096,0,1215,0,4099,0,307,0,4096,0,8221,0,4096,0,1350,0,4096,0,1164,0,4096,0,3894,0,4096,0,867,0,4096,0,337,0,4096,0,0,0,4096,0,2275,0,4097,0,1409,0,4144,0,240,0,4098,0,256,0,4097,0,0,0,4096,0,521,0,4096,0,1302,0,64,0x7fe07ee12e80,0,0,48,0,65536,65536,0,0,30529,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,458,41873,1726,0,48.0,322.0,0.0,262144.0,64,0x7fc7d7c6ce80,196167,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,14313,30697,8572,5470,0,40635,262437.0,0.0,47.0,262390.0,64,0x7f5e935ece80,32768,0,0,0,16384,16384,393216,22183863,964.0,513864.0,0.0,524288.0,1172677.0,32768.0,0,0,0,22082,130992.0,130992.0,0.0,130992.0,64,0x7fe12d8fae80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,56514.0,133383.0,64,0x7f0dea7dce80,0.0,64,0x7f724c9fae80,0,3475943,2700,2700,0,4382889,2704,2704,0,2977534,2664,2664,0,4569422,2718,2718,0,2738269,2712,2712,0,2775268,2740,2740,0,3964792,2692,2692,0,2906304,2728,2728,0,3457635,2700,2700,0,3151930,2693,2693,0,3739879,2711,2711,0,4260517,2740,2740,0,3898201,2721,2721,0,4593149,2681,2681,0,2616848,2673,2673,0,3074110,2720,2720,0,3037402,2702,2702,0,5530482,2702,2702,0,4108480,2672,2672,0,5353051,2732,2732,0,4190098,2714,2714,0,4717220,2720,2720,0,3191164,2681,2681,0,3468685,2720,2720,0,4292542,2704,2704,0,3009577,2698,2698,0,2741557,2726,2726,0,2857776,2726,2726,0,2373296,2704,2704,0,4238827,2697,2697,0,5488284,2714,2714,0,3239919,2720,2720,64,0x7f95e557ae80,348432,239263,3499622,16384,25597170,0,48,0,43553,43553,3878498.0,3080142.0,6708.0,1065910.0,2076089.0,0.0,3071098.0,2758670.0,348424,248715,43553,0,43553,0,1393696.0,818678.0,0.0,0.0,64,0x7ff258422e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131320.0,0.0,494.0,131319.0,64,0x7fad94a7ce80,1110653,360448,163840,0,0,180224,114688,0,73690187.0,193422943.0,77064220.0,131072.0,0.0,659148.0,0,0,25286,61768.0,0.0,0.0,61768.0,64,0x7f349a4bae80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8333,4237,8333,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8193,4097,8193,0,8192,4096,8192,0,8193,4097,8193,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8196,4100,8196,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f225df1ae80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86597.0,0.0,131112.0,0.0,64,0x7f2f5a676e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f16d41c6e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,3893,39971,0,131594.0,131072.0,0.0,87139.0,64,0x7f6626f04e80,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,0,43275,0,0,64,0x7f403d11ee80,131072.0,131072.0,0.0,2710148.0,0.0,0.0,131479249.0,48074288.0,64,0x7f62ac1dce80,2100,0,0,1486400,864,0,0,1219538,3353,0,0,1549735,2177,0,0,1508442,626,0,0,1306394,310,0,0,1335577,996,0,0,1292534,2422,0,0,1589674,624,0,0,1225109,488,0,0,1203448,3802,0,0,1664761,1714,0,0,1403540,2208,0,0,1515917,317,0,0,1195163,412,0,0,1259761,1985,0,0,1468103,1928,0,0,1486998,820,0,0,1231013,3271,0,0,1616855,2749,0,0,1567529,1081,0,0,1284094,1090,0,0,1373760,1415,0,0,1459118,4070,0,0,1697843,614,0,0,1203830,1130,0,0,1251547,1308,0,0,1359676,2857,0,0,1567353,1577,0,0,1327309,5217,0,0,1745689,6647,0,0,1887934,2853,0,0,1539207,2187817997919963,2187817997938843 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_1,obj_1,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_2,obj_2,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_3,obj_3,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_4,obj_4,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_5,obj_5,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_6,obj_6,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_7,obj_7,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_8,obj_8,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_9,obj_9,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_10,obj_10,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_11,obj_11,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_12,obj_12,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_13,obj_13,TCC_EA_ATOMIC_LEVEL_sum,wave_size_14,obj_14,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_15,obj_15,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_16,obj_16,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fb7f3d0ce80,32768,0,0,0,16384,16384,393216,22799363,960.0,513857.0,0.0,524288.0,937675.0,32768.0,0,0,0,17815,131072.0,131072.0,0.0,131072.0,64,0x7fec0dfd4e80,2530,0,0,1876463,1318,0,0,1674383,2929,0,0,1846800,1217,0,0,1773852,1883,0,0,1835287,437,0,0,1493268,2967,0,0,1918568,3235,0,0,1967857,1829,0,0,1879028,1904,0,0,1851091,2803,0,0,1999877,812,0,0,1654335,3345,0,0,2041352,997,0,0,1652931,2842,0,0,2041954,972,0,0,1739774,1449,0,0,1836713,1161,0,0,1719512,2556,0,0,1999577,1288,0,0,1632407,7073,0,0,2233833,970,0,0,1679503,2898,0,0,1954081,2192,0,0,1799634,2284,0,0,1894442,1447,0,0,1808942,5278,0,0,2158118,3740,0,0,2014092,3529,0,0,1934980,824,0,0,1671081,1771,0,0,1871654,1645,0,0,1740421,64,0x7f82b4402e80,2428980,360448,163840,0,0,180224,114688,0,70560227.0,201876389.0,77164444.0,131072.0,0.0,662088.0,0,0,27363,83368.0,0.0,0.0,83368.0,64,0x7f20ccc84e80,0,0,192,0,65536,64517,48,1292,31708,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,538,47648,1777,0,48.0,337.0,0.0,262288.0,64,0x7fc7127aae80,4096,0,8709,0,4096,0,852,0,4099,0,0,0,4096,0,691,0,4096,0,0,0,4096,0,118,0,4096,0,516,0,4096,0,550,0,4096,0,0,0,4096,0,136,0,4144,0,19,0,4096,0,602,0,4096,0,597,0,4096,0,1529,0,4096,0,22,0,4096,0,0,0,4096,0,0,0,4144,0,1211,0,4096,0,570,0,4096,0,778,0,4096,0,439,0,4097,0,527,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,58,0,4096,0,14,0,4096,0,1361,0,4215,0,337,0,64,0x7f8fffc3ae80,186813,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13518,29902,9775,550,0,47381,262828.0,0.0,188.0,262640.0,64,0x7fd1e9c0ce80,131072.0,131072.0,0.0,2643188.0,0.0,0.0,125484369.0,59505093.0,64,0x7f9a451d4e80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,141,8243,4288,8384,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8373,4277,8373,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f3bfaa68e80,383200,231552,3387407,16384,24201346,144,48,0,47899,47899,3826016.0,3009789.0,5558.0,1115673.0,2076619.0,0.0,3000511.0,2690377.0,381487,241484,47899,0,47899,0,1532768.0,964572.0,0.0,0.0,64,0x7f3a4c3cae80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131384.0,0.0,616.0,131383.0,64,0x7f6e434a0e80,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,64,0x7f0531c0ce80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86382.0,44690.0,131111.0,0.0,64,0x7f1f4682ce80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,38563.0,102086.0,64,0x7fcdd7804e80,0.0,64,0x7fad9aa9ee80,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f6b1a2aae80,0,3283429,4096,4096,0,4714789,4096,4096,0,2645901,4096,4096,0,3322523,4096,4096,0,3604637,4096,4096,0,3470840,4096,4096,0,3118047,4096,4096,0,3275482,4096,4096,0,3119950,4096,4096,0,3914636,4096,4096,0,5112391,4096,4096,0,3832640,4096,4096,0,5169291,4096,4096,0,4131816,4096,4096,0,3060466,4096,4096,0,3320476,4096,4096,0,4224276,4096,4096,0,4108513,4096,4096,0,3646382,4096,4096,0,4389395,4096,4096,0,4566367,4096,4096,0,4328148,4096,4096,0,2683668,4096,4096,0,3681846,4096,4096,0,3058709,4096,4096,0,4411880,4096,4096,0,4014910,4096,4096,0,3041667,4096,4096,0,3252977,4096,4096,0,3876865,4096,4096,0,3419351,4096,4096,0,3449367,4096,4096,64,0x7f662f32ce80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,46996,0,131485.0,131072.0,0.0,131104.0,194232901432521,194232901456681 +1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fb7f3d0ce80,32768,0,0,0,16384,16384,393216,23156011,960.0,513866.0,0.0,524288.0,1047326.0,32768.0,0,0,0,13390,86481.0,86481.0,0.0,86481.0,64,0x7fec0dfd4e80,1199,0,0,1317635,770,0,0,1308323,5148,0,0,1828726,5232,0,0,1800526,1929,0,0,1418453,1347,0,0,1383143,1508,0,0,1409509,5774,0,0,1874876,1370,0,0,1297879,1891,0,0,1382200,3785,0,0,1765809,3850,0,0,1774111,757,0,0,1232782,4082,0,0,1709004,3538,0,0,1658257,5786,0,0,1805313,539,0,0,1228118,594,0,0,1202674,3376,0,0,1640532,7139,0,0,1907019,1604,0,0,1375297,4852,0,0,1670716,5046,0,0,1773185,5201,0,0,1771851,1636,0,0,1410163,902,0,0,1245278,5480,0,0,1790857,6434,0,0,1815149,1667,0,0,1308244,1039,0,0,1237987,2566,0,0,1578243,4948,0,0,1751575,64,0x7f82b4402e80,1647014,360448,163840,0,0,180224,114688,0,71052221.0,186613591.0,79262691.0,131072.0,0.0,630120.0,0,0,25726,63283.0,0.0,0.0,63283.0,64,0x7f20ccc84e80,0,0,48,0,65536,65536,0,0,30904,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,457,42850,1734,0,48.0,365.0,0.0,262144.0,64,0x7fc7127aae80,4097,0,2082,0,4096,0,985,0,4096,0,3292,0,4096,0,1649,0,4096,0,2981,0,4096,0,5470,0,4096,0,658,0,4097,0,2363,0,4096,0,1736,0,4096,0,4399,0,4144,0,640,0,4096,0,3042,0,4096,0,2005,0,4096,0,990,0,4096,0,3626,0,4096,0,578,0,4096,0,4152,0,4144,0,1210,0,4096,0,1148,0,4096,0,2798,0,4096,0,814,0,4097,0,856,0,4096,0,2375,0,4099,0,2799,0,4096,0,4314,0,4096,0,90,0,4096,0,287,0,4096,0,792,0,4096,0,1252,0,4096,0,4667,0,4096,0,2086,0,4168,0,2320,0,64,0x7f8fffc3ae80,186371,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13277,29661,8692,2426,0,42069,262645.0,0.0,47.0,262598.0,64,0x7fd1e9c0ce80,131072.0,131072.0,0.0,2662368.0,0.0,0.0,124135047.0,46283642.0,64,0x7f9a451d4e80,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8338,4242,8338,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f3bfaa68e80,343224,227063,3322094,16384,24227873,0,48,0,42902,42902,3695444.0,3037195.0,5782.0,975253.0,2009754.0,0.0,3028517.0,2717822.0,343216,236379,42902,0,42902,0,1372864.0,813272.0,0.0,0.0,64,0x7f3a4c3cae80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131306.0,0.0,466.0,131305.0,64,0x7f6e434a0e80,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,64,0x7f0531c0ce80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86500.0,0.0,131118.0,0.0,64,0x7f1f4682ce80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,72533.0,144651.0,64,0x7fcdd7804e80,0.0,64,0x7fad9aa9ee80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f6b1a2aae80,0,5390743,2740,2740,0,4529613,2749,2749,0,3030456,2682,2682,0,3267365,2714,2714,0,4057592,2704,2704,0,4616353,2728,2728,0,3500249,2716,2716,0,2628551,2728,2728,0,3855143,2706,2706,0,3803408,2712,2712,0,4310852,2720,2720,0,4853321,2724,2724,0,4445389,2710,2710,0,4393337,2696,2696,0,3989937,2690,2690,0,3824329,2674,2674,0,4690996,2695,2695,0,4979742,2728,2728,0,4405812,2672,2672,0,5443521,2712,2712,0,3302766,2721,2721,0,3386652,2747,2747,0,3291027,2691,2691,0,3068963,2704,2704,0,5033160,2722,2722,0,3759041,2720,2720,0,3146656,2724,2724,0,2792034,2705,2705,0,4447282,2716,2716,0,4002383,2754,2754,0,4432364,2710,2710,0,3805608,2680,2680,64,0x7f662f32ce80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,240.0,524288.0,0.0,0.0,0,0,2884,45628,6588,131354.0,131072.0,0.0,131103.0,194232901551561,194232901570601 diff --git a/tests/workloads/dispatch_0_1/MI100/sysinfo.csv b/tests/workloads/dispatch_0_1/MI100/sysinfo.csv index ae2c4d5c2e..ab7cba6645 100644 --- a/tests/workloads/dispatch_0_1/MI100/sysinfo.csv +++ b/tests/workloads/dispatch_0_1/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -dispatch_0_1,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Fri Mar 1 16:45:25 2024 (CST),1,t006-003.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651240,,5.7.1-98,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +dispatch_0_1,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 07 Mar 2024 01:08:05 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/dispatch_0_1/MI100/timestamps.csv b/tests/workloads/dispatch_0_1/MI100/timestamps.csv index fcde267128..91c069428a 100644 --- a/tests/workloads/dispatch_0_1/MI100/timestamps.csv +++ b/tests/workloads/dispatch_0_1/MI100/timestamps.csv @@ -1,3 +1,3 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,2852071,2852071,1048576,256,0,0,8,8,16,64,0x0,0x7f0f1fe14e80,2187817997771027,2187817997797403,2187817997821723,2187817997835769 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,2852071,2852071,1048576,256,0,0,8,8,16,64,0x0,0x7f0f1fe14e80,2187817997834266,2187817997919963,2187817997938843,2187817997944092 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,159380,159380,1048576,256,0,0,8,8,16,64,0x0,0x7fd3f9e04e80,194232901406934,194232901432521,194232901456681,194232901471346 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,159380,159380,1048576,256,0,0,8,8,16,64,0x0,0x7fd3f9e04e80,194232901470003,194232901551561,194232901570601,194232901571726 diff --git a/tests/workloads/dispatch_0_1/MI200/SQ_IFETCH_LEVEL.csv b/tests/workloads/dispatch_0_1/MI200/SQ_IFETCH_LEVEL.csv new file mode 100644 index 0000000000..936271e619 --- /dev/null +++ b/tests/workloads/dispatch_0_1/MI200/SQ_IFETCH_LEVEL.csv @@ -0,0 +1,3 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,311135,311135,1048576,256,0,0,8,0,16,64,0x0,0x7f20e5dd0ec0,27333,27333,16384,65536,13914,1566164,198596821057709,198609512940794,198609512961274,198596836842831 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,311135,311135,1048576,256,0,0,8,0,16,64,0x0,0x7f20e5dd0ec0,41896,41896,16384,65536,9440,1048676,198596836864582,198609513046074,198609513062554,198596837190358 diff --git a/tests/workloads/dispatch_0_1/MI200/SQ_INST_LEVEL_LDS.csv b/tests/workloads/dispatch_0_1/MI200/SQ_INST_LEVEL_LDS.csv new file mode 100644 index 0000000000..76a58ab2cb --- /dev/null +++ b/tests/workloads/dispatch_0_1/MI200/SQ_INST_LEVEL_LDS.csv @@ -0,0 +1,3 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,311337,311337,1048576,256,0,0,8,0,16,64,0x0,0x7fef76aa8ec0,0,0,0,198597300509498,198609512940794,198609512961274,198597316434836 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,311337,311337,1048576,256,0,0,8,0,16,64,0x0,0x7fef76aa8ec0,0,0,0,198597316453451,198609513046074,198609513062554,198597316756414 diff --git a/tests/workloads/dispatch_0_1/MI200/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/dispatch_0_1/MI200/SQ_INST_LEVEL_SMEM.csv new file mode 100644 index 0000000000..5478b8f1de --- /dev/null +++ b/tests/workloads/dispatch_0_1/MI200/SQ_INST_LEVEL_SMEM.csv @@ -0,0 +1,3 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,311539,311539,1048576,256,0,0,8,0,16,64,0x0,0x7f00c60b0ec0,65536,178908,19932664,198597783544016,198609512940794,198609512961274,198597799509239 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,311539,311539,1048576,256,0,0,8,0,16,64,0x0,0x7f00c60b0ec0,65536,228948,25571704,198597799526401,198609513046074,198609513062554,198597799830967 diff --git a/tests/workloads/dispatch_0_1/MI200/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/dispatch_0_1/MI200/SQ_INST_LEVEL_VMEM.csv new file mode 100644 index 0000000000..982e8f2f52 --- /dev/null +++ b/tests/workloads/dispatch_0_1/MI200/SQ_INST_LEVEL_VMEM.csv @@ -0,0 +1,3 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,311741,311741,1048576,256,0,0,8,0,16,64,0x0,0x7f8f6070cec0,32768,295724,33126508,198598264016216,198609512940794,198609512961274,198598279668286 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,311741,311741,1048576,256,0,0,8,0,16,64,0x0,0x7f8f6070cec0,32768,579022,64857248,198598279691300,198609513046074,198609513062554,198598279967252 diff --git a/tests/workloads/dispatch_0_1/MI200/SQ_LEVEL_WAVES.csv b/tests/workloads/dispatch_0_1/MI200/SQ_LEVEL_WAVES.csv new file mode 100644 index 0000000000..8abec10d1c --- /dev/null +++ b/tests/workloads/dispatch_0_1/MI200/SQ_LEVEL_WAVES.csv @@ -0,0 +1,3 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,311942,311942,1048576,256,0,0,8,0,16,64,0x0,0x7fecfef2cec0,28002,28002,11107,224024,16384,11099231,131393,0,44906916,198598744115260,198609512940794,198609512961274,198598759705213 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,311942,311942,1048576,256,0,0,8,0,16,64,0x0,0x7fecfef2cec0,42307,42307,13512,338464,16384,20301423,231106,0,81693968,198598759736312,198609513046074,198609513062554,198598760106662 diff --git a/tests/workloads/dispatch_0_1/MI200/perfmon/SQ_IFETCH_LEVEL.txt b/tests/workloads/dispatch_0_1/MI200/perfmon/SQ_IFETCH_LEVEL.txt new file mode 100644 index 0000000000..ad1506b7f9 --- /dev/null +++ b/tests/workloads/dispatch_0_1/MI200/perfmon/SQ_IFETCH_LEVEL.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES + +gpu: +range: 0:2 +kernel: diff --git a/tests/workloads/dispatch_0_1/MI200/perfmon/SQ_INST_LEVEL_LDS.txt b/tests/workloads/dispatch_0_1/MI200/perfmon/SQ_INST_LEVEL_LDS.txt new file mode 100644 index 0000000000..af443a5fdf --- /dev/null +++ b/tests/workloads/dispatch_0_1/MI200/perfmon/SQ_INST_LEVEL_LDS.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES + +gpu: +range: 0:2 +kernel: diff --git a/tests/workloads/dispatch_0_1/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt b/tests/workloads/dispatch_0_1/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt new file mode 100644 index 0000000000..8e42534e97 --- /dev/null +++ b/tests/workloads/dispatch_0_1/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: 0:2 +kernel: diff --git a/tests/workloads/dispatch_0_1/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt b/tests/workloads/dispatch_0_1/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt new file mode 100644 index 0000000000..786628208e --- /dev/null +++ b/tests/workloads/dispatch_0_1/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: 0:2 +kernel: diff --git a/tests/workloads/dispatch_0_1/MI200/perfmon/SQ_LEVEL_WAVES.txt b/tests/workloads/dispatch_0_1/MI200/perfmon/SQ_LEVEL_WAVES.txt new file mode 100644 index 0000000000..c9c2bb4619 --- /dev/null +++ b/tests/workloads/dispatch_0_1/MI200/perfmon/SQ_LEVEL_WAVES.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES + +gpu: +range: 0:2 +kernel: diff --git a/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_0.txt b/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_0.txt new file mode 100644 index 0000000000..a68e81cd40 --- /dev/null +++ b/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_0.txt @@ -0,0 +1,5 @@ +pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES SQ_INSTS_VALU_CVT SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU GRBM_COUNT GRBM_GUI_ACTIVE TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum TA_TA_BUSY_sum TA_BUFFER_WAVEFRONTS_sum TD_TD_BUSY_sum TD_TC_STALL_sum SPI_CSN_WINDOW_VALID SPI_CSN_BUSY CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum + +gpu: +range: 0:2 +kernel: diff --git a/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_1.txt b/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_1.txt new file mode 100644 index 0000000000..f6d0ce4bc9 --- /dev/null +++ b/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_1.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VSKIPPED SQ_INSTS SQ_INSTS_VALU SQ_INSTS_VALU_ADD_F16 SQ_INSTS_VALU_MUL_F16 SQ_INSTS_VALU_FMA_F16 SQ_INSTS_VALU_TRANS_F16 SQ_INSTS_VALU_ADD_F32 GRBM_SPI_BUSY TCP_READ_TAGCONFLICT_STALL_CYCLES_sum TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum TCP_TA_TCP_STATE_READ_sum TA_BUFFER_READ_WAVEFRONTS_sum TA_BUFFER_WRITE_WAVEFRONTS_sum TD_SPI_STALL_sum TD_LOAD_WAVEFRONT_sum SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum + +gpu: +range: 0:2 +kernel: diff --git a/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_10.txt b/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_10.txt new file mode 100644 index 0000000000..7da3c6914c --- /dev/null +++ b/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_10.txt @@ -0,0 +1,5 @@ +pmc: SQC_TC_DATA_WRITE_REQ SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES + +gpu: +range: 0:2 +kernel: diff --git a/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_11.txt b/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_11.txt new file mode 100644 index 0000000000..9ae5b8af40 --- /dev/null +++ b/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_11.txt @@ -0,0 +1,5 @@ +pmc: SQC_ICACHE_MISSES_DUPLICATE SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE + +gpu: +range: 0:2 +kernel: diff --git a/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_12.txt b/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_12.txt new file mode 100644 index 0000000000..b08bae7f70 --- /dev/null +++ b/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_12.txt @@ -0,0 +1,5 @@ +pmc: SQC_DCACHE_REQ_READ_1 SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 + +gpu: +range: 0:2 +kernel: diff --git a/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_13.txt b/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_13.txt new file mode 100644 index 0000000000..847334ad4d --- /dev/null +++ b/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_13.txt @@ -0,0 +1,5 @@ +pmc: TCC_ATOMIC[0] TCC_CYCLE[0] TCC_EA_ATOMIC[0] TCC_EA_ATOMIC_LEVEL[0] TCC_ATOMIC[1] TCC_CYCLE[1] TCC_EA_ATOMIC[1] TCC_EA_ATOMIC_LEVEL[1] TCC_ATOMIC[2] TCC_CYCLE[2] TCC_EA_ATOMIC[2] TCC_EA_ATOMIC_LEVEL[2] TCC_ATOMIC[3] TCC_CYCLE[3] TCC_EA_ATOMIC[3] TCC_EA_ATOMIC_LEVEL[3] TCC_ATOMIC[4] TCC_CYCLE[4] TCC_EA_ATOMIC[4] TCC_EA_ATOMIC_LEVEL[4] TCC_ATOMIC[5] TCC_CYCLE[5] TCC_EA_ATOMIC[5] TCC_EA_ATOMIC_LEVEL[5] TCC_ATOMIC[6] TCC_CYCLE[6] TCC_EA_ATOMIC[6] TCC_EA_ATOMIC_LEVEL[6] TCC_ATOMIC[7] TCC_CYCLE[7] TCC_EA_ATOMIC[7] TCC_EA_ATOMIC_LEVEL[7] TCC_ATOMIC[8] TCC_CYCLE[8] TCC_EA_ATOMIC[8] TCC_EA_ATOMIC_LEVEL[8] TCC_ATOMIC[9] TCC_CYCLE[9] TCC_EA_ATOMIC[9] TCC_EA_ATOMIC_LEVEL[9] TCC_ATOMIC[10] TCC_CYCLE[10] TCC_EA_ATOMIC[10] TCC_EA_ATOMIC_LEVEL[10] TCC_ATOMIC[11] TCC_CYCLE[11] TCC_EA_ATOMIC[11] TCC_EA_ATOMIC_LEVEL[11] TCC_ATOMIC[12] TCC_CYCLE[12] TCC_EA_ATOMIC[12] TCC_EA_ATOMIC_LEVEL[12] TCC_ATOMIC[13] TCC_CYCLE[13] TCC_EA_ATOMIC[13] TCC_EA_ATOMIC_LEVEL[13] TCC_ATOMIC[14] TCC_CYCLE[14] TCC_EA_ATOMIC[14] TCC_EA_ATOMIC_LEVEL[14] TCC_ATOMIC[15] TCC_CYCLE[15] TCC_EA_ATOMIC[15] TCC_EA_ATOMIC_LEVEL[15] TCC_ATOMIC[16] TCC_CYCLE[16] TCC_EA_ATOMIC[16] TCC_EA_ATOMIC_LEVEL[16] TCC_ATOMIC[17] TCC_CYCLE[17] TCC_EA_ATOMIC[17] TCC_EA_ATOMIC_LEVEL[17] TCC_ATOMIC[18] TCC_CYCLE[18] TCC_EA_ATOMIC[18] TCC_EA_ATOMIC_LEVEL[18] TCC_ATOMIC[19] TCC_CYCLE[19] TCC_EA_ATOMIC[19] TCC_EA_ATOMIC_LEVEL[19] TCC_ATOMIC[20] TCC_CYCLE[20] TCC_EA_ATOMIC[20] TCC_EA_ATOMIC_LEVEL[20] TCC_ATOMIC[21] TCC_CYCLE[21] TCC_EA_ATOMIC[21] TCC_EA_ATOMIC_LEVEL[21] TCC_ATOMIC[22] TCC_CYCLE[22] TCC_EA_ATOMIC[22] TCC_EA_ATOMIC_LEVEL[22] TCC_ATOMIC[23] TCC_CYCLE[23] TCC_EA_ATOMIC[23] TCC_EA_ATOMIC_LEVEL[23] TCC_ATOMIC[24] TCC_CYCLE[24] TCC_EA_ATOMIC[24] TCC_EA_ATOMIC_LEVEL[24] TCC_ATOMIC[25] TCC_CYCLE[25] TCC_EA_ATOMIC[25] TCC_EA_ATOMIC_LEVEL[25] TCC_ATOMIC[26] TCC_CYCLE[26] TCC_EA_ATOMIC[26] TCC_EA_ATOMIC_LEVEL[26] TCC_ATOMIC[27] TCC_CYCLE[27] TCC_EA_ATOMIC[27] TCC_EA_ATOMIC_LEVEL[27] TCC_ATOMIC[28] TCC_CYCLE[28] TCC_EA_ATOMIC[28] TCC_EA_ATOMIC_LEVEL[28] TCC_ATOMIC[29] TCC_CYCLE[29] TCC_EA_ATOMIC[29] TCC_EA_ATOMIC_LEVEL[29] TCC_ATOMIC[30] TCC_CYCLE[30] TCC_EA_ATOMIC[30] TCC_EA_ATOMIC_LEVEL[30] TCC_ATOMIC[31] TCC_CYCLE[31] TCC_EA_ATOMIC[31] TCC_EA_ATOMIC_LEVEL[31] + +gpu: +range: 0:2 +kernel: diff --git a/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_14.txt b/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_14.txt new file mode 100644 index 0000000000..bd8d46aadf --- /dev/null +++ b/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_14.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_EA_RDREQ_GMI_CREDIT_STALL[0] TCC_EA_RDREQ[1] TCC_EA_RDREQ_32B[1] TCC_EA_RDREQ_DRAM_CREDIT_STALL[1] TCC_EA_RDREQ_GMI_CREDIT_STALL[1] TCC_EA_RDREQ[2] TCC_EA_RDREQ_32B[2] TCC_EA_RDREQ_DRAM_CREDIT_STALL[2] TCC_EA_RDREQ_GMI_CREDIT_STALL[2] TCC_EA_RDREQ[3] TCC_EA_RDREQ_32B[3] TCC_EA_RDREQ_DRAM_CREDIT_STALL[3] TCC_EA_RDREQ_GMI_CREDIT_STALL[3] TCC_EA_RDREQ[4] TCC_EA_RDREQ_32B[4] TCC_EA_RDREQ_DRAM_CREDIT_STALL[4] TCC_EA_RDREQ_GMI_CREDIT_STALL[4] TCC_EA_RDREQ[5] TCC_EA_RDREQ_32B[5] TCC_EA_RDREQ_DRAM_CREDIT_STALL[5] TCC_EA_RDREQ_GMI_CREDIT_STALL[5] TCC_EA_RDREQ[6] TCC_EA_RDREQ_32B[6] TCC_EA_RDREQ_DRAM_CREDIT_STALL[6] TCC_EA_RDREQ_GMI_CREDIT_STALL[6] TCC_EA_RDREQ[7] TCC_EA_RDREQ_32B[7] TCC_EA_RDREQ_DRAM_CREDIT_STALL[7] TCC_EA_RDREQ_GMI_CREDIT_STALL[7] TCC_EA_RDREQ[8] TCC_EA_RDREQ_32B[8] TCC_EA_RDREQ_DRAM_CREDIT_STALL[8] TCC_EA_RDREQ_GMI_CREDIT_STALL[8] TCC_EA_RDREQ[9] TCC_EA_RDREQ_32B[9] TCC_EA_RDREQ_DRAM_CREDIT_STALL[9] TCC_EA_RDREQ_GMI_CREDIT_STALL[9] TCC_EA_RDREQ[10] TCC_EA_RDREQ_32B[10] TCC_EA_RDREQ_DRAM_CREDIT_STALL[10] TCC_EA_RDREQ_GMI_CREDIT_STALL[10] TCC_EA_RDREQ[11] TCC_EA_RDREQ_32B[11] TCC_EA_RDREQ_DRAM_CREDIT_STALL[11] TCC_EA_RDREQ_GMI_CREDIT_STALL[11] TCC_EA_RDREQ[12] TCC_EA_RDREQ_32B[12] TCC_EA_RDREQ_DRAM_CREDIT_STALL[12] TCC_EA_RDREQ_GMI_CREDIT_STALL[12] TCC_EA_RDREQ[13] TCC_EA_RDREQ_32B[13] TCC_EA_RDREQ_DRAM_CREDIT_STALL[13] TCC_EA_RDREQ_GMI_CREDIT_STALL[13] TCC_EA_RDREQ[14] TCC_EA_RDREQ_32B[14] TCC_EA_RDREQ_DRAM_CREDIT_STALL[14] TCC_EA_RDREQ_GMI_CREDIT_STALL[14] TCC_EA_RDREQ[15] TCC_EA_RDREQ_32B[15] TCC_EA_RDREQ_DRAM_CREDIT_STALL[15] TCC_EA_RDREQ_GMI_CREDIT_STALL[15] TCC_EA_RDREQ[16] TCC_EA_RDREQ_32B[16] TCC_EA_RDREQ_DRAM_CREDIT_STALL[16] TCC_EA_RDREQ_GMI_CREDIT_STALL[16] TCC_EA_RDREQ[17] TCC_EA_RDREQ_32B[17] TCC_EA_RDREQ_DRAM_CREDIT_STALL[17] TCC_EA_RDREQ_GMI_CREDIT_STALL[17] TCC_EA_RDREQ[18] TCC_EA_RDREQ_32B[18] TCC_EA_RDREQ_DRAM_CREDIT_STALL[18] TCC_EA_RDREQ_GMI_CREDIT_STALL[18] TCC_EA_RDREQ[19] TCC_EA_RDREQ_32B[19] TCC_EA_RDREQ_DRAM_CREDIT_STALL[19] TCC_EA_RDREQ_GMI_CREDIT_STALL[19] TCC_EA_RDREQ[20] TCC_EA_RDREQ_32B[20] TCC_EA_RDREQ_DRAM_CREDIT_STALL[20] TCC_EA_RDREQ_GMI_CREDIT_STALL[20] TCC_EA_RDREQ[21] TCC_EA_RDREQ_32B[21] TCC_EA_RDREQ_DRAM_CREDIT_STALL[21] TCC_EA_RDREQ_GMI_CREDIT_STALL[21] TCC_EA_RDREQ[22] TCC_EA_RDREQ_32B[22] TCC_EA_RDREQ_DRAM_CREDIT_STALL[22] TCC_EA_RDREQ_GMI_CREDIT_STALL[22] TCC_EA_RDREQ[23] TCC_EA_RDREQ_32B[23] TCC_EA_RDREQ_DRAM_CREDIT_STALL[23] TCC_EA_RDREQ_GMI_CREDIT_STALL[23] TCC_EA_RDREQ[24] TCC_EA_RDREQ_32B[24] TCC_EA_RDREQ_DRAM_CREDIT_STALL[24] TCC_EA_RDREQ_GMI_CREDIT_STALL[24] TCC_EA_RDREQ[25] TCC_EA_RDREQ_32B[25] TCC_EA_RDREQ_DRAM_CREDIT_STALL[25] TCC_EA_RDREQ_GMI_CREDIT_STALL[25] TCC_EA_RDREQ[26] TCC_EA_RDREQ_32B[26] TCC_EA_RDREQ_DRAM_CREDIT_STALL[26] TCC_EA_RDREQ_GMI_CREDIT_STALL[26] TCC_EA_RDREQ[27] TCC_EA_RDREQ_32B[27] TCC_EA_RDREQ_DRAM_CREDIT_STALL[27] TCC_EA_RDREQ_GMI_CREDIT_STALL[27] TCC_EA_RDREQ[28] TCC_EA_RDREQ_32B[28] TCC_EA_RDREQ_DRAM_CREDIT_STALL[28] TCC_EA_RDREQ_GMI_CREDIT_STALL[28] TCC_EA_RDREQ[29] TCC_EA_RDREQ_32B[29] TCC_EA_RDREQ_DRAM_CREDIT_STALL[29] TCC_EA_RDREQ_GMI_CREDIT_STALL[29] TCC_EA_RDREQ[30] TCC_EA_RDREQ_32B[30] TCC_EA_RDREQ_DRAM_CREDIT_STALL[30] TCC_EA_RDREQ_GMI_CREDIT_STALL[30] TCC_EA_RDREQ[31] TCC_EA_RDREQ_32B[31] TCC_EA_RDREQ_DRAM_CREDIT_STALL[31] TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + +gpu: +range: 0:2 +kernel: diff --git a/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_15.txt b/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_15.txt new file mode 100644 index 0000000000..f1139d4eae --- /dev/null +++ b/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_15.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ[0] TCC_EA_WRREQ_64B[0] TCC_EA_RDREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_LEVEL[1] TCC_EA_WRREQ[1] TCC_EA_WRREQ_64B[1] TCC_EA_RDREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_LEVEL[2] TCC_EA_WRREQ[2] TCC_EA_WRREQ_64B[2] TCC_EA_RDREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_LEVEL[3] TCC_EA_WRREQ[3] TCC_EA_WRREQ_64B[3] TCC_EA_RDREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_LEVEL[4] TCC_EA_WRREQ[4] TCC_EA_WRREQ_64B[4] TCC_EA_RDREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_LEVEL[5] TCC_EA_WRREQ[5] TCC_EA_WRREQ_64B[5] TCC_EA_RDREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_LEVEL[6] TCC_EA_WRREQ[6] TCC_EA_WRREQ_64B[6] TCC_EA_RDREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_LEVEL[7] TCC_EA_WRREQ[7] TCC_EA_WRREQ_64B[7] TCC_EA_RDREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_LEVEL[8] TCC_EA_WRREQ[8] TCC_EA_WRREQ_64B[8] TCC_EA_RDREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_LEVEL[9] TCC_EA_WRREQ[9] TCC_EA_WRREQ_64B[9] TCC_EA_RDREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_LEVEL[10] TCC_EA_WRREQ[10] TCC_EA_WRREQ_64B[10] TCC_EA_RDREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_LEVEL[11] TCC_EA_WRREQ[11] TCC_EA_WRREQ_64B[11] TCC_EA_RDREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_LEVEL[12] TCC_EA_WRREQ[12] TCC_EA_WRREQ_64B[12] TCC_EA_RDREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_LEVEL[13] TCC_EA_WRREQ[13] TCC_EA_WRREQ_64B[13] TCC_EA_RDREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_LEVEL[14] TCC_EA_WRREQ[14] TCC_EA_WRREQ_64B[14] TCC_EA_RDREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_LEVEL[15] TCC_EA_WRREQ[15] TCC_EA_WRREQ_64B[15] TCC_EA_RDREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_LEVEL[16] TCC_EA_WRREQ[16] TCC_EA_WRREQ_64B[16] TCC_EA_RDREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_LEVEL[17] TCC_EA_WRREQ[17] TCC_EA_WRREQ_64B[17] TCC_EA_RDREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_LEVEL[18] TCC_EA_WRREQ[18] TCC_EA_WRREQ_64B[18] TCC_EA_RDREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_LEVEL[19] TCC_EA_WRREQ[19] TCC_EA_WRREQ_64B[19] TCC_EA_RDREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_LEVEL[20] TCC_EA_WRREQ[20] TCC_EA_WRREQ_64B[20] TCC_EA_RDREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_LEVEL[21] TCC_EA_WRREQ[21] TCC_EA_WRREQ_64B[21] TCC_EA_RDREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_LEVEL[22] TCC_EA_WRREQ[22] TCC_EA_WRREQ_64B[22] TCC_EA_RDREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_LEVEL[23] TCC_EA_WRREQ[23] TCC_EA_WRREQ_64B[23] TCC_EA_RDREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_LEVEL[24] TCC_EA_WRREQ[24] TCC_EA_WRREQ_64B[24] TCC_EA_RDREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_LEVEL[25] TCC_EA_WRREQ[25] TCC_EA_WRREQ_64B[25] TCC_EA_RDREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_LEVEL[26] TCC_EA_WRREQ[26] TCC_EA_WRREQ_64B[26] TCC_EA_RDREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_LEVEL[27] TCC_EA_WRREQ[27] TCC_EA_WRREQ_64B[27] TCC_EA_RDREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_LEVEL[28] TCC_EA_WRREQ[28] TCC_EA_WRREQ_64B[28] TCC_EA_RDREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_LEVEL[29] TCC_EA_WRREQ[29] TCC_EA_WRREQ_64B[29] TCC_EA_RDREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_LEVEL[30] TCC_EA_WRREQ[30] TCC_EA_WRREQ_64B[30] TCC_EA_RDREQ_IO_CREDIT_STALL[31] TCC_EA_RDREQ_LEVEL[31] TCC_EA_WRREQ[31] TCC_EA_WRREQ_64B[31] + +gpu: +range: 0:2 +kernel: diff --git a/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_16.txt b/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_16.txt new file mode 100644 index 0000000000..73c1f071d6 --- /dev/null +++ b/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_16.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_WRREQ_IO_CREDIT_STALL[0] TCC_EA_WRREQ_LEVEL[0] TCC_EA_WRREQ_DRAM_CREDIT_STALL[1] TCC_EA_WRREQ_GMI_CREDIT_STALL[1] TCC_EA_WRREQ_IO_CREDIT_STALL[1] TCC_EA_WRREQ_LEVEL[1] TCC_EA_WRREQ_DRAM_CREDIT_STALL[2] TCC_EA_WRREQ_GMI_CREDIT_STALL[2] TCC_EA_WRREQ_IO_CREDIT_STALL[2] TCC_EA_WRREQ_LEVEL[2] TCC_EA_WRREQ_DRAM_CREDIT_STALL[3] TCC_EA_WRREQ_GMI_CREDIT_STALL[3] TCC_EA_WRREQ_IO_CREDIT_STALL[3] TCC_EA_WRREQ_LEVEL[3] TCC_EA_WRREQ_DRAM_CREDIT_STALL[4] TCC_EA_WRREQ_GMI_CREDIT_STALL[4] TCC_EA_WRREQ_IO_CREDIT_STALL[4] TCC_EA_WRREQ_LEVEL[4] TCC_EA_WRREQ_DRAM_CREDIT_STALL[5] TCC_EA_WRREQ_GMI_CREDIT_STALL[5] TCC_EA_WRREQ_IO_CREDIT_STALL[5] TCC_EA_WRREQ_LEVEL[5] TCC_EA_WRREQ_DRAM_CREDIT_STALL[6] TCC_EA_WRREQ_GMI_CREDIT_STALL[6] TCC_EA_WRREQ_IO_CREDIT_STALL[6] TCC_EA_WRREQ_LEVEL[6] TCC_EA_WRREQ_DRAM_CREDIT_STALL[7] TCC_EA_WRREQ_GMI_CREDIT_STALL[7] TCC_EA_WRREQ_IO_CREDIT_STALL[7] TCC_EA_WRREQ_LEVEL[7] TCC_EA_WRREQ_DRAM_CREDIT_STALL[8] TCC_EA_WRREQ_GMI_CREDIT_STALL[8] TCC_EA_WRREQ_IO_CREDIT_STALL[8] TCC_EA_WRREQ_LEVEL[8] TCC_EA_WRREQ_DRAM_CREDIT_STALL[9] TCC_EA_WRREQ_GMI_CREDIT_STALL[9] TCC_EA_WRREQ_IO_CREDIT_STALL[9] TCC_EA_WRREQ_LEVEL[9] TCC_EA_WRREQ_DRAM_CREDIT_STALL[10] TCC_EA_WRREQ_GMI_CREDIT_STALL[10] TCC_EA_WRREQ_IO_CREDIT_STALL[10] TCC_EA_WRREQ_LEVEL[10] TCC_EA_WRREQ_DRAM_CREDIT_STALL[11] TCC_EA_WRREQ_GMI_CREDIT_STALL[11] TCC_EA_WRREQ_IO_CREDIT_STALL[11] TCC_EA_WRREQ_LEVEL[11] TCC_EA_WRREQ_DRAM_CREDIT_STALL[12] TCC_EA_WRREQ_GMI_CREDIT_STALL[12] TCC_EA_WRREQ_IO_CREDIT_STALL[12] TCC_EA_WRREQ_LEVEL[12] TCC_EA_WRREQ_DRAM_CREDIT_STALL[13] TCC_EA_WRREQ_GMI_CREDIT_STALL[13] TCC_EA_WRREQ_IO_CREDIT_STALL[13] TCC_EA_WRREQ_LEVEL[13] TCC_EA_WRREQ_DRAM_CREDIT_STALL[14] TCC_EA_WRREQ_GMI_CREDIT_STALL[14] TCC_EA_WRREQ_IO_CREDIT_STALL[14] TCC_EA_WRREQ_LEVEL[14] TCC_EA_WRREQ_DRAM_CREDIT_STALL[15] TCC_EA_WRREQ_GMI_CREDIT_STALL[15] TCC_EA_WRREQ_IO_CREDIT_STALL[15] TCC_EA_WRREQ_LEVEL[15] TCC_EA_WRREQ_DRAM_CREDIT_STALL[16] TCC_EA_WRREQ_GMI_CREDIT_STALL[16] TCC_EA_WRREQ_IO_CREDIT_STALL[16] TCC_EA_WRREQ_LEVEL[16] TCC_EA_WRREQ_DRAM_CREDIT_STALL[17] TCC_EA_WRREQ_GMI_CREDIT_STALL[17] TCC_EA_WRREQ_IO_CREDIT_STALL[17] TCC_EA_WRREQ_LEVEL[17] TCC_EA_WRREQ_DRAM_CREDIT_STALL[18] TCC_EA_WRREQ_GMI_CREDIT_STALL[18] TCC_EA_WRREQ_IO_CREDIT_STALL[18] TCC_EA_WRREQ_LEVEL[18] TCC_EA_WRREQ_DRAM_CREDIT_STALL[19] TCC_EA_WRREQ_GMI_CREDIT_STALL[19] TCC_EA_WRREQ_IO_CREDIT_STALL[19] TCC_EA_WRREQ_LEVEL[19] TCC_EA_WRREQ_DRAM_CREDIT_STALL[20] TCC_EA_WRREQ_GMI_CREDIT_STALL[20] TCC_EA_WRREQ_IO_CREDIT_STALL[20] TCC_EA_WRREQ_LEVEL[20] TCC_EA_WRREQ_DRAM_CREDIT_STALL[21] TCC_EA_WRREQ_GMI_CREDIT_STALL[21] TCC_EA_WRREQ_IO_CREDIT_STALL[21] TCC_EA_WRREQ_LEVEL[21] TCC_EA_WRREQ_DRAM_CREDIT_STALL[22] TCC_EA_WRREQ_GMI_CREDIT_STALL[22] TCC_EA_WRREQ_IO_CREDIT_STALL[22] TCC_EA_WRREQ_LEVEL[22] TCC_EA_WRREQ_DRAM_CREDIT_STALL[23] TCC_EA_WRREQ_GMI_CREDIT_STALL[23] TCC_EA_WRREQ_IO_CREDIT_STALL[23] TCC_EA_WRREQ_LEVEL[23] TCC_EA_WRREQ_DRAM_CREDIT_STALL[24] TCC_EA_WRREQ_GMI_CREDIT_STALL[24] TCC_EA_WRREQ_IO_CREDIT_STALL[24] TCC_EA_WRREQ_LEVEL[24] TCC_EA_WRREQ_DRAM_CREDIT_STALL[25] TCC_EA_WRREQ_GMI_CREDIT_STALL[25] TCC_EA_WRREQ_IO_CREDIT_STALL[25] TCC_EA_WRREQ_LEVEL[25] TCC_EA_WRREQ_DRAM_CREDIT_STALL[26] TCC_EA_WRREQ_GMI_CREDIT_STALL[26] TCC_EA_WRREQ_IO_CREDIT_STALL[26] TCC_EA_WRREQ_LEVEL[26] TCC_EA_WRREQ_DRAM_CREDIT_STALL[27] TCC_EA_WRREQ_GMI_CREDIT_STALL[27] TCC_EA_WRREQ_IO_CREDIT_STALL[27] TCC_EA_WRREQ_LEVEL[27] TCC_EA_WRREQ_DRAM_CREDIT_STALL[28] TCC_EA_WRREQ_GMI_CREDIT_STALL[28] TCC_EA_WRREQ_IO_CREDIT_STALL[28] TCC_EA_WRREQ_LEVEL[28] TCC_EA_WRREQ_DRAM_CREDIT_STALL[29] TCC_EA_WRREQ_GMI_CREDIT_STALL[29] TCC_EA_WRREQ_IO_CREDIT_STALL[29] TCC_EA_WRREQ_LEVEL[29] TCC_EA_WRREQ_DRAM_CREDIT_STALL[30] TCC_EA_WRREQ_GMI_CREDIT_STALL[30] TCC_EA_WRREQ_IO_CREDIT_STALL[30] TCC_EA_WRREQ_LEVEL[30] TCC_EA_WRREQ_DRAM_CREDIT_STALL[31] TCC_EA_WRREQ_GMI_CREDIT_STALL[31] TCC_EA_WRREQ_IO_CREDIT_STALL[31] TCC_EA_WRREQ_LEVEL[31] + +gpu: +range: 0:2 +kernel: diff --git a/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_17.txt b/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_17.txt new file mode 100644 index 0000000000..1f405e9b61 --- /dev/null +++ b/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_17.txt @@ -0,0 +1,5 @@ +pmc: TCC_HIT[0] TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_HIT[1] TCC_MISS[1] TCC_READ[1] TCC_REQ[1] TCC_HIT[2] TCC_MISS[2] TCC_READ[2] TCC_REQ[2] TCC_HIT[3] TCC_MISS[3] TCC_READ[3] TCC_REQ[3] TCC_HIT[4] TCC_MISS[4] TCC_READ[4] TCC_REQ[4] TCC_HIT[5] TCC_MISS[5] TCC_READ[5] TCC_REQ[5] TCC_HIT[6] TCC_MISS[6] TCC_READ[6] TCC_REQ[6] TCC_HIT[7] TCC_MISS[7] TCC_READ[7] TCC_REQ[7] TCC_HIT[8] TCC_MISS[8] TCC_READ[8] TCC_REQ[8] TCC_HIT[9] TCC_MISS[9] TCC_READ[9] TCC_REQ[9] TCC_HIT[10] TCC_MISS[10] TCC_READ[10] TCC_REQ[10] TCC_HIT[11] TCC_MISS[11] TCC_READ[11] TCC_REQ[11] TCC_HIT[12] TCC_MISS[12] TCC_READ[12] TCC_REQ[12] TCC_HIT[13] TCC_MISS[13] TCC_READ[13] TCC_REQ[13] TCC_HIT[14] TCC_MISS[14] TCC_READ[14] TCC_REQ[14] TCC_HIT[15] TCC_MISS[15] TCC_READ[15] TCC_REQ[15] TCC_HIT[16] TCC_MISS[16] TCC_READ[16] TCC_REQ[16] TCC_HIT[17] TCC_MISS[17] TCC_READ[17] TCC_REQ[17] TCC_HIT[18] TCC_MISS[18] TCC_READ[18] TCC_REQ[18] TCC_HIT[19] TCC_MISS[19] TCC_READ[19] TCC_REQ[19] TCC_HIT[20] TCC_MISS[20] TCC_READ[20] TCC_REQ[20] TCC_HIT[21] TCC_MISS[21] TCC_READ[21] TCC_REQ[21] TCC_HIT[22] TCC_MISS[22] TCC_READ[22] TCC_REQ[22] TCC_HIT[23] TCC_MISS[23] TCC_READ[23] TCC_REQ[23] TCC_HIT[24] TCC_MISS[24] TCC_READ[24] TCC_REQ[24] TCC_HIT[25] TCC_MISS[25] TCC_READ[25] TCC_REQ[25] TCC_HIT[26] TCC_MISS[26] TCC_READ[26] TCC_REQ[26] TCC_HIT[27] TCC_MISS[27] TCC_READ[27] TCC_REQ[27] TCC_HIT[28] TCC_MISS[28] TCC_READ[28] TCC_REQ[28] TCC_HIT[29] TCC_MISS[29] TCC_READ[29] TCC_REQ[29] TCC_HIT[30] TCC_MISS[30] TCC_READ[30] TCC_REQ[30] TCC_HIT[31] TCC_MISS[31] TCC_READ[31] TCC_REQ[31] + +gpu: +range: 0:2 +kernel: diff --git a/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_18.txt b/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_18.txt new file mode 100644 index 0000000000..5ed85db38d --- /dev/null +++ b/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_18.txt @@ -0,0 +1,5 @@ +pmc: TCC_RW_REQ[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_RW_REQ[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_WRITE[1] TCC_RW_REQ[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_WRITE[2] TCC_RW_REQ[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_WRITE[3] TCC_RW_REQ[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_WRITE[4] TCC_RW_REQ[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_WRITE[5] TCC_RW_REQ[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_WRITE[6] TCC_RW_REQ[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_WRITE[7] TCC_RW_REQ[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_WRITE[8] TCC_RW_REQ[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_WRITE[9] TCC_RW_REQ[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_WRITE[10] TCC_RW_REQ[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_WRITE[11] TCC_RW_REQ[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_WRITE[12] TCC_RW_REQ[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_WRITE[13] TCC_RW_REQ[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_WRITE[14] TCC_RW_REQ[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_WRITE[15] TCC_RW_REQ[16] TCC_TOO_MANY_EA_WRREQS_STALL[16] TCC_WRITE[16] TCC_RW_REQ[17] TCC_TOO_MANY_EA_WRREQS_STALL[17] TCC_WRITE[17] TCC_RW_REQ[18] TCC_TOO_MANY_EA_WRREQS_STALL[18] TCC_WRITE[18] TCC_RW_REQ[19] TCC_TOO_MANY_EA_WRREQS_STALL[19] TCC_WRITE[19] TCC_RW_REQ[20] TCC_TOO_MANY_EA_WRREQS_STALL[20] TCC_WRITE[20] TCC_RW_REQ[21] TCC_TOO_MANY_EA_WRREQS_STALL[21] TCC_WRITE[21] TCC_RW_REQ[22] TCC_TOO_MANY_EA_WRREQS_STALL[22] TCC_WRITE[22] TCC_RW_REQ[23] TCC_TOO_MANY_EA_WRREQS_STALL[23] TCC_WRITE[23] TCC_RW_REQ[24] TCC_TOO_MANY_EA_WRREQS_STALL[24] TCC_WRITE[24] TCC_RW_REQ[25] TCC_TOO_MANY_EA_WRREQS_STALL[25] TCC_WRITE[25] TCC_RW_REQ[26] TCC_TOO_MANY_EA_WRREQS_STALL[26] TCC_WRITE[26] TCC_RW_REQ[27] TCC_TOO_MANY_EA_WRREQS_STALL[27] TCC_WRITE[27] TCC_RW_REQ[28] TCC_TOO_MANY_EA_WRREQS_STALL[28] TCC_WRITE[28] TCC_RW_REQ[29] TCC_TOO_MANY_EA_WRREQS_STALL[29] TCC_WRITE[29] TCC_RW_REQ[30] TCC_TOO_MANY_EA_WRREQS_STALL[30] TCC_WRITE[30] TCC_RW_REQ[31] TCC_TOO_MANY_EA_WRREQS_STALL[31] TCC_WRITE[31] + +gpu: +range: 0:2 +kernel: diff --git a/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_2.txt b/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_2.txt new file mode 100644 index 0000000000..0e1ede0d38 --- /dev/null +++ b/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_2.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_MUL_F32 SQ_INSTS_VALU_FMA_F32 SQ_INSTS_VALU_TRANS_F32 SQ_INSTS_VALU_ADD_F64 SQ_INSTS_VALU_MUL_F64 SQ_INSTS_VALU_FMA_F64 SQ_INSTS_VALU_TRANS_F64 SQ_INSTS_VALU_INT32 TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum TA_BUFFER_ATOMIC_WAVEFRONTS_sum TA_BUFFER_TOTAL_CYCLES_sum TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum + +gpu: +range: 0:2 +kernel: diff --git a/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_3.txt b/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_3.txt new file mode 100644 index 0000000000..194bc4f1b3 --- /dev/null +++ b/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_3.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_INT64 SQ_INSTS_SMEM SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum TD_COALESCABLE_WAVEFRONT_sum SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE CPF_CMP_UTCL1_STALL_ON_TRANSLATION TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum + +gpu: +range: 0:2 +kernel: diff --git a/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_4.txt b/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_4.txt new file mode 100644 index 0000000000..a36664fdb5 --- /dev/null +++ b/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_4.txt @@ -0,0 +1,5 @@ +pmc: SQ_WAVE_CYCLES SQ_WAIT_ANY SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_BUSY_CU_CYCLES SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE TCC_EA_WRREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WR_UNCACHED_32B_sum TCC_EA_WRREQ_DRAM_sum + +gpu: +range: 0:2 +kernel: diff --git a/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_5.txt b/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_5.txt new file mode 100644 index 0000000000..5186fc01e6 --- /dev/null +++ b/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_5.txt @@ -0,0 +1,5 @@ +pmc: SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU TCP_TCP_LATENCY_sum TCP_TCC_READ_REQ_LATENCY_sum TCP_TCC_WRITE_REQ_LATENCY_sum TCP_TCC_READ_REQ_sum TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN CPC_ME1_DC0_SPI_BUSY TCC_EA_WRREQ_STALL_sum TCC_EA_RDREQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RD_UNCACHED_32B_sum + +gpu: +range: 0:2 +kernel: diff --git a/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_6.txt b/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_6.txt new file mode 100644 index 0000000000..1258829ee2 --- /dev/null +++ b/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_6.txt @@ -0,0 +1,5 @@ +pmc: SQ_THREAD_CYCLES_VALU SQ_IFETCH SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TCP_TCC_NC_READ_REQ_sum TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN TCC_EA_RDREQ_DRAM_sum TCC_TAG_STALL_sum TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum + +gpu: +range: 0:2 +kernel: diff --git a/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_7.txt b/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_7.txt new file mode 100644 index 0000000000..d41098b7fc --- /dev/null +++ b/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_7.txt @@ -0,0 +1,5 @@ +pmc: SQ_WAVES_LT_32 SQ_WAVES_LT_16 SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TCP_TCC_UC_WRITE_REQ_sum TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR TCC_NORMAL_EVICT_sum TCC_ALL_TC_OP_INV_EVICT_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA_ATOMIC_sum + +gpu: +range: 0:2 +kernel: diff --git a/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_8.txt b/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_8.txt new file mode 100644 index 0000000000..7435d0a135 --- /dev/null +++ b/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_8.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM_NORM SQ_INSTS_MFMA SQ_INSTS_VALU_MFMA_I8 SQ_INSTS_VALU_MFMA_F16 SQ_INSTS_VALU_MFMA_BF16 SQ_INSTS_VALU_MFMA_F32 SQ_INSTS_VALU_MFMA_F64 SQ_VALU_MFMA_BUSY_CYCLES TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TCP_TCC_CC_ATOMIC_REQ_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN TCC_EA_RDREQ_LEVEL_sum TCC_EA_WRREQ_LEVEL_sum TCC_EA_ATOMIC_LEVEL_sum + +gpu: +range: 0:2 +kernel: diff --git a/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_9.txt b/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_9.txt new file mode 100644 index 0000000000..47f3e39ce7 --- /dev/null +++ b/tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_9.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_FLAT_LDS_ONLY SQ_INSTS_VALU_MFMA_MOPS_I8 SQ_INSTS_VALU_MFMA_MOPS_F16 SQ_INSTS_VALU_MFMA_MOPS_BF16 SQ_INSTS_VALU_MFMA_MOPS_F32 SQ_INSTS_VALU_MFMA_MOPS_F64 SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum TCP_PENDING_STALL_CYCLES_sum + +gpu: +range: 0:2 +kernel: diff --git a/tests/workloads/dispatch_0_1/MI200/perfmon/timestamps.txt b/tests/workloads/dispatch_0_1/MI200/perfmon/timestamps.txt new file mode 100644 index 0000000000..0e97681a83 --- /dev/null +++ b/tests/workloads/dispatch_0_1/MI200/perfmon/timestamps.txt @@ -0,0 +1,5 @@ +pmc: + +gpu: +range: 0:2 +kernel: diff --git a/tests/workloads/dispatch_0_1/MI200/pmc_perf.csv b/tests/workloads/dispatch_0_1/MI200/pmc_perf.csv new file mode 100644 index 0000000000..7251d5c895 --- /dev/null +++ b/tests/workloads/dispatch_0_1/MI200/pmc_perf.csv @@ -0,0 +1,3 @@ +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_1,obj_1,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,wave_size_2,obj_2,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_3,obj_3,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_4,obj_4,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_5,obj_5,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_6,obj_6,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_7,obj_7,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_8,obj_8,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_DRAM_sum,TCC_TAG_STALL_sum,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,wave_size_9,obj_9,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_10,obj_10,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,wave_size_11,obj_11,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_12,obj_12,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,TD_COALESCABLE_WAVEFRONT_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_13,obj_13,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_14,obj_14,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_15,obj_15,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_16,obj_16,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_17,obj_17,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_18,obj_18,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,TCC_EA_ATOMIC_LEVEL_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f4a2fab8ec0,0,393216,163840,0,0,0,0,0,18187,0.0,0.0,0.0,32768.0,0.0,0.0,395.0,32768.0,4096,16384,352,28609,2100,0,56.0,8.0,0.0,204428.0,64,0x7f47e819cec0,114688,0,32768,32768,16384,16384,65536,49152,27519246.0,86577439.0,38720502.0,131072.0,0.0,233918.0,0,0,15372,569.0,131086.0,0.0,20.0,64,0x7f7e08b40ec0,1275,121672,0,0,65536,63800,56,1680,64,0x7fc86bf10ec0,0,0,0,224,0,65536,64213,56,64,0x7f0cb3310ec0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,64,0x7f892acf0ec0,6414,0,4096,6385,0,4096,6373,0,4096,6358,0,4096,6385,0,4096,6411,0,4096,6361,0,4096,6376,0,4096,6378,0,4096,6417,0,4096,6382,0,4096,6375,0,4096,6356,0,4096,6390,0,4096,6413,0,4096,6357,0,4096,6349,0,4096,6381,0,4096,6399,0,4096,6394,0,4096,6388,0,4096,6409,0,4096,6399,0,4096,6535,0,4096,6365,0,4096,6354,0,4096,6381,0,4096,6401,0,4096,6395,0,4096,6392,0,4096,6406,0,4096,6403,0,4096,64,0x7f84b8ac4ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13682,19128,8188,551,0,27229,204211.0,0.0,73130.0,131081.0,64,0x7f7f3b020ec0,0,0,0,1060632,13,0,0,1275584,0,0,0,999915,0,0,0,1129505,0,0,0,1096028,0,0,0,1055633,0,0,0,985615,0,0,0,1234953,0,0,0,1032049,0,0,0,1020348,0,0,0,1096685,0,0,0,1088182,0,0,0,1029177,0,0,0,1135761,0,0,0,1135865,0,0,0,1084249,73,0,0,1155288,0,0,0,977888,0,0,0,1141547,15,0,0,1316407,0,0,0,1050000,0,0,0,1195803,0,0,0,1036194,0,0,0,1066018,0,0,0,1046708,0,0,0,1012012,0,0,0,1007663,0,0,0,1164332,26,0,0,1180856,0,0,0,1034428,0,0,0,1023008,0,0,0,1251564,64,0x7f8fb71f8ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131083.0,34785.0,46209.0,19327.0,64,0x7f2960af4ec0,217216,125479,16384,0,16384,16384,32768,49152,27151,27151,1909016.0,1326876.0,3429.0,167194.0,1033159.0,0.0,1319211.0,1021505.0,215505,133626,27151,0,27151,0,868832.0,480116.0,0.0,0.0,64,0x7f7aa37f8ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65551.0,0.0,0.0,0.0,64,0x7fdf23204ec0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4098,0,0,0,4097,0,0,0,4096,0,7,0,4096,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4099,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,64,0x7f8f6cdf8ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,10836,0,819,28703,0,73230.0,131072.0,0.0,65568.0,64,0x7f724b4e8ec0,2253,4096,2253,6349,2274,4096,2274,6370,2315,4097,2316,6412,2279,4096,2279,6375,2244,4096,2244,6340,2300,4096,2300,6396,2258,4096,2258,6354,2285,4096,2285,6381,2286,4096,2286,6382,2253,4096,2253,6349,2271,4096,2271,6367,2261,4096,2261,6357,2281,4096,2281,6377,2246,4096,2246,6342,2300,4096,2300,6396,2262,4096,2262,6358,2263,4096,2263,6359,2288,4097,2289,6385,2283,4097,2284,6380,2277,4096,2277,6373,2303,4096,2303,6399,2239,4096,2239,6335,2290,4096,2290,6386,2469,4098,2471,6567,2297,4096,2297,6393,2265,4096,2265,6361,2287,4096,2287,6383,2287,4098,2289,6385,2283,4096,2283,6379,2305,4096,2305,6401,2245,4096,2245,6341,2290,4096,2290,6386,64,0x7fd8c4d90ec0,0,0,0,0,0,0,168,56,131072.0,131072.0,0.0,980822.0,64,0x7f2bf9774ec0,32768,32768,0,64,0x7f18be1d8ec0,11168674,9922713,901897,344064,1680292,0,0,163840,832.0,515136.0,0.0,524288.0,286559.0,32768.0,529152,0,0,10665,131072.0,131072.0,0.0,131072.0,64,0x7efd92da0ec0,0,1112958,4096,4096,0,1464234,4096,4096,0,1294198,4096,4096,0,1321579,4096,4096,0,1193151,4096,4096,0,1435597,4096,4096,0,1087935,4096,4096,0,1413763,4096,4096,0,1090049,4096,4096,0,1189635,4096,4096,0,1151982,4096,4096,0,1187887,4096,4096,0,1147006,4096,4096,0,1183703,4096,4096,0,1322546,4096,4096,0,1114940,4096,4096,0,1336345,4096,4096,0,1001566,4096,4096,0,1160359,4096,4096,0,1503085,4096,4096,0,1283481,4096,4096,0,1245318,4096,4096,0,1255709,4096,4096,0,1139847,4096,4096,0,1292855,4096,4096,0,1204703,4096,4096,0,1037434,4096,4096,0,1174830,4096,4096,0,1143410,4096,4096,0,1185666,4096,4096,0,1136483,4096,4096,0,1513929,4096,4096,64,0x7f029f7e8ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,39362136.0,34460235.0,0.0,198609512940794,198609512961274 +1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f4a2fab8ec0,0,393216,163840,0,0,0,0,0,28273,0.0,0.0,0.0,32768.0,0.0,0.0,264.0,32768.0,4096,16384,302,37505,2061,0,56.0,0.0,0.0,200647.0,64,0x7f47e819cec0,114688,0,32768,32768,16384,16384,65536,49152,58351689.0,199740715.0,47356153.0,131072.0,0.0,608661.0,0,0,25624,25352.0,131085.0,0.0,24.0,64,0x7f7e08b40ec0,0,211412,0,0,65536,63800,56,1680,64,0x7fc86bf10ec0,0,0,0,56,0,65536,65536,0,64,0x7f0cb3310ec0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,64,0x7f892acf0ec0,6290,0,4096,6278,0,4096,6285,0,4096,6258,0,4096,6260,0,4096,6250,0,4096,6296,0,4096,6269,0,4096,6274,0,4096,6289,0,4096,6279,0,4096,6286,0,4096,6262,0,4096,6263,0,4096,6252,0,4096,6299,0,4096,6278,0,4096,6277,0,4096,6276,0,4096,6286,0,4096,6254,0,4096,6236,0,4096,6275,0,4096,6274,0,4096,6274,0,4096,6281,0,4096,6275,0,4096,6278,0,4096,6284,0,4096,6252,0,4096,6246,0,4096,6272,0,4096,64,0x7f84b8ac4ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,35266,28104,9579,2829,0,41038,200795.0,0.0,69712.0,131083.0,64,0x7f7f3b020ec0,138,0,0,1807628,0,0,0,1827498,165,0,0,2227358,181,0,0,2120664,0,0,0,1497979,912,0,0,2223527,0,0,0,1933367,176,0,0,2159154,0,0,0,1909110,236,0,0,1643335,0,0,0,1638015,501,0,0,1947456,325,0,0,1837027,0,0,0,1461520,32,0,0,1944737,0,0,0,1874947,0,0,0,1657958,22,0,0,2204591,0,0,0,1540041,399,0,0,1860741,146,0,0,1686425,143,0,0,2245703,0,0,0,1437395,0,0,0,1645404,0,0,0,1619523,0,0,0,1641243,521,0,0,2152628,0,0,0,1950767,64,0,0,1549545,150,0,0,1695926,202,0,0,1685968,0,0,0,1777436,64,0x7f8fb71f8ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131084.0,92912.0,45614.0,0.0,64,0x7f2960af4ec0,331880,223650,16384,0,16384,16384,32768,49152,41484,41484,3184756.0,2511449.0,4735.0,382351.0,1781220.0,0.0,2499517.0,2190353.0,331872,232947,41484,0,41484,0,1327488.0,796855.0,0.0,0.0,64,0x7f7aa37f8ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65550.0,0.0,0.0,0.0,64,0x7fdf23204ec0,4096,0,468,0,4096,0,607,0,4096,0,1338,0,4096,0,532,0,4096,0,17,0,4096,0,111,0,4097,0,422,0,4096,0,1350,0,4096,0,1020,0,4096,0,226,0,4096,0,492,0,4097,0,1202,0,4096,0,997,0,4096,0,454,0,4098,0,1599,0,4097,0,1215,0,4096,0,227,0,4096,0,536,0,4097,0,244,0,4096,0,629,0,4096,0,305,0,4096,0,667,0,4096,0,315,0,4096,0,1196,0,4096,0,219,0,4096,0,956,0,4096,0,223,0,4097,0,141,0,4096,0,318,0,4098,0,133,0,4096,0,43,0,4096,0,10,0,64,0x7f8f6cdf8ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,15530,0,819,36227,0,69653.0,131072.0,0.0,45684.0,64,0x7f724b4e8ec0,2158,4097,2159,6255,2151,4096,2151,6247,2265,4097,2266,6362,2175,4096,2175,6271,2158,4096,2158,6254,2161,4097,2162,6258,2165,4096,2165,6261,2152,4096,2152,6248,2154,4096,2154,6250,2160,4097,2161,6257,2154,4096,2154,6250,2210,4096,2210,6306,2177,4096,2177,6273,2158,4096,2158,6254,2159,4096,2159,6255,2169,4096,2169,6265,2170,4096,2170,6266,2137,4097,2138,6234,2153,4098,2155,6251,2151,4096,2151,6247,2158,4096,2158,6254,2203,4096,2203,6299,2164,4096,2164,6260,2164,4096,2164,6260,2170,4096,2170,6266,2171,4096,2171,6267,2137,4096,2137,6233,2152,4098,2154,6250,2151,4096,2151,6247,2158,4096,2158,6254,2205,4096,2205,6301,2169,4096,2169,6265,64,0x7fd8c4d90ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2006123.0,64,0x7f2bf9774ec0,32768,32768,0,64,0x7f18be1d8ec0,19514784,18251139,919581,344064,2815906,0,0,163840,832.0,515136.0,0.0,524288.0,603815.0,32768.0,1013862,0,0,13766,91363.0,91363.0,0.0,91363.0,64,0x7efd92da0ec0,0,3426461,2852,2852,0,5196063,2894,2894,0,2808279,2860,2860,0,4040483,2856,2856,0,3772796,2870,2870,0,4040365,2838,2838,0,2840661,2842,2842,0,4380697,2792,2792,0,3625585,2792,2792,0,3694624,2852,2852,0,3192613,2896,2896,0,3174666,2860,2860,0,3270470,2858,2858,0,3538463,2876,2876,0,4660296,2836,2836,0,3792854,2840,2840,0,3855704,2816,2816,0,3029733,2820,2820,0,3888200,2864,2864,0,3951296,2860,2860,0,3411540,2844,2844,0,3724081,2872,2872,0,3666285,2832,2832,0,5354856,2828,2828,0,4530089,2828,2828,0,3023717,2816,2816,0,4697570,2814,2814,0,3849095,2864,2864,0,3167936,2860,2860,0,2773351,2844,2844,0,3706712,2876,2876,0,4062111,2830,2830,64,0x7f029f7e8ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,120455321.0,60544388.0,0.0,198609513046074,198609513062554 diff --git a/tests/workloads/dispatch_0_1/MI200/roofline.csv b/tests/workloads/dispatch_0_1/MI200/roofline.csv new file mode 100644 index 0000000000..96bfb308a8 --- /dev/null +++ b/tests/workloads/dispatch_0_1/MI200/roofline.csv @@ -0,0 +1,5 @@ +device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh +0,1389.0242,1388.5444,1389.5039,5014.0776,5010.7217,5017.4336,9224.2939,9223.6963,9224.8916,18054.982,18054.016,18055.949,20935.725,20875.342,20996.107,20261.689,20260.873,20262.506,170384.81,170381.8,170387.83,164856.69,164853.22,164860.16,41417.711,41417.168,41418.254,41477.18,41476.625,41477.734,166336.23,165848.91,166823.56 +1,1388.8065,1388.214,1389.399,5026.9512,5024.9131,5028.9893,9232.082,9231.4229,9232.7412,18087.27,18083.492,18091.047,20973.012,20906.764,21039.26,20291.207,20290.643,20291.771,170819.16,170814.88,170823.44,165083.95,165080.05,165087.86,41472.68,41471.848,41473.512,41536.34,41535.246,41537.434,166839.25,166835.88,166842.62 +2,1389.42,1388.8044,1390.0356,5035.7383,5033.4888,5037.9878,9261.5166,9260.8115,9262.2217,18109.811,18108.705,18110.916,21049.439,21049.039,21049.84,20352.191,20351.469,20352.914,171119.62,171114.88,171124.38,165490.05,165485.94,165494.16,41580.387,41579.566,41581.207,41639.574,41638.555,41640.594,166942.73,166357.73,167527.73 +3,1388.8628,1388.2523,1389.4733,5032.647,5031.3843,5033.9097,9240.2979,9239.7139,9240.8818,18025.895,18022.496,18029.293,21031.047,21030.645,21031.449,20311.537,20310.795,20312.279,171032.64,171028.23,171037.05,165246.34,165241.59,165251.09,41443.762,41292.008,41595.516,41583.09,41582.52,41583.66,167018.66,167016.94,167020.38 diff --git a/tests/workloads/dispatch_0_1/MI200/sysinfo.csv b/tests/workloads/dispatch_0_1/MI200/sysinfo.csv new file mode 100644 index 0000000000..270672d1e6 --- /dev/null +++ b/tests/workloads/dispatch_0_1/MI200/sysinfo.csv @@ -0,0 +1,2 @@ +workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd +dispatch_0_1,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 02:21:03 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/dispatch_0_1/MI200/timestamps.csv b/tests/workloads/dispatch_0_1/MI200/timestamps.csv new file mode 100644 index 0000000000..bd1ea2b4cf --- /dev/null +++ b/tests/workloads/dispatch_0_1/MI200/timestamps.csv @@ -0,0 +1,3 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,315904,315904,1048576,256,0,0,8,0,16,64,0x0,0x7fc0d1ec4ec0,198609512911564,198609512940794,198609512961274,198609512972029 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,315904,315904,1048576,256,0,0,8,0,16,64,0x0,0x7fc0d1ec4ec0,198609512972319,198609513046074,198609513062554,198609513063973 diff --git a/tests/workloads/dispatch_2/MI100/SQ_IFETCH_LEVEL.csv b/tests/workloads/dispatch_2/MI100/SQ_IFETCH_LEVEL.csv index 9b61eedc4c..c2258fd944 100644 --- a/tests/workloads/dispatch_2/MI100/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/dispatch_2/MI100/SQ_IFETCH_LEVEL.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2845401,2845401,1048576,256,0,0,8,8,16,64,0x0,0x7fcadc3dce80,38565,38565,16384,65536,8226,1048620,2187796746637903,2187794678392809,2187794678412009,2187796754235446 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,146368,146368,1048576,256,0,0,8,8,16,64,0x0,0x7f9f83152e80,38682,38682,16384,65536,8172,1048640,194190802937007,194203146753468,194203146772188,194190810926274 diff --git a/tests/workloads/dispatch_2/MI100/SQ_INST_LEVEL_LDS.csv b/tests/workloads/dispatch_2/MI100/SQ_INST_LEVEL_LDS.csv index ca9789ad7b..2c3b7f4e8b 100644 --- a/tests/workloads/dispatch_2/MI100/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/dispatch_2/MI100/SQ_INST_LEVEL_LDS.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2843019,2843019,1048576,256,0,0,8,8,16,64,0x0,0x7febe3572e80,0,0,0,2187790583277714,2187794678392809,2187794678412009,2187790590832306 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,146556,146556,1048576,256,0,0,8,8,16,64,0x0,0x7f9214dece80,0,0,0,194191303483541,194203146753468,194203146772188,194191311114590 diff --git a/tests/workloads/dispatch_2/MI100/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/dispatch_2/MI100/SQ_INST_LEVEL_SMEM.csv index 2b56f4a1af..26562bef9d 100644 --- a/tests/workloads/dispatch_2/MI100/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/dispatch_2/MI100/SQ_INST_LEVEL_SMEM.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2843570,2843570,1048576,256,0,0,8,8,16,64,0x0,0x7f59f3376e80,65536,89910,11518096,2187791957065822,2187794678392809,2187794678412009,2187791964652224 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,146743,146743,1048576,256,0,0,8,8,16,64,0x0,0x7fdb01522e80,65536,83590,10693168,194191799460013,194203146753468,194203146772188,194191807333481 diff --git a/tests/workloads/dispatch_2/MI100/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/dispatch_2/MI100/SQ_INST_LEVEL_VMEM.csv index 6b32130e81..ad075374a8 100644 --- a/tests/workloads/dispatch_2/MI100/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/dispatch_2/MI100/SQ_INST_LEVEL_VMEM.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2842271,2842271,1048576,256,0,0,8,8,16,64,0x0,0x7fd8069d0e80,32768,639748,81911640,2187788268757096,2187794678392809,2187794678412009,2187788276577677 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,146928,146928,1048576,256,0,0,8,8,16,64,0x0,0x7fe5463eae80,32768,663275,84884088,194192296631898,194203146753468,194203146772188,194192304449200 diff --git a/tests/workloads/dispatch_2/MI100/SQ_LEVEL_WAVES.csv b/tests/workloads/dispatch_2/MI100/SQ_LEVEL_WAVES.csv index cc6264ab38..0b70326ee0 100644 --- a/tests/workloads/dispatch_2/MI100/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/dispatch_2/MI100/SQ_LEVEL_WAVES.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2844302,2844302,1048576,256,0,0,8,8,16,64,0x0,0x7f98b83bee80,39353,39353,12306,314832,16384,22386567,216458,0,90050164,2187793773743550,2187794678392809,2187794678412009,2187793781232750 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,147115,147115,1048576,256,0,0,8,8,16,64,0x0,0x7fd659050e80,38457,38457,11850,307664,16384,22285112,212347,0,89633484,194192793995967,194203146753468,194203146772188,194192801697780 diff --git a/tests/workloads/dispatch_2/MI100/pmc_dispatch_info.csv b/tests/workloads/dispatch_2/MI100/pmc_dispatch_info.csv new file mode 100644 index 0000000000..16e52923f6 --- /dev/null +++ b/tests/workloads/dispatch_2/MI100/pmc_dispatch_info.csv @@ -0,0 +1,2 @@ +Dispatch_ID,Kernel_Name,GPU_ID +1,"vecCopy(double*, double*, double*, int, int) ",2 diff --git a/tests/workloads/dispatch_2/MI100/pmc_perf.csv b/tests/workloads/dispatch_2/MI100/pmc_perf.csv index 60c0a0dff9..e3e986509f 100644 --- a/tests/workloads/dispatch_2/MI100/pmc_perf.csv +++ b/tests/workloads/dispatch_2/MI100/pmc_perf.csv @@ -1,2 +1,2 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_1,obj_1,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_2,obj_2,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_3,obj_3,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_4,obj_4,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_5,obj_5,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_6,obj_6,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_7,obj_7,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_8,obj_8,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_9,obj_9,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_10,obj_10,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_11,obj_11,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_12,obj_12,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_13,obj_13,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_14,obj_14,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_15,obj_15,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_16,obj_16,TCC_EA_ATOMIC_LEVEL_sum,Start_Timestamp,End_Timestamp -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f8236e3ce80,32768,0,0,0,16384,16384,393216,22241342,0.0,524288.0,0.0,524288.0,719375.0,32768.0,0,0,0,12013,86583.0,86583.0,0.0,86583.0,64,0x7fac5c1fce80,136682,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13329,29713,7604,1462,0,36927,262194.0,0.0,47.0,262147.0,64,0x7fc0c15ece80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,56341.0,126058.0,64,0x7ff9bc0e4e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,38044,0,131120.0,131072.0,0.0,86505.0,64,0x7f5afe336e80,0,0,48,0,65536,65536,0,0,28348,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,436,37902,1745,0,48.0,0.0,0.0,262144.0,64,0x7f0614fdce80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fde1eda0e80,131072.0,131072.0,0.0,2611243.0,0.0,0.0,127446147.0,47598095.0,64,0x7f0a74f6ee80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131073.0,0.0,0.0,131072.0,64,0x7f93da470e80,0,4733576,2698,2698,0,4950371,2718,2718,0,3343062,2660,2660,0,4991429,2702,2702,0,3814454,2673,2673,0,4827291,2716,2716,0,3802294,2710,2710,0,4550844,2712,2712,0,4653501,2690,2690,0,4533577,2692,2692,0,3784597,2692,2692,0,4495445,2730,2730,0,4357469,2693,2693,0,3624396,2680,2680,0,4607537,2694,2694,0,3314040,2680,2680,0,4364060,2666,2666,0,4878204,2726,2726,0,3991236,2666,2666,0,4773393,2712,2712,0,3896694,2704,2704,0,3887271,2741,2741,0,4288052,2676,2676,0,4492545,2690,2690,0,3336323,2690,2690,0,4847770,2682,2682,0,4614927,2722,2722,0,4009045,2708,2708,0,3916086,2706,2706,0,4042568,2693,2693,0,4519454,2698,2698,0,3888336,2682,2682,64,0x7fd8e037ce80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86550.0,0.0,131110.0,0.0,64,0x7f82c9fdce80,309840,214878,3145099,16384,22497534,0,48,0,38729,38729,3513076.0,2970065.0,5756.0,1077804.0,1946413.0,0.0,2960237.0,2648110.0,308319,222962,38729,0,38729,0,1239328.0,804950.0,0.0,0.0,64,0x7fab341e8e80,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,64,0x7f29c3e04e80,4137,0,0,1636048,2067,0,0,1435641,1065,0,0,1297932,1785,0,0,1428162,1967,0,0,1530501,2415,0,0,1523447,808,0,0,1393467,796,0,0,1285312,1258,0,0,1320082,2453,0,0,1403696,1134,0,0,1375485,1140,0,0,1285513,3047,0,0,1572917,1062,0,0,1327053,1736,0,0,1478458,1681,0,0,1487434,2035,0,0,1460776,2120,0,0,1508369,2571,0,0,1511321,1734,0,0,1389877,420,0,0,1197709,901,0,0,1261289,3420,0,0,1673728,5642,0,0,1775752,3028,0,0,1583374,1358,0,0,1382535,3126,0,0,1626562,1167,0,0,1332831,1751,0,0,1448080,5578,0,0,1842878,1881,0,0,1446346,1003,0,0,1339746,64,0x7f7bf4c16e80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,64,0x7f3e474d6e80,224643,360448,163840,0,0,180224,114688,0,71268791.0,213987650.0,80373920.0,131072.0,0.0,577044.0,0,0,23408,78640.0,0.0,0.0,78640.0,64,0x7fcaf3f3ce80,4096,0,1506,0,4096,0,515,0,4096,0,4904,0,4096,0,3332,0,4096,0,2278,0,4096,0,116,0,4096,0,1952,0,4096,0,715,0,4096,0,1612,0,4096,0,135,0,4096,0,2300,0,4096,0,2405,0,4097,0,152,0,4096,0,2199,0,4096,0,3233,0,4096,0,0,0,4096,0,2088,0,4096,0,4368,0,4096,0,3726,0,4096,0,1080,0,4096,0,661,0,4096,0,6546,0,4096,0,2081,0,4096,0,0,0,4096,0,2265,0,4096,0,6117,0,4096,0,376,0,4096,0,133,0,4096,0,1164,0,4096,0,1080,0,4096,0,509,0,4096,0,892,0,64,0x7fedc8430e80,0.0,2187794678392809,2187794678412009 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_1,obj_1,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_2,obj_2,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_3,obj_3,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_4,obj_4,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_5,obj_5,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_6,obj_6,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_7,obj_7,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_8,obj_8,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_9,obj_9,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_10,obj_10,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_11,obj_11,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_12,obj_12,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_13,obj_13,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_14,obj_14,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_15,obj_15,TCC_EA_ATOMIC_LEVEL_sum,wave_size_16,obj_16,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],Start_Timestamp,End_Timestamp +1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f9d2e336e80,32768,0,0,0,16384,16384,393216,22258379,0.0,524288.0,0.0,524288.0,756880.0,32768.0,0,0,0,12033,86279.0,86279.0,0.0,86279.0,64,0x7f1253ca8e80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f20f41ace80,267240,360448,163840,0,0,180224,114688,0,73309661.0,192651152.0,76300063.0,131072.0,0.0,600187.0,0,0,23809,55275.0,0.0,0.0,55275.0,64,0x7f50bc202e80,317960,216097,3133375,16384,22276538,0,48,0,39744,39744,3531086.0,2977320.0,6696.0,1072822.0,1885794.0,0.0,2967310.0,2654791.0,316247,224150,39744,0,39744,0,1271808.0,808935.0,0.0,0.0,64,0x7f8b06c84e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131073.0,0.0,0.0,131072.0,64,0x7f0c123c2e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,38480,0,131126.0,131072.0,0.0,86403.0,64,0x7f256fbb6e80,131072.0,131072.0,0.0,2611512.0,0.0,0.0,131034005.0,46911848.0,64,0x7fb68d76ce80,0,0,48,0,65536,65536,0,0,29116,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,435,38798,1777,0,48.0,0.0,0.0,262144.0,64,0x7f55af786e80,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,64,0x7fdc0dd62e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,70561.0,138571.0,64,0x7f87fb1dce80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f4849b32e80,4096,0,639,0,4096,0,1990,0,4096,0,4342,0,4096,0,1328,0,4096,0,674,0,4096,0,4650,0,4096,0,1637,0,4096,0,4116,0,4096,0,4828,0,4096,0,400,0,4096,0,650,0,4096,0,2785,0,4096,0,4298,0,4096,0,56,0,4096,0,1478,0,4096,0,127,0,4096,0,7689,0,4096,0,4903,0,4096,0,1327,0,4096,0,169,0,4096,0,163,0,4096,0,510,0,4096,0,1418,0,4096,0,0,0,4096,0,1185,0,4096,0,6101,0,4096,0,1122,0,4096,0,758,0,4097,0,716,0,4096,0,3010,0,4096,0,1700,0,4096,0,2383,0,64,0x7f4fa15a6e80,0,4894410,2726,2726,0,3735599,2716,2716,0,3847119,2690,2690,0,4285804,2710,2710,0,3743691,2698,2698,0,4600312,2716,2716,0,4220009,2703,2703,0,3217035,2692,2692,0,5324435,2714,2714,0,4578757,2684,2684,0,3933091,2704,2704,0,4572521,2712,2712,0,4129359,2728,2728,0,4140789,2690,2690,0,4354666,2692,2692,0,3454426,2682,2682,0,4292049,2700,2700,0,4759631,2700,2700,0,4778717,2680,2680,0,2982741,2692,2692,0,3944175,2715,2715,0,4022589,2729,2729,0,5063179,2689,2689,0,3075216,2664,2664,0,4223611,2712,2712,0,3661037,2672,2672,0,2900795,2730,2730,0,2757186,2688,2688,0,4017619,2724,2724,0,3787118,2701,2701,0,3161261,2718,2718,0,2854284,2660,2660,64,0x7f28be10ce80,116093,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,12455,28839,7554,588,0,36789,262192.0,0.0,47.0,262145.0,64,0x7f2ca5c2ae80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86438.0,0.0,131110.0,0.0,64,0x7f8b4e3aae80,0.0,64,0x7f9ba8d88e80,2018,0,0,1494090,2904,0,0,1590602,1370,0,0,1398780,1727,0,0,1448082,1082,0,0,1376646,3171,0,0,1646816,634,0,0,1309077,1517,0,0,1365906,1022,0,0,1270748,1614,0,0,1462726,2741,0,0,1528453,1935,0,0,1498464,2356,0,0,1539245,3489,0,0,1657733,2074,0,0,1507276,783,0,0,1292359,1769,0,0,1414879,805,0,0,1261008,2331,0,0,1535474,1930,0,0,1423285,674,0,0,1275431,2328,0,0,1465495,2186,0,0,1517192,6454,0,0,1801469,2928,0,0,1522074,1410,0,0,1385807,1189,0,0,1385724,1781,0,0,1513774,1289,0,0,1421567,6379,0,0,1868219,2519,0,0,1507660,1482,0,0,1408059,194203146753468,194203146772188 diff --git a/tests/workloads/dispatch_2/MI100/sysinfo.csv b/tests/workloads/dispatch_2/MI100/sysinfo.csv index b67f121187..6f9566da38 100644 --- a/tests/workloads/dispatch_2/MI100/sysinfo.csv +++ b/tests/workloads/dispatch_2/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -dispatch_2,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Fri Mar 1 16:44:58 2024 (CST),1,t006-003.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651240,,5.7.1-98,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +dispatch_2,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 07 Mar 2024 01:07:35 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/dispatch_2/MI100/timestamps.csv b/tests/workloads/dispatch_2/MI100/timestamps.csv index 753723208f..81c565256e 100644 --- a/tests/workloads/dispatch_2/MI100/timestamps.csv +++ b/tests/workloads/dispatch_2/MI100/timestamps.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,2844668,2844668,1048576,256,0,0,8,8,16,64,0x0,0x7f3fa4688e80,2187794678379498,2187794678392809,2187794678412009,2187794678425044 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,150477,150477,1048576,256,0,0,8,8,16,64,0x0,0x7fb6015c6e80,194203146739938,194203146753468,194203146772188,194203146784432 diff --git a/tests/workloads/dispatch_2/MI200/SQ_IFETCH_LEVEL.csv b/tests/workloads/dispatch_2/MI200/SQ_IFETCH_LEVEL.csv new file mode 100644 index 0000000000..bb544dd5e4 --- /dev/null +++ b/tests/workloads/dispatch_2/MI200/SQ_IFETCH_LEVEL.csv @@ -0,0 +1,2 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,301053,301053,1048576,256,0,0,8,0,16,64,0x0,0x7f90d6404ec0,22880,22880,16384,65536,9554,1048680,198381671765204,198394440082212,198394440098052,198381687536921 diff --git a/tests/workloads/dispatch_2/MI200/SQ_INST_LEVEL_LDS.csv b/tests/workloads/dispatch_2/MI200/SQ_INST_LEVEL_LDS.csv new file mode 100644 index 0000000000..e1aaf98f5f --- /dev/null +++ b/tests/workloads/dispatch_2/MI200/SQ_INST_LEVEL_LDS.csv @@ -0,0 +1,2 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,301243,301243,1048576,256,0,0,8,0,16,64,0x0,0x7f58b1578ec0,0,0,0,198382158268734,198394440082212,198394440098052,198382174223788 diff --git a/tests/workloads/dispatch_2/MI200/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/dispatch_2/MI200/SQ_INST_LEVEL_SMEM.csv new file mode 100644 index 0000000000..d94c75d3ae --- /dev/null +++ b/tests/workloads/dispatch_2/MI200/SQ_INST_LEVEL_SMEM.csv @@ -0,0 +1,2 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,301429,301429,1048576,256,0,0,8,0,16,64,0x0,0x7f7811c08ec0,65536,72322,8038296,198382637273097,198394440082212,198394440098052,198382653420274 diff --git a/tests/workloads/dispatch_2/MI200/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/dispatch_2/MI200/SQ_INST_LEVEL_VMEM.csv new file mode 100644 index 0000000000..fe95af784a --- /dev/null +++ b/tests/workloads/dispatch_2/MI200/SQ_INST_LEVEL_VMEM.csv @@ -0,0 +1,2 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,301631,301631,1048576,256,0,0,8,0,16,64,0x0,0x7f936d250ec0,32768,283635,31759140,198383117083666,198394440082212,198394440098052,198383132862947 diff --git a/tests/workloads/dispatch_2/MI200/SQ_LEVEL_WAVES.csv b/tests/workloads/dispatch_2/MI200/SQ_LEVEL_WAVES.csv new file mode 100644 index 0000000000..a800b25c24 --- /dev/null +++ b/tests/workloads/dispatch_2/MI200/SQ_LEVEL_WAVES.csv @@ -0,0 +1,2 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,301833,301833,1048576,256,0,0,8,0,16,64,0x0,0x7fceeebd8ec0,22549,22549,8397,180400,16384,8919528,109698,0,36178612,198383600367705,198394440082212,198394440098052,198383616480267 diff --git a/tests/workloads/dispatch_2/MI200/perfmon/SQ_IFETCH_LEVEL.txt b/tests/workloads/dispatch_2/MI200/perfmon/SQ_IFETCH_LEVEL.txt new file mode 100644 index 0000000000..5faaf09cd3 --- /dev/null +++ b/tests/workloads/dispatch_2/MI200/perfmon/SQ_IFETCH_LEVEL.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES + +gpu: +range: 1 +kernel: diff --git a/tests/workloads/dispatch_2/MI200/perfmon/SQ_INST_LEVEL_LDS.txt b/tests/workloads/dispatch_2/MI200/perfmon/SQ_INST_LEVEL_LDS.txt new file mode 100644 index 0000000000..a26158b25b --- /dev/null +++ b/tests/workloads/dispatch_2/MI200/perfmon/SQ_INST_LEVEL_LDS.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES + +gpu: +range: 1 +kernel: diff --git a/tests/workloads/dispatch_2/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt b/tests/workloads/dispatch_2/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt new file mode 100644 index 0000000000..fb7520df1b --- /dev/null +++ b/tests/workloads/dispatch_2/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: 1 +kernel: diff --git a/tests/workloads/dispatch_2/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt b/tests/workloads/dispatch_2/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt new file mode 100644 index 0000000000..32d63ae2d9 --- /dev/null +++ b/tests/workloads/dispatch_2/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: 1 +kernel: diff --git a/tests/workloads/dispatch_2/MI200/perfmon/SQ_LEVEL_WAVES.txt b/tests/workloads/dispatch_2/MI200/perfmon/SQ_LEVEL_WAVES.txt new file mode 100644 index 0000000000..48c0dcc3d7 --- /dev/null +++ b/tests/workloads/dispatch_2/MI200/perfmon/SQ_LEVEL_WAVES.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES + +gpu: +range: 1 +kernel: diff --git a/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_0.txt b/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_0.txt new file mode 100644 index 0000000000..e81382e4b5 --- /dev/null +++ b/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_0.txt @@ -0,0 +1,5 @@ +pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES SQ_INSTS_VALU_CVT SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU GRBM_COUNT GRBM_GUI_ACTIVE TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum TA_TA_BUSY_sum TA_BUFFER_WAVEFRONTS_sum TD_TD_BUSY_sum TD_TC_STALL_sum SPI_CSN_WINDOW_VALID SPI_CSN_BUSY CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum + +gpu: +range: 1 +kernel: diff --git a/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_1.txt b/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_1.txt new file mode 100644 index 0000000000..88152a9b83 --- /dev/null +++ b/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_1.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VSKIPPED SQ_INSTS SQ_INSTS_VALU SQ_INSTS_VALU_ADD_F16 SQ_INSTS_VALU_MUL_F16 SQ_INSTS_VALU_FMA_F16 SQ_INSTS_VALU_TRANS_F16 SQ_INSTS_VALU_ADD_F32 GRBM_SPI_BUSY TCP_READ_TAGCONFLICT_STALL_CYCLES_sum TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum TCP_TA_TCP_STATE_READ_sum TA_BUFFER_READ_WAVEFRONTS_sum TA_BUFFER_WRITE_WAVEFRONTS_sum TD_SPI_STALL_sum TD_LOAD_WAVEFRONT_sum SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum + +gpu: +range: 1 +kernel: diff --git a/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_10.txt b/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_10.txt new file mode 100644 index 0000000000..bbe0315916 --- /dev/null +++ b/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_10.txt @@ -0,0 +1,5 @@ +pmc: SQC_TC_DATA_WRITE_REQ SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES + +gpu: +range: 1 +kernel: diff --git a/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_11.txt b/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_11.txt new file mode 100644 index 0000000000..b0b1b4a09d --- /dev/null +++ b/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_11.txt @@ -0,0 +1,5 @@ +pmc: SQC_ICACHE_MISSES_DUPLICATE SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE + +gpu: +range: 1 +kernel: diff --git a/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_12.txt b/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_12.txt new file mode 100644 index 0000000000..c557cf4640 --- /dev/null +++ b/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_12.txt @@ -0,0 +1,5 @@ +pmc: SQC_DCACHE_REQ_READ_1 SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 + +gpu: +range: 1 +kernel: diff --git a/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_13.txt b/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_13.txt new file mode 100644 index 0000000000..54a74f1d8f --- /dev/null +++ b/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_13.txt @@ -0,0 +1,5 @@ +pmc: TCC_ATOMIC[0] TCC_CYCLE[0] TCC_EA_ATOMIC[0] TCC_EA_ATOMIC_LEVEL[0] TCC_ATOMIC[1] TCC_CYCLE[1] TCC_EA_ATOMIC[1] TCC_EA_ATOMIC_LEVEL[1] TCC_ATOMIC[2] TCC_CYCLE[2] TCC_EA_ATOMIC[2] TCC_EA_ATOMIC_LEVEL[2] TCC_ATOMIC[3] TCC_CYCLE[3] TCC_EA_ATOMIC[3] TCC_EA_ATOMIC_LEVEL[3] TCC_ATOMIC[4] TCC_CYCLE[4] TCC_EA_ATOMIC[4] TCC_EA_ATOMIC_LEVEL[4] TCC_ATOMIC[5] TCC_CYCLE[5] TCC_EA_ATOMIC[5] TCC_EA_ATOMIC_LEVEL[5] TCC_ATOMIC[6] TCC_CYCLE[6] TCC_EA_ATOMIC[6] TCC_EA_ATOMIC_LEVEL[6] TCC_ATOMIC[7] TCC_CYCLE[7] TCC_EA_ATOMIC[7] TCC_EA_ATOMIC_LEVEL[7] TCC_ATOMIC[8] TCC_CYCLE[8] TCC_EA_ATOMIC[8] TCC_EA_ATOMIC_LEVEL[8] TCC_ATOMIC[9] TCC_CYCLE[9] TCC_EA_ATOMIC[9] TCC_EA_ATOMIC_LEVEL[9] TCC_ATOMIC[10] TCC_CYCLE[10] TCC_EA_ATOMIC[10] TCC_EA_ATOMIC_LEVEL[10] TCC_ATOMIC[11] TCC_CYCLE[11] TCC_EA_ATOMIC[11] TCC_EA_ATOMIC_LEVEL[11] TCC_ATOMIC[12] TCC_CYCLE[12] TCC_EA_ATOMIC[12] TCC_EA_ATOMIC_LEVEL[12] TCC_ATOMIC[13] TCC_CYCLE[13] TCC_EA_ATOMIC[13] TCC_EA_ATOMIC_LEVEL[13] TCC_ATOMIC[14] TCC_CYCLE[14] TCC_EA_ATOMIC[14] TCC_EA_ATOMIC_LEVEL[14] TCC_ATOMIC[15] TCC_CYCLE[15] TCC_EA_ATOMIC[15] TCC_EA_ATOMIC_LEVEL[15] TCC_ATOMIC[16] TCC_CYCLE[16] TCC_EA_ATOMIC[16] TCC_EA_ATOMIC_LEVEL[16] TCC_ATOMIC[17] TCC_CYCLE[17] TCC_EA_ATOMIC[17] TCC_EA_ATOMIC_LEVEL[17] TCC_ATOMIC[18] TCC_CYCLE[18] TCC_EA_ATOMIC[18] TCC_EA_ATOMIC_LEVEL[18] TCC_ATOMIC[19] TCC_CYCLE[19] TCC_EA_ATOMIC[19] TCC_EA_ATOMIC_LEVEL[19] TCC_ATOMIC[20] TCC_CYCLE[20] TCC_EA_ATOMIC[20] TCC_EA_ATOMIC_LEVEL[20] TCC_ATOMIC[21] TCC_CYCLE[21] TCC_EA_ATOMIC[21] TCC_EA_ATOMIC_LEVEL[21] TCC_ATOMIC[22] TCC_CYCLE[22] TCC_EA_ATOMIC[22] TCC_EA_ATOMIC_LEVEL[22] TCC_ATOMIC[23] TCC_CYCLE[23] TCC_EA_ATOMIC[23] TCC_EA_ATOMIC_LEVEL[23] TCC_ATOMIC[24] TCC_CYCLE[24] TCC_EA_ATOMIC[24] TCC_EA_ATOMIC_LEVEL[24] TCC_ATOMIC[25] TCC_CYCLE[25] TCC_EA_ATOMIC[25] TCC_EA_ATOMIC_LEVEL[25] TCC_ATOMIC[26] TCC_CYCLE[26] TCC_EA_ATOMIC[26] TCC_EA_ATOMIC_LEVEL[26] TCC_ATOMIC[27] TCC_CYCLE[27] TCC_EA_ATOMIC[27] TCC_EA_ATOMIC_LEVEL[27] TCC_ATOMIC[28] TCC_CYCLE[28] TCC_EA_ATOMIC[28] TCC_EA_ATOMIC_LEVEL[28] TCC_ATOMIC[29] TCC_CYCLE[29] TCC_EA_ATOMIC[29] TCC_EA_ATOMIC_LEVEL[29] TCC_ATOMIC[30] TCC_CYCLE[30] TCC_EA_ATOMIC[30] TCC_EA_ATOMIC_LEVEL[30] TCC_ATOMIC[31] TCC_CYCLE[31] TCC_EA_ATOMIC[31] TCC_EA_ATOMIC_LEVEL[31] + +gpu: +range: 1 +kernel: diff --git a/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_14.txt b/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_14.txt new file mode 100644 index 0000000000..fe62dda4cd --- /dev/null +++ b/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_14.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_EA_RDREQ_GMI_CREDIT_STALL[0] TCC_EA_RDREQ[1] TCC_EA_RDREQ_32B[1] TCC_EA_RDREQ_DRAM_CREDIT_STALL[1] TCC_EA_RDREQ_GMI_CREDIT_STALL[1] TCC_EA_RDREQ[2] TCC_EA_RDREQ_32B[2] TCC_EA_RDREQ_DRAM_CREDIT_STALL[2] TCC_EA_RDREQ_GMI_CREDIT_STALL[2] TCC_EA_RDREQ[3] TCC_EA_RDREQ_32B[3] TCC_EA_RDREQ_DRAM_CREDIT_STALL[3] TCC_EA_RDREQ_GMI_CREDIT_STALL[3] TCC_EA_RDREQ[4] TCC_EA_RDREQ_32B[4] TCC_EA_RDREQ_DRAM_CREDIT_STALL[4] TCC_EA_RDREQ_GMI_CREDIT_STALL[4] TCC_EA_RDREQ[5] TCC_EA_RDREQ_32B[5] TCC_EA_RDREQ_DRAM_CREDIT_STALL[5] TCC_EA_RDREQ_GMI_CREDIT_STALL[5] TCC_EA_RDREQ[6] TCC_EA_RDREQ_32B[6] TCC_EA_RDREQ_DRAM_CREDIT_STALL[6] TCC_EA_RDREQ_GMI_CREDIT_STALL[6] TCC_EA_RDREQ[7] TCC_EA_RDREQ_32B[7] TCC_EA_RDREQ_DRAM_CREDIT_STALL[7] TCC_EA_RDREQ_GMI_CREDIT_STALL[7] TCC_EA_RDREQ[8] TCC_EA_RDREQ_32B[8] TCC_EA_RDREQ_DRAM_CREDIT_STALL[8] TCC_EA_RDREQ_GMI_CREDIT_STALL[8] TCC_EA_RDREQ[9] TCC_EA_RDREQ_32B[9] TCC_EA_RDREQ_DRAM_CREDIT_STALL[9] TCC_EA_RDREQ_GMI_CREDIT_STALL[9] TCC_EA_RDREQ[10] TCC_EA_RDREQ_32B[10] TCC_EA_RDREQ_DRAM_CREDIT_STALL[10] TCC_EA_RDREQ_GMI_CREDIT_STALL[10] TCC_EA_RDREQ[11] TCC_EA_RDREQ_32B[11] TCC_EA_RDREQ_DRAM_CREDIT_STALL[11] TCC_EA_RDREQ_GMI_CREDIT_STALL[11] TCC_EA_RDREQ[12] TCC_EA_RDREQ_32B[12] TCC_EA_RDREQ_DRAM_CREDIT_STALL[12] TCC_EA_RDREQ_GMI_CREDIT_STALL[12] TCC_EA_RDREQ[13] TCC_EA_RDREQ_32B[13] TCC_EA_RDREQ_DRAM_CREDIT_STALL[13] TCC_EA_RDREQ_GMI_CREDIT_STALL[13] TCC_EA_RDREQ[14] TCC_EA_RDREQ_32B[14] TCC_EA_RDREQ_DRAM_CREDIT_STALL[14] TCC_EA_RDREQ_GMI_CREDIT_STALL[14] TCC_EA_RDREQ[15] TCC_EA_RDREQ_32B[15] TCC_EA_RDREQ_DRAM_CREDIT_STALL[15] TCC_EA_RDREQ_GMI_CREDIT_STALL[15] TCC_EA_RDREQ[16] TCC_EA_RDREQ_32B[16] TCC_EA_RDREQ_DRAM_CREDIT_STALL[16] TCC_EA_RDREQ_GMI_CREDIT_STALL[16] TCC_EA_RDREQ[17] TCC_EA_RDREQ_32B[17] TCC_EA_RDREQ_DRAM_CREDIT_STALL[17] TCC_EA_RDREQ_GMI_CREDIT_STALL[17] TCC_EA_RDREQ[18] TCC_EA_RDREQ_32B[18] TCC_EA_RDREQ_DRAM_CREDIT_STALL[18] TCC_EA_RDREQ_GMI_CREDIT_STALL[18] TCC_EA_RDREQ[19] TCC_EA_RDREQ_32B[19] TCC_EA_RDREQ_DRAM_CREDIT_STALL[19] TCC_EA_RDREQ_GMI_CREDIT_STALL[19] TCC_EA_RDREQ[20] TCC_EA_RDREQ_32B[20] TCC_EA_RDREQ_DRAM_CREDIT_STALL[20] TCC_EA_RDREQ_GMI_CREDIT_STALL[20] TCC_EA_RDREQ[21] TCC_EA_RDREQ_32B[21] TCC_EA_RDREQ_DRAM_CREDIT_STALL[21] TCC_EA_RDREQ_GMI_CREDIT_STALL[21] TCC_EA_RDREQ[22] TCC_EA_RDREQ_32B[22] TCC_EA_RDREQ_DRAM_CREDIT_STALL[22] TCC_EA_RDREQ_GMI_CREDIT_STALL[22] TCC_EA_RDREQ[23] TCC_EA_RDREQ_32B[23] TCC_EA_RDREQ_DRAM_CREDIT_STALL[23] TCC_EA_RDREQ_GMI_CREDIT_STALL[23] TCC_EA_RDREQ[24] TCC_EA_RDREQ_32B[24] TCC_EA_RDREQ_DRAM_CREDIT_STALL[24] TCC_EA_RDREQ_GMI_CREDIT_STALL[24] TCC_EA_RDREQ[25] TCC_EA_RDREQ_32B[25] TCC_EA_RDREQ_DRAM_CREDIT_STALL[25] TCC_EA_RDREQ_GMI_CREDIT_STALL[25] TCC_EA_RDREQ[26] TCC_EA_RDREQ_32B[26] TCC_EA_RDREQ_DRAM_CREDIT_STALL[26] TCC_EA_RDREQ_GMI_CREDIT_STALL[26] TCC_EA_RDREQ[27] TCC_EA_RDREQ_32B[27] TCC_EA_RDREQ_DRAM_CREDIT_STALL[27] TCC_EA_RDREQ_GMI_CREDIT_STALL[27] TCC_EA_RDREQ[28] TCC_EA_RDREQ_32B[28] TCC_EA_RDREQ_DRAM_CREDIT_STALL[28] TCC_EA_RDREQ_GMI_CREDIT_STALL[28] TCC_EA_RDREQ[29] TCC_EA_RDREQ_32B[29] TCC_EA_RDREQ_DRAM_CREDIT_STALL[29] TCC_EA_RDREQ_GMI_CREDIT_STALL[29] TCC_EA_RDREQ[30] TCC_EA_RDREQ_32B[30] TCC_EA_RDREQ_DRAM_CREDIT_STALL[30] TCC_EA_RDREQ_GMI_CREDIT_STALL[30] TCC_EA_RDREQ[31] TCC_EA_RDREQ_32B[31] TCC_EA_RDREQ_DRAM_CREDIT_STALL[31] TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + +gpu: +range: 1 +kernel: diff --git a/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_15.txt b/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_15.txt new file mode 100644 index 0000000000..69e1d25eaf --- /dev/null +++ b/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_15.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ[0] TCC_EA_WRREQ_64B[0] TCC_EA_RDREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_LEVEL[1] TCC_EA_WRREQ[1] TCC_EA_WRREQ_64B[1] TCC_EA_RDREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_LEVEL[2] TCC_EA_WRREQ[2] TCC_EA_WRREQ_64B[2] TCC_EA_RDREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_LEVEL[3] TCC_EA_WRREQ[3] TCC_EA_WRREQ_64B[3] TCC_EA_RDREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_LEVEL[4] TCC_EA_WRREQ[4] TCC_EA_WRREQ_64B[4] TCC_EA_RDREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_LEVEL[5] TCC_EA_WRREQ[5] TCC_EA_WRREQ_64B[5] TCC_EA_RDREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_LEVEL[6] TCC_EA_WRREQ[6] TCC_EA_WRREQ_64B[6] TCC_EA_RDREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_LEVEL[7] TCC_EA_WRREQ[7] TCC_EA_WRREQ_64B[7] TCC_EA_RDREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_LEVEL[8] TCC_EA_WRREQ[8] TCC_EA_WRREQ_64B[8] TCC_EA_RDREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_LEVEL[9] TCC_EA_WRREQ[9] TCC_EA_WRREQ_64B[9] TCC_EA_RDREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_LEVEL[10] TCC_EA_WRREQ[10] TCC_EA_WRREQ_64B[10] TCC_EA_RDREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_LEVEL[11] TCC_EA_WRREQ[11] TCC_EA_WRREQ_64B[11] TCC_EA_RDREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_LEVEL[12] TCC_EA_WRREQ[12] TCC_EA_WRREQ_64B[12] TCC_EA_RDREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_LEVEL[13] TCC_EA_WRREQ[13] TCC_EA_WRREQ_64B[13] TCC_EA_RDREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_LEVEL[14] TCC_EA_WRREQ[14] TCC_EA_WRREQ_64B[14] TCC_EA_RDREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_LEVEL[15] TCC_EA_WRREQ[15] TCC_EA_WRREQ_64B[15] TCC_EA_RDREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_LEVEL[16] TCC_EA_WRREQ[16] TCC_EA_WRREQ_64B[16] TCC_EA_RDREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_LEVEL[17] TCC_EA_WRREQ[17] TCC_EA_WRREQ_64B[17] TCC_EA_RDREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_LEVEL[18] TCC_EA_WRREQ[18] TCC_EA_WRREQ_64B[18] TCC_EA_RDREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_LEVEL[19] TCC_EA_WRREQ[19] TCC_EA_WRREQ_64B[19] TCC_EA_RDREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_LEVEL[20] TCC_EA_WRREQ[20] TCC_EA_WRREQ_64B[20] TCC_EA_RDREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_LEVEL[21] TCC_EA_WRREQ[21] TCC_EA_WRREQ_64B[21] TCC_EA_RDREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_LEVEL[22] TCC_EA_WRREQ[22] TCC_EA_WRREQ_64B[22] TCC_EA_RDREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_LEVEL[23] TCC_EA_WRREQ[23] TCC_EA_WRREQ_64B[23] TCC_EA_RDREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_LEVEL[24] TCC_EA_WRREQ[24] TCC_EA_WRREQ_64B[24] TCC_EA_RDREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_LEVEL[25] TCC_EA_WRREQ[25] TCC_EA_WRREQ_64B[25] TCC_EA_RDREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_LEVEL[26] TCC_EA_WRREQ[26] TCC_EA_WRREQ_64B[26] TCC_EA_RDREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_LEVEL[27] TCC_EA_WRREQ[27] TCC_EA_WRREQ_64B[27] TCC_EA_RDREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_LEVEL[28] TCC_EA_WRREQ[28] TCC_EA_WRREQ_64B[28] TCC_EA_RDREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_LEVEL[29] TCC_EA_WRREQ[29] TCC_EA_WRREQ_64B[29] TCC_EA_RDREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_LEVEL[30] TCC_EA_WRREQ[30] TCC_EA_WRREQ_64B[30] TCC_EA_RDREQ_IO_CREDIT_STALL[31] TCC_EA_RDREQ_LEVEL[31] TCC_EA_WRREQ[31] TCC_EA_WRREQ_64B[31] + +gpu: +range: 1 +kernel: diff --git a/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_16.txt b/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_16.txt new file mode 100644 index 0000000000..33a9a95cfc --- /dev/null +++ b/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_16.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_WRREQ_IO_CREDIT_STALL[0] TCC_EA_WRREQ_LEVEL[0] TCC_EA_WRREQ_DRAM_CREDIT_STALL[1] TCC_EA_WRREQ_GMI_CREDIT_STALL[1] TCC_EA_WRREQ_IO_CREDIT_STALL[1] TCC_EA_WRREQ_LEVEL[1] TCC_EA_WRREQ_DRAM_CREDIT_STALL[2] TCC_EA_WRREQ_GMI_CREDIT_STALL[2] TCC_EA_WRREQ_IO_CREDIT_STALL[2] TCC_EA_WRREQ_LEVEL[2] TCC_EA_WRREQ_DRAM_CREDIT_STALL[3] TCC_EA_WRREQ_GMI_CREDIT_STALL[3] TCC_EA_WRREQ_IO_CREDIT_STALL[3] TCC_EA_WRREQ_LEVEL[3] TCC_EA_WRREQ_DRAM_CREDIT_STALL[4] TCC_EA_WRREQ_GMI_CREDIT_STALL[4] TCC_EA_WRREQ_IO_CREDIT_STALL[4] TCC_EA_WRREQ_LEVEL[4] TCC_EA_WRREQ_DRAM_CREDIT_STALL[5] TCC_EA_WRREQ_GMI_CREDIT_STALL[5] TCC_EA_WRREQ_IO_CREDIT_STALL[5] TCC_EA_WRREQ_LEVEL[5] TCC_EA_WRREQ_DRAM_CREDIT_STALL[6] TCC_EA_WRREQ_GMI_CREDIT_STALL[6] TCC_EA_WRREQ_IO_CREDIT_STALL[6] TCC_EA_WRREQ_LEVEL[6] TCC_EA_WRREQ_DRAM_CREDIT_STALL[7] TCC_EA_WRREQ_GMI_CREDIT_STALL[7] TCC_EA_WRREQ_IO_CREDIT_STALL[7] TCC_EA_WRREQ_LEVEL[7] TCC_EA_WRREQ_DRAM_CREDIT_STALL[8] TCC_EA_WRREQ_GMI_CREDIT_STALL[8] TCC_EA_WRREQ_IO_CREDIT_STALL[8] TCC_EA_WRREQ_LEVEL[8] TCC_EA_WRREQ_DRAM_CREDIT_STALL[9] TCC_EA_WRREQ_GMI_CREDIT_STALL[9] TCC_EA_WRREQ_IO_CREDIT_STALL[9] TCC_EA_WRREQ_LEVEL[9] TCC_EA_WRREQ_DRAM_CREDIT_STALL[10] TCC_EA_WRREQ_GMI_CREDIT_STALL[10] TCC_EA_WRREQ_IO_CREDIT_STALL[10] TCC_EA_WRREQ_LEVEL[10] TCC_EA_WRREQ_DRAM_CREDIT_STALL[11] TCC_EA_WRREQ_GMI_CREDIT_STALL[11] TCC_EA_WRREQ_IO_CREDIT_STALL[11] TCC_EA_WRREQ_LEVEL[11] TCC_EA_WRREQ_DRAM_CREDIT_STALL[12] TCC_EA_WRREQ_GMI_CREDIT_STALL[12] TCC_EA_WRREQ_IO_CREDIT_STALL[12] TCC_EA_WRREQ_LEVEL[12] TCC_EA_WRREQ_DRAM_CREDIT_STALL[13] TCC_EA_WRREQ_GMI_CREDIT_STALL[13] TCC_EA_WRREQ_IO_CREDIT_STALL[13] TCC_EA_WRREQ_LEVEL[13] TCC_EA_WRREQ_DRAM_CREDIT_STALL[14] TCC_EA_WRREQ_GMI_CREDIT_STALL[14] TCC_EA_WRREQ_IO_CREDIT_STALL[14] TCC_EA_WRREQ_LEVEL[14] TCC_EA_WRREQ_DRAM_CREDIT_STALL[15] TCC_EA_WRREQ_GMI_CREDIT_STALL[15] TCC_EA_WRREQ_IO_CREDIT_STALL[15] TCC_EA_WRREQ_LEVEL[15] TCC_EA_WRREQ_DRAM_CREDIT_STALL[16] TCC_EA_WRREQ_GMI_CREDIT_STALL[16] TCC_EA_WRREQ_IO_CREDIT_STALL[16] TCC_EA_WRREQ_LEVEL[16] TCC_EA_WRREQ_DRAM_CREDIT_STALL[17] TCC_EA_WRREQ_GMI_CREDIT_STALL[17] TCC_EA_WRREQ_IO_CREDIT_STALL[17] TCC_EA_WRREQ_LEVEL[17] TCC_EA_WRREQ_DRAM_CREDIT_STALL[18] TCC_EA_WRREQ_GMI_CREDIT_STALL[18] TCC_EA_WRREQ_IO_CREDIT_STALL[18] TCC_EA_WRREQ_LEVEL[18] TCC_EA_WRREQ_DRAM_CREDIT_STALL[19] TCC_EA_WRREQ_GMI_CREDIT_STALL[19] TCC_EA_WRREQ_IO_CREDIT_STALL[19] TCC_EA_WRREQ_LEVEL[19] TCC_EA_WRREQ_DRAM_CREDIT_STALL[20] TCC_EA_WRREQ_GMI_CREDIT_STALL[20] TCC_EA_WRREQ_IO_CREDIT_STALL[20] TCC_EA_WRREQ_LEVEL[20] TCC_EA_WRREQ_DRAM_CREDIT_STALL[21] TCC_EA_WRREQ_GMI_CREDIT_STALL[21] TCC_EA_WRREQ_IO_CREDIT_STALL[21] TCC_EA_WRREQ_LEVEL[21] TCC_EA_WRREQ_DRAM_CREDIT_STALL[22] TCC_EA_WRREQ_GMI_CREDIT_STALL[22] TCC_EA_WRREQ_IO_CREDIT_STALL[22] TCC_EA_WRREQ_LEVEL[22] TCC_EA_WRREQ_DRAM_CREDIT_STALL[23] TCC_EA_WRREQ_GMI_CREDIT_STALL[23] TCC_EA_WRREQ_IO_CREDIT_STALL[23] TCC_EA_WRREQ_LEVEL[23] TCC_EA_WRREQ_DRAM_CREDIT_STALL[24] TCC_EA_WRREQ_GMI_CREDIT_STALL[24] TCC_EA_WRREQ_IO_CREDIT_STALL[24] TCC_EA_WRREQ_LEVEL[24] TCC_EA_WRREQ_DRAM_CREDIT_STALL[25] TCC_EA_WRREQ_GMI_CREDIT_STALL[25] TCC_EA_WRREQ_IO_CREDIT_STALL[25] TCC_EA_WRREQ_LEVEL[25] TCC_EA_WRREQ_DRAM_CREDIT_STALL[26] TCC_EA_WRREQ_GMI_CREDIT_STALL[26] TCC_EA_WRREQ_IO_CREDIT_STALL[26] TCC_EA_WRREQ_LEVEL[26] TCC_EA_WRREQ_DRAM_CREDIT_STALL[27] TCC_EA_WRREQ_GMI_CREDIT_STALL[27] TCC_EA_WRREQ_IO_CREDIT_STALL[27] TCC_EA_WRREQ_LEVEL[27] TCC_EA_WRREQ_DRAM_CREDIT_STALL[28] TCC_EA_WRREQ_GMI_CREDIT_STALL[28] TCC_EA_WRREQ_IO_CREDIT_STALL[28] TCC_EA_WRREQ_LEVEL[28] TCC_EA_WRREQ_DRAM_CREDIT_STALL[29] TCC_EA_WRREQ_GMI_CREDIT_STALL[29] TCC_EA_WRREQ_IO_CREDIT_STALL[29] TCC_EA_WRREQ_LEVEL[29] TCC_EA_WRREQ_DRAM_CREDIT_STALL[30] TCC_EA_WRREQ_GMI_CREDIT_STALL[30] TCC_EA_WRREQ_IO_CREDIT_STALL[30] TCC_EA_WRREQ_LEVEL[30] TCC_EA_WRREQ_DRAM_CREDIT_STALL[31] TCC_EA_WRREQ_GMI_CREDIT_STALL[31] TCC_EA_WRREQ_IO_CREDIT_STALL[31] TCC_EA_WRREQ_LEVEL[31] + +gpu: +range: 1 +kernel: diff --git a/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_17.txt b/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_17.txt new file mode 100644 index 0000000000..6bcdb4c59f --- /dev/null +++ b/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_17.txt @@ -0,0 +1,5 @@ +pmc: TCC_HIT[0] TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_HIT[1] TCC_MISS[1] TCC_READ[1] TCC_REQ[1] TCC_HIT[2] TCC_MISS[2] TCC_READ[2] TCC_REQ[2] TCC_HIT[3] TCC_MISS[3] TCC_READ[3] TCC_REQ[3] TCC_HIT[4] TCC_MISS[4] TCC_READ[4] TCC_REQ[4] TCC_HIT[5] TCC_MISS[5] TCC_READ[5] TCC_REQ[5] TCC_HIT[6] TCC_MISS[6] TCC_READ[6] TCC_REQ[6] TCC_HIT[7] TCC_MISS[7] TCC_READ[7] TCC_REQ[7] TCC_HIT[8] TCC_MISS[8] TCC_READ[8] TCC_REQ[8] TCC_HIT[9] TCC_MISS[9] TCC_READ[9] TCC_REQ[9] TCC_HIT[10] TCC_MISS[10] TCC_READ[10] TCC_REQ[10] TCC_HIT[11] TCC_MISS[11] TCC_READ[11] TCC_REQ[11] TCC_HIT[12] TCC_MISS[12] TCC_READ[12] TCC_REQ[12] TCC_HIT[13] TCC_MISS[13] TCC_READ[13] TCC_REQ[13] TCC_HIT[14] TCC_MISS[14] TCC_READ[14] TCC_REQ[14] TCC_HIT[15] TCC_MISS[15] TCC_READ[15] TCC_REQ[15] TCC_HIT[16] TCC_MISS[16] TCC_READ[16] TCC_REQ[16] TCC_HIT[17] TCC_MISS[17] TCC_READ[17] TCC_REQ[17] TCC_HIT[18] TCC_MISS[18] TCC_READ[18] TCC_REQ[18] TCC_HIT[19] TCC_MISS[19] TCC_READ[19] TCC_REQ[19] TCC_HIT[20] TCC_MISS[20] TCC_READ[20] TCC_REQ[20] TCC_HIT[21] TCC_MISS[21] TCC_READ[21] TCC_REQ[21] TCC_HIT[22] TCC_MISS[22] TCC_READ[22] TCC_REQ[22] TCC_HIT[23] TCC_MISS[23] TCC_READ[23] TCC_REQ[23] TCC_HIT[24] TCC_MISS[24] TCC_READ[24] TCC_REQ[24] TCC_HIT[25] TCC_MISS[25] TCC_READ[25] TCC_REQ[25] TCC_HIT[26] TCC_MISS[26] TCC_READ[26] TCC_REQ[26] TCC_HIT[27] TCC_MISS[27] TCC_READ[27] TCC_REQ[27] TCC_HIT[28] TCC_MISS[28] TCC_READ[28] TCC_REQ[28] TCC_HIT[29] TCC_MISS[29] TCC_READ[29] TCC_REQ[29] TCC_HIT[30] TCC_MISS[30] TCC_READ[30] TCC_REQ[30] TCC_HIT[31] TCC_MISS[31] TCC_READ[31] TCC_REQ[31] + +gpu: +range: 1 +kernel: diff --git a/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_18.txt b/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_18.txt new file mode 100644 index 0000000000..ab767357c0 --- /dev/null +++ b/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_18.txt @@ -0,0 +1,5 @@ +pmc: TCC_RW_REQ[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_RW_REQ[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_WRITE[1] TCC_RW_REQ[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_WRITE[2] TCC_RW_REQ[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_WRITE[3] TCC_RW_REQ[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_WRITE[4] TCC_RW_REQ[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_WRITE[5] TCC_RW_REQ[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_WRITE[6] TCC_RW_REQ[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_WRITE[7] TCC_RW_REQ[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_WRITE[8] TCC_RW_REQ[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_WRITE[9] TCC_RW_REQ[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_WRITE[10] TCC_RW_REQ[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_WRITE[11] TCC_RW_REQ[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_WRITE[12] TCC_RW_REQ[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_WRITE[13] TCC_RW_REQ[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_WRITE[14] TCC_RW_REQ[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_WRITE[15] TCC_RW_REQ[16] TCC_TOO_MANY_EA_WRREQS_STALL[16] TCC_WRITE[16] TCC_RW_REQ[17] TCC_TOO_MANY_EA_WRREQS_STALL[17] TCC_WRITE[17] TCC_RW_REQ[18] TCC_TOO_MANY_EA_WRREQS_STALL[18] TCC_WRITE[18] TCC_RW_REQ[19] TCC_TOO_MANY_EA_WRREQS_STALL[19] TCC_WRITE[19] TCC_RW_REQ[20] TCC_TOO_MANY_EA_WRREQS_STALL[20] TCC_WRITE[20] TCC_RW_REQ[21] TCC_TOO_MANY_EA_WRREQS_STALL[21] TCC_WRITE[21] TCC_RW_REQ[22] TCC_TOO_MANY_EA_WRREQS_STALL[22] TCC_WRITE[22] TCC_RW_REQ[23] TCC_TOO_MANY_EA_WRREQS_STALL[23] TCC_WRITE[23] TCC_RW_REQ[24] TCC_TOO_MANY_EA_WRREQS_STALL[24] TCC_WRITE[24] TCC_RW_REQ[25] TCC_TOO_MANY_EA_WRREQS_STALL[25] TCC_WRITE[25] TCC_RW_REQ[26] TCC_TOO_MANY_EA_WRREQS_STALL[26] TCC_WRITE[26] TCC_RW_REQ[27] TCC_TOO_MANY_EA_WRREQS_STALL[27] TCC_WRITE[27] TCC_RW_REQ[28] TCC_TOO_MANY_EA_WRREQS_STALL[28] TCC_WRITE[28] TCC_RW_REQ[29] TCC_TOO_MANY_EA_WRREQS_STALL[29] TCC_WRITE[29] TCC_RW_REQ[30] TCC_TOO_MANY_EA_WRREQS_STALL[30] TCC_WRITE[30] TCC_RW_REQ[31] TCC_TOO_MANY_EA_WRREQS_STALL[31] TCC_WRITE[31] + +gpu: +range: 1 +kernel: diff --git a/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_2.txt b/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_2.txt new file mode 100644 index 0000000000..a0d436bae9 --- /dev/null +++ b/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_2.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_MUL_F32 SQ_INSTS_VALU_FMA_F32 SQ_INSTS_VALU_TRANS_F32 SQ_INSTS_VALU_ADD_F64 SQ_INSTS_VALU_MUL_F64 SQ_INSTS_VALU_FMA_F64 SQ_INSTS_VALU_TRANS_F64 SQ_INSTS_VALU_INT32 TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum TA_BUFFER_ATOMIC_WAVEFRONTS_sum TA_BUFFER_TOTAL_CYCLES_sum TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum + +gpu: +range: 1 +kernel: diff --git a/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_3.txt b/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_3.txt new file mode 100644 index 0000000000..28935cc2dd --- /dev/null +++ b/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_3.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_INT64 SQ_INSTS_SMEM SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum TD_COALESCABLE_WAVEFRONT_sum SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE CPF_CMP_UTCL1_STALL_ON_TRANSLATION TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum + +gpu: +range: 1 +kernel: diff --git a/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_4.txt b/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_4.txt new file mode 100644 index 0000000000..197b427a30 --- /dev/null +++ b/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_4.txt @@ -0,0 +1,5 @@ +pmc: SQ_WAVE_CYCLES SQ_WAIT_ANY SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_BUSY_CU_CYCLES SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE TCC_EA_WRREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WR_UNCACHED_32B_sum TCC_EA_WRREQ_DRAM_sum + +gpu: +range: 1 +kernel: diff --git a/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_5.txt b/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_5.txt new file mode 100644 index 0000000000..c12d4823c8 --- /dev/null +++ b/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_5.txt @@ -0,0 +1,5 @@ +pmc: SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU TCP_TCP_LATENCY_sum TCP_TCC_READ_REQ_LATENCY_sum TCP_TCC_WRITE_REQ_LATENCY_sum TCP_TCC_READ_REQ_sum TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN CPC_ME1_DC0_SPI_BUSY TCC_EA_WRREQ_STALL_sum TCC_EA_RDREQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RD_UNCACHED_32B_sum + +gpu: +range: 1 +kernel: diff --git a/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_6.txt b/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_6.txt new file mode 100644 index 0000000000..679857138b --- /dev/null +++ b/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_6.txt @@ -0,0 +1,5 @@ +pmc: SQ_THREAD_CYCLES_VALU SQ_IFETCH SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TCP_TCC_NC_READ_REQ_sum TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN TCC_EA_RDREQ_DRAM_sum TCC_TAG_STALL_sum TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum + +gpu: +range: 1 +kernel: diff --git a/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_7.txt b/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_7.txt new file mode 100644 index 0000000000..d78f6b476b --- /dev/null +++ b/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_7.txt @@ -0,0 +1,5 @@ +pmc: SQ_WAVES_LT_32 SQ_WAVES_LT_16 SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TCP_TCC_UC_WRITE_REQ_sum TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR TCC_NORMAL_EVICT_sum TCC_ALL_TC_OP_INV_EVICT_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA_ATOMIC_sum + +gpu: +range: 1 +kernel: diff --git a/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_8.txt b/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_8.txt new file mode 100644 index 0000000000..ffec8efe9f --- /dev/null +++ b/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_8.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM_NORM SQ_INSTS_MFMA SQ_INSTS_VALU_MFMA_I8 SQ_INSTS_VALU_MFMA_F16 SQ_INSTS_VALU_MFMA_BF16 SQ_INSTS_VALU_MFMA_F32 SQ_INSTS_VALU_MFMA_F64 SQ_VALU_MFMA_BUSY_CYCLES TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TCP_TCC_CC_ATOMIC_REQ_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN TCC_EA_RDREQ_LEVEL_sum TCC_EA_WRREQ_LEVEL_sum TCC_EA_ATOMIC_LEVEL_sum + +gpu: +range: 1 +kernel: diff --git a/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_9.txt b/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_9.txt new file mode 100644 index 0000000000..4eff507229 --- /dev/null +++ b/tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_9.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_FLAT_LDS_ONLY SQ_INSTS_VALU_MFMA_MOPS_I8 SQ_INSTS_VALU_MFMA_MOPS_F16 SQ_INSTS_VALU_MFMA_MOPS_BF16 SQ_INSTS_VALU_MFMA_MOPS_F32 SQ_INSTS_VALU_MFMA_MOPS_F64 SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum TCP_PENDING_STALL_CYCLES_sum + +gpu: +range: 1 +kernel: diff --git a/tests/workloads/dispatch_2/MI200/perfmon/timestamps.txt b/tests/workloads/dispatch_2/MI200/perfmon/timestamps.txt new file mode 100644 index 0000000000..755f2b7b20 --- /dev/null +++ b/tests/workloads/dispatch_2/MI200/perfmon/timestamps.txt @@ -0,0 +1,5 @@ +pmc: + +gpu: +range: 1 +kernel: diff --git a/tests/workloads/dispatch_2/MI200/pmc_perf.csv b/tests/workloads/dispatch_2/MI200/pmc_perf.csv new file mode 100644 index 0000000000..00119c51e0 --- /dev/null +++ b/tests/workloads/dispatch_2/MI200/pmc_perf.csv @@ -0,0 +1,2 @@ +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_1,obj_1,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_2,obj_2,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,wave_size_3,obj_3,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_4,obj_4,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_5,obj_5,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,TD_COALESCABLE_WAVEFRONT_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_6,obj_6,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_7,obj_7,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_8,obj_8,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_9,obj_9,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_10,obj_10,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_11,obj_11,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_12,obj_12,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_13,obj_13,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_DRAM_sum,TCC_TAG_STALL_sum,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,wave_size_14,obj_14,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_15,obj_15,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_16,obj_16,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,wave_size_17,obj_17,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,TCC_EA_ATOMIC_LEVEL_sum,wave_size_18,obj_18,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],Start_Timestamp,End_Timestamp +1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7fafae7e8ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,8528,18678,6328,550,0,21756,203809.0,0.0,72736.0,131073.0,64,0x7fc2dd45cec0,8860939,8418214,98661,344064,1390094,0,0,163840,0.0,524288.0,0.0,524288.0,127328.0,32768.0,280006,0,0,8319,92408.0,92408.0,0.0,92408.0,64,0x7f67fb880ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65550.0,0.0,0.0,0.0,64,0x7f1be8a7cec0,6379,0,4096,6404,0,4096,6329,0,4096,6380,0,4096,6351,0,4096,6387,0,4096,6388,0,4096,6387,0,4096,6385,0,4096,6379,0,4096,6403,0,4096,6333,0,4096,6375,0,4096,6357,0,4096,6385,0,4096,6394,0,4096,6376,0,4096,6415,0,4096,6372,0,4096,6405,0,4096,6373,0,4096,6349,0,4096,6383,0,4096,6348,0,4096,6349,0,4096,6374,0,4096,6419,0,4096,6372,0,4096,6413,0,4096,6374,0,4096,6350,0,4096,6384,0,4096,64,0x7fe215058ec0,0,0,0,56,0,65536,65536,0,64,0x7f923af74ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,5843,0,819,21683,0,73269.0,131072.0,0.0,46242.0,64,0x7faee6264ec0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,64,0x7f3373cf8ec0,0,1070406,2872,2872,0,1355038,2900,2900,0,1235692,2896,2896,0,1330554,2896,2896,0,1272053,2924,2924,0,1225242,2880,2880,0,1069199,2924,2924,0,1249540,2864,2864,0,1242958,2864,2864,0,1136055,2868,2868,0,1216196,2896,2896,0,1199400,2900,2900,0,1292735,2892,2892,0,1197751,2924,2924,0,1165077,2872,2872,0,1569724,2920,2920,0,1384478,2848,2848,0,1249928,2924,2924,0,1204513,2852,2852,0,1309165,2912,2912,0,1392058,2880,2880,0,1301210,2888,2888,0,1198037,2848,2848,0,1499610,2872,2872,0,1150983,2866,2866,0,1135638,2852,2852,0,1617036,2924,2924,0,1195090,2856,2856,0,1532729,2912,2912,0,1230167,2880,2880,0,1248819,2888,2888,0,1320949,2852,2852,64,0x7f53820d4ec0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,31,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,64,0x7fe652204ec0,0,393216,163840,0,0,0,0,0,15953,0.0,0.0,0.0,32768.0,0.0,0.0,428.0,32768.0,4096,16384,302,22694,1286,0,56.0,0.0,0.0,203649.0,64,0x7f0eb4224ec0,0,0,0,932520,0,0,0,942446,0,0,0,883403,0,0,0,995686,0,0,0,999233,0,0,0,942774,0,0,0,882049,11,0,0,1077842,0,0,0,925990,0,0,0,869985,0,0,0,892724,0,0,0,934501,0,0,0,900272,8,0,0,1045353,0,0,0,1001744,0,0,0,989843,0,0,0,872030,0,0,0,1034514,0,0,0,892212,27,0,0,1133017,0,0,0,987952,0,0,0,1014360,0,0,0,943067,0,0,0,1014494,0,0,0,1022817,17,0,0,1032236,0,0,0,941043,0,0,0,949838,2,0,0,1099293,0,0,0,994135,0,0,0,1059857,0,0,0,943916,64,0x7fb3602b8ec0,32768,32768,0,64,0x7fc2ea4d4ec0,180672,110253,16384,0,16384,16384,32768,49152,22583,22583,1711520.0,1291155.0,3385.0,163871.0,955325.0,0.0,1282971.0,984804.0,178961,118388,22583,0,22583,0,722656.0,410389.0,0.0,0.0,64,0x7f6f850e8ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131072.0,34755.0,46215.0,0.0,64,0x7fcaea368ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,962608.0,64,0x7f33ba568ec0,0,55434,0,0,65536,63800,56,1680,64,0x7f084a7e8ec0,114688,0,32768,32768,16384,16384,65536,49152,27016783.0,85693015.0,39940578.0,131072.0,0.0,179709.0,0,0,12685,601.0,131073.0,0.0,0.0,64,0x7fc70d444ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,40346123.0,32083541.0,0.0,64,0x7ffa6c820ec0,2266,4096,2266,6362,2245,4096,2245,6341,2312,4096,2312,6408,2319,4096,2319,6415,2246,4096,2246,6342,2225,4096,2225,6321,2300,4096,2300,6396,2329,4096,2329,6425,2333,4096,2333,6429,2267,4096,2267,6363,2250,4096,2250,6346,2304,4096,2304,6400,2325,4096,2325,6421,2248,4096,2248,6344,2228,4096,2228,6324,2301,4096,2301,6397,2276,4096,2276,6372,2272,4096,2272,6368,2262,4096,2262,6358,2273,4096,2273,6369,2389,4097,2390,6486,2271,4096,2271,6367,2232,4096,2232,6328,2223,4096,2223,6319,2222,4096,2222,6318,2275,4096,2275,6371,2272,4096,2272,6368,2261,4096,2261,6357,2278,4096,2278,6374,2337,4096,2337,6433,2275,4096,2275,6371,2235,4096,2235,6331,198394440082212,198394440098052 diff --git a/tests/workloads/dispatch_2/MI200/roofline.csv b/tests/workloads/dispatch_2/MI200/roofline.csv new file mode 100644 index 0000000000..9429fe3e22 --- /dev/null +++ b/tests/workloads/dispatch_2/MI200/roofline.csv @@ -0,0 +1,5 @@ +device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh +0,1388.7772,1388.1665,1389.3879,5014.8452,5011.7578,5017.9326,9224.0459,9223.4287,9224.6631,18051.555,18050.539,18052.57,20931.686,20871.127,20992.244,20262.873,20262.266,20263.48,170395.78,170391.08,170400.48,164867.72,164862.77,164872.67,41417.938,41417.441,41418.434,41473.121,41472.258,41473.984,166331.56,165842,166821.12 +1,1389.5524,1388.957,1390.1477,5027.1084,5025.0698,5029.147,9234.0732,9233.4004,9234.7461,18092.131,18087.773,18096.488,20973.596,20906.982,21040.209,20294.998,20294.43,20295.566,170843.41,170839.48,170847.33,165112.16,165107.75,165116.56,41477.531,41476.762,41478.301,41536.461,41535.434,41537.488,166856.12,166850.86,166861.39 +2,1388.4222,1387.8956,1388.9489,5037.208,5034.7656,5039.6504,9260.0596,9259.3047,9260.8145,18102.715,18101.805,18103.625,21046.008,21045.592,21046.424,20349.283,20348.805,20349.762,171121.91,171118.34,171125.47,165485.56,165482.52,165488.61,41581.629,41580.355,41582.902,41641.801,41640.477,41643.125,166935.38,166323.91,167546.84 +3,1388.8452,1388.2465,1389.444,5033.5464,5032.2622,5034.8306,9242.0127,9241.4883,9242.5371,18025.061,18021.33,18028.791,21038.613,21038.105,21039.121,20313.775,20313.098,20314.453,171038.38,171034.86,171041.89,165235.06,165230.89,165239.23,41442.316,41286.215,41598.418,41584.824,41584.324,41585.324,167033.81,167031.94,167035.69 diff --git a/tests/workloads/dispatch_2/MI200/sysinfo.csv b/tests/workloads/dispatch_2/MI200/sysinfo.csv new file mode 100644 index 0000000000..bea3faa52a --- /dev/null +++ b/tests/workloads/dispatch_2/MI200/sysinfo.csv @@ -0,0 +1,2 @@ +workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd +dispatch_2,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 02:17:28 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/dispatch_2/MI200/timestamps.csv b/tests/workloads/dispatch_2/MI200/timestamps.csv new file mode 100644 index 0000000000..2e35c2631c --- /dev/null +++ b/tests/workloads/dispatch_2/MI200/timestamps.csv @@ -0,0 +1,2 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,305597,305597,1048576,256,0,0,8,0,16,64,0x0,0x7fadb1cc0ec0,198394440065730,198394440082212,198394440098052,198394440111888 diff --git a/tests/workloads/dispatch_6_8/MI100/sysinfo.csv b/tests/workloads/dispatch_6_8/MI100/sysinfo.csv index f24459e719..5285a1da29 100644 --- a/tests/workloads/dispatch_6_8/MI100/sysinfo.csv +++ b/tests/workloads/dispatch_6_8/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -dispatch_6_8,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Fri Mar 1 16:48:07 2024 (CST),1,t006-003.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651240,,5.7.1-98,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +dispatch_6_8,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 07 Mar 2024 01:11:04 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/dispatch_6_8/MI200/SQ_IFETCH_LEVEL.csv b/tests/workloads/dispatch_6_8/MI200/SQ_IFETCH_LEVEL.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/dispatch_6_8/MI200/SQ_IFETCH_LEVEL.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/dispatch_6_8/MI200/SQ_INST_LEVEL_LDS.csv b/tests/workloads/dispatch_6_8/MI200/SQ_INST_LEVEL_LDS.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/dispatch_6_8/MI200/SQ_INST_LEVEL_LDS.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/dispatch_6_8/MI200/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/dispatch_6_8/MI200/SQ_INST_LEVEL_SMEM.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/dispatch_6_8/MI200/SQ_INST_LEVEL_SMEM.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/dispatch_6_8/MI200/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/dispatch_6_8/MI200/SQ_INST_LEVEL_VMEM.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/dispatch_6_8/MI200/SQ_INST_LEVEL_VMEM.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/dispatch_6_8/MI200/SQ_LEVEL_WAVES.csv b/tests/workloads/dispatch_6_8/MI200/SQ_LEVEL_WAVES.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/dispatch_6_8/MI200/SQ_LEVEL_WAVES.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/dispatch_6_8/MI200/perfmon/SQ_IFETCH_LEVEL.txt b/tests/workloads/dispatch_6_8/MI200/perfmon/SQ_IFETCH_LEVEL.txt new file mode 100644 index 0000000000..2dfcf5315c --- /dev/null +++ b/tests/workloads/dispatch_6_8/MI200/perfmon/SQ_IFETCH_LEVEL.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES + +gpu: +range: 6:8 +kernel: diff --git a/tests/workloads/dispatch_6_8/MI200/perfmon/SQ_INST_LEVEL_LDS.txt b/tests/workloads/dispatch_6_8/MI200/perfmon/SQ_INST_LEVEL_LDS.txt new file mode 100644 index 0000000000..0c30d31fdc --- /dev/null +++ b/tests/workloads/dispatch_6_8/MI200/perfmon/SQ_INST_LEVEL_LDS.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES + +gpu: +range: 6:8 +kernel: diff --git a/tests/workloads/dispatch_6_8/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt b/tests/workloads/dispatch_6_8/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt new file mode 100644 index 0000000000..ecfdacf4ef --- /dev/null +++ b/tests/workloads/dispatch_6_8/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: 6:8 +kernel: diff --git a/tests/workloads/dispatch_6_8/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt b/tests/workloads/dispatch_6_8/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt new file mode 100644 index 0000000000..d066205a36 --- /dev/null +++ b/tests/workloads/dispatch_6_8/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: 6:8 +kernel: diff --git a/tests/workloads/dispatch_6_8/MI200/perfmon/SQ_LEVEL_WAVES.txt b/tests/workloads/dispatch_6_8/MI200/perfmon/SQ_LEVEL_WAVES.txt new file mode 100644 index 0000000000..0f485912b0 --- /dev/null +++ b/tests/workloads/dispatch_6_8/MI200/perfmon/SQ_LEVEL_WAVES.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES + +gpu: +range: 6:8 +kernel: diff --git a/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_0.txt b/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_0.txt new file mode 100644 index 0000000000..5a02c60e1a --- /dev/null +++ b/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_0.txt @@ -0,0 +1,5 @@ +pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES SQ_INSTS_VALU_CVT SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU GRBM_COUNT GRBM_GUI_ACTIVE TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum TA_TA_BUSY_sum TA_BUFFER_WAVEFRONTS_sum TD_TD_BUSY_sum TD_TC_STALL_sum SPI_CSN_WINDOW_VALID SPI_CSN_BUSY CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum + +gpu: +range: 6:8 +kernel: diff --git a/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_1.txt b/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_1.txt new file mode 100644 index 0000000000..1181c245df --- /dev/null +++ b/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_1.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VSKIPPED SQ_INSTS SQ_INSTS_VALU SQ_INSTS_VALU_ADD_F16 SQ_INSTS_VALU_MUL_F16 SQ_INSTS_VALU_FMA_F16 SQ_INSTS_VALU_TRANS_F16 SQ_INSTS_VALU_ADD_F32 GRBM_SPI_BUSY TCP_READ_TAGCONFLICT_STALL_CYCLES_sum TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum TCP_TA_TCP_STATE_READ_sum TA_BUFFER_READ_WAVEFRONTS_sum TA_BUFFER_WRITE_WAVEFRONTS_sum TD_SPI_STALL_sum TD_LOAD_WAVEFRONT_sum SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum + +gpu: +range: 6:8 +kernel: diff --git a/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_10.txt b/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_10.txt new file mode 100644 index 0000000000..03669a2c89 --- /dev/null +++ b/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_10.txt @@ -0,0 +1,5 @@ +pmc: SQC_TC_DATA_WRITE_REQ SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES + +gpu: +range: 6:8 +kernel: diff --git a/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_11.txt b/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_11.txt new file mode 100644 index 0000000000..84a792f2e2 --- /dev/null +++ b/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_11.txt @@ -0,0 +1,5 @@ +pmc: SQC_ICACHE_MISSES_DUPLICATE SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE + +gpu: +range: 6:8 +kernel: diff --git a/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_12.txt b/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_12.txt new file mode 100644 index 0000000000..529f946a6a --- /dev/null +++ b/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_12.txt @@ -0,0 +1,5 @@ +pmc: SQC_DCACHE_REQ_READ_1 SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 + +gpu: +range: 6:8 +kernel: diff --git a/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_13.txt b/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_13.txt new file mode 100644 index 0000000000..95dae77274 --- /dev/null +++ b/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_13.txt @@ -0,0 +1,5 @@ +pmc: TCC_ATOMIC[0] TCC_CYCLE[0] TCC_EA_ATOMIC[0] TCC_EA_ATOMIC_LEVEL[0] TCC_ATOMIC[1] TCC_CYCLE[1] TCC_EA_ATOMIC[1] TCC_EA_ATOMIC_LEVEL[1] TCC_ATOMIC[2] TCC_CYCLE[2] TCC_EA_ATOMIC[2] TCC_EA_ATOMIC_LEVEL[2] TCC_ATOMIC[3] TCC_CYCLE[3] TCC_EA_ATOMIC[3] TCC_EA_ATOMIC_LEVEL[3] TCC_ATOMIC[4] TCC_CYCLE[4] TCC_EA_ATOMIC[4] TCC_EA_ATOMIC_LEVEL[4] TCC_ATOMIC[5] TCC_CYCLE[5] TCC_EA_ATOMIC[5] TCC_EA_ATOMIC_LEVEL[5] TCC_ATOMIC[6] TCC_CYCLE[6] TCC_EA_ATOMIC[6] TCC_EA_ATOMIC_LEVEL[6] TCC_ATOMIC[7] TCC_CYCLE[7] TCC_EA_ATOMIC[7] TCC_EA_ATOMIC_LEVEL[7] TCC_ATOMIC[8] TCC_CYCLE[8] TCC_EA_ATOMIC[8] TCC_EA_ATOMIC_LEVEL[8] TCC_ATOMIC[9] TCC_CYCLE[9] TCC_EA_ATOMIC[9] TCC_EA_ATOMIC_LEVEL[9] TCC_ATOMIC[10] TCC_CYCLE[10] TCC_EA_ATOMIC[10] TCC_EA_ATOMIC_LEVEL[10] TCC_ATOMIC[11] TCC_CYCLE[11] TCC_EA_ATOMIC[11] TCC_EA_ATOMIC_LEVEL[11] TCC_ATOMIC[12] TCC_CYCLE[12] TCC_EA_ATOMIC[12] TCC_EA_ATOMIC_LEVEL[12] TCC_ATOMIC[13] TCC_CYCLE[13] TCC_EA_ATOMIC[13] TCC_EA_ATOMIC_LEVEL[13] TCC_ATOMIC[14] TCC_CYCLE[14] TCC_EA_ATOMIC[14] TCC_EA_ATOMIC_LEVEL[14] TCC_ATOMIC[15] TCC_CYCLE[15] TCC_EA_ATOMIC[15] TCC_EA_ATOMIC_LEVEL[15] TCC_ATOMIC[16] TCC_CYCLE[16] TCC_EA_ATOMIC[16] TCC_EA_ATOMIC_LEVEL[16] TCC_ATOMIC[17] TCC_CYCLE[17] TCC_EA_ATOMIC[17] TCC_EA_ATOMIC_LEVEL[17] TCC_ATOMIC[18] TCC_CYCLE[18] TCC_EA_ATOMIC[18] TCC_EA_ATOMIC_LEVEL[18] TCC_ATOMIC[19] TCC_CYCLE[19] TCC_EA_ATOMIC[19] TCC_EA_ATOMIC_LEVEL[19] TCC_ATOMIC[20] TCC_CYCLE[20] TCC_EA_ATOMIC[20] TCC_EA_ATOMIC_LEVEL[20] TCC_ATOMIC[21] TCC_CYCLE[21] TCC_EA_ATOMIC[21] TCC_EA_ATOMIC_LEVEL[21] TCC_ATOMIC[22] TCC_CYCLE[22] TCC_EA_ATOMIC[22] TCC_EA_ATOMIC_LEVEL[22] TCC_ATOMIC[23] TCC_CYCLE[23] TCC_EA_ATOMIC[23] TCC_EA_ATOMIC_LEVEL[23] TCC_ATOMIC[24] TCC_CYCLE[24] TCC_EA_ATOMIC[24] TCC_EA_ATOMIC_LEVEL[24] TCC_ATOMIC[25] TCC_CYCLE[25] TCC_EA_ATOMIC[25] TCC_EA_ATOMIC_LEVEL[25] TCC_ATOMIC[26] TCC_CYCLE[26] TCC_EA_ATOMIC[26] TCC_EA_ATOMIC_LEVEL[26] TCC_ATOMIC[27] TCC_CYCLE[27] TCC_EA_ATOMIC[27] TCC_EA_ATOMIC_LEVEL[27] TCC_ATOMIC[28] TCC_CYCLE[28] TCC_EA_ATOMIC[28] TCC_EA_ATOMIC_LEVEL[28] TCC_ATOMIC[29] TCC_CYCLE[29] TCC_EA_ATOMIC[29] TCC_EA_ATOMIC_LEVEL[29] TCC_ATOMIC[30] TCC_CYCLE[30] TCC_EA_ATOMIC[30] TCC_EA_ATOMIC_LEVEL[30] TCC_ATOMIC[31] TCC_CYCLE[31] TCC_EA_ATOMIC[31] TCC_EA_ATOMIC_LEVEL[31] + +gpu: +range: 6:8 +kernel: diff --git a/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_14.txt b/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_14.txt new file mode 100644 index 0000000000..e17c345afb --- /dev/null +++ b/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_14.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_EA_RDREQ_GMI_CREDIT_STALL[0] TCC_EA_RDREQ[1] TCC_EA_RDREQ_32B[1] TCC_EA_RDREQ_DRAM_CREDIT_STALL[1] TCC_EA_RDREQ_GMI_CREDIT_STALL[1] TCC_EA_RDREQ[2] TCC_EA_RDREQ_32B[2] TCC_EA_RDREQ_DRAM_CREDIT_STALL[2] TCC_EA_RDREQ_GMI_CREDIT_STALL[2] TCC_EA_RDREQ[3] TCC_EA_RDREQ_32B[3] TCC_EA_RDREQ_DRAM_CREDIT_STALL[3] TCC_EA_RDREQ_GMI_CREDIT_STALL[3] TCC_EA_RDREQ[4] TCC_EA_RDREQ_32B[4] TCC_EA_RDREQ_DRAM_CREDIT_STALL[4] TCC_EA_RDREQ_GMI_CREDIT_STALL[4] TCC_EA_RDREQ[5] TCC_EA_RDREQ_32B[5] TCC_EA_RDREQ_DRAM_CREDIT_STALL[5] TCC_EA_RDREQ_GMI_CREDIT_STALL[5] TCC_EA_RDREQ[6] TCC_EA_RDREQ_32B[6] TCC_EA_RDREQ_DRAM_CREDIT_STALL[6] TCC_EA_RDREQ_GMI_CREDIT_STALL[6] TCC_EA_RDREQ[7] TCC_EA_RDREQ_32B[7] TCC_EA_RDREQ_DRAM_CREDIT_STALL[7] TCC_EA_RDREQ_GMI_CREDIT_STALL[7] TCC_EA_RDREQ[8] TCC_EA_RDREQ_32B[8] TCC_EA_RDREQ_DRAM_CREDIT_STALL[8] TCC_EA_RDREQ_GMI_CREDIT_STALL[8] TCC_EA_RDREQ[9] TCC_EA_RDREQ_32B[9] TCC_EA_RDREQ_DRAM_CREDIT_STALL[9] TCC_EA_RDREQ_GMI_CREDIT_STALL[9] TCC_EA_RDREQ[10] TCC_EA_RDREQ_32B[10] TCC_EA_RDREQ_DRAM_CREDIT_STALL[10] TCC_EA_RDREQ_GMI_CREDIT_STALL[10] TCC_EA_RDREQ[11] TCC_EA_RDREQ_32B[11] TCC_EA_RDREQ_DRAM_CREDIT_STALL[11] TCC_EA_RDREQ_GMI_CREDIT_STALL[11] TCC_EA_RDREQ[12] TCC_EA_RDREQ_32B[12] TCC_EA_RDREQ_DRAM_CREDIT_STALL[12] TCC_EA_RDREQ_GMI_CREDIT_STALL[12] TCC_EA_RDREQ[13] TCC_EA_RDREQ_32B[13] TCC_EA_RDREQ_DRAM_CREDIT_STALL[13] TCC_EA_RDREQ_GMI_CREDIT_STALL[13] TCC_EA_RDREQ[14] TCC_EA_RDREQ_32B[14] TCC_EA_RDREQ_DRAM_CREDIT_STALL[14] TCC_EA_RDREQ_GMI_CREDIT_STALL[14] TCC_EA_RDREQ[15] TCC_EA_RDREQ_32B[15] TCC_EA_RDREQ_DRAM_CREDIT_STALL[15] TCC_EA_RDREQ_GMI_CREDIT_STALL[15] TCC_EA_RDREQ[16] TCC_EA_RDREQ_32B[16] TCC_EA_RDREQ_DRAM_CREDIT_STALL[16] TCC_EA_RDREQ_GMI_CREDIT_STALL[16] TCC_EA_RDREQ[17] TCC_EA_RDREQ_32B[17] TCC_EA_RDREQ_DRAM_CREDIT_STALL[17] TCC_EA_RDREQ_GMI_CREDIT_STALL[17] TCC_EA_RDREQ[18] TCC_EA_RDREQ_32B[18] TCC_EA_RDREQ_DRAM_CREDIT_STALL[18] TCC_EA_RDREQ_GMI_CREDIT_STALL[18] TCC_EA_RDREQ[19] TCC_EA_RDREQ_32B[19] TCC_EA_RDREQ_DRAM_CREDIT_STALL[19] TCC_EA_RDREQ_GMI_CREDIT_STALL[19] TCC_EA_RDREQ[20] TCC_EA_RDREQ_32B[20] TCC_EA_RDREQ_DRAM_CREDIT_STALL[20] TCC_EA_RDREQ_GMI_CREDIT_STALL[20] TCC_EA_RDREQ[21] TCC_EA_RDREQ_32B[21] TCC_EA_RDREQ_DRAM_CREDIT_STALL[21] TCC_EA_RDREQ_GMI_CREDIT_STALL[21] TCC_EA_RDREQ[22] TCC_EA_RDREQ_32B[22] TCC_EA_RDREQ_DRAM_CREDIT_STALL[22] TCC_EA_RDREQ_GMI_CREDIT_STALL[22] TCC_EA_RDREQ[23] TCC_EA_RDREQ_32B[23] TCC_EA_RDREQ_DRAM_CREDIT_STALL[23] TCC_EA_RDREQ_GMI_CREDIT_STALL[23] TCC_EA_RDREQ[24] TCC_EA_RDREQ_32B[24] TCC_EA_RDREQ_DRAM_CREDIT_STALL[24] TCC_EA_RDREQ_GMI_CREDIT_STALL[24] TCC_EA_RDREQ[25] TCC_EA_RDREQ_32B[25] TCC_EA_RDREQ_DRAM_CREDIT_STALL[25] TCC_EA_RDREQ_GMI_CREDIT_STALL[25] TCC_EA_RDREQ[26] TCC_EA_RDREQ_32B[26] TCC_EA_RDREQ_DRAM_CREDIT_STALL[26] TCC_EA_RDREQ_GMI_CREDIT_STALL[26] TCC_EA_RDREQ[27] TCC_EA_RDREQ_32B[27] TCC_EA_RDREQ_DRAM_CREDIT_STALL[27] TCC_EA_RDREQ_GMI_CREDIT_STALL[27] TCC_EA_RDREQ[28] TCC_EA_RDREQ_32B[28] TCC_EA_RDREQ_DRAM_CREDIT_STALL[28] TCC_EA_RDREQ_GMI_CREDIT_STALL[28] TCC_EA_RDREQ[29] TCC_EA_RDREQ_32B[29] TCC_EA_RDREQ_DRAM_CREDIT_STALL[29] TCC_EA_RDREQ_GMI_CREDIT_STALL[29] TCC_EA_RDREQ[30] TCC_EA_RDREQ_32B[30] TCC_EA_RDREQ_DRAM_CREDIT_STALL[30] TCC_EA_RDREQ_GMI_CREDIT_STALL[30] TCC_EA_RDREQ[31] TCC_EA_RDREQ_32B[31] TCC_EA_RDREQ_DRAM_CREDIT_STALL[31] TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + +gpu: +range: 6:8 +kernel: diff --git a/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_15.txt b/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_15.txt new file mode 100644 index 0000000000..be9a797c90 --- /dev/null +++ b/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_15.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ[0] TCC_EA_WRREQ_64B[0] TCC_EA_RDREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_LEVEL[1] TCC_EA_WRREQ[1] TCC_EA_WRREQ_64B[1] TCC_EA_RDREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_LEVEL[2] TCC_EA_WRREQ[2] TCC_EA_WRREQ_64B[2] TCC_EA_RDREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_LEVEL[3] TCC_EA_WRREQ[3] TCC_EA_WRREQ_64B[3] TCC_EA_RDREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_LEVEL[4] TCC_EA_WRREQ[4] TCC_EA_WRREQ_64B[4] TCC_EA_RDREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_LEVEL[5] TCC_EA_WRREQ[5] TCC_EA_WRREQ_64B[5] TCC_EA_RDREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_LEVEL[6] TCC_EA_WRREQ[6] TCC_EA_WRREQ_64B[6] TCC_EA_RDREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_LEVEL[7] TCC_EA_WRREQ[7] TCC_EA_WRREQ_64B[7] TCC_EA_RDREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_LEVEL[8] TCC_EA_WRREQ[8] TCC_EA_WRREQ_64B[8] TCC_EA_RDREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_LEVEL[9] TCC_EA_WRREQ[9] TCC_EA_WRREQ_64B[9] TCC_EA_RDREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_LEVEL[10] TCC_EA_WRREQ[10] TCC_EA_WRREQ_64B[10] TCC_EA_RDREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_LEVEL[11] TCC_EA_WRREQ[11] TCC_EA_WRREQ_64B[11] TCC_EA_RDREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_LEVEL[12] TCC_EA_WRREQ[12] TCC_EA_WRREQ_64B[12] TCC_EA_RDREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_LEVEL[13] TCC_EA_WRREQ[13] TCC_EA_WRREQ_64B[13] TCC_EA_RDREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_LEVEL[14] TCC_EA_WRREQ[14] TCC_EA_WRREQ_64B[14] TCC_EA_RDREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_LEVEL[15] TCC_EA_WRREQ[15] TCC_EA_WRREQ_64B[15] TCC_EA_RDREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_LEVEL[16] TCC_EA_WRREQ[16] TCC_EA_WRREQ_64B[16] TCC_EA_RDREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_LEVEL[17] TCC_EA_WRREQ[17] TCC_EA_WRREQ_64B[17] TCC_EA_RDREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_LEVEL[18] TCC_EA_WRREQ[18] TCC_EA_WRREQ_64B[18] TCC_EA_RDREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_LEVEL[19] TCC_EA_WRREQ[19] TCC_EA_WRREQ_64B[19] TCC_EA_RDREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_LEVEL[20] TCC_EA_WRREQ[20] TCC_EA_WRREQ_64B[20] TCC_EA_RDREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_LEVEL[21] TCC_EA_WRREQ[21] TCC_EA_WRREQ_64B[21] TCC_EA_RDREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_LEVEL[22] TCC_EA_WRREQ[22] TCC_EA_WRREQ_64B[22] TCC_EA_RDREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_LEVEL[23] TCC_EA_WRREQ[23] TCC_EA_WRREQ_64B[23] TCC_EA_RDREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_LEVEL[24] TCC_EA_WRREQ[24] TCC_EA_WRREQ_64B[24] TCC_EA_RDREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_LEVEL[25] TCC_EA_WRREQ[25] TCC_EA_WRREQ_64B[25] TCC_EA_RDREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_LEVEL[26] TCC_EA_WRREQ[26] TCC_EA_WRREQ_64B[26] TCC_EA_RDREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_LEVEL[27] TCC_EA_WRREQ[27] TCC_EA_WRREQ_64B[27] TCC_EA_RDREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_LEVEL[28] TCC_EA_WRREQ[28] TCC_EA_WRREQ_64B[28] TCC_EA_RDREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_LEVEL[29] TCC_EA_WRREQ[29] TCC_EA_WRREQ_64B[29] TCC_EA_RDREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_LEVEL[30] TCC_EA_WRREQ[30] TCC_EA_WRREQ_64B[30] TCC_EA_RDREQ_IO_CREDIT_STALL[31] TCC_EA_RDREQ_LEVEL[31] TCC_EA_WRREQ[31] TCC_EA_WRREQ_64B[31] + +gpu: +range: 6:8 +kernel: diff --git a/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_16.txt b/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_16.txt new file mode 100644 index 0000000000..929d5e2cf9 --- /dev/null +++ b/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_16.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_WRREQ_IO_CREDIT_STALL[0] TCC_EA_WRREQ_LEVEL[0] TCC_EA_WRREQ_DRAM_CREDIT_STALL[1] TCC_EA_WRREQ_GMI_CREDIT_STALL[1] TCC_EA_WRREQ_IO_CREDIT_STALL[1] TCC_EA_WRREQ_LEVEL[1] TCC_EA_WRREQ_DRAM_CREDIT_STALL[2] TCC_EA_WRREQ_GMI_CREDIT_STALL[2] TCC_EA_WRREQ_IO_CREDIT_STALL[2] TCC_EA_WRREQ_LEVEL[2] TCC_EA_WRREQ_DRAM_CREDIT_STALL[3] TCC_EA_WRREQ_GMI_CREDIT_STALL[3] TCC_EA_WRREQ_IO_CREDIT_STALL[3] TCC_EA_WRREQ_LEVEL[3] TCC_EA_WRREQ_DRAM_CREDIT_STALL[4] TCC_EA_WRREQ_GMI_CREDIT_STALL[4] TCC_EA_WRREQ_IO_CREDIT_STALL[4] TCC_EA_WRREQ_LEVEL[4] TCC_EA_WRREQ_DRAM_CREDIT_STALL[5] TCC_EA_WRREQ_GMI_CREDIT_STALL[5] TCC_EA_WRREQ_IO_CREDIT_STALL[5] TCC_EA_WRREQ_LEVEL[5] TCC_EA_WRREQ_DRAM_CREDIT_STALL[6] TCC_EA_WRREQ_GMI_CREDIT_STALL[6] TCC_EA_WRREQ_IO_CREDIT_STALL[6] TCC_EA_WRREQ_LEVEL[6] TCC_EA_WRREQ_DRAM_CREDIT_STALL[7] TCC_EA_WRREQ_GMI_CREDIT_STALL[7] TCC_EA_WRREQ_IO_CREDIT_STALL[7] TCC_EA_WRREQ_LEVEL[7] TCC_EA_WRREQ_DRAM_CREDIT_STALL[8] TCC_EA_WRREQ_GMI_CREDIT_STALL[8] TCC_EA_WRREQ_IO_CREDIT_STALL[8] TCC_EA_WRREQ_LEVEL[8] TCC_EA_WRREQ_DRAM_CREDIT_STALL[9] TCC_EA_WRREQ_GMI_CREDIT_STALL[9] TCC_EA_WRREQ_IO_CREDIT_STALL[9] TCC_EA_WRREQ_LEVEL[9] TCC_EA_WRREQ_DRAM_CREDIT_STALL[10] TCC_EA_WRREQ_GMI_CREDIT_STALL[10] TCC_EA_WRREQ_IO_CREDIT_STALL[10] TCC_EA_WRREQ_LEVEL[10] TCC_EA_WRREQ_DRAM_CREDIT_STALL[11] TCC_EA_WRREQ_GMI_CREDIT_STALL[11] TCC_EA_WRREQ_IO_CREDIT_STALL[11] TCC_EA_WRREQ_LEVEL[11] TCC_EA_WRREQ_DRAM_CREDIT_STALL[12] TCC_EA_WRREQ_GMI_CREDIT_STALL[12] TCC_EA_WRREQ_IO_CREDIT_STALL[12] TCC_EA_WRREQ_LEVEL[12] TCC_EA_WRREQ_DRAM_CREDIT_STALL[13] TCC_EA_WRREQ_GMI_CREDIT_STALL[13] TCC_EA_WRREQ_IO_CREDIT_STALL[13] TCC_EA_WRREQ_LEVEL[13] TCC_EA_WRREQ_DRAM_CREDIT_STALL[14] TCC_EA_WRREQ_GMI_CREDIT_STALL[14] TCC_EA_WRREQ_IO_CREDIT_STALL[14] TCC_EA_WRREQ_LEVEL[14] TCC_EA_WRREQ_DRAM_CREDIT_STALL[15] TCC_EA_WRREQ_GMI_CREDIT_STALL[15] TCC_EA_WRREQ_IO_CREDIT_STALL[15] TCC_EA_WRREQ_LEVEL[15] TCC_EA_WRREQ_DRAM_CREDIT_STALL[16] TCC_EA_WRREQ_GMI_CREDIT_STALL[16] TCC_EA_WRREQ_IO_CREDIT_STALL[16] TCC_EA_WRREQ_LEVEL[16] TCC_EA_WRREQ_DRAM_CREDIT_STALL[17] TCC_EA_WRREQ_GMI_CREDIT_STALL[17] TCC_EA_WRREQ_IO_CREDIT_STALL[17] TCC_EA_WRREQ_LEVEL[17] TCC_EA_WRREQ_DRAM_CREDIT_STALL[18] TCC_EA_WRREQ_GMI_CREDIT_STALL[18] TCC_EA_WRREQ_IO_CREDIT_STALL[18] TCC_EA_WRREQ_LEVEL[18] TCC_EA_WRREQ_DRAM_CREDIT_STALL[19] TCC_EA_WRREQ_GMI_CREDIT_STALL[19] TCC_EA_WRREQ_IO_CREDIT_STALL[19] TCC_EA_WRREQ_LEVEL[19] TCC_EA_WRREQ_DRAM_CREDIT_STALL[20] TCC_EA_WRREQ_GMI_CREDIT_STALL[20] TCC_EA_WRREQ_IO_CREDIT_STALL[20] TCC_EA_WRREQ_LEVEL[20] TCC_EA_WRREQ_DRAM_CREDIT_STALL[21] TCC_EA_WRREQ_GMI_CREDIT_STALL[21] TCC_EA_WRREQ_IO_CREDIT_STALL[21] TCC_EA_WRREQ_LEVEL[21] TCC_EA_WRREQ_DRAM_CREDIT_STALL[22] TCC_EA_WRREQ_GMI_CREDIT_STALL[22] TCC_EA_WRREQ_IO_CREDIT_STALL[22] TCC_EA_WRREQ_LEVEL[22] TCC_EA_WRREQ_DRAM_CREDIT_STALL[23] TCC_EA_WRREQ_GMI_CREDIT_STALL[23] TCC_EA_WRREQ_IO_CREDIT_STALL[23] TCC_EA_WRREQ_LEVEL[23] TCC_EA_WRREQ_DRAM_CREDIT_STALL[24] TCC_EA_WRREQ_GMI_CREDIT_STALL[24] TCC_EA_WRREQ_IO_CREDIT_STALL[24] TCC_EA_WRREQ_LEVEL[24] TCC_EA_WRREQ_DRAM_CREDIT_STALL[25] TCC_EA_WRREQ_GMI_CREDIT_STALL[25] TCC_EA_WRREQ_IO_CREDIT_STALL[25] TCC_EA_WRREQ_LEVEL[25] TCC_EA_WRREQ_DRAM_CREDIT_STALL[26] TCC_EA_WRREQ_GMI_CREDIT_STALL[26] TCC_EA_WRREQ_IO_CREDIT_STALL[26] TCC_EA_WRREQ_LEVEL[26] TCC_EA_WRREQ_DRAM_CREDIT_STALL[27] TCC_EA_WRREQ_GMI_CREDIT_STALL[27] TCC_EA_WRREQ_IO_CREDIT_STALL[27] TCC_EA_WRREQ_LEVEL[27] TCC_EA_WRREQ_DRAM_CREDIT_STALL[28] TCC_EA_WRREQ_GMI_CREDIT_STALL[28] TCC_EA_WRREQ_IO_CREDIT_STALL[28] TCC_EA_WRREQ_LEVEL[28] TCC_EA_WRREQ_DRAM_CREDIT_STALL[29] TCC_EA_WRREQ_GMI_CREDIT_STALL[29] TCC_EA_WRREQ_IO_CREDIT_STALL[29] TCC_EA_WRREQ_LEVEL[29] TCC_EA_WRREQ_DRAM_CREDIT_STALL[30] TCC_EA_WRREQ_GMI_CREDIT_STALL[30] TCC_EA_WRREQ_IO_CREDIT_STALL[30] TCC_EA_WRREQ_LEVEL[30] TCC_EA_WRREQ_DRAM_CREDIT_STALL[31] TCC_EA_WRREQ_GMI_CREDIT_STALL[31] TCC_EA_WRREQ_IO_CREDIT_STALL[31] TCC_EA_WRREQ_LEVEL[31] + +gpu: +range: 6:8 +kernel: diff --git a/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_17.txt b/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_17.txt new file mode 100644 index 0000000000..5a234a9e5e --- /dev/null +++ b/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_17.txt @@ -0,0 +1,5 @@ +pmc: TCC_HIT[0] TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_HIT[1] TCC_MISS[1] TCC_READ[1] TCC_REQ[1] TCC_HIT[2] TCC_MISS[2] TCC_READ[2] TCC_REQ[2] TCC_HIT[3] TCC_MISS[3] TCC_READ[3] TCC_REQ[3] TCC_HIT[4] TCC_MISS[4] TCC_READ[4] TCC_REQ[4] TCC_HIT[5] TCC_MISS[5] TCC_READ[5] TCC_REQ[5] TCC_HIT[6] TCC_MISS[6] TCC_READ[6] TCC_REQ[6] TCC_HIT[7] TCC_MISS[7] TCC_READ[7] TCC_REQ[7] TCC_HIT[8] TCC_MISS[8] TCC_READ[8] TCC_REQ[8] TCC_HIT[9] TCC_MISS[9] TCC_READ[9] TCC_REQ[9] TCC_HIT[10] TCC_MISS[10] TCC_READ[10] TCC_REQ[10] TCC_HIT[11] TCC_MISS[11] TCC_READ[11] TCC_REQ[11] TCC_HIT[12] TCC_MISS[12] TCC_READ[12] TCC_REQ[12] TCC_HIT[13] TCC_MISS[13] TCC_READ[13] TCC_REQ[13] TCC_HIT[14] TCC_MISS[14] TCC_READ[14] TCC_REQ[14] TCC_HIT[15] TCC_MISS[15] TCC_READ[15] TCC_REQ[15] TCC_HIT[16] TCC_MISS[16] TCC_READ[16] TCC_REQ[16] TCC_HIT[17] TCC_MISS[17] TCC_READ[17] TCC_REQ[17] TCC_HIT[18] TCC_MISS[18] TCC_READ[18] TCC_REQ[18] TCC_HIT[19] TCC_MISS[19] TCC_READ[19] TCC_REQ[19] TCC_HIT[20] TCC_MISS[20] TCC_READ[20] TCC_REQ[20] TCC_HIT[21] TCC_MISS[21] TCC_READ[21] TCC_REQ[21] TCC_HIT[22] TCC_MISS[22] TCC_READ[22] TCC_REQ[22] TCC_HIT[23] TCC_MISS[23] TCC_READ[23] TCC_REQ[23] TCC_HIT[24] TCC_MISS[24] TCC_READ[24] TCC_REQ[24] TCC_HIT[25] TCC_MISS[25] TCC_READ[25] TCC_REQ[25] TCC_HIT[26] TCC_MISS[26] TCC_READ[26] TCC_REQ[26] TCC_HIT[27] TCC_MISS[27] TCC_READ[27] TCC_REQ[27] TCC_HIT[28] TCC_MISS[28] TCC_READ[28] TCC_REQ[28] TCC_HIT[29] TCC_MISS[29] TCC_READ[29] TCC_REQ[29] TCC_HIT[30] TCC_MISS[30] TCC_READ[30] TCC_REQ[30] TCC_HIT[31] TCC_MISS[31] TCC_READ[31] TCC_REQ[31] + +gpu: +range: 6:8 +kernel: diff --git a/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_18.txt b/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_18.txt new file mode 100644 index 0000000000..599d79b221 --- /dev/null +++ b/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_18.txt @@ -0,0 +1,5 @@ +pmc: TCC_RW_REQ[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_RW_REQ[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_WRITE[1] TCC_RW_REQ[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_WRITE[2] TCC_RW_REQ[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_WRITE[3] TCC_RW_REQ[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_WRITE[4] TCC_RW_REQ[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_WRITE[5] TCC_RW_REQ[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_WRITE[6] TCC_RW_REQ[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_WRITE[7] TCC_RW_REQ[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_WRITE[8] TCC_RW_REQ[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_WRITE[9] TCC_RW_REQ[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_WRITE[10] TCC_RW_REQ[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_WRITE[11] TCC_RW_REQ[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_WRITE[12] TCC_RW_REQ[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_WRITE[13] TCC_RW_REQ[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_WRITE[14] TCC_RW_REQ[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_WRITE[15] TCC_RW_REQ[16] TCC_TOO_MANY_EA_WRREQS_STALL[16] TCC_WRITE[16] TCC_RW_REQ[17] TCC_TOO_MANY_EA_WRREQS_STALL[17] TCC_WRITE[17] TCC_RW_REQ[18] TCC_TOO_MANY_EA_WRREQS_STALL[18] TCC_WRITE[18] TCC_RW_REQ[19] TCC_TOO_MANY_EA_WRREQS_STALL[19] TCC_WRITE[19] TCC_RW_REQ[20] TCC_TOO_MANY_EA_WRREQS_STALL[20] TCC_WRITE[20] TCC_RW_REQ[21] TCC_TOO_MANY_EA_WRREQS_STALL[21] TCC_WRITE[21] TCC_RW_REQ[22] TCC_TOO_MANY_EA_WRREQS_STALL[22] TCC_WRITE[22] TCC_RW_REQ[23] TCC_TOO_MANY_EA_WRREQS_STALL[23] TCC_WRITE[23] TCC_RW_REQ[24] TCC_TOO_MANY_EA_WRREQS_STALL[24] TCC_WRITE[24] TCC_RW_REQ[25] TCC_TOO_MANY_EA_WRREQS_STALL[25] TCC_WRITE[25] TCC_RW_REQ[26] TCC_TOO_MANY_EA_WRREQS_STALL[26] TCC_WRITE[26] TCC_RW_REQ[27] TCC_TOO_MANY_EA_WRREQS_STALL[27] TCC_WRITE[27] TCC_RW_REQ[28] TCC_TOO_MANY_EA_WRREQS_STALL[28] TCC_WRITE[28] TCC_RW_REQ[29] TCC_TOO_MANY_EA_WRREQS_STALL[29] TCC_WRITE[29] TCC_RW_REQ[30] TCC_TOO_MANY_EA_WRREQS_STALL[30] TCC_WRITE[30] TCC_RW_REQ[31] TCC_TOO_MANY_EA_WRREQS_STALL[31] TCC_WRITE[31] + +gpu: +range: 6:8 +kernel: diff --git a/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_2.txt b/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_2.txt new file mode 100644 index 0000000000..fcc12b9b07 --- /dev/null +++ b/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_2.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_MUL_F32 SQ_INSTS_VALU_FMA_F32 SQ_INSTS_VALU_TRANS_F32 SQ_INSTS_VALU_ADD_F64 SQ_INSTS_VALU_MUL_F64 SQ_INSTS_VALU_FMA_F64 SQ_INSTS_VALU_TRANS_F64 SQ_INSTS_VALU_INT32 TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum TA_BUFFER_ATOMIC_WAVEFRONTS_sum TA_BUFFER_TOTAL_CYCLES_sum TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum + +gpu: +range: 6:8 +kernel: diff --git a/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_3.txt b/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_3.txt new file mode 100644 index 0000000000..ffeb03464b --- /dev/null +++ b/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_3.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_INT64 SQ_INSTS_SMEM SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum TD_COALESCABLE_WAVEFRONT_sum SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE CPF_CMP_UTCL1_STALL_ON_TRANSLATION TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum + +gpu: +range: 6:8 +kernel: diff --git a/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_4.txt b/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_4.txt new file mode 100644 index 0000000000..efa176aaaf --- /dev/null +++ b/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_4.txt @@ -0,0 +1,5 @@ +pmc: SQ_WAVE_CYCLES SQ_WAIT_ANY SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_BUSY_CU_CYCLES SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE TCC_EA_WRREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WR_UNCACHED_32B_sum TCC_EA_WRREQ_DRAM_sum + +gpu: +range: 6:8 +kernel: diff --git a/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_5.txt b/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_5.txt new file mode 100644 index 0000000000..70f2706d24 --- /dev/null +++ b/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_5.txt @@ -0,0 +1,5 @@ +pmc: SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU TCP_TCP_LATENCY_sum TCP_TCC_READ_REQ_LATENCY_sum TCP_TCC_WRITE_REQ_LATENCY_sum TCP_TCC_READ_REQ_sum TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN CPC_ME1_DC0_SPI_BUSY TCC_EA_WRREQ_STALL_sum TCC_EA_RDREQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RD_UNCACHED_32B_sum + +gpu: +range: 6:8 +kernel: diff --git a/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_6.txt b/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_6.txt new file mode 100644 index 0000000000..0dbf897eda --- /dev/null +++ b/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_6.txt @@ -0,0 +1,5 @@ +pmc: SQ_THREAD_CYCLES_VALU SQ_IFETCH SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TCP_TCC_NC_READ_REQ_sum TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN TCC_EA_RDREQ_DRAM_sum TCC_TAG_STALL_sum TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum + +gpu: +range: 6:8 +kernel: diff --git a/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_7.txt b/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_7.txt new file mode 100644 index 0000000000..7266b006ef --- /dev/null +++ b/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_7.txt @@ -0,0 +1,5 @@ +pmc: SQ_WAVES_LT_32 SQ_WAVES_LT_16 SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TCP_TCC_UC_WRITE_REQ_sum TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR TCC_NORMAL_EVICT_sum TCC_ALL_TC_OP_INV_EVICT_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA_ATOMIC_sum + +gpu: +range: 6:8 +kernel: diff --git a/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_8.txt b/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_8.txt new file mode 100644 index 0000000000..cd2c98f54f --- /dev/null +++ b/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_8.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM_NORM SQ_INSTS_MFMA SQ_INSTS_VALU_MFMA_I8 SQ_INSTS_VALU_MFMA_F16 SQ_INSTS_VALU_MFMA_BF16 SQ_INSTS_VALU_MFMA_F32 SQ_INSTS_VALU_MFMA_F64 SQ_VALU_MFMA_BUSY_CYCLES TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TCP_TCC_CC_ATOMIC_REQ_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN TCC_EA_RDREQ_LEVEL_sum TCC_EA_WRREQ_LEVEL_sum TCC_EA_ATOMIC_LEVEL_sum + +gpu: +range: 6:8 +kernel: diff --git a/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_9.txt b/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_9.txt new file mode 100644 index 0000000000..fbb8d431aa --- /dev/null +++ b/tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_9.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_FLAT_LDS_ONLY SQ_INSTS_VALU_MFMA_MOPS_I8 SQ_INSTS_VALU_MFMA_MOPS_F16 SQ_INSTS_VALU_MFMA_MOPS_BF16 SQ_INSTS_VALU_MFMA_MOPS_F32 SQ_INSTS_VALU_MFMA_MOPS_F64 SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum TCP_PENDING_STALL_CYCLES_sum + +gpu: +range: 6:8 +kernel: diff --git a/tests/workloads/dispatch_6_8/MI200/perfmon/timestamps.txt b/tests/workloads/dispatch_6_8/MI200/perfmon/timestamps.txt new file mode 100644 index 0000000000..73a5a3d86f --- /dev/null +++ b/tests/workloads/dispatch_6_8/MI200/perfmon/timestamps.txt @@ -0,0 +1,5 @@ +pmc: + +gpu: +range: 6:8 +kernel: diff --git a/tests/workloads/dispatch_6_8/MI200/pmc_perf_0.csv b/tests/workloads/dispatch_6_8/MI200/pmc_perf_0.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/dispatch_6_8/MI200/pmc_perf_0.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/dispatch_6_8/MI200/pmc_perf_1.csv b/tests/workloads/dispatch_6_8/MI200/pmc_perf_1.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/dispatch_6_8/MI200/pmc_perf_1.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/dispatch_6_8/MI200/pmc_perf_10.csv b/tests/workloads/dispatch_6_8/MI200/pmc_perf_10.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/dispatch_6_8/MI200/pmc_perf_10.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/dispatch_6_8/MI200/pmc_perf_11.csv b/tests/workloads/dispatch_6_8/MI200/pmc_perf_11.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/dispatch_6_8/MI200/pmc_perf_11.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/dispatch_6_8/MI200/pmc_perf_12.csv b/tests/workloads/dispatch_6_8/MI200/pmc_perf_12.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/dispatch_6_8/MI200/pmc_perf_12.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/dispatch_6_8/MI200/pmc_perf_13.csv b/tests/workloads/dispatch_6_8/MI200/pmc_perf_13.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/dispatch_6_8/MI200/pmc_perf_13.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/dispatch_6_8/MI200/pmc_perf_14.csv b/tests/workloads/dispatch_6_8/MI200/pmc_perf_14.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/dispatch_6_8/MI200/pmc_perf_14.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/dispatch_6_8/MI200/pmc_perf_15.csv b/tests/workloads/dispatch_6_8/MI200/pmc_perf_15.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/dispatch_6_8/MI200/pmc_perf_15.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/dispatch_6_8/MI200/pmc_perf_16.csv b/tests/workloads/dispatch_6_8/MI200/pmc_perf_16.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/dispatch_6_8/MI200/pmc_perf_16.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/dispatch_6_8/MI200/pmc_perf_17.csv b/tests/workloads/dispatch_6_8/MI200/pmc_perf_17.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/dispatch_6_8/MI200/pmc_perf_17.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/dispatch_6_8/MI200/pmc_perf_18.csv b/tests/workloads/dispatch_6_8/MI200/pmc_perf_18.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/dispatch_6_8/MI200/pmc_perf_18.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/dispatch_6_8/MI200/pmc_perf_2.csv b/tests/workloads/dispatch_6_8/MI200/pmc_perf_2.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/dispatch_6_8/MI200/pmc_perf_2.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/dispatch_6_8/MI200/pmc_perf_3.csv b/tests/workloads/dispatch_6_8/MI200/pmc_perf_3.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/dispatch_6_8/MI200/pmc_perf_3.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/dispatch_6_8/MI200/pmc_perf_4.csv b/tests/workloads/dispatch_6_8/MI200/pmc_perf_4.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/dispatch_6_8/MI200/pmc_perf_4.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/dispatch_6_8/MI200/pmc_perf_5.csv b/tests/workloads/dispatch_6_8/MI200/pmc_perf_5.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/dispatch_6_8/MI200/pmc_perf_5.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/dispatch_6_8/MI200/pmc_perf_6.csv b/tests/workloads/dispatch_6_8/MI200/pmc_perf_6.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/dispatch_6_8/MI200/pmc_perf_6.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/dispatch_6_8/MI200/pmc_perf_7.csv b/tests/workloads/dispatch_6_8/MI200/pmc_perf_7.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/dispatch_6_8/MI200/pmc_perf_7.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/dispatch_6_8/MI200/pmc_perf_8.csv b/tests/workloads/dispatch_6_8/MI200/pmc_perf_8.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/dispatch_6_8/MI200/pmc_perf_8.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/dispatch_6_8/MI200/pmc_perf_9.csv b/tests/workloads/dispatch_6_8/MI200/pmc_perf_9.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/dispatch_6_8/MI200/pmc_perf_9.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/dispatch_6_8/MI200/sysinfo.csv b/tests/workloads/dispatch_6_8/MI200/sysinfo.csv new file mode 100644 index 0000000000..dac3ef144e --- /dev/null +++ b/tests/workloads/dispatch_6_8/MI200/sysinfo.csv @@ -0,0 +1,2 @@ +workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd +dispatch_6_8,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 02:52:17 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/dispatch_6_8/MI200/timestamps.csv b/tests/workloads/dispatch_6_8/MI200/timestamps.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/dispatch_6_8/MI200/timestamps.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/dispatch_7/MI100/sysinfo.csv b/tests/workloads/dispatch_7/MI100/sysinfo.csv index 0d4d982066..a35070f152 100644 --- a/tests/workloads/dispatch_7/MI100/sysinfo.csv +++ b/tests/workloads/dispatch_7/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -dispatch_7,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Fri Mar 1 16:44:46 2024 (CST),1,t006-003.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651240,,5.7.1-98,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +dispatch_7,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 07 Mar 2024 01:07:22 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/dispatch_7/MI200/SQ_IFETCH_LEVEL.csv b/tests/workloads/dispatch_7/MI200/SQ_IFETCH_LEVEL.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/dispatch_7/MI200/SQ_IFETCH_LEVEL.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/dispatch_7/MI200/SQ_INST_LEVEL_LDS.csv b/tests/workloads/dispatch_7/MI200/SQ_INST_LEVEL_LDS.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/dispatch_7/MI200/SQ_INST_LEVEL_LDS.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/dispatch_7/MI200/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/dispatch_7/MI200/SQ_INST_LEVEL_SMEM.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/dispatch_7/MI200/SQ_INST_LEVEL_SMEM.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/dispatch_7/MI200/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/dispatch_7/MI200/SQ_INST_LEVEL_VMEM.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/dispatch_7/MI200/SQ_INST_LEVEL_VMEM.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/dispatch_7/MI200/SQ_LEVEL_WAVES.csv b/tests/workloads/dispatch_7/MI200/SQ_LEVEL_WAVES.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/dispatch_7/MI200/SQ_LEVEL_WAVES.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/dispatch_7/MI200/perfmon/SQ_IFETCH_LEVEL.txt b/tests/workloads/dispatch_7/MI200/perfmon/SQ_IFETCH_LEVEL.txt new file mode 100644 index 0000000000..3029bededa --- /dev/null +++ b/tests/workloads/dispatch_7/MI200/perfmon/SQ_IFETCH_LEVEL.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES + +gpu: +range: 7 +kernel: diff --git a/tests/workloads/dispatch_7/MI200/perfmon/SQ_INST_LEVEL_LDS.txt b/tests/workloads/dispatch_7/MI200/perfmon/SQ_INST_LEVEL_LDS.txt new file mode 100644 index 0000000000..72f0dd7ae0 --- /dev/null +++ b/tests/workloads/dispatch_7/MI200/perfmon/SQ_INST_LEVEL_LDS.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES + +gpu: +range: 7 +kernel: diff --git a/tests/workloads/dispatch_7/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt b/tests/workloads/dispatch_7/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt new file mode 100644 index 0000000000..d1fb435ceb --- /dev/null +++ b/tests/workloads/dispatch_7/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: 7 +kernel: diff --git a/tests/workloads/dispatch_7/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt b/tests/workloads/dispatch_7/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt new file mode 100644 index 0000000000..f2d012a210 --- /dev/null +++ b/tests/workloads/dispatch_7/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: 7 +kernel: diff --git a/tests/workloads/dispatch_7/MI200/perfmon/SQ_LEVEL_WAVES.txt b/tests/workloads/dispatch_7/MI200/perfmon/SQ_LEVEL_WAVES.txt new file mode 100644 index 0000000000..a0472148a3 --- /dev/null +++ b/tests/workloads/dispatch_7/MI200/perfmon/SQ_LEVEL_WAVES.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES + +gpu: +range: 7 +kernel: diff --git a/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_0.txt b/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_0.txt new file mode 100644 index 0000000000..96f9e3419b --- /dev/null +++ b/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_0.txt @@ -0,0 +1,5 @@ +pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES SQ_INSTS_VALU_CVT SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU GRBM_COUNT GRBM_GUI_ACTIVE TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum TA_TA_BUSY_sum TA_BUFFER_WAVEFRONTS_sum TD_TD_BUSY_sum TD_TC_STALL_sum SPI_CSN_WINDOW_VALID SPI_CSN_BUSY CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum + +gpu: +range: 7 +kernel: diff --git a/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_1.txt b/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_1.txt new file mode 100644 index 0000000000..0cf2c41342 --- /dev/null +++ b/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_1.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VSKIPPED SQ_INSTS SQ_INSTS_VALU SQ_INSTS_VALU_ADD_F16 SQ_INSTS_VALU_MUL_F16 SQ_INSTS_VALU_FMA_F16 SQ_INSTS_VALU_TRANS_F16 SQ_INSTS_VALU_ADD_F32 GRBM_SPI_BUSY TCP_READ_TAGCONFLICT_STALL_CYCLES_sum TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum TCP_TA_TCP_STATE_READ_sum TA_BUFFER_READ_WAVEFRONTS_sum TA_BUFFER_WRITE_WAVEFRONTS_sum TD_SPI_STALL_sum TD_LOAD_WAVEFRONT_sum SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum + +gpu: +range: 7 +kernel: diff --git a/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_10.txt b/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_10.txt new file mode 100644 index 0000000000..c8e2ab3008 --- /dev/null +++ b/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_10.txt @@ -0,0 +1,5 @@ +pmc: SQC_TC_DATA_WRITE_REQ SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES + +gpu: +range: 7 +kernel: diff --git a/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_11.txt b/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_11.txt new file mode 100644 index 0000000000..a95853744b --- /dev/null +++ b/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_11.txt @@ -0,0 +1,5 @@ +pmc: SQC_ICACHE_MISSES_DUPLICATE SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE + +gpu: +range: 7 +kernel: diff --git a/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_12.txt b/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_12.txt new file mode 100644 index 0000000000..0e5ee8d749 --- /dev/null +++ b/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_12.txt @@ -0,0 +1,5 @@ +pmc: SQC_DCACHE_REQ_READ_1 SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 + +gpu: +range: 7 +kernel: diff --git a/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_13.txt b/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_13.txt new file mode 100644 index 0000000000..e0c4c358c0 --- /dev/null +++ b/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_13.txt @@ -0,0 +1,5 @@ +pmc: TCC_ATOMIC[0] TCC_CYCLE[0] TCC_EA_ATOMIC[0] TCC_EA_ATOMIC_LEVEL[0] TCC_ATOMIC[1] TCC_CYCLE[1] TCC_EA_ATOMIC[1] TCC_EA_ATOMIC_LEVEL[1] TCC_ATOMIC[2] TCC_CYCLE[2] TCC_EA_ATOMIC[2] TCC_EA_ATOMIC_LEVEL[2] TCC_ATOMIC[3] TCC_CYCLE[3] TCC_EA_ATOMIC[3] TCC_EA_ATOMIC_LEVEL[3] TCC_ATOMIC[4] TCC_CYCLE[4] TCC_EA_ATOMIC[4] TCC_EA_ATOMIC_LEVEL[4] TCC_ATOMIC[5] TCC_CYCLE[5] TCC_EA_ATOMIC[5] TCC_EA_ATOMIC_LEVEL[5] TCC_ATOMIC[6] TCC_CYCLE[6] TCC_EA_ATOMIC[6] TCC_EA_ATOMIC_LEVEL[6] TCC_ATOMIC[7] TCC_CYCLE[7] TCC_EA_ATOMIC[7] TCC_EA_ATOMIC_LEVEL[7] TCC_ATOMIC[8] TCC_CYCLE[8] TCC_EA_ATOMIC[8] TCC_EA_ATOMIC_LEVEL[8] TCC_ATOMIC[9] TCC_CYCLE[9] TCC_EA_ATOMIC[9] TCC_EA_ATOMIC_LEVEL[9] TCC_ATOMIC[10] TCC_CYCLE[10] TCC_EA_ATOMIC[10] TCC_EA_ATOMIC_LEVEL[10] TCC_ATOMIC[11] TCC_CYCLE[11] TCC_EA_ATOMIC[11] TCC_EA_ATOMIC_LEVEL[11] TCC_ATOMIC[12] TCC_CYCLE[12] TCC_EA_ATOMIC[12] TCC_EA_ATOMIC_LEVEL[12] TCC_ATOMIC[13] TCC_CYCLE[13] TCC_EA_ATOMIC[13] TCC_EA_ATOMIC_LEVEL[13] TCC_ATOMIC[14] TCC_CYCLE[14] TCC_EA_ATOMIC[14] TCC_EA_ATOMIC_LEVEL[14] TCC_ATOMIC[15] TCC_CYCLE[15] TCC_EA_ATOMIC[15] TCC_EA_ATOMIC_LEVEL[15] TCC_ATOMIC[16] TCC_CYCLE[16] TCC_EA_ATOMIC[16] TCC_EA_ATOMIC_LEVEL[16] TCC_ATOMIC[17] TCC_CYCLE[17] TCC_EA_ATOMIC[17] TCC_EA_ATOMIC_LEVEL[17] TCC_ATOMIC[18] TCC_CYCLE[18] TCC_EA_ATOMIC[18] TCC_EA_ATOMIC_LEVEL[18] TCC_ATOMIC[19] TCC_CYCLE[19] TCC_EA_ATOMIC[19] TCC_EA_ATOMIC_LEVEL[19] TCC_ATOMIC[20] TCC_CYCLE[20] TCC_EA_ATOMIC[20] TCC_EA_ATOMIC_LEVEL[20] TCC_ATOMIC[21] TCC_CYCLE[21] TCC_EA_ATOMIC[21] TCC_EA_ATOMIC_LEVEL[21] TCC_ATOMIC[22] TCC_CYCLE[22] TCC_EA_ATOMIC[22] TCC_EA_ATOMIC_LEVEL[22] TCC_ATOMIC[23] TCC_CYCLE[23] TCC_EA_ATOMIC[23] TCC_EA_ATOMIC_LEVEL[23] TCC_ATOMIC[24] TCC_CYCLE[24] TCC_EA_ATOMIC[24] TCC_EA_ATOMIC_LEVEL[24] TCC_ATOMIC[25] TCC_CYCLE[25] TCC_EA_ATOMIC[25] TCC_EA_ATOMIC_LEVEL[25] TCC_ATOMIC[26] TCC_CYCLE[26] TCC_EA_ATOMIC[26] TCC_EA_ATOMIC_LEVEL[26] TCC_ATOMIC[27] TCC_CYCLE[27] TCC_EA_ATOMIC[27] TCC_EA_ATOMIC_LEVEL[27] TCC_ATOMIC[28] TCC_CYCLE[28] TCC_EA_ATOMIC[28] TCC_EA_ATOMIC_LEVEL[28] TCC_ATOMIC[29] TCC_CYCLE[29] TCC_EA_ATOMIC[29] TCC_EA_ATOMIC_LEVEL[29] TCC_ATOMIC[30] TCC_CYCLE[30] TCC_EA_ATOMIC[30] TCC_EA_ATOMIC_LEVEL[30] TCC_ATOMIC[31] TCC_CYCLE[31] TCC_EA_ATOMIC[31] TCC_EA_ATOMIC_LEVEL[31] + +gpu: +range: 7 +kernel: diff --git a/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_14.txt b/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_14.txt new file mode 100644 index 0000000000..75cd75ef0b --- /dev/null +++ b/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_14.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_EA_RDREQ_GMI_CREDIT_STALL[0] TCC_EA_RDREQ[1] TCC_EA_RDREQ_32B[1] TCC_EA_RDREQ_DRAM_CREDIT_STALL[1] TCC_EA_RDREQ_GMI_CREDIT_STALL[1] TCC_EA_RDREQ[2] TCC_EA_RDREQ_32B[2] TCC_EA_RDREQ_DRAM_CREDIT_STALL[2] TCC_EA_RDREQ_GMI_CREDIT_STALL[2] TCC_EA_RDREQ[3] TCC_EA_RDREQ_32B[3] TCC_EA_RDREQ_DRAM_CREDIT_STALL[3] TCC_EA_RDREQ_GMI_CREDIT_STALL[3] TCC_EA_RDREQ[4] TCC_EA_RDREQ_32B[4] TCC_EA_RDREQ_DRAM_CREDIT_STALL[4] TCC_EA_RDREQ_GMI_CREDIT_STALL[4] TCC_EA_RDREQ[5] TCC_EA_RDREQ_32B[5] TCC_EA_RDREQ_DRAM_CREDIT_STALL[5] TCC_EA_RDREQ_GMI_CREDIT_STALL[5] TCC_EA_RDREQ[6] TCC_EA_RDREQ_32B[6] TCC_EA_RDREQ_DRAM_CREDIT_STALL[6] TCC_EA_RDREQ_GMI_CREDIT_STALL[6] TCC_EA_RDREQ[7] TCC_EA_RDREQ_32B[7] TCC_EA_RDREQ_DRAM_CREDIT_STALL[7] TCC_EA_RDREQ_GMI_CREDIT_STALL[7] TCC_EA_RDREQ[8] TCC_EA_RDREQ_32B[8] TCC_EA_RDREQ_DRAM_CREDIT_STALL[8] TCC_EA_RDREQ_GMI_CREDIT_STALL[8] TCC_EA_RDREQ[9] TCC_EA_RDREQ_32B[9] TCC_EA_RDREQ_DRAM_CREDIT_STALL[9] TCC_EA_RDREQ_GMI_CREDIT_STALL[9] TCC_EA_RDREQ[10] TCC_EA_RDREQ_32B[10] TCC_EA_RDREQ_DRAM_CREDIT_STALL[10] TCC_EA_RDREQ_GMI_CREDIT_STALL[10] TCC_EA_RDREQ[11] TCC_EA_RDREQ_32B[11] TCC_EA_RDREQ_DRAM_CREDIT_STALL[11] TCC_EA_RDREQ_GMI_CREDIT_STALL[11] TCC_EA_RDREQ[12] TCC_EA_RDREQ_32B[12] TCC_EA_RDREQ_DRAM_CREDIT_STALL[12] TCC_EA_RDREQ_GMI_CREDIT_STALL[12] TCC_EA_RDREQ[13] TCC_EA_RDREQ_32B[13] TCC_EA_RDREQ_DRAM_CREDIT_STALL[13] TCC_EA_RDREQ_GMI_CREDIT_STALL[13] TCC_EA_RDREQ[14] TCC_EA_RDREQ_32B[14] TCC_EA_RDREQ_DRAM_CREDIT_STALL[14] TCC_EA_RDREQ_GMI_CREDIT_STALL[14] TCC_EA_RDREQ[15] TCC_EA_RDREQ_32B[15] TCC_EA_RDREQ_DRAM_CREDIT_STALL[15] TCC_EA_RDREQ_GMI_CREDIT_STALL[15] TCC_EA_RDREQ[16] TCC_EA_RDREQ_32B[16] TCC_EA_RDREQ_DRAM_CREDIT_STALL[16] TCC_EA_RDREQ_GMI_CREDIT_STALL[16] TCC_EA_RDREQ[17] TCC_EA_RDREQ_32B[17] TCC_EA_RDREQ_DRAM_CREDIT_STALL[17] TCC_EA_RDREQ_GMI_CREDIT_STALL[17] TCC_EA_RDREQ[18] TCC_EA_RDREQ_32B[18] TCC_EA_RDREQ_DRAM_CREDIT_STALL[18] TCC_EA_RDREQ_GMI_CREDIT_STALL[18] TCC_EA_RDREQ[19] TCC_EA_RDREQ_32B[19] TCC_EA_RDREQ_DRAM_CREDIT_STALL[19] TCC_EA_RDREQ_GMI_CREDIT_STALL[19] TCC_EA_RDREQ[20] TCC_EA_RDREQ_32B[20] TCC_EA_RDREQ_DRAM_CREDIT_STALL[20] TCC_EA_RDREQ_GMI_CREDIT_STALL[20] TCC_EA_RDREQ[21] TCC_EA_RDREQ_32B[21] TCC_EA_RDREQ_DRAM_CREDIT_STALL[21] TCC_EA_RDREQ_GMI_CREDIT_STALL[21] TCC_EA_RDREQ[22] TCC_EA_RDREQ_32B[22] TCC_EA_RDREQ_DRAM_CREDIT_STALL[22] TCC_EA_RDREQ_GMI_CREDIT_STALL[22] TCC_EA_RDREQ[23] TCC_EA_RDREQ_32B[23] TCC_EA_RDREQ_DRAM_CREDIT_STALL[23] TCC_EA_RDREQ_GMI_CREDIT_STALL[23] TCC_EA_RDREQ[24] TCC_EA_RDREQ_32B[24] TCC_EA_RDREQ_DRAM_CREDIT_STALL[24] TCC_EA_RDREQ_GMI_CREDIT_STALL[24] TCC_EA_RDREQ[25] TCC_EA_RDREQ_32B[25] TCC_EA_RDREQ_DRAM_CREDIT_STALL[25] TCC_EA_RDREQ_GMI_CREDIT_STALL[25] TCC_EA_RDREQ[26] TCC_EA_RDREQ_32B[26] TCC_EA_RDREQ_DRAM_CREDIT_STALL[26] TCC_EA_RDREQ_GMI_CREDIT_STALL[26] TCC_EA_RDREQ[27] TCC_EA_RDREQ_32B[27] TCC_EA_RDREQ_DRAM_CREDIT_STALL[27] TCC_EA_RDREQ_GMI_CREDIT_STALL[27] TCC_EA_RDREQ[28] TCC_EA_RDREQ_32B[28] TCC_EA_RDREQ_DRAM_CREDIT_STALL[28] TCC_EA_RDREQ_GMI_CREDIT_STALL[28] TCC_EA_RDREQ[29] TCC_EA_RDREQ_32B[29] TCC_EA_RDREQ_DRAM_CREDIT_STALL[29] TCC_EA_RDREQ_GMI_CREDIT_STALL[29] TCC_EA_RDREQ[30] TCC_EA_RDREQ_32B[30] TCC_EA_RDREQ_DRAM_CREDIT_STALL[30] TCC_EA_RDREQ_GMI_CREDIT_STALL[30] TCC_EA_RDREQ[31] TCC_EA_RDREQ_32B[31] TCC_EA_RDREQ_DRAM_CREDIT_STALL[31] TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + +gpu: +range: 7 +kernel: diff --git a/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_15.txt b/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_15.txt new file mode 100644 index 0000000000..daa7d522c8 --- /dev/null +++ b/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_15.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ[0] TCC_EA_WRREQ_64B[0] TCC_EA_RDREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_LEVEL[1] TCC_EA_WRREQ[1] TCC_EA_WRREQ_64B[1] TCC_EA_RDREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_LEVEL[2] TCC_EA_WRREQ[2] TCC_EA_WRREQ_64B[2] TCC_EA_RDREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_LEVEL[3] TCC_EA_WRREQ[3] TCC_EA_WRREQ_64B[3] TCC_EA_RDREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_LEVEL[4] TCC_EA_WRREQ[4] TCC_EA_WRREQ_64B[4] TCC_EA_RDREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_LEVEL[5] TCC_EA_WRREQ[5] TCC_EA_WRREQ_64B[5] TCC_EA_RDREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_LEVEL[6] TCC_EA_WRREQ[6] TCC_EA_WRREQ_64B[6] TCC_EA_RDREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_LEVEL[7] TCC_EA_WRREQ[7] TCC_EA_WRREQ_64B[7] TCC_EA_RDREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_LEVEL[8] TCC_EA_WRREQ[8] TCC_EA_WRREQ_64B[8] TCC_EA_RDREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_LEVEL[9] TCC_EA_WRREQ[9] TCC_EA_WRREQ_64B[9] TCC_EA_RDREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_LEVEL[10] TCC_EA_WRREQ[10] TCC_EA_WRREQ_64B[10] TCC_EA_RDREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_LEVEL[11] TCC_EA_WRREQ[11] TCC_EA_WRREQ_64B[11] TCC_EA_RDREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_LEVEL[12] TCC_EA_WRREQ[12] TCC_EA_WRREQ_64B[12] TCC_EA_RDREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_LEVEL[13] TCC_EA_WRREQ[13] TCC_EA_WRREQ_64B[13] TCC_EA_RDREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_LEVEL[14] TCC_EA_WRREQ[14] TCC_EA_WRREQ_64B[14] TCC_EA_RDREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_LEVEL[15] TCC_EA_WRREQ[15] TCC_EA_WRREQ_64B[15] TCC_EA_RDREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_LEVEL[16] TCC_EA_WRREQ[16] TCC_EA_WRREQ_64B[16] TCC_EA_RDREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_LEVEL[17] TCC_EA_WRREQ[17] TCC_EA_WRREQ_64B[17] TCC_EA_RDREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_LEVEL[18] TCC_EA_WRREQ[18] TCC_EA_WRREQ_64B[18] TCC_EA_RDREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_LEVEL[19] TCC_EA_WRREQ[19] TCC_EA_WRREQ_64B[19] TCC_EA_RDREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_LEVEL[20] TCC_EA_WRREQ[20] TCC_EA_WRREQ_64B[20] TCC_EA_RDREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_LEVEL[21] TCC_EA_WRREQ[21] TCC_EA_WRREQ_64B[21] TCC_EA_RDREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_LEVEL[22] TCC_EA_WRREQ[22] TCC_EA_WRREQ_64B[22] TCC_EA_RDREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_LEVEL[23] TCC_EA_WRREQ[23] TCC_EA_WRREQ_64B[23] TCC_EA_RDREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_LEVEL[24] TCC_EA_WRREQ[24] TCC_EA_WRREQ_64B[24] TCC_EA_RDREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_LEVEL[25] TCC_EA_WRREQ[25] TCC_EA_WRREQ_64B[25] TCC_EA_RDREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_LEVEL[26] TCC_EA_WRREQ[26] TCC_EA_WRREQ_64B[26] TCC_EA_RDREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_LEVEL[27] TCC_EA_WRREQ[27] TCC_EA_WRREQ_64B[27] TCC_EA_RDREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_LEVEL[28] TCC_EA_WRREQ[28] TCC_EA_WRREQ_64B[28] TCC_EA_RDREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_LEVEL[29] TCC_EA_WRREQ[29] TCC_EA_WRREQ_64B[29] TCC_EA_RDREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_LEVEL[30] TCC_EA_WRREQ[30] TCC_EA_WRREQ_64B[30] TCC_EA_RDREQ_IO_CREDIT_STALL[31] TCC_EA_RDREQ_LEVEL[31] TCC_EA_WRREQ[31] TCC_EA_WRREQ_64B[31] + +gpu: +range: 7 +kernel: diff --git a/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_16.txt b/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_16.txt new file mode 100644 index 0000000000..9886eda363 --- /dev/null +++ b/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_16.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_WRREQ_IO_CREDIT_STALL[0] TCC_EA_WRREQ_LEVEL[0] TCC_EA_WRREQ_DRAM_CREDIT_STALL[1] TCC_EA_WRREQ_GMI_CREDIT_STALL[1] TCC_EA_WRREQ_IO_CREDIT_STALL[1] TCC_EA_WRREQ_LEVEL[1] TCC_EA_WRREQ_DRAM_CREDIT_STALL[2] TCC_EA_WRREQ_GMI_CREDIT_STALL[2] TCC_EA_WRREQ_IO_CREDIT_STALL[2] TCC_EA_WRREQ_LEVEL[2] TCC_EA_WRREQ_DRAM_CREDIT_STALL[3] TCC_EA_WRREQ_GMI_CREDIT_STALL[3] TCC_EA_WRREQ_IO_CREDIT_STALL[3] TCC_EA_WRREQ_LEVEL[3] TCC_EA_WRREQ_DRAM_CREDIT_STALL[4] TCC_EA_WRREQ_GMI_CREDIT_STALL[4] TCC_EA_WRREQ_IO_CREDIT_STALL[4] TCC_EA_WRREQ_LEVEL[4] TCC_EA_WRREQ_DRAM_CREDIT_STALL[5] TCC_EA_WRREQ_GMI_CREDIT_STALL[5] TCC_EA_WRREQ_IO_CREDIT_STALL[5] TCC_EA_WRREQ_LEVEL[5] TCC_EA_WRREQ_DRAM_CREDIT_STALL[6] TCC_EA_WRREQ_GMI_CREDIT_STALL[6] TCC_EA_WRREQ_IO_CREDIT_STALL[6] TCC_EA_WRREQ_LEVEL[6] TCC_EA_WRREQ_DRAM_CREDIT_STALL[7] TCC_EA_WRREQ_GMI_CREDIT_STALL[7] TCC_EA_WRREQ_IO_CREDIT_STALL[7] TCC_EA_WRREQ_LEVEL[7] TCC_EA_WRREQ_DRAM_CREDIT_STALL[8] TCC_EA_WRREQ_GMI_CREDIT_STALL[8] TCC_EA_WRREQ_IO_CREDIT_STALL[8] TCC_EA_WRREQ_LEVEL[8] TCC_EA_WRREQ_DRAM_CREDIT_STALL[9] TCC_EA_WRREQ_GMI_CREDIT_STALL[9] TCC_EA_WRREQ_IO_CREDIT_STALL[9] TCC_EA_WRREQ_LEVEL[9] TCC_EA_WRREQ_DRAM_CREDIT_STALL[10] TCC_EA_WRREQ_GMI_CREDIT_STALL[10] TCC_EA_WRREQ_IO_CREDIT_STALL[10] TCC_EA_WRREQ_LEVEL[10] TCC_EA_WRREQ_DRAM_CREDIT_STALL[11] TCC_EA_WRREQ_GMI_CREDIT_STALL[11] TCC_EA_WRREQ_IO_CREDIT_STALL[11] TCC_EA_WRREQ_LEVEL[11] TCC_EA_WRREQ_DRAM_CREDIT_STALL[12] TCC_EA_WRREQ_GMI_CREDIT_STALL[12] TCC_EA_WRREQ_IO_CREDIT_STALL[12] TCC_EA_WRREQ_LEVEL[12] TCC_EA_WRREQ_DRAM_CREDIT_STALL[13] TCC_EA_WRREQ_GMI_CREDIT_STALL[13] TCC_EA_WRREQ_IO_CREDIT_STALL[13] TCC_EA_WRREQ_LEVEL[13] TCC_EA_WRREQ_DRAM_CREDIT_STALL[14] TCC_EA_WRREQ_GMI_CREDIT_STALL[14] TCC_EA_WRREQ_IO_CREDIT_STALL[14] TCC_EA_WRREQ_LEVEL[14] TCC_EA_WRREQ_DRAM_CREDIT_STALL[15] TCC_EA_WRREQ_GMI_CREDIT_STALL[15] TCC_EA_WRREQ_IO_CREDIT_STALL[15] TCC_EA_WRREQ_LEVEL[15] TCC_EA_WRREQ_DRAM_CREDIT_STALL[16] TCC_EA_WRREQ_GMI_CREDIT_STALL[16] TCC_EA_WRREQ_IO_CREDIT_STALL[16] TCC_EA_WRREQ_LEVEL[16] TCC_EA_WRREQ_DRAM_CREDIT_STALL[17] TCC_EA_WRREQ_GMI_CREDIT_STALL[17] TCC_EA_WRREQ_IO_CREDIT_STALL[17] TCC_EA_WRREQ_LEVEL[17] TCC_EA_WRREQ_DRAM_CREDIT_STALL[18] TCC_EA_WRREQ_GMI_CREDIT_STALL[18] TCC_EA_WRREQ_IO_CREDIT_STALL[18] TCC_EA_WRREQ_LEVEL[18] TCC_EA_WRREQ_DRAM_CREDIT_STALL[19] TCC_EA_WRREQ_GMI_CREDIT_STALL[19] TCC_EA_WRREQ_IO_CREDIT_STALL[19] TCC_EA_WRREQ_LEVEL[19] TCC_EA_WRREQ_DRAM_CREDIT_STALL[20] TCC_EA_WRREQ_GMI_CREDIT_STALL[20] TCC_EA_WRREQ_IO_CREDIT_STALL[20] TCC_EA_WRREQ_LEVEL[20] TCC_EA_WRREQ_DRAM_CREDIT_STALL[21] TCC_EA_WRREQ_GMI_CREDIT_STALL[21] TCC_EA_WRREQ_IO_CREDIT_STALL[21] TCC_EA_WRREQ_LEVEL[21] TCC_EA_WRREQ_DRAM_CREDIT_STALL[22] TCC_EA_WRREQ_GMI_CREDIT_STALL[22] TCC_EA_WRREQ_IO_CREDIT_STALL[22] TCC_EA_WRREQ_LEVEL[22] TCC_EA_WRREQ_DRAM_CREDIT_STALL[23] TCC_EA_WRREQ_GMI_CREDIT_STALL[23] TCC_EA_WRREQ_IO_CREDIT_STALL[23] TCC_EA_WRREQ_LEVEL[23] TCC_EA_WRREQ_DRAM_CREDIT_STALL[24] TCC_EA_WRREQ_GMI_CREDIT_STALL[24] TCC_EA_WRREQ_IO_CREDIT_STALL[24] TCC_EA_WRREQ_LEVEL[24] TCC_EA_WRREQ_DRAM_CREDIT_STALL[25] TCC_EA_WRREQ_GMI_CREDIT_STALL[25] TCC_EA_WRREQ_IO_CREDIT_STALL[25] TCC_EA_WRREQ_LEVEL[25] TCC_EA_WRREQ_DRAM_CREDIT_STALL[26] TCC_EA_WRREQ_GMI_CREDIT_STALL[26] TCC_EA_WRREQ_IO_CREDIT_STALL[26] TCC_EA_WRREQ_LEVEL[26] TCC_EA_WRREQ_DRAM_CREDIT_STALL[27] TCC_EA_WRREQ_GMI_CREDIT_STALL[27] TCC_EA_WRREQ_IO_CREDIT_STALL[27] TCC_EA_WRREQ_LEVEL[27] TCC_EA_WRREQ_DRAM_CREDIT_STALL[28] TCC_EA_WRREQ_GMI_CREDIT_STALL[28] TCC_EA_WRREQ_IO_CREDIT_STALL[28] TCC_EA_WRREQ_LEVEL[28] TCC_EA_WRREQ_DRAM_CREDIT_STALL[29] TCC_EA_WRREQ_GMI_CREDIT_STALL[29] TCC_EA_WRREQ_IO_CREDIT_STALL[29] TCC_EA_WRREQ_LEVEL[29] TCC_EA_WRREQ_DRAM_CREDIT_STALL[30] TCC_EA_WRREQ_GMI_CREDIT_STALL[30] TCC_EA_WRREQ_IO_CREDIT_STALL[30] TCC_EA_WRREQ_LEVEL[30] TCC_EA_WRREQ_DRAM_CREDIT_STALL[31] TCC_EA_WRREQ_GMI_CREDIT_STALL[31] TCC_EA_WRREQ_IO_CREDIT_STALL[31] TCC_EA_WRREQ_LEVEL[31] + +gpu: +range: 7 +kernel: diff --git a/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_17.txt b/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_17.txt new file mode 100644 index 0000000000..22ea42680e --- /dev/null +++ b/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_17.txt @@ -0,0 +1,5 @@ +pmc: TCC_HIT[0] TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_HIT[1] TCC_MISS[1] TCC_READ[1] TCC_REQ[1] TCC_HIT[2] TCC_MISS[2] TCC_READ[2] TCC_REQ[2] TCC_HIT[3] TCC_MISS[3] TCC_READ[3] TCC_REQ[3] TCC_HIT[4] TCC_MISS[4] TCC_READ[4] TCC_REQ[4] TCC_HIT[5] TCC_MISS[5] TCC_READ[5] TCC_REQ[5] TCC_HIT[6] TCC_MISS[6] TCC_READ[6] TCC_REQ[6] TCC_HIT[7] TCC_MISS[7] TCC_READ[7] TCC_REQ[7] TCC_HIT[8] TCC_MISS[8] TCC_READ[8] TCC_REQ[8] TCC_HIT[9] TCC_MISS[9] TCC_READ[9] TCC_REQ[9] TCC_HIT[10] TCC_MISS[10] TCC_READ[10] TCC_REQ[10] TCC_HIT[11] TCC_MISS[11] TCC_READ[11] TCC_REQ[11] TCC_HIT[12] TCC_MISS[12] TCC_READ[12] TCC_REQ[12] TCC_HIT[13] TCC_MISS[13] TCC_READ[13] TCC_REQ[13] TCC_HIT[14] TCC_MISS[14] TCC_READ[14] TCC_REQ[14] TCC_HIT[15] TCC_MISS[15] TCC_READ[15] TCC_REQ[15] TCC_HIT[16] TCC_MISS[16] TCC_READ[16] TCC_REQ[16] TCC_HIT[17] TCC_MISS[17] TCC_READ[17] TCC_REQ[17] TCC_HIT[18] TCC_MISS[18] TCC_READ[18] TCC_REQ[18] TCC_HIT[19] TCC_MISS[19] TCC_READ[19] TCC_REQ[19] TCC_HIT[20] TCC_MISS[20] TCC_READ[20] TCC_REQ[20] TCC_HIT[21] TCC_MISS[21] TCC_READ[21] TCC_REQ[21] TCC_HIT[22] TCC_MISS[22] TCC_READ[22] TCC_REQ[22] TCC_HIT[23] TCC_MISS[23] TCC_READ[23] TCC_REQ[23] TCC_HIT[24] TCC_MISS[24] TCC_READ[24] TCC_REQ[24] TCC_HIT[25] TCC_MISS[25] TCC_READ[25] TCC_REQ[25] TCC_HIT[26] TCC_MISS[26] TCC_READ[26] TCC_REQ[26] TCC_HIT[27] TCC_MISS[27] TCC_READ[27] TCC_REQ[27] TCC_HIT[28] TCC_MISS[28] TCC_READ[28] TCC_REQ[28] TCC_HIT[29] TCC_MISS[29] TCC_READ[29] TCC_REQ[29] TCC_HIT[30] TCC_MISS[30] TCC_READ[30] TCC_REQ[30] TCC_HIT[31] TCC_MISS[31] TCC_READ[31] TCC_REQ[31] + +gpu: +range: 7 +kernel: diff --git a/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_18.txt b/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_18.txt new file mode 100644 index 0000000000..bc57e80f59 --- /dev/null +++ b/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_18.txt @@ -0,0 +1,5 @@ +pmc: TCC_RW_REQ[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_RW_REQ[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_WRITE[1] TCC_RW_REQ[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_WRITE[2] TCC_RW_REQ[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_WRITE[3] TCC_RW_REQ[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_WRITE[4] TCC_RW_REQ[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_WRITE[5] TCC_RW_REQ[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_WRITE[6] TCC_RW_REQ[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_WRITE[7] TCC_RW_REQ[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_WRITE[8] TCC_RW_REQ[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_WRITE[9] TCC_RW_REQ[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_WRITE[10] TCC_RW_REQ[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_WRITE[11] TCC_RW_REQ[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_WRITE[12] TCC_RW_REQ[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_WRITE[13] TCC_RW_REQ[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_WRITE[14] TCC_RW_REQ[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_WRITE[15] TCC_RW_REQ[16] TCC_TOO_MANY_EA_WRREQS_STALL[16] TCC_WRITE[16] TCC_RW_REQ[17] TCC_TOO_MANY_EA_WRREQS_STALL[17] TCC_WRITE[17] TCC_RW_REQ[18] TCC_TOO_MANY_EA_WRREQS_STALL[18] TCC_WRITE[18] TCC_RW_REQ[19] TCC_TOO_MANY_EA_WRREQS_STALL[19] TCC_WRITE[19] TCC_RW_REQ[20] TCC_TOO_MANY_EA_WRREQS_STALL[20] TCC_WRITE[20] TCC_RW_REQ[21] TCC_TOO_MANY_EA_WRREQS_STALL[21] TCC_WRITE[21] TCC_RW_REQ[22] TCC_TOO_MANY_EA_WRREQS_STALL[22] TCC_WRITE[22] TCC_RW_REQ[23] TCC_TOO_MANY_EA_WRREQS_STALL[23] TCC_WRITE[23] TCC_RW_REQ[24] TCC_TOO_MANY_EA_WRREQS_STALL[24] TCC_WRITE[24] TCC_RW_REQ[25] TCC_TOO_MANY_EA_WRREQS_STALL[25] TCC_WRITE[25] TCC_RW_REQ[26] TCC_TOO_MANY_EA_WRREQS_STALL[26] TCC_WRITE[26] TCC_RW_REQ[27] TCC_TOO_MANY_EA_WRREQS_STALL[27] TCC_WRITE[27] TCC_RW_REQ[28] TCC_TOO_MANY_EA_WRREQS_STALL[28] TCC_WRITE[28] TCC_RW_REQ[29] TCC_TOO_MANY_EA_WRREQS_STALL[29] TCC_WRITE[29] TCC_RW_REQ[30] TCC_TOO_MANY_EA_WRREQS_STALL[30] TCC_WRITE[30] TCC_RW_REQ[31] TCC_TOO_MANY_EA_WRREQS_STALL[31] TCC_WRITE[31] + +gpu: +range: 7 +kernel: diff --git a/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_2.txt b/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_2.txt new file mode 100644 index 0000000000..3b7a02977e --- /dev/null +++ b/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_2.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_MUL_F32 SQ_INSTS_VALU_FMA_F32 SQ_INSTS_VALU_TRANS_F32 SQ_INSTS_VALU_ADD_F64 SQ_INSTS_VALU_MUL_F64 SQ_INSTS_VALU_FMA_F64 SQ_INSTS_VALU_TRANS_F64 SQ_INSTS_VALU_INT32 TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum TA_BUFFER_ATOMIC_WAVEFRONTS_sum TA_BUFFER_TOTAL_CYCLES_sum TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum + +gpu: +range: 7 +kernel: diff --git a/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_3.txt b/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_3.txt new file mode 100644 index 0000000000..5823affb4b --- /dev/null +++ b/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_3.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_INT64 SQ_INSTS_SMEM SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum TD_COALESCABLE_WAVEFRONT_sum SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE CPF_CMP_UTCL1_STALL_ON_TRANSLATION TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum + +gpu: +range: 7 +kernel: diff --git a/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_4.txt b/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_4.txt new file mode 100644 index 0000000000..678994424d --- /dev/null +++ b/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_4.txt @@ -0,0 +1,5 @@ +pmc: SQ_WAVE_CYCLES SQ_WAIT_ANY SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_BUSY_CU_CYCLES SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE TCC_EA_WRREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WR_UNCACHED_32B_sum TCC_EA_WRREQ_DRAM_sum + +gpu: +range: 7 +kernel: diff --git a/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_5.txt b/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_5.txt new file mode 100644 index 0000000000..fd10b0e02c --- /dev/null +++ b/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_5.txt @@ -0,0 +1,5 @@ +pmc: SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU TCP_TCP_LATENCY_sum TCP_TCC_READ_REQ_LATENCY_sum TCP_TCC_WRITE_REQ_LATENCY_sum TCP_TCC_READ_REQ_sum TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN CPC_ME1_DC0_SPI_BUSY TCC_EA_WRREQ_STALL_sum TCC_EA_RDREQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RD_UNCACHED_32B_sum + +gpu: +range: 7 +kernel: diff --git a/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_6.txt b/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_6.txt new file mode 100644 index 0000000000..0991c27a9a --- /dev/null +++ b/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_6.txt @@ -0,0 +1,5 @@ +pmc: SQ_THREAD_CYCLES_VALU SQ_IFETCH SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TCP_TCC_NC_READ_REQ_sum TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN TCC_EA_RDREQ_DRAM_sum TCC_TAG_STALL_sum TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum + +gpu: +range: 7 +kernel: diff --git a/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_7.txt b/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_7.txt new file mode 100644 index 0000000000..5a81466a61 --- /dev/null +++ b/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_7.txt @@ -0,0 +1,5 @@ +pmc: SQ_WAVES_LT_32 SQ_WAVES_LT_16 SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TCP_TCC_UC_WRITE_REQ_sum TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR TCC_NORMAL_EVICT_sum TCC_ALL_TC_OP_INV_EVICT_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA_ATOMIC_sum + +gpu: +range: 7 +kernel: diff --git a/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_8.txt b/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_8.txt new file mode 100644 index 0000000000..829f52df48 --- /dev/null +++ b/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_8.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM_NORM SQ_INSTS_MFMA SQ_INSTS_VALU_MFMA_I8 SQ_INSTS_VALU_MFMA_F16 SQ_INSTS_VALU_MFMA_BF16 SQ_INSTS_VALU_MFMA_F32 SQ_INSTS_VALU_MFMA_F64 SQ_VALU_MFMA_BUSY_CYCLES TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TCP_TCC_CC_ATOMIC_REQ_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN TCC_EA_RDREQ_LEVEL_sum TCC_EA_WRREQ_LEVEL_sum TCC_EA_ATOMIC_LEVEL_sum + +gpu: +range: 7 +kernel: diff --git a/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_9.txt b/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_9.txt new file mode 100644 index 0000000000..74698227fd --- /dev/null +++ b/tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_9.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_FLAT_LDS_ONLY SQ_INSTS_VALU_MFMA_MOPS_I8 SQ_INSTS_VALU_MFMA_MOPS_F16 SQ_INSTS_VALU_MFMA_MOPS_BF16 SQ_INSTS_VALU_MFMA_MOPS_F32 SQ_INSTS_VALU_MFMA_MOPS_F64 SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum TCP_PENDING_STALL_CYCLES_sum + +gpu: +range: 7 +kernel: diff --git a/tests/workloads/dispatch_7/MI200/perfmon/timestamps.txt b/tests/workloads/dispatch_7/MI200/perfmon/timestamps.txt new file mode 100644 index 0000000000..9f369ce301 --- /dev/null +++ b/tests/workloads/dispatch_7/MI200/perfmon/timestamps.txt @@ -0,0 +1,5 @@ +pmc: + +gpu: +range: 7 +kernel: diff --git a/tests/workloads/dispatch_7/MI200/pmc_perf_0.csv b/tests/workloads/dispatch_7/MI200/pmc_perf_0.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/dispatch_7/MI200/pmc_perf_0.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/dispatch_7/MI200/pmc_perf_1.csv b/tests/workloads/dispatch_7/MI200/pmc_perf_1.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/dispatch_7/MI200/pmc_perf_1.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/dispatch_7/MI200/pmc_perf_10.csv b/tests/workloads/dispatch_7/MI200/pmc_perf_10.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/dispatch_7/MI200/pmc_perf_10.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/dispatch_7/MI200/pmc_perf_11.csv b/tests/workloads/dispatch_7/MI200/pmc_perf_11.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/dispatch_7/MI200/pmc_perf_11.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/dispatch_7/MI200/pmc_perf_12.csv b/tests/workloads/dispatch_7/MI200/pmc_perf_12.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/dispatch_7/MI200/pmc_perf_12.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/dispatch_7/MI200/pmc_perf_13.csv b/tests/workloads/dispatch_7/MI200/pmc_perf_13.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/dispatch_7/MI200/pmc_perf_13.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/dispatch_7/MI200/pmc_perf_14.csv b/tests/workloads/dispatch_7/MI200/pmc_perf_14.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/dispatch_7/MI200/pmc_perf_14.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/dispatch_7/MI200/pmc_perf_15.csv b/tests/workloads/dispatch_7/MI200/pmc_perf_15.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/dispatch_7/MI200/pmc_perf_15.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/dispatch_7/MI200/pmc_perf_16.csv b/tests/workloads/dispatch_7/MI200/pmc_perf_16.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/dispatch_7/MI200/pmc_perf_16.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/dispatch_7/MI200/pmc_perf_17.csv b/tests/workloads/dispatch_7/MI200/pmc_perf_17.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/dispatch_7/MI200/pmc_perf_17.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/dispatch_7/MI200/pmc_perf_18.csv b/tests/workloads/dispatch_7/MI200/pmc_perf_18.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/dispatch_7/MI200/pmc_perf_18.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/dispatch_7/MI200/pmc_perf_2.csv b/tests/workloads/dispatch_7/MI200/pmc_perf_2.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/dispatch_7/MI200/pmc_perf_2.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/dispatch_7/MI200/pmc_perf_3.csv b/tests/workloads/dispatch_7/MI200/pmc_perf_3.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/dispatch_7/MI200/pmc_perf_3.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/dispatch_7/MI200/pmc_perf_4.csv b/tests/workloads/dispatch_7/MI200/pmc_perf_4.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/dispatch_7/MI200/pmc_perf_4.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/dispatch_7/MI200/pmc_perf_5.csv b/tests/workloads/dispatch_7/MI200/pmc_perf_5.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/dispatch_7/MI200/pmc_perf_5.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/dispatch_7/MI200/pmc_perf_6.csv b/tests/workloads/dispatch_7/MI200/pmc_perf_6.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/dispatch_7/MI200/pmc_perf_6.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/dispatch_7/MI200/pmc_perf_7.csv b/tests/workloads/dispatch_7/MI200/pmc_perf_7.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/dispatch_7/MI200/pmc_perf_7.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/dispatch_7/MI200/pmc_perf_8.csv b/tests/workloads/dispatch_7/MI200/pmc_perf_8.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/dispatch_7/MI200/pmc_perf_8.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/dispatch_7/MI200/pmc_perf_9.csv b/tests/workloads/dispatch_7/MI200/pmc_perf_9.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/dispatch_7/MI200/pmc_perf_9.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/dispatch_7/MI200/sysinfo.csv b/tests/workloads/dispatch_7/MI200/sysinfo.csv new file mode 100644 index 0000000000..7915957950 --- /dev/null +++ b/tests/workloads/dispatch_7/MI200/sysinfo.csv @@ -0,0 +1,2 @@ +workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd +dispatch_7,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 02:17:14 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/dispatch_7/MI200/timestamps.csv b/tests/workloads/dispatch_7/MI200/timestamps.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/dispatch_7/MI200/timestamps.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/dispatch_inv/MI100/SQ_IFETCH_LEVEL.csv b/tests/workloads/dispatch_inv/MI100/SQ_IFETCH_LEVEL.csv index 81a2b40883..c18b695a2a 100644 --- a/tests/workloads/dispatch_inv/MI100/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/dispatch_inv/MI100/SQ_IFETCH_LEVEL.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2802076,2802076,1048576,256,0,0,8,8,16,64,0x0,0x7f75dfc16e80,49408,49408,16384,65536,14474,1839408,2187670903710904,2187670460808016,2187670460832816,2187670911232314 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,100378,100378,1048576,256,0,0,8,8,16,64,0x0,0x7f626043ce80,47668,47668,16384,65536,29010,1854504,194051411496730,194063713519257,194063713543257,194051419980944 diff --git a/tests/workloads/dispatch_inv/MI100/SQ_INST_LEVEL_LDS.csv b/tests/workloads/dispatch_inv/MI100/SQ_INST_LEVEL_LDS.csv index a95368ce19..1f7bb3d9e6 100644 --- a/tests/workloads/dispatch_inv/MI100/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/dispatch_inv/MI100/SQ_INST_LEVEL_LDS.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2800963,2800963,1048576,256,0,0,8,8,16,64,0x0,0x7f52a8504e80,0,0,0,2187667942143695,2187670460808016,2187670460832816,2187667949765323 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,100568,100568,1048576,256,0,0,8,8,16,64,0x0,0x7fd4ec17ce80,0,0,0,194051899565198,194063713519257,194063713543257,194051907560356 diff --git a/tests/workloads/dispatch_inv/MI100/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/dispatch_inv/MI100/SQ_INST_LEVEL_SMEM.csv index c2d7b0c298..f8fbd94be0 100644 --- a/tests/workloads/dispatch_inv/MI100/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/dispatch_inv/MI100/SQ_INST_LEVEL_SMEM.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2799865,2799865,1048576,256,0,0,8,8,16,64,0x0,0x7fdba7ec8e80,65536,212188,27179520,2187664983133496,2187670460808016,2187670460832816,2187664990601125 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,100757,100757,1048576,256,0,0,8,8,16,64,0x0,0x7f9039444e80,65536,381816,24432184,194052393039211,194063713519257,194063713543257,194052400779427 diff --git a/tests/workloads/dispatch_inv/MI100/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/dispatch_inv/MI100/SQ_INST_LEVEL_VMEM.csv index 187b6ecc32..861cd8a132 100644 --- a/tests/workloads/dispatch_inv/MI100/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/dispatch_inv/MI100/SQ_INST_LEVEL_VMEM.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2800048,2800048,1048576,256,0,0,8,8,16,64,0x0,0x7f49a05c0e80,32768,657081,84118816,2187665433303653,2187670460808016,2187670460832816,2187665440779667 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,100958,100958,1048576,256,0,0,8,8,16,64,0x0,0x7f1524968e80,32768,1335366,85465152,194052885720815,194063713519257,194063713543257,194052895100074 diff --git a/tests/workloads/dispatch_inv/MI100/SQ_LEVEL_WAVES.csv b/tests/workloads/dispatch_inv/MI100/SQ_LEVEL_WAVES.csv index b633fab56a..d0e389b494 100644 --- a/tests/workloads/dispatch_inv/MI100/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/dispatch_inv/MI100/SQ_LEVEL_WAVES.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2800414,2800414,1048576,256,0,0,8,8,16,64,0x0,0x7f3a26ac0e80,47715,47715,15910,381728,16384,25251126,233100,0,101488776,2187666341957413,2187670460808016,2187670460832816,2187666349596293 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,101159,101159,1048576,256,0,0,8,8,16,64,0x0,0x7f37e15b8e80,48091,48091,17290,384736,16384,25334875,235204,0,101833412,194053385787391,194063713519257,194063713543257,194053393562893 diff --git a/tests/workloads/dispatch_inv/MI100/pmc_perf.csv b/tests/workloads/dispatch_inv/MI100/pmc_perf.csv index 8ddff0ca1d..b396c4a573 100644 --- a/tests/workloads/dispatch_inv/MI100/pmc_perf.csv +++ b/tests/workloads/dispatch_inv/MI100/pmc_perf.csv @@ -1,2 +1,2 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_1,obj_1,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_2,obj_2,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_3,obj_3,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_4,obj_4,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_5,obj_5,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_6,obj_6,TCC_EA_ATOMIC_LEVEL_sum,wave_size_7,obj_7,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_8,obj_8,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_9,obj_9,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_10,obj_10,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_11,obj_11,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_12,obj_12,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_13,obj_13,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_14,obj_14,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_15,obj_15,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_16,obj_16,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f60cab68e80,192681,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,14416,30800,9753,550,0,46397,262600.0,0.0,188.0,262412.0,64,0x7fe180ac6e80,0,47871,0,0,0,47871,0,0,0,47871,0,0,0,47871,0,0,0,47871,0,0,0,47871,0,0,0,47871,0,0,0,47871,0,0,0,47871,0,0,0,47871,0,0,0,47871,0,0,0,47871,0,0,0,47871,0,0,0,47871,0,0,0,47871,0,0,0,47871,0,0,0,47871,0,0,0,47871,0,0,0,47871,0,0,0,47871,0,0,0,47871,0,0,0,47871,0,0,0,47871,0,0,0,47871,0,0,0,47871,0,0,0,47871,0,0,0,47871,0,0,0,47871,0,0,0,47871,0,0,0,47871,0,0,0,47871,0,0,0,47871,0,0,64,0x7fe771ac6e80,3367,0,0,1978136,2742,0,0,1867150,1766,0,0,1833359,2664,0,0,1888267,2270,0,0,1816150,1457,0,0,1753118,1047,0,0,1654677,4176,0,0,2027724,3608,0,0,2074162,2483,0,0,1918542,1623,0,0,1796604,2732,0,0,1884282,3153,0,0,1946321,1617,0,0,1878895,2027,0,0,1820069,2769,0,0,1902060,3810,0,0,2023487,3111,0,0,1981324,2054,0,0,1818112,2591,0,0,1782405,3078,0,0,1966729,4530,0,0,2142757,1867,0,0,1808398,1732,0,0,1795154,3321,0,0,1967666,4289,0,0,2113769,2674,0,0,1924816,3523,0,0,2027491,3788,0,0,2022625,3573,0,0,1939912,4843,0,0,2217629,2723,0,0,1891021,64,0x7f18d0e62e80,0,0,192,0,65536,64534,48,1337,31457,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,538,47745,1742,0,48.0,249.0,0.0,262288.0,64,0x7f8d26f7ce80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86358.0,44714.0,131111.0,0.0,64,0x7fc8d65fce80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131460.0,0.0,768.0,131459.0,64,0x7f77032c2e80,0.0,64,0x7f4564b56e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,47356,0,131596.0,131072.0,0.0,131104.0,64,0x7fa59912ae80,376592,228178,3337833,16384,24350210,144,48,0,47073,47073,3775434.0,2960184.0,6177.0,1032470.0,2021855.0,0.0,2951490.0,2640713.0,374943,238116,47073,0,47073,0,1506336.0,956932.0,0.0,0.0,64,0x7f52dd6aee80,32768,0,0,0,16384,16384,393216,21770562,960.0,513847.0,0.0,524288.0,1135739.0,32768.0,0,0,0,16765,131072.0,131072.0,0.0,131072.0,64,0x7f18969dae80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,85037.0,153735.0,64,0x7fe3b360ee80,131072.0,131072.0,0.0,2452033.0,0.0,0.0,113029241.0,64126780.0,64,0x7f518e004e80,0,4284115,4096,4096,0,3501214,4096,4096,0,4766613,4096,4096,0,3631774,4096,4096,0,3739177,4096,4096,0,4627027,4096,4096,0,4026357,4096,4096,0,3459955,4096,4096,0,4132270,4096,4096,0,3907286,4096,4096,0,4939653,4096,4096,0,4463486,4096,4096,0,4794701,4096,4096,0,4377219,4096,4096,0,4876947,4096,4096,0,3513317,4096,4096,0,5278668,4096,4096,0,3019728,4096,4096,0,3937778,4096,4096,0,3547726,4096,4096,0,4196876,4096,4096,0,4479716,4096,4096,0,4628540,4096,4096,0,3964686,4096,4096,0,3182166,4096,4096,0,4430708,4096,4096,0,4002133,4096,4096,0,4678554,4096,4096,0,4450170,4096,4096,0,3976353,4096,4096,0,3143157,4096,4096,0,3452532,4096,4096,64,0x7f8117a1ce80,1907000,360448,163840,0,0,180224,114688,0,69624963.0,199016268.0,77948689.0,131072.0,0.0,676197.0,0,0,26619,91338.0,0.0,0.0,91338.0,64,0x7efc9e7eae80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,141,8195,4240,8336,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8360,4264,8360,64,0x7fb72e006e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,64,0x7f9d777d6e80,4096,0,2227,0,4096,0,19,0,4144,0,810,0,4096,0,627,0,4096,0,480,0,4348,0,1932,0,4096,0,571,0,4096,0,784,0,4096,0,1241,0,4096,0,0,0,4096,0,2605,0,4096,0,2076,0,4217,0,1731,0,4096,0,1197,0,4096,0,803,0,4096,0,4,0,4096,0,1077,0,4096,0,4023,0,4096,0,1107,0,4096,0,702,0,4096,0,1823,0,4096,0,1236,0,4096,0,836,0,4096,0,216,0,4096,0,0,0,4096,0,142,0,4096,0,1744,0,4144,0,1685,0,4096,0,223,0,4099,0,0,0,4096,0,746,0,4096,0,571,0,2187670460808016,2187670460832816 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_1,obj_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_2,obj_2,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_3,obj_3,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_4,obj_4,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_5,obj_5,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_6,obj_6,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_7,obj_7,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_8,obj_8,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_9,obj_9,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_10,obj_10,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_11,obj_11,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_12,obj_12,TCC_EA_ATOMIC_LEVEL_sum,wave_size_13,obj_13,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_14,obj_14,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_15,obj_15,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_16,obj_16,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fa86d120e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,57017.0,120687.0,64,0x7fbfe2004e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,47480,0,131499.0,131072.0,0.0,131104.0,64,0x7fc025a5ce80,1331,0,0,1684615,1241,0,0,1660687,1861,0,0,1651803,1145,0,0,1701557,779,0,0,1603459,1214,0,0,1779568,1791,0,0,1722197,1832,0,0,1746386,715,0,0,1601501,1056,0,0,1576397,2605,0,0,1829070,609,0,0,1633407,1118,0,0,1606097,2322,0,0,1832044,1545,0,0,1725820,802,0,0,1603711,5865,0,0,2224904,1079,0,0,1625376,1339,0,0,1639921,981,0,0,1632177,959,0,0,1632226,2710,0,0,1930909,1542,0,0,1744930,1033,0,0,1629899,1622,0,0,1709431,1967,0,0,1933344,861,0,0,1560684,3022,0,0,1896124,1288,0,0,1695077,1541,0,0,1653531,2553,0,0,1852185,1531,0,0,1712096,64,0x7f9a0950ee80,32768,0,0,0,16384,16384,393216,23411804,960.0,513882.0,0.0,524288.0,1104969.0,32768.0,0,0,0,17404,131072.0,131072.0,0.0,131072.0,64,0x7f3bd8102e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131413.0,0.0,674.0,131412.0,64,0x7f87862f6e80,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,64,0x7feec4b7ce80,4096,0,3368,0,4096,0,983,0,4099,0,1076,0,4096,0,159,0,4096,0,7475,0,4096,0,640,0,4096,0,4327,0,4096,0,1982,0,4096,0,1633,0,4096,0,3389,0,4144,0,2946,0,4096,0,4008,0,4144,0,2380,0,4096,0,4305,0,4096,0,4854,0,4097,0,212,0,4096,0,1122,0,4096,0,4725,0,4096,0,1599,0,4096,0,969,0,4243,0,3018,0,4096,0,1414,0,4096,0,3916,0,4096,0,88,0,4096,0,8,0,4096,0,1848,0,4096,0,3864,0,4096,0,262,0,4096,0,584,0,4096,0,241,0,4096,0,3987,0,4096,0,478,0,64,0x7fb6658f2e80,389200,234648,3409750,16384,24946073,144,48,0,48649,48649,3872532.0,3028791.0,7437.0,1264821.0,2119053.0,0.0,3019823.0,2707922.0,387743,244598,48649,0,48649,0,1556768.0,967322.0,0.0,0.0,64,0x7f04567b8e80,0,8192,4096,8192,0,8192,4096,8192,141,8360,4405,8501,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8240,4144,8240,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f17bbfa6e80,131072.0,131072.0,0.0,2548822.0,0.0,0.0,128759174.0,59741309.0,64,0x7fac5829ae80,188449,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,14082,30466,9744,550,0,46533,262608.0,0.0,188.0,262420.0,64,0x7f43c8166e80,2045156,360448,163840,0,0,180224,114688,0,71011798.0,209930567.0,81329775.0,131072.0,0.0,607422.0,0,0,26574,94204.0,0.0,0.0,94204.0,64,0x7fa533b2ee80,0.0,64,0x7fd9dc9dae80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86444.0,44628.0,131112.0,0.0,64,0x7fa5e3444e80,0,0,192,0,65536,64485,48,1331,31457,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,538,47483,1743,0,48.0,217.0,0.0,262288.0,64,0x7f6085844e80,0,3832605,4096,4096,0,3673784,4096,4096,0,3430738,4096,4096,0,3047997,4096,4096,0,5111374,4096,4096,0,3169517,4096,4096,0,3393920,4096,4096,0,3171252,4096,4096,0,3174715,4096,4096,0,4944689,4096,4096,0,3154798,4096,4096,0,3357818,4096,4096,0,3551138,4096,4096,0,4680239,4096,4096,0,2972474,4096,4096,0,3066952,4096,4096,0,3638371,4096,4096,0,4823148,4096,4096,0,3171402,4096,4096,0,3988047,4096,4096,0,5341242,4096,4096,0,4995249,4096,4096,0,3162568,4096,4096,0,2538109,4096,4096,0,2928889,4096,4096,0,3593153,4096,4096,0,3589396,4096,4096,0,3559980,4096,4096,0,3306367,4096,4096,0,3918173,4096,4096,0,2929314,4096,4096,0,4015677,4096,4096,64,0x7f3857fdae80,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,194063713519257,194063713543257 diff --git a/tests/workloads/dispatch_inv/MI100/sysinfo.csv b/tests/workloads/dispatch_inv/MI100/sysinfo.csv index c5745f84e2..fc0cb7d78a 100644 --- a/tests/workloads/dispatch_inv/MI100/sysinfo.csv +++ b/tests/workloads/dispatch_inv/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -dispatch_inv,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Fri Mar 1 16:42:50 2024 (CST),1,t006-003.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651240,,5.7.1-98,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +dispatch_inv,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 07 Mar 2024 01:05:16 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/dispatch_inv/MI100/timestamps.csv b/tests/workloads/dispatch_inv/MI100/timestamps.csv index eca0d50892..f95c9946ad 100644 --- a/tests/workloads/dispatch_inv/MI100/timestamps.csv +++ b/tests/workloads/dispatch_inv/MI100/timestamps.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,2801893,2801893,1048576,256,0,0,8,8,16,64,0x0,0x7f0e20cdae80,2187670460782592,2187670460808016,2187670460832816,2187670460845640 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,104717,104717,1048576,256,0,0,8,8,16,64,0x0,0x7fa555e9ee80,194063713493885,194063713519257,194063713543257,194063713554520 diff --git a/tests/workloads/dispatch_inv/MI200/SQ_IFETCH_LEVEL.csv b/tests/workloads/dispatch_inv/MI200/SQ_IFETCH_LEVEL.csv new file mode 100644 index 0000000000..a71e5dcad7 --- /dev/null +++ b/tests/workloads/dispatch_inv/MI200/SQ_IFETCH_LEVEL.csv @@ -0,0 +1,2 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,248270,248270,1048576,256,0,0,8,0,16,64,0x0,0x7fee6c1e8ec0,28159,28159,16384,65536,18528,2096508,197314699318636,197327446943430,197327446964070,197314715555093 diff --git a/tests/workloads/dispatch_inv/MI200/SQ_INST_LEVEL_LDS.csv b/tests/workloads/dispatch_inv/MI200/SQ_INST_LEVEL_LDS.csv new file mode 100644 index 0000000000..281f7bfecd --- /dev/null +++ b/tests/workloads/dispatch_inv/MI200/SQ_INST_LEVEL_LDS.csv @@ -0,0 +1,2 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,248472,248472,1048576,256,0,0,8,0,16,64,0x0,0x7f335e55cec0,0,0,0,197315182575180,197327446943430,197327446964070,197315198215128 diff --git a/tests/workloads/dispatch_inv/MI200/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/dispatch_inv/MI200/SQ_INST_LEVEL_SMEM.csv new file mode 100644 index 0000000000..7356929c4a --- /dev/null +++ b/tests/workloads/dispatch_inv/MI200/SQ_INST_LEVEL_SMEM.csv @@ -0,0 +1,2 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,248674,248674,1048576,256,0,0,8,0,16,64,0x0,0x7f09405d0ec0,65536,187198,20922392,197315663370888,197327446943430,197327446964070,197315679715439 diff --git a/tests/workloads/dispatch_inv/MI200/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/dispatch_inv/MI200/SQ_INST_LEVEL_VMEM.csv new file mode 100644 index 0000000000..463ea58766 --- /dev/null +++ b/tests/workloads/dispatch_inv/MI200/SQ_INST_LEVEL_VMEM.csv @@ -0,0 +1,2 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,248877,248877,1048576,256,0,0,8,0,16,64,0x0,0x7f819db68ec0,32768,293897,32918400,197316140235970,197327446943430,197327446964070,197316156066459 diff --git a/tests/workloads/dispatch_inv/MI200/SQ_LEVEL_WAVES.csv b/tests/workloads/dispatch_inv/MI200/SQ_LEVEL_WAVES.csv new file mode 100644 index 0000000000..fdc4eedb25 --- /dev/null +++ b/tests/workloads/dispatch_inv/MI200/SQ_LEVEL_WAVES.csv @@ -0,0 +1,2 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,249077,249077,1048576,256,0,0,8,0,16,64,0x0,0x7f2a00ac0ec0,27945,27945,11402,223568,16384,10871098,128273,0,43994300,197316621462013,197327446943430,197327446964070,197316637162384 diff --git a/tests/workloads/dispatch_inv/MI200/perfmon/SQ_IFETCH_LEVEL.txt b/tests/workloads/dispatch_inv/MI200/perfmon/SQ_IFETCH_LEVEL.txt new file mode 100644 index 0000000000..e7209bdada --- /dev/null +++ b/tests/workloads/dispatch_inv/MI200/perfmon/SQ_IFETCH_LEVEL.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES + +gpu: +range: invalid +kernel: diff --git a/tests/workloads/dispatch_inv/MI200/perfmon/SQ_INST_LEVEL_LDS.txt b/tests/workloads/dispatch_inv/MI200/perfmon/SQ_INST_LEVEL_LDS.txt new file mode 100644 index 0000000000..67fb5049bc --- /dev/null +++ b/tests/workloads/dispatch_inv/MI200/perfmon/SQ_INST_LEVEL_LDS.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES + +gpu: +range: invalid +kernel: diff --git a/tests/workloads/dispatch_inv/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt b/tests/workloads/dispatch_inv/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt new file mode 100644 index 0000000000..81efe0fd5b --- /dev/null +++ b/tests/workloads/dispatch_inv/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: invalid +kernel: diff --git a/tests/workloads/dispatch_inv/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt b/tests/workloads/dispatch_inv/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt new file mode 100644 index 0000000000..bbf5c9dbb7 --- /dev/null +++ b/tests/workloads/dispatch_inv/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: invalid +kernel: diff --git a/tests/workloads/dispatch_inv/MI200/perfmon/SQ_LEVEL_WAVES.txt b/tests/workloads/dispatch_inv/MI200/perfmon/SQ_LEVEL_WAVES.txt new file mode 100644 index 0000000000..1422b5f0d7 --- /dev/null +++ b/tests/workloads/dispatch_inv/MI200/perfmon/SQ_LEVEL_WAVES.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES + +gpu: +range: invalid +kernel: diff --git a/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_0.txt b/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_0.txt new file mode 100644 index 0000000000..ffa1693bc7 --- /dev/null +++ b/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_0.txt @@ -0,0 +1,5 @@ +pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES SQ_INSTS_VALU_CVT SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU GRBM_COUNT GRBM_GUI_ACTIVE TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum TA_TA_BUSY_sum TA_BUFFER_WAVEFRONTS_sum TD_TD_BUSY_sum TD_TC_STALL_sum SPI_CSN_WINDOW_VALID SPI_CSN_BUSY CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum + +gpu: +range: invalid +kernel: diff --git a/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_1.txt b/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_1.txt new file mode 100644 index 0000000000..f2b1f887b4 --- /dev/null +++ b/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_1.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VSKIPPED SQ_INSTS SQ_INSTS_VALU SQ_INSTS_VALU_ADD_F16 SQ_INSTS_VALU_MUL_F16 SQ_INSTS_VALU_FMA_F16 SQ_INSTS_VALU_TRANS_F16 SQ_INSTS_VALU_ADD_F32 GRBM_SPI_BUSY TCP_READ_TAGCONFLICT_STALL_CYCLES_sum TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum TCP_TA_TCP_STATE_READ_sum TA_BUFFER_READ_WAVEFRONTS_sum TA_BUFFER_WRITE_WAVEFRONTS_sum TD_SPI_STALL_sum TD_LOAD_WAVEFRONT_sum SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum + +gpu: +range: invalid +kernel: diff --git a/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_10.txt b/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_10.txt new file mode 100644 index 0000000000..3d0526095d --- /dev/null +++ b/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_10.txt @@ -0,0 +1,5 @@ +pmc: SQC_TC_DATA_WRITE_REQ SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES + +gpu: +range: invalid +kernel: diff --git a/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_11.txt b/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_11.txt new file mode 100644 index 0000000000..8ed618995a --- /dev/null +++ b/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_11.txt @@ -0,0 +1,5 @@ +pmc: SQC_ICACHE_MISSES_DUPLICATE SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE + +gpu: +range: invalid +kernel: diff --git a/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_12.txt b/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_12.txt new file mode 100644 index 0000000000..e530ceb729 --- /dev/null +++ b/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_12.txt @@ -0,0 +1,5 @@ +pmc: SQC_DCACHE_REQ_READ_1 SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 + +gpu: +range: invalid +kernel: diff --git a/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_13.txt b/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_13.txt new file mode 100644 index 0000000000..aa172720a9 --- /dev/null +++ b/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_13.txt @@ -0,0 +1,5 @@ +pmc: TCC_ATOMIC[0] TCC_CYCLE[0] TCC_EA_ATOMIC[0] TCC_EA_ATOMIC_LEVEL[0] TCC_ATOMIC[1] TCC_CYCLE[1] TCC_EA_ATOMIC[1] TCC_EA_ATOMIC_LEVEL[1] TCC_ATOMIC[2] TCC_CYCLE[2] TCC_EA_ATOMIC[2] TCC_EA_ATOMIC_LEVEL[2] TCC_ATOMIC[3] TCC_CYCLE[3] TCC_EA_ATOMIC[3] TCC_EA_ATOMIC_LEVEL[3] TCC_ATOMIC[4] TCC_CYCLE[4] TCC_EA_ATOMIC[4] TCC_EA_ATOMIC_LEVEL[4] TCC_ATOMIC[5] TCC_CYCLE[5] TCC_EA_ATOMIC[5] TCC_EA_ATOMIC_LEVEL[5] TCC_ATOMIC[6] TCC_CYCLE[6] TCC_EA_ATOMIC[6] TCC_EA_ATOMIC_LEVEL[6] TCC_ATOMIC[7] TCC_CYCLE[7] TCC_EA_ATOMIC[7] TCC_EA_ATOMIC_LEVEL[7] TCC_ATOMIC[8] TCC_CYCLE[8] TCC_EA_ATOMIC[8] TCC_EA_ATOMIC_LEVEL[8] TCC_ATOMIC[9] TCC_CYCLE[9] TCC_EA_ATOMIC[9] TCC_EA_ATOMIC_LEVEL[9] TCC_ATOMIC[10] TCC_CYCLE[10] TCC_EA_ATOMIC[10] TCC_EA_ATOMIC_LEVEL[10] TCC_ATOMIC[11] TCC_CYCLE[11] TCC_EA_ATOMIC[11] TCC_EA_ATOMIC_LEVEL[11] TCC_ATOMIC[12] TCC_CYCLE[12] TCC_EA_ATOMIC[12] TCC_EA_ATOMIC_LEVEL[12] TCC_ATOMIC[13] TCC_CYCLE[13] TCC_EA_ATOMIC[13] TCC_EA_ATOMIC_LEVEL[13] TCC_ATOMIC[14] TCC_CYCLE[14] TCC_EA_ATOMIC[14] TCC_EA_ATOMIC_LEVEL[14] TCC_ATOMIC[15] TCC_CYCLE[15] TCC_EA_ATOMIC[15] TCC_EA_ATOMIC_LEVEL[15] TCC_ATOMIC[16] TCC_CYCLE[16] TCC_EA_ATOMIC[16] TCC_EA_ATOMIC_LEVEL[16] TCC_ATOMIC[17] TCC_CYCLE[17] TCC_EA_ATOMIC[17] TCC_EA_ATOMIC_LEVEL[17] TCC_ATOMIC[18] TCC_CYCLE[18] TCC_EA_ATOMIC[18] TCC_EA_ATOMIC_LEVEL[18] TCC_ATOMIC[19] TCC_CYCLE[19] TCC_EA_ATOMIC[19] TCC_EA_ATOMIC_LEVEL[19] TCC_ATOMIC[20] TCC_CYCLE[20] TCC_EA_ATOMIC[20] TCC_EA_ATOMIC_LEVEL[20] TCC_ATOMIC[21] TCC_CYCLE[21] TCC_EA_ATOMIC[21] TCC_EA_ATOMIC_LEVEL[21] TCC_ATOMIC[22] TCC_CYCLE[22] TCC_EA_ATOMIC[22] TCC_EA_ATOMIC_LEVEL[22] TCC_ATOMIC[23] TCC_CYCLE[23] TCC_EA_ATOMIC[23] TCC_EA_ATOMIC_LEVEL[23] TCC_ATOMIC[24] TCC_CYCLE[24] TCC_EA_ATOMIC[24] TCC_EA_ATOMIC_LEVEL[24] TCC_ATOMIC[25] TCC_CYCLE[25] TCC_EA_ATOMIC[25] TCC_EA_ATOMIC_LEVEL[25] TCC_ATOMIC[26] TCC_CYCLE[26] TCC_EA_ATOMIC[26] TCC_EA_ATOMIC_LEVEL[26] TCC_ATOMIC[27] TCC_CYCLE[27] TCC_EA_ATOMIC[27] TCC_EA_ATOMIC_LEVEL[27] TCC_ATOMIC[28] TCC_CYCLE[28] TCC_EA_ATOMIC[28] TCC_EA_ATOMIC_LEVEL[28] TCC_ATOMIC[29] TCC_CYCLE[29] TCC_EA_ATOMIC[29] TCC_EA_ATOMIC_LEVEL[29] TCC_ATOMIC[30] TCC_CYCLE[30] TCC_EA_ATOMIC[30] TCC_EA_ATOMIC_LEVEL[30] TCC_ATOMIC[31] TCC_CYCLE[31] TCC_EA_ATOMIC[31] TCC_EA_ATOMIC_LEVEL[31] + +gpu: +range: invalid +kernel: diff --git a/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_14.txt b/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_14.txt new file mode 100644 index 0000000000..2ebfdba4b4 --- /dev/null +++ b/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_14.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_EA_RDREQ_GMI_CREDIT_STALL[0] TCC_EA_RDREQ[1] TCC_EA_RDREQ_32B[1] TCC_EA_RDREQ_DRAM_CREDIT_STALL[1] TCC_EA_RDREQ_GMI_CREDIT_STALL[1] TCC_EA_RDREQ[2] TCC_EA_RDREQ_32B[2] TCC_EA_RDREQ_DRAM_CREDIT_STALL[2] TCC_EA_RDREQ_GMI_CREDIT_STALL[2] TCC_EA_RDREQ[3] TCC_EA_RDREQ_32B[3] TCC_EA_RDREQ_DRAM_CREDIT_STALL[3] TCC_EA_RDREQ_GMI_CREDIT_STALL[3] TCC_EA_RDREQ[4] TCC_EA_RDREQ_32B[4] TCC_EA_RDREQ_DRAM_CREDIT_STALL[4] TCC_EA_RDREQ_GMI_CREDIT_STALL[4] TCC_EA_RDREQ[5] TCC_EA_RDREQ_32B[5] TCC_EA_RDREQ_DRAM_CREDIT_STALL[5] TCC_EA_RDREQ_GMI_CREDIT_STALL[5] TCC_EA_RDREQ[6] TCC_EA_RDREQ_32B[6] TCC_EA_RDREQ_DRAM_CREDIT_STALL[6] TCC_EA_RDREQ_GMI_CREDIT_STALL[6] TCC_EA_RDREQ[7] TCC_EA_RDREQ_32B[7] TCC_EA_RDREQ_DRAM_CREDIT_STALL[7] TCC_EA_RDREQ_GMI_CREDIT_STALL[7] TCC_EA_RDREQ[8] TCC_EA_RDREQ_32B[8] TCC_EA_RDREQ_DRAM_CREDIT_STALL[8] TCC_EA_RDREQ_GMI_CREDIT_STALL[8] TCC_EA_RDREQ[9] TCC_EA_RDREQ_32B[9] TCC_EA_RDREQ_DRAM_CREDIT_STALL[9] TCC_EA_RDREQ_GMI_CREDIT_STALL[9] TCC_EA_RDREQ[10] TCC_EA_RDREQ_32B[10] TCC_EA_RDREQ_DRAM_CREDIT_STALL[10] TCC_EA_RDREQ_GMI_CREDIT_STALL[10] TCC_EA_RDREQ[11] TCC_EA_RDREQ_32B[11] TCC_EA_RDREQ_DRAM_CREDIT_STALL[11] TCC_EA_RDREQ_GMI_CREDIT_STALL[11] TCC_EA_RDREQ[12] TCC_EA_RDREQ_32B[12] TCC_EA_RDREQ_DRAM_CREDIT_STALL[12] TCC_EA_RDREQ_GMI_CREDIT_STALL[12] TCC_EA_RDREQ[13] TCC_EA_RDREQ_32B[13] TCC_EA_RDREQ_DRAM_CREDIT_STALL[13] TCC_EA_RDREQ_GMI_CREDIT_STALL[13] TCC_EA_RDREQ[14] TCC_EA_RDREQ_32B[14] TCC_EA_RDREQ_DRAM_CREDIT_STALL[14] TCC_EA_RDREQ_GMI_CREDIT_STALL[14] TCC_EA_RDREQ[15] TCC_EA_RDREQ_32B[15] TCC_EA_RDREQ_DRAM_CREDIT_STALL[15] TCC_EA_RDREQ_GMI_CREDIT_STALL[15] TCC_EA_RDREQ[16] TCC_EA_RDREQ_32B[16] TCC_EA_RDREQ_DRAM_CREDIT_STALL[16] TCC_EA_RDREQ_GMI_CREDIT_STALL[16] TCC_EA_RDREQ[17] TCC_EA_RDREQ_32B[17] TCC_EA_RDREQ_DRAM_CREDIT_STALL[17] TCC_EA_RDREQ_GMI_CREDIT_STALL[17] TCC_EA_RDREQ[18] TCC_EA_RDREQ_32B[18] TCC_EA_RDREQ_DRAM_CREDIT_STALL[18] TCC_EA_RDREQ_GMI_CREDIT_STALL[18] TCC_EA_RDREQ[19] TCC_EA_RDREQ_32B[19] TCC_EA_RDREQ_DRAM_CREDIT_STALL[19] TCC_EA_RDREQ_GMI_CREDIT_STALL[19] TCC_EA_RDREQ[20] TCC_EA_RDREQ_32B[20] TCC_EA_RDREQ_DRAM_CREDIT_STALL[20] TCC_EA_RDREQ_GMI_CREDIT_STALL[20] TCC_EA_RDREQ[21] TCC_EA_RDREQ_32B[21] TCC_EA_RDREQ_DRAM_CREDIT_STALL[21] TCC_EA_RDREQ_GMI_CREDIT_STALL[21] TCC_EA_RDREQ[22] TCC_EA_RDREQ_32B[22] TCC_EA_RDREQ_DRAM_CREDIT_STALL[22] TCC_EA_RDREQ_GMI_CREDIT_STALL[22] TCC_EA_RDREQ[23] TCC_EA_RDREQ_32B[23] TCC_EA_RDREQ_DRAM_CREDIT_STALL[23] TCC_EA_RDREQ_GMI_CREDIT_STALL[23] TCC_EA_RDREQ[24] TCC_EA_RDREQ_32B[24] TCC_EA_RDREQ_DRAM_CREDIT_STALL[24] TCC_EA_RDREQ_GMI_CREDIT_STALL[24] TCC_EA_RDREQ[25] TCC_EA_RDREQ_32B[25] TCC_EA_RDREQ_DRAM_CREDIT_STALL[25] TCC_EA_RDREQ_GMI_CREDIT_STALL[25] TCC_EA_RDREQ[26] TCC_EA_RDREQ_32B[26] TCC_EA_RDREQ_DRAM_CREDIT_STALL[26] TCC_EA_RDREQ_GMI_CREDIT_STALL[26] TCC_EA_RDREQ[27] TCC_EA_RDREQ_32B[27] TCC_EA_RDREQ_DRAM_CREDIT_STALL[27] TCC_EA_RDREQ_GMI_CREDIT_STALL[27] TCC_EA_RDREQ[28] TCC_EA_RDREQ_32B[28] TCC_EA_RDREQ_DRAM_CREDIT_STALL[28] TCC_EA_RDREQ_GMI_CREDIT_STALL[28] TCC_EA_RDREQ[29] TCC_EA_RDREQ_32B[29] TCC_EA_RDREQ_DRAM_CREDIT_STALL[29] TCC_EA_RDREQ_GMI_CREDIT_STALL[29] TCC_EA_RDREQ[30] TCC_EA_RDREQ_32B[30] TCC_EA_RDREQ_DRAM_CREDIT_STALL[30] TCC_EA_RDREQ_GMI_CREDIT_STALL[30] TCC_EA_RDREQ[31] TCC_EA_RDREQ_32B[31] TCC_EA_RDREQ_DRAM_CREDIT_STALL[31] TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + +gpu: +range: invalid +kernel: diff --git a/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_15.txt b/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_15.txt new file mode 100644 index 0000000000..595907c8e9 --- /dev/null +++ b/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_15.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ[0] TCC_EA_WRREQ_64B[0] TCC_EA_RDREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_LEVEL[1] TCC_EA_WRREQ[1] TCC_EA_WRREQ_64B[1] TCC_EA_RDREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_LEVEL[2] TCC_EA_WRREQ[2] TCC_EA_WRREQ_64B[2] TCC_EA_RDREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_LEVEL[3] TCC_EA_WRREQ[3] TCC_EA_WRREQ_64B[3] TCC_EA_RDREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_LEVEL[4] TCC_EA_WRREQ[4] TCC_EA_WRREQ_64B[4] TCC_EA_RDREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_LEVEL[5] TCC_EA_WRREQ[5] TCC_EA_WRREQ_64B[5] TCC_EA_RDREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_LEVEL[6] TCC_EA_WRREQ[6] TCC_EA_WRREQ_64B[6] TCC_EA_RDREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_LEVEL[7] TCC_EA_WRREQ[7] TCC_EA_WRREQ_64B[7] TCC_EA_RDREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_LEVEL[8] TCC_EA_WRREQ[8] TCC_EA_WRREQ_64B[8] TCC_EA_RDREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_LEVEL[9] TCC_EA_WRREQ[9] TCC_EA_WRREQ_64B[9] TCC_EA_RDREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_LEVEL[10] TCC_EA_WRREQ[10] TCC_EA_WRREQ_64B[10] TCC_EA_RDREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_LEVEL[11] TCC_EA_WRREQ[11] TCC_EA_WRREQ_64B[11] TCC_EA_RDREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_LEVEL[12] TCC_EA_WRREQ[12] TCC_EA_WRREQ_64B[12] TCC_EA_RDREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_LEVEL[13] TCC_EA_WRREQ[13] TCC_EA_WRREQ_64B[13] TCC_EA_RDREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_LEVEL[14] TCC_EA_WRREQ[14] TCC_EA_WRREQ_64B[14] TCC_EA_RDREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_LEVEL[15] TCC_EA_WRREQ[15] TCC_EA_WRREQ_64B[15] TCC_EA_RDREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_LEVEL[16] TCC_EA_WRREQ[16] TCC_EA_WRREQ_64B[16] TCC_EA_RDREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_LEVEL[17] TCC_EA_WRREQ[17] TCC_EA_WRREQ_64B[17] TCC_EA_RDREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_LEVEL[18] TCC_EA_WRREQ[18] TCC_EA_WRREQ_64B[18] TCC_EA_RDREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_LEVEL[19] TCC_EA_WRREQ[19] TCC_EA_WRREQ_64B[19] TCC_EA_RDREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_LEVEL[20] TCC_EA_WRREQ[20] TCC_EA_WRREQ_64B[20] TCC_EA_RDREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_LEVEL[21] TCC_EA_WRREQ[21] TCC_EA_WRREQ_64B[21] TCC_EA_RDREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_LEVEL[22] TCC_EA_WRREQ[22] TCC_EA_WRREQ_64B[22] TCC_EA_RDREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_LEVEL[23] TCC_EA_WRREQ[23] TCC_EA_WRREQ_64B[23] TCC_EA_RDREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_LEVEL[24] TCC_EA_WRREQ[24] TCC_EA_WRREQ_64B[24] TCC_EA_RDREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_LEVEL[25] TCC_EA_WRREQ[25] TCC_EA_WRREQ_64B[25] TCC_EA_RDREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_LEVEL[26] TCC_EA_WRREQ[26] TCC_EA_WRREQ_64B[26] TCC_EA_RDREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_LEVEL[27] TCC_EA_WRREQ[27] TCC_EA_WRREQ_64B[27] TCC_EA_RDREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_LEVEL[28] TCC_EA_WRREQ[28] TCC_EA_WRREQ_64B[28] TCC_EA_RDREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_LEVEL[29] TCC_EA_WRREQ[29] TCC_EA_WRREQ_64B[29] TCC_EA_RDREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_LEVEL[30] TCC_EA_WRREQ[30] TCC_EA_WRREQ_64B[30] TCC_EA_RDREQ_IO_CREDIT_STALL[31] TCC_EA_RDREQ_LEVEL[31] TCC_EA_WRREQ[31] TCC_EA_WRREQ_64B[31] + +gpu: +range: invalid +kernel: diff --git a/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_16.txt b/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_16.txt new file mode 100644 index 0000000000..3abef42045 --- /dev/null +++ b/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_16.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_WRREQ_IO_CREDIT_STALL[0] TCC_EA_WRREQ_LEVEL[0] TCC_EA_WRREQ_DRAM_CREDIT_STALL[1] TCC_EA_WRREQ_GMI_CREDIT_STALL[1] TCC_EA_WRREQ_IO_CREDIT_STALL[1] TCC_EA_WRREQ_LEVEL[1] TCC_EA_WRREQ_DRAM_CREDIT_STALL[2] TCC_EA_WRREQ_GMI_CREDIT_STALL[2] TCC_EA_WRREQ_IO_CREDIT_STALL[2] TCC_EA_WRREQ_LEVEL[2] TCC_EA_WRREQ_DRAM_CREDIT_STALL[3] TCC_EA_WRREQ_GMI_CREDIT_STALL[3] TCC_EA_WRREQ_IO_CREDIT_STALL[3] TCC_EA_WRREQ_LEVEL[3] TCC_EA_WRREQ_DRAM_CREDIT_STALL[4] TCC_EA_WRREQ_GMI_CREDIT_STALL[4] TCC_EA_WRREQ_IO_CREDIT_STALL[4] TCC_EA_WRREQ_LEVEL[4] TCC_EA_WRREQ_DRAM_CREDIT_STALL[5] TCC_EA_WRREQ_GMI_CREDIT_STALL[5] TCC_EA_WRREQ_IO_CREDIT_STALL[5] TCC_EA_WRREQ_LEVEL[5] TCC_EA_WRREQ_DRAM_CREDIT_STALL[6] TCC_EA_WRREQ_GMI_CREDIT_STALL[6] TCC_EA_WRREQ_IO_CREDIT_STALL[6] TCC_EA_WRREQ_LEVEL[6] TCC_EA_WRREQ_DRAM_CREDIT_STALL[7] TCC_EA_WRREQ_GMI_CREDIT_STALL[7] TCC_EA_WRREQ_IO_CREDIT_STALL[7] TCC_EA_WRREQ_LEVEL[7] TCC_EA_WRREQ_DRAM_CREDIT_STALL[8] TCC_EA_WRREQ_GMI_CREDIT_STALL[8] TCC_EA_WRREQ_IO_CREDIT_STALL[8] TCC_EA_WRREQ_LEVEL[8] TCC_EA_WRREQ_DRAM_CREDIT_STALL[9] TCC_EA_WRREQ_GMI_CREDIT_STALL[9] TCC_EA_WRREQ_IO_CREDIT_STALL[9] TCC_EA_WRREQ_LEVEL[9] TCC_EA_WRREQ_DRAM_CREDIT_STALL[10] TCC_EA_WRREQ_GMI_CREDIT_STALL[10] TCC_EA_WRREQ_IO_CREDIT_STALL[10] TCC_EA_WRREQ_LEVEL[10] TCC_EA_WRREQ_DRAM_CREDIT_STALL[11] TCC_EA_WRREQ_GMI_CREDIT_STALL[11] TCC_EA_WRREQ_IO_CREDIT_STALL[11] TCC_EA_WRREQ_LEVEL[11] TCC_EA_WRREQ_DRAM_CREDIT_STALL[12] TCC_EA_WRREQ_GMI_CREDIT_STALL[12] TCC_EA_WRREQ_IO_CREDIT_STALL[12] TCC_EA_WRREQ_LEVEL[12] TCC_EA_WRREQ_DRAM_CREDIT_STALL[13] TCC_EA_WRREQ_GMI_CREDIT_STALL[13] TCC_EA_WRREQ_IO_CREDIT_STALL[13] TCC_EA_WRREQ_LEVEL[13] TCC_EA_WRREQ_DRAM_CREDIT_STALL[14] TCC_EA_WRREQ_GMI_CREDIT_STALL[14] TCC_EA_WRREQ_IO_CREDIT_STALL[14] TCC_EA_WRREQ_LEVEL[14] TCC_EA_WRREQ_DRAM_CREDIT_STALL[15] TCC_EA_WRREQ_GMI_CREDIT_STALL[15] TCC_EA_WRREQ_IO_CREDIT_STALL[15] TCC_EA_WRREQ_LEVEL[15] TCC_EA_WRREQ_DRAM_CREDIT_STALL[16] TCC_EA_WRREQ_GMI_CREDIT_STALL[16] TCC_EA_WRREQ_IO_CREDIT_STALL[16] TCC_EA_WRREQ_LEVEL[16] TCC_EA_WRREQ_DRAM_CREDIT_STALL[17] TCC_EA_WRREQ_GMI_CREDIT_STALL[17] TCC_EA_WRREQ_IO_CREDIT_STALL[17] TCC_EA_WRREQ_LEVEL[17] TCC_EA_WRREQ_DRAM_CREDIT_STALL[18] TCC_EA_WRREQ_GMI_CREDIT_STALL[18] TCC_EA_WRREQ_IO_CREDIT_STALL[18] TCC_EA_WRREQ_LEVEL[18] TCC_EA_WRREQ_DRAM_CREDIT_STALL[19] TCC_EA_WRREQ_GMI_CREDIT_STALL[19] TCC_EA_WRREQ_IO_CREDIT_STALL[19] TCC_EA_WRREQ_LEVEL[19] TCC_EA_WRREQ_DRAM_CREDIT_STALL[20] TCC_EA_WRREQ_GMI_CREDIT_STALL[20] TCC_EA_WRREQ_IO_CREDIT_STALL[20] TCC_EA_WRREQ_LEVEL[20] TCC_EA_WRREQ_DRAM_CREDIT_STALL[21] TCC_EA_WRREQ_GMI_CREDIT_STALL[21] TCC_EA_WRREQ_IO_CREDIT_STALL[21] TCC_EA_WRREQ_LEVEL[21] TCC_EA_WRREQ_DRAM_CREDIT_STALL[22] TCC_EA_WRREQ_GMI_CREDIT_STALL[22] TCC_EA_WRREQ_IO_CREDIT_STALL[22] TCC_EA_WRREQ_LEVEL[22] TCC_EA_WRREQ_DRAM_CREDIT_STALL[23] TCC_EA_WRREQ_GMI_CREDIT_STALL[23] TCC_EA_WRREQ_IO_CREDIT_STALL[23] TCC_EA_WRREQ_LEVEL[23] TCC_EA_WRREQ_DRAM_CREDIT_STALL[24] TCC_EA_WRREQ_GMI_CREDIT_STALL[24] TCC_EA_WRREQ_IO_CREDIT_STALL[24] TCC_EA_WRREQ_LEVEL[24] TCC_EA_WRREQ_DRAM_CREDIT_STALL[25] TCC_EA_WRREQ_GMI_CREDIT_STALL[25] TCC_EA_WRREQ_IO_CREDIT_STALL[25] TCC_EA_WRREQ_LEVEL[25] TCC_EA_WRREQ_DRAM_CREDIT_STALL[26] TCC_EA_WRREQ_GMI_CREDIT_STALL[26] TCC_EA_WRREQ_IO_CREDIT_STALL[26] TCC_EA_WRREQ_LEVEL[26] TCC_EA_WRREQ_DRAM_CREDIT_STALL[27] TCC_EA_WRREQ_GMI_CREDIT_STALL[27] TCC_EA_WRREQ_IO_CREDIT_STALL[27] TCC_EA_WRREQ_LEVEL[27] TCC_EA_WRREQ_DRAM_CREDIT_STALL[28] TCC_EA_WRREQ_GMI_CREDIT_STALL[28] TCC_EA_WRREQ_IO_CREDIT_STALL[28] TCC_EA_WRREQ_LEVEL[28] TCC_EA_WRREQ_DRAM_CREDIT_STALL[29] TCC_EA_WRREQ_GMI_CREDIT_STALL[29] TCC_EA_WRREQ_IO_CREDIT_STALL[29] TCC_EA_WRREQ_LEVEL[29] TCC_EA_WRREQ_DRAM_CREDIT_STALL[30] TCC_EA_WRREQ_GMI_CREDIT_STALL[30] TCC_EA_WRREQ_IO_CREDIT_STALL[30] TCC_EA_WRREQ_LEVEL[30] TCC_EA_WRREQ_DRAM_CREDIT_STALL[31] TCC_EA_WRREQ_GMI_CREDIT_STALL[31] TCC_EA_WRREQ_IO_CREDIT_STALL[31] TCC_EA_WRREQ_LEVEL[31] + +gpu: +range: invalid +kernel: diff --git a/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_17.txt b/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_17.txt new file mode 100644 index 0000000000..82a4b5dce2 --- /dev/null +++ b/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_17.txt @@ -0,0 +1,5 @@ +pmc: TCC_HIT[0] TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_HIT[1] TCC_MISS[1] TCC_READ[1] TCC_REQ[1] TCC_HIT[2] TCC_MISS[2] TCC_READ[2] TCC_REQ[2] TCC_HIT[3] TCC_MISS[3] TCC_READ[3] TCC_REQ[3] TCC_HIT[4] TCC_MISS[4] TCC_READ[4] TCC_REQ[4] TCC_HIT[5] TCC_MISS[5] TCC_READ[5] TCC_REQ[5] TCC_HIT[6] TCC_MISS[6] TCC_READ[6] TCC_REQ[6] TCC_HIT[7] TCC_MISS[7] TCC_READ[7] TCC_REQ[7] TCC_HIT[8] TCC_MISS[8] TCC_READ[8] TCC_REQ[8] TCC_HIT[9] TCC_MISS[9] TCC_READ[9] TCC_REQ[9] TCC_HIT[10] TCC_MISS[10] TCC_READ[10] TCC_REQ[10] TCC_HIT[11] TCC_MISS[11] TCC_READ[11] TCC_REQ[11] TCC_HIT[12] TCC_MISS[12] TCC_READ[12] TCC_REQ[12] TCC_HIT[13] TCC_MISS[13] TCC_READ[13] TCC_REQ[13] TCC_HIT[14] TCC_MISS[14] TCC_READ[14] TCC_REQ[14] TCC_HIT[15] TCC_MISS[15] TCC_READ[15] TCC_REQ[15] TCC_HIT[16] TCC_MISS[16] TCC_READ[16] TCC_REQ[16] TCC_HIT[17] TCC_MISS[17] TCC_READ[17] TCC_REQ[17] TCC_HIT[18] TCC_MISS[18] TCC_READ[18] TCC_REQ[18] TCC_HIT[19] TCC_MISS[19] TCC_READ[19] TCC_REQ[19] TCC_HIT[20] TCC_MISS[20] TCC_READ[20] TCC_REQ[20] TCC_HIT[21] TCC_MISS[21] TCC_READ[21] TCC_REQ[21] TCC_HIT[22] TCC_MISS[22] TCC_READ[22] TCC_REQ[22] TCC_HIT[23] TCC_MISS[23] TCC_READ[23] TCC_REQ[23] TCC_HIT[24] TCC_MISS[24] TCC_READ[24] TCC_REQ[24] TCC_HIT[25] TCC_MISS[25] TCC_READ[25] TCC_REQ[25] TCC_HIT[26] TCC_MISS[26] TCC_READ[26] TCC_REQ[26] TCC_HIT[27] TCC_MISS[27] TCC_READ[27] TCC_REQ[27] TCC_HIT[28] TCC_MISS[28] TCC_READ[28] TCC_REQ[28] TCC_HIT[29] TCC_MISS[29] TCC_READ[29] TCC_REQ[29] TCC_HIT[30] TCC_MISS[30] TCC_READ[30] TCC_REQ[30] TCC_HIT[31] TCC_MISS[31] TCC_READ[31] TCC_REQ[31] + +gpu: +range: invalid +kernel: diff --git a/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_18.txt b/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_18.txt new file mode 100644 index 0000000000..4a07aa911c --- /dev/null +++ b/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_18.txt @@ -0,0 +1,5 @@ +pmc: TCC_RW_REQ[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_RW_REQ[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_WRITE[1] TCC_RW_REQ[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_WRITE[2] TCC_RW_REQ[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_WRITE[3] TCC_RW_REQ[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_WRITE[4] TCC_RW_REQ[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_WRITE[5] TCC_RW_REQ[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_WRITE[6] TCC_RW_REQ[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_WRITE[7] TCC_RW_REQ[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_WRITE[8] TCC_RW_REQ[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_WRITE[9] TCC_RW_REQ[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_WRITE[10] TCC_RW_REQ[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_WRITE[11] TCC_RW_REQ[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_WRITE[12] TCC_RW_REQ[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_WRITE[13] TCC_RW_REQ[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_WRITE[14] TCC_RW_REQ[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_WRITE[15] TCC_RW_REQ[16] TCC_TOO_MANY_EA_WRREQS_STALL[16] TCC_WRITE[16] TCC_RW_REQ[17] TCC_TOO_MANY_EA_WRREQS_STALL[17] TCC_WRITE[17] TCC_RW_REQ[18] TCC_TOO_MANY_EA_WRREQS_STALL[18] TCC_WRITE[18] TCC_RW_REQ[19] TCC_TOO_MANY_EA_WRREQS_STALL[19] TCC_WRITE[19] TCC_RW_REQ[20] TCC_TOO_MANY_EA_WRREQS_STALL[20] TCC_WRITE[20] TCC_RW_REQ[21] TCC_TOO_MANY_EA_WRREQS_STALL[21] TCC_WRITE[21] TCC_RW_REQ[22] TCC_TOO_MANY_EA_WRREQS_STALL[22] TCC_WRITE[22] TCC_RW_REQ[23] TCC_TOO_MANY_EA_WRREQS_STALL[23] TCC_WRITE[23] TCC_RW_REQ[24] TCC_TOO_MANY_EA_WRREQS_STALL[24] TCC_WRITE[24] TCC_RW_REQ[25] TCC_TOO_MANY_EA_WRREQS_STALL[25] TCC_WRITE[25] TCC_RW_REQ[26] TCC_TOO_MANY_EA_WRREQS_STALL[26] TCC_WRITE[26] TCC_RW_REQ[27] TCC_TOO_MANY_EA_WRREQS_STALL[27] TCC_WRITE[27] TCC_RW_REQ[28] TCC_TOO_MANY_EA_WRREQS_STALL[28] TCC_WRITE[28] TCC_RW_REQ[29] TCC_TOO_MANY_EA_WRREQS_STALL[29] TCC_WRITE[29] TCC_RW_REQ[30] TCC_TOO_MANY_EA_WRREQS_STALL[30] TCC_WRITE[30] TCC_RW_REQ[31] TCC_TOO_MANY_EA_WRREQS_STALL[31] TCC_WRITE[31] + +gpu: +range: invalid +kernel: diff --git a/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_2.txt b/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_2.txt new file mode 100644 index 0000000000..529847d543 --- /dev/null +++ b/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_2.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_MUL_F32 SQ_INSTS_VALU_FMA_F32 SQ_INSTS_VALU_TRANS_F32 SQ_INSTS_VALU_ADD_F64 SQ_INSTS_VALU_MUL_F64 SQ_INSTS_VALU_FMA_F64 SQ_INSTS_VALU_TRANS_F64 SQ_INSTS_VALU_INT32 TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum TA_BUFFER_ATOMIC_WAVEFRONTS_sum TA_BUFFER_TOTAL_CYCLES_sum TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum + +gpu: +range: invalid +kernel: diff --git a/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_3.txt b/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_3.txt new file mode 100644 index 0000000000..fee4e56532 --- /dev/null +++ b/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_3.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_INT64 SQ_INSTS_SMEM SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum TD_COALESCABLE_WAVEFRONT_sum SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE CPF_CMP_UTCL1_STALL_ON_TRANSLATION TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum + +gpu: +range: invalid +kernel: diff --git a/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_4.txt b/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_4.txt new file mode 100644 index 0000000000..200816fdef --- /dev/null +++ b/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_4.txt @@ -0,0 +1,5 @@ +pmc: SQ_WAVE_CYCLES SQ_WAIT_ANY SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_BUSY_CU_CYCLES SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE TCC_EA_WRREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WR_UNCACHED_32B_sum TCC_EA_WRREQ_DRAM_sum + +gpu: +range: invalid +kernel: diff --git a/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_5.txt b/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_5.txt new file mode 100644 index 0000000000..c42b95fe42 --- /dev/null +++ b/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_5.txt @@ -0,0 +1,5 @@ +pmc: SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU TCP_TCP_LATENCY_sum TCP_TCC_READ_REQ_LATENCY_sum TCP_TCC_WRITE_REQ_LATENCY_sum TCP_TCC_READ_REQ_sum TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN CPC_ME1_DC0_SPI_BUSY TCC_EA_WRREQ_STALL_sum TCC_EA_RDREQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RD_UNCACHED_32B_sum + +gpu: +range: invalid +kernel: diff --git a/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_6.txt b/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_6.txt new file mode 100644 index 0000000000..6b1226367c --- /dev/null +++ b/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_6.txt @@ -0,0 +1,5 @@ +pmc: SQ_THREAD_CYCLES_VALU SQ_IFETCH SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TCP_TCC_NC_READ_REQ_sum TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN TCC_EA_RDREQ_DRAM_sum TCC_TAG_STALL_sum TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum + +gpu: +range: invalid +kernel: diff --git a/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_7.txt b/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_7.txt new file mode 100644 index 0000000000..237e94974d --- /dev/null +++ b/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_7.txt @@ -0,0 +1,5 @@ +pmc: SQ_WAVES_LT_32 SQ_WAVES_LT_16 SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TCP_TCC_UC_WRITE_REQ_sum TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR TCC_NORMAL_EVICT_sum TCC_ALL_TC_OP_INV_EVICT_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA_ATOMIC_sum + +gpu: +range: invalid +kernel: diff --git a/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_8.txt b/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_8.txt new file mode 100644 index 0000000000..d5bdf09d81 --- /dev/null +++ b/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_8.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM_NORM SQ_INSTS_MFMA SQ_INSTS_VALU_MFMA_I8 SQ_INSTS_VALU_MFMA_F16 SQ_INSTS_VALU_MFMA_BF16 SQ_INSTS_VALU_MFMA_F32 SQ_INSTS_VALU_MFMA_F64 SQ_VALU_MFMA_BUSY_CYCLES TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TCP_TCC_CC_ATOMIC_REQ_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN TCC_EA_RDREQ_LEVEL_sum TCC_EA_WRREQ_LEVEL_sum TCC_EA_ATOMIC_LEVEL_sum + +gpu: +range: invalid +kernel: diff --git a/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_9.txt b/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_9.txt new file mode 100644 index 0000000000..5effdba6ff --- /dev/null +++ b/tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_9.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_FLAT_LDS_ONLY SQ_INSTS_VALU_MFMA_MOPS_I8 SQ_INSTS_VALU_MFMA_MOPS_F16 SQ_INSTS_VALU_MFMA_MOPS_BF16 SQ_INSTS_VALU_MFMA_MOPS_F32 SQ_INSTS_VALU_MFMA_MOPS_F64 SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum TCP_PENDING_STALL_CYCLES_sum + +gpu: +range: invalid +kernel: diff --git a/tests/workloads/dispatch_inv/MI200/perfmon/timestamps.txt b/tests/workloads/dispatch_inv/MI200/perfmon/timestamps.txt new file mode 100644 index 0000000000..6a128303a2 --- /dev/null +++ b/tests/workloads/dispatch_inv/MI200/perfmon/timestamps.txt @@ -0,0 +1,5 @@ +pmc: + +gpu: +range: invalid +kernel: diff --git a/tests/workloads/dispatch_inv/MI200/pmc_perf.csv b/tests/workloads/dispatch_inv/MI200/pmc_perf.csv new file mode 100644 index 0000000000..c0fd6a1e47 --- /dev/null +++ b/tests/workloads/dispatch_inv/MI200/pmc_perf.csv @@ -0,0 +1,2 @@ +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,wave_size_1,obj_1,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_2,obj_2,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_3,obj_3,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_4,obj_4,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_5,obj_5,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,TCC_EA_ATOMIC_LEVEL_sum,wave_size_6,obj_6,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_7,obj_7,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_8,obj_8,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_9,obj_9,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_10,obj_10,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_11,obj_11,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_DRAM_sum,TCC_TAG_STALL_sum,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,wave_size_12,obj_12,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_13,obj_13,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_14,obj_14,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_15,obj_15,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_16,obj_16,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_17,obj_17,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,TD_COALESCABLE_WAVEFRONT_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_18,obj_18,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7fe1bb20cec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65551.0,0.0,0.0,0.0,64,0x7f3874a74ec0,0,1097200,4096,4096,0,1199653,4096,4096,0,1028773,4096,4096,0,1561528,4096,4096,0,1266742,4096,4096,0,1456356,4096,4096,0,1307832,4096,4096,0,1630491,4096,4096,0,1333695,4096,4096,0,1087211,4096,4096,0,1214691,4096,4096,0,1050612,4096,4096,0,1321283,4096,4096,0,1281606,4096,4096,0,1485071,4096,4096,0,1169175,4096,4096,0,1605275,4096,4096,0,1232186,4096,4096,0,1212127,4096,4096,0,1359730,4096,4096,0,1365995,4096,4096,0,1242651,4096,4096,0,1467441,4096,4096,0,1411604,4096,4096,0,1274583,4096,4096,0,1379246,4096,4096,0,1079984,4096,4096,0,1140860,4096,4096,0,1238929,4096,4096,0,1245134,4096,4096,0,1255696,4096,4096,0,1377782,4096,4096,64,0x7f9e7c560ec0,32768,32768,0,64,0x7f67ef650ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,12433,19287,8428,550,0,26694,204653.0,0.0,73573.0,131080.0,64,0x7f1d33dc4ec0,11223900,10020405,859431,344064,1675711,0,0,163840,832.0,515136.0,0.0,524288.0,269911.0,32768.0,519167,0,0,11712,131072.0,131072.0,0.0,131072.0,64,0x7f831b6acec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,40613004.0,34430496.0,0.0,64,0x7f8694874ec0,1305,119483,0,0,65536,63800,56,1680,64,0x7f406e490ec0,4096,0,0,0,4098,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,25,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,134,0,4096,0,352,0,4097,0,0,0,4097,0,17,0,4098,0,0,0,4096,0,0,0,4096,0,4,0,4099,0,0,0,4096,0,0,0,4096,0,120,0,4096,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,64,0x7f74523b8ec0,6364,0,4096,6418,0,4096,6326,0,4096,6344,0,4096,6356,0,4096,6421,0,4096,6362,0,4096,6376,0,4096,6374,0,4096,6362,0,4096,6419,0,4096,6324,0,4096,6343,0,4096,6364,0,4096,6425,0,4096,6369,0,4096,6387,0,4096,6349,0,4096,6380,0,4096,6410,0,4096,6363,0,4096,6356,0,4096,6382,0,4096,6576,0,4096,6410,0,4096,6390,0,4096,6351,0,4096,6380,0,4096,6412,0,4096,6365,0,4096,6356,0,4096,6381,0,4096,64,0x7f179fe04ec0,0,0,0,944777,0,0,0,984414,0,0,0,1149505,0,0,0,1084910,0,0,0,1159461,0,0,0,1123970,0,0,0,1014104,164,0,0,1262814,0,0,0,1002301,0,0,0,1037667,0,0,0,1039564,0,0,0,1144267,0,0,0,1013199,0,0,0,1143132,0,0,0,1106921,0,0,0,1114293,0,0,0,1145664,0,0,0,987066,0,0,0,989777,0,0,0,1089378,0,0,0,1094827,0,0,0,1128129,0,0,0,1066917,0,0,0,1072102,0,0,0,1056696,0,0,0,1072245,0,0,0,978155,0,0,0,1034294,0,0,0,1018866,0,0,0,1058529,0,0,0,1077004,0,0,0,1163029,64,0x7fd999f10ec0,0,0,0,0,0,0,168,56,131072.0,131072.0,0.0,947648.0,64,0x7f569def8ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131081.0,35137.0,46179.0,19357.0,64,0x7fcc4f2e8ec0,2273,4096,2273,6369,2229,4096,2229,6325,2292,4096,2292,6388,2280,4096,2280,6376,2222,4096,2222,6318,2238,4096,2238,6334,2274,4096,2274,6370,2317,4096,2317,6413,2315,4096,2315,6411,2271,4096,2271,6367,2234,4096,2234,6330,2292,4096,2292,6388,2281,4096,2281,6377,2218,4096,2218,6314,2240,4096,2240,6336,2275,4096,2275,6371,2268,4096,2268,6364,2350,4097,2351,6447,2242,4099,2245,6341,2254,4096,2254,6350,2291,4096,2291,6387,2271,4096,2271,6367,2233,4096,2233,6329,2389,4098,2391,6487,2224,4096,2224,6320,2272,4096,2272,6368,2299,4096,2299,6395,2240,4096,2240,6336,2253,4096,2253,6349,2292,4096,2292,6388,2274,4096,2274,6370,2236,4096,2236,6332,64,0x7fd3b30ccec0,232872,131873,16384,0,16384,16384,32768,49152,29108,29108,1991774.0,1410302.0,3617.0,174286.0,1102732.0,0.0,1402036.0,1103813.0,231161,139992,29108,0,29108,0,931456.0,496992.0,0.0,0.0,64,0x7f1147b28ec0,0,393216,163840,0,0,0,0,0,17968,0.0,0.0,0.0,32768.0,0.0,0.0,383.0,32768.0,4096,16384,352,28036,1892,0,56.0,5.0,0.0,204641.0,64,0x7ffb609c0ec0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,64,0x7fab2506cec0,0,0,0,224,0,65536,64260,56,64,0x7f4b84fe8ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,9202,0,814,27754,0,73211.0,131072.0,0.0,65568.0,64,0x7fdfed6d4ec0,114688,0,32768,32768,16384,16384,65536,49152,27679468.0,87536879.0,40795347.0,131072.0,0.0,196124.0,0,0,15278,1812.0,131084.0,0.0,16.0,197327446943430,197327446964070 diff --git a/tests/workloads/dispatch_inv/MI200/roofline.csv b/tests/workloads/dispatch_inv/MI200/roofline.csv new file mode 100644 index 0000000000..556e1ee880 --- /dev/null +++ b/tests/workloads/dispatch_inv/MI200/roofline.csv @@ -0,0 +1,5 @@ +device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh +0,1388.5352,1387.9612,1389.1091,5015.9067,5012.9795,5018.834,9222.8076,9222.2178,9223.3975,18052.672,18051.719,18053.625,20935.363,20875.119,20995.607,20266.707,20265.77,20267.645,170447.69,170443.23,170452.14,164876.22,164871.3,164881.14,41420.414,41419.844,41420.984,41477.77,41477.254,41478.285,166338.45,165842.38,166834.53 +1,1389.2339,1388.7003,1389.7675,5027.8267,5025.6963,5029.957,9235.0215,9234.4062,9235.6367,18093.281,18089.494,18097.068,20974.221,20906.723,21041.719,20295.463,20294.809,20296.117,170853.08,170848.84,170857.31,165136.75,165133,165140.5,41495.602,41494.711,41496.492,41552.312,41551.637,41552.988,166910.98,166908.33,166913.64 +2,1388.1539,1387.5933,1388.7146,5035.959,5033.6694,5038.2485,9263.0859,9262.3916,9263.7803,18110.701,18109.838,18111.564,21052.15,21051.787,21052.514,20358.631,20358.045,20359.217,171151.48,171147.84,171155.12,165561.08,165557.56,165564.59,41593.766,41592.574,41594.957,41652.289,41651.02,41653.559,167010.91,166416.05,167605.77 +3,1388.6646,1388.1143,1389.2148,5031.4497,5030.1416,5032.7578,9240.3379,9239.8271,9240.8486,18023.123,18019.518,18026.729,21031.461,21031.051,21031.871,20311.738,20311.039,20312.438,171003.95,171001.52,171006.39,165217.39,165214.22,165220.56,41438.289,41279.395,41597.184,41580.961,41580.465,41581.457,167015.88,167013.78,167017.97 diff --git a/tests/workloads/dispatch_inv/MI200/sysinfo.csv b/tests/workloads/dispatch_inv/MI200/sysinfo.csv new file mode 100644 index 0000000000..7137cbc9ac --- /dev/null +++ b/tests/workloads/dispatch_inv/MI200/sysinfo.csv @@ -0,0 +1,2 @@ +workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd +dispatch_inv,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 01:59:41 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/dispatch_inv/MI200/timestamps.csv b/tests/workloads/dispatch_inv/MI200/timestamps.csv new file mode 100644 index 0000000000..5aaa68b29b --- /dev/null +++ b/tests/workloads/dispatch_inv/MI200/timestamps.csv @@ -0,0 +1,2 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,253003,253003,1048576,256,0,0,8,0,16,64,0x0,0x7f70cdd84ec0,197327446918845,197327446943430,197327446964070,197327446982486 diff --git a/tests/workloads/dispatch_invalid/MI100/SQ_IFETCH_LEVEL.csv b/tests/workloads/dispatch_invalid/MI100/SQ_IFETCH_LEVEL.csv new file mode 100644 index 0000000000..bde2388710 --- /dev/null +++ b/tests/workloads/dispatch_invalid/MI100/SQ_IFETCH_LEVEL.csv @@ -0,0 +1,2 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,235868,235868,1048576,256,0,0,8,8,16,64,0x0,0x7fa08c19ce80,47992,47992,16384,65536,14610,1850384,194751940599758,194763952869715,194763952893715,194751948360141 diff --git a/tests/workloads/dispatch_invalid/MI100/SQ_INST_LEVEL_LDS.csv b/tests/workloads/dispatch_invalid/MI100/SQ_INST_LEVEL_LDS.csv new file mode 100644 index 0000000000..86c8a94481 --- /dev/null +++ b/tests/workloads/dispatch_invalid/MI100/SQ_INST_LEVEL_LDS.csv @@ -0,0 +1,2 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,236069,236069,1048576,256,0,0,8,8,16,64,0x0,0x7f19a09bee80,0,0,0,194752433427577,194763952869715,194763952893715,194752441182349 diff --git a/tests/workloads/dispatch_invalid/MI100/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/dispatch_invalid/MI100/SQ_INST_LEVEL_SMEM.csv new file mode 100644 index 0000000000..99af56290d --- /dev/null +++ b/tests/workloads/dispatch_invalid/MI100/SQ_INST_LEVEL_SMEM.csv @@ -0,0 +1,2 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,236254,236254,1048576,256,0,0,8,8,16,64,0x0,0x7f3dd32c0e80,65536,192118,24640568,194752919496971,194763952869715,194763952893715,194752927094886 diff --git a/tests/workloads/dispatch_invalid/MI100/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/dispatch_invalid/MI100/SQ_INST_LEVEL_VMEM.csv new file mode 100644 index 0000000000..c54d56d6c4 --- /dev/null +++ b/tests/workloads/dispatch_invalid/MI100/SQ_INST_LEVEL_VMEM.csv @@ -0,0 +1,2 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,236454,236454,1048576,256,0,0,8,8,16,64,0x0,0x7f29ec3dce80,32768,665139,85136644,194753406350358,194763952869715,194763952893715,194753414100392 diff --git a/tests/workloads/dispatch_invalid/MI100/SQ_LEVEL_WAVES.csv b/tests/workloads/dispatch_invalid/MI100/SQ_LEVEL_WAVES.csv new file mode 100644 index 0000000000..d8c91d740c --- /dev/null +++ b/tests/workloads/dispatch_invalid/MI100/SQ_LEVEL_WAVES.csv @@ -0,0 +1,2 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,236656,236656,1048576,256,0,0,8,8,16,64,0x0,0x7fcf4a7b8e80,46920,46920,16723,375368,16384,24359669,227526,0,97931704,194753896286713,194763952869715,194763952893715,194753903968578 diff --git a/tests/workloads/dispatch_invalid/MI100/perfmon/SQ_IFETCH_LEVEL.txt b/tests/workloads/dispatch_invalid/MI100/perfmon/SQ_IFETCH_LEVEL.txt new file mode 100644 index 0000000000..e7209bdada --- /dev/null +++ b/tests/workloads/dispatch_invalid/MI100/perfmon/SQ_IFETCH_LEVEL.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES + +gpu: +range: invalid +kernel: diff --git a/tests/workloads/dispatch_invalid/MI100/perfmon/SQ_INST_LEVEL_LDS.txt b/tests/workloads/dispatch_invalid/MI100/perfmon/SQ_INST_LEVEL_LDS.txt new file mode 100644 index 0000000000..67fb5049bc --- /dev/null +++ b/tests/workloads/dispatch_invalid/MI100/perfmon/SQ_INST_LEVEL_LDS.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES + +gpu: +range: invalid +kernel: diff --git a/tests/workloads/dispatch_invalid/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt b/tests/workloads/dispatch_invalid/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt new file mode 100644 index 0000000000..81efe0fd5b --- /dev/null +++ b/tests/workloads/dispatch_invalid/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: invalid +kernel: diff --git a/tests/workloads/dispatch_invalid/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt b/tests/workloads/dispatch_invalid/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt new file mode 100644 index 0000000000..bbf5c9dbb7 --- /dev/null +++ b/tests/workloads/dispatch_invalid/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: invalid +kernel: diff --git a/tests/workloads/dispatch_invalid/MI100/perfmon/SQ_LEVEL_WAVES.txt b/tests/workloads/dispatch_invalid/MI100/perfmon/SQ_LEVEL_WAVES.txt new file mode 100644 index 0000000000..1422b5f0d7 --- /dev/null +++ b/tests/workloads/dispatch_invalid/MI100/perfmon/SQ_LEVEL_WAVES.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES + +gpu: +range: invalid +kernel: diff --git a/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_0.txt b/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_0.txt new file mode 100644 index 0000000000..3e26d7a583 --- /dev/null +++ b/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_0.txt @@ -0,0 +1,5 @@ +pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ SQC_TC_DATA_WRITE_REQ GRBM_COUNT GRBM_GUI_ACTIVE TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum TA_TA_BUSY_sum TA_BUFFER_WAVEFRONTS_sum TD_TD_BUSY_sum TD_TC_STALL_sum SPI_CSN_WINDOW_VALID SPI_CSN_BUSY CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum + +gpu: +range: invalid +kernel: diff --git a/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_1.txt b/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_1.txt new file mode 100644 index 0000000000..d1e6a809cc --- /dev/null +++ b/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_1.txt @@ -0,0 +1,5 @@ +pmc: SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES SQC_ICACHE_MISSES_DUPLICATE GRBM_SPI_BUSY TCP_READ_TAGCONFLICT_STALL_CYCLES_sum TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum TCP_TA_TCP_STATE_READ_sum TA_BUFFER_READ_WAVEFRONTS_sum TA_BUFFER_WRITE_WAVEFRONTS_sum TD_COALESCABLE_WAVEFRONT_sum TD_LOAD_WAVEFRONT_sum SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum + +gpu: +range: invalid +kernel: diff --git a/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_10.txt b/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_10.txt new file mode 100644 index 0000000000..8e2c2857d8 --- /dev/null +++ b/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_10.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_ATOMIC_LEVEL_sum + +gpu: +range: invalid +kernel: diff --git a/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_11.txt b/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_11.txt new file mode 100644 index 0000000000..aa172720a9 --- /dev/null +++ b/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_11.txt @@ -0,0 +1,5 @@ +pmc: TCC_ATOMIC[0] TCC_CYCLE[0] TCC_EA_ATOMIC[0] TCC_EA_ATOMIC_LEVEL[0] TCC_ATOMIC[1] TCC_CYCLE[1] TCC_EA_ATOMIC[1] TCC_EA_ATOMIC_LEVEL[1] TCC_ATOMIC[2] TCC_CYCLE[2] TCC_EA_ATOMIC[2] TCC_EA_ATOMIC_LEVEL[2] TCC_ATOMIC[3] TCC_CYCLE[3] TCC_EA_ATOMIC[3] TCC_EA_ATOMIC_LEVEL[3] TCC_ATOMIC[4] TCC_CYCLE[4] TCC_EA_ATOMIC[4] TCC_EA_ATOMIC_LEVEL[4] TCC_ATOMIC[5] TCC_CYCLE[5] TCC_EA_ATOMIC[5] TCC_EA_ATOMIC_LEVEL[5] TCC_ATOMIC[6] TCC_CYCLE[6] TCC_EA_ATOMIC[6] TCC_EA_ATOMIC_LEVEL[6] TCC_ATOMIC[7] TCC_CYCLE[7] TCC_EA_ATOMIC[7] TCC_EA_ATOMIC_LEVEL[7] TCC_ATOMIC[8] TCC_CYCLE[8] TCC_EA_ATOMIC[8] TCC_EA_ATOMIC_LEVEL[8] TCC_ATOMIC[9] TCC_CYCLE[9] TCC_EA_ATOMIC[9] TCC_EA_ATOMIC_LEVEL[9] TCC_ATOMIC[10] TCC_CYCLE[10] TCC_EA_ATOMIC[10] TCC_EA_ATOMIC_LEVEL[10] TCC_ATOMIC[11] TCC_CYCLE[11] TCC_EA_ATOMIC[11] TCC_EA_ATOMIC_LEVEL[11] TCC_ATOMIC[12] TCC_CYCLE[12] TCC_EA_ATOMIC[12] TCC_EA_ATOMIC_LEVEL[12] TCC_ATOMIC[13] TCC_CYCLE[13] TCC_EA_ATOMIC[13] TCC_EA_ATOMIC_LEVEL[13] TCC_ATOMIC[14] TCC_CYCLE[14] TCC_EA_ATOMIC[14] TCC_EA_ATOMIC_LEVEL[14] TCC_ATOMIC[15] TCC_CYCLE[15] TCC_EA_ATOMIC[15] TCC_EA_ATOMIC_LEVEL[15] TCC_ATOMIC[16] TCC_CYCLE[16] TCC_EA_ATOMIC[16] TCC_EA_ATOMIC_LEVEL[16] TCC_ATOMIC[17] TCC_CYCLE[17] TCC_EA_ATOMIC[17] TCC_EA_ATOMIC_LEVEL[17] TCC_ATOMIC[18] TCC_CYCLE[18] TCC_EA_ATOMIC[18] TCC_EA_ATOMIC_LEVEL[18] TCC_ATOMIC[19] TCC_CYCLE[19] TCC_EA_ATOMIC[19] TCC_EA_ATOMIC_LEVEL[19] TCC_ATOMIC[20] TCC_CYCLE[20] TCC_EA_ATOMIC[20] TCC_EA_ATOMIC_LEVEL[20] TCC_ATOMIC[21] TCC_CYCLE[21] TCC_EA_ATOMIC[21] TCC_EA_ATOMIC_LEVEL[21] TCC_ATOMIC[22] TCC_CYCLE[22] TCC_EA_ATOMIC[22] TCC_EA_ATOMIC_LEVEL[22] TCC_ATOMIC[23] TCC_CYCLE[23] TCC_EA_ATOMIC[23] TCC_EA_ATOMIC_LEVEL[23] TCC_ATOMIC[24] TCC_CYCLE[24] TCC_EA_ATOMIC[24] TCC_EA_ATOMIC_LEVEL[24] TCC_ATOMIC[25] TCC_CYCLE[25] TCC_EA_ATOMIC[25] TCC_EA_ATOMIC_LEVEL[25] TCC_ATOMIC[26] TCC_CYCLE[26] TCC_EA_ATOMIC[26] TCC_EA_ATOMIC_LEVEL[26] TCC_ATOMIC[27] TCC_CYCLE[27] TCC_EA_ATOMIC[27] TCC_EA_ATOMIC_LEVEL[27] TCC_ATOMIC[28] TCC_CYCLE[28] TCC_EA_ATOMIC[28] TCC_EA_ATOMIC_LEVEL[28] TCC_ATOMIC[29] TCC_CYCLE[29] TCC_EA_ATOMIC[29] TCC_EA_ATOMIC_LEVEL[29] TCC_ATOMIC[30] TCC_CYCLE[30] TCC_EA_ATOMIC[30] TCC_EA_ATOMIC_LEVEL[30] TCC_ATOMIC[31] TCC_CYCLE[31] TCC_EA_ATOMIC[31] TCC_EA_ATOMIC_LEVEL[31] + +gpu: +range: invalid +kernel: diff --git a/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_12.txt b/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_12.txt new file mode 100644 index 0000000000..2ebfdba4b4 --- /dev/null +++ b/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_12.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_EA_RDREQ_GMI_CREDIT_STALL[0] TCC_EA_RDREQ[1] TCC_EA_RDREQ_32B[1] TCC_EA_RDREQ_DRAM_CREDIT_STALL[1] TCC_EA_RDREQ_GMI_CREDIT_STALL[1] TCC_EA_RDREQ[2] TCC_EA_RDREQ_32B[2] TCC_EA_RDREQ_DRAM_CREDIT_STALL[2] TCC_EA_RDREQ_GMI_CREDIT_STALL[2] TCC_EA_RDREQ[3] TCC_EA_RDREQ_32B[3] TCC_EA_RDREQ_DRAM_CREDIT_STALL[3] TCC_EA_RDREQ_GMI_CREDIT_STALL[3] TCC_EA_RDREQ[4] TCC_EA_RDREQ_32B[4] TCC_EA_RDREQ_DRAM_CREDIT_STALL[4] TCC_EA_RDREQ_GMI_CREDIT_STALL[4] TCC_EA_RDREQ[5] TCC_EA_RDREQ_32B[5] TCC_EA_RDREQ_DRAM_CREDIT_STALL[5] TCC_EA_RDREQ_GMI_CREDIT_STALL[5] TCC_EA_RDREQ[6] TCC_EA_RDREQ_32B[6] TCC_EA_RDREQ_DRAM_CREDIT_STALL[6] TCC_EA_RDREQ_GMI_CREDIT_STALL[6] TCC_EA_RDREQ[7] TCC_EA_RDREQ_32B[7] TCC_EA_RDREQ_DRAM_CREDIT_STALL[7] TCC_EA_RDREQ_GMI_CREDIT_STALL[7] TCC_EA_RDREQ[8] TCC_EA_RDREQ_32B[8] TCC_EA_RDREQ_DRAM_CREDIT_STALL[8] TCC_EA_RDREQ_GMI_CREDIT_STALL[8] TCC_EA_RDREQ[9] TCC_EA_RDREQ_32B[9] TCC_EA_RDREQ_DRAM_CREDIT_STALL[9] TCC_EA_RDREQ_GMI_CREDIT_STALL[9] TCC_EA_RDREQ[10] TCC_EA_RDREQ_32B[10] TCC_EA_RDREQ_DRAM_CREDIT_STALL[10] TCC_EA_RDREQ_GMI_CREDIT_STALL[10] TCC_EA_RDREQ[11] TCC_EA_RDREQ_32B[11] TCC_EA_RDREQ_DRAM_CREDIT_STALL[11] TCC_EA_RDREQ_GMI_CREDIT_STALL[11] TCC_EA_RDREQ[12] TCC_EA_RDREQ_32B[12] TCC_EA_RDREQ_DRAM_CREDIT_STALL[12] TCC_EA_RDREQ_GMI_CREDIT_STALL[12] TCC_EA_RDREQ[13] TCC_EA_RDREQ_32B[13] TCC_EA_RDREQ_DRAM_CREDIT_STALL[13] TCC_EA_RDREQ_GMI_CREDIT_STALL[13] TCC_EA_RDREQ[14] TCC_EA_RDREQ_32B[14] TCC_EA_RDREQ_DRAM_CREDIT_STALL[14] TCC_EA_RDREQ_GMI_CREDIT_STALL[14] TCC_EA_RDREQ[15] TCC_EA_RDREQ_32B[15] TCC_EA_RDREQ_DRAM_CREDIT_STALL[15] TCC_EA_RDREQ_GMI_CREDIT_STALL[15] TCC_EA_RDREQ[16] TCC_EA_RDREQ_32B[16] TCC_EA_RDREQ_DRAM_CREDIT_STALL[16] TCC_EA_RDREQ_GMI_CREDIT_STALL[16] TCC_EA_RDREQ[17] TCC_EA_RDREQ_32B[17] TCC_EA_RDREQ_DRAM_CREDIT_STALL[17] TCC_EA_RDREQ_GMI_CREDIT_STALL[17] TCC_EA_RDREQ[18] TCC_EA_RDREQ_32B[18] TCC_EA_RDREQ_DRAM_CREDIT_STALL[18] TCC_EA_RDREQ_GMI_CREDIT_STALL[18] TCC_EA_RDREQ[19] TCC_EA_RDREQ_32B[19] TCC_EA_RDREQ_DRAM_CREDIT_STALL[19] TCC_EA_RDREQ_GMI_CREDIT_STALL[19] TCC_EA_RDREQ[20] TCC_EA_RDREQ_32B[20] TCC_EA_RDREQ_DRAM_CREDIT_STALL[20] TCC_EA_RDREQ_GMI_CREDIT_STALL[20] TCC_EA_RDREQ[21] TCC_EA_RDREQ_32B[21] TCC_EA_RDREQ_DRAM_CREDIT_STALL[21] TCC_EA_RDREQ_GMI_CREDIT_STALL[21] TCC_EA_RDREQ[22] TCC_EA_RDREQ_32B[22] TCC_EA_RDREQ_DRAM_CREDIT_STALL[22] TCC_EA_RDREQ_GMI_CREDIT_STALL[22] TCC_EA_RDREQ[23] TCC_EA_RDREQ_32B[23] TCC_EA_RDREQ_DRAM_CREDIT_STALL[23] TCC_EA_RDREQ_GMI_CREDIT_STALL[23] TCC_EA_RDREQ[24] TCC_EA_RDREQ_32B[24] TCC_EA_RDREQ_DRAM_CREDIT_STALL[24] TCC_EA_RDREQ_GMI_CREDIT_STALL[24] TCC_EA_RDREQ[25] TCC_EA_RDREQ_32B[25] TCC_EA_RDREQ_DRAM_CREDIT_STALL[25] TCC_EA_RDREQ_GMI_CREDIT_STALL[25] TCC_EA_RDREQ[26] TCC_EA_RDREQ_32B[26] TCC_EA_RDREQ_DRAM_CREDIT_STALL[26] TCC_EA_RDREQ_GMI_CREDIT_STALL[26] TCC_EA_RDREQ[27] TCC_EA_RDREQ_32B[27] TCC_EA_RDREQ_DRAM_CREDIT_STALL[27] TCC_EA_RDREQ_GMI_CREDIT_STALL[27] TCC_EA_RDREQ[28] TCC_EA_RDREQ_32B[28] TCC_EA_RDREQ_DRAM_CREDIT_STALL[28] TCC_EA_RDREQ_GMI_CREDIT_STALL[28] TCC_EA_RDREQ[29] TCC_EA_RDREQ_32B[29] TCC_EA_RDREQ_DRAM_CREDIT_STALL[29] TCC_EA_RDREQ_GMI_CREDIT_STALL[29] TCC_EA_RDREQ[30] TCC_EA_RDREQ_32B[30] TCC_EA_RDREQ_DRAM_CREDIT_STALL[30] TCC_EA_RDREQ_GMI_CREDIT_STALL[30] TCC_EA_RDREQ[31] TCC_EA_RDREQ_32B[31] TCC_EA_RDREQ_DRAM_CREDIT_STALL[31] TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + +gpu: +range: invalid +kernel: diff --git a/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_13.txt b/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_13.txt new file mode 100644 index 0000000000..595907c8e9 --- /dev/null +++ b/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_13.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ[0] TCC_EA_WRREQ_64B[0] TCC_EA_RDREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_LEVEL[1] TCC_EA_WRREQ[1] TCC_EA_WRREQ_64B[1] TCC_EA_RDREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_LEVEL[2] TCC_EA_WRREQ[2] TCC_EA_WRREQ_64B[2] TCC_EA_RDREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_LEVEL[3] TCC_EA_WRREQ[3] TCC_EA_WRREQ_64B[3] TCC_EA_RDREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_LEVEL[4] TCC_EA_WRREQ[4] TCC_EA_WRREQ_64B[4] TCC_EA_RDREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_LEVEL[5] TCC_EA_WRREQ[5] TCC_EA_WRREQ_64B[5] TCC_EA_RDREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_LEVEL[6] TCC_EA_WRREQ[6] TCC_EA_WRREQ_64B[6] TCC_EA_RDREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_LEVEL[7] TCC_EA_WRREQ[7] TCC_EA_WRREQ_64B[7] TCC_EA_RDREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_LEVEL[8] TCC_EA_WRREQ[8] TCC_EA_WRREQ_64B[8] TCC_EA_RDREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_LEVEL[9] TCC_EA_WRREQ[9] TCC_EA_WRREQ_64B[9] TCC_EA_RDREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_LEVEL[10] TCC_EA_WRREQ[10] TCC_EA_WRREQ_64B[10] TCC_EA_RDREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_LEVEL[11] TCC_EA_WRREQ[11] TCC_EA_WRREQ_64B[11] TCC_EA_RDREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_LEVEL[12] TCC_EA_WRREQ[12] TCC_EA_WRREQ_64B[12] TCC_EA_RDREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_LEVEL[13] TCC_EA_WRREQ[13] TCC_EA_WRREQ_64B[13] TCC_EA_RDREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_LEVEL[14] TCC_EA_WRREQ[14] TCC_EA_WRREQ_64B[14] TCC_EA_RDREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_LEVEL[15] TCC_EA_WRREQ[15] TCC_EA_WRREQ_64B[15] TCC_EA_RDREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_LEVEL[16] TCC_EA_WRREQ[16] TCC_EA_WRREQ_64B[16] TCC_EA_RDREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_LEVEL[17] TCC_EA_WRREQ[17] TCC_EA_WRREQ_64B[17] TCC_EA_RDREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_LEVEL[18] TCC_EA_WRREQ[18] TCC_EA_WRREQ_64B[18] TCC_EA_RDREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_LEVEL[19] TCC_EA_WRREQ[19] TCC_EA_WRREQ_64B[19] TCC_EA_RDREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_LEVEL[20] TCC_EA_WRREQ[20] TCC_EA_WRREQ_64B[20] TCC_EA_RDREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_LEVEL[21] TCC_EA_WRREQ[21] TCC_EA_WRREQ_64B[21] TCC_EA_RDREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_LEVEL[22] TCC_EA_WRREQ[22] TCC_EA_WRREQ_64B[22] TCC_EA_RDREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_LEVEL[23] TCC_EA_WRREQ[23] TCC_EA_WRREQ_64B[23] TCC_EA_RDREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_LEVEL[24] TCC_EA_WRREQ[24] TCC_EA_WRREQ_64B[24] TCC_EA_RDREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_LEVEL[25] TCC_EA_WRREQ[25] TCC_EA_WRREQ_64B[25] TCC_EA_RDREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_LEVEL[26] TCC_EA_WRREQ[26] TCC_EA_WRREQ_64B[26] TCC_EA_RDREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_LEVEL[27] TCC_EA_WRREQ[27] TCC_EA_WRREQ_64B[27] TCC_EA_RDREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_LEVEL[28] TCC_EA_WRREQ[28] TCC_EA_WRREQ_64B[28] TCC_EA_RDREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_LEVEL[29] TCC_EA_WRREQ[29] TCC_EA_WRREQ_64B[29] TCC_EA_RDREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_LEVEL[30] TCC_EA_WRREQ[30] TCC_EA_WRREQ_64B[30] TCC_EA_RDREQ_IO_CREDIT_STALL[31] TCC_EA_RDREQ_LEVEL[31] TCC_EA_WRREQ[31] TCC_EA_WRREQ_64B[31] + +gpu: +range: invalid +kernel: diff --git a/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_14.txt b/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_14.txt new file mode 100644 index 0000000000..3abef42045 --- /dev/null +++ b/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_14.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_WRREQ_IO_CREDIT_STALL[0] TCC_EA_WRREQ_LEVEL[0] TCC_EA_WRREQ_DRAM_CREDIT_STALL[1] TCC_EA_WRREQ_GMI_CREDIT_STALL[1] TCC_EA_WRREQ_IO_CREDIT_STALL[1] TCC_EA_WRREQ_LEVEL[1] TCC_EA_WRREQ_DRAM_CREDIT_STALL[2] TCC_EA_WRREQ_GMI_CREDIT_STALL[2] TCC_EA_WRREQ_IO_CREDIT_STALL[2] TCC_EA_WRREQ_LEVEL[2] TCC_EA_WRREQ_DRAM_CREDIT_STALL[3] TCC_EA_WRREQ_GMI_CREDIT_STALL[3] TCC_EA_WRREQ_IO_CREDIT_STALL[3] TCC_EA_WRREQ_LEVEL[3] TCC_EA_WRREQ_DRAM_CREDIT_STALL[4] TCC_EA_WRREQ_GMI_CREDIT_STALL[4] TCC_EA_WRREQ_IO_CREDIT_STALL[4] TCC_EA_WRREQ_LEVEL[4] TCC_EA_WRREQ_DRAM_CREDIT_STALL[5] TCC_EA_WRREQ_GMI_CREDIT_STALL[5] TCC_EA_WRREQ_IO_CREDIT_STALL[5] TCC_EA_WRREQ_LEVEL[5] TCC_EA_WRREQ_DRAM_CREDIT_STALL[6] TCC_EA_WRREQ_GMI_CREDIT_STALL[6] TCC_EA_WRREQ_IO_CREDIT_STALL[6] TCC_EA_WRREQ_LEVEL[6] TCC_EA_WRREQ_DRAM_CREDIT_STALL[7] TCC_EA_WRREQ_GMI_CREDIT_STALL[7] TCC_EA_WRREQ_IO_CREDIT_STALL[7] TCC_EA_WRREQ_LEVEL[7] TCC_EA_WRREQ_DRAM_CREDIT_STALL[8] TCC_EA_WRREQ_GMI_CREDIT_STALL[8] TCC_EA_WRREQ_IO_CREDIT_STALL[8] TCC_EA_WRREQ_LEVEL[8] TCC_EA_WRREQ_DRAM_CREDIT_STALL[9] TCC_EA_WRREQ_GMI_CREDIT_STALL[9] TCC_EA_WRREQ_IO_CREDIT_STALL[9] TCC_EA_WRREQ_LEVEL[9] TCC_EA_WRREQ_DRAM_CREDIT_STALL[10] TCC_EA_WRREQ_GMI_CREDIT_STALL[10] TCC_EA_WRREQ_IO_CREDIT_STALL[10] TCC_EA_WRREQ_LEVEL[10] TCC_EA_WRREQ_DRAM_CREDIT_STALL[11] TCC_EA_WRREQ_GMI_CREDIT_STALL[11] TCC_EA_WRREQ_IO_CREDIT_STALL[11] TCC_EA_WRREQ_LEVEL[11] TCC_EA_WRREQ_DRAM_CREDIT_STALL[12] TCC_EA_WRREQ_GMI_CREDIT_STALL[12] TCC_EA_WRREQ_IO_CREDIT_STALL[12] TCC_EA_WRREQ_LEVEL[12] TCC_EA_WRREQ_DRAM_CREDIT_STALL[13] TCC_EA_WRREQ_GMI_CREDIT_STALL[13] TCC_EA_WRREQ_IO_CREDIT_STALL[13] TCC_EA_WRREQ_LEVEL[13] TCC_EA_WRREQ_DRAM_CREDIT_STALL[14] TCC_EA_WRREQ_GMI_CREDIT_STALL[14] TCC_EA_WRREQ_IO_CREDIT_STALL[14] TCC_EA_WRREQ_LEVEL[14] TCC_EA_WRREQ_DRAM_CREDIT_STALL[15] TCC_EA_WRREQ_GMI_CREDIT_STALL[15] TCC_EA_WRREQ_IO_CREDIT_STALL[15] TCC_EA_WRREQ_LEVEL[15] TCC_EA_WRREQ_DRAM_CREDIT_STALL[16] TCC_EA_WRREQ_GMI_CREDIT_STALL[16] TCC_EA_WRREQ_IO_CREDIT_STALL[16] TCC_EA_WRREQ_LEVEL[16] TCC_EA_WRREQ_DRAM_CREDIT_STALL[17] TCC_EA_WRREQ_GMI_CREDIT_STALL[17] TCC_EA_WRREQ_IO_CREDIT_STALL[17] TCC_EA_WRREQ_LEVEL[17] TCC_EA_WRREQ_DRAM_CREDIT_STALL[18] TCC_EA_WRREQ_GMI_CREDIT_STALL[18] TCC_EA_WRREQ_IO_CREDIT_STALL[18] TCC_EA_WRREQ_LEVEL[18] TCC_EA_WRREQ_DRAM_CREDIT_STALL[19] TCC_EA_WRREQ_GMI_CREDIT_STALL[19] TCC_EA_WRREQ_IO_CREDIT_STALL[19] TCC_EA_WRREQ_LEVEL[19] TCC_EA_WRREQ_DRAM_CREDIT_STALL[20] TCC_EA_WRREQ_GMI_CREDIT_STALL[20] TCC_EA_WRREQ_IO_CREDIT_STALL[20] TCC_EA_WRREQ_LEVEL[20] TCC_EA_WRREQ_DRAM_CREDIT_STALL[21] TCC_EA_WRREQ_GMI_CREDIT_STALL[21] TCC_EA_WRREQ_IO_CREDIT_STALL[21] TCC_EA_WRREQ_LEVEL[21] TCC_EA_WRREQ_DRAM_CREDIT_STALL[22] TCC_EA_WRREQ_GMI_CREDIT_STALL[22] TCC_EA_WRREQ_IO_CREDIT_STALL[22] TCC_EA_WRREQ_LEVEL[22] TCC_EA_WRREQ_DRAM_CREDIT_STALL[23] TCC_EA_WRREQ_GMI_CREDIT_STALL[23] TCC_EA_WRREQ_IO_CREDIT_STALL[23] TCC_EA_WRREQ_LEVEL[23] TCC_EA_WRREQ_DRAM_CREDIT_STALL[24] TCC_EA_WRREQ_GMI_CREDIT_STALL[24] TCC_EA_WRREQ_IO_CREDIT_STALL[24] TCC_EA_WRREQ_LEVEL[24] TCC_EA_WRREQ_DRAM_CREDIT_STALL[25] TCC_EA_WRREQ_GMI_CREDIT_STALL[25] TCC_EA_WRREQ_IO_CREDIT_STALL[25] TCC_EA_WRREQ_LEVEL[25] TCC_EA_WRREQ_DRAM_CREDIT_STALL[26] TCC_EA_WRREQ_GMI_CREDIT_STALL[26] TCC_EA_WRREQ_IO_CREDIT_STALL[26] TCC_EA_WRREQ_LEVEL[26] TCC_EA_WRREQ_DRAM_CREDIT_STALL[27] TCC_EA_WRREQ_GMI_CREDIT_STALL[27] TCC_EA_WRREQ_IO_CREDIT_STALL[27] TCC_EA_WRREQ_LEVEL[27] TCC_EA_WRREQ_DRAM_CREDIT_STALL[28] TCC_EA_WRREQ_GMI_CREDIT_STALL[28] TCC_EA_WRREQ_IO_CREDIT_STALL[28] TCC_EA_WRREQ_LEVEL[28] TCC_EA_WRREQ_DRAM_CREDIT_STALL[29] TCC_EA_WRREQ_GMI_CREDIT_STALL[29] TCC_EA_WRREQ_IO_CREDIT_STALL[29] TCC_EA_WRREQ_LEVEL[29] TCC_EA_WRREQ_DRAM_CREDIT_STALL[30] TCC_EA_WRREQ_GMI_CREDIT_STALL[30] TCC_EA_WRREQ_IO_CREDIT_STALL[30] TCC_EA_WRREQ_LEVEL[30] TCC_EA_WRREQ_DRAM_CREDIT_STALL[31] TCC_EA_WRREQ_GMI_CREDIT_STALL[31] TCC_EA_WRREQ_IO_CREDIT_STALL[31] TCC_EA_WRREQ_LEVEL[31] + +gpu: +range: invalid +kernel: diff --git a/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_15.txt b/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_15.txt new file mode 100644 index 0000000000..82a4b5dce2 --- /dev/null +++ b/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_15.txt @@ -0,0 +1,5 @@ +pmc: TCC_HIT[0] TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_HIT[1] TCC_MISS[1] TCC_READ[1] TCC_REQ[1] TCC_HIT[2] TCC_MISS[2] TCC_READ[2] TCC_REQ[2] TCC_HIT[3] TCC_MISS[3] TCC_READ[3] TCC_REQ[3] TCC_HIT[4] TCC_MISS[4] TCC_READ[4] TCC_REQ[4] TCC_HIT[5] TCC_MISS[5] TCC_READ[5] TCC_REQ[5] TCC_HIT[6] TCC_MISS[6] TCC_READ[6] TCC_REQ[6] TCC_HIT[7] TCC_MISS[7] TCC_READ[7] TCC_REQ[7] TCC_HIT[8] TCC_MISS[8] TCC_READ[8] TCC_REQ[8] TCC_HIT[9] TCC_MISS[9] TCC_READ[9] TCC_REQ[9] TCC_HIT[10] TCC_MISS[10] TCC_READ[10] TCC_REQ[10] TCC_HIT[11] TCC_MISS[11] TCC_READ[11] TCC_REQ[11] TCC_HIT[12] TCC_MISS[12] TCC_READ[12] TCC_REQ[12] TCC_HIT[13] TCC_MISS[13] TCC_READ[13] TCC_REQ[13] TCC_HIT[14] TCC_MISS[14] TCC_READ[14] TCC_REQ[14] TCC_HIT[15] TCC_MISS[15] TCC_READ[15] TCC_REQ[15] TCC_HIT[16] TCC_MISS[16] TCC_READ[16] TCC_REQ[16] TCC_HIT[17] TCC_MISS[17] TCC_READ[17] TCC_REQ[17] TCC_HIT[18] TCC_MISS[18] TCC_READ[18] TCC_REQ[18] TCC_HIT[19] TCC_MISS[19] TCC_READ[19] TCC_REQ[19] TCC_HIT[20] TCC_MISS[20] TCC_READ[20] TCC_REQ[20] TCC_HIT[21] TCC_MISS[21] TCC_READ[21] TCC_REQ[21] TCC_HIT[22] TCC_MISS[22] TCC_READ[22] TCC_REQ[22] TCC_HIT[23] TCC_MISS[23] TCC_READ[23] TCC_REQ[23] TCC_HIT[24] TCC_MISS[24] TCC_READ[24] TCC_REQ[24] TCC_HIT[25] TCC_MISS[25] TCC_READ[25] TCC_REQ[25] TCC_HIT[26] TCC_MISS[26] TCC_READ[26] TCC_REQ[26] TCC_HIT[27] TCC_MISS[27] TCC_READ[27] TCC_REQ[27] TCC_HIT[28] TCC_MISS[28] TCC_READ[28] TCC_REQ[28] TCC_HIT[29] TCC_MISS[29] TCC_READ[29] TCC_REQ[29] TCC_HIT[30] TCC_MISS[30] TCC_READ[30] TCC_REQ[30] TCC_HIT[31] TCC_MISS[31] TCC_READ[31] TCC_REQ[31] + +gpu: +range: invalid +kernel: diff --git a/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_16.txt b/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_16.txt new file mode 100644 index 0000000000..4a07aa911c --- /dev/null +++ b/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_16.txt @@ -0,0 +1,5 @@ +pmc: TCC_RW_REQ[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_RW_REQ[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_WRITE[1] TCC_RW_REQ[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_WRITE[2] TCC_RW_REQ[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_WRITE[3] TCC_RW_REQ[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_WRITE[4] TCC_RW_REQ[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_WRITE[5] TCC_RW_REQ[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_WRITE[6] TCC_RW_REQ[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_WRITE[7] TCC_RW_REQ[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_WRITE[8] TCC_RW_REQ[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_WRITE[9] TCC_RW_REQ[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_WRITE[10] TCC_RW_REQ[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_WRITE[11] TCC_RW_REQ[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_WRITE[12] TCC_RW_REQ[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_WRITE[13] TCC_RW_REQ[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_WRITE[14] TCC_RW_REQ[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_WRITE[15] TCC_RW_REQ[16] TCC_TOO_MANY_EA_WRREQS_STALL[16] TCC_WRITE[16] TCC_RW_REQ[17] TCC_TOO_MANY_EA_WRREQS_STALL[17] TCC_WRITE[17] TCC_RW_REQ[18] TCC_TOO_MANY_EA_WRREQS_STALL[18] TCC_WRITE[18] TCC_RW_REQ[19] TCC_TOO_MANY_EA_WRREQS_STALL[19] TCC_WRITE[19] TCC_RW_REQ[20] TCC_TOO_MANY_EA_WRREQS_STALL[20] TCC_WRITE[20] TCC_RW_REQ[21] TCC_TOO_MANY_EA_WRREQS_STALL[21] TCC_WRITE[21] TCC_RW_REQ[22] TCC_TOO_MANY_EA_WRREQS_STALL[22] TCC_WRITE[22] TCC_RW_REQ[23] TCC_TOO_MANY_EA_WRREQS_STALL[23] TCC_WRITE[23] TCC_RW_REQ[24] TCC_TOO_MANY_EA_WRREQS_STALL[24] TCC_WRITE[24] TCC_RW_REQ[25] TCC_TOO_MANY_EA_WRREQS_STALL[25] TCC_WRITE[25] TCC_RW_REQ[26] TCC_TOO_MANY_EA_WRREQS_STALL[26] TCC_WRITE[26] TCC_RW_REQ[27] TCC_TOO_MANY_EA_WRREQS_STALL[27] TCC_WRITE[27] TCC_RW_REQ[28] TCC_TOO_MANY_EA_WRREQS_STALL[28] TCC_WRITE[28] TCC_RW_REQ[29] TCC_TOO_MANY_EA_WRREQS_STALL[29] TCC_WRITE[29] TCC_RW_REQ[30] TCC_TOO_MANY_EA_WRREQS_STALL[30] TCC_WRITE[30] TCC_RW_REQ[31] TCC_TOO_MANY_EA_WRREQS_STALL[31] TCC_WRITE[31] + +gpu: +range: invalid +kernel: diff --git a/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_2.txt b/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_2.txt new file mode 100644 index 0000000000..63514f75ef --- /dev/null +++ b/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_2.txt @@ -0,0 +1,5 @@ +pmc: SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE SQC_DCACHE_REQ_READ_1 TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum TA_BUFFER_ATOMIC_WAVEFRONTS_sum TA_BUFFER_TOTAL_CYCLES_sum TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum + +gpu: +range: invalid +kernel: diff --git a/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_3.txt b/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_3.txt new file mode 100644 index 0000000000..09f18f4397 --- /dev/null +++ b/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_3.txt @@ -0,0 +1,5 @@ +pmc: SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU SQ_INSTS_VSKIPPED SQ_INSTS_SMEM TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE CPF_CMP_UTCL1_STALL_ON_TRANSLATION TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum + +gpu: +range: invalid +kernel: diff --git a/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_4.txt b/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_4.txt new file mode 100644 index 0000000000..7bf6cb865e --- /dev/null +++ b/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_4.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG SQ_INSTS SQ_WAIT_ANY TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE TCC_EA_WRREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WR_UNCACHED_32B_sum TCC_EA_WRREQ_DRAM_sum + +gpu: +range: invalid +kernel: diff --git a/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_5.txt b/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_5.txt new file mode 100644 index 0000000000..659841f973 --- /dev/null +++ b/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_5.txt @@ -0,0 +1,5 @@ +pmc: SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_INSTS_VALU SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS TCP_TCP_LATENCY_sum TCP_TCC_READ_REQ_LATENCY_sum TCP_TCC_WRITE_REQ_LATENCY_sum TCP_TCC_READ_REQ_sum TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN CPC_ME1_DC0_SPI_BUSY TCC_EA_WRREQ_STALL_sum TCC_EA_WRREQ_IO_CREDIT_STALL_sum TCC_EA_WRREQ_GMI_CREDIT_STALL_sum TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum + +gpu: +range: invalid +kernel: diff --git a/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_6.txt b/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_6.txt new file mode 100644 index 0000000000..40bc861ecc --- /dev/null +++ b/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_6.txt @@ -0,0 +1,5 @@ +pmc: SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU SQ_THREAD_CYCLES_VALU SQ_IFETCH TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TCP_TCC_NC_READ_REQ_sum TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN TCC_EA_RDREQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RD_UNCACHED_32B_sum TCC_EA_RDREQ_DRAM_sum + +gpu: +range: invalid +kernel: diff --git a/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_7.txt b/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_7.txt new file mode 100644 index 0000000000..997395a3ee --- /dev/null +++ b/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_7.txt @@ -0,0 +1,5 @@ +pmc: SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 SQ_WAVES_LT_32 SQ_WAVES_LT_16 TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TCP_TCC_UC_WRITE_REQ_sum TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR TCC_EA_RDREQ_IO_CREDIT_STALL_sum TCC_EA_RDREQ_GMI_CREDIT_STALL_sum TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum TCC_TAG_STALL_sum + +gpu: +range: invalid +kernel: diff --git a/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_8.txt b/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_8.txt new file mode 100644 index 0000000000..224a8eed8a --- /dev/null +++ b/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_8.txt @@ -0,0 +1,5 @@ +pmc: SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED SQ_INSTS_SMEM_NORM TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TCP_TCC_CC_ATOMIC_REQ_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum TCC_NORMAL_EVICT_sum TCC_ALL_TC_OP_INV_EVICT_sum + +gpu: +range: invalid +kernel: diff --git a/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_9.txt b/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_9.txt new file mode 100644 index 0000000000..8a86116b3d --- /dev/null +++ b/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_9.txt @@ -0,0 +1,5 @@ +pmc: TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum TCP_PENDING_STALL_CYCLES_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA_ATOMIC_sum TCC_EA_RDREQ_LEVEL_sum TCC_EA_WRREQ_LEVEL_sum + +gpu: +range: invalid +kernel: diff --git a/tests/workloads/dispatch_invalid/MI100/perfmon/timestamps.txt b/tests/workloads/dispatch_invalid/MI100/perfmon/timestamps.txt new file mode 100644 index 0000000000..6a128303a2 --- /dev/null +++ b/tests/workloads/dispatch_invalid/MI100/perfmon/timestamps.txt @@ -0,0 +1,5 @@ +pmc: + +gpu: +range: invalid +kernel: diff --git a/tests/workloads/dispatch_invalid/MI100/pmc_dispatch_info.csv b/tests/workloads/dispatch_invalid/MI100/pmc_dispatch_info.csv new file mode 100644 index 0000000000..e90d72a8cf --- /dev/null +++ b/tests/workloads/dispatch_invalid/MI100/pmc_dispatch_info.csv @@ -0,0 +1,2 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) ",2 diff --git a/tests/workloads/dispatch_invalid/MI100/pmc_perf.csv b/tests/workloads/dispatch_invalid/MI100/pmc_perf.csv new file mode 100644 index 0000000000..acccd717d8 --- /dev/null +++ b/tests/workloads/dispatch_invalid/MI100/pmc_perf.csv @@ -0,0 +1,2 @@ +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_1,obj_1,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_2,obj_2,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_3,obj_3,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_4,obj_4,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_5,obj_5,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_6,obj_6,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_7,obj_7,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_8,obj_8,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_9,obj_9,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_10,obj_10,TCC_EA_ATOMIC_LEVEL_sum,wave_size_11,obj_11,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_12,obj_12,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_13,obj_13,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_14,obj_14,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_15,obj_15,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_16,obj_16,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f932ed18e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86444.0,44628.0,131111.0,0.0,64,0x7fb884960e80,0,0,192,0,65536,64492,48,1180,32095,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,539,47886,1649,0,48.0,300.0,0.0,262288.0,64,0x7f70fde78e80,3624,0,0,2027059,1930,0,0,1795507,1572,0,0,1778103,1260,0,0,1670342,2111,0,0,1797791,548,0,0,1501244,7175,0,0,2289519,1730,0,0,1803850,1427,0,0,1777066,969,0,0,1766055,2674,0,0,1936612,1751,0,0,1738916,1684,0,0,1802919,1370,0,0,1808370,3044,0,0,2014769,5489,0,0,2245401,3806,0,0,1970282,1450,0,0,1735832,2352,0,0,1934472,1168,0,0,1645610,2176,0,0,1855537,1892,0,0,1897209,2248,0,0,1867928,753,0,0,1588095,1643,0,0,1740035,939,0,0,1674593,2460,0,0,1827118,4250,0,0,1965289,1759,0,0,1818903,1223,0,0,1672257,2870,0,0,1929807,1965,0,0,1814369,64,0x7f9c67a96e80,32768,0,0,0,16384,16384,393216,22905363,960.0,513925.0,0.0,524288.0,949484.0,32768.0,0,0,0,17834,131072.0,131072.0,0.0,131072.0,64,0x7f9bc4660e80,0,8192,4096,8192,0,8192,4096,8192,141,8195,4240,8336,47,8193,4144,8240,0,8192,4096,8192,0,8312,4216,8312,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f5d76cace80,131072.0,131072.0,0.0,2560703.0,0.0,0.0,126347271.0,63177897.0,64,0x7fd1e44dae80,4096,0,1265,0,4096,0,2988,0,4096,0,1992,0,4096,0,0,0,4096,0,5957,0,4096,0,415,0,4096,0,2908,0,4096,0,699,0,4096,0,1312,0,4096,0,4511,0,4351,0,3263,0,4147,0,584,0,4096,0,869,0,4097,0,236,0,4096,0,5208,0,4096,0,6002,0,4096,0,2293,0,4096,0,2183,0,4144,0,1370,0,4096,0,0,0,4096,0,1145,0,4096,0,417,0,4096,0,444,0,4096,0,0,0,4096,0,496,0,4096,0,1350,0,4096,0,2558,0,4096,0,49,0,4096,0,233,0,4096,0,0,0,4096,0,690,0,4096,0,0,0,64,0x7f65d5404e80,381968,234772,3430126,16384,25372852,144,48,0,47745,47745,3874301.0,3047202.0,5817.0,1076068.0,2188474.0,0.0,3037288.0,2725229.0,380255,244700,47745,0,47745,0,1527840.0,976120.0,0.0,0.0,64,0x7fecc7b96e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131298.0,0.0,444.0,131297.0,64,0x7fb9d7a3ce80,1625171,360448,163840,0,0,180224,114688,0,68823734.0,192270368.0,77516831.0,131072.0,0.0,695444.0,0,0,26431,142095.0,0.0,0.0,142095.0,64,0x7fed1c430e80,0.0,64,0x7f60d8a64e80,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,64,0x7f518cfa4e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,82342.0,163167.0,64,0x7fc1e78c4e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,48080,0,131535.0,131072.0,0.0,131104.0,64,0x7feb37616e80,0,3839398,4096,4096,0,3265058,4096,4096,0,4015402,4096,4096,0,3097596,4096,4096,0,3637199,4096,4096,0,3361265,4096,4096,0,3873696,4096,4096,0,3228194,4096,4096,0,4071125,4096,4096,0,4435600,4096,4096,0,3367730,4096,4096,0,3651688,4096,4096,0,3546183,4096,4096,0,3641431,4096,4096,0,4158548,4096,4096,0,2914552,4096,4096,0,5315537,4096,4096,0,4008013,4096,4096,0,4215771,4096,4096,0,3301663,4096,4096,0,4636662,4096,4096,0,3650563,4096,4096,0,4564222,4096,4096,0,2891708,4096,4096,0,4190911,4096,4096,0,3226044,4096,4096,0,4150036,4096,4096,0,2861234,4096,4096,0,3815145,4096,4096,0,3534716,4096,4096,0,4072909,4096,4096,0,5085333,4096,4096,64,0x7fdd88ad4e80,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fa998a84e80,116195,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13502,29886,9653,550,0,46167,262600.0,0.0,188.0,262412.0,194763952869715,194763952893715 diff --git a/tests/workloads/dispatch_invalid/MI100/sysinfo.csv b/tests/workloads/dispatch_invalid/MI100/sysinfo.csv new file mode 100644 index 0000000000..5011fc14b5 --- /dev/null +++ b/tests/workloads/dispatch_invalid/MI100/sysinfo.csv @@ -0,0 +1,2 @@ +workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd +dispatch_invalid,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 07 Mar 2024 01:16:56 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/dispatch_invalid/MI100/timestamps.csv b/tests/workloads/dispatch_invalid/MI100/timestamps.csv new file mode 100644 index 0000000000..596ddc5950 --- /dev/null +++ b/tests/workloads/dispatch_invalid/MI100/timestamps.csv @@ -0,0 +1,2 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,240105,240105,1048576,256,0,0,8,8,16,64,0x0,0x7f43ccdc4e80,194763952839587,194763952869715,194763952893715,194763952904830 diff --git a/tests/workloads/ipblocks_CPC/MI100/pmc_dispatch_info.csv b/tests/workloads/ipblocks_CPC/MI100/pmc_dispatch_info.csv new file mode 100644 index 0000000000..17300ae9af --- /dev/null +++ b/tests/workloads/ipblocks_CPC/MI100/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) ",2 +1,"vecCopy(double*, double*, double*, int, int) ",2 +2,"vecCopy(double*, double*, double*, int, int) ",2 diff --git a/tests/workloads/ipblocks_CPC/MI100/pmc_perf.csv b/tests/workloads/ipblocks_CPC/MI100/pmc_perf.csv index 3cde790df4..c312e5c0fc 100644 --- a/tests/workloads/ipblocks_CPC/MI100/pmc_perf.csv +++ b/tests/workloads/ipblocks_CPC/MI100/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,CPC_ME1_DC0_SPI_BUSY,wave_size_1,obj_1,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,wave_size_2,obj_2,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,wave_size_3,obj_3,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,wave_size_4,obj_4,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,wave_size_5,obj_5,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f6fa71d4e80,27198,64,0x7fb5721fce80,388912,238815,16384,48613,48613,48613,0,64,0x7f3c04c86e80,538,47259,64,0x7ff08dda4e80,913,47370,64,0x7fb5b8014e80,9870,550,64,0x7feefc7eae80,0,17489,2187834551870079,2187834551894719 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f6fa71d4e80,26091,64,0x7fb5721fce80,353088,232167,16384,44135,44135,44135,0,64,0x7f3c04c86e80,436,41950,64,0x7ff08dda4e80,4014,40236,64,0x7fb5b8014e80,8561,3266,64,0x7feefc7eae80,0,14240,2187834551991039,2187834552009919 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f6fa71d4e80,26166,64,0x7fb5721fce80,356864,237399,16384,44607,44607,44607,0,64,0x7f3c04c86e80,436,41763,64,0x7ff08dda4e80,3681,39368,64,0x7fb5b8014e80,8934,3427,64,0x7feefc7eae80,0,13774,2187834552031359,2187834552050719 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,wave_size_1,obj_1,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,wave_size_2,obj_2,CPC_ME1_DC0_SPI_BUSY,wave_size_3,obj_3,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,wave_size_4,obj_4,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,wave_size_5,obj_5,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7ff316284e80,0,18032,64,0x7f4d85fa8e80,538,47251,64,0x7f887490ee80,25840,64,0x7fd18aa26e80,383384,233291,16384,47922,47922,47922,0,64,0x7f0b8a080e80,913,47882,64,0x7f7df1112e80,9974,550,194244245026424,194244245050584 +1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7ff316284e80,0,13536,64,0x7f4d85fa8e80,456,42172,64,0x7f887490ee80,25547,64,0x7fd18aa26e80,338240,231210,16384,42279,42279,42279,0,64,0x7f0b8a080e80,3255,39736,64,0x7f7df1112e80,8663,2404,194244245150904,194244245169784 +2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7ff316284e80,0,13950,64,0x7f4d85fa8e80,455,41957,64,0x7f887490ee80,25075,64,0x7fd18aa26e80,336192,231870,16384,42023,42023,42023,0,64,0x7f0b8a080e80,3266,39317,64,0x7f7df1112e80,8698,2399,194244245191704,194244245210584 diff --git a/tests/workloads/ipblocks_CPC/MI100/sysinfo.csv b/tests/workloads/ipblocks_CPC/MI100/sysinfo.csv index 99e12fe751..b90598d910 100644 --- a/tests/workloads/ipblocks_CPC/MI100/sysinfo.csv +++ b/tests/workloads/ipblocks_CPC/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -ipblocks_CPC,./tests/vcopy -n 1048576 -b 256 -i 3,cpc,Fri Mar 1 16:45:44 2024 (CST),1,t006-003.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651240,,5.7.1-98,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +ipblocks_CPC,./tests/vcopy -n 1048576 -b 256 -i 3,cpc,Thu 07 Mar 2024 01:08:26 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/ipblocks_CPC/MI100/timestamps.csv b/tests/workloads/ipblocks_CPC/MI100/timestamps.csv index da3b10f4e8..931b9903c4 100644 --- a/tests/workloads/ipblocks_CPC/MI100/timestamps.csv +++ b/tests/workloads/ipblocks_CPC/MI100/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,2857632,2857632,1048576,256,0,0,8,8,16,64,0x0,0x7fcf7afb4e80,2187834551845710,2187834551870079,2187834551894719,2187834551905853 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,2857632,2857632,1048576,256,0,0,8,8,16,64,0x0,0x7fcf7afb4e80,2187834551907326,2187834551991039,2187834552009919,2187834552011181 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,2857632,2857632,1048576,256,0,0,8,8,16,64,0x0,0x7fcf7afb4e80,2187834552022082,2187834552031359,2187834552050719,2187834552051807 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,162824,162824,1048576,256,0,0,8,8,16,64,0x0,0x7f59dfa84e80,194244245000970,194244245026424,194244245050584,194244245063608 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,162824,162824,1048576,256,0,0,8,8,16,64,0x0,0x7f59dfa84e80,194244245063318,194244245150904,194244245169784,194244245171282 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,162824,162824,1048576,256,0,0,8,8,16,64,0x0,0x7f59dfa84e80,194244245182744,194244245191704,194244245210584,194244245211729 diff --git a/tests/workloads/ipblocks_CPC/MI200/perfmon/pmc_perf_0.txt b/tests/workloads/ipblocks_CPC/MI200/perfmon/pmc_perf_0.txt new file mode 100644 index 0000000000..88a77748fe --- /dev/null +++ b/tests/workloads/ipblocks_CPC/MI200/perfmon/pmc_perf_0.txt @@ -0,0 +1,5 @@ +pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES GRBM_COUNT GRBM_GUI_ACTIVE CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_CPC/MI200/perfmon/pmc_perf_1.txt b/tests/workloads/ipblocks_CPC/MI200/perfmon/pmc_perf_1.txt new file mode 100644 index 0000000000..8dc8d3bfb1 --- /dev/null +++ b/tests/workloads/ipblocks_CPC/MI200/perfmon/pmc_perf_1.txt @@ -0,0 +1,5 @@ +pmc: CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_CPC/MI200/perfmon/pmc_perf_2.txt b/tests/workloads/ipblocks_CPC/MI200/perfmon/pmc_perf_2.txt new file mode 100644 index 0000000000..8192b00754 --- /dev/null +++ b/tests/workloads/ipblocks_CPC/MI200/perfmon/pmc_perf_2.txt @@ -0,0 +1,5 @@ +pmc: CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_CPC/MI200/perfmon/pmc_perf_3.txt b/tests/workloads/ipblocks_CPC/MI200/perfmon/pmc_perf_3.txt new file mode 100644 index 0000000000..15c1f1d090 --- /dev/null +++ b/tests/workloads/ipblocks_CPC/MI200/perfmon/pmc_perf_3.txt @@ -0,0 +1,5 @@ +pmc: CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_CPC/MI200/perfmon/pmc_perf_4.txt b/tests/workloads/ipblocks_CPC/MI200/perfmon/pmc_perf_4.txt new file mode 100644 index 0000000000..9ed05c8b61 --- /dev/null +++ b/tests/workloads/ipblocks_CPC/MI200/perfmon/pmc_perf_4.txt @@ -0,0 +1,5 @@ +pmc: CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_CPC/MI200/perfmon/pmc_perf_5.txt b/tests/workloads/ipblocks_CPC/MI200/perfmon/pmc_perf_5.txt new file mode 100644 index 0000000000..0c50a1f2f4 --- /dev/null +++ b/tests/workloads/ipblocks_CPC/MI200/perfmon/pmc_perf_5.txt @@ -0,0 +1,5 @@ +pmc: CPC_ME1_DC0_SPI_BUSY + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_CPC/MI200/perfmon/timestamps.txt b/tests/workloads/ipblocks_CPC/MI200/perfmon/timestamps.txt new file mode 100644 index 0000000000..676cca1b80 --- /dev/null +++ b/tests/workloads/ipblocks_CPC/MI200/perfmon/timestamps.txt @@ -0,0 +1,5 @@ +pmc: + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_CPC/MI200/pmc_perf.csv b/tests/workloads/ipblocks_CPC/MI200/pmc_perf.csv new file mode 100644 index 0000000000..d488a210b4 --- /dev/null +++ b/tests/workloads/ipblocks_CPC/MI200/pmc_perf.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,wave_size_1,obj_1,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,wave_size_2,obj_2,CPC_ME1_DC0_SPI_BUSY,wave_size_3,obj_3,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,wave_size_4,obj_4,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,wave_size_5,obj_5,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f7b5b620ec0,7061,549,64,0x7f34dac88ec0,220344,128760,16384,27542,27542,27542,0,64,0x7f1388c50ec0,16121,64,0x7f2e75dd8ec0,352,27046,64,0x7fa7ccc7cec0,814,26808,64,0x7f8a762b0ec0,0,11071,198895939495862,198895939516022 +1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f7b5b620ec0,9533,2476,64,0x7f34dac88ec0,332232,225531,16384,41528,41528,41528,0,64,0x7f1388c50ec0,25649,64,0x7f2e75dd8ec0,302,42817,64,0x7fa7ccc7cec0,2628,39892,64,0x7f8a762b0ec0,0,14417,198895939535222,198895939551062 +2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f7b5b620ec0,9545,2467,64,0x7f34dac88ec0,330008,224905,16384,41250,41250,41250,0,64,0x7f1388c50ec0,26412,64,0x7f2e75dd8ec0,302,41569,64,0x7fa7ccc7cec0,2652,39346,64,0x7f8a762b0ec0,0,13685,198895939606582,198895939622742 diff --git a/tests/workloads/ipblocks_CPC/MI200/roofline.csv b/tests/workloads/ipblocks_CPC/MI200/roofline.csv new file mode 100644 index 0000000000..9faaaeff5b --- /dev/null +++ b/tests/workloads/ipblocks_CPC/MI200/roofline.csv @@ -0,0 +1,5 @@ +device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh +0,1389.0835,1388.5491,1389.6179,5013.0107,5010.002,5016.0195,9220.1738,9219.5938,9220.7539,18045.086,18044.184,18045.988,20923.201,20862.568,20983.834,20256.529,20255.801,20257.258,170333.5,170329.88,170337.12,164808.95,164805.06,164812.84,41402.754,41402.188,41403.32,41460.305,41459.68,41460.93,166272.33,165780.62,166764.03 +1,1389.6497,1389.1088,1390.1906,5027.5049,5025.3521,5029.6577,9230.7354,9230.0459,9231.4248,18088.08,18084.049,18092.111,20970.324,20903.604,21037.045,20290.588,20290.08,20291.096,170824.3,170819.86,170828.73,165087.86,165084.22,165091.5,41482.344,41481.582,41483.105,41541.422,41540.449,41542.395,166888.75,166885.91,166891.59 +2,1388.6713,1388.0886,1389.2539,5035.397,5033.2314,5037.5625,9258.9023,9258.1445,9259.6602,18103.68,18102.697,18104.662,21045.385,21044.947,21045.822,20346.889,20346.314,20347.463,171077.52,171073.62,171081.41,165468.52,165464.36,165472.67,41573.086,41571.988,41574.184,41629.473,41628.504,41630.441,166937.44,166346.31,167528.56 +3,1388.4886,1387.973,1389.0043,5032.6201,5031.2354,5034.0049,9240.5059,9239.9424,9241.0693,18025.992,18022.287,18029.697,21037.256,21036.428,21038.084,20312.686,20312.051,20313.32,171059.08,171053,171065.16,165231.14,165224.91,165237.38,41435.23,41273.004,41597.457,41580.984,41580.523,41581.445,167021.8,167019.53,167024.06 diff --git a/tests/workloads/ipblocks_CPC/MI200/sysinfo.csv b/tests/workloads/ipblocks_CPC/MI200/sysinfo.csv new file mode 100644 index 0000000000..c047bef687 --- /dev/null +++ b/tests/workloads/ipblocks_CPC/MI200/sysinfo.csv @@ -0,0 +1,2 @@ +workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd +ipblocks_CPC,./sample/vcopy -n 1048576 -b 256 -i 3,cpc|roofline,Thu 07 Mar 2024 02:26:00 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/ipblocks_CPC/MI200/timestamps.csv b/tests/workloads/ipblocks_CPC/MI200/timestamps.csv new file mode 100644 index 0000000000..8c99cef564 --- /dev/null +++ b/tests/workloads/ipblocks_CPC/MI200/timestamps.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,319954,319954,1048576,256,0,0,8,0,16,64,0x0,0x7fea700a8ec0,198895939470975,198895939495862,198895939516022,198895939529786 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,319954,319954,1048576,256,0,0,8,0,16,64,0x0,0x7fea700a8ec0,198895939527111,198895939535222,198895939551062,198895939604708 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,319954,319954,1048576,256,0,0,8,0,16,64,0x0,0x7fea700a8ec0,198895939561627,198895939606582,198895939622742,198895939623964 diff --git a/tests/workloads/ipblocks_CPF/MI100/pmc_dispatch_info.csv b/tests/workloads/ipblocks_CPF/MI100/pmc_dispatch_info.csv new file mode 100644 index 0000000000..17300ae9af --- /dev/null +++ b/tests/workloads/ipblocks_CPF/MI100/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) ",2 +1,"vecCopy(double*, double*, double*, int, int) ",2 +2,"vecCopy(double*, double*, double*, int, int) ",2 diff --git a/tests/workloads/ipblocks_CPF/MI100/pmc_perf.csv b/tests/workloads/ipblocks_CPF/MI100/pmc_perf.csv index cf9b1e9729..f1740ac568 100644 --- a/tests/workloads/ipblocks_CPF/MI100/pmc_perf.csv +++ b/tests/workloads/ipblocks_CPF/MI100/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,wave_size_1,obj_1,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,wave_size_2,obj_2,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,wave_size_3,obj_3,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,GRBM_COUNT,GRBM_GUI_ACTIVE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f39c2628e80,0,64,0x7fee87348e80,0,47324,64,0x7f39641bae80,1313,0,64,0x7f4e99172e80,387360,239187,16384,48419,48419,48419,0,2187830565872132,2187830565896772 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f39c2628e80,0,64,0x7fee87348e80,0,42283,64,0x7f39641bae80,1294,0,64,0x7f4e99172e80,352656,242219,16384,44081,44081,44081,0,2187830566004132,2187830566023172 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f39c2628e80,0,64,0x7fee87348e80,0,42963,64,0x7f39641bae80,1262,0,64,0x7f4e99172e80,343768,233611,16384,42970,42970,42970,0,2187830566044452,2187830566063492 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,GRBM_COUNT,GRBM_GUI_ACTIVE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,wave_size_1,obj_1,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,wave_size_2,obj_2,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,wave_size_3,obj_3,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f5b9070ee80,384264,232290,16384,48032,48032,48032,0,64,0x7f4350c04e80,0,47628,64,0x7f4004e74e80,1262,0,64,0x7fca1214ce80,0,194239843235063,194239843259383 +1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f5b9070ee80,313216,216625,16384,39151,39151,39151,0,64,0x7f4350c04e80,0,41835,64,0x7f4004e74e80,1310,0,64,0x7fca1214ce80,0,194239843423223,194239843442103 +2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f5b9070ee80,307328,212139,16384,38415,38415,38415,0,64,0x7f4350c04e80,0,42075,64,0x7f4004e74e80,1278,0,64,0x7fca1214ce80,0,194239843463863,194239843482903 diff --git a/tests/workloads/ipblocks_CPF/MI100/sysinfo.csv b/tests/workloads/ipblocks_CPF/MI100/sysinfo.csv index 6113665a71..0db40d9513 100644 --- a/tests/workloads/ipblocks_CPF/MI100/sysinfo.csv +++ b/tests/workloads/ipblocks_CPF/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -ipblocks_CPF,./tests/vcopy -n 1048576 -b 256 -i 3,cpf,Fri Mar 1 16:45:41 2024 (CST),1,t006-003.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651240,,5.7.1-98,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +ipblocks_CPF,./tests/vcopy -n 1048576 -b 256 -i 3,cpf,Thu 07 Mar 2024 01:08:22 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/ipblocks_CPF/MI100/timestamps.csv b/tests/workloads/ipblocks_CPF/MI100/timestamps.csv index 85254928ac..a0e0a3e8c8 100644 --- a/tests/workloads/ipblocks_CPF/MI100/timestamps.csv +++ b/tests/workloads/ipblocks_CPF/MI100/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,2856271,2856271,1048576,256,0,0,8,8,16,64,0x0,0x7f3ab40b2e80,2187830565846738,2187830565872132,2187830565896772,2187830565909636 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,2856271,2856271,1048576,256,0,0,8,8,16,64,0x0,0x7f3ab40b2e80,2187830565909316,2187830566004132,2187830566023172,2187830566024321 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,2856271,2856271,1048576,256,0,0,8,8,16,64,0x0,0x7f3ab40b2e80,2187830566035903,2187830566044452,2187830566063492,2187830566064567 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,161422,161422,1048576,256,0,0,8,8,16,64,0x0,0x7f152d9b8e80,194239843210061,194239843235063,194239843259383,194239843271157 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,161422,161422,1048576,256,0,0,8,8,16,64,0x0,0x7f152d9b8e80,194239843272410,194239843423223,194239843442103,194239843443864 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,161422,161422,1048576,256,0,0,8,8,16,64,0x0,0x7f152d9b8e80,194239843454464,194239843463863,194239843482903,194239843484351 diff --git a/tests/workloads/ipblocks_CPF/MI200/perfmon/pmc_perf_0.txt b/tests/workloads/ipblocks_CPF/MI200/perfmon/pmc_perf_0.txt new file mode 100644 index 0000000000..a0c27ffe5c --- /dev/null +++ b/tests/workloads/ipblocks_CPF/MI200/perfmon/pmc_perf_0.txt @@ -0,0 +1,5 @@ +pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES GRBM_COUNT GRBM_GUI_ACTIVE CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_CPF/MI200/perfmon/pmc_perf_1.txt b/tests/workloads/ipblocks_CPF/MI200/perfmon/pmc_perf_1.txt new file mode 100644 index 0000000000..1b469a07ef --- /dev/null +++ b/tests/workloads/ipblocks_CPF/MI200/perfmon/pmc_perf_1.txt @@ -0,0 +1,5 @@ +pmc: CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_CPF/MI200/perfmon/pmc_perf_2.txt b/tests/workloads/ipblocks_CPF/MI200/perfmon/pmc_perf_2.txt new file mode 100644 index 0000000000..4b8f76a224 --- /dev/null +++ b/tests/workloads/ipblocks_CPF/MI200/perfmon/pmc_perf_2.txt @@ -0,0 +1,5 @@ +pmc: CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_CPF/MI200/perfmon/pmc_perf_3.txt b/tests/workloads/ipblocks_CPF/MI200/perfmon/pmc_perf_3.txt new file mode 100644 index 0000000000..2b6588a9bb --- /dev/null +++ b/tests/workloads/ipblocks_CPF/MI200/perfmon/pmc_perf_3.txt @@ -0,0 +1,5 @@ +pmc: CPF_CMP_UTCL1_STALL_ON_TRANSLATION + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_CPF/MI200/perfmon/timestamps.txt b/tests/workloads/ipblocks_CPF/MI200/perfmon/timestamps.txt new file mode 100644 index 0000000000..676cca1b80 --- /dev/null +++ b/tests/workloads/ipblocks_CPF/MI200/perfmon/timestamps.txt @@ -0,0 +1,5 @@ +pmc: + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_CPF/MI200/pmc_perf.csv b/tests/workloads/ipblocks_CPF/MI200/pmc_perf.csv new file mode 100644 index 0000000000..bef8a4a588 --- /dev/null +++ b/tests/workloads/ipblocks_CPF/MI200/pmc_perf.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,wave_size_1,obj_1,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,GRBM_COUNT,GRBM_GUI_ACTIVE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,wave_size_2,obj_2,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,wave_size_3,obj_3,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f7c305a4ec0,0,64,0x7f5ee8368ec0,218152,127865,16384,27268,27268,27268,0,64,0x7f820dfc0ec0,873,0,64,0x7fd9c8d68ec0,0,26928,198799859549427,198799859569907 +1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f7c305a4ec0,0,64,0x7f5ee8368ec0,319392,221459,16384,39923,39923,39923,0,64,0x7f820dfc0ec0,1600,0,64,0x7fd9c8d68ec0,0,40230,198799859589747,198799859605587 +2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f7c305a4ec0,0,64,0x7f5ee8368ec0,318480,219809,16384,39809,39809,39809,0,64,0x7f820dfc0ec0,1622,0,64,0x7fd9c8d68ec0,0,39292,198799859659827,198799859676147 diff --git a/tests/workloads/ipblocks_CPF/MI200/roofline.csv b/tests/workloads/ipblocks_CPF/MI200/roofline.csv new file mode 100644 index 0000000000..0d4f131c18 --- /dev/null +++ b/tests/workloads/ipblocks_CPF/MI200/roofline.csv @@ -0,0 +1,5 @@ +device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh +0,1388.7466,1388.1986,1389.2946,5014.8066,5011.9419,5017.6714,9225.3555,9224.6377,9226.0732,18055.795,18054.943,18056.646,20937.562,20876.969,20998.156,20264.434,20263.588,20265.279,170425.69,170421.42,170429.95,164873.91,164868.66,164879.16,41419.789,41419.301,41420.277,41477.148,41476.148,41478.148,166317.8,165829.28,166806.31 +1,1389.0984,1388.5691,1389.6277,5028.8921,5027.0518,5030.7324,9235.1348,9234.4424,9235.8271,18099.438,18094.338,18104.537,20974.891,20908.201,21041.58,20295.033,20294.365,20295.701,170832.44,170829.27,170835.61,165091.3,165087.86,165094.73,41479.668,41478.977,41480.359,41534.102,41533.008,41535.195,166847.27,166844.38,166850.16 +2,1389.2231,1388.6008,1389.8455,5035.1265,5032.791,5037.4619,9260.9941,9260.3633,9261.625,18105.355,18104.672,18106.039,21044.99,21044.596,21045.385,20348.387,20347.891,20348.883,171090.92,171086.39,171095.45,165474.55,165470.22,165478.88,41575.297,41574.309,41576.285,41629.754,41628.738,41630.77,166909.95,166320.81,167499.09 +3,1388.8466,1388.299,1389.3942,5031.3447,5029.9229,5032.7666,9240.5459,9239.9502,9241.1416,18025.242,18021.904,18028.58,21033.998,21033.4,21034.596,20311.389,20310.717,20312.061,171009.09,171004.06,171014.12,165229.42,165225.45,165233.39,41444.457,41290.074,41598.84,41585.707,41585.25,41586.164,167035.59,167033.86,167037.33 diff --git a/tests/workloads/ipblocks_CPF/MI200/sysinfo.csv b/tests/workloads/ipblocks_CPF/MI200/sysinfo.csv new file mode 100644 index 0000000000..a28721cb0e --- /dev/null +++ b/tests/workloads/ipblocks_CPF/MI200/sysinfo.csv @@ -0,0 +1,2 @@ +workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd +ipblocks_CPF,./sample/vcopy -n 1048576 -b 256 -i 3,cpf|roofline,Thu 07 Mar 2024 02:24:25 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/ipblocks_CPF/MI200/timestamps.csv b/tests/workloads/ipblocks_CPF/MI200/timestamps.csv new file mode 100644 index 0000000000..b05a9a13c8 --- /dev/null +++ b/tests/workloads/ipblocks_CPF/MI200/timestamps.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,318314,318314,1048576,256,0,0,8,0,16,64,0x0,0x7f2c64ab0ec0,198799859525291,198799859549427,198799859569907,198799859583632 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,318314,318314,1048576,256,0,0,8,0,16,64,0x0,0x7f2c64ab0ec0,198799859580946,198799859589747,198799859605587,198799859655908 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,318314,318314,1048576,256,0,0,8,0,16,64,0x0,0x7f2c64ab0ec0,198799859615842,198799859659827,198799859676147,198799859677038 diff --git a/tests/workloads/ipblocks_SPI/MI100/pmc_dispatch_info.csv b/tests/workloads/ipblocks_SPI/MI100/pmc_dispatch_info.csv new file mode 100644 index 0000000000..17300ae9af --- /dev/null +++ b/tests/workloads/ipblocks_SPI/MI100/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) ",2 +1,"vecCopy(double*, double*, double*, int, int) ",2 +2,"vecCopy(double*, double*, double*, int, int) ",2 diff --git a/tests/workloads/ipblocks_SPI/MI100/pmc_perf.csv b/tests/workloads/ipblocks_SPI/MI100/pmc_perf.csv index f9bb21c1ee..1ee8ee9d54 100644 --- a/tests/workloads/ipblocks_SPI/MI100/pmc_perf.csv +++ b/tests/workloads/ipblocks_SPI/MI100/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,wave_size_1,obj_1,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,wave_size_2,obj_2,GRBM_SPI_BUSY,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,wave_size_3,obj_3,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,wave_size_4,obj_4,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,wave_size_5,obj_5,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,GRBM_COUNT,GRBM_GUI_ACTIVE,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,wave_size_6,obj_6,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,wave_size_7,obj_7,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,wave_size_8,obj_8,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f4616f2ee80,16384,0,64,0x7fb24c6bae80,0,0,64,0x7f85dc3ece80,31201,4096,16384,64,0x7f573485ce80,0,81920,64,0x7f8697510e80,14511,30895,64,0x7fb5ecdece80,375832,226214,16384,46978,46978,374119,236160,64,0x7fb2b80a8e80,0,0,64,0x7fa0a8748e80,0,0,64,0x7f7686f4ae80,0,0,2188006175005781,2188006175029621 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f4616f2ee80,16384,0,64,0x7fb24c6bae80,0,0,64,0x7f85dc3ece80,31365,4096,16384,64,0x7f573485ce80,0,81920,64,0x7f8697510e80,11844,28228,64,0x7fb5ecdece80,338792,226799,16384,42348,42348,338784,236593,64,0x7fb2b80a8e80,0,0,64,0x7fa0a8748e80,0,0,64,0x7f7686f4ae80,0,0,2188006175121781,2188006175140661 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f4616f2ee80,16384,0,64,0x7fb24c6bae80,0,0,64,0x7f85dc3ece80,31754,4096,16384,64,0x7f573485ce80,0,81920,64,0x7f8697510e80,13650,30034,64,0x7fb5ecdece80,335728,226652,16384,41965,41965,335720,236451,64,0x7fb2b80a8e80,0,0,64,0x7fa0a8748e80,0,0,64,0x7f7686f4ae80,0,0,2188006175161621,2188006175180181 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,wave_size_1,obj_1,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,wave_size_2,obj_2,GRBM_SPI_BUSY,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,wave_size_3,obj_3,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,GRBM_COUNT,GRBM_GUI_ACTIVE,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,wave_size_4,obj_4,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,wave_size_5,obj_5,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,wave_size_6,obj_6,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,wave_size_7,obj_7,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,wave_size_8,obj_8,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f3acecb2e80,0,0,64,0x7f05f5c54e80,16384,0,64,0x7f2e42c44e80,31956,4096,16384,64,0x7f7994d1ae80,381736,231428,16384,47716,47716,380023,241372,64,0x7f775c162e80,0,0,64,0x7fb00f7d2e80,0,0,64,0x7f2008b14e80,0,81920,64,0x7fd452f12e80,13179,29563,64,0x7f657ac3ae80,0,0,194434963621537,194434963646337 +1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f3acecb2e80,0,0,64,0x7f05f5c54e80,16384,0,64,0x7f2e42c44e80,30474,4096,16384,64,0x7f7994d1ae80,342736,228907,16384,42841,42841,342728,238673,64,0x7f775c162e80,0,0,64,0x7fb00f7d2e80,0,0,64,0x7f2008b14e80,0,81920,64,0x7fd452f12e80,12801,29185,64,0x7f657ac3ae80,0,0,194434963736257,194434963754977 +2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f3acecb2e80,0,0,64,0x7f05f5c54e80,16384,0,64,0x7f2e42c44e80,30469,4096,16384,64,0x7f7994d1ae80,339216,227589,16384,42401,42401,339208,237363,64,0x7f775c162e80,0,0,64,0x7fb00f7d2e80,0,0,64,0x7f2008b14e80,0,81920,64,0x7fd452f12e80,11173,27557,64,0x7f657ac3ae80,0,0,194434963776577,194434963795777 diff --git a/tests/workloads/ipblocks_SPI/MI100/sysinfo.csv b/tests/workloads/ipblocks_SPI/MI100/sysinfo.csv index 700ec95e9e..cd04524e93 100644 --- a/tests/workloads/ipblocks_SPI/MI100/sysinfo.csv +++ b/tests/workloads/ipblocks_SPI/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -ipblocks_SPI,./tests/vcopy -n 1048576 -b 256 -i 3,spi,Fri Mar 1 16:48:35 2024 (CST),1,t006-003.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651240,,5.7.1-98,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +ipblocks_SPI,./tests/vcopy -n 1048576 -b 256 -i 3,spi,Thu 07 Mar 2024 01:11:35 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/ipblocks_SPI/MI100/timestamps.csv b/tests/workloads/ipblocks_SPI/MI100/timestamps.csv index 576b10f954..0ffe3fd8dd 100644 --- a/tests/workloads/ipblocks_SPI/MI100/timestamps.csv +++ b/tests/workloads/ipblocks_SPI/MI100/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,2915163,2915163,1048576,256,0,0,8,8,16,64,0x0,0x7ff442052e80,2188006174978608,2188006175005781,2188006175029621,2188006175041476 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,2915163,2915163,1048576,256,0,0,8,8,16,64,0x0,0x7ff442052e80,2188006175042518,2188006175121781,2188006175140661,2188006175141614 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,2915163,2915163,1048576,256,0,0,8,8,16,64,0x0,0x7ff442052e80,2188006175152394,2188006175161621,2188006175180181,2188006175181178 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,221987,221987,1048576,256,0,0,8,8,16,64,0x0,0x7ffb63778e80,194434963596381,194434963621537,194434963646337,194434963659661 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,221987,221987,1048576,256,0,0,8,8,16,64,0x0,0x7ffb63778e80,194434963658889,194434963736257,194434963754977,194434963756154 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,221987,221987,1048576,256,0,0,8,8,16,64,0x0,0x7ffb63778e80,194434963767816,194434963776577,194434963795777,194434963797031 diff --git a/tests/workloads/ipblocks_SQ/MI100/SQ_IFETCH_LEVEL.csv b/tests/workloads/ipblocks_SQ/MI100/SQ_IFETCH_LEVEL.csv index 430c35d468..fb7bb937c9 100644 --- a/tests/workloads/ipblocks_SQ/MI100/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/ipblocks_SQ/MI100/SQ_IFETCH_LEVEL.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2873654,2873654,1048576,256,0,0,8,8,16,64,0x0,0x7f662a176e80,48498,48498,16384,65536,14078,1833852,2187881283676972,2187879063908574,2187879063933214,2187881291191960 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2873654,2873654,1048576,256,0,0,8,8,16,64,0x0,0x7f662a176e80,42092,42092,16384,65536,7895,1048580,2187881291214833,2187879063954814,2187879063973854,2187881291551154 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2873654,2873654,1048576,256,0,0,8,8,16,64,0x0,0x7f662a176e80,112601,112601,16384,65536,8134,1048576,2187881291583445,2187879064044414,2187879064063454,2187881291808808 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,176352,176352,1048576,256,0,0,8,8,16,64,0x0,0x7ff2f710ce80,48234,48234,16384,65536,13448,1730548,194287866542271,194294746542348,194294746566668,194287875222636 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,176352,176352,1048576,256,0,0,8,8,16,64,0x0,0x7ff2f710ce80,39353,39353,16384,65536,8354,1048644,194287874860921,194294746587308,194294746606348,194287876419964 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,176352,176352,1048576,256,0,0,8,8,16,64,0x0,0x7ff2f710ce80,38863,38863,16384,65536,8197,1048648,194287875000886,194294746690668,194294746709548,194287875226604 diff --git a/tests/workloads/ipblocks_SQ/MI100/SQ_INST_LEVEL_LDS.csv b/tests/workloads/ipblocks_SQ/MI100/SQ_INST_LEVEL_LDS.csv index 367a603a8c..784d9079d6 100644 --- a/tests/workloads/ipblocks_SQ/MI100/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/ipblocks_SQ/MI100/SQ_INST_LEVEL_LDS.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2873289,2873289,1048576,256,0,0,8,8,16,64,0x0,0x7f3aecccae80,0,0,0,2187880388588608,2187879063908574,2187879063933214,2187880395994711 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2873289,2873289,1048576,256,0,0,8,8,16,64,0x0,0x7f3aecccae80,0,0,0,2187880396014698,2187879063954814,2187879063973854,2187880396315653 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2873289,2873289,1048576,256,0,0,8,8,16,64,0x0,0x7f3aecccae80,0,0,0,2187880396344127,2187879064044414,2187879064063454,2187880396514446 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,176537,176537,1048576,256,0,0,8,8,16,64,0x0,0x7f3eb9a06e80,0,0,0,194288360563039,194294746542348,194294746566668,194288368404226 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,176537,176537,1048576,256,0,0,8,8,16,64,0x0,0x7f3eb9a06e80,0,0,0,194288368424535,194294746587308,194294746606348,194288368724302 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,176537,176537,1048576,256,0,0,8,8,16,64,0x0,0x7f3eb9a06e80,0,0,0,194288368752355,194294746690668,194294746709548,194288368924201 diff --git a/tests/workloads/ipblocks_SQ/MI100/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/ipblocks_SQ/MI100/SQ_INST_LEVEL_SMEM.csv index 4d95ee1f5f..599b11b04e 100644 --- a/tests/workloads/ipblocks_SQ/MI100/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/ipblocks_SQ/MI100/SQ_INST_LEVEL_SMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2872556,2872556,1048576,256,0,0,8,8,16,64,0x0,0x7f9c51360e80,65536,218636,27943032,2187878616493031,2187879063908574,2187879063933214,2187878624115891 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2872556,2872556,1048576,256,0,0,8,8,16,64,0x0,0x7f9c51360e80,65536,199468,25481856,2187878624135648,2187879063954814,2187879063973854,2187878624432345 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2872556,2872556,1048576,256,0,0,8,8,16,64,0x0,0x7f9c51360e80,65536,198332,25466912,2187878624461199,2187879064044414,2187879064063454,2187878624631759 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,176723,176723,1048576,256,0,0,8,8,16,64,0x0,0x7f36dba02e80,65536,215186,27423112,194288851113227,194294746542348,194294746566668,194288858883329 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,176723,176723,1048576,256,0,0,8,8,16,64,0x0,0x7f36dba02e80,65536,208000,26558816,194288858902876,194294746587308,194294746606348,194288859206020 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,176723,176723,1048576,256,0,0,8,8,16,64,0x0,0x7f36dba02e80,65536,189368,24301824,194288859234474,194294746690668,194294746709548,194288859410838 diff --git a/tests/workloads/ipblocks_SQ/MI100/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/ipblocks_SQ/MI100/SQ_INST_LEVEL_VMEM.csv index 77f5567266..a5b42e05d5 100644 --- a/tests/workloads/ipblocks_SQ/MI100/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/ipblocks_SQ/MI100/SQ_INST_LEVEL_VMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2873836,2873836,1048576,256,0,0,8,8,16,64,0x0,0x7fb6c67c4e80,32768,616756,78946200,2187881728450478,2187879063908574,2187879063933214,2187881735919089 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2873836,2873836,1048576,256,0,0,8,8,16,64,0x0,0x7fb6c67c4e80,32768,637569,81601708,2187881735944987,2187879063954814,2187879063973854,2187881736254789 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2873836,2873836,1048576,256,0,0,8,8,16,64,0x0,0x7fb6c67c4e80,32768,637487,81597940,2187881736283883,2187879064044414,2187879064063454,2187881736456568 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,176906,176906,1048576,256,0,0,8,8,16,64,0x0,0x7f7026c14e80,32768,641207,82083564,194289338933616,194294746542348,194294746566668,194289346782968 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,176906,176906,1048576,256,0,0,8,8,16,64,0x0,0x7f7026c14e80,32768,659200,84360976,194289346801022,194294746587308,194294746606348,194289347142408 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,176906,176906,1048576,256,0,0,8,8,16,64,0x0,0x7f7026c14e80,32768,634018,81134416,194289347171143,194294746690668,194294746709548,194289347345263 diff --git a/tests/workloads/ipblocks_SQ/MI100/SQ_LEVEL_WAVES.csv b/tests/workloads/ipblocks_SQ/MI100/SQ_LEVEL_WAVES.csv index 7279f8aa13..46e5cf0be9 100644 --- a/tests/workloads/ipblocks_SQ/MI100/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/ipblocks_SQ/MI100/SQ_LEVEL_WAVES.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2872192,2872192,1048576,256,0,0,8,8,16,64,0x0,0x7fbe227ece80,47890,47890,16831,383128,16384,25198619,232633,0,101294340,2187877723320012,2187879063908574,2187879063933214,2187877730996642 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2872192,2872192,1048576,256,0,0,8,8,16,64,0x0,0x7fbe227ece80,42983,42983,14166,343872,16384,25097382,230397,0,100879320,2187877731025657,2187879063954814,2187879063973854,2187877731346740 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2872192,2872192,1048576,256,0,0,8,8,16,64,0x0,0x7fbe227ece80,42303,42303,12871,338432,16384,24077325,228222,0,96793056,2187877731385022,2187879064044414,2187879064063454,2187877731540253 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,177092,177092,1048576,256,0,0,8,8,16,64,0x0,0x7fc837804e80,49473,49473,18573,395792,16384,25193691,240627,0,101250320,194289831974198,194294746542348,194294746566668,194289839769899 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,177092,177092,1048576,256,0,0,8,8,16,64,0x0,0x7fc837804e80,43137,43137,12928,345104,16384,25261600,238599,0,101529368,194289839802441,194294746587308,194294746606348,194289840061511 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,177092,177092,1048576,256,0,0,8,8,16,64,0x0,0x7fc837804e80,42681,42681,12493,341456,16384,24886720,234534,0,100039300,194289840101277,194294746690668,194294746709548,194289840270677 diff --git a/tests/workloads/ipblocks_SQ/MI100/pmc_dispatch_info.csv b/tests/workloads/ipblocks_SQ/MI100/pmc_dispatch_info.csv new file mode 100644 index 0000000000..17300ae9af --- /dev/null +++ b/tests/workloads/ipblocks_SQ/MI100/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) ",2 +1,"vecCopy(double*, double*, double*, int, int) ",2 +2,"vecCopy(double*, double*, double*, int, int) ",2 diff --git a/tests/workloads/ipblocks_SQ/MI100/pmc_perf.csv b/tests/workloads/ipblocks_SQ/MI100/pmc_perf.csv index fe1d7b7233..2c63a23501 100644 --- a/tests/workloads/ipblocks_SQ/MI100/pmc_perf.csv +++ b/tests/workloads/ipblocks_SQ/MI100/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,wave_size_1,obj_1,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,GRBM_COUNT,GRBM_GUI_ACTIVE,wave_size_2,obj_2,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,wave_size_3,obj_3,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,wave_size_4,obj_4,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,wave_size_5,obj_5,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,wave_size_6,obj_6,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_7,obj_7,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,wave_size_8,obj_8,SQ_ACTIVE_INST_ANY,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f0bbde98e80,0,131072,144,48,0,0,0,192,64,0x7fcf84fe8e80,16384,16384,32768,49152,0,65536,32768,0,48594,48594,64,0x7fe40d9f6e80,0,0,16384,16384,393216,25742902,23266754,2115700,64,0x7ff69aa4ee80,11534336,65536,0,0,0,16384,16384,0,64,0x7f08b97bae80,0,65536,64510,48,1294,187406,0,0,64,0x7f957386ce80,114688,0,32768,32768,16384,16384,65536,49152,64,0x7f9536616e80,65536,64048,48,1440,32768,32768,0,64,0x7f41ecd2ae80,0,0,0,1048576,0,0,0,0,64,0x7fe701bece80,360448,386176,233929,3425681,163840,0,0,180224,2187879063908574,2187879063933214 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f0bbde98e80,0,131072,0,48,0,0,0,48,64,0x7fcf84fe8e80,16384,16384,32768,49152,0,65536,32768,0,44434,44434,64,0x7fe40d9f6e80,0,0,16384,16384,393216,25229333,23070929,1797956,64,0x7ff69aa4ee80,11534336,65536,0,0,0,16384,16384,0,64,0x7f08b97bae80,0,65536,65536,0,0,182895,0,0,64,0x7f957386ce80,114688,0,32768,32768,16384,16384,65536,49152,64,0x7f9536616e80,65536,64048,48,1440,32768,32768,0,64,0x7f41ecd2ae80,0,0,0,1048576,0,0,0,0,64,0x7fe701bece80,360448,345696,233745,3428206,163840,0,0,180224,2187879063954814,2187879063973854 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f0bbde98e80,0,131072,0,48,0,0,0,48,64,0x7fcf84fe8e80,16384,16384,32768,49152,0,65536,32768,0,44746,44746,64,0x7fe40d9f6e80,0,0,16384,16384,393216,24815652,22931365,1523839,64,0x7ff69aa4ee80,11534336,65536,0,0,0,16384,16384,0,64,0x7f08b97bae80,0,65536,65536,0,0,185376,0,0,64,0x7f957386ce80,114688,0,32768,32768,16384,16384,65536,49152,64,0x7f9536616e80,65536,64048,48,1440,32768,32768,0,64,0x7f41ecd2ae80,0,0,0,1048576,0,0,0,0,64,0x7fe701bece80,360448,348640,232513,3393565,163840,0,0,180224,2187879064044414,2187879064063454 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_ACTIVE_INST_ANY,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,wave_size_1,obj_1,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_2,obj_2,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,wave_size_3,obj_3,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,wave_size_4,obj_4,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,wave_size_5,obj_5,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,wave_size_6,obj_6,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,wave_size_7,obj_7,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,wave_size_8,obj_8,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,GRBM_COUNT,GRBM_GUI_ACTIVE,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f2d32c78e80,360448,383040,230767,3394741,163840,0,0,180224,64,0x7f9f987fce80,65536,64048,48,1440,32768,32768,0,64,0x7ff727660e80,0,0,16384,16384,393216,24251404,21796835,2094121,64,0x7fa2e0434e80,0,65536,64548,48,1462,192379,0,0,64,0x7f6230282e80,11534336,65536,0,0,0,16384,16384,0,64,0x7f1a99face80,114688,0,32768,32768,16384,16384,65536,49152,64,0x7f221d6eae80,0,0,0,1048576,0,0,0,0,64,0x7fccf1014e80,0,131072,144,48,0,0,0,192,64,0x7f2865f04e80,16384,16384,32768,49152,0,65536,32768,0,48122,48122,194294746542348,194294746566668 +1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f2d32c78e80,360448,339472,228619,3354299,163840,0,0,180224,64,0x7f9f987fce80,65536,64048,48,1440,32768,32768,0,64,0x7ff727660e80,0,0,16384,16384,393216,24739969,23168673,1210848,64,0x7fa2e0434e80,0,65536,65536,0,0,204715,0,0,64,0x7f6230282e80,11534336,65536,0,0,0,16384,16384,0,64,0x7f1a99face80,114688,0,32768,32768,16384,16384,65536,49152,64,0x7f221d6eae80,0,0,0,1048576,0,0,0,0,64,0x7fccf1014e80,0,131072,0,48,0,0,0,48,64,0x7f2865f04e80,16384,16384,32768,49152,0,65536,32768,0,43105,43105,194294746587308,194294746606348 +2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f2d32c78e80,360448,345616,234177,3390078,163840,0,0,180224,64,0x7f9f987fce80,65536,64048,48,1440,32768,32768,0,64,0x7ff727660e80,0,0,16384,16384,393216,23757309,22259143,1137718,64,0x7fa2e0434e80,0,65536,65536,0,0,124150,0,0,64,0x7f6230282e80,11534336,65536,0,0,0,16384,16384,0,64,0x7f1a99face80,114688,0,32768,32768,16384,16384,65536,49152,64,0x7f221d6eae80,0,0,0,1048576,0,0,0,0,64,0x7fccf1014e80,0,131072,0,48,0,0,0,48,64,0x7f2865f04e80,16384,16384,32768,49152,0,65536,32768,0,43540,43540,194294746690668,194294746709548 diff --git a/tests/workloads/ipblocks_SQ/MI100/sysinfo.csv b/tests/workloads/ipblocks_SQ/MI100/sysinfo.csv index 7d8c7055fe..c13650d778 100644 --- a/tests/workloads/ipblocks_SQ/MI100/sysinfo.csv +++ b/tests/workloads/ipblocks_SQ/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -ipblocks_SQ,./tests/vcopy -n 1048576 -b 256 -i 3,sq,Fri Mar 1 16:46:26 2024 (CST),1,t006-003.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651240,,5.7.1-98,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +ipblocks_SQ,./tests/vcopy -n 1048576 -b 256 -i 3,sq,Thu 07 Mar 2024 01:09:12 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/ipblocks_SQ/MI100/timestamps.csv b/tests/workloads/ipblocks_SQ/MI100/timestamps.csv index ed80d12fc9..54300edca9 100644 --- a/tests/workloads/ipblocks_SQ/MI100/timestamps.csv +++ b/tests/workloads/ipblocks_SQ/MI100/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,2872743,2872743,1048576,256,0,0,8,8,16,64,0x0,0x7fd8a6dd2e80,2187879063882788,2187879063908574,2187879063933214,2187879063957599 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,2872743,2872743,1048576,256,0,0,8,8,16,64,0x0,0x7fd8a6dd2e80,2187879063946368,2187879063954814,2187879063973854,2187879064042518 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,2872743,2872743,1048576,256,0,0,8,8,16,64,0x0,0x7fd8a6dd2e80,2187879063985050,2187879064044414,2187879064063454,2187879064064369 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,178946,178946,1048576,256,0,0,8,8,16,64,0x0,0x7f140cd24e80,194294746517963,194294746542348,194294746566668,194294746592004 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,178946,178946,1048576,256,0,0,8,8,16,64,0x0,0x7f140cd24e80,194294746579850,194294746587308,194294746606348,194294746688917 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,178946,178946,1048576,256,0,0,8,8,16,64,0x0,0x7f140cd24e80,194294746618003,194294746690668,194294746709548,194294746710728 diff --git a/tests/workloads/ipblocks_SQ/MI200/SQ_IFETCH_LEVEL.csv b/tests/workloads/ipblocks_SQ/MI200/SQ_IFETCH_LEVEL.csv new file mode 100644 index 0000000000..6df566d2e8 --- /dev/null +++ b/tests/workloads/ipblocks_SQ/MI200/SQ_IFETCH_LEVEL.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,336275,336275,1048576,256,0,0,8,0,16,64,0x0,0x7f4f18340ec0,27606,27606,16384,65536,13698,1553080,199243257890335,199251858177827,199251858197828,199243273617477 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,336275,336275,1048576,256,0,0,8,0,16,64,0x0,0x7f4f18340ec0,40557,40557,16384,65536,9412,1048644,199243273638647,199251858218948,199251858234148,199243273939656 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,336275,336275,1048576,256,0,0,8,0,16,64,0x0,0x7f4f18340ec0,40036,40036,16384,65536,9730,1048692,199243273969292,199251858254148,199251858269668,199243274140837 diff --git a/tests/workloads/ipblocks_SQ/MI200/SQ_INST_LEVEL_LDS.csv b/tests/workloads/ipblocks_SQ/MI200/SQ_INST_LEVEL_LDS.csv new file mode 100644 index 0000000000..c6bc2d6b86 --- /dev/null +++ b/tests/workloads/ipblocks_SQ/MI200/SQ_INST_LEVEL_LDS.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,336459,336459,1048576,256,0,0,8,0,16,64,0x0,0x7f8d3eb34ec0,0,0,0,199243740198768,199251858177827,199251858197828,199243755900662 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,336459,336459,1048576,256,0,0,8,0,16,64,0x0,0x7f8d3eb34ec0,0,0,0,199243755918826,199251858218948,199251858234148,199243756228833 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,336459,336459,1048576,256,0,0,8,0,16,64,0x0,0x7f8d3eb34ec0,0,0,0,199243756254982,199251858254148,199251858269668,199243756413292 diff --git a/tests/workloads/ipblocks_SQ/MI200/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/ipblocks_SQ/MI200/SQ_INST_LEVEL_SMEM.csv new file mode 100644 index 0000000000..f2ba009db1 --- /dev/null +++ b/tests/workloads/ipblocks_SQ/MI200/SQ_INST_LEVEL_SMEM.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,336644,336644,1048576,256,0,0,8,0,16,64,0x0,0x7f601be04ec0,65536,172532,19226608,199244217858407,199251858177827,199251858197828,199244233653417 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,336644,336644,1048576,256,0,0,8,0,16,64,0x0,0x7f601be04ec0,65536,221966,24789584,199244233670409,199251858218948,199251858234148,199244233973923 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,336644,336644,1048576,256,0,0,8,0,16,64,0x0,0x7f601be04ec0,65536,223208,24976792,199244234000182,199251858254148,199251858269668,199244234155717 diff --git a/tests/workloads/ipblocks_SQ/MI200/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/ipblocks_SQ/MI200/SQ_INST_LEVEL_VMEM.csv new file mode 100644 index 0000000000..6e72edc0ad --- /dev/null +++ b/tests/workloads/ipblocks_SQ/MI200/SQ_INST_LEVEL_VMEM.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,336828,336828,1048576,256,0,0,8,0,16,64,0x0,0x7f57fc768ec0,32768,291116,32616104,199244692689033,199251858177827,199251858197828,199244708573473 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,336828,336828,1048576,256,0,0,8,0,16,64,0x0,0x7f57fc768ec0,32768,586097,65651116,199244708592498,199251858218948,199251858234148,199244708875995 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,336828,336828,1048576,256,0,0,8,0,16,64,0x0,0x7f57fc768ec0,32768,589928,66080600,199244708902164,199251858254148,199251858269668,199244709053841 diff --git a/tests/workloads/ipblocks_SQ/MI200/SQ_LEVEL_WAVES.csv b/tests/workloads/ipblocks_SQ/MI200/SQ_LEVEL_WAVES.csv new file mode 100644 index 0000000000..71f20939fa --- /dev/null +++ b/tests/workloads/ipblocks_SQ/MI200/SQ_LEVEL_WAVES.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,337011,337011,1048576,256,0,0,8,0,16,64,0x0,0x7f6e468a0ec0,28447,28447,11419,227584,16384,11171625,132835,0,45191448,199245172812934,199251858177827,199251858197828,199245188521290 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,337011,337011,1048576,256,0,0,8,0,16,64,0x0,0x7f6e468a0ec0,42213,42213,13481,337712,16384,19736747,227586,0,79416648,199245188549874,199251858218948,199251858234148,199245188790269 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,337011,337011,1048576,256,0,0,8,0,16,64,0x0,0x7f6e468a0ec0,43110,43110,14163,344888,16384,20211071,231384,0,81328932,199245188825485,199251858254148,199251858269668,199245188974427 diff --git a/tests/workloads/ipblocks_SQ/MI200/perfmon/SQ_IFETCH_LEVEL.txt b/tests/workloads/ipblocks_SQ/MI200/perfmon/SQ_IFETCH_LEVEL.txt new file mode 100644 index 0000000000..293092f641 --- /dev/null +++ b/tests/workloads/ipblocks_SQ/MI200/perfmon/SQ_IFETCH_LEVEL.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ/MI200/perfmon/SQ_INST_LEVEL_LDS.txt b/tests/workloads/ipblocks_SQ/MI200/perfmon/SQ_INST_LEVEL_LDS.txt new file mode 100644 index 0000000000..08439eedce --- /dev/null +++ b/tests/workloads/ipblocks_SQ/MI200/perfmon/SQ_INST_LEVEL_LDS.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt b/tests/workloads/ipblocks_SQ/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt new file mode 100644 index 0000000000..6cca322d4e --- /dev/null +++ b/tests/workloads/ipblocks_SQ/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt b/tests/workloads/ipblocks_SQ/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt new file mode 100644 index 0000000000..e527ad31ba --- /dev/null +++ b/tests/workloads/ipblocks_SQ/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ/MI200/perfmon/SQ_LEVEL_WAVES.txt b/tests/workloads/ipblocks_SQ/MI200/perfmon/SQ_LEVEL_WAVES.txt new file mode 100644 index 0000000000..3f8e04adb3 --- /dev/null +++ b/tests/workloads/ipblocks_SQ/MI200/perfmon/SQ_LEVEL_WAVES.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_0.txt b/tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_0.txt new file mode 100644 index 0000000000..a8af39a86a --- /dev/null +++ b/tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_0.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_CVT SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU SQ_INSTS_VSKIPPED SQ_INSTS SQ_INSTS_VALU GRBM_COUNT GRBM_GUI_ACTIVE + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_1.txt b/tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_1.txt new file mode 100644 index 0000000000..0ffea7de49 --- /dev/null +++ b/tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_1.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_ADD_F16 SQ_INSTS_VALU_MUL_F16 SQ_INSTS_VALU_FMA_F16 SQ_INSTS_VALU_TRANS_F16 SQ_INSTS_VALU_ADD_F32 SQ_INSTS_VALU_MUL_F32 SQ_INSTS_VALU_FMA_F32 SQ_INSTS_VALU_TRANS_F32 + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_10.txt b/tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_10.txt new file mode 100644 index 0000000000..7053d4dce6 --- /dev/null +++ b/tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_10.txt @@ -0,0 +1,5 @@ +pmc: SQC_TC_DATA_WRITE_REQ SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_11.txt b/tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_11.txt new file mode 100644 index 0000000000..77ae8b461f --- /dev/null +++ b/tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_11.txt @@ -0,0 +1,5 @@ +pmc: SQC_ICACHE_MISSES_DUPLICATE SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_12.txt b/tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_12.txt new file mode 100644 index 0000000000..dfb2cf65e5 --- /dev/null +++ b/tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_12.txt @@ -0,0 +1,5 @@ +pmc: SQC_DCACHE_REQ_READ_1 SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_2.txt b/tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_2.txt new file mode 100644 index 0000000000..35225290be --- /dev/null +++ b/tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_2.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_ADD_F64 SQ_INSTS_VALU_MUL_F64 SQ_INSTS_VALU_FMA_F64 SQ_INSTS_VALU_TRANS_F64 SQ_INSTS_VALU_INT32 SQ_INSTS_VALU_INT64 SQ_INSTS_SMEM SQ_INSTS_FLAT + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_3.txt b/tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_3.txt new file mode 100644 index 0000000000..50681b4ad7 --- /dev/null +++ b/tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_3.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG SQ_WAVE_CYCLES SQ_WAIT_ANY SQ_WAIT_INST_ANY + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_4.txt b/tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_4.txt new file mode 100644 index 0000000000..a2a744969f --- /dev/null +++ b/tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_4.txt @@ -0,0 +1,5 @@ +pmc: SQ_ACTIVE_INST_ANY SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU SQ_ACTIVE_INST_SCA + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_5.txt b/tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_5.txt new file mode 100644 index 0000000000..b6746a54f9 --- /dev/null +++ b/tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_5.txt @@ -0,0 +1,5 @@ +pmc: SQ_ACTIVE_INST_EXP_GDS SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU SQ_THREAD_CYCLES_VALU + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_6.txt b/tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_6.txt new file mode 100644 index 0000000000..e6e2d40811 --- /dev/null +++ b/tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_6.txt @@ -0,0 +1,5 @@ +pmc: SQ_IFETCH SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_7.txt b/tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_7.txt new file mode 100644 index 0000000000..86671fadbb --- /dev/null +++ b/tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_7.txt @@ -0,0 +1,5 @@ +pmc: SQ_WAVES_LT_32 SQ_WAVES_LT_16 SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_8.txt b/tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_8.txt new file mode 100644 index 0000000000..f01548a76d --- /dev/null +++ b/tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_8.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM_NORM SQ_INSTS_MFMA SQ_INSTS_VALU_MFMA_I8 SQ_INSTS_VALU_MFMA_F16 SQ_INSTS_VALU_MFMA_BF16 SQ_INSTS_VALU_MFMA_F32 SQ_INSTS_VALU_MFMA_F64 SQ_VALU_MFMA_BUSY_CYCLES + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_9.txt b/tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_9.txt new file mode 100644 index 0000000000..e9663fc4a5 --- /dev/null +++ b/tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_9.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_FLAT_LDS_ONLY SQ_INSTS_VALU_MFMA_MOPS_I8 SQ_INSTS_VALU_MFMA_MOPS_F16 SQ_INSTS_VALU_MFMA_MOPS_BF16 SQ_INSTS_VALU_MFMA_MOPS_F32 SQ_INSTS_VALU_MFMA_MOPS_F64 SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ/MI200/perfmon/timestamps.txt b/tests/workloads/ipblocks_SQ/MI200/perfmon/timestamps.txt new file mode 100644 index 0000000000..676cca1b80 --- /dev/null +++ b/tests/workloads/ipblocks_SQ/MI200/perfmon/timestamps.txt @@ -0,0 +1,5 @@ +pmc: + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ/MI200/pmc_perf.csv b/tests/workloads/ipblocks_SQ/MI200/pmc_perf.csv new file mode 100644 index 0000000000..2bb202d22c --- /dev/null +++ b/tests/workloads/ipblocks_SQ/MI200/pmc_perf.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,wave_size_1,obj_1,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,wave_size_2,obj_2,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,wave_size_3,obj_3,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,wave_size_4,obj_4,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,wave_size_5,obj_5,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,wave_size_6,obj_6,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_7,obj_7,SQ_ACTIVE_INST_ANY,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,wave_size_8,obj_8,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_9,obj_9,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_10,obj_10,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,wave_size_11,obj_11,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,GRBM_COUNT,GRBM_GUI_ACTIVE,wave_size_12,obj_12,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7fc9c3768ec0,0,0,1048576,0,0,0,0,0,64,0x7feb9ac18ec0,131072,0,0,0,0,0,0,0,64,0x7f12b2c28ec0,0,0,0,0,0,0,0,0,64,0x7f6c79108ec0,0,0,0,0,114688,0,65536,32768,64,0x7fa00f670ec0,0,0,0,16384,16384,10934965,9763176,827725,64,0x7fee3825cec0,0,0,0,0,0,0,168,56,64,0x7f59b1f38ec0,32768,32768,0,64,0x7f5674918ec0,344064,222976,127987,1615005,0,0,163840,114688,64,0x7f0011640ec0,0,0,0,224,0,65536,64162,56,64,0x7fe75edd8ec0,1319,113132,0,0,65536,63800,56,1680,64,0x7fae1f40cec0,65536,0,0,0,16384,16384,0,0,64,0x7f3d30f78ec0,0,16384,16384,32768,49152,0,393216,163840,28295,28295,64,0x7f89cd87cec0,0,32768,32768,16384,16384,65536,49152,10485760,199251858177827,199251858197828 +1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7fc9c3768ec0,0,0,1048576,0,0,0,0,0,64,0x7feb9ac18ec0,131072,0,0,0,0,0,0,0,64,0x7f12b2c28ec0,0,0,0,0,0,0,0,0,64,0x7f6c79108ec0,0,0,0,0,114688,0,65536,32768,64,0x7fa00f670ec0,0,0,0,16384,16384,19187139,18007559,835516,64,0x7fee3825cec0,0,0,0,0,0,0,0,56,64,0x7f59b1f38ec0,32768,32768,0,64,0x7f5674918ec0,344064,333920,223951,2824441,0,0,163840,114688,64,0x7f0011640ec0,0,0,0,56,0,65536,65536,0,64,0x7fe75edd8ec0,0,229693,0,0,65536,63800,56,1680,64,0x7fae1f40cec0,65536,0,0,0,16384,16384,0,0,64,0x7f3d30f78ec0,0,16384,16384,32768,49152,0,393216,163840,42135,42135,64,0x7f89cd87cec0,0,32768,32768,16384,16384,65536,49152,10485760,199251858218948,199251858234148 +2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7fc9c3768ec0,0,0,1048576,0,0,0,0,0,64,0x7feb9ac18ec0,131072,0,0,0,0,0,0,0,64,0x7f12b2c28ec0,0,0,0,0,0,0,0,0,64,0x7f6c79108ec0,0,0,0,0,114688,0,65536,32768,64,0x7fa00f670ec0,0,0,0,16384,16384,19443161,18081365,1017732,64,0x7fee3825cec0,0,0,0,0,0,0,0,56,64,0x7f59b1f38ec0,32768,32768,0,64,0x7f5674918ec0,344064,335296,224911,2814564,0,0,163840,114688,64,0x7f0011640ec0,0,0,0,56,0,65536,65536,0,64,0x7fe75edd8ec0,0,185998,0,0,65536,63800,56,1680,64,0x7fae1f40cec0,65536,0,0,0,16384,16384,0,0,64,0x7f3d30f78ec0,0,16384,16384,32768,49152,0,393216,163840,41526,41526,64,0x7f89cd87cec0,0,32768,32768,16384,16384,65536,49152,10485760,199251858254148,199251858269668 diff --git a/tests/workloads/ipblocks_SQ/MI200/roofline.csv b/tests/workloads/ipblocks_SQ/MI200/roofline.csv new file mode 100644 index 0000000000..eb12972e07 --- /dev/null +++ b/tests/workloads/ipblocks_SQ/MI200/roofline.csv @@ -0,0 +1,5 @@ +device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh +0,1388.606,1388.014,1389.1979,5013.4312,5010.3784,5016.4839,9222.1006,9221.4424,9222.7588,18048.148,18047.154,18049.143,20925.711,20865.328,20986.094,20259.674,20258.982,20260.365,170342.34,170338.62,170346.06,164805.45,164801.22,164809.69,41405.574,41404.898,41406.25,41467.379,41466.711,41468.047,166282.69,165791.16,166774.22 +1,1389.085,1388.5358,1389.6342,5028.3569,5026.0806,5030.6333,9233.1758,9232.5146,9233.8369,18085.131,18083.555,18086.707,20972.803,20905.426,21040.18,20294.641,20294.074,20295.207,170848.98,170844.91,170853.06,165103.45,165099.84,165107.06,41483.621,41482.855,41484.387,41543.184,41542.176,41544.191,166873.55,166870.08,166877.02 +2,1388.2489,1387.6832,1388.8146,5035.9229,5033.5801,5038.2656,9262.1865,9261.2529,9263.1201,18106.953,18106.029,18107.877,21051.465,21051.16,21051.77,20354.99,20354.521,20355.459,171135,171132.19,171137.81,165515.41,165511.5,165519.31,41590.117,41589.039,41591.195,41653.234,41652.277,41654.191,166991.17,166397.83,167584.52 +3,1388.8011,1388.223,1389.3793,5033.9556,5032.5698,5035.3413,9242.6387,9242.1729,9243.1045,18028.344,18024.803,18031.885,21039.02,21038.312,21039.727,20316.457,20315.727,20317.188,171056.38,171052.06,171060.69,165249.28,165243.64,165254.92,41447.359,41294.148,41600.57,41587.234,41586.715,41587.754,167034.94,167032.98,167036.89 diff --git a/tests/workloads/ipblocks_SQ/MI200/sysinfo.csv b/tests/workloads/ipblocks_SQ/MI200/sysinfo.csv new file mode 100644 index 0000000000..f770ed362f --- /dev/null +++ b/tests/workloads/ipblocks_SQ/MI200/sysinfo.csv @@ -0,0 +1,2 @@ +workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd +ipblocks_SQ,./sample/vcopy -n 1048576 -b 256 -i 3,sq|roofline,Thu 07 Mar 2024 02:31:50 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/ipblocks_SQ/MI200/timestamps.csv b/tests/workloads/ipblocks_SQ/MI200/timestamps.csv new file mode 100644 index 0000000000..c1b26c690f --- /dev/null +++ b/tests/workloads/ipblocks_SQ/MI200/timestamps.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,339689,339689,1048576,256,0,0,8,0,16,64,0x0,0x7f29ed89cec0,199251858149201,199251858177827,199251858197828,199251858425263 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,339689,339689,1048576,256,0,0,8,0,16,64,0x0,0x7f29ed89cec0,199251858210547,199251858218948,199251858234148,199251858515855 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,339689,339689,1048576,256,0,0,8,0,16,64,0x0,0x7f29ed89cec0,199251858244962,199251858254148,199251858269668,199251858506176 diff --git a/tests/workloads/ipblocks_SQC/MI100/pmc_dispatch_info.csv b/tests/workloads/ipblocks_SQC/MI100/pmc_dispatch_info.csv new file mode 100644 index 0000000000..17300ae9af --- /dev/null +++ b/tests/workloads/ipblocks_SQC/MI100/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) ",2 +1,"vecCopy(double*, double*, double*, int, int) ",2 +2,"vecCopy(double*, double*, double*, int, int) ",2 diff --git a/tests/workloads/ipblocks_SQC/MI100/pmc_perf.csv b/tests/workloads/ipblocks_SQC/MI100/pmc_perf.csv index 7861c6bf79..622ae8c42f 100644 --- a/tests/workloads/ipblocks_SQC/MI100/pmc_perf.csv +++ b/tests/workloads/ipblocks_SQC/MI100/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,wave_size_1,obj_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_2,obj_2,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,wave_size_3,obj_3,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f429a576e80,0,0,192,0,65536,64572,48,1310,64,0x7fd114776e80,32768,0,64,0x7ff82cc10e80,388784,236554,3418693,16384,24890081,144,48,0,48597,48597,64,0x7ff7fd286e80,188162,0,0,65536,64048,48,1440,32768,2187828369530420,2187828369554580 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f429a576e80,0,0,48,0,65536,65536,0,0,64,0x7fd114776e80,32768,0,64,0x7ff82cc10e80,348888,237232,3439625,16384,24376003,0,48,0,43610,43610,64,0x7ff7fd286e80,136488,0,0,65536,64048,48,1440,32768,2187828369645780,2187828369664980 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f429a576e80,0,0,48,0,65536,65536,0,0,64,0x7fd114776e80,32768,0,64,0x7ff82cc10e80,344400,229807,3366573,16384,24900236,0,48,0,43049,43049,64,0x7ff7fd286e80,186306,0,0,65536,64048,48,1440,32768,2187828369686100,2187828369705140 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,wave_size_1,obj_1,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,wave_size_2,obj_2,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_3,obj_3,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f8502124e80,186901,0,0,65536,64048,48,1440,32768,64,0x7f9356168e80,382680,232518,3401999,16384,25014980,144,48,0,47834,47834,64,0x7f36d050ee80,32768,0,64,0x7fbac8766e80,0,0,192,0,65536,64491,48,1460,194236443950538,194236443974218 +1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f8502124e80,135615,0,0,65536,64048,48,1440,32768,64,0x7f9356168e80,342496,231822,3379461,16384,24720277,0,48,0,42811,42811,64,0x7f36d050ee80,32768,0,64,0x7fbac8766e80,0,0,48,0,65536,65536,0,0,194236444061258,194236444080778 +2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f8502124e80,186340,0,0,65536,64048,48,1440,32768,64,0x7f9356168e80,338336,226328,3294963,16384,23775059,0,48,0,42291,42291,64,0x7f36d050ee80,32768,0,64,0x7fbac8766e80,0,0,48,0,65536,65536,0,0,194236444104138,194236444123338 diff --git a/tests/workloads/ipblocks_SQC/MI100/sysinfo.csv b/tests/workloads/ipblocks_SQC/MI100/sysinfo.csv index d50b9ba4c9..7146d184e7 100644 --- a/tests/workloads/ipblocks_SQC/MI100/sysinfo.csv +++ b/tests/workloads/ipblocks_SQC/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -ipblocks_SQC,./tests/vcopy -n 1048576 -b 256 -i 3,sqc,Fri Mar 1 16:45:37 2024 (CST),1,t006-003.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651240,,5.7.1-98,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +ipblocks_SQC,./tests/vcopy -n 1048576 -b 256 -i 3,sqc,Thu 07 Mar 2024 01:08:19 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/ipblocks_SQC/MI100/timestamps.csv b/tests/workloads/ipblocks_SQC/MI100/timestamps.csv index 2e361652b6..8f9ff4ebd7 100644 --- a/tests/workloads/ipblocks_SQC/MI100/timestamps.csv +++ b/tests/workloads/ipblocks_SQC/MI100/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,2855637,2855637,1048576,256,0,0,8,8,16,64,0x0,0x7fbda45cce80,2187828369504409,2187828369530420,2187828369554580,2187828369565684 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,2855637,2855637,1048576,256,0,0,8,8,16,64,0x0,0x7fbda45cce80,2187828369567137,2187828369645780,2187828369664980,2187828369665982 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,2855637,2855637,1048576,256,0,0,8,8,16,64,0x0,0x7fbda45cce80,2187828369676522,2187828369686100,2187828369705140,2187828369706127 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,160402,160402,1048576,256,0,0,8,8,16,64,0x0,0x7f851f682e80,194236443922433,194236443950538,194236443974218,194236443985733 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,160402,160402,1048576,256,0,0,8,8,16,64,0x0,0x7f851f682e80,194236443988097,194236444061258,194236444080778,194236444082426 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,160402,160402,1048576,256,0,0,8,8,16,64,0x0,0x7f851f682e80,194236444093878,194236444104138,194236444123338,194236444124756 diff --git a/tests/workloads/ipblocks_SQC/MI200/perfmon/pmc_perf_0.txt b/tests/workloads/ipblocks_SQC/MI200/perfmon/pmc_perf_0.txt new file mode 100644 index 0000000000..bdc62f52a1 --- /dev/null +++ b/tests/workloads/ipblocks_SQC/MI200/perfmon/pmc_perf_0.txt @@ -0,0 +1,5 @@ +pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ SQC_TC_DATA_WRITE_REQ GRBM_COUNT GRBM_GUI_ACTIVE + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQC/MI200/perfmon/pmc_perf_1.txt b/tests/workloads/ipblocks_SQC/MI200/perfmon/pmc_perf_1.txt new file mode 100644 index 0000000000..21c59688f7 --- /dev/null +++ b/tests/workloads/ipblocks_SQC/MI200/perfmon/pmc_perf_1.txt @@ -0,0 +1,5 @@ +pmc: SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES SQC_ICACHE_MISSES_DUPLICATE + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQC/MI200/perfmon/pmc_perf_2.txt b/tests/workloads/ipblocks_SQC/MI200/perfmon/pmc_perf_2.txt new file mode 100644 index 0000000000..df6d67d7b7 --- /dev/null +++ b/tests/workloads/ipblocks_SQC/MI200/perfmon/pmc_perf_2.txt @@ -0,0 +1,5 @@ +pmc: SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE SQC_DCACHE_REQ_READ_1 + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQC/MI200/perfmon/pmc_perf_3.txt b/tests/workloads/ipblocks_SQC/MI200/perfmon/pmc_perf_3.txt new file mode 100644 index 0000000000..6e5320c11c --- /dev/null +++ b/tests/workloads/ipblocks_SQC/MI200/perfmon/pmc_perf_3.txt @@ -0,0 +1,5 @@ +pmc: SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQC/MI200/perfmon/timestamps.txt b/tests/workloads/ipblocks_SQC/MI200/perfmon/timestamps.txt new file mode 100644 index 0000000000..676cca1b80 --- /dev/null +++ b/tests/workloads/ipblocks_SQC/MI200/perfmon/timestamps.txt @@ -0,0 +1,5 @@ +pmc: + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQC/MI200/pmc_perf.csv b/tests/workloads/ipblocks_SQC/MI200/pmc_perf.csv new file mode 100644 index 0000000000..ff6a97d7d8 --- /dev/null +++ b/tests/workloads/ipblocks_SQC/MI200/pmc_perf.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,wave_size_1,obj_1,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,wave_size_2,obj_2,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,wave_size_3,obj_3,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7fce0fe80ec0,219376,127421,1603313,16384,10739783,168,56,0,27421,27421,64,0x7effd4f98ec0,115211,0,0,65536,63800,56,1680,32768,64,0x7f31cc13cec0,0,0,224,0,65536,64213,56,1267,64,0x7efecfec0ec0,32768,0,198704749963343,198704749983343 +1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7fce0fe80ec0,333120,218312,2747759,16384,19026276,0,56,0,41639,41639,64,0x7effd4f98ec0,219412,0,0,65536,63800,56,1680,32768,64,0x7f31cc13cec0,0,0,56,0,65536,65536,0,0,64,0x7efecfec0ec0,32768,0,198704750002383,198704750018383 +2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7fce0fe80ec0,325832,218495,2717504,16384,18986325,0,56,0,40728,40728,64,0x7effd4f98ec0,217554,0,0,65536,63800,56,1680,32768,64,0x7f31cc13cec0,0,0,56,0,65536,65536,0,0,64,0x7efecfec0ec0,32768,0,198704750078383,198704750095343 diff --git a/tests/workloads/ipblocks_SQC/MI200/roofline.csv b/tests/workloads/ipblocks_SQC/MI200/roofline.csv new file mode 100644 index 0000000000..60fcbd8066 --- /dev/null +++ b/tests/workloads/ipblocks_SQC/MI200/roofline.csv @@ -0,0 +1,5 @@ +device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh +0,1388.7397,1388.1733,1389.3062,5015.8813,5012.8813,5018.8813,9222.6709,9222.0166,9223.3252,18048.17,18047.064,18049.275,20930.85,20870.938,20990.762,20262.855,20262.229,20263.482,170394.98,170390.84,170399.12,164837.41,164832.53,164842.28,41414.047,41413.523,41414.57,41474.961,41474.348,41475.574,166325.28,165839.44,166811.12 +1,1389.2844,1388.7231,1389.8457,5028.6113,5026.665,5030.5576,9234.4121,9233.7969,9235.0273,18091.221,18088.502,18093.939,20975.447,20909.34,21041.555,20293.709,20293.186,20294.232,170842.59,170837.84,170847.34,165111.66,165108.61,165114.7,41485.648,41484.945,41486.352,41545.789,41544.871,41546.707,166902.91,166900.58,166905.23 +2,1388.4371,1387.9282,1388.946,5036.417,5034.2773,5038.5566,9257.5527,9256.7119,9258.3936,18101.041,18100.248,18101.834,21043.045,21042.604,21043.486,20343.709,20343.178,20344.24,171059.3,171054.94,171063.66,165454.78,165450.5,165459.06,41572.215,41571.301,41573.129,41629.695,41628.672,41630.719,166910.55,166325.86,167495.23 +3,1388.9329,1388.3834,1389.4823,5030.9453,5029.4277,5032.4629,9239.9854,9239.418,9240.5527,18024.152,18020.881,18027.424,21028.113,21027.771,21028.455,20310.254,20309.654,20310.854,170997,170993.67,171000.33,165191.84,165187.67,165196.02,41437.301,41285.773,41588.828,41577.523,41576.809,41578.238,166997.12,166994.06,167000.19 diff --git a/tests/workloads/ipblocks_SQC/MI200/sysinfo.csv b/tests/workloads/ipblocks_SQC/MI200/sysinfo.csv new file mode 100644 index 0000000000..5c32b483cd --- /dev/null +++ b/tests/workloads/ipblocks_SQC/MI200/sysinfo.csv @@ -0,0 +1,2 @@ +workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd +ipblocks_SQC,./sample/vcopy -n 1048576 -b 256 -i 3,sqc|roofline,Thu 07 Mar 2024 02:22:49 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/ipblocks_SQC/MI200/timestamps.csv b/tests/workloads/ipblocks_SQC/MI200/timestamps.csv new file mode 100644 index 0000000000..5a3983e799 --- /dev/null +++ b/tests/workloads/ipblocks_SQC/MI200/timestamps.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,317082,317082,1048576,256,0,0,8,0,16,64,0x0,0x7f2883b64ec0,198704749934740,198704749963343,198704749983343,198704749996978 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,317082,317082,1048576,256,0,0,8,0,16,64,0x0,0x7f2883b64ec0,198704749994884,198704750002383,198704750018383,198704750077080 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,317082,317082,1048576,256,0,0,8,0,16,64,0x0,0x7f2883b64ec0,198704750029149,198704750078383,198704750095343,198704750096626 diff --git a/tests/workloads/ipblocks_SQ_CPC/MI100/SQ_IFETCH_LEVEL.csv b/tests/workloads/ipblocks_SQ_CPC/MI100/SQ_IFETCH_LEVEL.csv index 70a56e08d2..e8982b8f0f 100644 --- a/tests/workloads/ipblocks_SQ_CPC/MI100/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/ipblocks_SQ_CPC/MI100/SQ_IFETCH_LEVEL.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2876835,2876835,1048576,256,0,0,8,8,16,64,0x0,0x7f9f9afc4e80,48709,48709,16384,65536,13162,1682428,2187889777048379,2187887112527251,2187887112551091,2187889784581601 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2876835,2876835,1048576,256,0,0,8,8,16,64,0x0,0x7f9f9afc4e80,44010,44010,16384,65536,8191,1048588,2187889784604053,2187887112653331,2187887112672531,2187889784917381 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2876835,2876835,1048576,256,0,0,8,8,16,64,0x0,0x7f9f9afc4e80,44123,44123,16384,65536,8279,1048580,2187889784950133,2187887112694931,2187887112713811,2187889785144317 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,179219,179219,1048576,256,0,0,8,8,16,64,0x0,0x7f4fa8cdae80,48237,48237,16384,65536,12726,1616628,194296245157507,194303154953219,194303154977539,194296253306787 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,179219,179219,1048576,256,0,0,8,8,16,64,0x0,0x7f4fa8cdae80,43612,43612,16384,65536,8203,1048584,194296253328137,194303155101219,194303155120099,194296253677840 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,179219,179219,1048576,256,0,0,8,8,16,64,0x0,0x7f4fa8cdae80,42636,42636,16384,65536,8398,1048580,194296253711113,194303155144579,194303155163459,194296253904108 diff --git a/tests/workloads/ipblocks_SQ_CPC/MI100/SQ_INST_LEVEL_LDS.csv b/tests/workloads/ipblocks_SQ_CPC/MI100/SQ_INST_LEVEL_LDS.csv index 7d1f834ddf..4896b0c14e 100644 --- a/tests/workloads/ipblocks_SQ_CPC/MI100/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/ipblocks_SQ_CPC/MI100/SQ_INST_LEVEL_LDS.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2874833,2874833,1048576,256,0,0,8,8,16,64,0x0,0x7f6acc138e80,0,0,0,2187884874553566,2187887112527251,2187887112551091,2187884882258029 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2874833,2874833,1048576,256,0,0,8,8,16,64,0x0,0x7f6acc138e80,0,0,0,2187884882278517,2187887112653331,2187887112672531,2187884882536662 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2874833,2874833,1048576,256,0,0,8,8,16,64,0x0,0x7f6acc138e80,0,0,0,2187884882565486,2187887112694931,2187887112713811,2187884882714716 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,179403,179403,1048576,256,0,0,8,8,16,64,0x0,0x7ffb2d164e80,0,0,0,194296741272601,194303154953219,194303154977539,194296748949056 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,179403,179403,1048576,256,0,0,8,8,16,64,0x0,0x7ffb2d164e80,0,0,0,194296748969966,194303155101219,194303155120099,194296749218075 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,179403,179403,1048576,256,0,0,8,8,16,64,0x0,0x7ffb2d164e80,0,0,0,194296749247321,194303155144579,194303155163459,194296749392927 diff --git a/tests/workloads/ipblocks_SQ_CPC/MI100/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/ipblocks_SQ_CPC/MI100/SQ_INST_LEVEL_SMEM.csv index c2c54f8166..ccc2429eed 100644 --- a/tests/workloads/ipblocks_SQ_CPC/MI100/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/ipblocks_SQ_CPC/MI100/SQ_INST_LEVEL_SMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2875015,2875015,1048576,256,0,0,8,8,16,64,0x0,0x7f283f57ae80,65536,217216,27767632,2187885322687259,2187887112527251,2187887112551091,2187885330274052 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2875015,2875015,1048576,256,0,0,8,8,16,64,0x0,0x7f283f57ae80,65536,209234,26715320,2187885330291765,2187887112653331,2187887112672531,2187885330612477 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2875015,2875015,1048576,256,0,0,8,8,16,64,0x0,0x7f283f57ae80,65536,196192,25140224,2187885330640580,2187887112694931,2187887112713811,2187885330812412 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,179603,179603,1048576,256,0,0,8,8,16,64,0x0,0x7fed1067ee80,65536,191914,24554992,194297231769678,194303154953219,194303154977539,194297239406849 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,179603,179603,1048576,256,0,0,8,8,16,64,0x0,0x7fed1067ee80,65536,176036,22521432,194297239426245,194303155101219,194303155120099,194297239733517 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,179603,179603,1048576,256,0,0,8,8,16,64,0x0,0x7fed1067ee80,65536,180074,23061640,194297239762101,194303155144579,194303155163459,194297239932263 diff --git a/tests/workloads/ipblocks_SQ_CPC/MI100/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/ipblocks_SQ_CPC/MI100/SQ_INST_LEVEL_VMEM.csv index 61d2af3fe6..31d386d446 100644 --- a/tests/workloads/ipblocks_SQ_CPC/MI100/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/ipblocks_SQ_CPC/MI100/SQ_INST_LEVEL_VMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2876289,2876289,1048576,256,0,0,8,8,16,64,0x0,0x7f174c088e80,32768,652039,83463552,2187888441783939,2187887112527251,2187887112551091,2187888449299878 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2876289,2876289,1048576,256,0,0,8,8,16,64,0x0,0x7f174c088e80,32768,652467,83518484,2187888449319185,2187887112653331,2187887112672531,2187888449624498 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2876289,2876289,1048576,256,0,0,8,8,16,64,0x0,0x7f174c088e80,32768,651541,83386636,2187888449652781,2187887112694931,2187887112713811,2187888449827248 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,179787,179787,1048576,256,0,0,8,8,16,64,0x0,0x7f7116630e80,32768,662899,84848352,194297721610422,194303154953219,194303154977539,194297729775242 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,179787,179787,1048576,256,0,0,8,8,16,64,0x0,0x7f7116630e80,32768,678115,86800424,194297729793015,194303155101219,194303155120099,194297730132308 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,179787,179787,1048576,256,0,0,8,8,16,64,0x0,0x7f7116630e80,32768,670499,85820956,194297730160451,194303155144579,194303155163459,194297730337426 diff --git a/tests/workloads/ipblocks_SQ_CPC/MI100/SQ_LEVEL_WAVES.csv b/tests/workloads/ipblocks_SQ_CPC/MI100/SQ_LEVEL_WAVES.csv index 05fa1683c6..b534b5f98f 100644 --- a/tests/workloads/ipblocks_SQ_CPC/MI100/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/ipblocks_SQ_CPC/MI100/SQ_LEVEL_WAVES.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2875925,2875925,1048576,256,0,0,8,8,16,64,0x0,0x7fe579dcee80,47838,47838,16628,382712,16384,25226890,233099,0,101407552,2187887547830896,2187887112527251,2187887112551091,2187887555436594 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2875925,2875925,1048576,256,0,0,8,8,16,64,0x0,0x7fe579dcee80,42810,42810,12868,342488,16384,25670891,238345,0,103180768,2187887555466379,2187887112653331,2187887112672531,2187887555775430 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2875925,2875925,1048576,256,0,0,8,8,16,64,0x0,0x7fe579dcee80,42405,42405,13118,339248,16384,25101023,233485,0,100894448,2187887555813992,2187887112694931,2187887112713811,2187887556012765 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,179971,179971,1048576,256,0,0,8,8,16,64,0x0,0x7f93969ece80,47115,47115,16580,376928,16384,24402873,228411,0,98111176,194298215596255,194303154953219,194303154977539,194298223228756 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,179971,179971,1048576,256,0,0,8,8,16,64,0x0,0x7f93969ece80,42027,42027,14108,336224,16384,23800432,225815,0,95691556,194298223258402,194303155101219,194303155120099,194298223587736 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,179971,179971,1048576,256,0,0,8,8,16,64,0x0,0x7f93969ece80,41914,41914,13672,335320,16384,23933998,225355,0,96226252,194298223626329,194303155144579,194303155163459,194298223811700 diff --git a/tests/workloads/ipblocks_SQ_CPC/MI100/pmc_dispatch_info.csv b/tests/workloads/ipblocks_SQ_CPC/MI100/pmc_dispatch_info.csv new file mode 100644 index 0000000000..17300ae9af --- /dev/null +++ b/tests/workloads/ipblocks_SQ_CPC/MI100/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) ",2 +1,"vecCopy(double*, double*, double*, int, int) ",2 +2,"vecCopy(double*, double*, double*, int, int) ",2 diff --git a/tests/workloads/ipblocks_SQ_CPC/MI100/pmc_perf.csv b/tests/workloads/ipblocks_SQ_CPC/MI100/pmc_perf.csv index 45cbf900eb..6afb61f1a9 100644 --- a/tests/workloads/ipblocks_SQ_CPC/MI100/pmc_perf.csv +++ b/tests/workloads/ipblocks_SQ_CPC/MI100/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,wave_size_1,obj_1,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,wave_size_2,obj_2,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,wave_size_3,obj_3,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,wave_size_4,obj_4,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,wave_size_5,obj_5,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,wave_size_6,obj_6,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,CPC_ME1_DC0_SPI_BUSY,wave_size_7,obj_7,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,wave_size_8,obj_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fc120b86e80,180224,114688,0,32768,32768,16384,16384,65536,1294,118687,64,0x7fcce82e6e80,25325450,23019006,1945996,360448,3457216,163840,0,0,9921,550,64,0x7f76ed1ece80,0,65536,64436,48,1353,193497,0,0,64,0x7f8825558e80,49152,11534336,65536,0,0,0,16384,0,0,16964,64,0x7f2f6ccdee80,65536,32768,0,0,0,16384,16384,393216,538,48334,64,0x7fbccec4ce80,0,131072,144,48,0,0,0,192,64,0x7f1319d92e80,0,0,0,1048576,0,0,0,0,27622,64,0x7fe234190e80,383056,231266,16384,16384,16384,32768,49152,0,47881,47881,47881,0,64,0x7fa48ba7ce80,65536,64048,48,1440,32768,32768,0,2187887112527251,2187887112551091 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fc120b86e80,180224,114688,0,32768,32768,16384,16384,65536,4152,40951,64,0x7fcce82e6e80,24808883,22904901,1543534,360448,3354181,163840,0,0,8543,3842,64,0x7f76ed1ece80,0,65536,65536,0,0,108173,0,0,64,0x7f8825558e80,49152,11534336,65536,0,0,0,16384,0,0,13882,64,0x7f2f6ccdee80,65536,32768,0,0,0,16384,16384,393216,457,43398,64,0x7fbccec4ce80,0,131072,0,48,0,0,0,48,64,0x7f1319d92e80,0,0,0,1048576,0,0,0,0,25909,64,0x7fe234190e80,341312,226738,16384,16384,16384,32768,49152,0,42663,42663,42663,0,64,0x7fa48ba7ce80,65536,64048,48,1440,32768,32768,0,2187887112653331,2187887112672531 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fc120b86e80,180224,114688,0,32768,32768,16384,16384,65536,3894,38945,64,0x7fcce82e6e80,25366443,23263639,1742356,360448,3413055,163840,0,0,8566,3364,64,0x7f76ed1ece80,0,65536,65536,0,0,212444,0,0,64,0x7f8825558e80,49152,11534336,65536,0,0,0,16384,0,0,14129,64,0x7f2f6ccdee80,65536,32768,0,0,0,16384,16384,393216,457,42179,64,0x7fbccec4ce80,0,131072,0,48,0,0,0,48,64,0x7f1319d92e80,0,0,0,1048576,0,0,0,0,27177,64,0x7fe234190e80,336432,224844,16384,16384,16384,32768,49152,0,42053,42053,42053,0,64,0x7fa48ba7ce80,65536,64048,48,1440,32768,32768,0,2187887112694931,2187887112713811 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,wave_size_1,obj_1,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,wave_size_2,obj_2,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,wave_size_3,obj_3,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_4,obj_4,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,wave_size_5,obj_5,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,wave_size_6,obj_6,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,wave_size_7,obj_7,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,CPC_ME1_DC0_SPI_BUSY,wave_size_8,obj_8,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f7de483ee80,0,65536,64420,48,1512,184781,0,0,64,0x7fc02916ae80,0,131072,144,48,0,0,0,192,64,0x7fd39d668e80,25190401,22862816,1967137,360448,3464068,163840,0,0,9922,550,64,0x7f2836094e80,65536,64048,48,1440,32768,32768,0,64,0x7fcaf0230e80,386640,236679,16384,16384,16384,32768,49152,0,48329,48329,48329,0,64,0x7f7cff96ae80,65536,32768,0,0,0,16384,16384,393216,538,48520,64,0x7f5cc86cee80,49152,11534336,65536,0,0,0,16384,0,0,17178,64,0x7faf9f4f8e80,0,0,0,1048576,0,0,0,0,26608,64,0x7f39e9cf0e80,180224,114688,0,32768,32768,16384,16384,65536,913,46716,194303154953219,194303154977539 +1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f7de483ee80,0,65536,65536,0,0,189056,0,0,64,0x7fc02916ae80,0,131072,0,48,0,0,0,48,64,0x7fd39d668e80,24542210,23002282,1179480,360448,3326223,163840,0,0,8528,2446,64,0x7f2836094e80,65536,64048,48,1440,32768,32768,0,64,0x7fcaf0230e80,339080,229752,16384,16384,16384,32768,49152,0,42384,42384,42384,0,64,0x7f7cff96ae80,65536,32768,0,0,0,16384,16384,393216,458,42952,64,0x7f5cc86cee80,49152,11534336,65536,0,0,0,16384,0,0,13929,64,0x7faf9f4f8e80,0,0,0,1048576,0,0,0,0,26163,64,0x7f39e9cf0e80,180224,114688,0,32768,32768,16384,16384,65536,3403,39353,194303155101219,194303155120099 +2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f7de483ee80,0,65536,65536,0,0,188847,0,0,64,0x7fc02916ae80,0,131072,0,48,0,0,0,48,64,0x7fd39d668e80,24773562,22908769,1504345,360448,3353456,163840,0,0,8561,2448,64,0x7f2836094e80,65536,64048,48,1440,32768,32768,0,64,0x7fcaf0230e80,340424,229204,16384,16384,16384,32768,49152,0,42552,42552,42552,0,64,0x7f7cff96ae80,65536,32768,0,0,0,16384,16384,393216,458,42745,64,0x7f5cc86cee80,49152,11534336,65536,0,0,0,16384,0,0,13916,64,0x7faf9f4f8e80,0,0,0,1048576,0,0,0,0,26695,64,0x7f39e9cf0e80,180224,114688,0,32768,32768,16384,16384,65536,3197,39311,194303155144579,194303155163459 diff --git a/tests/workloads/ipblocks_SQ_CPC/MI100/sysinfo.csv b/tests/workloads/ipblocks_SQ_CPC/MI100/sysinfo.csv index db8f2b519c..d15e30ddd0 100644 --- a/tests/workloads/ipblocks_SQ_CPC/MI100/sysinfo.csv +++ b/tests/workloads/ipblocks_SQ_CPC/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -ipblocks_SQ_CPC,./tests/vcopy -n 1048576 -b 256 -i 3,sq|cpc,Fri Mar 1 16:46:34 2024 (CST),1,t006-003.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651240,,5.7.1-98,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +ipblocks_SQ_CPC,./tests/vcopy -n 1048576 -b 256 -i 3,sq|cpc,Thu 07 Mar 2024 01:09:21 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/ipblocks_SQ_CPC/MI100/timestamps.csv b/tests/workloads/ipblocks_SQ_CPC/MI100/timestamps.csv index f7f162c4f0..a74ac54706 100644 --- a/tests/workloads/ipblocks_SQ_CPC/MI100/timestamps.csv +++ b/tests/workloads/ipblocks_SQ_CPC/MI100/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,2875743,2875743,1048576,256,0,0,8,8,16,64,0x0,0x7f792f336e80,2187887112501909,2187887112527251,2187887112551091,2187887112564226 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,2875743,2875743,1048576,256,0,0,8,8,16,64,0x0,0x7f792f336e80,2187887112563545,2187887112653331,2187887112672531,2187887112673562 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,2875743,2875743,1048576,256,0,0,8,8,16,64,0x0,0x7f792f336e80,2187887112684622,2187887112694931,2187887112713811,2187887112714769 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,181828,181828,1048576,256,0,0,8,8,16,64,0x0,0x7faed23dce80,194303154921411,194303154953219,194303154977539,194303154991624 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,181828,181828,1048576,256,0,0,8,8,16,64,0x0,0x7faed23dce80,194303154992265,194303155101219,194303155120099,194303155121700 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,181828,181828,1048576,256,0,0,8,8,16,64,0x0,0x7faed23dce80,194303155133332,194303155144579,194303155163459,194303155164551 diff --git a/tests/workloads/ipblocks_SQ_CPC/MI200/SQ_IFETCH_LEVEL.csv b/tests/workloads/ipblocks_SQ_CPC/MI200/SQ_IFETCH_LEVEL.csv new file mode 100644 index 0000000000..ae6276d011 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_CPC/MI200/SQ_IFETCH_LEVEL.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,340095,340095,1048576,256,0,0,8,0,16,64,0x0,0x7fbfbed34ec0,27545,27545,16384,65536,13794,1537480,199346183656323,199354805603573,199354805623573,199346199519652 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,340095,340095,1048576,256,0,0,8,0,16,64,0x0,0x7fbfbed34ec0,39996,39996,16384,65536,9115,1048660,199346199542595,199354805693333,199354805709493,199346199799782 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,340095,340095,1048576,256,0,0,8,0,16,64,0x0,0x7fbfbed34ec0,40217,40217,16384,65536,9662,1048624,199346199830089,199354805729173,199354805744853,199346199968210 diff --git a/tests/workloads/ipblocks_SQ_CPC/MI200/SQ_INST_LEVEL_LDS.csv b/tests/workloads/ipblocks_SQ_CPC/MI200/SQ_INST_LEVEL_LDS.csv new file mode 100644 index 0000000000..c49f56e0fb --- /dev/null +++ b/tests/workloads/ipblocks_SQ_CPC/MI200/SQ_INST_LEVEL_LDS.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,340296,340296,1048576,256,0,0,8,0,16,64,0x0,0x7f2cae3d8ec0,0,0,0,199346665525434,199354805603573,199354805623573,199346681607207 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,340296,340296,1048576,256,0,0,8,0,16,64,0x0,0x7f2cae3d8ec0,0,0,0,199346681627014,199354805693333,199354805709493,199346681918365 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,340296,340296,1048576,256,0,0,8,0,16,64,0x0,0x7f2cae3d8ec0,0,0,0,199346681944725,199354805729173,199354805744853,199346682095040 diff --git a/tests/workloads/ipblocks_SQ_CPC/MI200/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/ipblocks_SQ_CPC/MI200/SQ_INST_LEVEL_SMEM.csv new file mode 100644 index 0000000000..809ba6c7f6 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_CPC/MI200/SQ_INST_LEVEL_SMEM.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,340481,340481,1048576,256,0,0,8,0,16,64,0x0,0x7f1759bd4ec0,65536,178848,20060256,199347149054236,199354805603573,199354805623573,199347165898721 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,340481,340481,1048576,256,0,0,8,0,16,64,0x0,0x7f1759bd4ec0,65536,240092,26751520,199347165915412,199354805693333,199354805709493,199347166219187 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,340481,340481,1048576,256,0,0,8,0,16,64,0x0,0x7f1759bd4ec0,65536,273970,30599728,199347166245417,199354805729173,199354805744853,199347166403686 diff --git a/tests/workloads/ipblocks_SQ_CPC/MI200/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/ipblocks_SQ_CPC/MI200/SQ_INST_LEVEL_VMEM.csv new file mode 100644 index 0000000000..7118877eb0 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_CPC/MI200/SQ_INST_LEVEL_VMEM.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,340665,340665,1048576,256,0,0,8,0,16,64,0x0,0x7ff7d7298ec0,32768,294077,32921148,199347626702343,199354805603573,199354805623573,199347642382786 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,340665,340665,1048576,256,0,0,8,0,16,64,0x0,0x7ff7d7298ec0,32768,588434,65913900,199347642400749,199354805693333,199354805709493,199347642690558 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,340665,340665,1048576,256,0,0,8,0,16,64,0x0,0x7ff7d7298ec0,32768,581140,65092960,199347642716938,199354805729173,199354805744853,199347642866701 diff --git a/tests/workloads/ipblocks_SQ_CPC/MI200/SQ_LEVEL_WAVES.csv b/tests/workloads/ipblocks_SQ_CPC/MI200/SQ_LEVEL_WAVES.csv new file mode 100644 index 0000000000..1dc2e3cc83 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_CPC/MI200/SQ_LEVEL_WAVES.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,340850,340850,1048576,256,0,0,8,0,16,64,0x0,0x7fb581614ec0,27751,27751,10948,222016,16384,11022828,130256,0,44587476,199348107548679,199354805603573,199354805623573,199348123449429 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,340850,340850,1048576,256,0,0,8,0,16,64,0x0,0x7fb581614ec0,41274,41274,14375,330200,16384,18889989,221826,0,76041052,199348123477242,199354805693333,199354805709493,199348123798940 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,340850,340850,1048576,256,0,0,8,0,16,64,0x0,0x7fb581614ec0,41644,41644,14220,333160,16384,19526078,223830,0,78584000,199348123833596,199354805729173,199354805744853,199348123999540 diff --git a/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/SQ_IFETCH_LEVEL.txt b/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/SQ_IFETCH_LEVEL.txt new file mode 100644 index 0000000000..293092f641 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/SQ_IFETCH_LEVEL.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/SQ_INST_LEVEL_LDS.txt b/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/SQ_INST_LEVEL_LDS.txt new file mode 100644 index 0000000000..08439eedce --- /dev/null +++ b/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/SQ_INST_LEVEL_LDS.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt b/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt new file mode 100644 index 0000000000..6cca322d4e --- /dev/null +++ b/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt b/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt new file mode 100644 index 0000000000..e527ad31ba --- /dev/null +++ b/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/SQ_LEVEL_WAVES.txt b/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/SQ_LEVEL_WAVES.txt new file mode 100644 index 0000000000..3f8e04adb3 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/SQ_LEVEL_WAVES.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_0.txt b/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_0.txt new file mode 100644 index 0000000000..45a3daf103 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_0.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_CVT SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU SQ_INSTS_VSKIPPED SQ_INSTS SQ_INSTS_VALU GRBM_COUNT GRBM_GUI_ACTIVE CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_1.txt b/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_1.txt new file mode 100644 index 0000000000..3eed6ed7c9 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_1.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_ADD_F16 SQ_INSTS_VALU_MUL_F16 SQ_INSTS_VALU_FMA_F16 SQ_INSTS_VALU_TRANS_F16 SQ_INSTS_VALU_ADD_F32 SQ_INSTS_VALU_MUL_F32 SQ_INSTS_VALU_FMA_F32 SQ_INSTS_VALU_TRANS_F32 CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_10.txt b/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_10.txt new file mode 100644 index 0000000000..7053d4dce6 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_10.txt @@ -0,0 +1,5 @@ +pmc: SQC_TC_DATA_WRITE_REQ SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_11.txt b/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_11.txt new file mode 100644 index 0000000000..77ae8b461f --- /dev/null +++ b/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_11.txt @@ -0,0 +1,5 @@ +pmc: SQC_ICACHE_MISSES_DUPLICATE SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_12.txt b/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_12.txt new file mode 100644 index 0000000000..dfb2cf65e5 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_12.txt @@ -0,0 +1,5 @@ +pmc: SQC_DCACHE_REQ_READ_1 SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_2.txt b/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_2.txt new file mode 100644 index 0000000000..adf1880635 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_2.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_ADD_F64 SQ_INSTS_VALU_MUL_F64 SQ_INSTS_VALU_FMA_F64 SQ_INSTS_VALU_TRANS_F64 SQ_INSTS_VALU_INT32 SQ_INSTS_VALU_INT64 SQ_INSTS_SMEM SQ_INSTS_FLAT CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_3.txt b/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_3.txt new file mode 100644 index 0000000000..fc22e552ae --- /dev/null +++ b/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_3.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG SQ_WAVE_CYCLES SQ_WAIT_ANY SQ_WAIT_INST_ANY CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_4.txt b/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_4.txt new file mode 100644 index 0000000000..637dd5dfc6 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_4.txt @@ -0,0 +1,5 @@ +pmc: SQ_ACTIVE_INST_ANY SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU SQ_ACTIVE_INST_SCA CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_5.txt b/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_5.txt new file mode 100644 index 0000000000..7272d68e44 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_5.txt @@ -0,0 +1,5 @@ +pmc: SQ_ACTIVE_INST_EXP_GDS SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU SQ_THREAD_CYCLES_VALU CPC_ME1_DC0_SPI_BUSY + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_6.txt b/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_6.txt new file mode 100644 index 0000000000..e6e2d40811 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_6.txt @@ -0,0 +1,5 @@ +pmc: SQ_IFETCH SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_7.txt b/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_7.txt new file mode 100644 index 0000000000..86671fadbb --- /dev/null +++ b/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_7.txt @@ -0,0 +1,5 @@ +pmc: SQ_WAVES_LT_32 SQ_WAVES_LT_16 SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_8.txt b/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_8.txt new file mode 100644 index 0000000000..f01548a76d --- /dev/null +++ b/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_8.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM_NORM SQ_INSTS_MFMA SQ_INSTS_VALU_MFMA_I8 SQ_INSTS_VALU_MFMA_F16 SQ_INSTS_VALU_MFMA_BF16 SQ_INSTS_VALU_MFMA_F32 SQ_INSTS_VALU_MFMA_F64 SQ_VALU_MFMA_BUSY_CYCLES + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_9.txt b/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_9.txt new file mode 100644 index 0000000000..e9663fc4a5 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_9.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_FLAT_LDS_ONLY SQ_INSTS_VALU_MFMA_MOPS_I8 SQ_INSTS_VALU_MFMA_MOPS_F16 SQ_INSTS_VALU_MFMA_MOPS_BF16 SQ_INSTS_VALU_MFMA_MOPS_F32 SQ_INSTS_VALU_MFMA_MOPS_F64 SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/timestamps.txt b/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/timestamps.txt new file mode 100644 index 0000000000..676cca1b80 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/timestamps.txt @@ -0,0 +1,5 @@ +pmc: + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_CPC/MI200/pmc_perf.csv b/tests/workloads/ipblocks_SQ_CPC/MI200/pmc_perf.csv new file mode 100644 index 0000000000..e3d61d14b5 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_CPC/MI200/pmc_perf.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,wave_size_1,obj_1,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_2,obj_2,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,wave_size_3,obj_3,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_4,obj_4,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,wave_size_5,obj_5,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,wave_size_6,obj_6,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,wave_size_7,obj_7,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_8,obj_8,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,wave_size_9,obj_9,SQ_ACTIVE_INST_ANY,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,wave_size_10,obj_10,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,CPC_ME1_DC0_SPI_BUSY,wave_size_11,obj_11,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,wave_size_12,obj_12,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f5c00d38ec0,0,0,1048576,0,0,0,0,0,64,0x7f969f5b8ec0,32768,32768,0,64,0x7f4f8e064ec0,65536,0,0,0,16384,16384,0,0,64,0x7f8b5522cec0,1309,118813,0,0,65536,63800,56,1680,64,0x7f01b1a78ec0,0,0,0,0,0,0,0,0,352,26713,64,0x7fd799508ec0,0,0,0,0,0,0,168,56,64,0x7f2fd4028ec0,0,0,0,0,114688,0,65536,32768,6975,545,64,0x7f92067f8ec0,0,0,0,224,0,65536,64281,56,64,0x7f07c3da4ec0,0,0,0,16384,16384,10962787,9750506,868217,819,27095,64,0x7f1dfa30cec0,344064,222320,129677,1638076,0,0,163840,114688,0,10897,64,0x7f2afe650ec0,0,32768,32768,16384,16384,65536,49152,10485760,14976,64,0x7fe928480ec0,131072,0,0,0,0,0,0,0,64,0x7f2dd787cec0,0,16384,16384,32768,49152,0,393216,163840,28084,28084,28084,0,199354805603573,199354805623573 +1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f5c00d38ec0,0,0,1048576,0,0,0,0,0,64,0x7f969f5b8ec0,32768,32768,0,64,0x7f4f8e064ec0,65536,0,0,0,16384,16384,0,0,64,0x7f8b5522cec0,0,184208,0,0,65536,63800,56,1680,64,0x7f01b1a78ec0,0,0,0,0,0,0,0,0,302,40076,64,0x7fd799508ec0,0,0,0,0,0,0,0,56,64,0x7f2fd4028ec0,0,0,0,0,114688,0,65536,32768,9493,3123,64,0x7f92067f8ec0,0,0,0,56,0,65536,65536,0,64,0x7f07c3da4ec0,0,0,0,16384,16384,20187209,18709486,1133659,3400,39163,64,0x7f1dfa30cec0,344064,335088,226311,2849726,0,0,163840,114688,0,13257,64,0x7f2afe650ec0,0,32768,32768,16384,16384,65536,49152,10485760,25389,64,0x7fe928480ec0,131072,0,0,0,0,0,0,0,64,0x7f2dd787cec0,0,16384,16384,32768,49152,0,393216,163840,43103,43103,43103,0,199354805693333,199354805709493 +2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f5c00d38ec0,0,0,1048576,0,0,0,0,0,64,0x7f969f5b8ec0,32768,32768,0,64,0x7f4f8e064ec0,65536,0,0,0,16384,16384,0,0,64,0x7f8b5522cec0,0,186988,0,0,65536,63800,56,1680,64,0x7f01b1a78ec0,0,0,0,0,0,0,0,0,302,40301,64,0x7fd799508ec0,0,0,0,0,0,0,0,56,64,0x7f2fd4028ec0,0,0,0,0,114688,0,65536,32768,9501,3093,64,0x7f92067f8ec0,0,0,0,56,0,65536,65536,0,64,0x7f07c3da4ec0,0,0,0,16384,16384,19566197,18340038,882095,3396,38395,64,0x7f1dfa30cec0,344064,329504,221551,2765990,0,0,163840,114688,0,13935,64,0x7f2afe650ec0,0,32768,32768,16384,16384,65536,49152,10485760,25246,64,0x7fe928480ec0,131072,0,0,0,0,0,0,0,64,0x7f2dd787cec0,0,16384,16384,32768,49152,0,393216,163840,43655,43655,43655,0,199354805729173,199354805744853 diff --git a/tests/workloads/ipblocks_SQ_CPC/MI200/roofline.csv b/tests/workloads/ipblocks_SQ_CPC/MI200/roofline.csv new file mode 100644 index 0000000000..6eee7a1e9c --- /dev/null +++ b/tests/workloads/ipblocks_SQ_CPC/MI200/roofline.csv @@ -0,0 +1,5 @@ +device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh +0,1388.4314,1387.9395,1388.9233,5015.6025,5012.6465,5018.5586,9222.3379,9221.7363,9222.9395,18050.59,18049.518,18051.662,20929.807,20867.709,20991.904,20262.221,20261.627,20262.814,170387.2,170383.38,170391.03,164851.75,164847.52,164855.98,41416.543,41415.984,41417.102,41473.898,41473.359,41474.438,166320.42,165829.55,166811.3 +1,1389.0236,1388.483,1389.5641,5027.7773,5025.6187,5029.936,9233.9785,9233.334,9234.623,18091.418,18088.111,18094.725,20974.865,20908.154,21041.576,20295.217,20294.699,20295.734,170844.5,170840.8,170848.2,165102.59,165099.59,165105.59,41483.016,41482.293,41483.738,41542.473,41541.531,41543.414,166885.02,166882.05,166887.98 +2,1389.0247,1388.4352,1389.6141,5037.124,5034.7544,5039.4937,9263.2285,9262.3828,9264.0742,18109.248,18108.34,18110.156,21052.637,21052.268,21053.006,20357.676,20357.145,20358.207,171147.55,171144.06,171151.03,165545,165541.28,165548.72,41594.102,41593.266,41594.938,41649.09,41648.023,41650.156,167005.12,166409.08,167601.17 +3,1389.4426,1388.9342,1389.951,5033.2988,5031.9365,5034.6611,9242.4365,9241.75,9243.123,18030.496,18027.463,18033.529,21037.92,21037.492,21038.348,20317.32,20316.609,20318.031,171048.77,171045.73,171051.8,165249.95,165246.5,165253.41,41449.465,41294.613,41604.316,41588.441,41587.867,41589.016,167047.19,167045.06,167049.31 diff --git a/tests/workloads/ipblocks_SQ_CPC/MI200/sysinfo.csv b/tests/workloads/ipblocks_SQ_CPC/MI200/sysinfo.csv new file mode 100644 index 0000000000..af00d1fd25 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_CPC/MI200/sysinfo.csv @@ -0,0 +1,2 @@ +workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd +ipblocks_SQ_CPC,./sample/vcopy -n 1048576 -b 256 -i 3,sq|cpc|roofline,Thu 07 Mar 2024 02:33:33 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/ipblocks_SQ_CPC/MI200/timestamps.csv b/tests/workloads/ipblocks_SQ_CPC/MI200/timestamps.csv new file mode 100644 index 0000000000..6164bfea33 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_CPC/MI200/timestamps.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,343486,343486,1048576,256,0,0,8,0,16,64,0x0,0x7f55a444cec0,199354805579822,199354805603573,199354805623573,199354805635117 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,343486,343486,1048576,256,0,0,8,0,16,64,0x0,0x7f55a444cec0,199354805634415,199354805693333,199354805709493,199354805710539 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,343486,343486,1048576,256,0,0,8,0,16,64,0x0,0x7f55a444cec0,199354805720829,199354805729173,199354805744853,199354805745776 diff --git a/tests/workloads/ipblocks_SQ_SPI/MI100/SQ_IFETCH_LEVEL.csv b/tests/workloads/ipblocks_SQ_SPI/MI100/SQ_IFETCH_LEVEL.csv index 4b722defeb..fefe68ca0a 100644 --- a/tests/workloads/ipblocks_SQ_SPI/MI100/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/ipblocks_SQ_SPI/MI100/SQ_IFETCH_LEVEL.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2832494,2832494,1048576,256,0,0,8,8,16,64,0x0,0x7f62372a2e80,48243,48243,16384,65536,12897,1651108,2187759213113020,2187761447977782,2187761448002422,2187759220736902 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2832494,2832494,1048576,256,0,0,8,8,16,64,0x0,0x7f62372a2e80,42543,42543,16384,65536,8489,1048588,2187759220759334,2187761448100342,2187761448119222,2187759221209459 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2832494,2832494,1048576,256,0,0,8,8,16,64,0x0,0x7f62372a2e80,43015,43015,16384,65536,8041,1048584,2187759221241799,2187761448139702,2187761448158742,2187759221424693 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,134626,134626,1048576,256,0,0,8,8,16,64,0x0,0x7f7f2ff9ae80,48131,48131,16384,65536,12910,1645524,194154641852352,194161603172864,194161603197984,194154649704009 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,134626,134626,1048576,256,0,0,8,8,16,64,0x0,0x7f7f2ff9ae80,42906,42906,16384,65536,8228,1048580,194154649726401,194161603299102,194161603318622,194154650043171 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,134626,134626,1048576,256,0,0,8,8,16,64,0x0,0x7f7f2ff9ae80,42538,42538,16384,65536,8309,1048580,194154650085221,194161603339422,194161603358782,194154650269850 diff --git a/tests/workloads/ipblocks_SQ_SPI/MI100/SQ_INST_LEVEL_LDS.csv b/tests/workloads/ipblocks_SQ_SPI/MI100/SQ_INST_LEVEL_LDS.csv index 1012c3ac8f..1d04feffad 100644 --- a/tests/workloads/ipblocks_SQ_SPI/MI100/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/ipblocks_SQ_SPI/MI100/SQ_INST_LEVEL_LDS.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2831943,2831943,1048576,256,0,0,8,8,16,64,0x0,0x7f5f2630ee80,0,0,0,2187757861912073,2187761447977782,2187761448002422,2187757870028409 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2831943,2831943,1048576,256,0,0,8,8,16,64,0x0,0x7f5f2630ee80,0,0,0,2187757870047064,2187761448100342,2187761448119222,2187757870374499 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2831943,2831943,1048576,256,0,0,8,8,16,64,0x0,0x7f5f2630ee80,0,0,0,2187757870403864,2187761448139702,2187761448158742,2187757870576618 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,134813,134813,1048576,256,0,0,8,8,16,64,0x0,0x7f05c5dcce80,0,0,0,194155149233598,194161603172864,194161603197984,194155156840731 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,134813,134813,1048576,256,0,0,8,8,16,64,0x0,0x7f05c5dcce80,0,0,0,194155156859918,194161603299102,194161603318622,194155157181146 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,134813,134813,1048576,256,0,0,8,8,16,64,0x0,0x7f05c5dcce80,0,0,0,194155157209219,194161603339422,194161603358782,194155157389641 diff --git a/tests/workloads/ipblocks_SQ_SPI/MI100/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/ipblocks_SQ_SPI/MI100/SQ_INST_LEVEL_SMEM.csv index 0b1927d37c..f32d70fb64 100644 --- a/tests/workloads/ipblocks_SQ_SPI/MI100/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/ipblocks_SQ_SPI/MI100/SQ_INST_LEVEL_SMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2831397,2831397,1048576,256,0,0,8,8,16,64,0x0,0x7ff785bc4e80,65536,227374,29155080,2187756514075472,2187761447977782,2187761448002422,2187756521596079 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2831397,2831397,1048576,256,0,0,8,8,16,64,0x0,0x7ff785bc4e80,65536,178876,22973048,2187756521615336,2187761448100342,2187761448119222,2187756521929135 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2831397,2831397,1048576,256,0,0,8,8,16,64,0x0,0x7ff785bc4e80,65536,184648,23609216,2187756521958500,2187761448139702,2187761448158742,2187756522137696 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,135010,135010,1048576,256,0,0,8,8,16,64,0x0,0x7f8d722cee80,65536,186144,23831152,194155648390291,194161603172864,194161603197984,194155656189689 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,135010,135010,1048576,256,0,0,8,8,16,64,0x0,0x7f8d722cee80,65536,162520,20755640,194155656209657,194161603299102,194161603318622,194155656532107 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,135010,135010,1048576,256,0,0,8,8,16,64,0x0,0x7f8d722cee80,65536,165198,21102216,194155656561563,194161603339422,194161603358782,194155656745271 diff --git a/tests/workloads/ipblocks_SQ_SPI/MI100/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/ipblocks_SQ_SPI/MI100/SQ_INST_LEVEL_VMEM.csv index 9dcc5631b2..156c7a6aa7 100644 --- a/tests/workloads/ipblocks_SQ_SPI/MI100/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/ipblocks_SQ_SPI/MI100/SQ_INST_LEVEL_VMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2832858,2832858,1048576,256,0,0,8,8,16,64,0x0,0x7f6c3a2f6e80,32768,633722,81113028,2187760106002126,2187761447977782,2187761448002422,2187760113453684 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2832858,2832858,1048576,256,0,0,8,8,16,64,0x0,0x7f6c3a2f6e80,32768,638062,81675456,2187760113471919,2187761448100342,2187761448119222,2187760113782872 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2832858,2832858,1048576,256,0,0,8,8,16,64,0x0,0x7f6c3a2f6e80,32768,637852,81649080,2187760113812037,2187761448139702,2187761448158742,2187760113994910 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,135197,135197,1048576,256,0,0,8,8,16,64,0x0,0x7f29c5cd8e80,32768,668934,85616252,194156148107576,194161603172864,194161603197984,194156155682769 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,135197,135197,1048576,256,0,0,8,8,16,64,0x0,0x7f29c5cd8e80,32768,674790,86381088,194156155699641,194161603299102,194161603318622,194156156015058 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,135197,135197,1048576,256,0,0,8,8,16,64,0x0,0x7f29c5cd8e80,32768,665462,85191512,194156156043151,194161603339422,194161603358782,194156156215438 diff --git a/tests/workloads/ipblocks_SQ_SPI/MI100/SQ_LEVEL_WAVES.csv b/tests/workloads/ipblocks_SQ_SPI/MI100/SQ_LEVEL_WAVES.csv index c98ed578b9..aaaf6b9cf1 100644 --- a/tests/workloads/ipblocks_SQ_SPI/MI100/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/ipblocks_SQ_SPI/MI100/SQ_LEVEL_WAVES.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2831579,2831579,1048576,256,0,0,8,8,16,64,0x0,0x7f8711a16e80,48134,48134,18156,385080,16384,25232694,231731,0,101422472,2187756959638279,2187761447977782,2187761448002422,2187756967344075 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2831579,2831579,1048576,256,0,0,8,8,16,64,0x0,0x7f8711a16e80,41549,41549,12851,332400,16384,24655918,228768,0,99120360,2187756967371727,2187761448100342,2187761448119222,2187756967698420 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2831579,2831579,1048576,256,0,0,8,8,16,64,0x0,0x7f8711a16e80,42093,42093,13254,336752,16384,24737209,231584,0,99441668,2187756967736983,2187761448139702,2187761448158742,2187756967919816 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,135386,135386,1048576,256,0,0,8,8,16,64,0x0,0x7f6c8e1bae80,48123,48123,17292,384992,16384,25142758,233752,0,101056832,194156649274716,194161603172864,194161603197984,194156657125771 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,135386,135386,1048576,256,0,0,8,8,16,64,0x0,0x7f6c8e1bae80,42746,42746,13457,341976,16384,25281138,232746,0,101615784,194156657156529,194161603299102,194161603318622,194156657462328 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,135386,135386,1048576,256,0,0,8,8,16,64,0x0,0x7f6c8e1bae80,42114,42114,13671,336920,16384,23618044,225682,0,94966952,194156657500110,194161603339422,194161603358782,194156657688617 diff --git a/tests/workloads/ipblocks_SQ_SPI/MI100/pmc_dispatch_info.csv b/tests/workloads/ipblocks_SQ_SPI/MI100/pmc_dispatch_info.csv new file mode 100644 index 0000000000..17300ae9af --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI/MI100/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) ",2 +1,"vecCopy(double*, double*, double*, int, int) ",2 +2,"vecCopy(double*, double*, double*, int, int) ",2 diff --git a/tests/workloads/ipblocks_SQ_SPI/MI100/pmc_perf.csv b/tests/workloads/ipblocks_SQ_SPI/MI100/pmc_perf.csv index 2bfcfb7ac4..f3eaae786e 100644 --- a/tests/workloads/ipblocks_SQ_SPI/MI100/pmc_perf.csv +++ b/tests/workloads/ipblocks_SQ_SPI/MI100/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,wave_size_1,obj_1,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,GRBM_SPI_BUSY,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,wave_size_2,obj_2,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,wave_size_3,obj_3,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,wave_size_4,obj_4,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,wave_size_5,obj_5,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,wave_size_6,obj_6,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,wave_size_7,obj_7,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,GRBM_COUNT,GRBM_GUI_ACTIVE,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,wave_size_8,obj_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fa2103a6e80,0,65536,64391,48,1497,192943,0,0,0,81920,64,0x7f430ddece80,65536,32768,0,0,0,16384,16384,393216,31585,4096,16384,64,0x7fede21a2e80,25229679,21724755,3144476,360448,3493834,163840,0,0,12949,29333,64,0x7f61f3754e80,0,0,0,1048576,0,0,0,0,0,0,64,0x7f59e033ae80,180224,114688,0,32768,32768,16384,16384,65536,0,0,64,0x7f05728a6e80,49152,11534336,65536,0,0,0,16384,0,0,0,64,0x7f44ff8a0e80,0,131072,144,48,0,0,0,192,0,0,64,0x7f5f88bdce80,388920,240086,16384,16384,16384,32768,49152,0,48614,48614,387207,250014,64,0x7f8c261ece80,65536,64048,48,1440,32768,32768,0,16384,0,2187761447977782,2187761448002422 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fa2103a6e80,0,65536,65536,0,0,191587,0,0,0,81920,64,0x7f430ddece80,65536,32768,0,0,0,16384,16384,393216,30644,4096,16384,64,0x7fede21a2e80,24015717,21450671,2204598,360448,3356936,163840,0,0,11134,27518,64,0x7f61f3754e80,0,0,0,1048576,0,0,0,0,0,0,64,0x7f59e033ae80,180224,114688,0,32768,32768,16384,16384,65536,0,0,64,0x7f05728a6e80,49152,11534336,65536,0,0,0,16384,0,0,0,64,0x7f44ff8a0e80,0,131072,0,48,0,0,0,48,0,0,64,0x7f5f88bdce80,347136,232950,16384,16384,16384,32768,49152,0,43391,43391,347128,242717,64,0x7f8c261ece80,65536,64048,48,1440,32768,32768,0,16384,0,2187761448100342,2187761448119222 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fa2103a6e80,0,65536,65536,0,0,169423,0,0,0,81920,64,0x7f430ddece80,65536,32768,0,0,0,16384,16384,393216,31546,4096,16384,64,0x7fede21a2e80,23967997,20854288,2753261,360448,3361755,163840,0,0,12302,28686,64,0x7f61f3754e80,0,0,0,1048576,0,0,0,0,0,0,64,0x7f59e033ae80,180224,114688,0,32768,32768,16384,16384,65536,0,0,64,0x7f05728a6e80,49152,11534336,65536,0,0,0,16384,0,0,0,64,0x7f44ff8a0e80,0,131072,0,48,0,0,0,48,0,0,64,0x7f5f88bdce80,340640,225223,16384,16384,16384,32768,49152,0,42579,42579,340632,235011,64,0x7f8c261ece80,65536,64048,48,1440,32768,32768,0,16384,0,2187761448139702,2187761448158742 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,wave_size_1,obj_1,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,wave_size_2,obj_2,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,GRBM_COUNT,GRBM_GUI_ACTIVE,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,wave_size_3,obj_3,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,GRBM_SPI_BUSY,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,wave_size_4,obj_4,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,wave_size_5,obj_5,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,wave_size_6,obj_6,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,wave_size_7,obj_7,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,wave_size_8,obj_8,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f5923544e80,0,0,0,1048576,0,0,0,0,0,0,64,0x7fa935b38e80,49152,11534336,65536,0,0,0,16384,0,0,0,64,0x7f7859e02e80,395368,236097,16384,16384,16384,32768,49152,0,49420,49420,393655,246030,64,0x7feaa9ba2e80,65536,32768,0,0,0,16384,16384,393216,31452,4096,16384,64,0x7fb995e02e80,0,131072,144,48,0,0,0,192,0,0,64,0x7f4f2c506e80,24520468,22424805,1735215,360448,3334469,163840,0,0,13494,29878,64,0x7fec1cb22e80,0,65536,64442,48,1376,187995,0,0,0,81920,64,0x7f8560958e80,65536,64048,48,1440,32768,32768,0,16384,0,64,0x7fe5b7f64e80,180224,114688,0,32768,32768,16384,16384,65536,0,0,194161603172864,194161603197984 +1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f5923544e80,0,0,0,1048576,0,0,0,0,0,0,64,0x7fa935b38e80,49152,11534336,65536,0,0,0,16384,0,0,0,64,0x7f7859e02e80,353216,233714,16384,16384,16384,32768,49152,0,44151,44151,353208,243493,64,0x7feaa9ba2e80,65536,32768,0,0,0,16384,16384,393216,31284,4096,16384,64,0x7fb995e02e80,0,131072,0,48,0,0,0,48,0,0,64,0x7f4f2c506e80,24356495,22744903,1251144,360448,3325659,163840,0,0,14177,30561,64,0x7fec1cb22e80,0,65536,65536,0,0,185875,0,0,0,81920,64,0x7f8560958e80,65536,64048,48,1440,32768,32768,0,16384,0,64,0x7fe5b7f64e80,180224,114688,0,32768,32768,16384,16384,65536,0,0,194161603299102,194161603318622 +2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f5923544e80,0,0,0,1048576,0,0,0,0,0,0,64,0x7fa935b38e80,49152,11534336,65536,0,0,0,16384,0,0,0,64,0x7f7859e02e80,349696,229854,16384,16384,16384,32768,49152,0,43711,43711,349688,239631,64,0x7feaa9ba2e80,65536,32768,0,0,0,16384,16384,393216,30778,4096,16384,64,0x7fb995e02e80,0,131072,0,48,0,0,0,48,0,0,64,0x7f4f2c506e80,24572646,23048526,1163672,360448,3374138,163840,0,0,14639,31023,64,0x7fec1cb22e80,0,65536,65536,0,0,190076,0,0,0,81920,64,0x7f8560958e80,65536,64048,48,1440,32768,32768,0,16384,0,64,0x7fe5b7f64e80,180224,114688,0,32768,32768,16384,16384,65536,0,0,194161603339422,194161603358782 diff --git a/tests/workloads/ipblocks_SQ_SPI/MI100/sysinfo.csv b/tests/workloads/ipblocks_SQ_SPI/MI100/sysinfo.csv index 34caf5480b..0a350019fc 100644 --- a/tests/workloads/ipblocks_SQ_SPI/MI100/sysinfo.csv +++ b/tests/workloads/ipblocks_SQ_SPI/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -ipblocks_SQ_SPI,./tests/vcopy -n 1048576 -b 256 -i 3,sq|spi,Fri Mar 1 16:44:25 2024 (CST),1,t006-003.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651240,,5.7.1-98,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +ipblocks_SQ_SPI,./tests/vcopy -n 1048576 -b 256 -i 3,sq|spi,Thu 07 Mar 2024 01:06:59 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/ipblocks_SQ_SPI/MI100/timestamps.csv b/tests/workloads/ipblocks_SQ_SPI/MI100/timestamps.csv index ca88a1e262..3c296667c3 100644 --- a/tests/workloads/ipblocks_SQ_SPI/MI100/timestamps.csv +++ b/tests/workloads/ipblocks_SQ_SPI/MI100/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,2833404,2833404,1048576,256,0,0,8,8,16,64,0x0,0x7f88f5972e80,2187761447951145,2187761447977782,2187761448002422,2187761448016247 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,2833404,2833404,1048576,256,0,0,8,8,16,64,0x0,0x7f88f5972e80,2187761448014835,2187761448100342,2187761448119222,2187761448120373 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,2833404,2833404,1048576,256,0,0,8,8,16,64,0x0,0x7f88f5972e80,2187761448130962,2187761448139702,2187761448158742,2187761448159626 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,137249,137249,1048576,256,0,0,8,8,16,64,0x0,0x7ff2ac8b6e80,194161603144802,194161603172864,194161603197984,194161603211438 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,137249,137249,1048576,256,0,0,8,8,16,64,0x0,0x7ff2ac8b6e80,194161603210616,194161603299102,194161603318622,194161603319783 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,137249,137249,1048576,256,0,0,8,8,16,64,0x0,0x7ff2ac8b6e80,194161603330663,194161603339422,194161603358782,194161603359678 diff --git a/tests/workloads/ipblocks_SQ_SPI/MI200/SQ_IFETCH_LEVEL.csv b/tests/workloads/ipblocks_SQ_SPI/MI200/SQ_IFETCH_LEVEL.csv new file mode 100644 index 0000000000..f9e3462d8c --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI/MI200/SQ_IFETCH_LEVEL.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,287510,287510,1048576,256,0,0,8,0,16,64,0x0,0x7f0f3f26cec0,27747,27747,16384,65536,13573,1533656,198159671186521,198168314115755,198168314136235,198159687476718 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,287510,287510,1048576,256,0,0,8,0,16,64,0x0,0x7f0f3f26cec0,40947,40947,16384,65536,9537,1048636,198159687497668,198168314155755,198168314170955,198159687804268 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,287510,287510,1048576,256,0,0,8,0,16,64,0x0,0x7f0f3f26cec0,40747,40747,16384,65536,9442,1048632,198159687833403,198168314242315,198168314259115,198159687995650 diff --git a/tests/workloads/ipblocks_SQ_SPI/MI200/SQ_INST_LEVEL_LDS.csv b/tests/workloads/ipblocks_SQ_SPI/MI200/SQ_INST_LEVEL_LDS.csv new file mode 100644 index 0000000000..3ccec59a01 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI/MI200/SQ_INST_LEVEL_LDS.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,287694,287694,1048576,256,0,0,8,0,16,64,0x0,0x7ff9fd7e8ec0,0,0,0,198160151120061,198168314115755,198168314136235,198160166914551 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,287694,287694,1048576,256,0,0,8,0,16,64,0x0,0x7ff9fd7e8ec0,0,0,0,198160166933878,198168314155755,198168314170955,198160167213346 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,287694,287694,1048576,256,0,0,8,0,16,64,0x0,0x7ff9fd7e8ec0,0,0,0,198160167239686,198168314242315,198168314259115,198160167399539 diff --git a/tests/workloads/ipblocks_SQ_SPI/MI200/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/ipblocks_SQ_SPI/MI200/SQ_INST_LEVEL_SMEM.csv new file mode 100644 index 0000000000..4f90c02c78 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI/MI200/SQ_INST_LEVEL_SMEM.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,287895,287895,1048576,256,0,0,8,0,16,64,0x0,0x7f0ebd7a4ec0,65536,171962,19168800,198160631067549,198168314115755,198168314136235,198160647001192 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,287895,287895,1048576,256,0,0,8,0,16,64,0x0,0x7f0ebd7a4ec0,65536,228224,25515656,198160647021250,198168314155755,198168314170955,198160647358648 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,287895,287895,1048576,256,0,0,8,0,16,64,0x0,0x7f0ebd7a4ec0,65536,226978,25364048,198160647386110,198168314242315,198168314259115,198160647554188 diff --git a/tests/workloads/ipblocks_SQ_SPI/MI200/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/ipblocks_SQ_SPI/MI200/SQ_INST_LEVEL_VMEM.csv new file mode 100644 index 0000000000..0dde5094a2 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI/MI200/SQ_INST_LEVEL_VMEM.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,288099,288099,1048576,256,0,0,8,0,16,64,0x0,0x7f9821224ec0,32768,287176,32152116,198161107879535,198168314115755,198168314136235,198161123985894 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,288099,288099,1048576,256,0,0,8,0,16,64,0x0,0x7f9821224ec0,32768,578942,64844504,198161124004279,198168314155755,198168314170955,198161124322030 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,288099,288099,1048576,256,0,0,8,0,16,64,0x0,0x7f9821224ec0,32768,580926,65072092,198161124347368,198168314242315,198168314259115,198161124505938 diff --git a/tests/workloads/ipblocks_SQ_SPI/MI200/SQ_LEVEL_WAVES.csv b/tests/workloads/ipblocks_SQ_SPI/MI200/SQ_LEVEL_WAVES.csv new file mode 100644 index 0000000000..51ea5d84ee --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI/MI200/SQ_LEVEL_WAVES.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,288284,288284,1048576,256,0,0,8,0,16,64,0x0,0x7f65cd2a4ec0,27442,27442,10817,219544,16384,10743312,127984,0,43470904,198161591136943,198168314115755,198168314136235,198161606839219 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,288284,288284,1048576,256,0,0,8,0,16,64,0x0,0x7f65cd2a4ec0,41459,41459,13582,331680,16384,19631876,222003,0,79003076,198161606865017,198168314155755,198168314170955,198161607196715 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,288284,288284,1048576,256,0,0,8,0,16,64,0x0,0x7f65cd2a4ec0,41888,41888,13699,335112,16384,19466021,225878,0,78363356,198161607231401,198168314242315,198168314259115,198161607403847 diff --git a/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/SQ_IFETCH_LEVEL.txt b/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/SQ_IFETCH_LEVEL.txt new file mode 100644 index 0000000000..293092f641 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/SQ_IFETCH_LEVEL.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/SQ_INST_LEVEL_LDS.txt b/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/SQ_INST_LEVEL_LDS.txt new file mode 100644 index 0000000000..08439eedce --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/SQ_INST_LEVEL_LDS.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt b/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt new file mode 100644 index 0000000000..6cca322d4e --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt b/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt new file mode 100644 index 0000000000..e527ad31ba --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/SQ_LEVEL_WAVES.txt b/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/SQ_LEVEL_WAVES.txt new file mode 100644 index 0000000000..3f8e04adb3 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/SQ_LEVEL_WAVES.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_0.txt b/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_0.txt new file mode 100644 index 0000000000..25b3939875 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_0.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_CVT SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU SQ_INSTS_VSKIPPED SQ_INSTS SQ_INSTS_VALU GRBM_COUNT GRBM_GUI_ACTIVE SPI_CSN_WINDOW_VALID SPI_CSN_BUSY + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_1.txt b/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_1.txt new file mode 100644 index 0000000000..406a4234a6 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_1.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_ADD_F16 SQ_INSTS_VALU_MUL_F16 SQ_INSTS_VALU_FMA_F16 SQ_INSTS_VALU_TRANS_F16 SQ_INSTS_VALU_ADD_F32 SQ_INSTS_VALU_MUL_F32 SQ_INSTS_VALU_FMA_F32 SQ_INSTS_VALU_TRANS_F32 GRBM_SPI_BUSY SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_10.txt b/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_10.txt new file mode 100644 index 0000000000..7053d4dce6 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_10.txt @@ -0,0 +1,5 @@ +pmc: SQC_TC_DATA_WRITE_REQ SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_11.txt b/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_11.txt new file mode 100644 index 0000000000..77ae8b461f --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_11.txt @@ -0,0 +1,5 @@ +pmc: SQC_ICACHE_MISSES_DUPLICATE SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_12.txt b/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_12.txt new file mode 100644 index 0000000000..dfb2cf65e5 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_12.txt @@ -0,0 +1,5 @@ +pmc: SQC_DCACHE_REQ_READ_1 SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_2.txt b/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_2.txt new file mode 100644 index 0000000000..971524626e --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_2.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_ADD_F64 SQ_INSTS_VALU_MUL_F64 SQ_INSTS_VALU_FMA_F64 SQ_INSTS_VALU_TRANS_F64 SQ_INSTS_VALU_INT32 SQ_INSTS_VALU_INT64 SQ_INSTS_SMEM SQ_INSTS_FLAT SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_3.txt b/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_3.txt new file mode 100644 index 0000000000..59067067dc --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_3.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG SQ_WAVE_CYCLES SQ_WAIT_ANY SQ_WAIT_INST_ANY SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_4.txt b/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_4.txt new file mode 100644 index 0000000000..2c49ab07dd --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_4.txt @@ -0,0 +1,5 @@ +pmc: SQ_ACTIVE_INST_ANY SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU SQ_ACTIVE_INST_SCA SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_5.txt b/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_5.txt new file mode 100644 index 0000000000..9e42b0b86c --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_5.txt @@ -0,0 +1,5 @@ +pmc: SQ_ACTIVE_INST_EXP_GDS SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU SQ_THREAD_CYCLES_VALU SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_6.txt b/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_6.txt new file mode 100644 index 0000000000..5c9a93c55d --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_6.txt @@ -0,0 +1,5 @@ +pmc: SQ_IFETCH SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_7.txt b/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_7.txt new file mode 100644 index 0000000000..30c806c977 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_7.txt @@ -0,0 +1,5 @@ +pmc: SQ_WAVES_LT_32 SQ_WAVES_LT_16 SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_8.txt b/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_8.txt new file mode 100644 index 0000000000..9e33272f73 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_8.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM_NORM SQ_INSTS_MFMA SQ_INSTS_VALU_MFMA_I8 SQ_INSTS_VALU_MFMA_F16 SQ_INSTS_VALU_MFMA_BF16 SQ_INSTS_VALU_MFMA_F32 SQ_INSTS_VALU_MFMA_F64 SQ_VALU_MFMA_BUSY_CYCLES SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_9.txt b/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_9.txt new file mode 100644 index 0000000000..e9663fc4a5 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_9.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_FLAT_LDS_ONLY SQ_INSTS_VALU_MFMA_MOPS_I8 SQ_INSTS_VALU_MFMA_MOPS_F16 SQ_INSTS_VALU_MFMA_MOPS_BF16 SQ_INSTS_VALU_MFMA_MOPS_F32 SQ_INSTS_VALU_MFMA_MOPS_F64 SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/timestamps.txt b/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/timestamps.txt new file mode 100644 index 0000000000..676cca1b80 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/timestamps.txt @@ -0,0 +1,5 @@ +pmc: + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SPI/MI200/pmc_perf.csv b/tests/workloads/ipblocks_SQ_SPI/MI200/pmc_perf.csv new file mode 100644 index 0000000000..df5b2b20c7 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI/MI200/pmc_perf.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_ACTIVE_INST_ANY,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,wave_size_1,obj_1,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,wave_size_2,obj_2,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,wave_size_3,obj_3,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_4,obj_4,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,GRBM_SPI_BUSY,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,wave_size_5,obj_5,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,GRBM_COUNT,GRBM_GUI_ACTIVE,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,wave_size_6,obj_6,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_7,obj_7,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,wave_size_8,obj_8,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,wave_size_9,obj_9,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_10,obj_10,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,wave_size_11,obj_11,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,wave_size_12,obj_12,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f91da168ec0,344064,224752,132874,1676287,0,0,163840,114688,540944,0,64,0x7f3fab4e8ec0,0,0,0,16384,16384,10977714,9695634,938016,10605,0,64,0x7f42d5018ec0,0,0,0,0,114688,0,65536,32768,12144,18590,64,0x7ff0e2e18ec0,1907,119011,0,0,65536,63800,56,1680,64,0x7f13f57d8ec0,0,0,0,0,0,0,0,0,17743,4096,16384,64,0x7f2613534ec0,0,16384,16384,32768,49152,0,393216,163840,27557,27557,218753,135290,64,0x7effe6794ec0,32768,32768,0,64,0x7f74fae7cec0,65536,0,0,0,16384,16384,0,0,0,0,64,0x7fc7e3068ec0,131072,0,0,0,0,0,0,0,16384,0,64,0x7f974543cec0,0,0,0,224,0,65536,63530,56,64,0x7f935d93cec0,0,0,0,0,0,0,168,56,64,0x7f8e9dbc4ec0,0,0,1048576,0,0,0,0,0,0,32768,64,0x7f5fc9a24ec0,0,32768,32768,16384,16384,65536,49152,10485760,0,0,198168314115755,198168314136235 +1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f91da168ec0,344064,336800,228544,2865927,0,0,163840,114688,1086607,0,64,0x7f3fab4e8ec0,0,0,0,16384,16384,20446740,18834238,1268438,22328,0,64,0x7f42d5018ec0,0,0,0,0,114688,0,65536,32768,30760,27082,64,0x7ff0e2e18ec0,0,186318,0,0,65536,63800,56,1680,64,0x7f13f57d8ec0,0,0,0,0,0,0,0,0,29393,4096,16384,64,0x7f2613534ec0,0,16384,16384,32768,49152,0,393216,163840,41015,41015,328120,229183,64,0x7effe6794ec0,32768,32768,0,64,0x7f74fae7cec0,65536,0,0,0,16384,16384,0,0,0,0,64,0x7fc7e3068ec0,131072,0,0,0,0,0,0,0,16384,0,64,0x7f974543cec0,0,0,0,56,0,65536,65536,0,64,0x7f935d93cec0,0,0,0,0,0,0,0,56,64,0x7f8e9dbc4ec0,0,0,1048576,0,0,0,0,0,0,32768,64,0x7f5fc9a24ec0,0,32768,32768,16384,16384,65536,49152,10485760,0,0,198168314155755,198168314170955 +2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f91da168ec0,344064,339920,229468,2874232,0,0,163840,114688,1058378,0,64,0x7f3fab4e8ec0,0,0,0,16384,16384,19365443,18057527,963852,20373,0,64,0x7f42d5018ec0,0,0,0,0,114688,0,65536,32768,31008,27817,64,0x7ff0e2e18ec0,0,185450,0,0,65536,63800,56,1680,64,0x7f13f57d8ec0,0,0,0,0,0,0,0,0,31289,4096,16384,64,0x7f2613534ec0,0,16384,16384,32768,49152,0,393216,163840,41675,41675,333400,232571,64,0x7effe6794ec0,32768,32768,0,64,0x7f74fae7cec0,65536,0,0,0,16384,16384,0,0,0,0,64,0x7fc7e3068ec0,131072,0,0,0,0,0,0,0,16384,0,64,0x7f974543cec0,0,0,0,56,0,65536,65536,0,64,0x7f935d93cec0,0,0,0,0,0,0,0,56,64,0x7f8e9dbc4ec0,0,0,1048576,0,0,0,0,0,0,32768,64,0x7f5fc9a24ec0,0,32768,32768,16384,16384,65536,49152,10485760,0,0,198168314242315,198168314259115 diff --git a/tests/workloads/ipblocks_SQ_SPI/MI200/roofline.csv b/tests/workloads/ipblocks_SQ_SPI/MI200/roofline.csv new file mode 100644 index 0000000000..603442600d --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI/MI200/roofline.csv @@ -0,0 +1,5 @@ +device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh +0,1389.2981,1388.6581,1389.9381,5016.5327,5013.4414,5019.624,9223.5947,9222.998,9224.1914,18050.371,18049.385,18051.357,20933.727,20873.285,20994.168,20264.689,20264.02,20265.359,170412.19,170406.34,170418.03,164847.23,164841.38,164853.09,41415.691,41415.066,41416.316,41473.828,41473.082,41474.574,166301.5,165803.25,166799.75 +1,1389.3405,1388.8101,1389.8708,5027.9414,5025.811,5030.0718,9235.7158,9235.0078,9236.4238,18095.494,18091.707,18099.281,20976.84,20909.99,21043.689,20299.086,20298.502,20299.67,170871.09,170867.22,170874.97,165139.88,165133.42,165146.33,41490.809,41489.973,41491.645,41554.738,41553.953,41555.523,166900.34,166896.47,166904.22 +2,1388.2317,1387.6322,1388.8312,5036.1846,5033.8223,5038.5469,9262.5654,9261.708,9263.4229,18105.012,18104.068,18105.955,21048.953,21048.598,21049.309,20354.756,20354.223,20355.289,171126.64,171123.47,171129.81,165513.05,165509.33,165516.77,41587.539,41586.488,41588.59,41648.672,41647.238,41650.105,166971.38,166380.41,167562.34 +3,1388.9213,1388.332,1389.5105,5032.4907,5031.2202,5033.7612,9241.041,9240.5186,9241.5635,18023.152,18019.688,18026.617,21033.707,21033.018,21034.396,20314.184,20313.395,20314.973,171044.81,171041.44,171048.19,165239.59,165235.86,165243.33,41442.719,41288.254,41597.184,41582.965,41582.488,41583.441,167032.02,167030.33,167033.7 diff --git a/tests/workloads/ipblocks_SQ_SPI/MI200/sysinfo.csv b/tests/workloads/ipblocks_SQ_SPI/MI200/sysinfo.csv new file mode 100644 index 0000000000..4b91da03b4 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI/MI200/sysinfo.csv @@ -0,0 +1,2 @@ +workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd +ipblocks_SQ_SPI,./sample/vcopy -n 1048576 -b 256 -i 3,sq|spi|roofline,Thu 07 Mar 2024 02:13:46 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/ipblocks_SQ_SPI/MI200/timestamps.csv b/tests/workloads/ipblocks_SQ_SPI/MI200/timestamps.csv new file mode 100644 index 0000000000..2e8c320f58 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI/MI200/timestamps.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,290916,290916,1048576,256,0,0,8,0,16,64,0x0,0x7fca90930ec0,198168314092247,198168314115755,198168314136235,198168314161749 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,290916,290916,1048576,256,0,0,8,0,16,64,0x0,0x7fca90930ec0,198168314147683,198168314155755,198168314170955,198168314239666 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,290916,290916,1048576,256,0,0,8,0,16,64,0x0,0x7fca90930ec0,198168314181466,198168314242315,198168314259115,198168314261067 diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/SQ_IFETCH_LEVEL.csv b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/SQ_IFETCH_LEVEL.csv index dd3ab8d85c..d2c95ab678 100644 --- a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/SQ_IFETCH_LEVEL.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2813260,2813260,1048576,256,0,0,8,8,16,64,0x0,0x7f59cc1a0e80,48363,48363,16384,65536,13056,1654968,2187703771435626,2187704213628199,2187704213652359,2187703778923242 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2813260,2813260,1048576,256,0,0,8,8,16,64,0x0,0x7f59cc1a0e80,42935,42935,16384,65536,8145,1048600,2187703778947107,2187704213728679,2187704213794279,2187703779364200 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2813260,2813260,1048576,256,0,0,8,8,16,64,0x0,0x7f59cc1a0e80,43495,43495,16384,65536,8009,1048576,2187703779396590,2187704213814919,2187704213833639,2187703779581678 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,114804,114804,1048576,256,0,0,8,8,16,64,0x0,0x7f2225ccee80,47612,47612,16384,65536,14038,1815892,194094975442809,194102861062915,194102861087395,194094983210487 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,114804,114804,1048576,256,0,0,8,8,16,64,0x0,0x7f2225ccee80,41618,41618,16384,65536,8188,1048580,194094983232428,194102861176995,194102861195875,194094983556031 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,114804,114804,1048576,256,0,0,8,8,16,64,0x0,0x7f2225ccee80,42058,42058,16384,65536,8308,1048608,194094983588442,194102861217315,194102861236515,194094983753735 diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/SQ_INST_LEVEL_LDS.csv b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/SQ_INST_LEVEL_LDS.csv index 1e090a644c..c4aee2e07a 100644 --- a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/SQ_INST_LEVEL_LDS.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2813988,2813988,1048576,256,0,0,8,8,16,64,0x0,0x7fa54366ae80,0,0,0,2187705554639465,2187704213628199,2187704213652359,2187705562156286 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2813988,2813988,1048576,256,0,0,8,8,16,64,0x0,0x7fa54366ae80,0,0,0,2187705562174490,2187704213728679,2187704213794279,2187705562605590 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2813988,2813988,1048576,256,0,0,8,8,16,64,0x0,0x7fa54366ae80,0,0,0,2187705562634204,2187704213814919,2187704213833639,2187705562808160 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,115016,115016,1048576,256,0,0,8,8,16,64,0x0,0x7f2b54f20e80,0,0,0,194095472713822,194102861062915,194102861087395,194095480325935 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,115016,115016,1048576,256,0,0,8,8,16,64,0x0,0x7f2b54f20e80,0,0,0,194095480345362,194102861176995,194102861195875,194095480648586 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,115016,115016,1048576,256,0,0,8,8,16,64,0x0,0x7f2b54f20e80,0,0,0,194095480676559,194102861217315,194102861236515,194095480846561 diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/SQ_INST_LEVEL_SMEM.csv index 78b9ea4d7b..e001bba91b 100644 --- a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/SQ_INST_LEVEL_SMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2811985,2811985,1048576,256,0,0,8,8,16,64,0x0,0x7f4a75da6e80,65536,208842,26733592,2187700631294390,2187704213628199,2187704213652359,2187700638791034 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2811985,2811985,1048576,256,0,0,8,8,16,64,0x0,0x7f4a75da6e80,65536,197408,25251248,2187700638810019,2187704213728679,2187704213794279,2187700639134298 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2811985,2811985,1048576,256,0,0,8,8,16,64,0x0,0x7f4a75da6e80,65536,195354,25035608,2187700639163242,2187704213814919,2187704213833639,2187700639324725 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,115205,115205,1048576,256,0,0,8,8,16,64,0x0,0x7ff93663ae80,65536,217060,27703096,194095962342495,194102861062915,194102861087395,194095970358883 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,115205,115205,1048576,256,0,0,8,8,16,64,0x0,0x7ff93663ae80,65536,154114,19694896,194095970377949,194102861176995,194102861195875,194095970678538 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,115205,115205,1048576,256,0,0,8,8,16,64,0x0,0x7ff93663ae80,65536,186826,23911120,194095970706852,194102861217315,194102861236515,194095970877345 diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/SQ_INST_LEVEL_VMEM.csv index f3712b86ef..0112fe9dc1 100644 --- a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/SQ_INST_LEVEL_VMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2812713,2812713,1048576,256,0,0,8,8,16,64,0x0,0x7ffa790c0e80,32768,607297,77747872,2187702429209426,2187704213628199,2187704213652359,2187702436697463 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2812713,2812713,1048576,256,0,0,8,8,16,64,0x0,0x7ffa790c0e80,32768,655474,83878632,2187702436717521,2187704213728679,2187704213794279,2187702437030940 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2812713,2812713,1048576,256,0,0,8,8,16,64,0x0,0x7ffa790c0e80,32768,664403,85035728,2187702437059673,2187704213814919,2187704213833639,2187702437287521 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,115396,115396,1048576,256,0,0,8,8,16,64,0x0,0x7fbf9e40ee80,32768,656989,84067744,194096454708641,194102861062915,194102861087395,194096464884598 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,115396,115396,1048576,256,0,0,8,8,16,64,0x0,0x7fbf9e40ee80,32768,672665,86091356,194096464502735,194102861176995,194102861195875,194096466421498 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,115396,115396,1048576,256,0,0,8,8,16,64,0x0,0x7fbf9e40ee80,32768,665343,85156924,194096464629004,194102861217315,194102861236515,194096464887523 diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/SQ_LEVEL_WAVES.csv b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/SQ_LEVEL_WAVES.csv index 07c084c065..67b62b38e1 100644 --- a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/SQ_LEVEL_WAVES.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2813624,2813624,1048576,256,0,0,8,8,16,64,0x0,0x7fd3195fce80,48291,48291,18202,386336,16384,25594201,233896,0,102864884,2187704653896826,2187704213628199,2187704213652359,2187704661607271 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2813624,2813624,1048576,256,0,0,8,8,16,64,0x0,0x7fd3195fce80,43567,43567,14086,348544,16384,25169856,235904,0,101172088,2187704661636245,2187704213728679,2187704213794279,2187704661986372 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2813624,2813624,1048576,256,0,0,8,8,16,64,0x0,0x7fd3195fce80,43391,43391,13834,347136,16384,25319736,234709,0,101761908,2187704662025776,2187704213814919,2187704213833639,2187704662221193 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,115585,115585,1048576,256,0,0,8,8,16,64,0x0,0x7f9f8bd2ae80,48998,48998,17076,391992,16384,25118597,240543,0,100974952,194096951203704,194102861062915,194102861087395,194096958897582 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,115585,115585,1048576,256,0,0,8,8,16,64,0x0,0x7f9f8bd2ae80,42877,42877,13400,343024,16384,25037316,231371,0,100640244,194096958926386,194102861176995,194102861195875,194096959282872 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,115585,115585,1048576,256,0,0,8,8,16,64,0x0,0x7f9f8bd2ae80,43653,43653,13953,349232,16384,25264572,235861,0,101535948,194096959321014,194102861217315,194102861236515,194096959513127 diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/perfmon/pmc_perf_0.txt b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/perfmon/pmc_perf_0.txt index 314291a651..3abb17cfef 100644 --- a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/perfmon/pmc_perf_0.txt +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/perfmon/pmc_perf_0.txt @@ -1,4 +1,4 @@ -pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM GRBM_COUNT GRBM_GUI_ACTIVE TA_TA_BUSY_sum TA_BUFFER_WAVEFRONTS_sum SPI_CSN_WINDOW_VALID SPI_CSN_BUSY CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum +pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES SQ_BUSY_CU_CYCLES SQ_WAVE_CYCLES SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM GRBM_COUNT GRBM_GUI_ACTIVE TA_TA_BUSY_sum TA_BUFFER_WAVEFRONTS_sum SPI_CSN_WINDOW_VALID SPI_CSN_BUSY CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum gpu: range: diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/pmc_dispatch_info.csv b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/pmc_dispatch_info.csv new file mode 100644 index 0000000000..17300ae9af --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) ",2 +1,"vecCopy(double*, double*, double*, int, int) ",2 +2,"vecCopy(double*, double*, double*, int, int) ",2 diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/pmc_perf.csv b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/pmc_perf.csv index c8c9159baf..5720ad4f34 100644 --- a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/pmc_perf.csv +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_1,obj_1,TCC_EA_ATOMIC_LEVEL_sum,wave_size_2,obj_2,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_3,obj_3,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_4,obj_4,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_5,obj_5,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_6,obj_6,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_7,obj_7,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,GRBM_SPI_BUSY,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_8,obj_8,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,GRBM_COUNT,GRBM_GUI_ACTIVE,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_9,obj_9,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_10,obj_10,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f9f8e6dee80,49152,11534336,65536,0,0,0,16384,0,858292.0,32768.0,0,0,131072.0,131072.0,0.0,131072.0,64,0x7f51bd354e80,0.0,64,0x7f7791dc8e80,16384,393216,22761923,2037673,360448,163840,0,0,0.0,0.0,11640,28024,0,46964,262600.0,0.0,188.0,262412.0,64,0x7f68b621ae80,0,0,0,1048576,0,0,0,0,0.0,583748.0,0,0,81278.0,0.0,0.0,81278.0,64,0x7f6cc4abce80,0.0,0.0,123601900.0,57970794.0,64,0x7f851a3dce80,0,131072,144,48,0,0,0,192,32768.0,16384.0,0,0,131412.0,0.0,672.0,131411.0,64,0x7f8dc1c18e80,180224,114688,0,32768,32768,16384,16384,65536,0.0,0.0,0,0,0,131529.0,131072.0,0.0,131104.0,64,0x7f21da004e80,49152,0,65536,32768,0,0,0,16384,31572,0.0,0.0,4096,16384,1710,0,48.0,265.0,0.0,262288.0,64,0x7fae5833ae80,383048,230333,3377126,16384,24941627,16384,16384,32768,47880,47880,2095970.0,0.0,381335,240288,47880,0,1532160.0,958177.0,0.0,0.0,64,0x7fc36b564e80,0,65536,64521,48,1334,124911,0,0,16384.0,0.0,0,81920,0.0,0.0,45680.0,111759.0,64,0x7f7765cace80,65536,64048,48,1440,32768,32768,0,16384,0,86604.0,44468.0,131111.0,0.0,2187704213628199,2187704213652359 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f9f8e6dee80,49152,11534336,65536,0,0,0,16384,0,861313.0,32768.0,0,0,86641.0,86641.0,0.0,86641.0,64,0x7f51bd354e80,0.0,64,0x7f7791dc8e80,16384,393216,23200491,1485999,360448,163840,0,0,0.0,0.0,14385,30769,0,41764,262461.0,0.0,47.0,262414.0,64,0x7f68b621ae80,0,0,0,1048576,0,0,0,0,0.0,613558.0,0,0,63068.0,0.0,0.0,63068.0,64,0x7f6cc4abce80,0.0,0.0,132506086.0,46444556.0,64,0x7f851a3dce80,0,131072,0,48,0,0,0,48,32768.0,16384.0,0,0,131415.0,0.0,684.0,131414.0,64,0x7f8dc1c18e80,180224,114688,0,32768,32768,16384,16384,65536,0.0,0.0,0,0,0,131391.0,131072.0,0.0,86603.0,64,0x7f21da004e80,49152,0,65536,32768,0,0,0,16384,30780,0.0,0.0,4096,16384,1736,0,48.0,274.0,0.0,262144.0,64,0x7fae5833ae80,350736,238917,3487788,16384,24999090,16384,16384,32768,43841,43841,2041192.0,0.0,350728,248691,43841,0,1402912.0,826971.0,0.0,0.0,64,0x7fc36b564e80,0,65536,65536,0,0,189624,0,0,16384.0,0.0,0,81920,0.0,0.0,58151.0,121912.0,64,0x7f7765cace80,65536,64048,48,1440,32768,32768,0,16384,0,86517.0,0.0,131112.0,0.0,2187704213728679,2187704213794279 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f9f8e6dee80,49152,11534336,65536,0,0,0,16384,0,848424.0,32768.0,0,0,86428.0,86428.0,0.0,86428.0,64,0x7f51bd354e80,0.0,64,0x7f7791dc8e80,16384,393216,23166769,1811758,360448,163840,0,0,0.0,0.0,13421,29805,0,41348,262461.0,0.0,47.0,262414.0,64,0x7f68b621ae80,0,0,0,1048576,0,0,0,0,0.0,582360.0,0,0,70670.0,0.0,0.0,70670.0,64,0x7f6cc4abce80,0.0,0.0,115119321.0,44348226.0,64,0x7f851a3dce80,0,131072,0,48,0,0,0,48,32768.0,16384.0,0,0,131415.0,0.0,684.0,131414.0,64,0x7f8dc1c18e80,180224,114688,0,32768,32768,16384,16384,65536,0.0,0.0,0,0,0,131389.0,131072.0,0.0,86661.0,64,0x7f21da004e80,49152,0,65536,32768,0,0,0,16384,32186,0.0,0.0,4096,16384,1727,0,48.0,281.0,0.0,262144.0,64,0x7fae5833ae80,337392,228021,3317631,16384,23797459,16384,16384,32768,42173,42173,2088259.0,0.0,337384,237821,42173,0,1349536.0,798487.0,0.0,0.0,64,0x7fc36b564e80,0,65536,65536,0,0,188881,0,0,16384.0,0.0,0,81920,0.0,0.0,55846.0,124943.0,64,0x7f7765cace80,65536,64048,48,1440,32768,32768,0,16384,0,86418.0,0.0,131112.0,0.0,2187704213814919,2187704213833639 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_1,obj_1,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_2,obj_2,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,GRBM_SPI_BUSY,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_3,obj_3,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_BUSY_CU_CYCLES,SQ_WAVE_CYCLES,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,GRBM_COUNT,GRBM_GUI_ACTIVE,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_4,obj_4,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_5,obj_5,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_6,obj_6,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_7,obj_7,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_8,obj_8,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_9,obj_9,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_10,obj_10,TCC_EA_ATOMIC_LEVEL_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fb2865aae80,16384,393216,22200776,1784152,360448,163840,0,0,0.0,0.0,10568,26952,0,46139,262599.0,0.0,188.0,262411.0,64,0x7f1040c5ee80,0,131072,144,48,0,0,0,192,32768.0,16384.0,0,0,131432.0,0.0,712.0,131431.0,64,0x7f444f876e80,49152,0,65536,32768,0,0,0,16384,32609,0.0,0.0,4096,16384,1734,0,48.0,275.0,0.0,262288.0,64,0x7f65e7486e80,377376,229487,16384,3356073,24168392,16384,16384,32768,47171,47171,2112502.0,0.0,375663,239438,47171,0,1509472.0,968203.0,0.0,0.0,64,0x7f54eaa56e80,49152,11534336,65536,0,0,0,16384,0,989401.0,32768.0,0,0,131072.0,131072.0,0.0,131072.0,64,0x7fa3d4626e80,65536,64048,48,1440,32768,32768,0,16384,0,86490.0,44582.0,131111.0,0.0,64,0x7f6c4e3cae80,0.0,0.0,117210790.0,58805693.0,64,0x7efff43bae80,180224,114688,0,32768,32768,16384,16384,65536,0.0,0.0,0,0,0,131527.0,131072.0,0.0,131104.0,64,0x7fed748cce80,0,65536,64448,48,1331,186472,0,0,16384.0,0.0,0,81920,0.0,0.0,52176.0,115093.0,64,0x7f122a504e80,0,0,0,1048576,0,0,0,0,0.0,754560.0,0,0,109899.0,0.0,0.0,109899.0,64,0x7fefe395ae80,0.0,194102861062915,194102861087395 +1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fb2865aae80,16384,393216,22419225,1797965,360448,163840,0,0,0.0,0.0,12398,28782,0,41377,262543.0,0.0,47.0,262496.0,64,0x7f1040c5ee80,0,131072,0,48,0,0,0,48,32768.0,16384.0,0,0,131425.0,0.0,704.0,131424.0,64,0x7f444f876e80,49152,0,65536,32768,0,0,0,16384,30644,0.0,0.0,4096,16384,1752,0,48.0,239.0,0.0,262144.0,64,0x7f65e7486e80,339744,226057,16384,3281399,23894728,16384,16384,32768,42467,42467,2103992.0,0.0,339736,235841,42467,0,1358944.0,808999.0,0.0,0.0,64,0x7f54eaa56e80,49152,11534336,65536,0,0,0,16384,0,1111960.0,32768.0,0,0,86787.0,86787.0,0.0,86787.0,64,0x7fa3d4626e80,65536,64048,48,1440,32768,32768,0,16384,0,86453.0,0.0,131112.0,0.0,64,0x7f6c4e3cae80,0.0,0.0,116595345.0,46381801.0,64,0x7efff43bae80,180224,114688,0,32768,32768,16384,16384,65536,0.0,0.0,0,0,0,131435.0,131072.0,0.0,86619.0,64,0x7fed748cce80,0,65536,65536,0,0,184717,0,0,16384.0,0.0,0,81920,0.0,0.0,50787.0,121609.0,64,0x7f122a504e80,0,0,0,1048576,0,0,0,0,0.0,673275.0,0,0,71820.0,0.0,0.0,71820.0,64,0x7fefe395ae80,0.0,194102861176995,194102861195875 +2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fb2865aae80,16384,393216,22225569,1344615,360448,163840,0,0,0.0,0.0,11428,27812,0,40916,262515.0,0.0,47.0,262468.0,64,0x7f1040c5ee80,0,131072,0,48,0,0,0,48,32768.0,16384.0,0,0,131416.0,0.0,686.0,131415.0,64,0x7f444f876e80,49152,0,65536,32768,0,0,0,16384,30772,0.0,0.0,4096,16384,1746,0,48.0,226.0,0.0,262144.0,64,0x7f65e7486e80,339920,226305,16384,3282794,24119530,16384,16384,32768,42489,42489,2109274.0,0.0,339912,236097,42489,0,1359648.0,804899.0,0.0,0.0,64,0x7f54eaa56e80,49152,11534336,65536,0,0,0,16384,0,910482.0,32768.0,0,0,86377.0,86377.0,0.0,86377.0,64,0x7fa3d4626e80,65536,64048,48,1440,32768,32768,0,16384,0,86405.0,0.0,131112.0,0.0,64,0x7f6c4e3cae80,0.0,0.0,125024782.0,46812143.0,64,0x7efff43bae80,180224,114688,0,32768,32768,16384,16384,65536,0.0,0.0,0,0,0,131472.0,131072.0,0.0,86713.0,64,0x7fed748cce80,0,65536,65536,0,0,187107,0,0,16384.0,0.0,0,81920,0.0,0.0,65660.0,137400.0,64,0x7f122a504e80,0,0,0,1048576,0,0,0,0,0.0,698067.0,0,0,114936.0,0.0,0.0,114936.0,64,0x7fefe395ae80,0.0,194102861217315,194102861236515 diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/sysinfo.csv b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/sysinfo.csv index ac77cf1214..70c030dc44 100644 --- a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/sysinfo.csv +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -ipblocks_SQ_SPI_TA_TCC_CPF,./tests/vcopy -n 1048576 -b 256 -i 3,sq|spi|ta|tcc|cpf,Fri Mar 1 16:43:30 2024 (CST),1,t006-003.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651240,,5.7.1-98,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +ipblocks_SQ_SPI_TA_TCC_CPF,./tests/vcopy -n 1048576 -b 256 -i 3,sq|spi|ta|tcc|cpf,Thu 07 Mar 2024 01:05:59 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/timestamps.csv b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/timestamps.csv index 7820b3300e..af4e05ae68 100644 --- a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/timestamps.csv +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,2813442,2813442,1048576,256,0,0,8,8,16,64,0x0,0x7f6b4ead2e80,2187704213603420,2187704213628199,2187704213652359,2187704213662922 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,2813442,2813442,1048576,256,0,0,8,8,16,64,0x0,0x7f6b4ead2e80,2187704213664876,2187704213728679,2187704213794279,2187704213795211 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,2813442,2813442,1048576,256,0,0,8,8,16,64,0x0,0x7f6b4ead2e80,2187704213806351,2187704213814919,2187704213833639,2187704213834534 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,117917,117917,1048576,256,0,0,8,8,16,64,0x0,0x7f5421004e80,194102861037891,194102861062915,194102861087395,194102861100219 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,117917,117917,1048576,256,0,0,8,8,16,64,0x0,0x7f5421004e80,194102861100209,194102861176995,194102861195875,194102861196962 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,117917,117917,1048576,256,0,0,8,8,16,64,0x0,0x7f5421004e80,194102861208575,194102861217315,194102861236515,194102861237539 diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/SQ_IFETCH_LEVEL.csv b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/SQ_IFETCH_LEVEL.csv new file mode 100644 index 0000000000..6d08223946 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/SQ_IFETCH_LEVEL.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,264901,264901,1048576,256,0,0,8,0,16,64,0x0,0x7f68fb114ec0,27991,27991,16384,65536,13987,1573028,197729653263752,197738340012541,197738340033181,197729668961669 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,264901,264901,1048576,256,0,0,8,0,16,64,0x0,0x7f68fb114ec0,40318,40318,16384,65536,8950,1048712,197729668981958,197738340125821,197738340142461,197729669313745 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,264901,264901,1048576,256,0,0,8,0,16,64,0x0,0x7f68fb114ec0,40963,40963,16384,65536,9263,1048628,197729669343392,197738340160861,197738340176861,197729669511239 diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/SQ_INST_LEVEL_LDS.csv b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/SQ_INST_LEVEL_LDS.csv new file mode 100644 index 0000000000..8762467a6e --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/SQ_INST_LEVEL_LDS.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,265102,265102,1048576,256,0,0,8,0,16,64,0x0,0x7f8645a54ec0,0,0,0,197730137973074,197738340012541,197738340033181,197730153856552 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,265102,265102,1048576,256,0,0,8,0,16,64,0x0,0x7f8645a54ec0,0,0,0,197730153873514,197738340125821,197738340142461,197730154179894 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,265102,265102,1048576,256,0,0,8,0,16,64,0x0,0x7f8645a54ec0,0,0,0,197730154205703,197738340160861,197738340176861,197730154365595 diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/SQ_INST_LEVEL_SMEM.csv new file mode 100644 index 0000000000..3ec0290360 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/SQ_INST_LEVEL_SMEM.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,265303,265303,1048576,256,0,0,8,0,16,64,0x0,0x7f1a876d0ec0,65536,198076,22038840,197730616407645,197738340012541,197738340033181,197730632452178 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,265303,265303,1048576,256,0,0,8,0,16,64,0x0,0x7f1a876d0ec0,65536,254952,28605296,197730632472366,197738340125821,197738340142461,197730632706750 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,265303,265303,1048576,256,0,0,8,0,16,64,0x0,0x7f1a876d0ec0,65536,255292,28543104,197730632733601,197738340160861,197738340176861,197730632865109 diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/SQ_INST_LEVEL_VMEM.csv new file mode 100644 index 0000000000..58b602b1b9 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/SQ_INST_LEVEL_VMEM.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,265506,265506,1048576,256,0,0,8,0,16,64,0x0,0x7f651c14cec0,32768,299920,33591524,197731094150167,197738340012541,197738340033181,197731109995744 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,265506,265506,1048576,256,0,0,8,0,16,64,0x0,0x7f651c14cec0,32768,580241,64987892,197731110013077,197738340125821,197738340142461,197731110326710 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,265506,265506,1048576,256,0,0,8,0,16,64,0x0,0x7f651c14cec0,32768,569729,63814316,197731110352609,197738340160861,197738340176861,197731110507672 diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/SQ_LEVEL_WAVES.csv b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/SQ_LEVEL_WAVES.csv new file mode 100644 index 0000000000..e03729ad67 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/SQ_LEVEL_WAVES.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,265690,265690,1048576,256,0,0,8,0,16,64,0x0,0x7f00f8b24ec0,27542,27542,10902,220344,16384,10616210,128610,0,42968660,197731581001963,197738340012541,197738340033181,197731596878277 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,265690,265690,1048576,256,0,0,8,0,16,64,0x0,0x7f00f8b24ec0,41116,41116,13786,328936,16384,18935434,220606,0,76241532,197731596909767,197738340125821,197738340142461,197731597137267 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,265690,265690,1048576,256,0,0,8,0,16,64,0x0,0x7f00f8b24ec0,40838,40838,13793,326712,16384,19028590,218114,0,76587924,197731597169007,197738340160861,197738340176861,197731597315545 diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/SQ_IFETCH_LEVEL.txt b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/SQ_IFETCH_LEVEL.txt new file mode 100644 index 0000000000..293092f641 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/SQ_IFETCH_LEVEL.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/SQ_INST_LEVEL_LDS.txt b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/SQ_INST_LEVEL_LDS.txt new file mode 100644 index 0000000000..08439eedce --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/SQ_INST_LEVEL_LDS.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt new file mode 100644 index 0000000000..6cca322d4e --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt new file mode 100644 index 0000000000..e527ad31ba --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/SQ_LEVEL_WAVES.txt b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/SQ_LEVEL_WAVES.txt new file mode 100644 index 0000000000..3f8e04adb3 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/SQ_LEVEL_WAVES.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_0.txt b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_0.txt new file mode 100644 index 0000000000..2c06cac804 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_0.txt @@ -0,0 +1,5 @@ +pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES SQ_INSTS_VALU_CVT SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU GRBM_COUNT GRBM_GUI_ACTIVE TA_TA_BUSY_sum TA_BUFFER_WAVEFRONTS_sum SPI_CSN_WINDOW_VALID SPI_CSN_BUSY CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_1.txt b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_1.txt new file mode 100644 index 0000000000..9ebd7b0cfe --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_1.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VSKIPPED SQ_INSTS SQ_INSTS_VALU SQ_INSTS_VALU_ADD_F16 SQ_INSTS_VALU_MUL_F16 SQ_INSTS_VALU_FMA_F16 SQ_INSTS_VALU_TRANS_F16 SQ_INSTS_VALU_ADD_F32 GRBM_SPI_BUSY TA_BUFFER_READ_WAVEFRONTS_sum TA_BUFFER_WRITE_WAVEFRONTS_sum SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_10.txt b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_10.txt new file mode 100644 index 0000000000..7053d4dce6 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_10.txt @@ -0,0 +1,5 @@ +pmc: SQC_TC_DATA_WRITE_REQ SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_11.txt b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_11.txt new file mode 100644 index 0000000000..77ae8b461f --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_11.txt @@ -0,0 +1,5 @@ +pmc: SQC_ICACHE_MISSES_DUPLICATE SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_12.txt b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_12.txt new file mode 100644 index 0000000000..dfb2cf65e5 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_12.txt @@ -0,0 +1,5 @@ +pmc: SQC_DCACHE_REQ_READ_1 SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_2.txt b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_2.txt new file mode 100644 index 0000000000..1ced726d33 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_2.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_MUL_F32 SQ_INSTS_VALU_FMA_F32 SQ_INSTS_VALU_TRANS_F32 SQ_INSTS_VALU_ADD_F64 SQ_INSTS_VALU_MUL_F64 SQ_INSTS_VALU_FMA_F64 SQ_INSTS_VALU_TRANS_F64 SQ_INSTS_VALU_INT32 TA_BUFFER_ATOMIC_WAVEFRONTS_sum TA_BUFFER_TOTAL_CYCLES_sum SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_3.txt b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_3.txt new file mode 100644 index 0000000000..5839191d40 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_3.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_INT64 SQ_INSTS_SMEM SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN CPF_CMP_UTCL1_STALL_ON_TRANSLATION TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_4.txt b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_4.txt new file mode 100644 index 0000000000..47eeb6cb8a --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_4.txt @@ -0,0 +1,5 @@ +pmc: SQ_WAVE_CYCLES SQ_WAIT_ANY SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_BUSY_CU_CYCLES SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN TCC_EA_WRREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WR_UNCACHED_32B_sum TCC_EA_WRREQ_DRAM_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_5.txt b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_5.txt new file mode 100644 index 0000000000..dafbae8010 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_5.txt @@ -0,0 +1,5 @@ +pmc: SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN TCC_EA_WRREQ_STALL_sum TCC_EA_RDREQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RD_UNCACHED_32B_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_6.txt b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_6.txt new file mode 100644 index 0000000000..b0a6be7dec --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_6.txt @@ -0,0 +1,5 @@ +pmc: SQ_THREAD_CYCLES_VALU SQ_IFETCH SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN TCC_EA_RDREQ_DRAM_sum TCC_TAG_STALL_sum TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_7.txt b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_7.txt new file mode 100644 index 0000000000..ea8ad6729d --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_7.txt @@ -0,0 +1,5 @@ +pmc: SQ_WAVES_LT_32 SQ_WAVES_LT_16 SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR TCC_NORMAL_EVICT_sum TCC_ALL_TC_OP_INV_EVICT_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA_ATOMIC_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_8.txt b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_8.txt new file mode 100644 index 0000000000..4876448069 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_8.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM_NORM SQ_INSTS_MFMA SQ_INSTS_VALU_MFMA_I8 SQ_INSTS_VALU_MFMA_F16 SQ_INSTS_VALU_MFMA_BF16 SQ_INSTS_VALU_MFMA_F32 SQ_INSTS_VALU_MFMA_F64 SQ_VALU_MFMA_BUSY_CYCLES SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN TCC_EA_RDREQ_LEVEL_sum TCC_EA_WRREQ_LEVEL_sum TCC_EA_ATOMIC_LEVEL_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_9.txt b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_9.txt new file mode 100644 index 0000000000..e9663fc4a5 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_9.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_FLAT_LDS_ONLY SQ_INSTS_VALU_MFMA_MOPS_I8 SQ_INSTS_VALU_MFMA_MOPS_F16 SQ_INSTS_VALU_MFMA_MOPS_BF16 SQ_INSTS_VALU_MFMA_MOPS_F32 SQ_INSTS_VALU_MFMA_MOPS_F64 SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/timestamps.txt b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/timestamps.txt new file mode 100644 index 0000000000..676cca1b80 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/timestamps.txt @@ -0,0 +1,5 @@ +pmc: + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/pmc_perf.csv b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/pmc_perf.csv new file mode 100644 index 0000000000..f612280d07 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/pmc_perf.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_DRAM_sum,TCC_TAG_STALL_sum,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,wave_size_1,obj_1,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,TCC_EA_ATOMIC_LEVEL_sum,wave_size_2,obj_2,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,GRBM_SPI_BUSY,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_3,obj_3,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_4,obj_4,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_5,obj_5,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,TCC_EA_WRREQ_STALL_sum,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,wave_size_6,obj_6,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_7,obj_7,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_8,obj_8,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,wave_size_9,obj_9,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_10,obj_10,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_11,obj_11,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,wave_size_12,obj_12,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f1f91fa8ec0,10485760,65536,0,0,0,16384,0,0,32768.0,16384.0,0,0,131081.0,34724.0,46249.0,19287.0,64,0x7f79ec6c0ec0,131072,0,0,0,0,0,0,0,16384,0,39490065.0,35717872.0,0.0,64,0x7fd989278ec0,0,393216,163840,0,0,0,0,0,18078,0.0,0.0,4096,16384,1344,0,56.0,6.0,0.0,204330.0,64,0x7faf24d0cec0,1742,117297,0,0,65536,63800,56,1680,64,0x7f6a58f3cec0,218520,126960,16384,0,16384,16384,32768,49152,27314,27314,1052955.0,0.0,216809,135082,27314,0,874048.0,493813.0,0.0,0.0,64,0x7fdb88d68ec0,114688,0,32768,32768,16384,16384,65536,49152,0.0,234886.0,0,0,298.0,131083.0,0.0,14.0,64,0x7f400d080ec0,10899495,9735651,819780,344064,1621749,0,0,163840,283274.0,32768.0,487861,0,131072.0,131072.0,0.0,131072.0,64,0x7fd0cc9bcec0,0,0,0,0,0,0,0,114688,0.0,0.0,12360,18768,0,26168,204288.0,0.0,73209.0,131079.0,64,0x7f3658754ec0,0,0,0,0,0,0,168,56,64,0x7fbff87d8ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,9804,0,0,73114.0,131072.0,0.0,65568.0,64,0x7f66b5768ec0,32768,32768,0,64,0x7f394f3a0ec0,0,0,1048576,0,0,0,0,0,16384.0,0.0,0,32768,65551.0,0.0,0.0,0.0,64,0x7fb0d7274ec0,0,0,0,224,0,65536,64261,56,197738340012541,197738340033181 +1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f1f91fa8ec0,10485760,65536,0,0,0,16384,0,0,32768.0,16384.0,0,0,131072.0,103006.0,45538.0,0.0,64,0x7f79ec6c0ec0,131072,0,0,0,0,0,0,0,16384,0,120457593.0,58766642.0,0.0,64,0x7fd989278ec0,0,393216,163840,0,0,0,0,0,27601,0.0,0.0,4096,16384,2029,0,56.0,0.0,0.0,200309.0,64,0x7faf24d0cec0,0,192825,0,0,65536,63800,56,1680,64,0x7f6a58f3cec0,298056,205865,16384,0,16384,16384,32768,49152,37256,37256,1641830.0,0.0,298048,215699,37256,0,1192192.0,769375.0,2.0,0.0,64,0x7fdb88d68ec0,114688,0,32768,32768,16384,16384,65536,49152,0.0,488393.0,0,0,5625.0,131075.0,0.0,4.0,64,0x7f400d080ec0,17880032,17293519,242449,344064,2563790,0,0,163840,610908.0,32768.0,807534,0,91016.0,91016.0,0.0,91016.0,64,0x7fd0cc9bcec0,0,0,0,0,0,0,0,114688,0.0,0.0,27561,27138,0,35627,201041.0,0.0,69966.0,131075.0,64,0x7f3658754ec0,0,0,0,0,0,0,0,56,64,0x7fbff87d8ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,16543,0,0,69339.0,131072.0,0.0,45524.0,64,0x7f66b5768ec0,32768,32768,0,64,0x7f394f3a0ec0,0,0,1048576,0,0,0,0,0,16384.0,0.0,0,32768,65550.0,0.0,0.0,0.0,64,0x7fb0d7274ec0,0,0,0,56,0,65536,65536,0,197738340125821,197738340142461 +2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f1f91fa8ec0,10485760,65536,0,0,0,16384,0,0,32768.0,16384.0,0,0,131085.0,84607.0,45537.0,0.0,64,0x7f79ec6c0ec0,131072,0,0,0,0,0,0,0,16384,0,114147217.0,58588700.0,0.0,64,0x7fd989278ec0,0,393216,163840,0,0,0,0,0,30286,0.0,0.0,4096,16384,2098,0,56.0,10.0,0.0,200992.0,64,0x7faf24d0cec0,0,194417,0,0,65536,63800,56,1680,64,0x7f6a58f3cec0,323152,214939,16384,0,16384,16384,32768,49152,40393,40393,1663115.0,0.0,323144,224787,40393,0,1292576.0,772002.0,0.0,0.0,64,0x7fdb88d68ec0,114688,0,32768,32768,16384,16384,65536,49152,0.0,572071.0,0,0,2423.0,131083.0,0.0,20.0,64,0x7f400d080ec0,19566165,18231591,990510,344064,2793194,0,0,163840,564966.0,32768.0,1000045,0,91086.0,91086.0,0.0,91086.0,64,0x7fd0cc9bcec0,0,0,0,0,0,0,0,114688,0.0,0.0,29796,26724,0,38585,200339.0,0.0,69257.0,131082.0,64,0x7f3658754ec0,0,0,0,0,0,0,0,56,64,0x7fbff87d8ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,20896,0,0,69107.0,131072.0,0.0,45533.0,64,0x7f66b5768ec0,32768,32768,0,64,0x7f394f3a0ec0,0,0,1048576,0,0,0,0,0,16384.0,0.0,0,32768,65554.0,0.0,0.0,0.0,64,0x7fb0d7274ec0,0,0,0,56,0,65536,65536,0,197738340160861,197738340176861 diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/roofline.csv b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/roofline.csv new file mode 100644 index 0000000000..4dd3f7395d --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/roofline.csv @@ -0,0 +1,5 @@ +device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh +0,1388.8623,1388.2758,1389.4489,5015.0771,5012.0532,5018.1011,9223.1035,9222.5381,9223.6689,18054.863,18053.896,18055.83,20934.51,20873.84,20995.18,20265.703,20265.008,20266.398,170438.22,170433.8,170442.64,164871.09,164866.47,164875.72,41417.742,41417.215,41418.27,41475.672,41475.148,41476.195,166335.41,165840.38,166830.44 +1,1389.1528,1388.5985,1389.7072,5026.2896,5024.1938,5028.3853,9233.2656,9232.6162,9233.915,18097.365,18092.242,18102.488,20973.391,20905.871,21040.91,20296.227,20295.758,20296.695,170859.81,170854.62,170865,165145.91,165142.66,165149.16,41491.523,41490.824,41492.223,41550.941,41550.047,41551.836,166909.02,166906.33,166911.7 +2,1388.7634,1388.2198,1389.307,5035.9404,5033.4253,5038.4556,9258.4541,9257.6875,9259.2207,18101.965,18100.9,18103.029,21045.875,21045.451,21046.299,20350.631,20350.086,20351.176,171082.23,171077.95,171086.52,165465.41,165461.77,165469.05,41570.293,41569.453,41571.133,41627.977,41627,41628.953,166901.95,166307.72,167496.19 +3,1388.174,1387.5312,1388.8167,5030.9858,5029.6353,5032.3364,9239.751,9239.1602,9240.3418,18025.277,18021.568,18028.986,21033.902,21033.303,21034.502,20310.432,20309.742,20311.121,171030.23,171026.98,171033.48,165220.55,165216.59,165224.5,41438.586,41283.68,41593.492,41580.109,41579.582,41580.637,167006.55,167004.34,167008.75 diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/sysinfo.csv b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/sysinfo.csv new file mode 100644 index 0000000000..adffddd8da --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/sysinfo.csv @@ -0,0 +1,2 @@ +workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd +ipblocks_SQ_SPI_TA_TCC_CPF,./sample/vcopy -n 1048576 -b 256 -i 3,sq|spi|ta|tcc|cpf|roofline,Thu 07 Mar 2024 02:06:36 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/timestamps.csv b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/timestamps.csv new file mode 100644 index 0000000000..65ea55bd1f --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/timestamps.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,268356,268356,1048576,256,0,0,8,0,16,64,0x0,0x7f8141afcec0,197738339987385,197738340012541,197738340033181,197738340046206 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,268356,268356,1048576,256,0,0,8,0,16,64,0x0,0x7f8141afcec0,197738340044352,197738340125821,197738340142461,197738340144001 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,268356,268356,1048576,256,0,0,8,0,16,64,0x0,0x7f8141afcec0,197738340153509,197738340160861,197738340176861,197738340178055 diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/SQ_IFETCH_LEVEL.csv b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/SQ_IFETCH_LEVEL.csv index 83758f430a..0fa7ec4f6c 100644 --- a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/SQ_IFETCH_LEVEL.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2819263,2819263,1048576,256,0,0,8,8,16,64,0x0,0x7fd3271fce80,48779,48779,16384,65536,14243,1839704,2187721540247711,2187726928458253,2187726928482253,2187721547896660 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2819263,2819263,1048576,256,0,0,8,8,16,64,0x0,0x7fd3271fce80,43690,43690,16384,65536,8233,1048580,2187721547919753,2187726928559533,2187726928578733,2187721548244383 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2819263,2819263,1048576,256,0,0,8,8,16,64,0x0,0x7fd3271fce80,44162,44162,16384,65536,8105,1048580,2187721548276714,2187726928599853,2187726928618733,2187721548459166 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,122674,122674,1048576,256,0,0,8,8,16,64,0x0,0x7fa61d720e80,48220,48220,16384,65536,14544,1868668,194118309669326,194125699131803,194125699155643,194118317402538 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,122674,122674,1048576,256,0,0,8,8,16,64,0x0,0x7fa61d720e80,43074,43074,16384,65536,8103,1048576,194118317423819,194125699242363,194125699260923,194118317787547 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,122674,122674,1048576,256,0,0,8,8,16,64,0x0,0x7fa61d720e80,42466,42466,16384,65536,8183,1048576,194118317819288,194125699281723,194125699300603,194118318003877 diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/SQ_INST_LEVEL_LDS.csv b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/SQ_INST_LEVEL_LDS.csv index 25dded7998..f5f73f6e30 100644 --- a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/SQ_INST_LEVEL_LDS.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2819445,2819445,1048576,256,0,0,8,8,16,64,0x0,0x7f12d988ce80,0,0,0,2187721994108436,2187726928458253,2187726928482253,2187722001659131 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2819445,2819445,1048576,256,0,0,8,8,16,64,0x0,0x7f12d988ce80,0,0,0,2187722001678687,2187726928559533,2187726928578733,2187722001999109 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2819445,2819445,1048576,256,0,0,8,8,16,64,0x0,0x7f12d988ce80,0,0,0,2187722002027893,2187726928599853,2187726928618733,2187722002206278 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,122861,122861,1048576,256,0,0,8,8,16,64,0x0,0x7f92fac8ee80,0,0,0,194118798617961,194125699131803,194125699155643,194118806316107 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,122861,122861,1048576,256,0,0,8,8,16,64,0x0,0x7f92fac8ee80,0,0,0,194118806335313,194125699242363,194125699260923,194118806630883 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,122861,122861,1048576,256,0,0,8,8,16,64,0x0,0x7f92fac8ee80,0,0,0,194118806659387,194125699281723,194125699300603,194118806829449 diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/SQ_INST_LEVEL_SMEM.csv index 5788a21eae..0c46932e00 100644 --- a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/SQ_INST_LEVEL_SMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2820355,2820355,1048576,256,0,0,8,8,16,64,0x0,0x7f05b4012e80,65536,190612,24488704,2187724235922447,2187726928458253,2187726928482253,2187724243534687 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2820355,2820355,1048576,256,0,0,8,8,16,64,0x0,0x7f05b4012e80,65536,172034,22006264,2187724243553332,2187726928559533,2187726928578733,2187724243975755 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2820355,2820355,1048576,256,0,0,8,8,16,64,0x0,0x7f05b4012e80,65536,173122,22197048,2187724244004519,2187726928599853,2187726928618733,2187724244182503 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,123049,123049,1048576,256,0,0,8,8,16,64,0x0,0x7f964be06e80,65536,203206,25982456,194119291932773,194125699131803,194125699155643,194119299617183 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,123049,123049,1048576,256,0,0,8,8,16,64,0x0,0x7f964be06e80,65536,170204,21847384,194119299639586,194125699242363,194125699260923,194119299885892 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,123049,123049,1048576,256,0,0,8,8,16,64,0x0,0x7f964be06e80,65536,169822,21706128,194119299914736,194125699281723,194125699300603,194119300065041 diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/SQ_INST_LEVEL_VMEM.csv index dee36bd32b..84229d7996 100644 --- a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/SQ_INST_LEVEL_VMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2821629,2821629,1048576,256,0,0,8,8,16,64,0x0,0x7f7dcad90e80,32768,657087,84097448,2187727356268432,2187726928458253,2187726928482253,2187727363972895 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2821629,2821629,1048576,256,0,0,8,8,16,64,0x0,0x7f7dcad90e80,32768,679235,86938996,2187727363996068,2187726928559533,2187726928578733,2187727364333251 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2821629,2821629,1048576,256,0,0,8,8,16,64,0x0,0x7f7dcad90e80,32768,666007,85229740,2187727364362777,2187726928599853,2187726928618733,2187727364509402 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,123235,123235,1048576,256,0,0,8,8,16,64,0x0,0x7f60e135ae80,32768,667174,85383028,194119777699844,194125699131803,194125699155643,194119785694431 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,123235,123235,1048576,256,0,0,8,8,16,64,0x0,0x7f60e135ae80,32768,673940,86254240,194119785714219,194125699242363,194125699260923,194119786050996 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,123235,123235,1048576,256,0,0,8,8,16,64,0x0,0x7f60e135ae80,32768,668795,85597592,194119786085021,194125699281723,194125699300603,194119786271163 diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/SQ_LEVEL_WAVES.csv b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/SQ_LEVEL_WAVES.csv index a6224ff11a..51607afe1b 100644 --- a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/SQ_LEVEL_WAVES.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2820901,2820901,1048576,256,0,0,8,8,16,64,0x0,0x7fd760c22e80,48211,48211,16861,385696,16384,24880933,234837,0,100012040,2187725577281388,2187726928458253,2187726928482253,2187725584929185 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2820901,2820901,1048576,256,0,0,8,8,16,64,0x0,0x7fd760c22e80,112416,112416,11756,899336,16384,24580272,231562,0,98811156,2187725584959311,2187726928559533,2187726928578733,2187725585316151 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2820901,2820901,1048576,256,0,0,8,8,16,64,0x0,0x7fd760c22e80,46048,46048,16878,368392,16384,24472447,230681,0,98373496,2187725585355255,2187726928599853,2187726928618733,2187725585538739 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,123419,123419,1048576,256,0,0,8,8,16,64,0x0,0x7f7130cf6e80,47994,47994,16739,383960,16384,25209574,233475,0,101327412,194120274842524,194125699131803,194125699155643,194120282542253 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,123419,123419,1048576,256,0,0,8,8,16,64,0x0,0x7f7130cf6e80,41992,41992,12962,335944,16384,25266450,231306,0,101551480,194120282569234,194125699242363,194125699260923,194120282895672 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,123419,123419,1048576,256,0,0,8,8,16,64,0x0,0x7f7130cf6e80,41856,41856,12840,334856,16384,24684109,230369,0,99229788,194120282933744,194125699281723,194125699300603,194120283125557 diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/perfmon/pmc_perf_0.txt b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/perfmon/pmc_perf_0.txt index 56da2065ec..109d419459 100644 --- a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/perfmon/pmc_perf_0.txt +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/perfmon/pmc_perf_0.txt @@ -1,4 +1,4 @@ -pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ SQC_TC_DATA_WRITE_REQ GRBM_COUNT GRBM_GUI_ACTIVE TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE +pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES SQ_BUSY_CU_CYCLES SQ_WAVE_CYCLES SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ SQC_TC_DATA_WRITE_REQ GRBM_COUNT GRBM_GUI_ACTIVE TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE gpu: range: diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/pmc_dispatch_info.csv b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/pmc_dispatch_info.csv new file mode 100644 index 0000000000..17300ae9af --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) ",2 +1,"vecCopy(double*, double*, double*, int, int) ",2 +2,"vecCopy(double*, double*, double*, int, int) ",2 diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/pmc_perf.csv b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/pmc_perf.csv index e4e4660d65..32a911ff60 100644 --- a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/pmc_perf.csv +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,wave_size_1,obj_1,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,wave_size_2,obj_2,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,wave_size_3,obj_3,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,wave_size_4,obj_4,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,wave_size_5,obj_5,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,CPC_ME1_DC0_SPI_BUSY,wave_size_6,obj_6,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,wave_size_7,obj_7,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,wave_size_8,obj_8,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,wave_size_9,obj_9,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7ff93f9c4e80,32768,0,0,0,16384,16384,393216,22267376,960.0,513968.0,0.0,524288.0,0,18216,64,0x7f7707a80e80,388320,239103,3475035,16384,24580992,144,48,0,48539,48539,3933705.0,3095412.0,4976.0,1013296.0,48539,0,64,0x7efcb3e56e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,64,0x7f449467ae80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,64,0x7fcdf00c2e80,209157,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,9965,550,64,0x7fa5e5d08e80,1849140,360448,163840,0,0,180224,114688,0,69309515.0,180071918.0,74895310.0,131072.0,26161,64,0x7fe5abd6ee80,0,0,192,0,65536,64489,48,1309,0.0,0.0,0.0,32768.0,538,47602,64,0x7f63544d0e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,64,0x7fc705a10e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,913,46637,64,0x7f3e590d0e80,131072.0,131072.0,0.0,2552697.0,2187726928458253,2187726928482253 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7ff93f9c4e80,32768,0,0,0,16384,16384,393216,22276415,960.0,513973.0,0.0,524288.0,0,14978,64,0x7f7707a80e80,307264,213932,3122793,16384,22378558,0,48,0,38407,38407,3493635.0,2964826.0,6577.0,1454406.0,38407,0,64,0x7efcb3e56e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,64,0x7f449467ae80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,64,0x7fcdf00c2e80,145865,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,18148,4150,64,0x7fa5e5d08e80,221097,360448,163840,0,0,180224,114688,0,74091755.0,206735929.0,77719619.0,131072.0,23667,64,0x7fe5abd6ee80,0,0,48,0,65536,65536,0,0,0.0,0.0,0.0,32768.0,435,39137,64,0x7f63544d0e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,64,0x7fc705a10e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,913,38870,64,0x7f3e590d0e80,131072.0,131072.0,0.0,2559487.0,2187726928559533,2187726928578733 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7ff93f9c4e80,32768,0,0,0,16384,16384,393216,22135459,960.0,513878.0,0.0,524288.0,0,15148,64,0x7f7707a80e80,334056,229531,3320359,16384,24423895,0,48,0,41756,41756,3735660.0,3035003.0,5770.0,1054124.0,41756,0,64,0x7efcb3e56e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,64,0x7f449467ae80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,64,0x7fcdf00c2e80,209871,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,9113,3232,64,0x7fa5e5d08e80,1605566,360448,163840,0,0,180224,114688,0,73056119.0,191205597.0,74915615.0,131072.0,26188,64,0x7fe5abd6ee80,0,0,48,0,65536,65536,0,0,0.0,0.0,0.0,32768.0,432,41932,64,0x7f63544d0e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,64,0x7fc705a10e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,2754,38687,64,0x7f3e590d0e80,131072.0,131072.0,0.0,2637640.0,2187726928599853,2187726928618733 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_1,obj_1,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,wave_size_2,obj_2,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,CPC_ME1_DC0_SPI_BUSY,wave_size_3,obj_3,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,wave_size_4,obj_4,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,wave_size_5,obj_5,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,wave_size_6,obj_6,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,wave_size_7,obj_7,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,wave_size_8,obj_8,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,wave_size_9,obj_9,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_BUSY_CU_CYCLES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fea865a8e80,131072.0,131072.0,0.0,2543874.0,64,0x7fa4c0e92e80,0,0,192,0,65536,64325,48,1550,0.0,0.0,0.0,32768.0,538,47685,64,0x7f7613e96e80,1932381,360448,163840,0,0,180224,114688,0,70516604.0,208780825.0,79499142.0,131072.0,26008,64,0x7f9d1dac2e80,32768,0,0,0,16384,16384,393216,22941776,960.0,514021.0,0.0,524288.0,0,17981,64,0x7fd9def56e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,64,0x7f588375ee80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,2728,47404,64,0x7fd8cc436e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,64,0x7f36bfe3ce80,193103,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,9922,550,64,0x7f8481244e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,64,0x7f8cb54eae80,385504,236665,16384,3479670,25335685,144,48,0,48187,48187,3897750.0,3077421.0,7001.0,1048151.0,48187,0,194125699131803,194125699155643 +1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fea865a8e80,131072.0,131072.0,0.0,2635437.0,64,0x7fa4c0e92e80,0,0,48,0,65536,65536,0,0,0.0,0.0,0.0,32768.0,588,48185,64,0x7f7613e96e80,1586536,360448,163840,0,0,180224,114688,0,70397592.0,197861031.0,76054912.0,131072.0,25898,64,0x7f9d1dac2e80,32768,0,0,0,16384,16384,393216,25081865,240.0,521663.0,0.0,524288.0,0,21203,64,0x7fd9def56e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,64,0x7f588375ee80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,240.0,524288.0,5932,40018,64,0x7fd8cc436e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,64,0x7f36bfe3ce80,121776,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,7773,588,64,0x7f8481244e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,64,0x7f8cb54eae80,344704,231920,16384,3397452,25194808,0,48,0,43087,43087,3763350.0,3104622.0,5667.0,1066874.0,43087,0,194125699242363,194125699260923 +2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fea865a8e80,131072.0,131072.0,0.0,2515231.0,64,0x7fa4c0e92e80,0,0,48,0,65536,65536,0,0,0.0,0.0,0.0,32768.0,432,41348,64,0x7f7613e96e80,1400699,360448,163840,0,0,180224,114688,0,72535482.0,188588285.0,74214524.0,131072.0,26085,64,0x7f9d1dac2e80,32768,0,0,0,16384,16384,393216,23096321,960.0,513907.0,0.0,524288.0,0,14780,64,0x7fd9def56e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,64,0x7f588375ee80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,4573,38128,64,0x7fd8cc436e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,64,0x7f36bfe3ce80,194465,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,8908,2385,64,0x7f8481244e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,64,0x7f8cb54eae80,336352,226728,16384,3304402,24106612,0,48,0,42043,42043,3687584.0,3011362.0,5447.0,1000897.0,42043,0,194125699281723,194125699300603 diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/sysinfo.csv b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/sysinfo.csv index f73b016672..f390c406ae 100644 --- a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/sysinfo.csv +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -ipblocks_SQ_SQC_TCP_CPC,./tests/vcopy -n 1048576 -b 256 -i 3,sq|sqc|tcp|cpc,Fri Mar 1 16:43:52 2024 (CST),1,t006-003.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651240,,5.7.1-98,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +ipblocks_SQ_SQC_TCP_CPC,./tests/vcopy -n 1048576 -b 256 -i 3,sq|sqc|tcp|cpc,Thu 07 Mar 2024 01:06:23 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/timestamps.csv b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/timestamps.csv index ac275c5de9..3bec46a004 100644 --- a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/timestamps.csv +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,2821447,2821447,1048576,256,0,0,8,8,16,64,0x0,0x7f8b82ebce80,2187726928433493,2187726928458253,2187726928482253,2187726928493877 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,2821447,2821447,1048576,256,0,0,8,8,16,64,0x0,0x7f8b82ebce80,2187726928494989,2187726928559533,2187726928578733,2187726928579778 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,2821447,2821447,1048576,256,0,0,8,8,16,64,0x0,0x7f8b82ebce80,2187726928590849,2187726928599853,2187726928618733,2187726928619813 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,125477,125477,1048576,256,0,0,8,8,16,64,0x0,0x7f7838d5ce80,194125699105040,194125699131803,194125699155643,194125699167298 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,125477,125477,1048576,256,0,0,8,8,16,64,0x0,0x7f7838d5ce80,194125699168571,194125699242363,194125699260923,194125699262428 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,125477,125477,1048576,256,0,0,8,8,16,64,0x0,0x7f7838d5ce80,194125699273650,194125699281723,194125699300603,194125699301833 diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/SQ_IFETCH_LEVEL.csv b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/SQ_IFETCH_LEVEL.csv new file mode 100644 index 0000000000..639f3e8c46 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/SQ_IFETCH_LEVEL.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,273833,273833,1048576,256,0,0,8,0,16,64,0x0,0x7fe6733a8ec0,28198,28198,16384,65536,13973,1557568,197937688664559,197946401420195,197946401440355,197937704802067 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,273833,273833,1048576,256,0,0,8,0,16,64,0x0,0x7fe6733a8ec0,41193,41193,16384,65536,9264,1048672,197937704822767,197946401459235,197946401475075,197937705081326 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,273833,273833,1048576,256,0,0,8,0,16,64,0x0,0x7fe6733a8ec0,40627,40627,16384,65536,9571,1048672,197937705111132,197946401540515,197946401557155,197937705267588 diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/SQ_INST_LEVEL_LDS.csv b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/SQ_INST_LEVEL_LDS.csv new file mode 100644 index 0000000000..33cecaeab4 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/SQ_INST_LEVEL_LDS.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,274019,274019,1048576,256,0,0,8,0,16,64,0x0,0x7fbb53a20ec0,0,0,0,197938174609107,197946401420195,197946401440355,197938190896290 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,274019,274019,1048576,256,0,0,8,0,16,64,0x0,0x7fbb53a20ec0,0,0,0,197938190913041,197946401459235,197946401475075,197938191245039 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,274019,274019,1048576,256,0,0,8,0,16,64,0x0,0x7fbb53a20ec0,0,0,0,197938191271509,197946401540515,197946401557155,197938191429588 diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/SQ_INST_LEVEL_SMEM.csv new file mode 100644 index 0000000000..bfc920e015 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/SQ_INST_LEVEL_SMEM.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,274220,274220,1048576,256,0,0,8,0,16,64,0x0,0x7f95243d8ec0,65536,168886,18969808,197938655465490,197946401420195,197946401440355,197938671639167 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,274220,274220,1048576,256,0,0,8,0,16,64,0x0,0x7f95243d8ec0,65536,223370,25131648,197938671658394,197946401459235,197946401475075,197938671917674 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,274220,274220,1048576,256,0,0,8,0,16,64,0x0,0x7f95243d8ec0,65536,229236,25772136,197938671944375,197946401540515,197946401557155,197938672077206 diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/SQ_INST_LEVEL_VMEM.csv new file mode 100644 index 0000000000..e5bc356deb --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/SQ_INST_LEVEL_VMEM.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,274419,274419,1048576,256,0,0,8,0,16,64,0x0,0x7fd36ab24ec0,32768,288927,32358464,197939132572009,197946401420195,197946401440355,197939148812653 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,274419,274419,1048576,256,0,0,8,0,16,64,0x0,0x7fd36ab24ec0,32768,575469,64457372,197939148830557,197946401459235,197946401475075,197939149112881 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,274419,274419,1048576,256,0,0,8,0,16,64,0x0,0x7fd36ab24ec0,32768,586224,65666236,197939149143299,197946401540515,197946401557155,197939149316015 diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/SQ_LEVEL_WAVES.csv b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/SQ_LEVEL_WAVES.csv new file mode 100644 index 0000000000..9b73d65f8c --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/SQ_LEVEL_WAVES.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,274604,274604,1048576,256,0,0,8,0,16,64,0x0,0x7f8127084ec0,27907,27907,11496,223264,16384,10880182,129014,0,44024896,197939615767006,197946401420195,197946401440355,197939631710448 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,274604,274604,1048576,256,0,0,8,0,16,64,0x0,0x7f8127084ec0,41500,41500,13088,332008,16384,20096204,229373,0,80869096,197939631737509,197946401459235,197946401475075,197939632032528 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,274604,274604,1048576,256,0,0,8,0,16,64,0x0,0x7f8127084ec0,41713,41713,13872,333712,16384,19653160,226241,0,79095984,197939632067884,197946401540515,197946401557155,197939632243687 diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/SQ_IFETCH_LEVEL.txt b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/SQ_IFETCH_LEVEL.txt new file mode 100644 index 0000000000..293092f641 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/SQ_IFETCH_LEVEL.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/SQ_INST_LEVEL_LDS.txt b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/SQ_INST_LEVEL_LDS.txt new file mode 100644 index 0000000000..08439eedce --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/SQ_INST_LEVEL_LDS.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt new file mode 100644 index 0000000000..6cca322d4e --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt new file mode 100644 index 0000000000..e527ad31ba --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/SQ_LEVEL_WAVES.txt b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/SQ_LEVEL_WAVES.txt new file mode 100644 index 0000000000..3f8e04adb3 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/SQ_LEVEL_WAVES.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_0.txt b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_0.txt new file mode 100644 index 0000000000..362468befa --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_0.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_CVT SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU SQ_INSTS_VSKIPPED SQ_INSTS SQ_INSTS_VALU GRBM_COUNT GRBM_GUI_ACTIVE TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_1.txt b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_1.txt new file mode 100644 index 0000000000..8f02917f2f --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_1.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_ADD_F16 SQ_INSTS_VALU_MUL_F16 SQ_INSTS_VALU_FMA_F16 SQ_INSTS_VALU_TRANS_F16 SQ_INSTS_VALU_ADD_F32 SQ_INSTS_VALU_MUL_F32 SQ_INSTS_VALU_FMA_F32 SQ_INSTS_VALU_TRANS_F32 TCP_READ_TAGCONFLICT_STALL_CYCLES_sum TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum TCP_TA_TCP_STATE_READ_sum CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_10.txt b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_10.txt new file mode 100644 index 0000000000..7053d4dce6 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_10.txt @@ -0,0 +1,5 @@ +pmc: SQC_TC_DATA_WRITE_REQ SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_11.txt b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_11.txt new file mode 100644 index 0000000000..77ae8b461f --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_11.txt @@ -0,0 +1,5 @@ +pmc: SQC_ICACHE_MISSES_DUPLICATE SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_12.txt b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_12.txt new file mode 100644 index 0000000000..dfb2cf65e5 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_12.txt @@ -0,0 +1,5 @@ +pmc: SQC_DCACHE_REQ_READ_1 SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_2.txt b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_2.txt new file mode 100644 index 0000000000..876bc44376 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_2.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_ADD_F64 SQ_INSTS_VALU_MUL_F64 SQ_INSTS_VALU_FMA_F64 SQ_INSTS_VALU_TRANS_F64 SQ_INSTS_VALU_INT32 SQ_INSTS_VALU_INT64 SQ_INSTS_SMEM SQ_INSTS_FLAT TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_3.txt b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_3.txt new file mode 100644 index 0000000000..a502338117 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_3.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG SQ_WAVE_CYCLES SQ_WAIT_ANY SQ_WAIT_INST_ANY TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_4.txt b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_4.txt new file mode 100644 index 0000000000..cea1a640aa --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_4.txt @@ -0,0 +1,5 @@ +pmc: SQ_ACTIVE_INST_ANY SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU SQ_ACTIVE_INST_SCA TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_5.txt b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_5.txt new file mode 100644 index 0000000000..c069792010 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_5.txt @@ -0,0 +1,5 @@ +pmc: SQ_ACTIVE_INST_EXP_GDS SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU SQ_THREAD_CYCLES_VALU TCP_TCP_LATENCY_sum TCP_TCC_READ_REQ_LATENCY_sum TCP_TCC_WRITE_REQ_LATENCY_sum TCP_TCC_READ_REQ_sum CPC_ME1_DC0_SPI_BUSY + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_6.txt b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_6.txt new file mode 100644 index 0000000000..3ad6efb0f1 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_6.txt @@ -0,0 +1,5 @@ +pmc: SQ_IFETCH SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TCP_TCC_NC_READ_REQ_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_7.txt b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_7.txt new file mode 100644 index 0000000000..9add981bfa --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_7.txt @@ -0,0 +1,5 @@ +pmc: SQ_WAVES_LT_32 SQ_WAVES_LT_16 SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TCP_TCC_UC_WRITE_REQ_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_8.txt b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_8.txt new file mode 100644 index 0000000000..b0de340d61 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_8.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM_NORM SQ_INSTS_MFMA SQ_INSTS_VALU_MFMA_I8 SQ_INSTS_VALU_MFMA_F16 SQ_INSTS_VALU_MFMA_BF16 SQ_INSTS_VALU_MFMA_F32 SQ_INSTS_VALU_MFMA_F64 SQ_VALU_MFMA_BUSY_CYCLES TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TCP_TCC_CC_ATOMIC_REQ_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_9.txt b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_9.txt new file mode 100644 index 0000000000..9ffe5778c3 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_9.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_FLAT_LDS_ONLY SQ_INSTS_VALU_MFMA_MOPS_I8 SQ_INSTS_VALU_MFMA_MOPS_F16 SQ_INSTS_VALU_MFMA_MOPS_BF16 SQ_INSTS_VALU_MFMA_MOPS_F32 SQ_INSTS_VALU_MFMA_MOPS_F64 SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum TCP_PENDING_STALL_CYCLES_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/timestamps.txt b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/timestamps.txt new file mode 100644 index 0000000000..676cca1b80 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/timestamps.txt @@ -0,0 +1,5 @@ +pmc: + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/pmc_perf.csv b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/pmc_perf.csv new file mode 100644 index 0000000000..b5eb681f09 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/pmc_perf.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,CPC_ME1_DC0_SPI_BUSY,wave_size_1,obj_1,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_2,obj_2,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_3,obj_3,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,wave_size_4,obj_4,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,wave_size_5,obj_5,SQ_ACTIVE_INST_ANY,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,wave_size_6,obj_6,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,wave_size_7,obj_7,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,wave_size_8,obj_8,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,wave_size_9,obj_9,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,wave_size_10,obj_10,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_11,obj_11,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_12,obj_12,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f5bf43d8ec0,0,32768,32768,16384,16384,65536,49152,10485760,26997165.0,85414825.0,40321453.0,131072.0,15250,64,0x7ff45f9c8ec0,1303,140878,0,0,65536,63800,56,1680,64,0x7f06a65d4ec0,0,0,0,0,0,0,168,56,131072.0,131072.0,0.0,986628.0,64,0x7f5d58e98ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,64,0x7f2b31420ec0,0,16384,16384,32768,49152,0,393216,163840,27880,27880,1961510.0,1349883.0,3786.0,165711.0,27880,0,64,0x7f1eadf9cec0,344064,225112,130673,1654406,0,0,163840,114688,832.0,515136.0,0.0,524288.0,0,11233,64,0x7fad2c518ec0,0,0,0,16384,16384,10564914,9520920,699930,0.0,0.0,0.0,524288.0,814,26641,64,0x7f5e6e3ccec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,64,0x7f94213d0ec0,0,0,0,0,114688,0,65536,32768,2097152.0,2097152.0,1048576.0,1048576.0,7086,546,64,0x7f3060d3cec0,65536,0,0,0,16384,16384,0,0,131072.0,0.0,0.0,0.0,64,0x7fb4d61a8ec0,0,0,0,224,0,65536,64282,56,64,0x7f7ed5c28ec0,32768,32768,0,64,0x7f7f21050ec0,0,0,0,0,0,0,0,0,0.0,0.0,0.0,32768.0,352,27567,197946401420195,197946401440355 +1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f5bf43d8ec0,0,32768,32768,16384,16384,65536,49152,10485760,56798761.0,192841727.0,50094814.0,131072.0,23371,64,0x7ff45f9c8ec0,0,205433,0,0,65536,63800,56,1680,64,0x7f06a65d4ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2097499.0,64,0x7f5d58e98ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,64,0x7f2b31420ec0,0,16384,16384,32768,49152,0,393216,163840,36462,36462,2899286.0,2330506.0,4810.0,343689.0,36462,0,64,0x7f1eadf9cec0,344064,300568,205692,2552053,0,0,163840,114688,0.0,524288.0,0.0,524288.0,0,12176,64,0x7fad2c518ec0,0,0,0,16384,16384,17958261,17365707,248490,0.0,0.0,0.0,524288.0,819,37111,64,0x7f5e6e3ccec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,64,0x7f94213d0ec0,0,0,0,0,114688,0,65536,32768,2097152.0,2097152.0,1048576.0,1048576.0,8554,550,64,0x7f3060d3cec0,65536,0,0,0,16384,16384,0,0,131072.0,0.0,0.0,0.0,64,0x7fb4d61a8ec0,0,0,0,56,0,65536,65536,0,64,0x7f7ed5c28ec0,32768,32768,0,64,0x7f7f21050ec0,0,0,0,0,0,0,0,0,0.0,0.0,0.0,32768.0,302,36886,197946401459235,197946401475075 +2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f5bf43d8ec0,0,32768,32768,16384,16384,65536,49152,10485760,58517425.0,207689965.0,45731510.0,131072.0,26266,64,0x7ff45f9c8ec0,0,184796,0,0,65536,63800,56,1680,64,0x7f06a65d4ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2055072.0,64,0x7f5d58e98ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,64,0x7f2b31420ec0,0,16384,16384,32768,49152,0,393216,163840,42234,42234,3176485.0,2544885.0,4671.0,358348.0,42234,0,64,0x7f1eadf9cec0,344064,343640,229400,2862506,0,0,163840,114688,832.0,515160.0,0.0,524288.0,0,14317,64,0x7fad2c518ec0,0,0,0,16384,16384,19021718,17882543,795111,0.0,0.0,0.0,524288.0,2712,38099,64,0x7f5e6e3ccec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,64,0x7f94213d0ec0,0,0,0,0,114688,0,65536,32768,2097152.0,2097152.0,1048576.0,1048576.0,9664,2458,64,0x7f3060d3cec0,65536,0,0,0,16384,16384,0,0,131072.0,0.0,0.0,0.0,64,0x7fb4d61a8ec0,0,0,0,56,0,65536,65536,0,64,0x7f7ed5c28ec0,32768,32768,0,64,0x7f7f21050ec0,0,0,0,0,0,0,0,0,0.0,0.0,0.0,32768.0,302,40518,197946401540515,197946401557155 diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/roofline.csv b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/roofline.csv new file mode 100644 index 0000000000..e82a6792c8 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/roofline.csv @@ -0,0 +1,5 @@ +device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh +0,1389.4381,1388.8553,1390.0209,5015.0967,5011.8203,5018.373,9224.3516,9223.6533,9225.0498,18051.711,18050.818,18052.604,20932.088,20871.99,20992.186,20267.361,20266.695,20268.027,170435.88,170431.92,170439.83,164881.86,164875.77,164887.95,41421.273,41420.738,41421.809,41478.977,41478.379,41479.574,166347.16,165855.5,166838.81 +1,1388.8232,1388.2603,1389.3862,5028.1265,5026.0376,5030.2153,9235.1104,9234.4307,9235.79,18096.645,18092.363,18100.926,20974.473,20907.904,21041.041,20294.145,20293.709,20294.58,170841,170837.2,170844.8,165117.02,165111.83,165122.2,41481.996,41481.355,41482.637,41541.391,41540.145,41542.637,166875.09,166870.98,166879.2 +2,1388.4731,1387.8798,1389.0665,5034.4199,5032.0317,5036.8081,9257.6221,9256.875,9258.3691,18100.244,18099.41,18101.078,21040.211,21039.766,21040.656,20343.441,20342.75,20344.133,171043.92,171037.59,171050.25,165460.86,165456.91,165464.81,41566.301,41565.512,41567.09,41626.738,41625.742,41627.734,166920.09,166325.59,167514.59 +3,1389.2181,1388.5493,1389.887,5031.2817,5029.7422,5032.8213,9239.5068,9238.8262,9240.1875,18021.037,18017.094,18024.98,21033.131,21032.49,21033.771,20310.314,20309.557,20311.072,171045.16,171040.42,171049.89,165223.34,165217.73,165228.95,41439.453,41285.234,41593.672,41581.762,41581.203,41582.32,167012.78,167010.56,167015 diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/sysinfo.csv b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/sysinfo.csv new file mode 100644 index 0000000000..e8e7bc9c0e --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/sysinfo.csv @@ -0,0 +1,2 @@ +workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd +ipblocks_SQ_SQC_TCP_CPC,./sample/vcopy -n 1048576 -b 256 -i 3,sq|sqc|tcp|cpc|roofline,Thu 07 Mar 2024 02:10:04 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/timestamps.csv b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/timestamps.csv new file mode 100644 index 0000000000..8bf03b3b27 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/timestamps.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,277271,277271,1048576,256,0,0,8,0,16,64,0x0,0x7f5312804ec0,197946401394660,197946401420195,197946401440355,197946401458611 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,277271,277271,1048576,256,0,0,8,0,16,64,0x0,0x7f5312804ec0,197946401451037,197946401459235,197946401475075,197946401537901 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,277271,277271,1048576,256,0,0,8,0,16,64,0x0,0x7f5312804ec0,197946401485091,197946401540515,197946401557155,197946401557939 diff --git a/tests/workloads/ipblocks_SQ_TA/MI100/SQ_IFETCH_LEVEL.csv b/tests/workloads/ipblocks_SQ_TA/MI100/SQ_IFETCH_LEVEL.csv index bbf579d8db..e1f38f84f6 100644 --- a/tests/workloads/ipblocks_SQ_TA/MI100/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/ipblocks_SQ_TA/MI100/SQ_IFETCH_LEVEL.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2809891,2809891,1048576,256,0,0,8,8,16,64,0x0,0x7f5e6ae8ee80,48299,48299,16384,65536,13199,1695184,2187694738844564,2187696529458971,2187696529483771,2187694746359051 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2809891,2809891,1048576,256,0,0,8,8,16,64,0x0,0x7f5e6ae8ee80,42220,42220,16384,65536,8135,1048588,2187694746382756,2187696529666491,2187696529685051,2187694746698548 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2809891,2809891,1048576,256,0,0,8,8,16,64,0x0,0x7f5e6ae8ee80,42546,42546,16384,65536,8314,1048588,2187694746731350,2187696529706491,2187696529725212,2187694746910246 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,111832,111832,1048576,256,0,0,8,8,16,64,0x0,0x7faca850ee80,47672,47672,16384,65536,13016,1662396,194086530612610,194093425213997,194093425237997,194086538366892 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,111832,111832,1048576,256,0,0,8,8,16,64,0x0,0x7faca850ee80,42063,42063,16384,65536,8271,1048608,194086538389365,194093425324077,194093425343117,194086538701616 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,111832,111832,1048576,256,0,0,8,8,16,64,0x0,0x7faca850ee80,42511,42511,16384,65536,8182,1048588,194086538733907,194093425365197,194093425384237,194086538913838 diff --git a/tests/workloads/ipblocks_SQ_TA/MI100/SQ_INST_LEVEL_LDS.csv b/tests/workloads/ipblocks_SQ_TA/MI100/SQ_INST_LEVEL_LDS.csv index 0d8f45d9ed..0ff257e463 100644 --- a/tests/workloads/ipblocks_SQ_TA/MI100/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/ipblocks_SQ_TA/MI100/SQ_INST_LEVEL_LDS.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2810073,2810073,1048576,256,0,0,8,8,16,64,0x0,0x7f061e2ace80,0,0,0,2187695188004786,2187696529458971,2187696529483771,2187695195647002 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2810073,2810073,1048576,256,0,0,8,8,16,64,0x0,0x7f061e2ace80,0,0,0,2187695195664334,2187696529666491,2187696529685051,2187695195982822 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2810073,2810073,1048576,256,0,0,8,8,16,64,0x0,0x7f061e2ace80,0,0,0,2187695196011245,2187696529706491,2187696529725212,2187695196190662 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,112032,112032,1048576,256,0,0,8,8,16,64,0x0,0x7fb86e3d2e80,0,0,0,194087028102668,194093425213997,194093425237997,194087035834237 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,112032,112032,1048576,256,0,0,8,8,16,64,0x0,0x7fb86e3d2e80,0,0,0,194087035852191,194093425324077,194093425343117,194087036186023 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,112032,112032,1048576,256,0,0,8,8,16,64,0x0,0x7fb86e3d2e80,0,0,0,194087036214236,194093425365197,194093425384237,194087036395239 diff --git a/tests/workloads/ipblocks_SQ_TA/MI100/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/ipblocks_SQ_TA/MI100/SQ_INST_LEVEL_SMEM.csv index 6ce910c685..e3c06eeb3e 100644 --- a/tests/workloads/ipblocks_SQ_TA/MI100/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/ipblocks_SQ_TA/MI100/SQ_INST_LEVEL_SMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2810255,2810255,1048576,256,0,0,8,8,16,64,0x0,0x7f24c6524e80,65536,194638,24884840,2187695633152254,2187696529458971,2187696529483771,2187695640618980 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2810255,2810255,1048576,256,0,0,8,8,16,64,0x0,0x7f24c6524e80,65536,200012,25602944,2187695640636814,2187696529666491,2187696529685051,2187695640946255 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2810255,2810255,1048576,256,0,0,8,8,16,64,0x0,0x7f24c6524e80,65536,167482,21457760,2187695640974748,2187696529706491,2187696529725212,2187695641154566 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,112232,112232,1048576,256,0,0,8,8,16,64,0x0,0x7efdde722e80,65536,191952,24597432,194087514744535,194093425213997,194093425237997,194087522319548 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,112232,112232,1048576,256,0,0,8,8,16,64,0x0,0x7efdde722e80,65536,170250,21804832,194087522338704,194093425324077,194093425343117,194087522640035 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,112232,112232,1048576,256,0,0,8,8,16,64,0x0,0x7efdde722e80,65536,172682,22115960,194087522668108,194093425365197,194093425384237,194087522839282 diff --git a/tests/workloads/ipblocks_SQ_TA/MI100/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/ipblocks_SQ_TA/MI100/SQ_INST_LEVEL_VMEM.csv index 6e811be7ac..a6bd0b5928 100644 --- a/tests/workloads/ipblocks_SQ_TA/MI100/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/ipblocks_SQ_TA/MI100/SQ_INST_LEVEL_VMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2809345,2809345,1048576,256,0,0,8,8,16,64,0x0,0x7fc1c3466e80,32768,634396,81209404,2187693399118439,2187696529458971,2187696529483771,2187693406790230 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2809345,2809345,1048576,256,0,0,8,8,16,64,0x0,0x7fc1c3466e80,32768,651215,83359912,2187693406811801,2187696529666491,2187696529685051,2187693407115160 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2809345,2809345,1048576,256,0,0,8,8,16,64,0x0,0x7fc1c3466e80,32768,640677,81998540,2187693407144485,2187696529706491,2187696529725212,2187693407317831 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,112432,112432,1048576,256,0,0,8,8,16,64,0x0,0x7fdc35118e80,32768,657184,84113380,194088000794372,194093425213997,194093425237997,194088008716061 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,112432,112432,1048576,256,0,0,8,8,16,64,0x0,0x7fdc35118e80,32768,677062,86659932,194088008733764,194093425324077,194093425343117,194088009053039 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,112432,112432,1048576,256,0,0,8,8,16,64,0x0,0x7fdc35118e80,32768,674346,86322100,194088009081683,194093425365197,194093425384237,194088009274979 diff --git a/tests/workloads/ipblocks_SQ_TA/MI100/SQ_LEVEL_WAVES.csv b/tests/workloads/ipblocks_SQ_TA/MI100/SQ_LEVEL_WAVES.csv index dab0df4ee6..e45c9d67d6 100644 --- a/tests/workloads/ipblocks_SQ_TA/MI100/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/ipblocks_SQ_TA/MI100/SQ_LEVEL_WAVES.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2810983,2810983,1048576,256,0,0,8,8,16,64,0x0,0x7face131ae80,48115,48115,17504,384928,16384,25356498,235125,0,101913456,2187697416245996,2187696529458971,2187696529483771,2187697423741798 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2810983,2810983,1048576,256,0,0,8,8,16,64,0x0,0x7face131ae80,42600,42600,13520,340808,16384,24807935,230438,0,99731944,2187697423770211,2187696529666491,2187696529685051,2187697424108507 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2810983,2810983,1048576,256,0,0,8,8,16,64,0x0,0x7face131ae80,42885,42885,13986,343088,16384,24678470,229171,0,99200520,2187697424146448,2187696529706491,2187696529725212,2187697424331786 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,112617,112617,1048576,256,0,0,8,8,16,64,0x0,0x7f931de7ee80,48195,48195,17010,385568,16384,24987261,235382,0,100448300,194088497423749,194093425213997,194093425237997,194088506641663 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,112617,112617,1048576,256,0,0,8,8,16,64,0x0,0x7f931de7ee80,42266,42266,13728,338136,16384,24959166,232279,0,100332820,194088506673243,194093425324077,194093425343117,194088506961308 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,112617,112617,1048576,256,0,0,8,8,16,64,0x0,0x7f931de7ee80,41786,41786,13364,334296,16384,24285447,225010,0,97631512,194088507000733,194093425365197,194093425384237,194088507187757 diff --git a/tests/workloads/ipblocks_SQ_TA/MI100/pmc_dispatch_info.csv b/tests/workloads/ipblocks_SQ_TA/MI100/pmc_dispatch_info.csv new file mode 100644 index 0000000000..17300ae9af --- /dev/null +++ b/tests/workloads/ipblocks_SQ_TA/MI100/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) ",2 +1,"vecCopy(double*, double*, double*, int, int) ",2 +2,"vecCopy(double*, double*, double*, int, int) ",2 diff --git a/tests/workloads/ipblocks_SQ_TA/MI100/pmc_perf.csv b/tests/workloads/ipblocks_SQ_TA/MI100/pmc_perf.csv index a564804933..2296381e3d 100644 --- a/tests/workloads/ipblocks_SQ_TA/MI100/pmc_perf.csv +++ b/tests/workloads/ipblocks_SQ_TA/MI100/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,wave_size_1,obj_1,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,wave_size_2,obj_2,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,wave_size_3,obj_3,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,wave_size_4,obj_4,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,wave_size_5,obj_5,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,GRBM_COUNT,GRBM_GUI_ACTIVE,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,wave_size_6,obj_6,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,wave_size_7,obj_7,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_8,obj_8,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f02a01bae80,0,131072,144,48,0,0,0,192,32768.0,16384.0,64,0x7f9860de6e80,0,65536,64140,48,2165,184906,0,0,16384.0,0.0,64,0x7f32649fce80,49152,11534336,65536,0,0,0,16384,0,1340691.0,32768.0,64,0x7f02fa9a8e80,16384,393216,22823455,1699766,360448,163840,0,0,0.0,0.0,64,0x7f768170ee80,180224,114688,0,32768,32768,16384,16384,65536,0.0,0.0,64,0x7f5927308e80,395344,245799,3554639,16384,26152860,16384,16384,32768,49417,49417,2465283.0,0.0,64,0x7f5c780cae80,49152,0,65536,32768,0,0,0,16384,0.0,0.0,64,0x7f01da15ee80,65536,64048,48,1440,32768,32768,0,64,0x7f1b20104e80,0,0,0,1048576,0,0,0,0,0.0,594598.0,2187696529458971,2187696529483771 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f02a01bae80,0,131072,0,48,0,0,0,48,32768.0,16384.0,64,0x7f9860de6e80,0,65536,65536,0,0,187468,0,0,16384.0,0.0,64,0x7f32649fce80,49152,11534336,65536,0,0,0,16384,0,1059869.0,32768.0,64,0x7f02fa9a8e80,16384,393216,22762345,1266639,360448,163840,0,0,0.0,0.0,64,0x7f768170ee80,180224,114688,0,32768,32768,16384,16384,65536,0.0,0.0,64,0x7f5927308e80,910416,238962,3461066,16384,24586798,16384,16384,32768,113801,113801,2320098.0,0.0,64,0x7f5c780cae80,49152,0,65536,32768,0,0,0,16384,0.0,0.0,64,0x7f01da15ee80,65536,64048,48,1440,32768,32768,0,64,0x7f1b20104e80,0,0,0,1048576,0,0,0,0,0.0,595106.0,2187696529666491,2187696529685051 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f02a01bae80,0,131072,0,48,0,0,0,48,32768.0,16384.0,64,0x7f9860de6e80,0,65536,65536,0,0,185371,0,0,16384.0,0.0,64,0x7f32649fce80,49152,11534336,65536,0,0,0,16384,0,1199953.0,32768.0,64,0x7f02fa9a8e80,16384,393216,22529112,1133194,360448,163840,0,0,0.0,0.0,64,0x7f768170ee80,180224,114688,0,32768,32768,16384,16384,65536,0.0,0.0,64,0x7f5927308e80,383520,239451,3452169,16384,24898173,16384,16384,32768,47939,47939,2385087.0,0.0,64,0x7f5c780cae80,49152,0,65536,32768,0,0,0,16384,0.0,0.0,64,0x7f01da15ee80,65536,64048,48,1440,32768,32768,0,64,0x7f1b20104e80,0,0,0,1048576,0,0,0,0,0.0,578683.0,2187696529706491,2187696529725212 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,wave_size_1,obj_1,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,GRBM_COUNT,GRBM_GUI_ACTIVE,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,wave_size_2,obj_2,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,wave_size_3,obj_3,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,wave_size_4,obj_4,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,wave_size_5,obj_5,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,wave_size_6,obj_6,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_7,obj_7,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,wave_size_8,obj_8,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f57df22ce80,0,131072,144,48,0,0,0,192,32768.0,16384.0,64,0x7f578ac6ce80,384208,233514,3414819,16384,25361297,16384,16384,32768,48025,48025,2054029.0,0.0,64,0x7f152ac70e80,49152,0,65536,32768,0,0,0,16384,0.0,0.0,64,0x7fb03f932e80,180224,114688,0,32768,32768,16384,16384,65536,0.0,0.0,64,0x7fecd7b64e80,0,0,0,1048576,0,0,0,0,0.0,580352.0,64,0x7f53aa404e80,49152,11534336,65536,0,0,0,16384,0,931521.0,32768.0,64,0x7ff4bf300e80,65536,64048,48,1440,32768,32768,0,64,0x7f0c6b402e80,0,65536,64480,48,1358,185497,0,0,16384.0,0.0,64,0x7fd299446e80,16384,393216,22671296,1650806,360448,163840,0,0,0.0,0.0,194093425213997,194093425237997 +1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f57df22ce80,0,131072,0,48,0,0,0,48,32768.0,16384.0,64,0x7f578ac6ce80,341200,231657,3384515,16384,25334508,16384,16384,32768,42649,42649,2136241.0,0.0,64,0x7f152ac70e80,49152,0,65536,32768,0,0,0,16384,0.0,0.0,64,0x7fb03f932e80,180224,114688,0,32768,32768,16384,16384,65536,0.0,0.0,64,0x7fecd7b64e80,0,0,0,1048576,0,0,0,0,0.0,615386.0,64,0x7f53aa404e80,49152,11534336,65536,0,0,0,16384,0,1137406.0,32768.0,64,0x7ff4bf300e80,65536,64048,48,1440,32768,32768,0,64,0x7f0c6b402e80,0,65536,65536,0,0,190996,0,0,16384.0,0.0,64,0x7fd299446e80,16384,393216,23016849,1129850,360448,163840,0,0,0.0,0.0,194093425324077,194093425343117 +2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f57df22ce80,0,131072,0,48,0,0,0,48,32768.0,16384.0,64,0x7f578ac6ce80,349200,233179,3382702,16384,24402589,16384,16384,32768,43649,43649,2132975.0,0.0,64,0x7f152ac70e80,49152,0,65536,32768,0,0,0,16384,0.0,0.0,64,0x7fb03f932e80,180224,114688,0,32768,32768,16384,16384,65536,0.0,0.0,64,0x7fecd7b64e80,0,0,0,1048576,0,0,0,0,0.0,626002.0,64,0x7f53aa404e80,49152,11534336,65536,0,0,0,16384,0,960706.0,32768.0,64,0x7ff4bf300e80,65536,64048,48,1440,32768,32768,0,64,0x7f0c6b402e80,0,65536,65536,0,0,190685,0,0,16384.0,0.0,64,0x7fd299446e80,16384,393216,22578421,1415558,360448,163840,0,0,0.0,0.0,194093425365197,194093425384237 diff --git a/tests/workloads/ipblocks_SQ_TA/MI100/sysinfo.csv b/tests/workloads/ipblocks_SQ_TA/MI100/sysinfo.csv index 3dbc427a3b..1f0a73a519 100644 --- a/tests/workloads/ipblocks_SQ_TA/MI100/sysinfo.csv +++ b/tests/workloads/ipblocks_SQ_TA/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -ipblocks_SQ_TA,./tests/vcopy -n 1048576 -b 256 -i 3,sq|ta,Fri Mar 1 16:43:22 2024 (CST),1,t006-003.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651240,,5.7.1-98,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +ipblocks_SQ_TA,./tests/vcopy -n 1048576 -b 256 -i 3,sq|ta,Thu 07 Mar 2024 01:05:51 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/ipblocks_SQ_TA/MI100/timestamps.csv b/tests/workloads/ipblocks_SQ_TA/MI100/timestamps.csv index 5f07204a97..b25ca7356b 100644 --- a/tests/workloads/ipblocks_SQ_TA/MI100/timestamps.csv +++ b/tests/workloads/ipblocks_SQ_TA/MI100/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,2810619,2810619,1048576,256,0,0,8,8,16,64,0x0,0x7f4b13652e80,2187696529431865,2187696529458971,2187696529483771,2187696529496115 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,2810619,2810619,1048576,256,0,0,8,8,16,64,0x0,0x7f4b13652e80,2187696529495684,2187696529666491,2187696529685051,2187696529685741 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,2810619,2810619,1048576,256,0,0,8,8,16,64,0x0,0x7f4b13652e80,2187696529696631,2187696529706491,2187696529725212,2187696529725846 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,114517,114517,1048576,256,0,0,8,8,16,64,0x0,0x7fb248498e80,194093425188607,194093425213997,194093425237997,194093425249272 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,114517,114517,1048576,256,0,0,8,8,16,64,0x0,0x7fb248498e80,194093425250645,194093425324077,194093425343117,194093425344372 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,114517,114517,1048576,256,0,0,8,8,16,64,0x0,0x7fb248498e80,194093425355103,194093425365197,194093425384237,194093425385330 diff --git a/tests/workloads/ipblocks_SQ_TA/MI200/SQ_IFETCH_LEVEL.csv b/tests/workloads/ipblocks_SQ_TA/MI200/SQ_IFETCH_LEVEL.csv new file mode 100644 index 0000000000..f089fe1f1f --- /dev/null +++ b/tests/workloads/ipblocks_SQ_TA/MI200/SQ_IFETCH_LEVEL.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,260873,260873,1048576,256,0,0,8,0,16,64,0x0,0x7fca39d14ec0,27599,27599,16384,65536,13477,1515696,197627776181140,197636385194490,197636385214970,197627792265678 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,260873,260873,1048576,256,0,0,8,0,16,64,0x0,0x7fca39d14ec0,41312,41312,16384,65536,9545,1048732,197627792287700,197636385234650,197636385250330,197627792597797 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,260873,260873,1048576,256,0,0,8,0,16,64,0x0,0x7fca39d14ec0,41112,41112,16384,65536,9748,1048736,197627792627844,197636385313530,197636385329850,197627792788167 diff --git a/tests/workloads/ipblocks_SQ_TA/MI200/SQ_INST_LEVEL_LDS.csv b/tests/workloads/ipblocks_SQ_TA/MI200/SQ_INST_LEVEL_LDS.csv new file mode 100644 index 0000000000..bb25873c2e --- /dev/null +++ b/tests/workloads/ipblocks_SQ_TA/MI200/SQ_INST_LEVEL_LDS.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,261074,261074,1048576,256,0,0,8,0,16,64,0x0,0x7ff069a4cec0,0,0,0,197628254734295,197636385194490,197636385214970,197628271117038 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,261074,261074,1048576,256,0,0,8,0,16,64,0x0,0x7ff069a4cec0,0,0,0,197628271143789,197636385234650,197636385250330,197628271426203 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,261074,261074,1048576,256,0,0,8,0,16,64,0x0,0x7ff069a4cec0,0,0,0,197628271452042,197636385313530,197636385329850,197628271607847 diff --git a/tests/workloads/ipblocks_SQ_TA/MI200/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/ipblocks_SQ_TA/MI200/SQ_INST_LEVEL_SMEM.csv new file mode 100644 index 0000000000..95b2cc313a --- /dev/null +++ b/tests/workloads/ipblocks_SQ_TA/MI200/SQ_INST_LEVEL_SMEM.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,261275,261275,1048576,256,0,0,8,0,16,64,0x0,0x7fa709da8ec0,65536,193830,21666056,197628730626066,197636385194490,197636385214970,197628746888422 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,261275,261275,1048576,256,0,0,8,0,16,64,0x0,0x7fa709da8ec0,65536,260130,29024072,197628746909942,197636385234650,197636385250330,197628747192296 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,261275,261275,1048576,256,0,0,8,0,16,64,0x0,0x7fa709da8ec0,65536,285904,32101264,197628747218776,197636385313530,197636385329850,197628747375483 diff --git a/tests/workloads/ipblocks_SQ_TA/MI200/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/ipblocks_SQ_TA/MI200/SQ_INST_LEVEL_VMEM.csv new file mode 100644 index 0000000000..e4f05f614b --- /dev/null +++ b/tests/workloads/ipblocks_SQ_TA/MI200/SQ_INST_LEVEL_VMEM.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,261476,261476,1048576,256,0,0,8,0,16,64,0x0,0x7fada3084ec0,32768,286992,32144468,197629205844033,197636385194490,197636385214970,197629221870281 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,261476,261476,1048576,256,0,0,8,0,16,64,0x0,0x7fada3084ec0,32768,586845,65733004,197629221888145,197636385234650,197636385250330,197629222196458 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,261476,261476,1048576,256,0,0,8,0,16,64,0x0,0x7fada3084ec0,32768,577854,64705004,197629222222728,197636385313530,197636385329850,197629222383442 diff --git a/tests/workloads/ipblocks_SQ_TA/MI200/SQ_LEVEL_WAVES.csv b/tests/workloads/ipblocks_SQ_TA/MI200/SQ_LEVEL_WAVES.csv new file mode 100644 index 0000000000..7a3eb7e45b --- /dev/null +++ b/tests/workloads/ipblocks_SQ_TA/MI200/SQ_LEVEL_WAVES.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,261677,261677,1048576,256,0,0,8,0,16,64,0x0,0x7f8418fd8ec0,26820,26820,10945,214568,16384,10185915,122068,0,41244244,197629680567754,197636385194490,197636385214970,197629696489424 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,261677,261677,1048576,256,0,0,8,0,16,64,0x0,0x7f8418fd8ec0,40790,40790,13103,326328,16384,18741062,218779,0,75437420,197629696518710,197636385234650,197636385250330,197629696813588 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,261677,261677,1048576,256,0,0,8,0,16,64,0x0,0x7f8418fd8ec0,40129,40129,13421,321040,16384,18585030,215100,0,74824632,197629696849115,197636385313530,197636385329850,197629697015940 diff --git a/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/SQ_IFETCH_LEVEL.txt b/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/SQ_IFETCH_LEVEL.txt new file mode 100644 index 0000000000..293092f641 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/SQ_IFETCH_LEVEL.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/SQ_INST_LEVEL_LDS.txt b/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/SQ_INST_LEVEL_LDS.txt new file mode 100644 index 0000000000..08439eedce --- /dev/null +++ b/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/SQ_INST_LEVEL_LDS.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt b/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt new file mode 100644 index 0000000000..6cca322d4e --- /dev/null +++ b/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt b/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt new file mode 100644 index 0000000000..e527ad31ba --- /dev/null +++ b/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/SQ_LEVEL_WAVES.txt b/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/SQ_LEVEL_WAVES.txt new file mode 100644 index 0000000000..3f8e04adb3 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/SQ_LEVEL_WAVES.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_0.txt b/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_0.txt new file mode 100644 index 0000000000..039e5a5e84 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_0.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_CVT SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU SQ_INSTS_VSKIPPED SQ_INSTS SQ_INSTS_VALU GRBM_COUNT GRBM_GUI_ACTIVE TA_TA_BUSY_sum TA_BUFFER_WAVEFRONTS_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_1.txt b/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_1.txt new file mode 100644 index 0000000000..9c89f3223a --- /dev/null +++ b/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_1.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_ADD_F16 SQ_INSTS_VALU_MUL_F16 SQ_INSTS_VALU_FMA_F16 SQ_INSTS_VALU_TRANS_F16 SQ_INSTS_VALU_ADD_F32 SQ_INSTS_VALU_MUL_F32 SQ_INSTS_VALU_FMA_F32 SQ_INSTS_VALU_TRANS_F32 TA_BUFFER_READ_WAVEFRONTS_sum TA_BUFFER_WRITE_WAVEFRONTS_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_10.txt b/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_10.txt new file mode 100644 index 0000000000..7053d4dce6 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_10.txt @@ -0,0 +1,5 @@ +pmc: SQC_TC_DATA_WRITE_REQ SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_11.txt b/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_11.txt new file mode 100644 index 0000000000..77ae8b461f --- /dev/null +++ b/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_11.txt @@ -0,0 +1,5 @@ +pmc: SQC_ICACHE_MISSES_DUPLICATE SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_12.txt b/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_12.txt new file mode 100644 index 0000000000..dfb2cf65e5 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_12.txt @@ -0,0 +1,5 @@ +pmc: SQC_DCACHE_REQ_READ_1 SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_2.txt b/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_2.txt new file mode 100644 index 0000000000..8a0653bf4b --- /dev/null +++ b/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_2.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_ADD_F64 SQ_INSTS_VALU_MUL_F64 SQ_INSTS_VALU_FMA_F64 SQ_INSTS_VALU_TRANS_F64 SQ_INSTS_VALU_INT32 SQ_INSTS_VALU_INT64 SQ_INSTS_SMEM SQ_INSTS_FLAT TA_BUFFER_ATOMIC_WAVEFRONTS_sum TA_BUFFER_TOTAL_CYCLES_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_3.txt b/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_3.txt new file mode 100644 index 0000000000..7564b0189e --- /dev/null +++ b/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_3.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG SQ_WAVE_CYCLES SQ_WAIT_ANY SQ_WAIT_INST_ANY TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_4.txt b/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_4.txt new file mode 100644 index 0000000000..ede375e72e --- /dev/null +++ b/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_4.txt @@ -0,0 +1,5 @@ +pmc: SQ_ACTIVE_INST_ANY SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU SQ_ACTIVE_INST_SCA TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_5.txt b/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_5.txt new file mode 100644 index 0000000000..0d34cf1d32 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_5.txt @@ -0,0 +1,5 @@ +pmc: SQ_ACTIVE_INST_EXP_GDS SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU SQ_THREAD_CYCLES_VALU TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_6.txt b/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_6.txt new file mode 100644 index 0000000000..478ea17284 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_6.txt @@ -0,0 +1,5 @@ +pmc: SQ_IFETCH SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_7.txt b/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_7.txt new file mode 100644 index 0000000000..eb72f3a2c7 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_7.txt @@ -0,0 +1,5 @@ +pmc: SQ_WAVES_LT_32 SQ_WAVES_LT_16 SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_8.txt b/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_8.txt new file mode 100644 index 0000000000..f01548a76d --- /dev/null +++ b/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_8.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM_NORM SQ_INSTS_MFMA SQ_INSTS_VALU_MFMA_I8 SQ_INSTS_VALU_MFMA_F16 SQ_INSTS_VALU_MFMA_BF16 SQ_INSTS_VALU_MFMA_F32 SQ_INSTS_VALU_MFMA_F64 SQ_VALU_MFMA_BUSY_CYCLES + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_9.txt b/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_9.txt new file mode 100644 index 0000000000..e9663fc4a5 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_9.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_FLAT_LDS_ONLY SQ_INSTS_VALU_MFMA_MOPS_I8 SQ_INSTS_VALU_MFMA_MOPS_F16 SQ_INSTS_VALU_MFMA_MOPS_BF16 SQ_INSTS_VALU_MFMA_MOPS_F32 SQ_INSTS_VALU_MFMA_MOPS_F64 SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/timestamps.txt b/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/timestamps.txt new file mode 100644 index 0000000000..676cca1b80 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_TA/MI200/perfmon/timestamps.txt @@ -0,0 +1,5 @@ +pmc: + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SQ_TA/MI200/pmc_perf.csv b/tests/workloads/ipblocks_SQ_TA/MI200/pmc_perf.csv new file mode 100644 index 0000000000..53a9f7675e --- /dev/null +++ b/tests/workloads/ipblocks_SQ_TA/MI200/pmc_perf.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,wave_size_1,obj_1,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_2,obj_2,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,wave_size_3,obj_3,SQ_ACTIVE_INST_ANY,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,wave_size_4,obj_4,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,wave_size_5,obj_5,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,wave_size_6,obj_6,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_7,obj_7,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,wave_size_8,obj_8,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,wave_size_9,obj_9,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,wave_size_10,obj_10,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,wave_size_11,obj_11,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_12,obj_12,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f7151634ec0,0,0,1048576,0,0,0,0,0,16384.0,0.0,64,0x7f61b0404ec0,0,0,0,224,0,65536,64209,56,64,0x7f84a35c4ec0,65536,0,0,0,16384,16384,0,0,32768.0,16384.0,64,0x7fa133074ec0,344064,226464,134756,1702621,0,0,163840,114688,259449.0,32768.0,64,0x7ff1a5bd8ec0,0,16384,16384,32768,49152,0,393216,163840,27784,27784,1038475.0,0.0,64,0x7fb51c518ec0,0,0,0,16384,16384,10612853,9512844,755945,0.0,0.0,64,0x7fdf34ae4ec0,32768,32768,0,64,0x7f4c20ba8ec0,0,32768,32768,16384,16384,65536,49152,10485760,0.0,225616.0,64,0x7f0416f28ec0,0,0,0,0,114688,0,65536,32768,0.0,0.0,64,0x7fdd9bf3cec0,0,0,0,0,0,0,0,0,0.0,0.0,64,0x7f0a3d084ec0,0,0,0,0,0,0,168,56,64,0x7fb675a04ec0,1308,119573,0,0,65536,63800,56,1680,64,0x7f142814cec0,131072,0,0,0,0,0,0,0,197636385194490,197636385214970 +1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f7151634ec0,0,0,1048576,0,0,0,0,0,16384.0,0.0,64,0x7f61b0404ec0,0,0,0,56,0,65536,65536,0,64,0x7f84a35c4ec0,65536,0,0,0,16384,16384,0,0,32768.0,16384.0,64,0x7fa133074ec0,344064,299936,206150,2558989,0,0,163840,114688,446443.0,32768.0,64,0x7ff1a5bd8ec0,0,16384,16384,32768,49152,0,393216,163840,38484,38484,1736112.0,0.0,64,0x7fb51c518ec0,0,0,0,16384,16384,17686698,17104122,238512,0.0,0.0,64,0x7fdf34ae4ec0,32768,32768,0,64,0x7f4c20ba8ec0,0,32768,32768,16384,16384,65536,49152,10485760,0.0,470988.0,64,0x7f0416f28ec0,0,0,0,0,114688,0,65536,32768,0.0,0.0,64,0x7fdd9bf3cec0,0,0,0,0,0,0,0,0,0.0,0.0,64,0x7f0a3d084ec0,0,0,0,0,0,0,0,56,64,0x7fb675a04ec0,0,192083,0,0,65536,63800,56,1680,64,0x7f142814cec0,131072,0,0,0,0,0,0,0,197636385234650,197636385250330 +2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f7151634ec0,0,0,1048576,0,0,0,0,0,16384.0,0.0,64,0x7f61b0404ec0,0,0,0,56,0,65536,65536,0,64,0x7f84a35c4ec0,65536,0,0,0,16384,16384,0,0,32768.0,16384.0,64,0x7fa133074ec0,344064,337144,231351,2886370,0,0,163840,114688,625844.0,32768.0,64,0x7ff1a5bd8ec0,0,16384,16384,32768,49152,0,393216,163840,40532,40532,1638787.0,0.0,64,0x7fb51c518ec0,0,0,0,16384,16384,19861626,18505828,1011734,0.0,0.0,64,0x7fdf34ae4ec0,32768,32768,0,64,0x7f4c20ba8ec0,0,32768,32768,16384,16384,65536,49152,10485760,0.0,492901.0,64,0x7f0416f28ec0,0,0,0,0,114688,0,65536,32768,0.0,0.0,64,0x7fdd9bf3cec0,0,0,0,0,0,0,0,0,0.0,0.0,64,0x7f0a3d084ec0,0,0,0,0,0,0,0,56,64,0x7fb675a04ec0,0,190677,0,0,65536,63800,56,1680,64,0x7f142814cec0,131072,0,0,0,0,0,0,0,197636385313530,197636385329850 diff --git a/tests/workloads/ipblocks_SQ_TA/MI200/roofline.csv b/tests/workloads/ipblocks_SQ_TA/MI200/roofline.csv new file mode 100644 index 0000000000..e1bb33e76c --- /dev/null +++ b/tests/workloads/ipblocks_SQ_TA/MI200/roofline.csv @@ -0,0 +1,5 @@ +device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh +0,1388.9526,1388.4111,1389.4941,5015.6484,5012.5898,5018.707,9223.4463,9222.7646,9224.1279,18051.945,18050.785,18053.105,20935.199,20875.307,20995.092,20264.828,20264.057,20265.6,170420.14,170416.5,170423.78,164861.64,164856.98,164866.3,41416.578,41416.203,41416.953,41476.453,41475.875,41477.031,166325.31,165837.67,166812.95 +1,1389.5095,1388.9309,1390.0881,5026.0811,5023.9771,5028.1851,9233.0938,9232.4082,9233.7793,18087.664,18083.631,18091.697,20970.012,20903.859,21036.164,20289.217,20288.719,20289.715,170813.81,170809.28,170818.34,165056.77,165053.3,165060.23,41467.969,41467.148,41468.789,41530.449,41529.344,41531.555,166829.2,166826.05,166832.36 +2,1388.5624,1388.0015,1389.1233,5035.5742,5033.3438,5037.8047,9259.7334,9258.9971,9260.4697,18101.963,18101.021,18102.904,21044.383,21044.031,21044.734,20349.049,20348.586,20349.512,171079.44,171075.62,171083.25,165481.09,165477.31,165484.88,41577.289,41576.395,41578.184,41631.129,41630.27,41631.988,166923,166338.03,167507.97 +3,1389.2155,1388.5825,1389.8484,5032.1416,5030.8301,5033.4531,9240.2666,9239.7314,9240.8018,18025.797,18022.486,18029.107,21033.242,21032.709,21033.775,20313.852,20313.191,20314.512,171032.44,171029.55,171035.33,165228.91,165224.12,165233.69,41438.621,41286.715,41590.527,41581.562,41580.84,41582.285,167020.28,167018.2,167022.36 diff --git a/tests/workloads/ipblocks_SQ_TA/MI200/sysinfo.csv b/tests/workloads/ipblocks_SQ_TA/MI200/sysinfo.csv new file mode 100644 index 0000000000..21fd52dabf --- /dev/null +++ b/tests/workloads/ipblocks_SQ_TA/MI200/sysinfo.csv @@ -0,0 +1,2 @@ +workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd +ipblocks_SQ_TA,./sample/vcopy -n 1048576 -b 256 -i 3,sq|ta|roofline,Thu 07 Mar 2024 02:04:54 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/ipblocks_SQ_TA/MI200/timestamps.csv b/tests/workloads/ipblocks_SQ_TA/MI200/timestamps.csv new file mode 100644 index 0000000000..8e87960e7e --- /dev/null +++ b/tests/workloads/ipblocks_SQ_TA/MI200/timestamps.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,264493,264493,1048576,256,0,0,8,0,16,64,0x0,0x7f93825d8ec0,197636385166327,197636385194490,197636385214970,197636385228815 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,264493,264493,1048576,256,0,0,8,0,16,64,0x0,0x7f93825d8ec0,197636385226540,197636385234650,197636385250330,197636385312433 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,264493,264493,1048576,256,0,0,8,0,16,64,0x0,0x7f93825d8ec0,197636385260815,197636385313530,197636385329850,197636385331229 diff --git a/tests/workloads/ipblocks_TA/MI100/pmc_dispatch_info.csv b/tests/workloads/ipblocks_TA/MI100/pmc_dispatch_info.csv new file mode 100644 index 0000000000..17300ae9af --- /dev/null +++ b/tests/workloads/ipblocks_TA/MI100/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) ",2 +1,"vecCopy(double*, double*, double*, int, int) ",2 +2,"vecCopy(double*, double*, double*, int, int) ",2 diff --git a/tests/workloads/ipblocks_TA/MI100/pmc_perf.csv b/tests/workloads/ipblocks_TA/MI100/pmc_perf.csv index e830b897a8..6ed25350c3 100644 --- a/tests/workloads/ipblocks_TA/MI100/pmc_perf.csv +++ b/tests/workloads/ipblocks_TA/MI100/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,wave_size_1,obj_1,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,wave_size_2,obj_2,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,wave_size_3,obj_3,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,wave_size_4,obj_4,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,wave_size_5,obj_5,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,GRBM_COUNT,GRBM_GUI_ACTIVE,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,wave_size_6,obj_6,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,wave_size_7,obj_7,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f8310990e80,0.0,0.0,64,0x7fe4e625ce80,16384.0,0.0,64,0x7f3028aeee80,0.0,739906.0,64,0x7fb0760dae80,0.0,0.0,64,0x7ff6733ece80,32768.0,16384.0,64,0x7f879b358e80,394736,241131,3510779,16384,25835097,49341,49341,2187759.0,0.0,64,0x7f1cfd254e80,1050684.0,32768.0,64,0x7f62e38cae80,0.0,0.0,2187891575753536,2187891575777536 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f8310990e80,0.0,0.0,64,0x7fe4e625ce80,16384.0,0.0,64,0x7f3028aeee80,0.0,695999.0,64,0x7fb0760dae80,0.0,0.0,64,0x7ff6733ece80,32768.0,16384.0,64,0x7f879b358e80,348144,232072,3377797,16384,23740819,43517,43517,2100539.0,0.0,64,0x7f1cfd254e80,1106216.0,32768.0,64,0x7f62e38cae80,0.0,0.0,2187891575877376,2187891575896256 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f8310990e80,0.0,0.0,64,0x7fe4e625ce80,16384.0,0.0,64,0x7f3028aeee80,0.0,762480.0,64,0x7fb0760dae80,0.0,0.0,64,0x7ff6733ece80,32768.0,16384.0,64,0x7f879b358e80,344880,231085,3357778,16384,24683181,43109,43109,2205144.0,0.0,64,0x7f1cfd254e80,950368.0,32768.0,64,0x7f62e38cae80,0.0,0.0,2187891575919296,2187891575937696 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,wave_size_1,obj_1,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,wave_size_2,obj_2,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,wave_size_3,obj_3,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,wave_size_4,obj_4,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,wave_size_5,obj_5,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,wave_size_6,obj_6,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,wave_size_7,obj_7,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,GRBM_COUNT,GRBM_GUI_ACTIVE,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fea74eb4e80,0.0,0.0,64,0x7ff137308e80,841565.0,32768.0,64,0x7f786c57ce80,0.0,0.0,64,0x7f4bd9d10e80,16384.0,0.0,64,0x7fb094e62e80,32768.0,16384.0,64,0x7f54f69c8e80,0.0,0.0,64,0x7fbfa0282e80,0.0,593523.0,64,0x7f90dee3ae80,381672,234420,3428747,16384,25273222,47708,47708,2052968.0,0.0,194308620288632,194308620312472 +1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fea74eb4e80,0.0,0.0,64,0x7ff137308e80,917516.0,32768.0,64,0x7f786c57ce80,0.0,0.0,64,0x7f4bd9d10e80,16384.0,0.0,64,0x7fb094e62e80,32768.0,16384.0,64,0x7f54f69c8e80,0.0,0.0,64,0x7fbfa0282e80,0.0,619240.0,64,0x7f90dee3ae80,346216,231235,3364080,16384,24621168,43276,43276,2118458.0,0.0,194308620481592,194308620501272 +2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fea74eb4e80,0.0,0.0,64,0x7ff137308e80,868090.0,32768.0,64,0x7f786c57ce80,0.0,0.0,64,0x7f4bd9d10e80,16384.0,0.0,64,0x7fb094e62e80,32768.0,16384.0,64,0x7f54f69c8e80,0.0,0.0,64,0x7fbfa0282e80,0.0,558978.0,64,0x7f90dee3ae80,336168,225346,3302853,16384,24110920,42020,42020,2048198.0,0.0,194308620522712,194308620541432 diff --git a/tests/workloads/ipblocks_TA/MI100/sysinfo.csv b/tests/workloads/ipblocks_TA/MI100/sysinfo.csv index 8924a478d2..60476624be 100644 --- a/tests/workloads/ipblocks_TA/MI100/sysinfo.csv +++ b/tests/workloads/ipblocks_TA/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -ipblocks_TA,./tests/vcopy -n 1048576 -b 256 -i 3,ta,Fri Mar 1 16:46:42 2024 (CST),1,t006-003.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651240,,5.7.1-98,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +ipblocks_TA,./tests/vcopy -n 1048576 -b 256 -i 3,ta,Thu 07 Mar 2024 01:09:29 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/ipblocks_TA/MI100/timestamps.csv b/tests/workloads/ipblocks_TA/MI100/timestamps.csv index dcc48e7e9b..6e31e34042 100644 --- a/tests/workloads/ipblocks_TA/MI100/timestamps.csv +++ b/tests/workloads/ipblocks_TA/MI100/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,2877286,2877286,1048576,256,0,0,8,8,16,64,0x0,0x7efdd9dd8e80,2187891575724724,2187891575753536,2187891575777536,2187891575792181 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,2877286,2877286,1048576,256,0,0,8,8,16,64,0x0,0x7efdd9dd8e80,2187891575792832,2187891575877376,2187891575896256,2187891575897739 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,2877286,2877286,1048576,256,0,0,8,8,16,64,0x0,0x7efdd9dd8e80,2187891575909752,2187891575919296,2187891575937696,2187891575945048 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,183593,183593,1048576,256,0,0,8,8,16,64,0x0,0x7f9431e1ce80,194308620262246,194308620288632,194308620312472,194308620326317 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,183593,183593,1048576,256,0,0,8,8,16,64,0x0,0x7f9431e1ce80,194308620325285,194308620481592,194308620501272,194308620502911 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,183593,183593,1048576,256,0,0,8,8,16,64,0x0,0x7f9431e1ce80,194308620514063,194308620522712,194308620541432,194308620542998 diff --git a/tests/workloads/ipblocks_TA/MI200/perfmon/pmc_perf_0.txt b/tests/workloads/ipblocks_TA/MI200/perfmon/pmc_perf_0.txt new file mode 100644 index 0000000000..96b3270b4c --- /dev/null +++ b/tests/workloads/ipblocks_TA/MI200/perfmon/pmc_perf_0.txt @@ -0,0 +1,5 @@ +pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_WAVES SQ_WAVE_CYCLES GRBM_COUNT GRBM_GUI_ACTIVE TA_TA_BUSY_sum TA_BUFFER_WAVEFRONTS_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_TA/MI200/perfmon/pmc_perf_1.txt b/tests/workloads/ipblocks_TA/MI200/perfmon/pmc_perf_1.txt new file mode 100644 index 0000000000..a397846c1a --- /dev/null +++ b/tests/workloads/ipblocks_TA/MI200/perfmon/pmc_perf_1.txt @@ -0,0 +1,5 @@ +pmc: TA_BUFFER_READ_WAVEFRONTS_sum TA_BUFFER_WRITE_WAVEFRONTS_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_TA/MI200/perfmon/pmc_perf_2.txt b/tests/workloads/ipblocks_TA/MI200/perfmon/pmc_perf_2.txt new file mode 100644 index 0000000000..e037603986 --- /dev/null +++ b/tests/workloads/ipblocks_TA/MI200/perfmon/pmc_perf_2.txt @@ -0,0 +1,5 @@ +pmc: TA_BUFFER_ATOMIC_WAVEFRONTS_sum TA_BUFFER_TOTAL_CYCLES_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_TA/MI200/perfmon/pmc_perf_3.txt b/tests/workloads/ipblocks_TA/MI200/perfmon/pmc_perf_3.txt new file mode 100644 index 0000000000..ee090ea5d3 --- /dev/null +++ b/tests/workloads/ipblocks_TA/MI200/perfmon/pmc_perf_3.txt @@ -0,0 +1,5 @@ +pmc: TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_TA/MI200/perfmon/pmc_perf_4.txt b/tests/workloads/ipblocks_TA/MI200/perfmon/pmc_perf_4.txt new file mode 100644 index 0000000000..b4e096fbcc --- /dev/null +++ b/tests/workloads/ipblocks_TA/MI200/perfmon/pmc_perf_4.txt @@ -0,0 +1,5 @@ +pmc: TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_TA/MI200/perfmon/pmc_perf_5.txt b/tests/workloads/ipblocks_TA/MI200/perfmon/pmc_perf_5.txt new file mode 100644 index 0000000000..8f2eb4c560 --- /dev/null +++ b/tests/workloads/ipblocks_TA/MI200/perfmon/pmc_perf_5.txt @@ -0,0 +1,5 @@ +pmc: TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_TA/MI200/perfmon/pmc_perf_6.txt b/tests/workloads/ipblocks_TA/MI200/perfmon/pmc_perf_6.txt new file mode 100644 index 0000000000..340f00c69e --- /dev/null +++ b/tests/workloads/ipblocks_TA/MI200/perfmon/pmc_perf_6.txt @@ -0,0 +1,5 @@ +pmc: TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_TA/MI200/perfmon/pmc_perf_7.txt b/tests/workloads/ipblocks_TA/MI200/perfmon/pmc_perf_7.txt new file mode 100644 index 0000000000..7befec94eb --- /dev/null +++ b/tests/workloads/ipblocks_TA/MI200/perfmon/pmc_perf_7.txt @@ -0,0 +1,5 @@ +pmc: TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_TA/MI200/perfmon/timestamps.txt b/tests/workloads/ipblocks_TA/MI200/perfmon/timestamps.txt new file mode 100644 index 0000000000..676cca1b80 --- /dev/null +++ b/tests/workloads/ipblocks_TA/MI200/perfmon/timestamps.txt @@ -0,0 +1,5 @@ +pmc: + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_TA/MI200/pmc_perf.csv b/tests/workloads/ipblocks_TA/MI200/pmc_perf.csv new file mode 100644 index 0000000000..dc931e5cf9 --- /dev/null +++ b/tests/workloads/ipblocks_TA/MI200/pmc_perf.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,wave_size_1,obj_1,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,wave_size_2,obj_2,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,wave_size_3,obj_3,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,wave_size_4,obj_4,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,wave_size_5,obj_5,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,wave_size_6,obj_6,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,wave_size_7,obj_7,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,GRBM_COUNT,GRBM_GUI_ACTIVE,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7ff436634ec0,0.0,226324.0,64,0x7fe878d30ec0,0.0,0.0,64,0x7fa24dbacec0,32768.0,16384.0,64,0x7fbdc1da0ec0,0.0,0.0,64,0x7f724f8e4ec0,16384.0,0.0,64,0x7f475bd44ec0,0.0,0.0,64,0x7f559dbb0ec0,255549.0,32768.0,64,0x7fc234e30ec0,219008,126900,1608328,16384,10694012,27375,27375,1045887.0,0.0,199451887941398,199451887961558 +1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7ff436634ec0,0.0,469789.0,64,0x7fe878d30ec0,0.0,0.0,64,0x7fa24dbacec0,32768.0,16384.0,64,0x7fbdc1da0ec0,0.0,0.0,64,0x7f724f8e4ec0,16384.0,0.0,64,0x7f475bd44ec0,0.0,0.0,64,0x7f559dbb0ec0,521967.0,32768.0,64,0x7fc234e30ec0,296264,205468,2560009,16384,17525786,37032,37032,1715803.0,0.0,199451888050358,199451888066678 +2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7ff436634ec0,0.0,442860.0,64,0x7fe878d30ec0,0.0,0.0,64,0x7fa24dbacec0,32768.0,16384.0,64,0x7fbdc1da0ec0,0.0,0.0,64,0x7f724f8e4ec0,16384.0,0.0,64,0x7f475bd44ec0,0.0,0.0,64,0x7f559dbb0ec0,679685.0,32768.0,64,0x7fc234e30ec0,332312,220734,2755623,16384,19165388,41538,41538,1709964.0,0.0,199451888085398,199451888101078 diff --git a/tests/workloads/ipblocks_TA/MI200/roofline.csv b/tests/workloads/ipblocks_TA/MI200/roofline.csv new file mode 100644 index 0000000000..fc0c9a2c2b --- /dev/null +++ b/tests/workloads/ipblocks_TA/MI200/roofline.csv @@ -0,0 +1,5 @@ +device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh +0,1389.2339,1388.6835,1389.7843,5014.834,5011.9429,5017.7251,9222.5566,9221.916,9223.1973,18050.242,18049.102,18051.383,20932.727,20872.451,20993.002,20261.408,20260.77,20262.047,170379.27,170375.23,170383.3,164850,164845.41,164854.59,41415.238,41414.723,41415.754,41472.098,41471.441,41472.754,166318.23,165827.38,166809.09 +1,1389.1729,1388.5649,1389.7808,5026.5298,5024.5435,5028.5161,9232.5303,9231.9238,9233.1367,18090.807,18087.168,18094.445,20972.15,20905.209,21039.092,20293.615,20292.992,20294.238,170840.88,170835.75,170846,165114.09,165110.69,165117.5,41484.23,41483.559,41484.902,41542.656,41541.648,41543.664,166878.97,166875.61,166882.33 +2,1388.4468,1387.9023,1388.9912,5034.792,5032.4917,5037.0923,9261.7051,9261.0332,9262.377,18103.418,18102.588,18104.248,21046.811,21046.393,21047.229,20351.721,20351.152,20352.289,171101.66,171098.2,171105.11,165474.23,165470.09,165478.38,41578.957,41578.066,41579.848,41628.684,41627.777,41629.59,166910.78,166309.39,167512.17 +3,1388.8716,1388.2726,1389.4706,5032.1841,5030.8164,5033.5518,9241.4023,9240.6934,9242.1113,18022.926,18019.047,18026.805,21037.811,21037.062,21038.559,20314.686,20314.041,20315.33,171043.86,171039.8,171047.92,165241.16,165235.89,165246.42,41440.902,41287.016,41594.789,41585.141,41584.398,41585.883,167028.31,167025.28,167031.34 diff --git a/tests/workloads/ipblocks_TA/MI200/sysinfo.csv b/tests/workloads/ipblocks_TA/MI200/sysinfo.csv new file mode 100644 index 0000000000..bfa856c146 --- /dev/null +++ b/tests/workloads/ipblocks_TA/MI200/sysinfo.csv @@ -0,0 +1,2 @@ +workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd +ipblocks_TA,./sample/vcopy -n 1048576 -b 256 -i 3,ta|roofline,Thu 07 Mar 2024 02:35:15 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/ipblocks_TA/MI200/timestamps.csv b/tests/workloads/ipblocks_TA/MI200/timestamps.csv new file mode 100644 index 0000000000..bd392f6583 --- /dev/null +++ b/tests/workloads/ipblocks_TA/MI200/timestamps.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,345465,345465,1048576,256,0,0,8,0,16,64,0x0,0x7f35bbee8ec0,199451887917687,199451887941398,199451887961558,199451887973773 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,345465,345465,1048576,256,0,0,8,0,16,64,0x0,0x7f35bbee8ec0,199451887972370,199451888050358,199451888066678,199451888068051 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,345465,345465,1048576,256,0,0,8,0,16,64,0x0,0x7f35bbee8ec0,199451888077589,199451888085398,199451888101078,199451888102156 diff --git a/tests/workloads/ipblocks_TCC/MI100/pmc_dispatch_info.csv b/tests/workloads/ipblocks_TCC/MI100/pmc_dispatch_info.csv new file mode 100644 index 0000000000..17300ae9af --- /dev/null +++ b/tests/workloads/ipblocks_TCC/MI100/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) ",2 +1,"vecCopy(double*, double*, double*, int, int) ",2 +2,"vecCopy(double*, double*, double*, int, int) ",2 diff --git a/tests/workloads/ipblocks_TCC/MI100/pmc_perf.csv b/tests/workloads/ipblocks_TCC/MI100/pmc_perf.csv index da1227b74d..1d10766679 100644 --- a/tests/workloads/ipblocks_TCC/MI100/pmc_perf.csv +++ b/tests/workloads/ipblocks_TCC/MI100/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCC_EA_ATOMIC_LEVEL_sum,wave_size_1,obj_1,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_2,obj_2,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_3,obj_3,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_4,obj_4,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_5,obj_5,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_6,obj_6,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_7,obj_7,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_8,obj_8,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_9,obj_9,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_10,obj_10,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,GRBM_COUNT,GRBM_GUI_ACTIVE,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f4a126dae80,0.0,64,0x7f67b2dfce80,131418.0,0.0,684.0,131417.0,64,0x7faa93444e80,48.0,264.0,0.0,262288.0,64,0x7ff1394d2e80,0.0,0.0,15322.0,115612.0,64,0x7f35a3ca8e80,86617.0,44455.0,131111.0,0.0,64,0x7f0a931d0e80,0.0,0.0,114048404.0,63240274.0,64,0x7f9d24486e80,262674.0,0.0,188.0,262486.0,64,0x7f74b9a54e80,77627.0,0.0,0.0,77627.0,64,0x7f2e081cee80,131528.0,131072.0,0.0,131104.0,64,0x7f9508dece80,131072.0,131072.0,0.0,131072.0,64,0x7fc888f7ae80,384104,234705,16384,48012,48012,1536384.0,983162.0,0.0,0.0,2187654326218795,2187654326242955 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f4a126dae80,0.0,64,0x7f67b2dfce80,131418.0,0.0,690.0,131417.0,64,0x7faa93444e80,48.0,270.0,0.0,262144.0,64,0x7ff1394d2e80,0.0,0.0,31873.0,110796.0,64,0x7f35a3ca8e80,86823.0,0.0,131112.0,0.0,64,0x7f0a931d0e80,0.0,0.0,106998604.0,48246088.0,64,0x7f9d24486e80,262535.0,0.0,47.0,262488.0,64,0x7f74b9a54e80,75464.0,0.0,0.0,75464.0,64,0x7f2e081cee80,131418.0,131072.0,0.0,86516.0,64,0x7f9508dece80,87433.0,87433.0,0.0,87433.0,64,0x7fc888f7ae80,337704,227034,16384,42212,42212,1350784.0,821069.0,0.0,0.0,2187654326432235,2187654326451435 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f4a126dae80,0.0,64,0x7f67b2dfce80,131418.0,0.0,690.0,131417.0,64,0x7faa93444e80,48.0,270.0,0.0,262144.0,64,0x7ff1394d2e80,0.0,0.0,39556.0,116520.0,64,0x7f35a3ca8e80,86457.0,0.0,131110.0,0.0,64,0x7f0a931d0e80,0.0,0.0,121343430.0,49595715.0,64,0x7f9d24486e80,262536.0,0.0,47.0,262489.0,64,0x7f74b9a54e80,64879.0,0.0,0.0,64879.0,64,0x7f2e081cee80,131395.0,131072.0,0.0,86368.0,64,0x7f9508dece80,87205.0,87205.0,0.0,87205.0,64,0x7fc888f7ae80,337544,226922,16384,42192,42192,1350144.0,823283.0,0.0,0.0,2187654326473355,2187654326492715 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_1,obj_1,TCC_EA_ATOMIC_LEVEL_sum,wave_size_2,obj_2,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_3,obj_3,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_4,obj_4,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,GRBM_COUNT,GRBM_GUI_ACTIVE,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_5,obj_5,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_6,obj_6,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_7,obj_7,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_8,obj_8,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_9,obj_9,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_10,obj_10,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fd7b2a82e80,131072.0,131072.0,0.0,131072.0,64,0x7f7014f62e80,0.0,64,0x7f44b3226e80,131480.0,131072.0,0.0,131104.0,64,0x7ff185560e80,86770.0,44302.0,131112.0,0.0,64,0x7fae2a094e80,378088,232735,16384,47260,47260,1512320.0,967311.0,0.0,0.0,64,0x7fbac7f20e80,131340.0,0.0,528.0,131339.0,64,0x7f3d3e006e80,262667.0,0.0,188.0,262479.0,64,0x7fb39b6f0e80,0.0,0.0,44974.0,110378.0,64,0x7f58921a2e80,0.0,0.0,131706455.0,62205335.0,64,0x7ff374bcce80,48.0,232.0,0.0,262288.0,64,0x7f871fd60e80,70997.0,0.0,0.0,70997.0,194049837194911,194049837219071 +1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fd7b2a82e80,86461.0,86461.0,0.0,86461.0,64,0x7f7014f62e80,0.0,64,0x7f44b3226e80,131336.0,131072.0,0.0,87201.0,64,0x7ff185560e80,86334.0,0.0,131112.0,0.0,64,0x7fae2a094e80,345920,230957,16384,43239,43239,1383648.0,824837.0,0.0,0.0,64,0x7fbac7f20e80,131342.0,0.0,538.0,131341.0,64,0x7f3d3e006e80,262574.0,0.0,47.0,262527.0,64,0x7fb39b6f0e80,0.0,0.0,73288.0,143478.0,64,0x7f58921a2e80,0.0,0.0,135537432.0,48703834.0,64,0x7ff374bcce80,48.0,273.0,0.0,262144.0,64,0x7f871fd60e80,57845.0,0.0,0.0,57845.0,194049837306111,194049837325471 +2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fd7b2a82e80,86761.0,86761.0,0.0,86761.0,64,0x7f7014f62e80,0.0,64,0x7f44b3226e80,131354.0,131072.0,0.0,87437.0,64,0x7ff185560e80,86609.0,0.0,131112.0,0.0,64,0x7fae2a094e80,342752,228195,16384,42843,42843,1370976.0,808889.0,0.0,0.0,64,0x7fbac7f20e80,131342.0,0.0,538.0,131341.0,64,0x7f3d3e006e80,262567.0,0.0,47.0,262520.0,64,0x7fb39b6f0e80,0.0,0.0,63293.0,128704.0,64,0x7f58921a2e80,0.0,0.0,137180155.0,48683210.0,64,0x7ff374bcce80,48.0,244.0,0.0,262144.0,64,0x7f871fd60e80,69388.0,0.0,0.0,69388.0,194049837347391,194049837366591 diff --git a/tests/workloads/ipblocks_TCC/MI100/sysinfo.csv b/tests/workloads/ipblocks_TCC/MI100/sysinfo.csv index 09e3faf66a..466aef0b4b 100644 --- a/tests/workloads/ipblocks_TCC/MI100/sysinfo.csv +++ b/tests/workloads/ipblocks_TCC/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -ipblocks_TCC,./tests/vcopy -n 1048576 -b 256 -i 3,tcc,Fri Mar 1 16:42:44 2024 (CST),1,t006-003.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651240,,5.7.1-98,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +ipblocks_TCC,./tests/vcopy -n 1048576 -b 256 -i 3,tcc,Thu 07 Mar 2024 01:05:09 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/ipblocks_TCC/MI100/timestamps.csv b/tests/workloads/ipblocks_TCC/MI100/timestamps.csv index 7d872982b1..90b1d3d4b7 100644 --- a/tests/workloads/ipblocks_TCC/MI100/timestamps.csv +++ b/tests/workloads/ipblocks_TCC/MI100/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,2796122,2796122,1048576,256,0,0,8,8,16,64,0x0,0x7fe7a7106e80,2187654326192031,2187654326218795,2187654326242955,2187654326254879 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,2796122,2796122,1048576,256,0,0,8,8,16,64,0x0,0x7fe7a7106e80,2187654326256071,2187654326432235,2187654326451435,2187654326452640 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,2796122,2796122,1048576,256,0,0,8,8,16,64,0x0,0x7fe7a7106e80,2187654326463450,2187654326473355,2187654326492715,2187654326493877 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,100093,100093,1048576,256,0,0,8,8,16,64,0x0,0x7f1bd1faae80,194049837169557,194049837194911,194049837219071,194049837231976 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,100093,100093,1048576,256,0,0,8,8,16,64,0x0,0x7f1bd1faae80,194049837232156,194049837306111,194049837325471,194049837326685 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,100093,100093,1048576,256,0,0,8,8,16,64,0x0,0x7f1bd1faae80,194049837337425,194049837347391,194049837366591,194049837367592 diff --git a/tests/workloads/ipblocks_TCC/MI200/perfmon/pmc_perf_0.txt b/tests/workloads/ipblocks_TCC/MI200/perfmon/pmc_perf_0.txt new file mode 100644 index 0000000000..f504436b1b --- /dev/null +++ b/tests/workloads/ipblocks_TCC/MI200/perfmon/pmc_perf_0.txt @@ -0,0 +1,5 @@ +pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES GRBM_COUNT GRBM_GUI_ACTIVE TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_TCC/MI200/perfmon/pmc_perf_1.txt b/tests/workloads/ipblocks_TCC/MI200/perfmon/pmc_perf_1.txt new file mode 100644 index 0000000000..34fff42539 --- /dev/null +++ b/tests/workloads/ipblocks_TCC/MI200/perfmon/pmc_perf_1.txt @@ -0,0 +1,5 @@ +pmc: TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_TCC/MI200/perfmon/pmc_perf_2.txt b/tests/workloads/ipblocks_TCC/MI200/perfmon/pmc_perf_2.txt new file mode 100644 index 0000000000..608725e21f --- /dev/null +++ b/tests/workloads/ipblocks_TCC/MI200/perfmon/pmc_perf_2.txt @@ -0,0 +1,5 @@ +pmc: TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_TCC/MI200/perfmon/pmc_perf_3.txt b/tests/workloads/ipblocks_TCC/MI200/perfmon/pmc_perf_3.txt new file mode 100644 index 0000000000..66b74f5c52 --- /dev/null +++ b/tests/workloads/ipblocks_TCC/MI200/perfmon/pmc_perf_3.txt @@ -0,0 +1,5 @@ +pmc: TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_TCC/MI200/perfmon/pmc_perf_4.txt b/tests/workloads/ipblocks_TCC/MI200/perfmon/pmc_perf_4.txt new file mode 100644 index 0000000000..2307e8bceb --- /dev/null +++ b/tests/workloads/ipblocks_TCC/MI200/perfmon/pmc_perf_4.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_WRREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WR_UNCACHED_32B_sum TCC_EA_WRREQ_DRAM_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_TCC/MI200/perfmon/pmc_perf_5.txt b/tests/workloads/ipblocks_TCC/MI200/perfmon/pmc_perf_5.txt new file mode 100644 index 0000000000..1e789a2dc1 --- /dev/null +++ b/tests/workloads/ipblocks_TCC/MI200/perfmon/pmc_perf_5.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_WRREQ_STALL_sum TCC_EA_RDREQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RD_UNCACHED_32B_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_TCC/MI200/perfmon/pmc_perf_6.txt b/tests/workloads/ipblocks_TCC/MI200/perfmon/pmc_perf_6.txt new file mode 100644 index 0000000000..36eae81668 --- /dev/null +++ b/tests/workloads/ipblocks_TCC/MI200/perfmon/pmc_perf_6.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_RDREQ_DRAM_sum TCC_TAG_STALL_sum TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_TCC/MI200/perfmon/pmc_perf_7.txt b/tests/workloads/ipblocks_TCC/MI200/perfmon/pmc_perf_7.txt new file mode 100644 index 0000000000..314286941a --- /dev/null +++ b/tests/workloads/ipblocks_TCC/MI200/perfmon/pmc_perf_7.txt @@ -0,0 +1,5 @@ +pmc: TCC_NORMAL_EVICT_sum TCC_ALL_TC_OP_INV_EVICT_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA_ATOMIC_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_TCC/MI200/perfmon/pmc_perf_8.txt b/tests/workloads/ipblocks_TCC/MI200/perfmon/pmc_perf_8.txt new file mode 100644 index 0000000000..c9cb71c6cc --- /dev/null +++ b/tests/workloads/ipblocks_TCC/MI200/perfmon/pmc_perf_8.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_RDREQ_LEVEL_sum TCC_EA_WRREQ_LEVEL_sum TCC_EA_ATOMIC_LEVEL_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_TCC/MI200/perfmon/timestamps.txt b/tests/workloads/ipblocks_TCC/MI200/perfmon/timestamps.txt new file mode 100644 index 0000000000..676cca1b80 --- /dev/null +++ b/tests/workloads/ipblocks_TCC/MI200/perfmon/timestamps.txt @@ -0,0 +1,5 @@ +pmc: + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_TCC/MI200/pmc_perf.csv b/tests/workloads/ipblocks_TCC/MI200/pmc_perf.csv new file mode 100644 index 0000000000..5030017cf0 --- /dev/null +++ b/tests/workloads/ipblocks_TCC/MI200/pmc_perf.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_1,obj_1,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,TCC_EA_ATOMIC_LEVEL_sum,wave_size_2,obj_2,TCC_EA_RDREQ_DRAM_sum,TCC_TAG_STALL_sum,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,wave_size_3,obj_3,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_4,obj_4,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_5,obj_5,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,wave_size_6,obj_6,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,GRBM_COUNT,GRBM_GUI_ACTIVE,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_7,obj_7,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_8,obj_8,TCC_EA_WRREQ_STALL_sum,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f4e138d8ec0,131072.0,131072.0,0.0,131072.0,64,0x7f9bbb83cec0,39574578.0,35049244.0,0.0,64,0x7f233bc40ec0,131083.0,34173.0,46381.0,19155.0,64,0x7f89c7560ec0,73109.0,131072.0,0.0,65568.0,64,0x7f5f10404ec0,56.0,6.0,0.0,204354.0,64,0x7fc9638d0ec0,65551.0,0.0,0.0,0.0,64,0x7f45aad84ec0,223400,130306,16384,27924,27924,893568.0,484905.0,0.0,0.0,64,0x7f5ebb060ec0,204668.0,0.0,73587.0,131081.0,64,0x7f3df06d8ec0,511.0,131081.0,0.0,10.0,197221464101706,197221464121866 +1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f4e138d8ec0,91182.0,91182.0,0.0,91182.0,64,0x7f9bbb83cec0,120415173.0,58005504.0,0.0,64,0x7f233bc40ec0,131084.0,85270.0,45690.0,0.0,64,0x7f89c7560ec0,69560.0,131072.0,0.0,45420.0,64,0x7f5f10404ec0,56.0,9.0,0.0,200481.0,64,0x7fc9638d0ec0,65552.0,0.0,0.0,0.0,64,0x7f45aad84ec0,330360,222253,16384,41294,41294,1321408.0,780115.0,0.0,0.0,64,0x7f5ebb060ec0,201082.0,0.0,69998.0,131084.0,64,0x7f3df06d8ec0,5930.0,131083.0,0.0,20.0,197221464151626,197221464166986 +2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f4e138d8ec0,91226.0,91226.0,0.0,91226.0,64,0x7f9bbb83cec0,118873813.0,60394998.0,0.0,64,0x7f233bc40ec0,131083.0,95089.0,45502.0,0.0,64,0x7f89c7560ec0,69737.0,131072.0,0.0,45790.0,64,0x7f5f10404ec0,56.0,10.0,0.0,200441.0,64,0x7fc9638d0ec0,65552.0,0.0,0.0,0.0,64,0x7f45aad84ec0,334568,224123,16384,41820,41820,1338240.0,778279.0,0.0,0.0,64,0x7f5ebb060ec0,200553.0,0.0,69469.0,131084.0,64,0x7f3df06d8ec0,4408.0,131083.0,0.0,20.0,197221464220586,197221464237226 diff --git a/tests/workloads/ipblocks_TCC/MI200/roofline.csv b/tests/workloads/ipblocks_TCC/MI200/roofline.csv new file mode 100644 index 0000000000..33d4ca68f6 --- /dev/null +++ b/tests/workloads/ipblocks_TCC/MI200/roofline.csv @@ -0,0 +1,5 @@ +device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh +0,1388.6752,1388.1373,1389.213,5017.1997,5014.0039,5020.3955,9224.4521,9223.7148,9225.1895,18054.023,18053.035,18055.012,20937.457,20877.061,20997.854,20266.201,20265.646,20266.756,170439.42,170434.2,170444.64,164884.09,164879.08,164889.11,41419.691,41418.996,41420.387,41480.391,41479.809,41480.973,166345.41,165853.98,166836.83 +1,1389.1864,1388.6312,1389.7416,5027.6445,5025.6069,5029.6821,9233.4541,9232.8564,9234.0518,18093.193,18089.07,18097.316,20973.025,20905.926,21040.125,20290.9,20290.348,20291.453,170828.36,170823.75,170832.97,165075.27,165070.19,165080.34,41479.719,41478.855,41480.582,41539.012,41537.801,41540.223,166861.7,166858.67,166864.73 +2,1388.9811,1388.4561,1389.5061,5036.355,5034.291,5038.4189,9261.3633,9260.626,9262.1006,18108.422,18107.715,18109.129,21048.971,21048.531,21049.41,20354.988,20354.508,20355.469,171128.56,171124.98,171132.14,165508.55,165504.98,165512.11,41587.398,41585.887,41588.91,41649.879,41648.688,41651.07,166974.3,166380.06,167568.53 +3,1388.9543,1388.3977,1389.511,5032.1895,5030.8799,5033.499,9239.9756,9239.4219,9240.5293,18023.918,18020.02,18027.816,21033.564,21032.939,21034.189,20313.762,20313.125,20314.398,171030.3,171027.31,171033.28,165229.09,165223.56,165234.62,41438.047,41282.539,41593.555,41581.246,41580.742,41581.75,167015.31,167013.75,167016.88 diff --git a/tests/workloads/ipblocks_TCC/MI200/sysinfo.csv b/tests/workloads/ipblocks_TCC/MI200/sysinfo.csv new file mode 100644 index 0000000000..7ebfa17df1 --- /dev/null +++ b/tests/workloads/ipblocks_TCC/MI200/sysinfo.csv @@ -0,0 +1,2 @@ +workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd +ipblocks_TCC,./sample/vcopy -n 1048576 -b 256 -i 3,tcc|roofline,Thu 07 Mar 2024 01:58:04 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/ipblocks_TCC/MI200/timestamps.csv b/tests/workloads/ipblocks_TCC/MI200/timestamps.csv new file mode 100644 index 0000000000..3c285df99c --- /dev/null +++ b/tests/workloads/ipblocks_TCC/MI200/timestamps.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,247861,247861,1048576,256,0,0,8,0,16,64,0x0,0x7fcdc9168ec0,197221464077878,197221464101706,197221464121866,197221464147971 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,247861,247861,1048576,256,0,0,8,0,16,64,0x0,0x7fcdc9168ec0,197221464140487,197221464151626,197221464166986,197221464217122 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,247861,247861,1048576,256,0,0,8,0,16,64,0x0,0x7fcdc9168ec0,197221464177567,197221464220586,197221464237226,197221464238242 diff --git a/tests/workloads/ipblocks_TCP/MI100/pmc_dispatch_info.csv b/tests/workloads/ipblocks_TCP/MI100/pmc_dispatch_info.csv new file mode 100644 index 0000000000..17300ae9af --- /dev/null +++ b/tests/workloads/ipblocks_TCP/MI100/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) ",2 +1,"vecCopy(double*, double*, double*, int, int) ",2 +2,"vecCopy(double*, double*, double*, int, int) ",2 diff --git a/tests/workloads/ipblocks_TCP/MI100/pmc_perf.csv b/tests/workloads/ipblocks_TCP/MI100/pmc_perf.csv index 70e3995ce4..02289b4959 100644 --- a/tests/workloads/ipblocks_TCP/MI100/pmc_perf.csv +++ b/tests/workloads/ipblocks_TCP/MI100/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,wave_size_1,obj_1,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,wave_size_2,obj_2,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,wave_size_3,obj_3,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,wave_size_4,obj_4,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,wave_size_5,obj_5,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,wave_size_6,obj_6,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,wave_size_7,obj_7,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,wave_size_8,obj_8,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,wave_size_9,obj_9,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f1b88596e80,383032,233049,3405514,16384,24888019,47878,47878,3848486.0,3005476.0,4369.0,1194229.0,64,0x7f9a656c8e80,61744472.0,165055501.0,74549153.0,131072.0,64,0x7f42d8e9ee80,131072.0,0.0,0.0,0.0,64,0x7f4c71692e80,960.0,513828.0,0.0,524288.0,64,0x7fd12e99ae80,0.0,0.0,0.0,32768.0,64,0x7fbf3e2cae80,0.0,0.0,0.0,0.0,64,0x7f326366ae80,0.0,0.0,0.0,0.0,64,0x7ff8a571ae80,0.0,0.0,120.0,524288.0,64,0x7f1d08adce80,2097152.0,2097152.0,1048576.0,1048576.0,64,0x7f0db9fe8e80,131072.0,131072.0,0.0,2441883.0,2187673516070860,2187673516095180 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f1b88596e80,406088,263467,3515843,16384,23227715,50760,50760,4242236.0,3427380.0,6222.0,1267309.0,64,0x7f9a656c8e80,64302031.0,176959356.0,72649195.0,131072.0,64,0x7f42d8e9ee80,131072.0,0.0,0.0,0.0,64,0x7f4c71692e80,960.0,513935.0,0.0,524288.0,64,0x7fd12e99ae80,0.0,0.0,0.0,32768.0,64,0x7fbf3e2cae80,0.0,0.0,0.0,0.0,64,0x7f326366ae80,0.0,0.0,0.0,0.0,64,0x7ff8a571ae80,0.0,0.0,120.0,524288.0,64,0x7f1d08adce80,2097152.0,2097152.0,1048576.0,1048576.0,64,0x7f0db9fe8e80,131072.0,131072.0,0.0,2455106.0,2187673516186380,2187673516205580 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f1b88596e80,334472,227963,3301081,16384,24069186,41808,41808,3717596.0,3015690.0,5380.0,1150413.0,64,0x7f9a656c8e80,61453714.0,161685113.0,69680141.0,131072.0,64,0x7f42d8e9ee80,131072.0,0.0,0.0,0.0,64,0x7f4c71692e80,960.0,513902.0,0.0,524288.0,64,0x7fd12e99ae80,0.0,0.0,0.0,32768.0,64,0x7fbf3e2cae80,0.0,0.0,0.0,0.0,64,0x7f326366ae80,0.0,0.0,0.0,0.0,64,0x7ff8a571ae80,0.0,0.0,120.0,524288.0,64,0x7f1d08adce80,2097152.0,2097152.0,1048576.0,1048576.0,64,0x7f0db9fe8e80,131072.0,131072.0,0.0,2419630.0,2187673516226380,2187673516245580 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,wave_size_1,obj_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,wave_size_2,obj_2,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,wave_size_3,obj_3,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,wave_size_4,obj_4,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_5,obj_5,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,wave_size_6,obj_6,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,wave_size_7,obj_7,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,wave_size_8,obj_8,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,wave_size_9,obj_9,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f12cc0f6e80,0.0,0.0,120.0,524288.0,64,0x7f495b82ae80,2097152.0,2097152.0,1048576.0,1048576.0,64,0x7f9b0bfd2e80,406872,240230,3508070,16384,25521642,50858,50858,3956486.0,3023959.0,8290.0,1189874.0,64,0x7f828a5d8e80,960.0,513952.0,0.0,524288.0,64,0x7f3e0b46ae80,131072.0,131072.0,0.0,2589805.0,64,0x7f9b95378e80,0.0,0.0,0.0,0.0,64,0x7f08eb366e80,0.0,0.0,0.0,32768.0,64,0x7fdc3fb00e80,131072.0,0.0,0.0,0.0,64,0x7f6afaf00e80,71052435.0,201658168.0,81356112.0,131072.0,64,0x7fcec552ae80,0.0,0.0,0.0,0.0,194070298825333,194070298849653 +1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f12cc0f6e80,0.0,0.0,120.0,524288.0,64,0x7f495b82ae80,2097152.0,2097152.0,1048576.0,1048576.0,64,0x7f9b0bfd2e80,396416,218905,3203855,16384,23148465,49551,49551,3573611.0,3040613.0,6466.0,1230212.0,64,0x7f828a5d8e80,960.0,513897.0,0.0,524288.0,64,0x7f3e0b46ae80,131072.0,131072.0,0.0,2568024.0,64,0x7f9b95378e80,0.0,0.0,0.0,0.0,64,0x7f08eb366e80,0.0,0.0,0.0,32768.0,64,0x7fdc3fb00e80,131072.0,0.0,0.0,0.0,64,0x7f6afaf00e80,68065829.0,192283723.0,76332243.0,131072.0,64,0x7fcec552ae80,0.0,0.0,0.0,0.0,194070298947253,194070298966453 +2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f12cc0f6e80,0.0,0.0,120.0,524288.0,64,0x7f495b82ae80,2097152.0,2097152.0,1048576.0,1048576.0,64,0x7f9b0bfd2e80,344600,229289,3355582,16384,24502194,43074,43074,3737726.0,3019215.0,6611.0,1052353.0,64,0x7f828a5d8e80,960.0,513968.0,0.0,524288.0,64,0x7f3e0b46ae80,131072.0,131072.0,0.0,2449269.0,64,0x7f9b95378e80,0.0,0.0,0.0,0.0,64,0x7f08eb366e80,0.0,0.0,0.0,32768.0,64,0x7fdc3fb00e80,131072.0,0.0,0.0,0.0,64,0x7f6afaf00e80,69082609.0,188996267.0,77536972.0,131072.0,64,0x7fcec552ae80,0.0,0.0,0.0,0.0,194070298990293,194070299009493 diff --git a/tests/workloads/ipblocks_TCP/MI100/sysinfo.csv b/tests/workloads/ipblocks_TCP/MI100/sysinfo.csv index 71f7c4d696..9ebace481a 100644 --- a/tests/workloads/ipblocks_TCP/MI100/sysinfo.csv +++ b/tests/workloads/ipblocks_TCP/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -ipblocks_TCP,./tests/vcopy -n 1048576 -b 256 -i 3,tcp,Fri Mar 1 16:43:03 2024 (CST),1,t006-003.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651240,,5.7.1-98,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +ipblocks_TCP,./tests/vcopy -n 1048576 -b 256 -i 3,tcp,Thu 07 Mar 2024 01:05:30 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/ipblocks_TCP/MI100/timestamps.csv b/tests/workloads/ipblocks_TCP/MI100/timestamps.csv index d0608cfd3a..5f67cfaacb 100644 --- a/tests/workloads/ipblocks_TCP/MI100/timestamps.csv +++ b/tests/workloads/ipblocks_TCP/MI100/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,2802710,2802710,1048576,256,0,0,8,8,16,64,0x0,0x7f5e5269ce80,2187673516044909,2187673516070860,2187673516095180,2187673516106475 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,2802710,2802710,1048576,256,0,0,8,8,16,64,0x0,0x7f5e5269ce80,2187673516107677,2187673516186380,2187673516205580,2187673516206643 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,2802710,2802710,1048576,256,0,0,8,8,16,64,0x0,0x7f5e5269ce80,2187673516217213,2187673516226380,2187673516245580,2187673516246418 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,106948,106948,1048576,256,0,0,8,8,16,64,0x0,0x7f08c7b52e80,194070298794474,194070298825333,194070298849653,194070298865609 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,106948,106948,1048576,256,0,0,8,8,16,64,0x0,0x7f08c7b52e80,194070298865779,194070298947253,194070298966453,194070298967762 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,106948,106948,1048576,256,0,0,8,8,16,64,0x0,0x7f08c7b52e80,194070298979905,194070298990293,194070299009493,194070299010673 diff --git a/tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_0.txt b/tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_0.txt new file mode 100644 index 0000000000..c976322613 --- /dev/null +++ b/tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_0.txt @@ -0,0 +1,5 @@ +pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_WAVES SQ_WAVE_CYCLES GRBM_COUNT GRBM_GUI_ACTIVE TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_1.txt b/tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_1.txt new file mode 100644 index 0000000000..c97a94bb67 --- /dev/null +++ b/tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_1.txt @@ -0,0 +1,5 @@ +pmc: TCP_READ_TAGCONFLICT_STALL_CYCLES_sum TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum TCP_TA_TCP_STATE_READ_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_2.txt b/tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_2.txt new file mode 100644 index 0000000000..6bdbd65d97 --- /dev/null +++ b/tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_2.txt @@ -0,0 +1,5 @@ +pmc: TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_3.txt b/tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_3.txt new file mode 100644 index 0000000000..a96f3c792d --- /dev/null +++ b/tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_3.txt @@ -0,0 +1,5 @@ +pmc: TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_4.txt b/tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_4.txt new file mode 100644 index 0000000000..62b5dac3b5 --- /dev/null +++ b/tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_4.txt @@ -0,0 +1,5 @@ +pmc: TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_5.txt b/tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_5.txt new file mode 100644 index 0000000000..387d756f97 --- /dev/null +++ b/tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_5.txt @@ -0,0 +1,5 @@ +pmc: TCP_TCP_LATENCY_sum TCP_TCC_READ_REQ_LATENCY_sum TCP_TCC_WRITE_REQ_LATENCY_sum TCP_TCC_READ_REQ_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_6.txt b/tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_6.txt new file mode 100644 index 0000000000..f1b625f4b2 --- /dev/null +++ b/tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_6.txt @@ -0,0 +1,5 @@ +pmc: TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TCP_TCC_NC_READ_REQ_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_7.txt b/tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_7.txt new file mode 100644 index 0000000000..8d98088f4c --- /dev/null +++ b/tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_7.txt @@ -0,0 +1,5 @@ +pmc: TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TCP_TCC_UC_WRITE_REQ_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_8.txt b/tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_8.txt new file mode 100644 index 0000000000..d0137cab93 --- /dev/null +++ b/tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_8.txt @@ -0,0 +1,5 @@ +pmc: TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TCP_TCC_CC_ATOMIC_REQ_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_9.txt b/tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_9.txt new file mode 100644 index 0000000000..8261a88c51 --- /dev/null +++ b/tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_9.txt @@ -0,0 +1,5 @@ +pmc: TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum TCP_PENDING_STALL_CYCLES_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_TCP/MI200/perfmon/timestamps.txt b/tests/workloads/ipblocks_TCP/MI200/perfmon/timestamps.txt new file mode 100644 index 0000000000..676cca1b80 --- /dev/null +++ b/tests/workloads/ipblocks_TCP/MI200/perfmon/timestamps.txt @@ -0,0 +1,5 @@ +pmc: + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_TCP/MI200/pmc_perf.csv b/tests/workloads/ipblocks_TCP/MI200/pmc_perf.csv new file mode 100644 index 0000000000..3df0bb08ca --- /dev/null +++ b/tests/workloads/ipblocks_TCP/MI200/pmc_perf.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,wave_size_1,obj_1,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,wave_size_2,obj_2,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,wave_size_3,obj_3,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_4,obj_4,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,wave_size_5,obj_5,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,wave_size_6,obj_6,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,wave_size_7,obj_7,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,wave_size_8,obj_8,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,wave_size_9,obj_9,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f9404948ec0,0.0,0.0,0.0,32768.0,64,0x7f2689a48ec0,0.0,0.0,0.0,0.0,64,0x7f60248f0ec0,2097152.0,2097152.0,1048576.0,1048576.0,64,0x7f98f1a8cec0,131072.0,131072.0,0.0,916665.0,64,0x7f99e30d4ec0,0.0,0.0,0.0,0.0,64,0x7f49da658ec0,218024,126138,1592956,16384,10612728,27252,27252,1917310.0,1320290.0,3653.0,175563.0,64,0x7f87c2994ec0,27579886.0,86090451.0,39383215.0,131072.0,64,0x7fde3a900ec0,131072.0,0.0,0.0,0.0,64,0x7f3bbb108ec0,0.0,0.0,0.0,524288.0,64,0x7f6d3ba48ec0,832.0,515140.0,0.0,524288.0,197425575298507,197425575319307 +1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f9404948ec0,0.0,0.0,0.0,32768.0,64,0x7f2689a48ec0,0.0,0.0,0.0,0.0,64,0x7f60248f0ec0,2097152.0,2097152.0,1048576.0,1048576.0,64,0x7f98f1a8cec0,131072.0,131072.0,0.0,2085832.0,64,0x7f99e30d4ec0,0.0,0.0,0.0,0.0,64,0x7f49da658ec0,300064,204807,2541439,16384,17422948,37507,37507,2940098.0,2361650.0,4186.0,338609.0,64,0x7f87c2994ec0,58079980.0,197098793.0,45794862.0,131072.0,64,0x7fde3a900ec0,131072.0,0.0,0.0,0.0,64,0x7f3bbb108ec0,0.0,0.0,0.0,524288.0,64,0x7f6d3ba48ec0,0.0,524288.0,0.0,524288.0,197425575401067,197425575417707 +2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f9404948ec0,0.0,0.0,0.0,32768.0,64,0x7f2689a48ec0,0.0,0.0,0.0,0.0,64,0x7f60248f0ec0,2097152.0,2097152.0,1048576.0,1048576.0,64,0x7f98f1a8cec0,131072.0,131072.0,0.0,1992345.0,64,0x7f99e30d4ec0,0.0,0.0,0.0,0.0,64,0x7f49da658ec0,327256,221096,2738473,16384,19028519,40906,40906,3152076.0,2440924.0,4152.0,379488.0,64,0x7f87c2994ec0,58426172.0,197564310.0,47383725.0,131072.0,64,0x7fde3a900ec0,131072.0,0.0,0.0,0.0,64,0x7f3bbb108ec0,0.0,0.0,0.0,524288.0,64,0x7f6d3ba48ec0,832.0,515152.0,0.0,524288.0,197425575438347,197425575454027 diff --git a/tests/workloads/ipblocks_TCP/MI200/roofline.csv b/tests/workloads/ipblocks_TCP/MI200/roofline.csv new file mode 100644 index 0000000000..e19a404bcd --- /dev/null +++ b/tests/workloads/ipblocks_TCP/MI200/roofline.csv @@ -0,0 +1,5 @@ +device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh +0,1389.191,1388.6029,1389.7792,5016.8271,5013.8096,5019.8447,9224.8887,9224.0996,9225.6777,18054.102,18053.037,18055.166,20938.258,20877.508,20999.008,20267.289,20266.496,20268.082,170451.02,170447.69,170454.34,164887.59,164882.64,164892.55,41427.105,41426.293,41427.918,41483.168,41482.504,41483.832,166362.02,165869.12,166854.91 +1,1389.2063,1388.6646,1389.748,5027.7417,5025.7686,5029.7148,9234.083,9233.3975,9234.7686,18089.377,18086.072,18092.682,20975.256,20908.32,21042.191,20295.521,20294.941,20296.102,170852.36,170848.52,170856.2,165103,165099.17,165106.83,41484.324,41483.551,41485.098,41539.77,41538.516,41541.023,166875.3,166872.31,166878.28 +2,1388.9279,1388.3605,1389.4952,5036.6958,5034.4482,5038.9434,9260.9668,9260.041,9261.8926,18104.98,18104.059,18105.902,21050.352,21050.016,21050.688,20357.52,20356.998,20358.041,171149.73,171146.53,171152.94,165557.28,165553.61,165560.95,41596.461,41595.207,41597.715,41654.727,41653.766,41655.688,167314.88,167310.36,167319.39 +3,1388.734,1388.205,1389.2631,5031.7368,5030.3604,5033.1133,9239.874,9239.3086,9240.4395,18022.992,18018.922,18027.062,21029.609,21029.219,21030,20311.082,20310.459,20311.705,171019.62,171016.36,171022.89,165217.78,165212.28,165223.28,41438.387,41283.484,41593.289,41580.906,41580.363,41581.449,167016.12,167013.67,167018.58 diff --git a/tests/workloads/ipblocks_TCP/MI200/sysinfo.csv b/tests/workloads/ipblocks_TCP/MI200/sysinfo.csv new file mode 100644 index 0000000000..31a43e0624 --- /dev/null +++ b/tests/workloads/ipblocks_TCP/MI200/sysinfo.csv @@ -0,0 +1,2 @@ +workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd +ipblocks_TCP,./sample/vcopy -n 1048576 -b 256 -i 3,tcp|roofline,Thu 07 Mar 2024 02:01:27 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/ipblocks_TCP/MI200/timestamps.csv b/tests/workloads/ipblocks_TCP/MI200/timestamps.csv new file mode 100644 index 0000000000..cee39d536c --- /dev/null +++ b/tests/workloads/ipblocks_TCP/MI200/timestamps.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,255418,255418,1048576,256,0,0,8,0,16,64,0x0,0x7f14cf350ec0,197425575274886,197425575298507,197425575319307,197425575330561 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,255418,255418,1048576,256,0,0,8,0,16,64,0x0,0x7f14cf350ec0,197425575330261,197425575401067,197425575417707,197425575419189 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,255418,255418,1048576,256,0,0,8,0,16,64,0x0,0x7f14cf350ec0,197425575428927,197425575438347,197425575454027,197425575455397 diff --git a/tests/workloads/ipblocks_TD/MI100/pmc_dispatch_info.csv b/tests/workloads/ipblocks_TD/MI100/pmc_dispatch_info.csv new file mode 100644 index 0000000000..17300ae9af --- /dev/null +++ b/tests/workloads/ipblocks_TD/MI100/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) ",2 +1,"vecCopy(double*, double*, double*, int, int) ",2 +2,"vecCopy(double*, double*, double*, int, int) ",2 diff --git a/tests/workloads/ipblocks_TD/MI100/pmc_perf.csv b/tests/workloads/ipblocks_TD/MI100/pmc_perf.csv index cf96285abc..39d3142d42 100644 --- a/tests/workloads/ipblocks_TD/MI100/pmc_perf.csv +++ b/tests/workloads/ipblocks_TD/MI100/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,wave_size_1,obj_1,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,GRBM_COUNT,GRBM_GUI_ACTIVE,TD_TD_BUSY_sum,TD_TC_STALL_sum,wave_size_2,obj_2,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fec6f558e80,0.0,16384.0,64,0x7fd0bc59ce80,386960,234213,3405532,16384,25040985,48369,48369,2962624.0,2653028.0,64,0x7fc6612a0e80,0.0,32768.0,2187896433292582,2187896433316422 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fec6f558e80,0.0,16384.0,64,0x7fd0bc59ce80,338888,228752,3297604,16384,23929870,42360,42360,2989968.0,2681321.0,64,0x7fc6612a0e80,0.0,32768.0,2187896433495782,2187896433514822 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fec6f558e80,0.0,16384.0,64,0x7fd0bc59ce80,339656,229300,3312398,16384,24128426,42456,42456,3005685.0,2696624.0,64,0x7fc6612a0e80,0.0,32768.0,2187896433535942,2187896433554982 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,wave_size_1,obj_1,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,wave_size_2,obj_2,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,GRBM_COUNT,GRBM_GUI_ACTIVE,TD_TD_BUSY_sum,TD_TC_STALL_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fd71c252e80,0.0,16384.0,64,0x7f9093004e80,0.0,32768.0,64,0x7fd456aeee80,379632,228565,3336391,16384,24381609,47453,47453,2952060.0,2641101.0,194311556312654,194311556337134 +1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fd71c252e80,0.0,16384.0,64,0x7f9093004e80,0.0,32768.0,64,0x7fd456aeee80,336336,227259,3312174,16384,24240462,42041,42041,2989256.0,2678517.0,194311556410734,194311556429614 +2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fd71c252e80,0.0,16384.0,64,0x7f9093004e80,0.0,32768.0,64,0x7fd456aeee80,335624,225631,3288156,16384,24209884,41952,41952,2975008.0,2666527.0,194311556450414,194311556469294 diff --git a/tests/workloads/ipblocks_TD/MI100/sysinfo.csv b/tests/workloads/ipblocks_TD/MI100/sysinfo.csv index 60940538fa..a1607a79ad 100644 --- a/tests/workloads/ipblocks_TD/MI100/sysinfo.csv +++ b/tests/workloads/ipblocks_TD/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -ipblocks_TD,./tests/vcopy -n 1048576 -b 256 -i 3,td,Fri Mar 1 16:46:46 2024 (CST),1,t006-003.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651240,,5.7.1-98,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +ipblocks_TD,./tests/vcopy -n 1048576 -b 256 -i 3,td,Thu 07 Mar 2024 01:09:35 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/ipblocks_TD/MI100/timestamps.csv b/tests/workloads/ipblocks_TD/MI100/timestamps.csv index 2cc279aa22..f583dc2261 100644 --- a/tests/workloads/ipblocks_TD/MI100/timestamps.csv +++ b/tests/workloads/ipblocks_TD/MI100/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,2879013,2879013,1048576,256,0,0,8,8,16,64,0x0,0x7f2d0453ce80,2187896433266371,2187896433292582,2187896433316422,2187896433328227 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,2879013,2879013,1048576,256,0,0,8,8,16,64,0x0,0x7f2d0453ce80,2187896433329169,2187896433495782,2187896433514822,2187896433516019 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,2879013,2879013,1048576,256,0,0,8,8,16,64,0x0,0x7f2d0453ce80,2187896433526659,2187896433535942,2187896433554982,2187896433556105 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,184422,184422,1048576,256,0,0,8,8,16,64,0x0,0x7f5d4bd20e80,194311556287244,194311556312654,194311556337134,194311556347738 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,184422,184422,1048576,256,0,0,8,8,16,64,0x0,0x7f5d4bd20e80,194311556350103,194311556410734,194311556429614,194311556430645 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,184422,184422,1048576,256,0,0,8,8,16,64,0x0,0x7f5d4bd20e80,194311556441726,194311556450414,194311556469294,194311556470401 diff --git a/tests/workloads/ipblocks_TD/MI200/perfmon/pmc_perf_0.txt b/tests/workloads/ipblocks_TD/MI200/perfmon/pmc_perf_0.txt new file mode 100644 index 0000000000..694315e03e --- /dev/null +++ b/tests/workloads/ipblocks_TD/MI200/perfmon/pmc_perf_0.txt @@ -0,0 +1,5 @@ +pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_WAVES SQ_WAVE_CYCLES GRBM_COUNT GRBM_GUI_ACTIVE TD_TD_BUSY_sum TD_TC_STALL_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_TD/MI200/perfmon/pmc_perf_1.txt b/tests/workloads/ipblocks_TD/MI200/perfmon/pmc_perf_1.txt new file mode 100644 index 0000000000..1f572a724b --- /dev/null +++ b/tests/workloads/ipblocks_TD/MI200/perfmon/pmc_perf_1.txt @@ -0,0 +1,5 @@ +pmc: TD_SPI_STALL_sum TD_LOAD_WAVEFRONT_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_TD/MI200/perfmon/pmc_perf_2.txt b/tests/workloads/ipblocks_TD/MI200/perfmon/pmc_perf_2.txt new file mode 100644 index 0000000000..6a7f8b1f73 --- /dev/null +++ b/tests/workloads/ipblocks_TD/MI200/perfmon/pmc_perf_2.txt @@ -0,0 +1,5 @@ +pmc: TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_TD/MI200/perfmon/pmc_perf_3.txt b/tests/workloads/ipblocks_TD/MI200/perfmon/pmc_perf_3.txt new file mode 100644 index 0000000000..fc3e8fe7c2 --- /dev/null +++ b/tests/workloads/ipblocks_TD/MI200/perfmon/pmc_perf_3.txt @@ -0,0 +1,5 @@ +pmc: TD_COALESCABLE_WAVEFRONT_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_TD/MI200/perfmon/timestamps.txt b/tests/workloads/ipblocks_TD/MI200/perfmon/timestamps.txt new file mode 100644 index 0000000000..676cca1b80 --- /dev/null +++ b/tests/workloads/ipblocks_TD/MI200/perfmon/timestamps.txt @@ -0,0 +1,5 @@ +pmc: + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_TD/MI200/pmc_perf.csv b/tests/workloads/ipblocks_TD/MI200/pmc_perf.csv new file mode 100644 index 0000000000..6e32f3b4ab --- /dev/null +++ b/tests/workloads/ipblocks_TD/MI200/pmc_perf.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,wave_size_1,obj_1,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,wave_size_2,obj_2,TD_COALESCABLE_WAVEFRONT_sum,wave_size_3,obj_3,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,GRBM_COUNT,GRBM_GUI_ACTIVE,TD_TD_BUSY_sum,TD_TC_STALL_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f249e60cec0,0.0,16384.0,64,0x7fca27f10ec0,399.0,32768.0,64,0x7f18657b8ec0,0.0,64,0x7f46abdacec0,223128,131708,1668426,16384,11242880,27890,27890,1325799.0,1027102.0,199547059519110,199547059539430 +1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f249e60cec0,0.0,16384.0,64,0x7fca27f10ec0,210.0,32768.0,64,0x7f18657b8ec0,0.0,64,0x7f46abdacec0,302160,208300,2564434,16384,18120165,37769,37769,2373984.0,2062477.0,199547059627110,199547059643270 +2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f249e60cec0,0.0,16384.0,64,0x7fca27f10ec0,274.0,32768.0,64,0x7f18657b8ec0,0.0,64,0x7f46abdacec0,333448,224363,2787083,16384,19455944,41680,41680,2452213.0,2146452.0,199547059664230,199547059679750 diff --git a/tests/workloads/ipblocks_TD/MI200/roofline.csv b/tests/workloads/ipblocks_TD/MI200/roofline.csv new file mode 100644 index 0000000000..6b666a5638 --- /dev/null +++ b/tests/workloads/ipblocks_TD/MI200/roofline.csv @@ -0,0 +1,5 @@ +device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh +0,1388.9509,1388.3612,1389.5406,5014.793,5011.5312,5018.0547,9223.0742,9222.4434,9223.7051,18049.586,18048.721,18050.451,20931.9,20871.432,20992.369,20261.727,20261.002,20262.451,170399.3,170395.31,170403.28,164852.52,164847.61,164857.42,41417.066,41416.535,41417.598,41477.52,41476.922,41478.117,166330.03,165838.83,166821.23 +1,1389.3237,1388.8047,1389.8428,5026.1694,5024.1035,5028.2354,9231.6592,9230.9326,9232.3857,18088.08,18084.199,18091.961,20970.721,20903.84,21037.602,20289.123,20288.473,20289.773,170790.78,170786.94,170794.62,165046.8,165043.45,165050.14,41469.863,41468.957,41470.77,41529.766,41528.867,41530.664,166845.92,166842.92,166848.92 +2,1388.3853,1387.8412,1388.9293,5035.041,5032.6895,5037.3926,9259.8057,9259.0186,9260.5928,18102.119,18101.258,18102.98,21044.225,21043.779,21044.67,20347.809,20347.166,20348.451,171085.16,171081.53,171088.78,165468.19,165464.12,165472.25,41572.938,41571.941,41573.934,41631.891,41631.031,41632.75,166910.88,166318.69,167503.06 +3,1388.9561,1388.4015,1389.5106,5032.2793,5031.104,5033.4546,9240.8994,9240.209,9241.5898,18024.684,18021.26,18028.107,21037.52,21036.775,21038.264,20313.844,20313.178,20314.51,171021.56,171017.92,171025.2,165226.5,165222.19,165230.81,41441.406,41287.621,41595.191,41583.449,41582.934,41583.965,167031.38,167029.02,167033.73 diff --git a/tests/workloads/ipblocks_TD/MI200/sysinfo.csv b/tests/workloads/ipblocks_TD/MI200/sysinfo.csv new file mode 100644 index 0000000000..fd7dc35618 --- /dev/null +++ b/tests/workloads/ipblocks_TD/MI200/sysinfo.csv @@ -0,0 +1,2 @@ +workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd +ipblocks_TD,./sample/vcopy -n 1048576 -b 256 -i 3,td|roofline,Thu 07 Mar 2024 02:36:52 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/ipblocks_TD/MI200/timestamps.csv b/tests/workloads/ipblocks_TD/MI200/timestamps.csv new file mode 100644 index 0000000000..7859d631c0 --- /dev/null +++ b/tests/workloads/ipblocks_TD/MI200/timestamps.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,346607,346607,1048576,256,0,0,8,0,16,64,0x0,0x7fee2b950ec0,199547059494326,199547059519110,199547059539430,199547059552055 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,346607,346607,1048576,256,0,0,8,0,16,64,0x0,0x7fee2b950ec0,199547059550312,199547059627110,199547059643270,199547059644400 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,346607,346607,1048576,256,0,0,8,0,16,64,0x0,0x7fee2b950ec0,199547059654429,199547059664230,199547059679750,199547059680738 diff --git a/tests/workloads/join_type_grid/MI100/SQ_IFETCH_LEVEL.csv b/tests/workloads/join_type_grid/MI100/SQ_IFETCH_LEVEL.csv index 425f83e316..1dfb1d5aa5 100644 --- a/tests/workloads/join_type_grid/MI100/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/join_type_grid/MI100/SQ_IFETCH_LEVEL.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2815532,2815532,1048576,256,0,0,8,8,16,64,0x0,0x7f394a7ece80,48912,48912,16384,65536,14382,1830536,2187710081303245,2187711888967638,2187711888992278,2187710088920725 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2815532,2815532,1048576,256,0,0,8,8,16,64,0x0,0x7f394a7ece80,43753,43753,16384,65536,8309,1048580,2187710088945852,2187711889086198,2187711889105558,2187710089289737 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2815532,2815532,1048576,256,0,0,8,8,16,64,0x0,0x7f394a7ece80,43137,43137,16384,65536,8321,1048588,2187710089322709,2187711889126678,2187711889145878,2187710089506965 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,118192,118192,1048576,256,0,0,8,8,16,64,0x0,0x7fd6acbaae80,48437,48437,16384,65536,14298,1816332,194104431495577,194116676571166,194116676595486,194104439234270 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,118192,118192,1048576,256,0,0,8,8,16,64,0x0,0x7fd6acbaae80,42764,42764,16384,65536,8238,1048580,194104439255931,194116676615646,194116676634206,194104439587438 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,118192,118192,1048576,256,0,0,8,8,16,64,0x0,0x7fd6acbaae80,42796,42796,16384,65536,8222,1048588,194104439621202,194116676727326,194116676746366,194104439801504 diff --git a/tests/workloads/join_type_grid/MI100/SQ_INST_LEVEL_LDS.csv b/tests/workloads/join_type_grid/MI100/SQ_INST_LEVEL_LDS.csv index 1838b77454..8b7a71eed8 100644 --- a/tests/workloads/join_type_grid/MI100/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/join_type_grid/MI100/SQ_INST_LEVEL_LDS.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2818082,2818082,1048576,256,0,0,8,8,16,64,0x0,0x7fb7b58d8e80,0,0,0,2187717309705312,2187711888967638,2187711888992278,2187717317152633 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2818082,2818082,1048576,256,0,0,8,8,16,64,0x0,0x7fb7b58d8e80,0,0,0,2187717317172350,2187711889086198,2187711889105558,2187717317470089 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2818082,2818082,1048576,256,0,0,8,8,16,64,0x0,0x7fb7b58d8e80,0,0,0,2187717317498472,2187711889126678,2187711889145878,2187717317671246 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,118382,118382,1048576,256,0,0,8,8,16,64,0x0,0x7f17127dce80,0,0,0,194104926213446,194116676571166,194116676595486,194104933889590 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,118382,118382,1048576,256,0,0,8,8,16,64,0x0,0x7f17127dce80,0,0,0,194104933908085,194116676615646,194116676634206,194104934234704 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,118382,118382,1048576,256,0,0,8,8,16,64,0x0,0x7f17127dce80,0,0,0,194104934263328,194116676727326,194116676746366,194104934440583 diff --git a/tests/workloads/join_type_grid/MI100/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/join_type_grid/MI100/SQ_INST_LEVEL_SMEM.csv index ac3e988c32..6a831ec11a 100644 --- a/tests/workloads/join_type_grid/MI100/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/join_type_grid/MI100/SQ_INST_LEVEL_SMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2817900,2817900,1048576,256,0,0,8,8,16,64,0x0,0x7ff24f49ee80,65536,194734,24890280,2187716865338380,2187711888967638,2187711888992278,2187716872882872 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2817900,2817900,1048576,256,0,0,8,8,16,64,0x0,0x7ff24f49ee80,65536,182558,23377352,2187716872902810,2187711889086198,2187711889105558,2187716873228271 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2817900,2817900,1048576,256,0,0,8,8,16,64,0x0,0x7ff24f49ee80,65536,207520,26602616,2187716873258397,2187711889126678,2187711889145878,2187716873435600 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,118567,118567,1048576,256,0,0,8,8,16,64,0x0,0x7f7400394e80,65536,197034,25247432,194105416376991,194116676571166,194116676595486,194105424085737 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,118567,118567,1048576,256,0,0,8,8,16,64,0x0,0x7f7400394e80,65536,176914,22629536,194105424102449,194116676615646,194116676634206,194105424410733 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,118567,118567,1048576,256,0,0,8,8,16,64,0x0,0x7f7400394e80,65536,184956,23691288,194105424438876,194116676727326,194116676746366,194105424602586 diff --git a/tests/workloads/join_type_grid/MI100/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/join_type_grid/MI100/SQ_INST_LEVEL_VMEM.csv index ccf5660b8f..1bea4b4a54 100644 --- a/tests/workloads/join_type_grid/MI100/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/join_type_grid/MI100/SQ_INST_LEVEL_VMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2817354,2817354,1048576,256,0,0,8,8,16,64,0x0,0x7fe161a0ce80,32768,661930,84746380,2187715252143548,2187711888967638,2187711888992278,2187715259860063 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2817354,2817354,1048576,256,0,0,8,8,16,64,0x0,0x7fe161a0ce80,32768,660996,84597008,2187715259880041,2187711889086198,2187711889105558,2187715260196515 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2817354,2817354,1048576,256,0,0,8,8,16,64,0x0,0x7fe161a0ce80,32768,666462,85315908,2187715260224918,2187711889126678,2187711889145878,2187715260408343 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,118767,118767,1048576,256,0,0,8,8,16,64,0x0,0x7f979e936e80,32768,627003,80249452,194105910406296,194116676571166,194116676595486,194105918239688 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,118767,118767,1048576,256,0,0,8,8,16,64,0x0,0x7f979e936e80,32768,682198,87324288,194105918259445,194116676615646,194116676634206,194105918569532 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,118767,118767,1048576,256,0,0,8,8,16,64,0x0,0x7f979e936e80,32768,666672,85351124,194105918598307,194116676727326,194116676746366,194105918772246 diff --git a/tests/workloads/join_type_grid/MI100/SQ_LEVEL_WAVES.csv b/tests/workloads/join_type_grid/MI100/SQ_LEVEL_WAVES.csv index ef0a158b86..8a5ac79a6a 100644 --- a/tests/workloads/join_type_grid/MI100/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/join_type_grid/MI100/SQ_LEVEL_WAVES.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2816988,2816988,1048576,256,0,0,8,8,16,64,0x0,0x7f913a356e80,48457,48457,17849,387664,16384,24737000,236129,0,99435200,2187714348242980,2187711888967638,2187711888992278,2187714355726649 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2816988,2816988,1048576,256,0,0,8,8,16,64,0x0,0x7f913a356e80,43210,43210,14183,345688,16384,25247384,239343,0,101470452,2187714355757426,2187711889086198,2187711889105558,2187714356069302 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2816988,2816988,1048576,256,0,0,8,8,16,64,0x0,0x7f913a356e80,43165,43165,13724,345328,16384,24249301,235545,0,97492512,2187714356108305,2187711889126678,2187711889145878,2187714356302780 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,118955,118955,1048576,256,0,0,8,8,16,64,0x0,0x7fa2db79ce80,47707,47707,16762,381664,16384,25174271,233099,0,101191452,194106398813286,194116676571166,194116676595486,194106406589529 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,118955,118955,1048576,256,0,0,8,8,16,64,0x0,0x7fa2db79ce80,43514,43514,14451,348120,16384,24820386,234052,0,99779440,194106406621440,194116676615646,194116676634206,194106406876623 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,118955,118955,1048576,256,0,0,8,8,16,64,0x0,0x7fa2db79ce80,42906,42906,13717,343256,16384,24906156,231361,0,100124212,194106406914885,194116676727326,194116676746366,194106407073626 diff --git a/tests/workloads/join_type_grid/MI100/pmc_dispatch_info.csv b/tests/workloads/join_type_grid/MI100/pmc_dispatch_info.csv new file mode 100644 index 0000000000..17300ae9af --- /dev/null +++ b/tests/workloads/join_type_grid/MI100/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) ",2 +1,"vecCopy(double*, double*, double*, int, int) ",2 +2,"vecCopy(double*, double*, double*, int, int) ",2 diff --git a/tests/workloads/join_type_grid/MI100/pmc_perf.csv b/tests/workloads/join_type_grid/MI100/pmc_perf.csv index 746d5225dc..412205a8d0 100644 --- a/tests/workloads/join_type_grid/MI100/pmc_perf.csv +++ b/tests/workloads/join_type_grid/MI100/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_1,obj_1,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_2,obj_2,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_3,obj_3,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_4,obj_4,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_5,obj_5,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_6,obj_6,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_7,obj_7,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_8,obj_8,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_9,obj_9,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_10,obj_10,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_11,obj_11,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_12,obj_12,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_13,obj_13,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_14,obj_14,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_15,obj_15,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_16,obj_16,TCC_EA_ATOMIC_LEVEL_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fb241eb8e80,4096,0,5001,0,4096,0,651,0,4096,0,238,0,4099,0,0,0,4096,0,2035,0,4096,0,848,0,4096,0,591,0,4096,0,1831,0,4096,0,2650,0,4096,0,486,0,4096,0,298,0,4096,0,911,0,4096,0,219,0,4096,0,1211,0,4096,0,709,0,4096,0,100,0,4096,0,915,0,4264,0,6258,0,4096,0,0,0,4096,0,1232,0,4096,0,431,0,4096,0,816,0,4096,0,6381,0,4144,0,444,0,4096,0,303,0,4096,0,391,0,4097,0,730,0,4144,0,1774,0,4096,0,209,0,4100,0,799,0,4096,0,0,0,4096,0,1103,0,64,0x7fd7ca83ae80,0,48035,0,0,0,48035,0,0,0,48035,0,0,0,48035,0,0,0,48035,0,0,0,48035,0,0,0,48035,0,0,0,48035,0,0,0,48035,0,0,0,48035,0,0,0,48035,0,0,0,48035,0,0,0,48035,0,0,0,48035,0,0,0,48035,0,0,0,48035,0,0,0,48035,0,0,0,48035,0,0,0,48035,0,0,0,48035,0,0,0,48035,0,0,0,48035,0,0,0,48035,0,0,0,48035,0,0,0,48035,0,0,0,48035,0,0,0,48035,0,0,0,48035,0,0,0,48035,0,0,0,48035,0,0,0,48035,0,0,0,48035,0,0,64,0x7f263e1dce80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,44833.0,126748.0,64,0x7f149630ee80,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8432,4336,8432,0,8192,4096,8192,141,8243,4288,8384,0,8192,4096,8192,0,8192,4096,8192,64,0x7fa99f246e80,388744,236100,3444985,16384,25415154,144,48,0,48592,48592,3894416.0,3042466.0,7201.0,934517.0,2088520.0,0.0,3033596.0,2722269.0,387031,246040,48592,0,48592,0,1554944.0,963186.0,0.0,0.0,64,0x7fd90d7dce80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,47376,0,131723.0,131072.0,0.0,131104.0,64,0x7f83d783ae80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86274.0,44798.0,131111.0,0.0,64,0x7fbb24b5ee80,8192,0,4096,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7efe09b50e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131399.0,0.0,646.0,131398.0,64,0x7fb1b823ee80,131072.0,131072.0,0.0,2585841.0,0.0,0.0,122513600.0,59690818.0,64,0x7fcf01160e80,1744467,360448,163840,0,0,180224,114688,0,70043852.0,180538271.0,71447342.0,131072.0,0.0,635775.0,0,0,26547,78589.0,0.0,0.0,78589.0,64,0x7fcfd52a2e80,0,0,192,0,65536,64510,48,1314,30817,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,539,46740,1676,0,48.0,203.0,0.0,262288.0,64,0x7fce5a68ee80,3319,0,0,1983497,4944,0,0,2090715,2794,0,0,1880965,7377,0,0,2295357,3965,0,0,2022987,3032,0,0,1886036,3695,0,0,2072977,4733,0,0,2122872,2783,0,0,1933472,4254,0,0,2004665,3946,0,0,2053172,2543,0,0,1925250,4447,0,0,2091631,5025,0,0,2185801,2041,0,0,1855200,3593,0,0,2144185,4719,0,0,2072447,3732,0,0,1991531,4610,0,0,2103762,6361,0,0,2193253,2724,0,0,1886885,4069,0,0,1964991,3731,0,0,2018635,5815,0,0,2217708,4425,0,0,2090134,4007,0,0,2030236,3032,0,0,1947315,5149,0,0,2107012,3278,0,0,1865650,5123,0,0,2044269,5337,0,0,2222337,7082,0,0,2351242,64,0x7fe1911ece80,211159,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,14084,30468,9718,550,0,46325,262602.0,0.0,188.0,262414.0,64,0x7fe7d2a1ce80,32768,0,0,0,16384,16384,393216,22188411,960.0,513968.0,0.0,524288.0,1149551.0,32768.0,0,0,0,17545,131072.0,131072.0,0.0,131072.0,64,0x7f4de5d32e80,0,4712732,4096,4096,0,3515985,4096,4096,0,4245657,4096,4096,0,4063844,4096,4096,0,3872686,4096,4096,0,4132930,4096,4096,0,4675076,4096,4096,0,4689096,4096,4096,0,3922952,4096,4096,0,4090534,4096,4096,0,4892474,4096,4096,0,4278827,4096,4096,0,4251692,4096,4096,0,4273756,4096,4096,0,4518431,4096,4096,0,4217034,4096,4096,0,4014593,4096,4096,0,4739825,4096,4096,0,5042370,4096,4096,0,4759484,4096,4096,0,4090016,4096,4096,0,4403335,4096,4096,0,3774799,4096,4096,0,3925225,4096,4096,0,3961421,4096,4096,0,3338080,4096,4096,0,3782889,4096,4096,0,3674145,4096,4096,0,3999528,4096,4096,0,3901948,4096,4096,0,4932348,4096,4096,0,3862639,4096,4096,64,0x7fc56975ee80,0.0,2187711888967638,2187711888992278 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fb241eb8e80,4096,0,54,0,4096,0,931,0,4096,0,1850,0,4096,0,54,0,4096,0,737,0,4096,0,0,0,4096,0,1663,0,4096,0,564,0,4096,0,0,0,4096,0,1117,0,4097,0,469,0,4096,0,9010,0,4096,0,1160,0,4096,0,0,0,4096,0,7117,0,4096,0,0,0,4096,0,1471,0,4264,0,3064,0,4096,0,1122,0,4096,0,1584,0,4096,0,1067,0,4096,0,0,0,4096,0,713,0,4144,0,681,0,4097,0,0,0,4096,0,0,0,4097,0,1479,0,4144,0,138,0,4098,0,185,0,4102,0,0,0,4096,0,0,0,4096,0,207,0,64,0x7fd7ca83ae80,0,43351,0,0,0,43351,0,0,0,43351,0,0,0,43351,0,0,0,43351,0,0,0,43351,0,0,0,43351,0,0,0,43351,0,0,0,43351,0,0,0,43351,0,0,0,43351,0,0,0,43351,0,0,0,43351,0,0,0,43351,0,0,0,43351,0,0,0,43351,0,0,0,43351,0,0,0,43351,0,0,0,43351,0,0,0,43351,0,0,0,43351,0,0,0,43351,0,0,0,43351,0,0,0,43351,0,0,0,43351,0,0,0,43351,0,0,0,43351,0,0,0,43351,0,0,0,43351,0,0,0,43351,0,0,0,43351,0,0,0,43351,0,0,64,0x7f263e1dce80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,18932.0,117662.0,64,0x7f149630ee80,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8194,4098,8194,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8432,4336,8432,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,64,0x7fa99f246e80,340536,229865,3370581,16384,24587800,0,48,0,42566,42566,3737381.0,3075987.0,6281.0,824976.0,2098966.0,0.0,3067013.0,2756034.0,340528,239241,42566,0,42566,0,1362112.0,805459.0,0.0,0.0,64,0x7fd90d7dce80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,5941,39171,0,131481.0,131072.0,0.0,86594.0,64,0x7f83d783ae80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86427.0,0.0,131112.0,0.0,64,0x7fbb24b5ee80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7efe09b50e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131357.0,0.0,568.0,131356.0,64,0x7fb1b823ee80,131072.0,131072.0,0.0,2970933.0,0.0,0.0,110284011.0,58904655.0,64,0x7fcf01160e80,1151003,360448,163840,0,0,180224,114688,0,71281444.0,200018298.0,78240038.0,131072.0,0.0,628860.0,0,0,24785,69160.0,0.0,0.0,69160.0,64,0x7fcfd52a2e80,0,0,48,0,65536,65536,0,0,30017,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,457,41914,1686,0,48.0,209.0,0.0,262144.0,64,0x7fce5a68ee80,4070,0,0,1620369,4863,0,0,1694264,696,0,0,1377299,6044,0,0,1828172,4360,0,0,1645648,1647,0,0,1445584,3318,0,0,1558392,3221,0,0,1456153,1886,0,0,1438989,3490,0,0,1627068,3668,0,0,1597125,2921,0,0,1491060,3993,0,0,1598901,2369,0,0,1436705,3684,0,0,1577818,3629,0,0,1491670,4638,0,0,1611851,1761,0,0,1445719,3984,0,0,1592274,3879,0,0,1497282,3975,0,0,1634123,4259,0,0,1671451,3511,0,0,1615499,4519,0,0,1555584,4059,0,0,1557734,1417,0,0,1433702,2883,0,0,1526083,3516,0,0,1464299,5321,0,0,1647014,4956,0,0,1651478,3196,0,0,1576638,3800,0,0,1598790,64,0x7fe1911ece80,210158,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,14962,31346,8994,3815,0,42517,262494.0,0.0,47.0,262447.0,64,0x7fe7d2a1ce80,32768,0,0,0,16384,16384,393216,21395488,960.0,513966.0,0.0,524288.0,1069270.0,32768.0,0,0,0,14028,87897.0,87897.0,0.0,87897.0,64,0x7f4de5d32e80,0,3564724,2696,2696,0,3111606,2730,2730,0,3072322,2684,2684,0,5398995,2712,2712,0,3647837,2691,2691,0,3506042,2712,2712,0,3185045,2726,2726,0,3455556,2712,2712,0,3355101,2704,2704,0,2939774,2694,2694,0,2800177,2710,2710,0,3533046,2748,2748,0,2987663,2688,2688,0,3662756,2696,2696,0,3515357,2682,2682,0,2520552,2713,2713,0,3265340,2684,2684,0,3606741,2686,2686,0,3207425,2678,2678,0,4143903,2736,2736,0,2663910,2697,2697,0,4376675,2730,2730,0,3414215,2676,2676,0,3061055,2704,2704,0,2706507,2684,2684,0,3832554,2689,2689,0,3633620,2742,2742,0,3027550,2724,2724,0,2530279,2684,2684,0,2206823,2716,2716,0,3166076,2704,2704,0,2669931,2706,2706,64,0x7fc56975ee80,0.0,2187711889086198,2187711889105558 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fb241eb8e80,4096,0,614,0,4096,0,842,0,4096,0,85,0,4096,0,159,0,4096,0,332,0,4096,0,258,0,4096,0,0,0,4096,0,216,0,4096,0,71,0,4096,0,501,0,4097,0,874,0,4096,0,1393,0,4096,0,2748,0,4096,0,347,0,4096,0,1594,0,4096,0,39,0,4096,0,1521,0,4264,0,7728,0,4096,0,420,0,4096,0,1374,0,4096,0,430,0,4096,0,0,0,4096,0,1375,0,4144,0,306,0,4097,0,2130,0,4096,0,914,0,4097,0,852,0,4144,0,0,0,4098,0,148,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,64,0x7fd7ca83ae80,0,43023,0,0,0,43023,0,0,0,43023,0,0,0,43023,0,0,0,43023,0,0,0,43023,0,0,0,43023,0,0,0,43023,0,0,0,43023,0,0,0,43023,0,0,0,43023,0,0,0,43023,0,0,0,43023,0,0,0,43023,0,0,0,43023,0,0,0,43023,0,0,0,43023,0,0,0,43023,0,0,0,43023,0,0,0,43023,0,0,0,43023,0,0,0,43023,0,0,0,43023,0,0,0,43023,0,0,0,43023,0,0,0,43023,0,0,0,43023,0,0,0,43023,0,0,0,43023,0,0,0,43023,0,0,0,43023,0,0,0,43023,0,0,64,0x7f263e1dce80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,60142.0,155804.0,64,0x7f149630ee80,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8194,4098,8194,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8432,4336,8432,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,64,0x7fa99f246e80,343144,229378,3365780,16384,24852769,0,48,0,42892,42892,3730272.0,3074864.0,5735.0,886850.0,2132685.0,0.0,3065664.0,2755096.0,343136,238895,42892,0,42892,0,1372544.0,809720.0,0.0,0.0,64,0x7fd90d7dce80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,3992,37849,0,131485.0,131072.0,0.0,86580.0,64,0x7f83d783ae80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86452.0,0.0,131112.0,0.0,64,0x7fbb24b5ee80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7efe09b50e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131386.0,0.0,626.0,131385.0,64,0x7fb1b823ee80,131072.0,131072.0,0.0,2504136.0,0.0,0.0,125397901.0,48822562.0,64,0x7fcf01160e80,1139057,360448,163840,0,0,180224,114688,0,70922399.0,200417559.0,79842278.0,131072.0,0.0,619095.0,0,0,24913,75380.0,0.0,0.0,75380.0,64,0x7fcfd52a2e80,0,0,48,0,65536,65536,0,0,30008,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,458,41437,1684,0,48.0,206.0,0.0,262144.0,64,0x7fce5a68ee80,4474,0,0,1627101,3791,0,0,1559330,2817,0,0,1525808,6521,0,0,1871360,4090,0,0,1578209,2923,0,0,1486706,3586,0,0,1538756,3472,0,0,1486575,3286,0,0,1477313,3531,0,0,1531593,3358,0,0,1517035,3809,0,0,1596540,2608,0,0,1508946,3005,0,0,1497301,3277,0,0,1561134,3446,0,0,1489561,3289,0,0,1520477,3691,0,0,1551824,4333,0,0,1576990,3744,0,0,1537034,3303,0,0,1428850,3624,0,0,1507687,6528,0,0,1864567,4021,0,0,1623748,3258,0,0,1486494,3196,0,0,1461128,3500,0,0,1551119,4272,0,0,1637389,3694,0,0,1585698,4641,0,0,1617488,3861,0,0,1590662,4246,0,0,1659574,64,0x7fe1911ece80,191635,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,14123,30507,8941,3832,0,41565,262464.0,0.0,47.0,262417.0,64,0x7fe7d2a1ce80,32768,0,0,0,16384,16384,393216,21866768,960.0,513878.0,0.0,524288.0,1130476.0,32768.0,0,0,0,13810,86997.0,86997.0,0.0,86997.0,64,0x7f4de5d32e80,0,3553451,2698,2698,0,3517027,2698,2698,0,4247141,2692,2692,0,3849708,2718,2718,0,3603314,2677,2677,0,3271705,2724,2724,0,3840544,2728,2728,0,4691607,2718,2718,0,3392003,2694,2694,0,4356758,2676,2676,0,3640424,2710,2710,0,4292645,2750,2750,0,2812692,2692,2692,0,3365168,2669,2669,0,4795910,2722,2722,0,4271849,2709,2709,0,2890925,2680,2680,0,3831044,2690,2690,0,2918276,2710,2710,0,4888792,2728,2728,0,3707889,2676,2676,0,3223081,2725,2725,0,4410472,2700,2700,0,4116903,2726,2726,0,3351775,2677,2677,0,3547892,2696,2696,0,3166633,2744,2744,0,4635544,2730,2730,0,3488649,2690,2690,0,3053801,2689,2689,0,3418995,2746,2746,0,3626014,2712,2712,64,0x7fc56975ee80,0.0,2187711889126678,2187711889145878 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_1,obj_1,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_2,obj_2,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_3,obj_3,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_4,obj_4,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_5,obj_5,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_6,obj_6,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_7,obj_7,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_8,obj_8,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_9,obj_9,TCC_EA_ATOMIC_LEVEL_sum,wave_size_10,obj_10,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_11,obj_11,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_12,obj_12,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_13,obj_13,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_14,obj_14,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_15,obj_15,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_16,obj_16,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f69d2202e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131355.0,0.0,558.0,131354.0,64,0x7f80b7dcae80,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,64,0x7f09074bce80,0,0,192,0,65536,64477,48,1361,30817,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,538,46993,1710,0,48.0,223.0,0.0,262288.0,64,0x7f1fbcc16e80,131072.0,131072.0,0.0,2401475.0,0.0,0.0,124242912.0,59220180.0,64,0x7f2339a40e80,211138,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13048,29432,9842,550,0,46317,262608.0,0.0,188.0,262420.0,64,0x7fde3c94ce80,1878775,360448,163840,0,0,180224,114688,0,69894909.0,180908813.0,65456755.0,131072.0,0.0,648298.0,0,0,25969,81303.0,0.0,0.0,81303.0,64,0x7f075536ce80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,47188,0,131540.0,131072.0,0.0,131104.0,64,0x7f688fdc2e80,32768,0,0,0,16384,16384,393216,23122952,960.0,513926.0,0.0,524288.0,953338.0,32768.0,0,0,0,16936,131072.0,131072.0,0.0,131072.0,64,0x7f470fe8ae80,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f958f3cce80,0.0,64,0x7f761c6b0e80,4096,0,1128,0,4096,0,2253,0,4099,0,846,0,4096,0,1305,0,4096,0,1406,0,4096,0,0,0,4096,0,1364,0,4096,0,0,0,4096,0,2488,0,4096,0,2211,0,4144,0,486,0,4096,0,2499,0,4096,0,946,0,4096,0,7089,0,4096,0,1682,0,4096,0,0,0,4096,0,4589,0,4096,0,3591,0,4097,0,1732,0,4096,0,399,0,4096,0,775,0,4096,0,829,0,4096,0,3663,0,4216,0,664,0,4096,0,5833,0,4096,0,4597,0,4096,0,461,0,4096,0,0,0,4096,0,4137,0,4096,0,90,0,4096,0,267,0,4144,0,0,0,64,0x7efdecf5ce80,0,4882666,4096,4096,0,4315012,4096,4096,0,4476841,4096,4096,0,3912802,4096,4096,0,3390103,4096,4096,0,4277346,4096,4096,0,3258684,4096,4096,0,4092835,4096,4096,0,4790502,4096,4096,0,3490827,4096,4096,0,3457748,4096,4096,0,3128836,4096,4096,0,4988102,4096,4096,0,3379177,4096,4096,0,3755354,4096,4096,0,2659601,4096,4096,0,3647878,4096,4096,0,5216862,4096,4096,0,5485276,4096,4096,0,2689073,4096,4096,0,4594790,4096,4096,0,4774406,4096,4096,0,3905553,4096,4096,0,2957427,4096,4096,0,3385873,4096,4096,0,3163970,4096,4096,0,3686859,4096,4096,0,3458076,4096,4096,0,4241359,4096,4096,0,4170003,4096,4096,0,3269196,4096,4096,0,4551421,4096,4096,64,0x7fa00b4cae80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,87115.0,43957.0,131111.0,0.0,64,0x7f472dd2ae80,387016,233630,3414217,16384,25158558,144,48,0,48376,48376,3857066.0,3030825.0,6946.0,1037678.0,2051107.0,0.0,3021647.0,2710059.0,385303,243554,48376,0,48376,0,1548032.0,967341.0,0.0,0.0,64,0x7fdea5c62e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,53693.0,119588.0,64,0x7f3cbdc46e80,0,8192,4096,8192,0,8192,4096,8192,141,8195,4240,8336,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8360,4264,8360,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7fb120050e80,2027,0,0,1825912,3947,0,0,2070916,2144,0,0,1838162,3535,0,0,1974164,1942,0,0,1849379,1640,0,0,1769866,3008,0,0,1957094,2397,0,0,1977340,1128,0,0,1713467,1469,0,0,1836888,3938,0,0,2051117,2591,0,0,1896217,2505,0,0,1932320,1729,0,0,1820007,2338,0,0,1822817,1503,0,0,1773016,1467,0,0,1761135,1114,0,0,1722059,4956,0,0,2049123,2378,0,0,1895404,2957,0,0,1865355,2221,0,0,1865019,3188,0,0,1984519,3249,0,0,2007555,2504,0,0,1876894,950,0,0,1660382,6177,0,0,2201001,4101,0,0,2077845,2807,0,0,1934125,1518,0,0,1725891,3219,0,0,1961188,4664,0,0,2095589,194116676571166,194116676595486 +1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f69d2202e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131734.0,0.0,1322.0,131733.0,64,0x7f80b7dcae80,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,64,0x7f09074bce80,0,0,48,0,65536,65536,0,0,30004,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,457,41483,1756,0,48.0,203.0,0.0,262144.0,64,0x7f1fbcc16e80,131072.0,131072.0,0.0,2491310.0,0.0,0.0,109960527.0,37960389.0,64,0x7f2339a40e80,149423,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,12371,28755,8597,2428,0,41184,262433.0,0.0,47.0,262386.0,64,0x7fde3c94ce80,1325503,360448,163840,0,0,180224,114688,0,69020920.0,179384934.0,67818306.0,131072.0,0.0,710902.0,0,0,25828,57573.0,0.0,0.0,57573.0,64,0x7f075536ce80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,240.0,524288.0,0.0,0.0,0,0,5588,44149,1078,131909.0,131072.0,0.0,93433.0,64,0x7f688fdc2e80,32768,0,0,0,16384,16384,393216,23551080,960.0,513993.0,0.0,524288.0,909914.0,32768.0,0,0,0,14511,86716.0,86716.0,0.0,86716.0,64,0x7f470fe8ae80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f958f3cce80,0.0,64,0x7f761c6b0e80,4096,0,0,0,4096,0,322,0,4096,0,830,0,4096,0,197,0,4096,0,215,0,4096,0,754,0,4096,0,438,0,4098,0,280,0,4096,0,0,0,4096,0,800,0,4144,0,396,0,4097,0,8179,0,4096,0,444,0,4096,0,0,0,4096,0,995,0,4096,0,0,0,4096,0,689,0,4096,0,3183,0,4097,0,511,0,4096,0,991,0,4096,0,0,0,4096,0,91,0,4096,0,591,0,4216,0,433,0,4096,0,0,0,4097,0,484,0,4096,0,719,0,4096,0,0,0,4096,0,0,0,4096,0,433,0,4096,0,639,0,4144,0,363,0,64,0x7efdecf5ce80,0,4455261,2724,2724,0,2831778,2740,2740,0,3672359,2672,2672,0,3119734,2680,2680,0,4081614,2676,2676,0,2765774,2748,2748,0,3090099,2682,2682,0,4186396,2690,2690,0,4053287,2702,2702,0,3171033,2719,2719,0,2838616,2705,2705,0,4110556,2716,2716,0,4200362,2706,2706,0,3786327,2712,2712,0,3494750,2681,2681,0,3993452,2680,2680,0,4126363,2690,2690,0,3851237,2705,2705,0,3789524,2692,2692,0,3704780,2696,2696,0,4088835,2712,2712,0,4293048,2731,2731,0,3377943,2688,2688,0,3095349,2675,2675,0,4205647,2690,2690,0,5094923,2708,2708,0,3002549,2704,2704,0,3469424,2684,2684,0,3564544,2724,2724,0,3540920,2729,2729,0,4042738,2706,2706,0,3469019,2680,2680,64,0x7fa00b4cae80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,87290.0,0.0,131112.0,0.0,64,0x7f472dd2ae80,380584,231131,3348462,16384,23567267,0,48,0,47572,47572,3756915.0,3067444.0,6559.0,1220484.0,2078956.0,0.0,3057436.0,2746209.0,380576,240825,47572,0,47572,977,1522304.0,845079.0,0.0,0.0,64,0x7fdea5c62e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,76859.0,140552.0,64,0x7f3cbdc46e80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8362,4266,8362,0,8192,4096,8192,0,8193,4097,8193,47,8193,4144,8240,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7fb120050e80,3570,0,0,1696906,1757,0,0,1410916,3193,0,0,1609150,4152,0,0,1721417,5259,0,0,1830601,817,0,0,1283728,1483,0,0,1424629,725,0,0,1346660,1728,0,0,1370028,1952,0,0,1516038,838,0,0,1289218,1632,0,0,1458473,831,0,0,1221025,3727,0,0,1687681,893,0,0,1283193,2558,0,0,1587276,952,0,0,1324301,2099,0,0,1576361,2055,0,0,1518370,1295,0,0,1414906,1647,0,0,1344793,1541,0,0,1440963,4439,0,0,1730681,6584,0,0,1897334,1675,0,0,1452641,1550,0,0,1485876,2872,0,0,1651929,3836,0,0,1698706,1157,0,0,1349765,1936,0,0,1490784,2431,0,0,1558439,3806,0,0,1672864,194116676615646,194116676634206 +2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f69d2202e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131320.0,0.0,494.0,131319.0,64,0x7f80b7dcae80,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,64,0x7f09074bce80,0,0,48,0,65536,65536,0,0,31039,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,457,42457,1743,0,48.0,224.0,0.0,262144.0,64,0x7f1fbcc16e80,131072.0,131072.0,0.0,2347788.0,0.0,0.0,127170115.0,48008462.0,64,0x7f2339a40e80,185700,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,10428,26812,8524,2539,0,41029,262467.0,0.0,47.0,262420.0,64,0x7fde3c94ce80,1576509,360448,163840,0,0,180224,114688,0,71542653.0,190382994.0,68240330.0,131072.0,0.0,743773.0,0,0,25858,93202.0,0.0,0.0,93202.0,64,0x7f075536ce80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,2790,40033,0,131395.0,131072.0,0.0,86956.0,64,0x7f688fdc2e80,32768,0,0,0,16384,16384,393216,23274918,960.0,513912.0,0.0,524288.0,1037782.0,32768.0,0,0,0,13449,86514.0,86514.0,0.0,86514.0,64,0x7f470fe8ae80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f958f3cce80,0.0,64,0x7f761c6b0e80,4096,0,1191,0,4096,0,699,0,4096,0,236,0,4096,0,0,0,4096,0,658,0,4096,0,206,0,4096,0,0,0,4098,0,1273,0,4096,0,1663,0,4096,0,13,0,4144,0,372,0,4097,0,1699,0,4096,0,756,0,4096,0,143,0,4096,0,1123,0,4096,0,0,0,4096,0,1637,0,4096,0,1970,0,4097,0,268,0,4096,0,145,0,4096,0,244,0,4096,0,7021,0,4096,0,0,0,4216,0,0,0,4096,0,1085,0,4097,0,162,0,4096,0,590,0,4096,0,117,0,4096,0,1504,0,4096,0,214,0,4096,0,18,0,4144,0,203,0,64,0x7efdecf5ce80,0,3789727,2708,2708,0,4145600,2707,2707,0,3932662,2656,2656,0,4125888,2696,2696,0,3594798,2698,2698,0,3494827,2740,2740,0,3307567,2714,2714,0,4032329,2708,2708,0,4479334,2704,2704,0,3967079,2704,2704,0,3573241,2688,2688,0,4158832,2736,2736,0,3510227,2706,2706,0,4272727,2708,2708,0,3662961,2674,2674,0,4262311,2674,2674,0,4833370,2697,2697,0,3906428,2713,2713,0,3977740,2696,2696,0,4376696,2708,2708,0,4824920,2712,2712,0,4923431,2748,2748,0,3385540,2696,2696,0,4625894,2692,2692,0,3513986,2704,2704,0,4125405,2689,2689,0,3506967,2742,2742,0,3174388,2678,2678,0,3730756,2734,2734,0,4871593,2685,2685,0,3710968,2724,2724,0,3475452,2696,2696,64,0x7fa00b4cae80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86695.0,0.0,131112.0,0.0,64,0x7f472dd2ae80,334496,224843,3296742,16384,24356490,0,48,0,41811,41811,3662176.0,3009269.0,5876.0,991004.0,2061252.0,0.0,3000693.0,2689802.0,334488,234109,41811,0,41811,0,1337952.0,790729.0,0.0,0.0,64,0x7fdea5c62e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,59427.0,126090.0,64,0x7f3cbdc46e80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8372,4276,8372,0,8192,4096,8192,0,8193,4097,8193,47,8193,4144,8240,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7fb120050e80,4247,0,0,1679600,3503,0,0,1582477,3308,0,0,1631995,4362,0,0,1696865,4815,0,0,1710487,1461,0,0,1432848,2807,0,0,1607771,2642,0,0,1570268,885,0,0,1218049,1403,0,0,1400418,5220,0,0,1805574,2701,0,0,1662686,2361,0,0,1529643,1249,0,0,1404184,1528,0,0,1525621,717,0,0,1342620,2102,0,0,1455186,561,0,0,1217845,3764,0,0,1638630,1359,0,0,1404365,1478,0,0,1415279,2509,0,0,1507952,6369,0,0,1756437,7466,0,0,1902456,2341,0,0,1428084,1435,0,0,1340307,4209,0,0,1708167,5138,0,0,1712099,2524,0,0,1507465,1449,0,0,1389305,2328,0,0,1522256,297,0,0,1275174,194116676727326,194116676746366 diff --git a/tests/workloads/join_type_grid/MI100/sysinfo.csv b/tests/workloads/join_type_grid/MI100/sysinfo.csv index eb1041203e..2d0391f20a 100644 --- a/tests/workloads/join_type_grid/MI100/sysinfo.csv +++ b/tests/workloads/join_type_grid/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -join_type_grid,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Fri Mar 1 16:43:39 2024 (CST),1,t006-003.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651240,,5.7.1-98,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +join_type_grid,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 07 Mar 2024 01:06:09 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/join_type_grid/MI100/timestamps.csv b/tests/workloads/join_type_grid/MI100/timestamps.csv index 671e7e15c4..82c5599f3f 100644 --- a/tests/workloads/join_type_grid/MI100/timestamps.csv +++ b/tests/workloads/join_type_grid/MI100/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,2816260,2816260,1048576,256,0,0,8,8,16,64,0x0,0x7fc915b30e80,2187711888941454,2187711888967638,2187711888992278,2187711889004612 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,2816260,2816260,1048576,256,0,0,8,8,16,64,0x0,0x7fc915b30e80,2187711889005083,2187711889086198,2187711889105558,2187711889106393 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,2816260,2816260,1048576,256,0,0,8,8,16,64,0x0,0x7fc915b30e80,2187711889117424,2187711889126678,2187711889145878,2187711889146569 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,122400,122400,1048576,256,0,0,8,8,16,64,0x0,0x7f4349e02e80,194116676544295,194116676571166,194116676595486,194116676616381 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,122400,122400,1048576,256,0,0,8,8,16,64,0x0,0x7f4349e02e80,194116676607995,194116676615646,194116676634206,194116676725127 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,122400,122400,1048576,256,0,0,8,8,16,64,0x0,0x7f4349e02e80,194116676645276,194116676727326,194116676746366,194116676747299 diff --git a/tests/workloads/join_type_grid/MI200/SQ_IFETCH_LEVEL.csv b/tests/workloads/join_type_grid/MI200/SQ_IFETCH_LEVEL.csv new file mode 100644 index 0000000000..ab02c81f08 --- /dev/null +++ b/tests/workloads/join_type_grid/MI200/SQ_IFETCH_LEVEL.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,268795,268795,1048576,256,0,0,8,0,16,64,0x0,0x7f3875f94ec0,27374,27374,16384,65536,13435,1482776,197831630573234,197844341953097,197844341974057,197831646365049 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,268795,268795,1048576,256,0,0,8,0,16,64,0x0,0x7f3875f94ec0,41961,41961,16384,65536,9034,1048676,197831646388163,197844342059817,197844342076617,197831646690244 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,268795,268795,1048576,256,0,0,8,0,16,64,0x0,0x7f3875f94ec0,40396,40396,16384,65536,9362,1048708,197831646720141,197844342096937,197844342112777,197831646881486 diff --git a/tests/workloads/join_type_grid/MI200/SQ_INST_LEVEL_LDS.csv b/tests/workloads/join_type_grid/MI200/SQ_INST_LEVEL_LDS.csv new file mode 100644 index 0000000000..320769e4f3 --- /dev/null +++ b/tests/workloads/join_type_grid/MI200/SQ_INST_LEVEL_LDS.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,268979,268979,1048576,256,0,0,8,0,16,64,0x0,0x7f6a88b28ec0,0,0,0,197832117662258,197844341953097,197844341974057,197832133615228 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,268979,268979,1048576,256,0,0,8,0,16,64,0x0,0x7f6a88b28ec0,0,0,0,197832133634524,197844342059817,197844342076617,197832133945623 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,268979,268979,1048576,256,0,0,8,0,16,64,0x0,0x7f6a88b28ec0,0,0,0,197832133972123,197844342096937,197844342112777,197832134122668 diff --git a/tests/workloads/join_type_grid/MI200/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/join_type_grid/MI200/SQ_INST_LEVEL_SMEM.csv new file mode 100644 index 0000000000..cd375daec3 --- /dev/null +++ b/tests/workloads/join_type_grid/MI200/SQ_INST_LEVEL_SMEM.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,269164,269164,1048576,256,0,0,8,0,16,64,0x0,0x7f70c5ab0ec0,65536,172876,19306104,197832602591055,197844341953097,197844341974057,197832618916540 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,269164,269164,1048576,256,0,0,8,0,16,64,0x0,0x7f70c5ab0ec0,65536,225082,25263696,197832618933692,197844342059817,197844342076617,197832619241725 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,269164,269164,1048576,256,0,0,8,0,16,64,0x0,0x7f70c5ab0ec0,65536,223104,25083768,197832619268415,197844342096937,197844342112777,197832619429540 diff --git a/tests/workloads/join_type_grid/MI200/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/join_type_grid/MI200/SQ_INST_LEVEL_VMEM.csv new file mode 100644 index 0000000000..dc5d376a15 --- /dev/null +++ b/tests/workloads/join_type_grid/MI200/SQ_INST_LEVEL_VMEM.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,269364,269364,1048576,256,0,0,8,0,16,64,0x0,0x7f8ebb654ec0,32768,293577,32894296,197833079703706,197844341953097,197844341974057,197833095734944 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,269364,269364,1048576,256,0,0,8,0,16,64,0x0,0x7f8ebb654ec0,32768,595549,66696720,197833095754490,197844342059817,197844342076617,197833096028789 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,269364,269364,1048576,256,0,0,8,0,16,64,0x0,0x7f8ebb654ec0,32768,591031,66199820,197833096054588,197844342096937,197844342112777,197833096222225 diff --git a/tests/workloads/join_type_grid/MI200/SQ_LEVEL_WAVES.csv b/tests/workloads/join_type_grid/MI200/SQ_LEVEL_WAVES.csv new file mode 100644 index 0000000000..154bd95d72 --- /dev/null +++ b/tests/workloads/join_type_grid/MI200/SQ_LEVEL_WAVES.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,269547,269547,1048576,256,0,0,8,0,16,64,0x0,0x7f01b4c28ec0,27994,27994,11084,223960,16384,11107366,131595,0,44938912,197833559590174,197844341953097,197844341974057,197833575321725 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,269547,269547,1048576,256,0,0,8,0,16,64,0x0,0x7f01b4c28ec0,41763,41763,13589,334112,16384,19618427,225469,0,78963024,197833575346992,197844342059817,197844342076617,197833575660425 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,269547,269547,1048576,256,0,0,8,0,16,64,0x0,0x7f01b4c28ec0,41696,41696,13755,333576,16384,19502404,225614,0,78488224,197833575695722,197844342096937,197844342112777,197833575860744 diff --git a/tests/workloads/join_type_grid/MI200/perfmon/SQ_IFETCH_LEVEL.txt b/tests/workloads/join_type_grid/MI200/perfmon/SQ_IFETCH_LEVEL.txt new file mode 100644 index 0000000000..293092f641 --- /dev/null +++ b/tests/workloads/join_type_grid/MI200/perfmon/SQ_IFETCH_LEVEL.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/join_type_grid/MI200/perfmon/SQ_INST_LEVEL_LDS.txt b/tests/workloads/join_type_grid/MI200/perfmon/SQ_INST_LEVEL_LDS.txt new file mode 100644 index 0000000000..08439eedce --- /dev/null +++ b/tests/workloads/join_type_grid/MI200/perfmon/SQ_INST_LEVEL_LDS.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/join_type_grid/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt b/tests/workloads/join_type_grid/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt new file mode 100644 index 0000000000..6cca322d4e --- /dev/null +++ b/tests/workloads/join_type_grid/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/join_type_grid/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt b/tests/workloads/join_type_grid/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt new file mode 100644 index 0000000000..e527ad31ba --- /dev/null +++ b/tests/workloads/join_type_grid/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/join_type_grid/MI200/perfmon/SQ_LEVEL_WAVES.txt b/tests/workloads/join_type_grid/MI200/perfmon/SQ_LEVEL_WAVES.txt new file mode 100644 index 0000000000..3f8e04adb3 --- /dev/null +++ b/tests/workloads/join_type_grid/MI200/perfmon/SQ_LEVEL_WAVES.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_0.txt b/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_0.txt new file mode 100644 index 0000000000..4ffdc32149 --- /dev/null +++ b/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_0.txt @@ -0,0 +1,5 @@ +pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES SQ_INSTS_VALU_CVT SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU GRBM_COUNT GRBM_GUI_ACTIVE TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum TA_TA_BUSY_sum TA_BUFFER_WAVEFRONTS_sum TD_TD_BUSY_sum TD_TC_STALL_sum SPI_CSN_WINDOW_VALID SPI_CSN_BUSY CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_1.txt b/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_1.txt new file mode 100644 index 0000000000..6c277f4a37 --- /dev/null +++ b/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_1.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VSKIPPED SQ_INSTS SQ_INSTS_VALU SQ_INSTS_VALU_ADD_F16 SQ_INSTS_VALU_MUL_F16 SQ_INSTS_VALU_FMA_F16 SQ_INSTS_VALU_TRANS_F16 SQ_INSTS_VALU_ADD_F32 GRBM_SPI_BUSY TCP_READ_TAGCONFLICT_STALL_CYCLES_sum TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum TCP_TA_TCP_STATE_READ_sum TA_BUFFER_READ_WAVEFRONTS_sum TA_BUFFER_WRITE_WAVEFRONTS_sum TD_SPI_STALL_sum TD_LOAD_WAVEFRONT_sum SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_10.txt b/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_10.txt new file mode 100644 index 0000000000..7053d4dce6 --- /dev/null +++ b/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_10.txt @@ -0,0 +1,5 @@ +pmc: SQC_TC_DATA_WRITE_REQ SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES + +gpu: +range: +kernel: diff --git a/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_11.txt b/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_11.txt new file mode 100644 index 0000000000..77ae8b461f --- /dev/null +++ b/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_11.txt @@ -0,0 +1,5 @@ +pmc: SQC_ICACHE_MISSES_DUPLICATE SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE + +gpu: +range: +kernel: diff --git a/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_12.txt b/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_12.txt new file mode 100644 index 0000000000..dfb2cf65e5 --- /dev/null +++ b/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_12.txt @@ -0,0 +1,5 @@ +pmc: SQC_DCACHE_REQ_READ_1 SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 + +gpu: +range: +kernel: diff --git a/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_13.txt b/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_13.txt new file mode 100644 index 0000000000..062fc9644a --- /dev/null +++ b/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_13.txt @@ -0,0 +1,5 @@ +pmc: TCC_ATOMIC[0] TCC_CYCLE[0] TCC_EA_ATOMIC[0] TCC_EA_ATOMIC_LEVEL[0] TCC_ATOMIC[1] TCC_CYCLE[1] TCC_EA_ATOMIC[1] TCC_EA_ATOMIC_LEVEL[1] TCC_ATOMIC[2] TCC_CYCLE[2] TCC_EA_ATOMIC[2] TCC_EA_ATOMIC_LEVEL[2] TCC_ATOMIC[3] TCC_CYCLE[3] TCC_EA_ATOMIC[3] TCC_EA_ATOMIC_LEVEL[3] TCC_ATOMIC[4] TCC_CYCLE[4] TCC_EA_ATOMIC[4] TCC_EA_ATOMIC_LEVEL[4] TCC_ATOMIC[5] TCC_CYCLE[5] TCC_EA_ATOMIC[5] TCC_EA_ATOMIC_LEVEL[5] TCC_ATOMIC[6] TCC_CYCLE[6] TCC_EA_ATOMIC[6] TCC_EA_ATOMIC_LEVEL[6] TCC_ATOMIC[7] TCC_CYCLE[7] TCC_EA_ATOMIC[7] TCC_EA_ATOMIC_LEVEL[7] TCC_ATOMIC[8] TCC_CYCLE[8] TCC_EA_ATOMIC[8] TCC_EA_ATOMIC_LEVEL[8] TCC_ATOMIC[9] TCC_CYCLE[9] TCC_EA_ATOMIC[9] TCC_EA_ATOMIC_LEVEL[9] TCC_ATOMIC[10] TCC_CYCLE[10] TCC_EA_ATOMIC[10] TCC_EA_ATOMIC_LEVEL[10] TCC_ATOMIC[11] TCC_CYCLE[11] TCC_EA_ATOMIC[11] TCC_EA_ATOMIC_LEVEL[11] TCC_ATOMIC[12] TCC_CYCLE[12] TCC_EA_ATOMIC[12] TCC_EA_ATOMIC_LEVEL[12] TCC_ATOMIC[13] TCC_CYCLE[13] TCC_EA_ATOMIC[13] TCC_EA_ATOMIC_LEVEL[13] TCC_ATOMIC[14] TCC_CYCLE[14] TCC_EA_ATOMIC[14] TCC_EA_ATOMIC_LEVEL[14] TCC_ATOMIC[15] TCC_CYCLE[15] TCC_EA_ATOMIC[15] TCC_EA_ATOMIC_LEVEL[15] TCC_ATOMIC[16] TCC_CYCLE[16] TCC_EA_ATOMIC[16] TCC_EA_ATOMIC_LEVEL[16] TCC_ATOMIC[17] TCC_CYCLE[17] TCC_EA_ATOMIC[17] TCC_EA_ATOMIC_LEVEL[17] TCC_ATOMIC[18] TCC_CYCLE[18] TCC_EA_ATOMIC[18] TCC_EA_ATOMIC_LEVEL[18] TCC_ATOMIC[19] TCC_CYCLE[19] TCC_EA_ATOMIC[19] TCC_EA_ATOMIC_LEVEL[19] TCC_ATOMIC[20] TCC_CYCLE[20] TCC_EA_ATOMIC[20] TCC_EA_ATOMIC_LEVEL[20] TCC_ATOMIC[21] TCC_CYCLE[21] TCC_EA_ATOMIC[21] TCC_EA_ATOMIC_LEVEL[21] TCC_ATOMIC[22] TCC_CYCLE[22] TCC_EA_ATOMIC[22] TCC_EA_ATOMIC_LEVEL[22] TCC_ATOMIC[23] TCC_CYCLE[23] TCC_EA_ATOMIC[23] TCC_EA_ATOMIC_LEVEL[23] TCC_ATOMIC[24] TCC_CYCLE[24] TCC_EA_ATOMIC[24] TCC_EA_ATOMIC_LEVEL[24] TCC_ATOMIC[25] TCC_CYCLE[25] TCC_EA_ATOMIC[25] TCC_EA_ATOMIC_LEVEL[25] TCC_ATOMIC[26] TCC_CYCLE[26] TCC_EA_ATOMIC[26] TCC_EA_ATOMIC_LEVEL[26] TCC_ATOMIC[27] TCC_CYCLE[27] TCC_EA_ATOMIC[27] TCC_EA_ATOMIC_LEVEL[27] TCC_ATOMIC[28] TCC_CYCLE[28] TCC_EA_ATOMIC[28] TCC_EA_ATOMIC_LEVEL[28] TCC_ATOMIC[29] TCC_CYCLE[29] TCC_EA_ATOMIC[29] TCC_EA_ATOMIC_LEVEL[29] TCC_ATOMIC[30] TCC_CYCLE[30] TCC_EA_ATOMIC[30] TCC_EA_ATOMIC_LEVEL[30] TCC_ATOMIC[31] TCC_CYCLE[31] TCC_EA_ATOMIC[31] TCC_EA_ATOMIC_LEVEL[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_14.txt b/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_14.txt new file mode 100644 index 0000000000..e0698dbf57 --- /dev/null +++ b/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_14.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_EA_RDREQ_GMI_CREDIT_STALL[0] TCC_EA_RDREQ[1] TCC_EA_RDREQ_32B[1] TCC_EA_RDREQ_DRAM_CREDIT_STALL[1] TCC_EA_RDREQ_GMI_CREDIT_STALL[1] TCC_EA_RDREQ[2] TCC_EA_RDREQ_32B[2] TCC_EA_RDREQ_DRAM_CREDIT_STALL[2] TCC_EA_RDREQ_GMI_CREDIT_STALL[2] TCC_EA_RDREQ[3] TCC_EA_RDREQ_32B[3] TCC_EA_RDREQ_DRAM_CREDIT_STALL[3] TCC_EA_RDREQ_GMI_CREDIT_STALL[3] TCC_EA_RDREQ[4] TCC_EA_RDREQ_32B[4] TCC_EA_RDREQ_DRAM_CREDIT_STALL[4] TCC_EA_RDREQ_GMI_CREDIT_STALL[4] TCC_EA_RDREQ[5] TCC_EA_RDREQ_32B[5] TCC_EA_RDREQ_DRAM_CREDIT_STALL[5] TCC_EA_RDREQ_GMI_CREDIT_STALL[5] TCC_EA_RDREQ[6] TCC_EA_RDREQ_32B[6] TCC_EA_RDREQ_DRAM_CREDIT_STALL[6] TCC_EA_RDREQ_GMI_CREDIT_STALL[6] TCC_EA_RDREQ[7] TCC_EA_RDREQ_32B[7] TCC_EA_RDREQ_DRAM_CREDIT_STALL[7] TCC_EA_RDREQ_GMI_CREDIT_STALL[7] TCC_EA_RDREQ[8] TCC_EA_RDREQ_32B[8] TCC_EA_RDREQ_DRAM_CREDIT_STALL[8] TCC_EA_RDREQ_GMI_CREDIT_STALL[8] TCC_EA_RDREQ[9] TCC_EA_RDREQ_32B[9] TCC_EA_RDREQ_DRAM_CREDIT_STALL[9] TCC_EA_RDREQ_GMI_CREDIT_STALL[9] TCC_EA_RDREQ[10] TCC_EA_RDREQ_32B[10] TCC_EA_RDREQ_DRAM_CREDIT_STALL[10] TCC_EA_RDREQ_GMI_CREDIT_STALL[10] TCC_EA_RDREQ[11] TCC_EA_RDREQ_32B[11] TCC_EA_RDREQ_DRAM_CREDIT_STALL[11] TCC_EA_RDREQ_GMI_CREDIT_STALL[11] TCC_EA_RDREQ[12] TCC_EA_RDREQ_32B[12] TCC_EA_RDREQ_DRAM_CREDIT_STALL[12] TCC_EA_RDREQ_GMI_CREDIT_STALL[12] TCC_EA_RDREQ[13] TCC_EA_RDREQ_32B[13] TCC_EA_RDREQ_DRAM_CREDIT_STALL[13] TCC_EA_RDREQ_GMI_CREDIT_STALL[13] TCC_EA_RDREQ[14] TCC_EA_RDREQ_32B[14] TCC_EA_RDREQ_DRAM_CREDIT_STALL[14] TCC_EA_RDREQ_GMI_CREDIT_STALL[14] TCC_EA_RDREQ[15] TCC_EA_RDREQ_32B[15] TCC_EA_RDREQ_DRAM_CREDIT_STALL[15] TCC_EA_RDREQ_GMI_CREDIT_STALL[15] TCC_EA_RDREQ[16] TCC_EA_RDREQ_32B[16] TCC_EA_RDREQ_DRAM_CREDIT_STALL[16] TCC_EA_RDREQ_GMI_CREDIT_STALL[16] TCC_EA_RDREQ[17] TCC_EA_RDREQ_32B[17] TCC_EA_RDREQ_DRAM_CREDIT_STALL[17] TCC_EA_RDREQ_GMI_CREDIT_STALL[17] TCC_EA_RDREQ[18] TCC_EA_RDREQ_32B[18] TCC_EA_RDREQ_DRAM_CREDIT_STALL[18] TCC_EA_RDREQ_GMI_CREDIT_STALL[18] TCC_EA_RDREQ[19] TCC_EA_RDREQ_32B[19] TCC_EA_RDREQ_DRAM_CREDIT_STALL[19] TCC_EA_RDREQ_GMI_CREDIT_STALL[19] TCC_EA_RDREQ[20] TCC_EA_RDREQ_32B[20] TCC_EA_RDREQ_DRAM_CREDIT_STALL[20] TCC_EA_RDREQ_GMI_CREDIT_STALL[20] TCC_EA_RDREQ[21] TCC_EA_RDREQ_32B[21] TCC_EA_RDREQ_DRAM_CREDIT_STALL[21] TCC_EA_RDREQ_GMI_CREDIT_STALL[21] TCC_EA_RDREQ[22] TCC_EA_RDREQ_32B[22] TCC_EA_RDREQ_DRAM_CREDIT_STALL[22] TCC_EA_RDREQ_GMI_CREDIT_STALL[22] TCC_EA_RDREQ[23] TCC_EA_RDREQ_32B[23] TCC_EA_RDREQ_DRAM_CREDIT_STALL[23] TCC_EA_RDREQ_GMI_CREDIT_STALL[23] TCC_EA_RDREQ[24] TCC_EA_RDREQ_32B[24] TCC_EA_RDREQ_DRAM_CREDIT_STALL[24] TCC_EA_RDREQ_GMI_CREDIT_STALL[24] TCC_EA_RDREQ[25] TCC_EA_RDREQ_32B[25] TCC_EA_RDREQ_DRAM_CREDIT_STALL[25] TCC_EA_RDREQ_GMI_CREDIT_STALL[25] TCC_EA_RDREQ[26] TCC_EA_RDREQ_32B[26] TCC_EA_RDREQ_DRAM_CREDIT_STALL[26] TCC_EA_RDREQ_GMI_CREDIT_STALL[26] TCC_EA_RDREQ[27] TCC_EA_RDREQ_32B[27] TCC_EA_RDREQ_DRAM_CREDIT_STALL[27] TCC_EA_RDREQ_GMI_CREDIT_STALL[27] TCC_EA_RDREQ[28] TCC_EA_RDREQ_32B[28] TCC_EA_RDREQ_DRAM_CREDIT_STALL[28] TCC_EA_RDREQ_GMI_CREDIT_STALL[28] TCC_EA_RDREQ[29] TCC_EA_RDREQ_32B[29] TCC_EA_RDREQ_DRAM_CREDIT_STALL[29] TCC_EA_RDREQ_GMI_CREDIT_STALL[29] TCC_EA_RDREQ[30] TCC_EA_RDREQ_32B[30] TCC_EA_RDREQ_DRAM_CREDIT_STALL[30] TCC_EA_RDREQ_GMI_CREDIT_STALL[30] TCC_EA_RDREQ[31] TCC_EA_RDREQ_32B[31] TCC_EA_RDREQ_DRAM_CREDIT_STALL[31] TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_15.txt b/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_15.txt new file mode 100644 index 0000000000..77ad088669 --- /dev/null +++ b/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_15.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ[0] TCC_EA_WRREQ_64B[0] TCC_EA_RDREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_LEVEL[1] TCC_EA_WRREQ[1] TCC_EA_WRREQ_64B[1] TCC_EA_RDREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_LEVEL[2] TCC_EA_WRREQ[2] TCC_EA_WRREQ_64B[2] TCC_EA_RDREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_LEVEL[3] TCC_EA_WRREQ[3] TCC_EA_WRREQ_64B[3] TCC_EA_RDREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_LEVEL[4] TCC_EA_WRREQ[4] TCC_EA_WRREQ_64B[4] TCC_EA_RDREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_LEVEL[5] TCC_EA_WRREQ[5] TCC_EA_WRREQ_64B[5] TCC_EA_RDREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_LEVEL[6] TCC_EA_WRREQ[6] TCC_EA_WRREQ_64B[6] TCC_EA_RDREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_LEVEL[7] TCC_EA_WRREQ[7] TCC_EA_WRREQ_64B[7] TCC_EA_RDREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_LEVEL[8] TCC_EA_WRREQ[8] TCC_EA_WRREQ_64B[8] TCC_EA_RDREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_LEVEL[9] TCC_EA_WRREQ[9] TCC_EA_WRREQ_64B[9] TCC_EA_RDREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_LEVEL[10] TCC_EA_WRREQ[10] TCC_EA_WRREQ_64B[10] TCC_EA_RDREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_LEVEL[11] TCC_EA_WRREQ[11] TCC_EA_WRREQ_64B[11] TCC_EA_RDREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_LEVEL[12] TCC_EA_WRREQ[12] TCC_EA_WRREQ_64B[12] TCC_EA_RDREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_LEVEL[13] TCC_EA_WRREQ[13] TCC_EA_WRREQ_64B[13] TCC_EA_RDREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_LEVEL[14] TCC_EA_WRREQ[14] TCC_EA_WRREQ_64B[14] TCC_EA_RDREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_LEVEL[15] TCC_EA_WRREQ[15] TCC_EA_WRREQ_64B[15] TCC_EA_RDREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_LEVEL[16] TCC_EA_WRREQ[16] TCC_EA_WRREQ_64B[16] TCC_EA_RDREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_LEVEL[17] TCC_EA_WRREQ[17] TCC_EA_WRREQ_64B[17] TCC_EA_RDREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_LEVEL[18] TCC_EA_WRREQ[18] TCC_EA_WRREQ_64B[18] TCC_EA_RDREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_LEVEL[19] TCC_EA_WRREQ[19] TCC_EA_WRREQ_64B[19] TCC_EA_RDREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_LEVEL[20] TCC_EA_WRREQ[20] TCC_EA_WRREQ_64B[20] TCC_EA_RDREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_LEVEL[21] TCC_EA_WRREQ[21] TCC_EA_WRREQ_64B[21] TCC_EA_RDREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_LEVEL[22] TCC_EA_WRREQ[22] TCC_EA_WRREQ_64B[22] TCC_EA_RDREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_LEVEL[23] TCC_EA_WRREQ[23] TCC_EA_WRREQ_64B[23] TCC_EA_RDREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_LEVEL[24] TCC_EA_WRREQ[24] TCC_EA_WRREQ_64B[24] TCC_EA_RDREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_LEVEL[25] TCC_EA_WRREQ[25] TCC_EA_WRREQ_64B[25] TCC_EA_RDREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_LEVEL[26] TCC_EA_WRREQ[26] TCC_EA_WRREQ_64B[26] TCC_EA_RDREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_LEVEL[27] TCC_EA_WRREQ[27] TCC_EA_WRREQ_64B[27] TCC_EA_RDREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_LEVEL[28] TCC_EA_WRREQ[28] TCC_EA_WRREQ_64B[28] TCC_EA_RDREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_LEVEL[29] TCC_EA_WRREQ[29] TCC_EA_WRREQ_64B[29] TCC_EA_RDREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_LEVEL[30] TCC_EA_WRREQ[30] TCC_EA_WRREQ_64B[30] TCC_EA_RDREQ_IO_CREDIT_STALL[31] TCC_EA_RDREQ_LEVEL[31] TCC_EA_WRREQ[31] TCC_EA_WRREQ_64B[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_16.txt b/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_16.txt new file mode 100644 index 0000000000..d0628bb948 --- /dev/null +++ b/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_16.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_WRREQ_IO_CREDIT_STALL[0] TCC_EA_WRREQ_LEVEL[0] TCC_EA_WRREQ_DRAM_CREDIT_STALL[1] TCC_EA_WRREQ_GMI_CREDIT_STALL[1] TCC_EA_WRREQ_IO_CREDIT_STALL[1] TCC_EA_WRREQ_LEVEL[1] TCC_EA_WRREQ_DRAM_CREDIT_STALL[2] TCC_EA_WRREQ_GMI_CREDIT_STALL[2] TCC_EA_WRREQ_IO_CREDIT_STALL[2] TCC_EA_WRREQ_LEVEL[2] TCC_EA_WRREQ_DRAM_CREDIT_STALL[3] TCC_EA_WRREQ_GMI_CREDIT_STALL[3] TCC_EA_WRREQ_IO_CREDIT_STALL[3] TCC_EA_WRREQ_LEVEL[3] TCC_EA_WRREQ_DRAM_CREDIT_STALL[4] TCC_EA_WRREQ_GMI_CREDIT_STALL[4] TCC_EA_WRREQ_IO_CREDIT_STALL[4] TCC_EA_WRREQ_LEVEL[4] TCC_EA_WRREQ_DRAM_CREDIT_STALL[5] TCC_EA_WRREQ_GMI_CREDIT_STALL[5] TCC_EA_WRREQ_IO_CREDIT_STALL[5] TCC_EA_WRREQ_LEVEL[5] TCC_EA_WRREQ_DRAM_CREDIT_STALL[6] TCC_EA_WRREQ_GMI_CREDIT_STALL[6] TCC_EA_WRREQ_IO_CREDIT_STALL[6] TCC_EA_WRREQ_LEVEL[6] TCC_EA_WRREQ_DRAM_CREDIT_STALL[7] TCC_EA_WRREQ_GMI_CREDIT_STALL[7] TCC_EA_WRREQ_IO_CREDIT_STALL[7] TCC_EA_WRREQ_LEVEL[7] TCC_EA_WRREQ_DRAM_CREDIT_STALL[8] TCC_EA_WRREQ_GMI_CREDIT_STALL[8] TCC_EA_WRREQ_IO_CREDIT_STALL[8] TCC_EA_WRREQ_LEVEL[8] TCC_EA_WRREQ_DRAM_CREDIT_STALL[9] TCC_EA_WRREQ_GMI_CREDIT_STALL[9] TCC_EA_WRREQ_IO_CREDIT_STALL[9] TCC_EA_WRREQ_LEVEL[9] TCC_EA_WRREQ_DRAM_CREDIT_STALL[10] TCC_EA_WRREQ_GMI_CREDIT_STALL[10] TCC_EA_WRREQ_IO_CREDIT_STALL[10] TCC_EA_WRREQ_LEVEL[10] TCC_EA_WRREQ_DRAM_CREDIT_STALL[11] TCC_EA_WRREQ_GMI_CREDIT_STALL[11] TCC_EA_WRREQ_IO_CREDIT_STALL[11] TCC_EA_WRREQ_LEVEL[11] TCC_EA_WRREQ_DRAM_CREDIT_STALL[12] TCC_EA_WRREQ_GMI_CREDIT_STALL[12] TCC_EA_WRREQ_IO_CREDIT_STALL[12] TCC_EA_WRREQ_LEVEL[12] TCC_EA_WRREQ_DRAM_CREDIT_STALL[13] TCC_EA_WRREQ_GMI_CREDIT_STALL[13] TCC_EA_WRREQ_IO_CREDIT_STALL[13] TCC_EA_WRREQ_LEVEL[13] TCC_EA_WRREQ_DRAM_CREDIT_STALL[14] TCC_EA_WRREQ_GMI_CREDIT_STALL[14] TCC_EA_WRREQ_IO_CREDIT_STALL[14] TCC_EA_WRREQ_LEVEL[14] TCC_EA_WRREQ_DRAM_CREDIT_STALL[15] TCC_EA_WRREQ_GMI_CREDIT_STALL[15] TCC_EA_WRREQ_IO_CREDIT_STALL[15] TCC_EA_WRREQ_LEVEL[15] TCC_EA_WRREQ_DRAM_CREDIT_STALL[16] TCC_EA_WRREQ_GMI_CREDIT_STALL[16] TCC_EA_WRREQ_IO_CREDIT_STALL[16] TCC_EA_WRREQ_LEVEL[16] TCC_EA_WRREQ_DRAM_CREDIT_STALL[17] TCC_EA_WRREQ_GMI_CREDIT_STALL[17] TCC_EA_WRREQ_IO_CREDIT_STALL[17] TCC_EA_WRREQ_LEVEL[17] TCC_EA_WRREQ_DRAM_CREDIT_STALL[18] TCC_EA_WRREQ_GMI_CREDIT_STALL[18] TCC_EA_WRREQ_IO_CREDIT_STALL[18] TCC_EA_WRREQ_LEVEL[18] TCC_EA_WRREQ_DRAM_CREDIT_STALL[19] TCC_EA_WRREQ_GMI_CREDIT_STALL[19] TCC_EA_WRREQ_IO_CREDIT_STALL[19] TCC_EA_WRREQ_LEVEL[19] TCC_EA_WRREQ_DRAM_CREDIT_STALL[20] TCC_EA_WRREQ_GMI_CREDIT_STALL[20] TCC_EA_WRREQ_IO_CREDIT_STALL[20] TCC_EA_WRREQ_LEVEL[20] TCC_EA_WRREQ_DRAM_CREDIT_STALL[21] TCC_EA_WRREQ_GMI_CREDIT_STALL[21] TCC_EA_WRREQ_IO_CREDIT_STALL[21] TCC_EA_WRREQ_LEVEL[21] TCC_EA_WRREQ_DRAM_CREDIT_STALL[22] TCC_EA_WRREQ_GMI_CREDIT_STALL[22] TCC_EA_WRREQ_IO_CREDIT_STALL[22] TCC_EA_WRREQ_LEVEL[22] TCC_EA_WRREQ_DRAM_CREDIT_STALL[23] TCC_EA_WRREQ_GMI_CREDIT_STALL[23] TCC_EA_WRREQ_IO_CREDIT_STALL[23] TCC_EA_WRREQ_LEVEL[23] TCC_EA_WRREQ_DRAM_CREDIT_STALL[24] TCC_EA_WRREQ_GMI_CREDIT_STALL[24] TCC_EA_WRREQ_IO_CREDIT_STALL[24] TCC_EA_WRREQ_LEVEL[24] TCC_EA_WRREQ_DRAM_CREDIT_STALL[25] TCC_EA_WRREQ_GMI_CREDIT_STALL[25] TCC_EA_WRREQ_IO_CREDIT_STALL[25] TCC_EA_WRREQ_LEVEL[25] TCC_EA_WRREQ_DRAM_CREDIT_STALL[26] TCC_EA_WRREQ_GMI_CREDIT_STALL[26] TCC_EA_WRREQ_IO_CREDIT_STALL[26] TCC_EA_WRREQ_LEVEL[26] TCC_EA_WRREQ_DRAM_CREDIT_STALL[27] TCC_EA_WRREQ_GMI_CREDIT_STALL[27] TCC_EA_WRREQ_IO_CREDIT_STALL[27] TCC_EA_WRREQ_LEVEL[27] TCC_EA_WRREQ_DRAM_CREDIT_STALL[28] TCC_EA_WRREQ_GMI_CREDIT_STALL[28] TCC_EA_WRREQ_IO_CREDIT_STALL[28] TCC_EA_WRREQ_LEVEL[28] TCC_EA_WRREQ_DRAM_CREDIT_STALL[29] TCC_EA_WRREQ_GMI_CREDIT_STALL[29] TCC_EA_WRREQ_IO_CREDIT_STALL[29] TCC_EA_WRREQ_LEVEL[29] TCC_EA_WRREQ_DRAM_CREDIT_STALL[30] TCC_EA_WRREQ_GMI_CREDIT_STALL[30] TCC_EA_WRREQ_IO_CREDIT_STALL[30] TCC_EA_WRREQ_LEVEL[30] TCC_EA_WRREQ_DRAM_CREDIT_STALL[31] TCC_EA_WRREQ_GMI_CREDIT_STALL[31] TCC_EA_WRREQ_IO_CREDIT_STALL[31] TCC_EA_WRREQ_LEVEL[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_17.txt b/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_17.txt new file mode 100644 index 0000000000..343869c5f1 --- /dev/null +++ b/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_17.txt @@ -0,0 +1,5 @@ +pmc: TCC_HIT[0] TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_HIT[1] TCC_MISS[1] TCC_READ[1] TCC_REQ[1] TCC_HIT[2] TCC_MISS[2] TCC_READ[2] TCC_REQ[2] TCC_HIT[3] TCC_MISS[3] TCC_READ[3] TCC_REQ[3] TCC_HIT[4] TCC_MISS[4] TCC_READ[4] TCC_REQ[4] TCC_HIT[5] TCC_MISS[5] TCC_READ[5] TCC_REQ[5] TCC_HIT[6] TCC_MISS[6] TCC_READ[6] TCC_REQ[6] TCC_HIT[7] TCC_MISS[7] TCC_READ[7] TCC_REQ[7] TCC_HIT[8] TCC_MISS[8] TCC_READ[8] TCC_REQ[8] TCC_HIT[9] TCC_MISS[9] TCC_READ[9] TCC_REQ[9] TCC_HIT[10] TCC_MISS[10] TCC_READ[10] TCC_REQ[10] TCC_HIT[11] TCC_MISS[11] TCC_READ[11] TCC_REQ[11] TCC_HIT[12] TCC_MISS[12] TCC_READ[12] TCC_REQ[12] TCC_HIT[13] TCC_MISS[13] TCC_READ[13] TCC_REQ[13] TCC_HIT[14] TCC_MISS[14] TCC_READ[14] TCC_REQ[14] TCC_HIT[15] TCC_MISS[15] TCC_READ[15] TCC_REQ[15] TCC_HIT[16] TCC_MISS[16] TCC_READ[16] TCC_REQ[16] TCC_HIT[17] TCC_MISS[17] TCC_READ[17] TCC_REQ[17] TCC_HIT[18] TCC_MISS[18] TCC_READ[18] TCC_REQ[18] TCC_HIT[19] TCC_MISS[19] TCC_READ[19] TCC_REQ[19] TCC_HIT[20] TCC_MISS[20] TCC_READ[20] TCC_REQ[20] TCC_HIT[21] TCC_MISS[21] TCC_READ[21] TCC_REQ[21] TCC_HIT[22] TCC_MISS[22] TCC_READ[22] TCC_REQ[22] TCC_HIT[23] TCC_MISS[23] TCC_READ[23] TCC_REQ[23] TCC_HIT[24] TCC_MISS[24] TCC_READ[24] TCC_REQ[24] TCC_HIT[25] TCC_MISS[25] TCC_READ[25] TCC_REQ[25] TCC_HIT[26] TCC_MISS[26] TCC_READ[26] TCC_REQ[26] TCC_HIT[27] TCC_MISS[27] TCC_READ[27] TCC_REQ[27] TCC_HIT[28] TCC_MISS[28] TCC_READ[28] TCC_REQ[28] TCC_HIT[29] TCC_MISS[29] TCC_READ[29] TCC_REQ[29] TCC_HIT[30] TCC_MISS[30] TCC_READ[30] TCC_REQ[30] TCC_HIT[31] TCC_MISS[31] TCC_READ[31] TCC_REQ[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_18.txt b/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_18.txt new file mode 100644 index 0000000000..a74cefd281 --- /dev/null +++ b/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_18.txt @@ -0,0 +1,5 @@ +pmc: TCC_RW_REQ[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_RW_REQ[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_WRITE[1] TCC_RW_REQ[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_WRITE[2] TCC_RW_REQ[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_WRITE[3] TCC_RW_REQ[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_WRITE[4] TCC_RW_REQ[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_WRITE[5] TCC_RW_REQ[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_WRITE[6] TCC_RW_REQ[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_WRITE[7] TCC_RW_REQ[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_WRITE[8] TCC_RW_REQ[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_WRITE[9] TCC_RW_REQ[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_WRITE[10] TCC_RW_REQ[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_WRITE[11] TCC_RW_REQ[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_WRITE[12] TCC_RW_REQ[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_WRITE[13] TCC_RW_REQ[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_WRITE[14] TCC_RW_REQ[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_WRITE[15] TCC_RW_REQ[16] TCC_TOO_MANY_EA_WRREQS_STALL[16] TCC_WRITE[16] TCC_RW_REQ[17] TCC_TOO_MANY_EA_WRREQS_STALL[17] TCC_WRITE[17] TCC_RW_REQ[18] TCC_TOO_MANY_EA_WRREQS_STALL[18] TCC_WRITE[18] TCC_RW_REQ[19] TCC_TOO_MANY_EA_WRREQS_STALL[19] TCC_WRITE[19] TCC_RW_REQ[20] TCC_TOO_MANY_EA_WRREQS_STALL[20] TCC_WRITE[20] TCC_RW_REQ[21] TCC_TOO_MANY_EA_WRREQS_STALL[21] TCC_WRITE[21] TCC_RW_REQ[22] TCC_TOO_MANY_EA_WRREQS_STALL[22] TCC_WRITE[22] TCC_RW_REQ[23] TCC_TOO_MANY_EA_WRREQS_STALL[23] TCC_WRITE[23] TCC_RW_REQ[24] TCC_TOO_MANY_EA_WRREQS_STALL[24] TCC_WRITE[24] TCC_RW_REQ[25] TCC_TOO_MANY_EA_WRREQS_STALL[25] TCC_WRITE[25] TCC_RW_REQ[26] TCC_TOO_MANY_EA_WRREQS_STALL[26] TCC_WRITE[26] TCC_RW_REQ[27] TCC_TOO_MANY_EA_WRREQS_STALL[27] TCC_WRITE[27] TCC_RW_REQ[28] TCC_TOO_MANY_EA_WRREQS_STALL[28] TCC_WRITE[28] TCC_RW_REQ[29] TCC_TOO_MANY_EA_WRREQS_STALL[29] TCC_WRITE[29] TCC_RW_REQ[30] TCC_TOO_MANY_EA_WRREQS_STALL[30] TCC_WRITE[30] TCC_RW_REQ[31] TCC_TOO_MANY_EA_WRREQS_STALL[31] TCC_WRITE[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_2.txt b/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_2.txt new file mode 100644 index 0000000000..70b69f8928 --- /dev/null +++ b/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_2.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_MUL_F32 SQ_INSTS_VALU_FMA_F32 SQ_INSTS_VALU_TRANS_F32 SQ_INSTS_VALU_ADD_F64 SQ_INSTS_VALU_MUL_F64 SQ_INSTS_VALU_FMA_F64 SQ_INSTS_VALU_TRANS_F64 SQ_INSTS_VALU_INT32 TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum TA_BUFFER_ATOMIC_WAVEFRONTS_sum TA_BUFFER_TOTAL_CYCLES_sum TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_3.txt b/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_3.txt new file mode 100644 index 0000000000..e47f8e33c9 --- /dev/null +++ b/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_3.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_INT64 SQ_INSTS_SMEM SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum TD_COALESCABLE_WAVEFRONT_sum SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE CPF_CMP_UTCL1_STALL_ON_TRANSLATION TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_4.txt b/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_4.txt new file mode 100644 index 0000000000..2d96f365a9 --- /dev/null +++ b/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_4.txt @@ -0,0 +1,5 @@ +pmc: SQ_WAVE_CYCLES SQ_WAIT_ANY SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_BUSY_CU_CYCLES SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE TCC_EA_WRREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WR_UNCACHED_32B_sum TCC_EA_WRREQ_DRAM_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_5.txt b/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_5.txt new file mode 100644 index 0000000000..e50beed390 --- /dev/null +++ b/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_5.txt @@ -0,0 +1,5 @@ +pmc: SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU TCP_TCP_LATENCY_sum TCP_TCC_READ_REQ_LATENCY_sum TCP_TCC_WRITE_REQ_LATENCY_sum TCP_TCC_READ_REQ_sum TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN CPC_ME1_DC0_SPI_BUSY TCC_EA_WRREQ_STALL_sum TCC_EA_RDREQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RD_UNCACHED_32B_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_6.txt b/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_6.txt new file mode 100644 index 0000000000..15a2277c1b --- /dev/null +++ b/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_6.txt @@ -0,0 +1,5 @@ +pmc: SQ_THREAD_CYCLES_VALU SQ_IFETCH SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TCP_TCC_NC_READ_REQ_sum TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN TCC_EA_RDREQ_DRAM_sum TCC_TAG_STALL_sum TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_7.txt b/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_7.txt new file mode 100644 index 0000000000..b42ce91618 --- /dev/null +++ b/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_7.txt @@ -0,0 +1,5 @@ +pmc: SQ_WAVES_LT_32 SQ_WAVES_LT_16 SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TCP_TCC_UC_WRITE_REQ_sum TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR TCC_NORMAL_EVICT_sum TCC_ALL_TC_OP_INV_EVICT_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA_ATOMIC_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_8.txt b/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_8.txt new file mode 100644 index 0000000000..21d4c7a998 --- /dev/null +++ b/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_8.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM_NORM SQ_INSTS_MFMA SQ_INSTS_VALU_MFMA_I8 SQ_INSTS_VALU_MFMA_F16 SQ_INSTS_VALU_MFMA_BF16 SQ_INSTS_VALU_MFMA_F32 SQ_INSTS_VALU_MFMA_F64 SQ_VALU_MFMA_BUSY_CYCLES TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TCP_TCC_CC_ATOMIC_REQ_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN TCC_EA_RDREQ_LEVEL_sum TCC_EA_WRREQ_LEVEL_sum TCC_EA_ATOMIC_LEVEL_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_9.txt b/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_9.txt new file mode 100644 index 0000000000..9ffe5778c3 --- /dev/null +++ b/tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_9.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_FLAT_LDS_ONLY SQ_INSTS_VALU_MFMA_MOPS_I8 SQ_INSTS_VALU_MFMA_MOPS_F16 SQ_INSTS_VALU_MFMA_MOPS_BF16 SQ_INSTS_VALU_MFMA_MOPS_F32 SQ_INSTS_VALU_MFMA_MOPS_F64 SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum TCP_PENDING_STALL_CYCLES_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/join_type_grid/MI200/perfmon/timestamps.txt b/tests/workloads/join_type_grid/MI200/perfmon/timestamps.txt new file mode 100644 index 0000000000..676cca1b80 --- /dev/null +++ b/tests/workloads/join_type_grid/MI200/perfmon/timestamps.txt @@ -0,0 +1,5 @@ +pmc: + +gpu: +range: +kernel: diff --git a/tests/workloads/join_type_grid/MI200/pmc_perf.csv b/tests/workloads/join_type_grid/MI200/pmc_perf.csv new file mode 100644 index 0000000000..4aad1beca8 --- /dev/null +++ b/tests/workloads/join_type_grid/MI200/pmc_perf.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_DRAM_sum,TCC_TAG_STALL_sum,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,wave_size_1,obj_1,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_2,obj_2,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_3,obj_3,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_4,obj_4,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,wave_size_5,obj_5,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_6,obj_6,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,TD_COALESCABLE_WAVEFRONT_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_7,obj_7,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_8,obj_8,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,TCC_EA_ATOMIC_LEVEL_sum,wave_size_9,obj_9,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_10,obj_10,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_11,obj_11,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_12,obj_12,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_13,obj_13,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,wave_size_14,obj_14,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_15,obj_15,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_16,obj_16,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_17,obj_17,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_18,obj_18,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f8219bd4ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131080.0,33301.0,46111.0,19425.0,64,0x7fb8b6fd4ec0,2229,4096,2229,6325,2294,4096,2294,6390,2285,4101,2290,6386,2290,4096,2290,6386,2237,4096,2237,6333,2293,4096,2293,6389,2277,4096,2277,6373,2296,4096,2296,6392,2298,4096,2298,6394,2232,4096,2232,6328,2293,4096,2293,6389,2287,4096,2287,6383,2288,4096,2288,6384,2240,4096,2240,6336,2298,4097,2299,6395,2276,4096,2276,6372,2282,4096,2282,6378,2316,4097,2317,6413,2269,4097,2270,6366,2271,4096,2271,6367,2275,4096,2275,6371,2287,4096,2287,6383,2279,4096,2279,6375,2452,4098,2454,6550,2285,4096,2285,6381,2283,4096,2283,6379,2267,4096,2267,6363,2271,4096,2271,6367,2270,4096,2270,6366,2277,4096,2277,6373,2291,4096,2291,6387,2277,4096,2277,6373,64,0x7f28659a0ec0,32768,32768,0,64,0x7f67610acec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13364,18796,8402,545,0,27442,203985.0,0.0,72905.0,131080.0,64,0x7f7390f20ec0,114688,0,32768,32768,16384,16384,65536,49152,27600530.0,88074395.0,39774833.0,131072.0,0.0,226745.0,0,0,15332,2099.0,131084.0,0.0,16.0,64,0x7ffa3c3e8ec0,10662847,9620852,697931,344064,1605485,0,0,163840,832.0,515136.0,0.0,524288.0,270332.0,32768.0,465143,0,0,11101,131072.0,131072.0,0.0,131072.0,64,0x7fa841cb8ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,10188,0,818,28498,0,73091.0,131072.0,0.0,65571.0,64,0x7feaf8264ec0,0,0,0,1010297,0,0,0,1205994,0,0,0,965878,0,0,0,1072759,123,0,0,1161639,0,0,0,1124670,0,0,0,993668,0,0,0,1119435,0,0,0,993244,0,0,0,992961,0,0,0,1137637,0,0,0,1078361,0,0,0,996449,0,0,0,1108712,306,0,0,1309156,0,0,0,1092686,0,0,0,1161945,0,0,0,1146745,0,0,0,1091460,0,0,0,1150877,0,0,0,1016505,0,0,0,1134661,0,0,0,1099405,0,0,0,1193689,0,0,0,1128075,0,0,0,1015156,0,0,0,1076809,0,0,0,1209301,0,0,0,1111766,0,0,0,1117718,0,0,0,1045141,0,0,0,1104540,64,0x7f4c38760ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,41282079.0,35751621.0,0.0,64,0x7f34e1488ec0,4096,0,0,0,4096,0,0,0,4096,0,298,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,12,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4099,0,0,0,4099,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,116,0,64,0x7fd4443e8ec0,231088,129063,16384,0,16384,16384,32768,49152,28885,28885,1955608.0,1373203.0,3754.0,165838.0,1069114.0,0.0,1364828.0,1065832.0,229377,137184,28885,0,28885,0,924320.0,493058.0,0.0,0.0,64,0x7f596a470ec0,0,0,0,0,0,0,168,56,131072.0,131072.0,0.0,924928.0,64,0x7f12afa38ec0,1284,115449,0,0,65536,63800,56,1680,64,0x7efd09584ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65551.0,0.0,0.0,0.0,64,0x7f499dd68ec0,6382,0,4096,6404,0,4096,6357,0,4096,6364,0,4096,6368,0,4096,6355,0,4096,6325,0,4096,6376,0,4096,6376,0,4096,6384,0,4096,6405,0,4096,6362,0,4096,6364,0,4096,6373,0,4096,6361,0,4096,6326,0,4096,6397,0,4096,6361,0,4096,6354,0,4096,6377,0,4096,6372,0,4096,6423,0,4096,6348,0,4096,6572,0,4096,6410,0,4096,6398,0,4096,6364,0,4096,6354,0,4096,6373,0,4096,6374,0,4096,6419,0,4096,6352,0,4096,64,0x7f0e35368ec0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,64,0x7f7222850ec0,0,0,0,224,0,65536,64210,56,64,0x7fc809a60ec0,0,1222409,4096,4096,0,1302727,4096,4096,0,1356041,4096,4096,0,1334083,4096,4096,0,1271855,4096,4096,0,1504049,4096,4096,0,1130210,4096,4096,0,1307177,4096,4096,0,1220555,4096,4096,0,1114533,4096,4096,0,1208079,4096,4096,0,1233047,4096,4096,0,1374161,4096,4096,0,1335796,4096,4096,0,1197253,4096,4096,0,1352839,4096,4096,0,1255753,4096,4096,0,1316838,4096,4096,0,1091375,4096,4096,0,1539189,4096,4096,0,1300862,4096,4096,0,1247546,4096,4096,0,1316370,4096,4096,0,1182013,4096,4096,0,1396198,4096,4096,0,1207880,4096,4096,0,1211839,4096,4096,0,1179703,4096,4096,0,1160592,4096,4096,0,1261145,4096,4096,0,1121675,4096,4096,0,1384759,4096,4096,64,0x7f33184f8ec0,0,393216,163840,0,0,0,0,0,17516,0.0,0.0,0.0,32768.0,0.0,0.0,399.0,32768.0,4096,16384,352,28026,2157,0,56.0,5.0,0.0,204159.0,197844341953097,197844341974057 +1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f8219bd4ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131083.0,99055.0,45546.0,0.0,64,0x7fb8b6fd4ec0,2156,4096,2156,6252,2142,4096,2142,6238,2135,4101,2140,6236,2142,4096,2142,6238,2145,4096,2145,6241,2159,4096,2159,6255,2149,4096,2149,6245,2158,4096,2158,6254,2164,4096,2164,6260,2153,4096,2153,6249,2141,4096,2141,6237,2139,4096,2139,6235,2142,4096,2142,6238,2145,4096,2145,6241,2156,4097,2157,6253,2149,4096,2149,6245,2154,4097,2155,6251,2230,4097,2231,6327,2141,4097,2142,6238,2148,4096,2148,6244,2148,4096,2148,6244,2154,4098,2156,6252,2167,4096,2167,6263,2165,4096,2165,6261,2165,4096,2165,6261,2155,4096,2155,6251,2174,4096,2174,6270,2144,4096,2144,6240,2147,4096,2147,6243,2150,4096,2150,6246,2153,4096,2153,6249,2174,4096,2174,6270,64,0x7f28659a0ec0,32768,32768,0,64,0x7f67610acec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,27332,27234,8880,550,0,35961,200365.0,0.0,69290.0,131075.0,64,0x7f7390f20ec0,114688,0,32768,32768,16384,16384,65536,49152,58908740.0,201592118.0,44567153.0,131072.0,0.0,568390.0,0,0,25658,5211.0,131085.0,0.0,24.0,64,0x7ffa3c3e8ec0,19391063,17952502,1094497,344064,2791220,0,0,163840,832.0,515136.0,0.0,524288.0,640095.0,32768.0,1022544,0,0,14126,91208.0,91208.0,0.0,91208.0,64,0x7fa841cb8ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,23172,0,3579,39602,0,69614.0,131072.0,0.0,45643.0,64,0x7feaf8264ec0,252,0,0,1996095,364,0,0,2121606,0,0,0,1756899,257,0,0,2138562,0,0,0,1966917,2087,0,0,2926074,145,0,0,1741464,0,0,0,2037348,0,0,0,1937336,0,0,0,1703304,290,0,0,1907139,31,0,0,1905018,3,0,0,2142949,445,0,0,2148298,0,0,0,2066979,507,0,0,1904322,292,0,0,2090429,0,0,0,1662207,0,0,0,1502967,472,0,0,2290706,118,0,0,2052461,413,0,0,2335740,0,0,0,1644030,0,0,0,1913009,0,0,0,1943825,559,0,0,2132393,0,0,0,1845826,116,0,0,1880531,17,0,0,1885777,0,0,0,1799122,133,0,0,2017165,211,0,0,2134717,64,0x7f4c38760ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,119970001.0,56535132.0,0.0,64,0x7f34e1488ec0,4096,0,0,0,4096,0,128,0,4096,0,376,0,4096,0,369,0,4096,0,194,0,4096,0,1740,0,4096,0,0,0,4096,0,1251,0,4097,0,631,0,4096,0,0,0,4096,0,269,0,4096,0,0,0,4097,0,2,0,4096,0,1,0,4097,0,542,0,4096,0,0,0,4096,0,1066,0,4096,0,2088,0,4097,0,733,0,4096,0,306,0,4096,0,383,0,4096,0,19,0,4096,0,2121,0,4096,0,2007,0,4099,0,541,0,4096,0,151,0,4096,0,1809,0,4096,0,48,0,4097,0,651,0,4098,0,3,0,4096,0,0,0,4096,0,542,0,64,0x7fd4443e8ec0,328880,220244,16384,0,16384,16384,32768,49152,41109,41109,3138900.0,2456048.0,3847.0,343411.0,1792770.0,0.0,2442986.0,2134347.0,328872,229229,41109,0,41109,0,1315488.0,779252.0,0.0,0.0,64,0x7f596a470ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2041505.0,64,0x7f12afa38ec0,0,190653,0,0,65536,63800,56,1680,64,0x7efd09584ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65550.0,0.0,0.0,0.0,64,0x7f499dd68ec0,6286,0,4096,6274,0,4096,6274,0,4096,6261,0,4096,6243,0,4096,6244,0,4096,6244,0,4096,6258,0,4096,6255,0,4096,6292,0,4096,6279,0,4096,6277,0,4096,6264,0,4096,6248,0,4096,6247,0,4096,6244,0,4096,6267,0,4096,6249,0,4096,6270,0,4096,6248,0,4096,6249,0,4096,6259,0,4096,6244,0,4096,6247,0,4096,6250,0,4096,6266,0,4096,6245,0,4096,6271,0,4096,6253,0,4096,6242,0,4096,6257,0,4096,6250,0,4096,64,0x7f0e35368ec0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,64,0x7f7222850ec0,0,0,0,56,0,65536,65536,0,64,0x7fc809a60ec0,0,2744594,2836,2836,0,5416069,2872,2872,0,3378193,2848,2848,0,3202107,2820,2820,0,3626216,2884,2884,0,4579554,2856,2856,0,2579320,2892,2892,0,4268680,2852,2852,0,3182503,2848,2848,0,3100945,2832,2832,0,2961554,2880,2880,0,2927444,2848,2848,0,3122292,2820,2820,0,4400137,2884,2884,0,3741985,2856,2856,0,3228068,2892,2892,0,3329799,2848,2848,0,2993407,2878,2878,0,3398330,2860,2860,0,3685781,2860,2860,0,2626384,2812,2812,0,3286665,2860,2860,0,3143182,2844,2844,0,3705295,2850,2850,0,3730003,2848,2848,0,2932908,2852,2852,0,2948310,2880,2880,0,3430493,2860,2860,0,2804760,2856,2856,0,2883802,2812,2812,0,2641071,2856,2856,0,2825556,2844,2844,64,0x7f33184f8ec0,0,393216,163840,0,0,0,0,0,29393,0.0,0.0,0.0,32768.0,0.0,0.0,237.0,32768.0,4096,16384,302,40429,1936,0,56.0,9.0,0.0,201064.0,197844342059817,197844342076617 +2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f8219bd4ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131084.0,85898.0,45692.0,0.0,64,0x7fb8b6fd4ec0,2185,4096,2185,6281,2179,4096,2179,6275,2172,4101,2177,6273,2173,4096,2173,6269,2179,4096,2179,6275,2199,4096,2199,6295,2186,4096,2186,6282,2201,4096,2201,6297,2201,4096,2201,6297,2182,4096,2182,6278,2184,4096,2184,6280,2172,4096,2172,6268,2172,4096,2172,6268,2180,4096,2180,6276,2200,4097,2201,6297,2189,4096,2189,6285,2213,4097,2214,6310,2265,4097,2266,6362,2166,4097,2167,6263,2166,4096,2166,6262,2185,4096,2185,6281,2190,4098,2192,6288,2208,4096,2208,6304,2186,4096,2186,6282,2186,4096,2186,6282,2218,4096,2218,6314,2211,4096,2211,6307,2169,4096,2169,6265,2166,4096,2166,6262,2187,4096,2187,6283,2184,4096,2184,6280,2208,4096,2208,6304,64,0x7f28659a0ec0,32768,32768,0,64,0x7f67610acec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,29872,27145,9771,3011,0,39089,200551.0,0.0,69468.0,131083.0,64,0x7f7390f20ec0,114688,0,32768,32768,16384,16384,65536,49152,56545889.0,196016443.0,47805110.0,131072.0,0.0,506043.0,0,0,25452,9004.0,131088.0,0.0,30.0,64,0x7ffa3c3e8ec0,19281669,17915533,1022072,344064,2794785,0,0,163840,832.0,515156.0,0.0,524288.0,543776.0,32768.0,1008504,0,0,13428,91062.0,91062.0,0.0,91062.0,64,0x7fa841cb8ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,21299,0,3201,38468,0,69727.0,131072.0,0.0,45609.0,64,0x7feaf8264ec0,0,0,0,1636856,91,0,0,1759257,0,0,0,1500771,0,0,0,2179376,0,0,0,1865353,0,0,0,1955465,254,0,0,1608139,84,0,0,2248820,334,0,0,1931047,152,0,0,1606182,672,0,0,2470605,0,0,0,1704716,213,0,0,1856647,14,0,0,1756608,21,0,0,1821685,350,0,0,1851164,0,0,0,1783520,0,0,0,1975559,0,0,0,1420386,231,0,0,2130494,196,0,0,1889017,0,0,0,1935297,185,0,0,1712951,0,0,0,2069704,0,0,0,1564384,0,0,0,1692698,0,0,0,1565693,293,0,0,2083546,417,0,0,1948398,0,0,0,1844399,0,0,0,1598763,369,0,0,1762484,64,0x7f4c38760ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,120877902.0,60992876.0,0.0,64,0x7f34e1488ec0,4096,0,0,0,4096,0,320,0,4096,0,880,0,4096,0,324,0,4096,0,280,0,4096,0,1200,0,4096,0,96,0,4096,0,508,0,4097,0,112,0,4096,0,1,0,4096,0,11,0,4096,0,2433,0,4097,0,248,0,4096,0,0,0,4097,0,282,0,4096,0,128,0,4096,0,970,0,4096,0,563,0,4097,0,0,0,4096,0,281,0,4096,0,384,0,4096,0,394,0,4096,0,0,0,4096,0,210,0,4098,0,660,0,4096,0,2,0,4096,0,226,0,4096,0,377,0,4097,0,0,0,4098,0,399,0,4096,0,363,0,4096,0,0,0,64,0x7fd4443e8ec0,324072,217506,16384,0,16384,16384,32768,49152,40508,40508,3104469.0,2410672.0,4728.0,354900.0,1708183.0,0.0,2399106.0,2090110.0,324064,226637,40508,0,40508,0,1296256.0,771834.0,0.0,0.0,64,0x7f596a470ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2029773.0,64,0x7f12afa38ec0,0,183665,0,0,65536,63800,56,1680,64,0x7efd09584ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65554.0,0.0,0.0,0.0,64,0x7f499dd68ec0,6253,0,4096,6257,0,4096,6269,0,4096,6282,0,4096,6286,0,4096,6293,0,4096,6263,0,4096,6249,0,4096,6246,0,4096,6252,0,4096,6264,0,4096,6272,0,4096,6289,0,4096,6292,0,4096,6292,0,4096,6266,0,4096,6294,0,4096,6279,0,4096,6241,0,4096,6252,0,4096,6252,0,4096,6274,0,4096,6299,0,4096,6265,0,4096,6266,0,4096,6296,0,4096,6279,0,4096,6244,0,4096,6254,0,4096,6255,0,4096,6277,0,4096,6297,0,4096,64,0x7f0e35368ec0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,64,0x7f7222850ec0,0,0,0,56,0,65536,65536,0,64,0x7fc809a60ec0,0,3756839,2828,2828,0,4265889,2856,2856,0,4035033,2848,2848,0,4488624,2840,2840,0,2872436,2888,2888,0,3289530,2856,2856,0,2955224,2852,2852,0,4395018,2804,2804,0,3142593,2804,2804,0,2783675,2828,2828,0,3214670,2856,2856,0,3308008,2848,2848,0,4744349,2832,2832,0,2815373,2888,2888,0,5380790,2856,2856,0,3508411,2856,2856,0,3018342,2804,2804,0,3753540,2828,2828,0,3567803,2840,2840,0,3536128,2860,2860,0,5112421,2824,2824,0,3337315,2856,2856,0,3196234,2836,2836,0,3495189,2838,2838,0,3175295,2840,2840,0,2689358,2804,2804,0,3138631,2828,2828,0,3978952,2844,2844,0,2965545,2858,2858,0,4732657,2826,2826,0,3317425,2862,2862,0,3437194,2836,2836,64,0x7f33184f8ec0,0,393216,163840,0,0,0,0,0,29277,0.0,0.0,0.0,32768.0,0.0,0.0,206.0,32768.0,4096,16384,302,40412,2004,0,56.0,10.0,0.0,200839.0,197844342096937,197844342112777 diff --git a/tests/workloads/join_type_grid/MI200/roofline.csv b/tests/workloads/join_type_grid/MI200/roofline.csv new file mode 100644 index 0000000000..8f9e7cf7a2 --- /dev/null +++ b/tests/workloads/join_type_grid/MI200/roofline.csv @@ -0,0 +1,5 @@ +device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh +0,1389.0038,1388.3987,1389.6089,5015.1157,5012.2314,5018,9223.8711,9223.167,9224.5752,18053.973,18052.926,18055.02,20936.111,20875.215,20997.008,20262.564,20261.719,20263.41,170386.69,170382.23,170391.14,164843.95,164841.16,164846.75,41416.551,41416.031,41417.07,41475.82,41474.93,41476.711,166322.44,165832.12,166812.75 +1,1389.3538,1388.8239,1389.8837,5027.9702,5025.9165,5030.0239,9236.3096,9235.7012,9236.918,18098.809,18094.221,18103.396,20977.502,20910.598,21044.406,20295.943,20295.197,20296.689,170841.7,170837.19,170846.22,165119.48,165116.42,165122.55,41489.344,41488.586,41490.102,41547.473,41546.598,41548.348,166895.52,166891.62,166899.41 +2,1388.7098,1388.161,1389.2587,5033.98,5031.833,5036.127,9261.2559,9260.3711,9262.1406,18105.875,18104.926,18106.824,21048.035,21047.703,21048.367,20349.461,20348.93,20349.992,171090.62,171086.73,171094.52,165487.03,165483.39,165490.67,41579.785,41578.727,41580.844,41633.246,41632.113,41634.379,166922.98,166326.97,167519 +3,1388.9546,1388.3644,1389.5448,5032.0625,5030.7207,5033.4043,9241.0859,9240.6084,9241.5635,18022.875,18019.514,18026.236,21029.26,21028.918,21029.602,20310.809,20310.252,20311.365,171002.44,170997.73,171007.14,165216.23,165212.27,165220.2,41438.988,41283.625,41594.352,41579.773,41579.082,41580.465,167024.95,167023.23,167026.67 diff --git a/tests/workloads/join_type_grid/MI200/sysinfo.csv b/tests/workloads/join_type_grid/MI200/sysinfo.csv new file mode 100644 index 0000000000..5bbcaa02f5 --- /dev/null +++ b/tests/workloads/join_type_grid/MI200/sysinfo.csv @@ -0,0 +1,2 @@ +workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd +join_type_grid,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 02:08:18 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/join_type_grid/MI200/timestamps.csv b/tests/workloads/join_type_grid/MI200/timestamps.csv new file mode 100644 index 0000000000..498169935f --- /dev/null +++ b/tests/workloads/join_type_grid/MI200/timestamps.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,273424,273424,1048576,256,0,0,8,0,16,64,0x0,0x7f334f7d0ec0,197844341928655,197844341953097,197844341974057,197844341984981 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,273424,273424,1048576,256,0,0,8,0,16,64,0x0,0x7f334f7d0ec0,197844341984380,197844342059817,197844342076617,197844342077587 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,273424,273424,1048576,256,0,0,8,0,16,64,0x0,0x7f334f7d0ec0,197844342087405,197844342096937,197844342112777,197844342113544 diff --git a/tests/workloads/join_type_kernel/MI100/SQ_IFETCH_LEVEL.csv b/tests/workloads/join_type_kernel/MI100/SQ_IFETCH_LEVEL.csv index 83ada919f5..7e971f2dec 100644 --- a/tests/workloads/join_type_kernel/MI100/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/join_type_kernel/MI100/SQ_IFETCH_LEVEL.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2808348,2808348,1048576,256,0,0,8,8,16,64,0x0,0x7f89ac7aae80,47434,47434,16384,65536,12939,1661128,2187690142856377,2187681303619298,2187681303643618,2187690150447978 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2808348,2808348,1048576,256,0,0,8,8,16,64,0x0,0x7f89ac7aae80,43993,43993,16384,65536,8286,1048580,2187690150470340,2187681303664418,2187681303682978,2187690150791954 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2808348,2808348,1048576,256,0,0,8,8,16,64,0x0,0x7f89ac7aae80,44188,44188,16384,65536,8232,1048592,2187690150824435,2187681303760738,2187681303779618,2187690151022116 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,107324,107324,1048576,256,0,0,8,8,16,64,0x0,0x7f9e0721ce80,48789,48789,16384,65536,14279,1856036,194072742742975,194084901267928,194084901291928,194072750548113 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,107324,107324,1048576,256,0,0,8,8,16,64,0x0,0x7f9e0721ce80,42404,42404,16384,65536,8167,1048576,194072750570585,194084901373528,194084901392248,194072750884239 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,107324,107324,1048576,256,0,0,8,8,16,64,0x0,0x7f9e0721ce80,42548,42548,16384,65536,8218,1048576,194072750916059,194084901413848,194084901433048,194072751093325 diff --git a/tests/workloads/join_type_kernel/MI100/SQ_INST_LEVEL_LDS.csv b/tests/workloads/join_type_kernel/MI100/SQ_INST_LEVEL_LDS.csv index c6414b7c97..e16792aa9a 100644 --- a/tests/workloads/join_type_kernel/MI100/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/join_type_kernel/MI100/SQ_INST_LEVEL_LDS.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2808712,2808712,1048576,256,0,0,8,8,16,64,0x0,0x7f5b681b0e80,0,0,0,2187691042646548,2187681303619298,2187681303643618,2187691050441340 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2808712,2808712,1048576,256,0,0,8,8,16,64,0x0,0x7f5b681b0e80,0,0,0,2187691050460476,2187681303664418,2187681303682978,2187691050771751 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2808712,2808712,1048576,256,0,0,8,8,16,64,0x0,0x7f5b681b0e80,0,0,0,2187691050800815,2187681303760738,2187681303779618,2187691050979330 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,107512,107512,1048576,256,0,0,8,8,16,64,0x0,0x7f219311ae80,0,0,0,194073237479869,194084901267928,194084901291928,194073245258187 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,107512,107512,1048576,256,0,0,8,8,16,64,0x0,0x7f219311ae80,0,0,0,194073245279247,194084901373528,194084901392248,194073245605574 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,107512,107512,1048576,256,0,0,8,8,16,64,0x0,0x7f219311ae80,0,0,0,194073245634449,194084901413848,194084901433048,194073245820271 diff --git a/tests/workloads/join_type_kernel/MI100/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/join_type_kernel/MI100/SQ_INST_LEVEL_SMEM.csv index 227292a5cf..fdc6eadf7a 100644 --- a/tests/workloads/join_type_kernel/MI100/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/join_type_kernel/MI100/SQ_INST_LEVEL_SMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2808530,2808530,1048576,256,0,0,8,8,16,64,0x0,0x7f049f964e80,65536,187470,23958016,2187690592747991,2187681303619298,2187681303643618,2187690600530781 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2808530,2808530,1048576,256,0,0,8,8,16,64,0x0,0x7f049f964e80,65536,169730,21753024,2187690600549296,2187681303664418,2187681303682978,2187690600858175 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2808530,2808530,1048576,256,0,0,8,8,16,64,0x0,0x7f049f964e80,65536,172408,22061112,2187690600886278,2187681303760738,2187681303779618,2187690601071265 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,107700,107700,1048576,256,0,0,8,8,16,64,0x0,0x7f85a6368e80,65536,169686,21865424,194073731739119,194084901267928,194084901291928,194073739288864 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,107700,107700,1048576,256,0,0,8,8,16,64,0x0,0x7f85a6368e80,65536,173334,22159048,194073739309193,194084901373528,194084901392248,194073739595585 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,107700,107700,1048576,256,0,0,8,8,16,64,0x0,0x7f85a6368e80,65536,162678,20825528,194073739623377,194084901413848,194084901433048,194073739793309 diff --git a/tests/workloads/join_type_kernel/MI100/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/join_type_kernel/MI100/SQ_INST_LEVEL_VMEM.csv index 267b7ed225..cd1876f940 100644 --- a/tests/workloads/join_type_kernel/MI100/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/join_type_kernel/MI100/SQ_INST_LEVEL_VMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2807800,2807800,1048576,256,0,0,8,8,16,64,0x0,0x7f1b74946e80,32768,653733,83679400,2187688538690614,2187681303619298,2187681303643618,2187688546175876 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2807800,2807800,1048576,256,0,0,8,8,16,64,0x0,0x7f1b74946e80,32768,652231,83494464,2187688546194761,2187681303664418,2187681303682978,2187688546509282 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2807800,2807800,1048576,256,0,0,8,8,16,64,0x0,0x7f1b74946e80,32768,657896,84202180,2187688546538717,2187681303760738,2187681303779618,2187688546706221 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,107890,107890,1048576,256,0,0,8,8,16,64,0x0,0x7f0b3aa6ce80,32768,656568,84046520,194074222823518,194084901267928,194084901291928,194074230843173 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,107890,107890,1048576,256,0,0,8,8,16,64,0x0,0x7f0b3aa6ce80,32768,678091,86774128,194074230863100,194084901373528,194084901392248,194074231212693 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,107890,107890,1048576,256,0,0,8,8,16,64,0x0,0x7f0b3aa6ce80,32768,662440,84790852,194074231241938,194084901413848,194084901433048,194074231406800 diff --git a/tests/workloads/join_type_kernel/MI100/SQ_LEVEL_WAVES.csv b/tests/workloads/join_type_kernel/MI100/SQ_LEVEL_WAVES.csv index f5b94df921..3c0df479b6 100644 --- a/tests/workloads/join_type_kernel/MI100/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/join_type_kernel/MI100/SQ_LEVEL_WAVES.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2807436,2807436,1048576,256,0,0,8,8,16,64,0x0,0x7f746c7c8e80,47683,47683,16956,381472,16384,24235728,230389,0,97440568,2187687643528711,2187681303619298,2187681303643618,2187687651185555 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2807436,2807436,1048576,256,0,0,8,8,16,64,0x0,0x7f746c7c8e80,113578,113578,12383,908632,16384,23243977,225755,0,93466656,2187687651218577,2187681303664418,2187681303682978,2187687651517188 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2807436,2807436,1048576,256,0,0,8,8,16,64,0x0,0x7f746c7c8e80,45594,45594,16529,364760,16384,23667285,222028,0,95158432,2187687651556461,2187681303760738,2187681303779618,2187687651719257 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,108080,108080,1048576,256,0,0,8,8,16,64,0x0,0x7f1bafecee80,48611,48611,16931,388896,16384,25448970,234378,0,102279796,194074720168701,194084901267928,194084901291928,194074727847260 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,108080,108080,1048576,256,0,0,8,8,16,64,0x0,0x7f1bafecee80,43466,43466,13493,347736,16384,25133504,238792,0,101023004,194074727875574,194084901373528,194084901392248,194074728202763 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,108080,108080,1048576,256,0,0,8,8,16,64,0x0,0x7f1bafecee80,42354,42354,13000,338840,16384,25537295,234589,0,102649744,194074728241056,194084901413848,194084901433048,194074728433761 diff --git a/tests/workloads/join_type_kernel/MI100/pmc_dispatch_info.csv b/tests/workloads/join_type_kernel/MI100/pmc_dispatch_info.csv new file mode 100644 index 0000000000..17300ae9af --- /dev/null +++ b/tests/workloads/join_type_kernel/MI100/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) ",2 +1,"vecCopy(double*, double*, double*, int, int) ",2 +2,"vecCopy(double*, double*, double*, int, int) ",2 diff --git a/tests/workloads/join_type_kernel/MI100/pmc_perf.csv b/tests/workloads/join_type_kernel/MI100/pmc_perf.csv index b14d9c41e4..a7093fd748 100644 --- a/tests/workloads/join_type_kernel/MI100/pmc_perf.csv +++ b/tests/workloads/join_type_kernel/MI100/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_1,obj_1,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_2,obj_2,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_3,obj_3,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_4,obj_4,TCC_EA_ATOMIC_LEVEL_sum,wave_size_5,obj_5,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_6,obj_6,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_7,obj_7,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_8,obj_8,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_9,obj_9,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_10,obj_10,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_11,obj_11,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_12,obj_12,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_13,obj_13,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_14,obj_14,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_15,obj_15,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_16,obj_16,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f2c59dd4e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131340.0,0.0,528.0,131339.0,64,0x7fcaea130e80,2903,0,0,1817111,3559,0,0,1810167,3505,0,0,1853721,2022,0,0,1810025,2408,0,0,1750948,3176,0,0,1869172,2697,0,0,1872603,3195,0,0,1958054,3652,0,0,1857351,3750,0,0,1916438,3285,0,0,1881399,3634,0,0,1911847,3267,0,0,1835856,1798,0,0,1862510,3351,0,0,1915247,4023,0,0,1916866,2680,0,0,1785726,3424,0,0,1928705,3577,0,0,1928359,2323,0,0,1856559,2660,0,0,1786224,4650,0,0,2043786,3901,0,0,1958781,3798,0,0,1871018,3338,0,0,1849408,1395,0,0,1688933,2545,0,0,1783638,3939,0,0,1931980,3281,0,0,1842184,3458,0,0,1877418,3214,0,0,1850179,4927,0,0,2031902,64,0x7f303fd72e80,4096,0,466,0,4327,0,333,0,4144,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,2116,0,4096,0,367,0,4096,0,1911,0,4096,0,1019,0,4096,0,0,0,4096,0,0,0,4096,0,360,0,4096,0,0,0,4099,0,332,0,4096,0,0,0,4097,0,1584,0,4096,0,942,0,4096,0,0,0,4096,0,8189,0,4096,0,600,0,4096,0,0,0,4096,0,222,0,4096,0,0,0,4144,0,195,0,4096,0,0,0,4096,0,0,0,4096,0,679,0,4096,0,3537,0,4096,0,0,0,4096,0,0,0,4096,0,365,0,4096,0,1074,0,64,0x7f94aa856e80,8192,0,4096,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fbd1b43ce80,0.0,64,0x7fd1b6084e80,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8360,4264,8360,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8226,4130,8226,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,141,8195,4240,8336,47,8193,4144,8240,0,8192,4096,8192,64,0x7f55dcfa4e80,381840,228324,3324127,16384,24092685,144,48,0,47729,47729,3777402.0,2920244.0,7266.0,1403019.0,1950688.0,0.0,2910535.0,2598591.0,380383,238260,47729,0,47729,0,1527328.0,956599.0,0.0,0.0,64,0x7f0da6108e80,0,47579,0,0,0,47579,0,0,0,47579,0,0,0,47579,0,0,0,47579,0,0,0,47579,0,0,0,47579,0,0,0,47579,0,0,0,47579,0,0,0,47579,0,0,0,47579,0,0,0,47579,0,0,0,47579,0,0,0,47579,0,0,0,47579,0,0,0,47579,0,0,0,47579,0,0,0,47579,0,0,0,47579,0,0,0,47579,0,0,0,47579,0,0,0,47579,0,0,0,47579,0,0,0,47579,0,0,0,47579,0,0,0,47579,0,0,0,47579,0,0,0,47579,0,0,0,47579,0,0,0,47579,0,0,0,47579,0,0,0,47579,0,0,64,0x7f61318c8e80,131072.0,131072.0,0.0,2635335.0,0.0,0.0,119915234.0,59112102.0,64,0x7f9424a62e80,0,4925012,4096,4096,0,3404062,4096,4096,0,4206637,4096,4096,0,3027867,4096,4096,0,3747372,4096,4096,0,3755551,4096,4096,0,4283659,4096,4096,0,4530528,4096,4096,0,4497746,4096,4096,0,3797023,4096,4096,0,3797460,4096,4096,0,4186286,4096,4096,0,4587043,4096,4096,0,4241217,4096,4096,0,4868334,4096,4096,0,4434915,4096,4096,0,4322809,4096,4096,0,3582479,4096,4096,0,4153094,4096,4096,0,4675835,4096,4096,0,3536954,4096,4096,0,3738109,4096,4096,0,3849378,4096,4096,0,3170437,4096,4096,0,4067008,4096,4096,0,3373082,4096,4096,0,4707747,4096,4096,0,4526521,4096,4096,0,4510466,4096,4096,0,3614638,4096,4096,0,3721858,4096,4096,0,3840464,4096,4096,64,0x7f0fe6956e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,87077.0,43995.0,131111.0,0.0,64,0x7f3fc84a6e80,2006910,360448,163840,0,0,180224,114688,0,69425334.0,188677034.0,73597177.0,131072.0,0.0,650663.0,0,0,26128,83379.0,0.0,0.0,83379.0,64,0x7f3f9dbdce80,0,0,192,0,65536,64503,48,1238,31839,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,539,47760,1718,0,48.0,264.0,0.0,262288.0,64,0x7f2c68cc4e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,47456,0,131596.0,131072.0,0.0,131104.0,64,0x7f779f0c0e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,34818.0,118584.0,64,0x7fbb2db50e80,32768,0,0,0,16384,16384,393216,23280318,960.0,513959.0,0.0,524288.0,906787.0,32768.0,0,0,0,17525,131072.0,131072.0,0.0,131072.0,64,0x7f2436812e80,184701,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,14673,31057,10034,550,0,47245,262673.0,0.0,188.0,262485.0,2187681303619298,2187681303643618 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f2c59dd4e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131343.0,0.0,540.0,131342.0,64,0x7fcaea130e80,4272,0,0,1650374,1007,0,0,1351960,2810,0,0,1575582,4709,0,0,1702465,4313,0,0,1633490,3548,0,0,1509097,3576,0,0,1639064,3510,0,0,1663201,3853,0,0,1666655,3522,0,0,1690738,1780,0,0,1488036,3620,0,0,1652270,3659,0,0,1652742,3422,0,0,1579211,3992,0,0,1673645,5409,0,0,1755188,3815,0,0,1630026,2884,0,0,1528680,1966,0,0,1524204,2514,0,0,1502681,3253,0,0,1533556,2169,0,0,1595315,3030,0,0,1557621,2077,0,0,1560479,5901,0,0,1786904,343,0,0,1263256,2765,0,0,1529189,5206,0,0,1636837,4321,0,0,1663814,3309,0,0,1570919,4288,0,0,1678381,2435,0,0,1426633,64,0x7f303fd72e80,4096,0,1354,0,4279,0,687,0,4144,0,0,0,4096,0,705,0,4099,0,0,0,4096,0,361,0,4096,0,591,0,4096,0,0,0,4096,0,2190,0,4096,0,37,0,4096,0,0,0,4096,0,7978,0,4096,0,281,0,4096,0,41,0,4096,0,938,0,4097,0,0,0,4096,0,9352,0,4098,0,215,0,4096,0,1189,0,4096,0,1243,0,4096,0,23,0,4096,0,269,0,4096,0,0,0,4144,0,0,0,4096,0,706,0,4096,0,213,0,4096,0,3050,0,4096,0,0,0,4097,0,0,0,4096,0,419,0,4096,0,325,0,4096,0,1390,0,64,0x7f94aa856e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fbd1b43ce80,0.0,64,0x7fd1b6084e80,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8194,4098,8194,0,8360,4264,8360,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8195,4099,8195,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,64,0x7f55dcfa4e80,401088,256066,3724480,16384,27728240,0,96,0,50135,50135,4130754.0,3121473.0,3715.0,1204013.0,2297582.0,0.0,3102823.0,2790101.0,401080,265773,50135,0,50135,1076,1604320.0,890688.0,1.0,0.0,64,0x7f0da6108e80,0,44284,0,0,0,44284,0,0,0,44284,0,0,0,44284,0,0,0,44284,0,0,0,44284,0,0,0,44284,0,0,0,44284,0,0,0,44284,0,0,0,44284,0,0,0,44284,0,0,0,44284,0,0,0,44284,0,0,0,44284,0,0,0,44284,0,0,0,44284,0,0,0,44284,0,0,0,44284,0,0,0,44284,0,0,0,44284,0,0,0,44284,0,0,0,44284,0,0,0,44284,0,0,0,44284,0,0,0,44284,0,0,0,44284,0,0,0,44284,0,0,0,44284,0,0,0,44284,0,0,0,44284,0,0,0,44284,0,0,0,44284,0,0,64,0x7f61318c8e80,131072.0,131072.0,0.0,2617408.0,0.0,0.0,119211219.0,48556959.0,64,0x7f9424a62e80,0,4103784,2706,2706,0,4348414,2717,2717,0,4424217,2670,2670,0,5316282,2704,2704,0,4355410,2700,2700,0,3959119,2750,2750,0,4230909,2710,2710,0,4913441,2708,2708,0,3889064,2692,2692,0,4472637,2690,2690,0,4112779,2700,2700,0,4026609,2728,2728,0,4130618,2685,2685,0,3549268,2682,2682,0,4801662,2696,2696,0,4041892,2680,2680,0,5084859,2690,2690,0,4673507,2702,2702,0,4042680,2690,2690,0,5046249,2686,2686,0,4235044,2711,2711,0,4580538,2736,2736,0,4007686,2676,2676,0,4122287,2699,2699,0,2974310,2692,2692,0,3781292,2682,2682,0,3577847,2718,2718,0,4364353,2712,2712,0,4590689,2708,2708,0,4311994,2714,2714,0,3503713,2716,2716,0,4887006,2690,2690,64,0x7f0fe6956e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,66990.0,19780.0,79352.0,0.0,64,0x7f3fc84a6e80,1571070,360448,163840,0,0,180224,114688,0,70648760.0,199594452.0,77844100.0,131072.0,0.0,646294.0,0,0,25309,75538.0,0.0,0.0,75538.0,64,0x7f3f9dbdce80,0,0,48,0,65536,65536,0,0,28602,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,436,38023,1726,0,48.0,0.0,0.0,262144.0,64,0x7f2c68cc4e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,3596,39201,0,131448.0,131072.0,0.0,87092.0,64,0x7f779f0c0e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,41379.0,129338.0,64,0x7fbb2db50e80,32768,0,0,0,16384,16384,393216,22949909,960.0,513990.0,0.0,524288.0,937189.0,32768.0,0,0,0,14177,86537.0,86537.0,0.0,86537.0,64,0x7f2436812e80,145115,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13278,29662,8654,3947,0,41653,262538.0,0.0,47.0,262491.0,2187681303664418,2187681303682978 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f2c59dd4e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131343.0,0.0,540.0,131342.0,64,0x7fcaea130e80,2179,0,0,1452357,1858,0,0,1353903,1977,0,0,1368511,2979,0,0,1512993,2329,0,0,1474736,2076,0,0,1443506,1895,0,0,1485184,1688,0,0,1461950,1872,0,0,1448314,866,0,0,1253227,1645,0,0,1377934,1521,0,0,1433046,2918,0,0,1555758,2384,0,0,1509682,658,0,0,1293862,3596,0,0,1544359,3758,0,0,1614394,3281,0,0,1622915,1771,0,0,1393825,1857,0,0,1387232,1541,0,0,1384805,3812,0,0,1710501,1314,0,0,1315687,1730,0,0,1351339,2987,0,0,1499648,1530,0,0,1308987,2253,0,0,1492702,1540,0,0,1385081,2338,0,0,1456974,1842,0,0,1363008,1508,0,0,1304151,1825,0,0,1433043,64,0x7f303fd72e80,4096,0,1845,0,4275,0,5493,0,4144,0,3511,0,4096,0,536,0,4099,0,3434,0,4096,0,574,0,4096,0,2701,0,4096,0,2747,0,4096,0,4147,0,4096,0,1406,0,4096,0,6150,0,4096,0,3568,0,4096,0,1361,0,4096,0,1388,0,4096,0,3420,0,4097,0,58,0,4096,0,1868,0,4098,0,2192,0,4096,0,2681,0,4096,0,1204,0,4096,0,371,0,4096,0,1883,0,4096,0,2885,0,4144,0,262,0,4096,0,204,0,4096,0,1780,0,4096,0,5068,0,4096,0,649,0,4097,0,40,0,4096,0,82,0,4096,0,3184,0,4096,0,2277,0,64,0x7f94aa856e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fbd1b43ce80,0.0,64,0x7fd1b6084e80,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8194,4098,8194,0,8360,4264,8360,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8197,4101,8197,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8195,4099,8195,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,64,0x7f55dcfa4e80,339104,223324,3269183,16384,24048631,0,48,0,42387,42387,3639597.0,2963803.0,5756.0,1133350.0,2066852.0,0.0,2955115.0,2644049.0,339096,232847,42387,0,42387,0,1356384.0,810870.0,0.0,0.0,64,0x7f0da6108e80,0,42575,0,0,0,42575,0,0,0,42575,0,0,0,42575,0,0,0,42575,0,0,0,42575,0,0,0,42575,0,0,0,42575,0,0,0,42575,0,0,0,42575,0,0,0,42575,0,0,0,42575,0,0,0,42575,0,0,0,42575,0,0,0,42575,0,0,0,42575,0,0,0,42575,0,0,0,42575,0,0,0,42575,0,0,0,42575,0,0,0,42575,0,0,0,42575,0,0,0,42575,0,0,0,42575,0,0,0,42575,0,0,0,42575,0,0,0,42575,0,0,0,42575,0,0,0,42575,0,0,0,42575,0,0,0,42575,0,0,0,42575,0,0,64,0x7f61318c8e80,131072.0,131072.0,0.0,2602351.0,0.0,0.0,124926177.0,48162652.0,64,0x7f9424a62e80,0,3741512,2702,2702,0,2989867,2720,2720,0,4522091,2668,2668,0,3858367,2702,2702,0,4287410,2696,2696,0,4945945,2698,2698,0,3567423,2684,2684,0,3805905,2696,2696,0,3070814,2696,2696,0,3545189,2666,2666,0,4825895,2710,2710,0,4548345,2728,2728,0,4310185,2700,2700,0,2986330,2682,2682,0,4510496,2696,2696,0,3676113,2688,2688,0,3388000,2690,2690,0,3442444,2700,2700,0,3460111,2692,2692,0,4293207,2718,2718,0,4586961,2706,2706,0,3449983,2721,2721,0,4779737,2672,2672,0,4421978,2689,2689,0,3226047,2676,2676,0,3870100,2688,2688,0,4784842,2706,2706,0,3708473,2704,2704,0,4103305,2712,2712,0,4336117,2700,2700,0,4251370,2713,2713,0,4266727,2688,2688,64,0x7f0fe6956e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,87194.0,0.0,131113.0,0.0,64,0x7f3fc84a6e80,1298230,360448,163840,0,0,180224,114688,0,69742223.0,176595079.0,73821996.0,131072.0,0.0,609070.0,0,0,24847,52301.0,0.0,0.0,52301.0,64,0x7f3f9dbdce80,0,0,48,0,65536,65536,0,0,31457,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,432,43168,2011,0,48.0,271.0,0.0,262144.0,64,0x7f2c68cc4e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,3541,38014,0,131432.0,131072.0,0.0,86736.0,64,0x7f779f0c0e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,41650.0,128127.0,64,0x7fbb2db50e80,32768,0,0,0,16384,16384,393216,22891623,960.0,513879.0,0.0,524288.0,1007723.0,32768.0,0,0,0,14901,86601.0,86601.0,0.0,86601.0,64,0x7f2436812e80,218200,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13656,30040,8470,3265,0,40757,262536.0,0.0,47.0,262489.0,2187681303760738,2187681303779618 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_1,obj_1,TCC_EA_ATOMIC_LEVEL_sum,wave_size_2,obj_2,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_3,obj_3,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_4,obj_4,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_5,obj_5,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_6,obj_6,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_7,obj_7,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_8,obj_8,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_9,obj_9,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_10,obj_10,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_11,obj_11,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_12,obj_12,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_13,obj_13,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_14,obj_14,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_15,obj_15,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_16,obj_16,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f308a89ae80,32768,0,0,0,16384,16384,393216,23021945,960.0,513880.0,0.0,524288.0,1035416.0,32768.0,0,0,0,16452,131072.0,131072.0,0.0,131072.0,64,0x7f68e6ccee80,0.0,64,0x7fae8f0bae80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86591.0,44481.0,131112.0,0.0,64,0x7fe717cf8e80,4096,0,6029,0,4096,0,928,0,4099,0,1337,0,4096,0,1330,0,4096,0,768,0,4096,0,1127,0,4096,0,3179,0,4096,0,2371,0,4096,0,359,0,4096,0,1415,0,4144,0,2879,0,4096,0,4362,0,4144,0,550,0,4096,0,2171,0,4096,0,5017,0,4222,0,674,0,4144,0,1657,0,4096,0,4504,0,4096,0,4287,0,4097,0,1080,0,4096,0,520,0,4096,0,1875,0,4096,0,794,0,4096,0,132,0,4096,0,3468,0,4096,0,1465,0,4096,0,1816,0,4096,0,3882,0,4096,0,0,0,4096,0,0,0,4096,0,2415,0,4096,0,4937,0,64,0x7f253c6d2e80,396496,247181,3576669,16384,25746310,144,48,0,49561,49561,4060644.0,3197256.0,5271.0,1223515.0,2284571.0,0.0,3186550.0,2873089.0,394847,257128,49561,0,49561,0,1585952.0,1009554.0,0.0,0.0,64,0x7f98d4602e80,131072.0,131072.0,0.0,2533597.0,0.0,0.0,126684161.0,61263601.0,64,0x7fef762bce80,188377,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,11749,28133,10075,550,0,47669,262741.0,0.0,188.0,262553.0,64,0x7fdaa3618e80,935,0,0,1689023,1232,0,0,1675081,2421,0,0,2011805,4180,0,0,2102217,1046,0,0,1710903,3766,0,0,2112402,1296,0,0,1738320,1235,0,0,1837294,1446,0,0,1816291,1553,0,0,1729779,1501,0,0,1780265,3240,0,0,2016916,1986,0,0,1845160,2348,0,0,1869493,1936,0,0,1845088,3741,0,0,2037699,644,0,0,1583892,624,0,0,1621783,1844,0,0,1881684,1523,0,0,1868360,2557,0,0,1861041,2251,0,0,1915379,2123,0,0,1838643,2373,0,0,1961977,1620,0,0,1743108,1183,0,0,1768085,1035,0,0,1752932,4966,0,0,2139336,1108,0,0,1686681,1591,0,0,1725298,1567,0,0,1831951,3238,0,0,1962881,64,0x7f9e43120e80,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,64,0x7f85434cce80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131293.0,0.0,434.0,131292.0,64,0x7f18eb488e80,0,0,192,0,65536,64466,48,1368,30943,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,538,46985,1710,0,48.0,201.0,0.0,262288.0,64,0x7f9688a28e80,0,3663238,4096,4096,0,3901874,4096,4096,0,4029749,4096,4096,0,3045492,4096,4096,0,3553483,4096,4096,0,3526377,4096,4096,0,3162538,4096,4096,0,5179828,4096,4096,0,3586097,4096,4096,0,3329358,4096,4096,0,3892962,4096,4096,0,3636824,4096,4096,0,4323277,4096,4096,0,3905153,4096,4096,0,2847329,4096,4096,0,3168819,4096,4096,0,4039784,4096,4096,0,5320449,4096,4096,0,3822901,4096,4096,0,3177539,4096,4096,0,3894450,4096,4096,0,3920855,4096,4096,0,2834706,4096,4096,0,2867897,4096,4096,0,3478928,4096,4096,0,5134370,4096,4096,0,2688673,4096,4096,0,3085342,4096,4096,0,3342339,4096,4096,0,4050464,4096,4096,0,2992545,4096,4096,0,2899927,4096,4096,64,0x7f4427492e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,47186,0,131488.0,131072.0,0.0,131104.0,64,0x7f8f0d2b6e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f583f4f0e80,0,8192,4096,8192,0,8192,4096,8192,141,8195,4240,8336,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8218,4122,8218,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8360,4264,8360,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7fb62b0c0e80,1879014,360448,163840,0,0,180224,114688,0,66861208.0,199267740.0,79073197.0,131072.0,0.0,704340.0,0,0,26430,127544.0,0.0,0.0,127544.0,64,0x7f9f08402e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,60745.0,127569.0,194084901267928,194084901291928 +1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f308a89ae80,32768,0,0,0,16384,16384,393216,23098874,960.0,513891.0,0.0,524288.0,1021920.0,32768.0,0,0,0,15470,86488.0,86488.0,0.0,86488.0,64,0x7f68e6ccee80,0.0,64,0x7fae8f0bae80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,67412.0,18982.0,79660.0,0.0,64,0x7fe717cf8e80,4096,0,5761,0,4096,0,4077,0,4096,0,3,0,4097,0,1479,0,4096,0,3371,0,4096,0,5997,0,4097,0,5207,0,4096,0,343,0,4096,0,1771,0,4096,0,3363,0,4144,0,608,0,4097,0,3648,0,4144,0,3085,0,4096,0,3292,0,4096,0,4728,0,4228,0,0,0,4144,0,24,0,4096,0,2648,0,4096,0,1674,0,4097,0,0,0,4096,0,3427,0,4096,0,1098,0,4096,0,2348,0,4096,0,0,0,4096,0,5369,0,4096,0,1466,0,4096,0,1852,0,4098,0,1311,0,4096,0,975,0,4096,0,2491,0,4096,0,56,0,4096,0,2434,0,64,0x7f253c6d2e80,344360,233753,3409093,16384,25291285,0,48,0,43044,43044,3795786.0,3121299.0,4193.0,1099743.0,2233278.0,0.0,3111631.0,2801880.0,344352,243173,43044,0,43044,0,1377408.0,838607.0,0.0,0.0,64,0x7f98d4602e80,131072.0,131072.0,0.0,2697989.0,0.0,0.0,131643077.0,46828420.0,64,0x7fef762bce80,343319,0,0,65536,62560,96,2880,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,14057,30441,20716,5245,0,43975,262740.0,0.0,94.0,262646.0,64,0x7fdaa3618e80,3486,0,0,1618217,2911,0,0,1587798,2877,0,0,1611560,4936,0,0,1712931,1643,0,0,1502838,2885,0,0,1575418,2173,0,0,1517556,6208,0,0,1762309,1251,0,0,1340381,3051,0,0,1702705,4518,0,0,1672937,3692,0,0,1588288,3623,0,0,1609830,4503,0,0,1589109,4151,0,0,1649764,4723,0,0,1681657,2612,0,0,1564365,2821,0,0,1549110,3421,0,0,1640318,6116,0,0,1794891,2764,0,0,1506976,5342,0,0,1829144,2676,0,0,1556229,2914,0,0,1649169,3790,0,0,1638053,5271,0,0,1767638,2967,0,0,1517144,4763,0,0,1634813,3110,0,0,1523754,2394,0,0,1543963,2944,0,0,1535202,5254,0,0,1730864,64,0x7f9e43120e80,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,64,0x7f85434cce80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131283.0,0.0,420.0,131282.0,64,0x7f18eb488e80,0,0,48,0,65536,65536,0,0,30271,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,457,41630,1660,0,48.0,180.0,0.0,262144.0,64,0x7f9688a28e80,0,4508742,2718,2718,0,4230106,2680,2680,0,4696852,2682,2682,0,3305402,2677,2677,0,3623814,2700,2700,0,3141352,2714,2714,0,3909720,2708,2708,0,5003226,2702,2702,0,3343126,2712,2712,0,4761479,2684,2684,0,4181584,2706,2706,0,4693580,2728,2728,0,4314759,2710,2710,0,3292184,2650,2650,0,4923718,2714,2714,0,3181891,2672,2672,0,5101272,2701,2701,0,4029456,2688,2688,0,4093851,2714,2714,0,3434987,2700,2700,0,4152898,2700,2700,0,3373290,2724,2724,0,3629606,2679,2679,0,3555868,2696,2696,0,3670948,2700,2700,0,3231057,2680,2680,0,3161780,2750,2750,0,4051029,2695,2695,0,4535908,2708,2708,0,4124704,2685,2685,0,3799962,2739,2739,0,3374548,2664,2664,64,0x7f4427492e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,240.0,524288.0,0.0,0.0,0,0,4691,115036,2648,131683.0,131072.0,0.0,86593.0,64,0x7f8f0d2b6e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f583f4f0e80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8195,4099,8195,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8360,4264,8360,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,64,0x7fb62b0c0e80,2138857,360448,163840,0,0,180224,114688,0,67352205.0,182483944.0,80511844.0,131072.0,0.0,1263757.0,0,0,25862,113261.0,0.0,0.0,113261.0,64,0x7f9f08402e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,57908.0,121756.0,194084901373528,194084901392248 +2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f308a89ae80,32768,0,0,0,16384,16384,393216,22492981,960.0,513899.0,0.0,524288.0,1016014.0,32768.0,0,0,0,13834,86625.0,86625.0,0.0,86625.0,64,0x7f68e6ccee80,0.0,64,0x7fae8f0bae80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86438.0,0.0,131112.0,0.0,64,0x7fe717cf8e80,4096,0,2318,0,4096,0,0,0,4096,0,4003,0,4097,0,99,0,4096,0,784,0,4096,0,1198,0,4097,0,5441,0,4096,0,1124,0,4096,0,1998,0,4096,0,2168,0,4144,0,4942,0,4097,0,2778,0,4144,0,5358,0,4096,0,1190,0,4096,0,3999,0,4277,0,983,0,4144,0,5333,0,4096,0,3137,0,4096,0,5825,0,4097,0,913,0,4096,0,481,0,4096,0,3286,0,4096,0,2499,0,4096,0,197,0,4096,0,1201,0,4096,0,269,0,4096,0,3096,0,4098,0,0,0,4096,0,0,0,4096,0,3804,0,4096,0,897,0,4096,0,3888,0,64,0x7f253c6d2e80,337736,227079,3307439,16384,24374740,0,48,0,42216,42216,3696092.0,3024979.0,6186.0,930092.0,2087592.0,0.0,3015989.0,2704595.0,337728,236579,42216,0,42216,0,1350912.0,806228.0,0.0,0.0,64,0x7f98d4602e80,131072.0,131072.0,0.0,2542059.0,0.0,0.0,115463903.0,48109140.0,64,0x7fef762bce80,184719,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,12521,28905,8515,2383,0,40535,262485.0,0.0,47.0,262438.0,64,0x7fdaa3618e80,820,0,0,1269261,634,0,0,1249799,3827,0,0,1792084,1736,0,0,1447232,1284,0,0,1392304,1794,0,0,1403650,1715,0,0,1395218,1722,0,0,1476916,1634,0,0,1462308,2200,0,0,1507856,1161,0,0,1354323,1315,0,0,1332219,773,0,0,1263668,977,0,0,1313894,1204,0,0,1416278,2214,0,0,1429371,746,0,0,1259164,699,0,0,1268324,1409,0,0,1376564,1155,0,0,1336346,2890,0,0,1521808,541,0,0,1262555,867,0,0,1337871,1483,0,0,1410430,1866,0,0,1448175,599,0,0,1220318,1087,0,0,1376710,1926,0,0,1393188,4557,0,0,1770447,1531,0,0,1337357,1300,0,0,1473575,2615,0,0,1624433,64,0x7f9e43120e80,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,64,0x7f85434cce80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131274.0,0.0,402.0,131273.0,64,0x7f18eb488e80,0,0,48,0,65536,65536,0,0,29759,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,457,41192,1785,0,48.0,175.0,0.0,262144.0,64,0x7f9688a28e80,0,4579310,2718,2718,0,4578344,2730,2730,0,3494035,2694,2694,0,4590352,2716,2716,0,4072427,2687,2687,0,3994941,2718,2718,0,3822256,2708,2708,0,5133382,2684,2684,0,4701668,2696,2696,0,3795514,2678,2678,0,4550848,2722,2722,0,5019740,2718,2718,0,3653020,2690,2690,0,4588499,2690,2690,0,4528406,2698,2698,0,4991125,2688,2688,0,4909365,2688,2688,0,5394473,2704,2704,0,4546273,2682,2682,0,4742109,2725,2725,0,4447117,2697,2697,0,4353893,2730,2730,0,4613906,2684,2684,0,4689922,2696,2696,0,3349309,2688,2688,0,4785506,2708,2708,0,3834543,2708,2708,0,4525187,2708,2708,0,4155600,2713,2713,0,4661963,2699,2699,0,3452318,2732,2732,0,5077875,2685,2685,64,0x7f4427492e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,2721,41522,0,131331.0,131072.0,0.0,86549.0,64,0x7f8f0d2b6e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f583f4f0e80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8199,4103,8199,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8360,4264,8360,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,64,0x7fb62b0c0e80,1444200,360448,163840,0,0,180224,114688,0,69800357.0,204180012.0,83768321.0,131072.0,0.0,764267.0,0,0,25149,126647.0,0.0,0.0,126647.0,64,0x7f9f08402e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,60370.0,127344.0,194084901413848,194084901433048 diff --git a/tests/workloads/join_type_kernel/MI100/sysinfo.csv b/tests/workloads/join_type_kernel/MI100/sysinfo.csv index 0b3816e0e6..829f442436 100644 --- a/tests/workloads/join_type_kernel/MI100/sysinfo.csv +++ b/tests/workloads/join_type_kernel/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -join_type_kernel,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Fri Mar 1 16:43:10 2024 (CST),1,t006-003.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651240,,5.7.1-98,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +join_type_kernel,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 07 Mar 2024 01:05:37 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/join_type_kernel/MI100/timestamps.csv b/tests/workloads/join_type_kernel/MI100/timestamps.csv index e26d2bfdba..a222669d1d 100644 --- a/tests/workloads/join_type_kernel/MI100/timestamps.csv +++ b/tests/workloads/join_type_kernel/MI100/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,2805251,2805251,1048576,256,0,0,8,8,16,64,0x0,0x7feb2ead2e80,2187681303589831,2187681303619298,2187681303643618,2187681303660013 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,2805251,2805251,1048576,256,0,0,8,8,16,64,0x0,0x7feb2ead2e80,2187681303656597,2187681303664418,2187681303682978,2187681303760081 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,2805251,2805251,1048576,256,0,0,8,8,16,64,0x0,0x7feb2ead2e80,2187681303694247,2187681303760738,2187681303779618,2187681303780680 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,111541,111541,1048576,256,0,0,8,8,16,64,0x0,0x7f92adaaae80,194084901241938,194084901267928,194084901291928,194084901302753 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,111541,111541,1048576,256,0,0,8,8,16,64,0x0,0x7f92adaaae80,194084901304466,194084901373528,194084901392248,194084901393525 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,111541,111541,1048576,256,0,0,8,8,16,64,0x0,0x7f92adaaae80,194084901404696,194084901413848,194084901433048,194084901433981 diff --git a/tests/workloads/join_type_kernel/MI200/SQ_IFETCH_LEVEL.csv b/tests/workloads/join_type_kernel/MI200/SQ_IFETCH_LEVEL.csv new file mode 100644 index 0000000000..3a04c9a50d --- /dev/null +++ b/tests/workloads/join_type_kernel/MI200/SQ_IFETCH_LEVEL.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,255986,255986,1048576,256,0,0,8,0,16,64,0x0,0x7fb7bd7d8ec0,27983,27983,16384,65536,13707,1560612,197521716951863,197534469403014,197534469423814,197521733076207 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,255986,255986,1048576,256,0,0,8,0,16,64,0x0,0x7fb7bd7d8ec0,42909,42909,16384,65536,9425,1048676,197521733096034,197534469442374,197534469458214,197521733407794 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,255986,255986,1048576,256,0,0,8,0,16,64,0x0,0x7fb7bd7d8ec0,41713,41713,16384,65536,9886,1048628,197521733437200,197534469518374,197534469534854,197521733601480 diff --git a/tests/workloads/join_type_kernel/MI200/SQ_INST_LEVEL_LDS.csv b/tests/workloads/join_type_kernel/MI200/SQ_INST_LEVEL_LDS.csv new file mode 100644 index 0000000000..eac310db69 --- /dev/null +++ b/tests/workloads/join_type_kernel/MI200/SQ_INST_LEVEL_LDS.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,256171,256171,1048576,256,0,0,8,0,16,64,0x0,0x7f568c1c0ec0,0,0,0,197522204232008,197534469403014,197534469423814,197522219925467 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,256171,256171,1048576,256,0,0,8,0,16,64,0x0,0x7f568c1c0ec0,0,0,0,197522219945194,197534469442374,197534469458214,197522220218641 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,256171,256171,1048576,256,0,0,8,0,16,64,0x0,0x7f568c1c0ec0,0,0,0,197522220245552,197534469518374,197534469534854,197522220377843 diff --git a/tests/workloads/join_type_kernel/MI200/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/join_type_kernel/MI200/SQ_INST_LEVEL_SMEM.csv new file mode 100644 index 0000000000..3ec66409cc --- /dev/null +++ b/tests/workloads/join_type_kernel/MI200/SQ_INST_LEVEL_SMEM.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,256357,256357,1048576,256,0,0,8,0,16,64,0x0,0x7fa7558e0ec0,65536,170284,19010128,197522677930159,197534469403014,197534469423814,197522694066336 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,256357,256357,1048576,256,0,0,8,0,16,64,0x0,0x7fa7558e0ec0,65536,246650,27715904,197522694083328,197534469442374,197534469458214,197522694399366 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,256357,256357,1048576,256,0,0,8,0,16,64,0x0,0x7fa7558e0ec0,65536,270936,30238816,197522694425665,197534469518374,197534469534854,197522694583033 diff --git a/tests/workloads/join_type_kernel/MI200/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/join_type_kernel/MI200/SQ_INST_LEVEL_VMEM.csv new file mode 100644 index 0000000000..7766ad598d --- /dev/null +++ b/tests/workloads/join_type_kernel/MI200/SQ_INST_LEVEL_VMEM.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,256558,256558,1048576,256,0,0,8,0,16,64,0x0,0x7f3982d4cec0,32768,303049,33928300,197523157025941,197534469403014,197534469423814,197523172794913 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,256558,256558,1048576,256,0,0,8,0,16,64,0x0,0x7f3982d4cec0,32768,579114,64866424,197523172814270,197534469442374,197534469458214,197523173100291 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,256558,256558,1048576,256,0,0,8,0,16,64,0x0,0x7f3982d4cec0,32768,588082,65852356,197523173126430,197534469518374,197534469534854,197523173306040 diff --git a/tests/workloads/join_type_kernel/MI200/SQ_LEVEL_WAVES.csv b/tests/workloads/join_type_kernel/MI200/SQ_LEVEL_WAVES.csv new file mode 100644 index 0000000000..85f2e22670 --- /dev/null +++ b/tests/workloads/join_type_kernel/MI200/SQ_LEVEL_WAVES.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,256756,256756,1048576,256,0,0,8,0,16,64,0x0,0x7fa46fc68ec0,27731,27731,11030,221856,16384,10910338,129553,0,44147600,197523639048099,197534469403014,197534469423814,197523656028593 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,256756,256756,1048576,256,0,0,8,0,16,64,0x0,0x7fa46fc68ec0,41874,41874,14115,335000,16384,19688539,225944,0,79236504,197523656056957,197534469442374,197534469458214,197523656351574 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,256756,256756,1048576,256,0,0,8,0,16,64,0x0,0x7fa46fc68ec0,44053,44053,13987,352432,16384,20594261,236972,0,82853636,197523656386520,197534469518374,197534469534854,197523656560850 diff --git a/tests/workloads/join_type_kernel/MI200/perfmon/SQ_IFETCH_LEVEL.txt b/tests/workloads/join_type_kernel/MI200/perfmon/SQ_IFETCH_LEVEL.txt new file mode 100644 index 0000000000..293092f641 --- /dev/null +++ b/tests/workloads/join_type_kernel/MI200/perfmon/SQ_IFETCH_LEVEL.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/join_type_kernel/MI200/perfmon/SQ_INST_LEVEL_LDS.txt b/tests/workloads/join_type_kernel/MI200/perfmon/SQ_INST_LEVEL_LDS.txt new file mode 100644 index 0000000000..08439eedce --- /dev/null +++ b/tests/workloads/join_type_kernel/MI200/perfmon/SQ_INST_LEVEL_LDS.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/join_type_kernel/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt b/tests/workloads/join_type_kernel/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt new file mode 100644 index 0000000000..6cca322d4e --- /dev/null +++ b/tests/workloads/join_type_kernel/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/join_type_kernel/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt b/tests/workloads/join_type_kernel/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt new file mode 100644 index 0000000000..e527ad31ba --- /dev/null +++ b/tests/workloads/join_type_kernel/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/join_type_kernel/MI200/perfmon/SQ_LEVEL_WAVES.txt b/tests/workloads/join_type_kernel/MI200/perfmon/SQ_LEVEL_WAVES.txt new file mode 100644 index 0000000000..3f8e04adb3 --- /dev/null +++ b/tests/workloads/join_type_kernel/MI200/perfmon/SQ_LEVEL_WAVES.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_0.txt b/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_0.txt new file mode 100644 index 0000000000..4ffdc32149 --- /dev/null +++ b/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_0.txt @@ -0,0 +1,5 @@ +pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES SQ_INSTS_VALU_CVT SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU GRBM_COUNT GRBM_GUI_ACTIVE TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum TA_TA_BUSY_sum TA_BUFFER_WAVEFRONTS_sum TD_TD_BUSY_sum TD_TC_STALL_sum SPI_CSN_WINDOW_VALID SPI_CSN_BUSY CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_1.txt b/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_1.txt new file mode 100644 index 0000000000..6c277f4a37 --- /dev/null +++ b/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_1.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VSKIPPED SQ_INSTS SQ_INSTS_VALU SQ_INSTS_VALU_ADD_F16 SQ_INSTS_VALU_MUL_F16 SQ_INSTS_VALU_FMA_F16 SQ_INSTS_VALU_TRANS_F16 SQ_INSTS_VALU_ADD_F32 GRBM_SPI_BUSY TCP_READ_TAGCONFLICT_STALL_CYCLES_sum TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum TCP_TA_TCP_STATE_READ_sum TA_BUFFER_READ_WAVEFRONTS_sum TA_BUFFER_WRITE_WAVEFRONTS_sum TD_SPI_STALL_sum TD_LOAD_WAVEFRONT_sum SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_10.txt b/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_10.txt new file mode 100644 index 0000000000..7053d4dce6 --- /dev/null +++ b/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_10.txt @@ -0,0 +1,5 @@ +pmc: SQC_TC_DATA_WRITE_REQ SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES + +gpu: +range: +kernel: diff --git a/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_11.txt b/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_11.txt new file mode 100644 index 0000000000..77ae8b461f --- /dev/null +++ b/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_11.txt @@ -0,0 +1,5 @@ +pmc: SQC_ICACHE_MISSES_DUPLICATE SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE + +gpu: +range: +kernel: diff --git a/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_12.txt b/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_12.txt new file mode 100644 index 0000000000..dfb2cf65e5 --- /dev/null +++ b/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_12.txt @@ -0,0 +1,5 @@ +pmc: SQC_DCACHE_REQ_READ_1 SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 + +gpu: +range: +kernel: diff --git a/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_13.txt b/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_13.txt new file mode 100644 index 0000000000..062fc9644a --- /dev/null +++ b/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_13.txt @@ -0,0 +1,5 @@ +pmc: TCC_ATOMIC[0] TCC_CYCLE[0] TCC_EA_ATOMIC[0] TCC_EA_ATOMIC_LEVEL[0] TCC_ATOMIC[1] TCC_CYCLE[1] TCC_EA_ATOMIC[1] TCC_EA_ATOMIC_LEVEL[1] TCC_ATOMIC[2] TCC_CYCLE[2] TCC_EA_ATOMIC[2] TCC_EA_ATOMIC_LEVEL[2] TCC_ATOMIC[3] TCC_CYCLE[3] TCC_EA_ATOMIC[3] TCC_EA_ATOMIC_LEVEL[3] TCC_ATOMIC[4] TCC_CYCLE[4] TCC_EA_ATOMIC[4] TCC_EA_ATOMIC_LEVEL[4] TCC_ATOMIC[5] TCC_CYCLE[5] TCC_EA_ATOMIC[5] TCC_EA_ATOMIC_LEVEL[5] TCC_ATOMIC[6] TCC_CYCLE[6] TCC_EA_ATOMIC[6] TCC_EA_ATOMIC_LEVEL[6] TCC_ATOMIC[7] TCC_CYCLE[7] TCC_EA_ATOMIC[7] TCC_EA_ATOMIC_LEVEL[7] TCC_ATOMIC[8] TCC_CYCLE[8] TCC_EA_ATOMIC[8] TCC_EA_ATOMIC_LEVEL[8] TCC_ATOMIC[9] TCC_CYCLE[9] TCC_EA_ATOMIC[9] TCC_EA_ATOMIC_LEVEL[9] TCC_ATOMIC[10] TCC_CYCLE[10] TCC_EA_ATOMIC[10] TCC_EA_ATOMIC_LEVEL[10] TCC_ATOMIC[11] TCC_CYCLE[11] TCC_EA_ATOMIC[11] TCC_EA_ATOMIC_LEVEL[11] TCC_ATOMIC[12] TCC_CYCLE[12] TCC_EA_ATOMIC[12] TCC_EA_ATOMIC_LEVEL[12] TCC_ATOMIC[13] TCC_CYCLE[13] TCC_EA_ATOMIC[13] TCC_EA_ATOMIC_LEVEL[13] TCC_ATOMIC[14] TCC_CYCLE[14] TCC_EA_ATOMIC[14] TCC_EA_ATOMIC_LEVEL[14] TCC_ATOMIC[15] TCC_CYCLE[15] TCC_EA_ATOMIC[15] TCC_EA_ATOMIC_LEVEL[15] TCC_ATOMIC[16] TCC_CYCLE[16] TCC_EA_ATOMIC[16] TCC_EA_ATOMIC_LEVEL[16] TCC_ATOMIC[17] TCC_CYCLE[17] TCC_EA_ATOMIC[17] TCC_EA_ATOMIC_LEVEL[17] TCC_ATOMIC[18] TCC_CYCLE[18] TCC_EA_ATOMIC[18] TCC_EA_ATOMIC_LEVEL[18] TCC_ATOMIC[19] TCC_CYCLE[19] TCC_EA_ATOMIC[19] TCC_EA_ATOMIC_LEVEL[19] TCC_ATOMIC[20] TCC_CYCLE[20] TCC_EA_ATOMIC[20] TCC_EA_ATOMIC_LEVEL[20] TCC_ATOMIC[21] TCC_CYCLE[21] TCC_EA_ATOMIC[21] TCC_EA_ATOMIC_LEVEL[21] TCC_ATOMIC[22] TCC_CYCLE[22] TCC_EA_ATOMIC[22] TCC_EA_ATOMIC_LEVEL[22] TCC_ATOMIC[23] TCC_CYCLE[23] TCC_EA_ATOMIC[23] TCC_EA_ATOMIC_LEVEL[23] TCC_ATOMIC[24] TCC_CYCLE[24] TCC_EA_ATOMIC[24] TCC_EA_ATOMIC_LEVEL[24] TCC_ATOMIC[25] TCC_CYCLE[25] TCC_EA_ATOMIC[25] TCC_EA_ATOMIC_LEVEL[25] TCC_ATOMIC[26] TCC_CYCLE[26] TCC_EA_ATOMIC[26] TCC_EA_ATOMIC_LEVEL[26] TCC_ATOMIC[27] TCC_CYCLE[27] TCC_EA_ATOMIC[27] TCC_EA_ATOMIC_LEVEL[27] TCC_ATOMIC[28] TCC_CYCLE[28] TCC_EA_ATOMIC[28] TCC_EA_ATOMIC_LEVEL[28] TCC_ATOMIC[29] TCC_CYCLE[29] TCC_EA_ATOMIC[29] TCC_EA_ATOMIC_LEVEL[29] TCC_ATOMIC[30] TCC_CYCLE[30] TCC_EA_ATOMIC[30] TCC_EA_ATOMIC_LEVEL[30] TCC_ATOMIC[31] TCC_CYCLE[31] TCC_EA_ATOMIC[31] TCC_EA_ATOMIC_LEVEL[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_14.txt b/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_14.txt new file mode 100644 index 0000000000..e0698dbf57 --- /dev/null +++ b/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_14.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_EA_RDREQ_GMI_CREDIT_STALL[0] TCC_EA_RDREQ[1] TCC_EA_RDREQ_32B[1] TCC_EA_RDREQ_DRAM_CREDIT_STALL[1] TCC_EA_RDREQ_GMI_CREDIT_STALL[1] TCC_EA_RDREQ[2] TCC_EA_RDREQ_32B[2] TCC_EA_RDREQ_DRAM_CREDIT_STALL[2] TCC_EA_RDREQ_GMI_CREDIT_STALL[2] TCC_EA_RDREQ[3] TCC_EA_RDREQ_32B[3] TCC_EA_RDREQ_DRAM_CREDIT_STALL[3] TCC_EA_RDREQ_GMI_CREDIT_STALL[3] TCC_EA_RDREQ[4] TCC_EA_RDREQ_32B[4] TCC_EA_RDREQ_DRAM_CREDIT_STALL[4] TCC_EA_RDREQ_GMI_CREDIT_STALL[4] TCC_EA_RDREQ[5] TCC_EA_RDREQ_32B[5] TCC_EA_RDREQ_DRAM_CREDIT_STALL[5] TCC_EA_RDREQ_GMI_CREDIT_STALL[5] TCC_EA_RDREQ[6] TCC_EA_RDREQ_32B[6] TCC_EA_RDREQ_DRAM_CREDIT_STALL[6] TCC_EA_RDREQ_GMI_CREDIT_STALL[6] TCC_EA_RDREQ[7] TCC_EA_RDREQ_32B[7] TCC_EA_RDREQ_DRAM_CREDIT_STALL[7] TCC_EA_RDREQ_GMI_CREDIT_STALL[7] TCC_EA_RDREQ[8] TCC_EA_RDREQ_32B[8] TCC_EA_RDREQ_DRAM_CREDIT_STALL[8] TCC_EA_RDREQ_GMI_CREDIT_STALL[8] TCC_EA_RDREQ[9] TCC_EA_RDREQ_32B[9] TCC_EA_RDREQ_DRAM_CREDIT_STALL[9] TCC_EA_RDREQ_GMI_CREDIT_STALL[9] TCC_EA_RDREQ[10] TCC_EA_RDREQ_32B[10] TCC_EA_RDREQ_DRAM_CREDIT_STALL[10] TCC_EA_RDREQ_GMI_CREDIT_STALL[10] TCC_EA_RDREQ[11] TCC_EA_RDREQ_32B[11] TCC_EA_RDREQ_DRAM_CREDIT_STALL[11] TCC_EA_RDREQ_GMI_CREDIT_STALL[11] TCC_EA_RDREQ[12] TCC_EA_RDREQ_32B[12] TCC_EA_RDREQ_DRAM_CREDIT_STALL[12] TCC_EA_RDREQ_GMI_CREDIT_STALL[12] TCC_EA_RDREQ[13] TCC_EA_RDREQ_32B[13] TCC_EA_RDREQ_DRAM_CREDIT_STALL[13] TCC_EA_RDREQ_GMI_CREDIT_STALL[13] TCC_EA_RDREQ[14] TCC_EA_RDREQ_32B[14] TCC_EA_RDREQ_DRAM_CREDIT_STALL[14] TCC_EA_RDREQ_GMI_CREDIT_STALL[14] TCC_EA_RDREQ[15] TCC_EA_RDREQ_32B[15] TCC_EA_RDREQ_DRAM_CREDIT_STALL[15] TCC_EA_RDREQ_GMI_CREDIT_STALL[15] TCC_EA_RDREQ[16] TCC_EA_RDREQ_32B[16] TCC_EA_RDREQ_DRAM_CREDIT_STALL[16] TCC_EA_RDREQ_GMI_CREDIT_STALL[16] TCC_EA_RDREQ[17] TCC_EA_RDREQ_32B[17] TCC_EA_RDREQ_DRAM_CREDIT_STALL[17] TCC_EA_RDREQ_GMI_CREDIT_STALL[17] TCC_EA_RDREQ[18] TCC_EA_RDREQ_32B[18] TCC_EA_RDREQ_DRAM_CREDIT_STALL[18] TCC_EA_RDREQ_GMI_CREDIT_STALL[18] TCC_EA_RDREQ[19] TCC_EA_RDREQ_32B[19] TCC_EA_RDREQ_DRAM_CREDIT_STALL[19] TCC_EA_RDREQ_GMI_CREDIT_STALL[19] TCC_EA_RDREQ[20] TCC_EA_RDREQ_32B[20] TCC_EA_RDREQ_DRAM_CREDIT_STALL[20] TCC_EA_RDREQ_GMI_CREDIT_STALL[20] TCC_EA_RDREQ[21] TCC_EA_RDREQ_32B[21] TCC_EA_RDREQ_DRAM_CREDIT_STALL[21] TCC_EA_RDREQ_GMI_CREDIT_STALL[21] TCC_EA_RDREQ[22] TCC_EA_RDREQ_32B[22] TCC_EA_RDREQ_DRAM_CREDIT_STALL[22] TCC_EA_RDREQ_GMI_CREDIT_STALL[22] TCC_EA_RDREQ[23] TCC_EA_RDREQ_32B[23] TCC_EA_RDREQ_DRAM_CREDIT_STALL[23] TCC_EA_RDREQ_GMI_CREDIT_STALL[23] TCC_EA_RDREQ[24] TCC_EA_RDREQ_32B[24] TCC_EA_RDREQ_DRAM_CREDIT_STALL[24] TCC_EA_RDREQ_GMI_CREDIT_STALL[24] TCC_EA_RDREQ[25] TCC_EA_RDREQ_32B[25] TCC_EA_RDREQ_DRAM_CREDIT_STALL[25] TCC_EA_RDREQ_GMI_CREDIT_STALL[25] TCC_EA_RDREQ[26] TCC_EA_RDREQ_32B[26] TCC_EA_RDREQ_DRAM_CREDIT_STALL[26] TCC_EA_RDREQ_GMI_CREDIT_STALL[26] TCC_EA_RDREQ[27] TCC_EA_RDREQ_32B[27] TCC_EA_RDREQ_DRAM_CREDIT_STALL[27] TCC_EA_RDREQ_GMI_CREDIT_STALL[27] TCC_EA_RDREQ[28] TCC_EA_RDREQ_32B[28] TCC_EA_RDREQ_DRAM_CREDIT_STALL[28] TCC_EA_RDREQ_GMI_CREDIT_STALL[28] TCC_EA_RDREQ[29] TCC_EA_RDREQ_32B[29] TCC_EA_RDREQ_DRAM_CREDIT_STALL[29] TCC_EA_RDREQ_GMI_CREDIT_STALL[29] TCC_EA_RDREQ[30] TCC_EA_RDREQ_32B[30] TCC_EA_RDREQ_DRAM_CREDIT_STALL[30] TCC_EA_RDREQ_GMI_CREDIT_STALL[30] TCC_EA_RDREQ[31] TCC_EA_RDREQ_32B[31] TCC_EA_RDREQ_DRAM_CREDIT_STALL[31] TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_15.txt b/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_15.txt new file mode 100644 index 0000000000..77ad088669 --- /dev/null +++ b/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_15.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ[0] TCC_EA_WRREQ_64B[0] TCC_EA_RDREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_LEVEL[1] TCC_EA_WRREQ[1] TCC_EA_WRREQ_64B[1] TCC_EA_RDREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_LEVEL[2] TCC_EA_WRREQ[2] TCC_EA_WRREQ_64B[2] TCC_EA_RDREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_LEVEL[3] TCC_EA_WRREQ[3] TCC_EA_WRREQ_64B[3] TCC_EA_RDREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_LEVEL[4] TCC_EA_WRREQ[4] TCC_EA_WRREQ_64B[4] TCC_EA_RDREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_LEVEL[5] TCC_EA_WRREQ[5] TCC_EA_WRREQ_64B[5] TCC_EA_RDREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_LEVEL[6] TCC_EA_WRREQ[6] TCC_EA_WRREQ_64B[6] TCC_EA_RDREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_LEVEL[7] TCC_EA_WRREQ[7] TCC_EA_WRREQ_64B[7] TCC_EA_RDREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_LEVEL[8] TCC_EA_WRREQ[8] TCC_EA_WRREQ_64B[8] TCC_EA_RDREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_LEVEL[9] TCC_EA_WRREQ[9] TCC_EA_WRREQ_64B[9] TCC_EA_RDREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_LEVEL[10] TCC_EA_WRREQ[10] TCC_EA_WRREQ_64B[10] TCC_EA_RDREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_LEVEL[11] TCC_EA_WRREQ[11] TCC_EA_WRREQ_64B[11] TCC_EA_RDREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_LEVEL[12] TCC_EA_WRREQ[12] TCC_EA_WRREQ_64B[12] TCC_EA_RDREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_LEVEL[13] TCC_EA_WRREQ[13] TCC_EA_WRREQ_64B[13] TCC_EA_RDREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_LEVEL[14] TCC_EA_WRREQ[14] TCC_EA_WRREQ_64B[14] TCC_EA_RDREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_LEVEL[15] TCC_EA_WRREQ[15] TCC_EA_WRREQ_64B[15] TCC_EA_RDREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_LEVEL[16] TCC_EA_WRREQ[16] TCC_EA_WRREQ_64B[16] TCC_EA_RDREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_LEVEL[17] TCC_EA_WRREQ[17] TCC_EA_WRREQ_64B[17] TCC_EA_RDREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_LEVEL[18] TCC_EA_WRREQ[18] TCC_EA_WRREQ_64B[18] TCC_EA_RDREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_LEVEL[19] TCC_EA_WRREQ[19] TCC_EA_WRREQ_64B[19] TCC_EA_RDREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_LEVEL[20] TCC_EA_WRREQ[20] TCC_EA_WRREQ_64B[20] TCC_EA_RDREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_LEVEL[21] TCC_EA_WRREQ[21] TCC_EA_WRREQ_64B[21] TCC_EA_RDREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_LEVEL[22] TCC_EA_WRREQ[22] TCC_EA_WRREQ_64B[22] TCC_EA_RDREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_LEVEL[23] TCC_EA_WRREQ[23] TCC_EA_WRREQ_64B[23] TCC_EA_RDREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_LEVEL[24] TCC_EA_WRREQ[24] TCC_EA_WRREQ_64B[24] TCC_EA_RDREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_LEVEL[25] TCC_EA_WRREQ[25] TCC_EA_WRREQ_64B[25] TCC_EA_RDREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_LEVEL[26] TCC_EA_WRREQ[26] TCC_EA_WRREQ_64B[26] TCC_EA_RDREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_LEVEL[27] TCC_EA_WRREQ[27] TCC_EA_WRREQ_64B[27] TCC_EA_RDREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_LEVEL[28] TCC_EA_WRREQ[28] TCC_EA_WRREQ_64B[28] TCC_EA_RDREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_LEVEL[29] TCC_EA_WRREQ[29] TCC_EA_WRREQ_64B[29] TCC_EA_RDREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_LEVEL[30] TCC_EA_WRREQ[30] TCC_EA_WRREQ_64B[30] TCC_EA_RDREQ_IO_CREDIT_STALL[31] TCC_EA_RDREQ_LEVEL[31] TCC_EA_WRREQ[31] TCC_EA_WRREQ_64B[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_16.txt b/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_16.txt new file mode 100644 index 0000000000..d0628bb948 --- /dev/null +++ b/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_16.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_WRREQ_IO_CREDIT_STALL[0] TCC_EA_WRREQ_LEVEL[0] TCC_EA_WRREQ_DRAM_CREDIT_STALL[1] TCC_EA_WRREQ_GMI_CREDIT_STALL[1] TCC_EA_WRREQ_IO_CREDIT_STALL[1] TCC_EA_WRREQ_LEVEL[1] TCC_EA_WRREQ_DRAM_CREDIT_STALL[2] TCC_EA_WRREQ_GMI_CREDIT_STALL[2] TCC_EA_WRREQ_IO_CREDIT_STALL[2] TCC_EA_WRREQ_LEVEL[2] TCC_EA_WRREQ_DRAM_CREDIT_STALL[3] TCC_EA_WRREQ_GMI_CREDIT_STALL[3] TCC_EA_WRREQ_IO_CREDIT_STALL[3] TCC_EA_WRREQ_LEVEL[3] TCC_EA_WRREQ_DRAM_CREDIT_STALL[4] TCC_EA_WRREQ_GMI_CREDIT_STALL[4] TCC_EA_WRREQ_IO_CREDIT_STALL[4] TCC_EA_WRREQ_LEVEL[4] TCC_EA_WRREQ_DRAM_CREDIT_STALL[5] TCC_EA_WRREQ_GMI_CREDIT_STALL[5] TCC_EA_WRREQ_IO_CREDIT_STALL[5] TCC_EA_WRREQ_LEVEL[5] TCC_EA_WRREQ_DRAM_CREDIT_STALL[6] TCC_EA_WRREQ_GMI_CREDIT_STALL[6] TCC_EA_WRREQ_IO_CREDIT_STALL[6] TCC_EA_WRREQ_LEVEL[6] TCC_EA_WRREQ_DRAM_CREDIT_STALL[7] TCC_EA_WRREQ_GMI_CREDIT_STALL[7] TCC_EA_WRREQ_IO_CREDIT_STALL[7] TCC_EA_WRREQ_LEVEL[7] TCC_EA_WRREQ_DRAM_CREDIT_STALL[8] TCC_EA_WRREQ_GMI_CREDIT_STALL[8] TCC_EA_WRREQ_IO_CREDIT_STALL[8] TCC_EA_WRREQ_LEVEL[8] TCC_EA_WRREQ_DRAM_CREDIT_STALL[9] TCC_EA_WRREQ_GMI_CREDIT_STALL[9] TCC_EA_WRREQ_IO_CREDIT_STALL[9] TCC_EA_WRREQ_LEVEL[9] TCC_EA_WRREQ_DRAM_CREDIT_STALL[10] TCC_EA_WRREQ_GMI_CREDIT_STALL[10] TCC_EA_WRREQ_IO_CREDIT_STALL[10] TCC_EA_WRREQ_LEVEL[10] TCC_EA_WRREQ_DRAM_CREDIT_STALL[11] TCC_EA_WRREQ_GMI_CREDIT_STALL[11] TCC_EA_WRREQ_IO_CREDIT_STALL[11] TCC_EA_WRREQ_LEVEL[11] TCC_EA_WRREQ_DRAM_CREDIT_STALL[12] TCC_EA_WRREQ_GMI_CREDIT_STALL[12] TCC_EA_WRREQ_IO_CREDIT_STALL[12] TCC_EA_WRREQ_LEVEL[12] TCC_EA_WRREQ_DRAM_CREDIT_STALL[13] TCC_EA_WRREQ_GMI_CREDIT_STALL[13] TCC_EA_WRREQ_IO_CREDIT_STALL[13] TCC_EA_WRREQ_LEVEL[13] TCC_EA_WRREQ_DRAM_CREDIT_STALL[14] TCC_EA_WRREQ_GMI_CREDIT_STALL[14] TCC_EA_WRREQ_IO_CREDIT_STALL[14] TCC_EA_WRREQ_LEVEL[14] TCC_EA_WRREQ_DRAM_CREDIT_STALL[15] TCC_EA_WRREQ_GMI_CREDIT_STALL[15] TCC_EA_WRREQ_IO_CREDIT_STALL[15] TCC_EA_WRREQ_LEVEL[15] TCC_EA_WRREQ_DRAM_CREDIT_STALL[16] TCC_EA_WRREQ_GMI_CREDIT_STALL[16] TCC_EA_WRREQ_IO_CREDIT_STALL[16] TCC_EA_WRREQ_LEVEL[16] TCC_EA_WRREQ_DRAM_CREDIT_STALL[17] TCC_EA_WRREQ_GMI_CREDIT_STALL[17] TCC_EA_WRREQ_IO_CREDIT_STALL[17] TCC_EA_WRREQ_LEVEL[17] TCC_EA_WRREQ_DRAM_CREDIT_STALL[18] TCC_EA_WRREQ_GMI_CREDIT_STALL[18] TCC_EA_WRREQ_IO_CREDIT_STALL[18] TCC_EA_WRREQ_LEVEL[18] TCC_EA_WRREQ_DRAM_CREDIT_STALL[19] TCC_EA_WRREQ_GMI_CREDIT_STALL[19] TCC_EA_WRREQ_IO_CREDIT_STALL[19] TCC_EA_WRREQ_LEVEL[19] TCC_EA_WRREQ_DRAM_CREDIT_STALL[20] TCC_EA_WRREQ_GMI_CREDIT_STALL[20] TCC_EA_WRREQ_IO_CREDIT_STALL[20] TCC_EA_WRREQ_LEVEL[20] TCC_EA_WRREQ_DRAM_CREDIT_STALL[21] TCC_EA_WRREQ_GMI_CREDIT_STALL[21] TCC_EA_WRREQ_IO_CREDIT_STALL[21] TCC_EA_WRREQ_LEVEL[21] TCC_EA_WRREQ_DRAM_CREDIT_STALL[22] TCC_EA_WRREQ_GMI_CREDIT_STALL[22] TCC_EA_WRREQ_IO_CREDIT_STALL[22] TCC_EA_WRREQ_LEVEL[22] TCC_EA_WRREQ_DRAM_CREDIT_STALL[23] TCC_EA_WRREQ_GMI_CREDIT_STALL[23] TCC_EA_WRREQ_IO_CREDIT_STALL[23] TCC_EA_WRREQ_LEVEL[23] TCC_EA_WRREQ_DRAM_CREDIT_STALL[24] TCC_EA_WRREQ_GMI_CREDIT_STALL[24] TCC_EA_WRREQ_IO_CREDIT_STALL[24] TCC_EA_WRREQ_LEVEL[24] TCC_EA_WRREQ_DRAM_CREDIT_STALL[25] TCC_EA_WRREQ_GMI_CREDIT_STALL[25] TCC_EA_WRREQ_IO_CREDIT_STALL[25] TCC_EA_WRREQ_LEVEL[25] TCC_EA_WRREQ_DRAM_CREDIT_STALL[26] TCC_EA_WRREQ_GMI_CREDIT_STALL[26] TCC_EA_WRREQ_IO_CREDIT_STALL[26] TCC_EA_WRREQ_LEVEL[26] TCC_EA_WRREQ_DRAM_CREDIT_STALL[27] TCC_EA_WRREQ_GMI_CREDIT_STALL[27] TCC_EA_WRREQ_IO_CREDIT_STALL[27] TCC_EA_WRREQ_LEVEL[27] TCC_EA_WRREQ_DRAM_CREDIT_STALL[28] TCC_EA_WRREQ_GMI_CREDIT_STALL[28] TCC_EA_WRREQ_IO_CREDIT_STALL[28] TCC_EA_WRREQ_LEVEL[28] TCC_EA_WRREQ_DRAM_CREDIT_STALL[29] TCC_EA_WRREQ_GMI_CREDIT_STALL[29] TCC_EA_WRREQ_IO_CREDIT_STALL[29] TCC_EA_WRREQ_LEVEL[29] TCC_EA_WRREQ_DRAM_CREDIT_STALL[30] TCC_EA_WRREQ_GMI_CREDIT_STALL[30] TCC_EA_WRREQ_IO_CREDIT_STALL[30] TCC_EA_WRREQ_LEVEL[30] TCC_EA_WRREQ_DRAM_CREDIT_STALL[31] TCC_EA_WRREQ_GMI_CREDIT_STALL[31] TCC_EA_WRREQ_IO_CREDIT_STALL[31] TCC_EA_WRREQ_LEVEL[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_17.txt b/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_17.txt new file mode 100644 index 0000000000..343869c5f1 --- /dev/null +++ b/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_17.txt @@ -0,0 +1,5 @@ +pmc: TCC_HIT[0] TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_HIT[1] TCC_MISS[1] TCC_READ[1] TCC_REQ[1] TCC_HIT[2] TCC_MISS[2] TCC_READ[2] TCC_REQ[2] TCC_HIT[3] TCC_MISS[3] TCC_READ[3] TCC_REQ[3] TCC_HIT[4] TCC_MISS[4] TCC_READ[4] TCC_REQ[4] TCC_HIT[5] TCC_MISS[5] TCC_READ[5] TCC_REQ[5] TCC_HIT[6] TCC_MISS[6] TCC_READ[6] TCC_REQ[6] TCC_HIT[7] TCC_MISS[7] TCC_READ[7] TCC_REQ[7] TCC_HIT[8] TCC_MISS[8] TCC_READ[8] TCC_REQ[8] TCC_HIT[9] TCC_MISS[9] TCC_READ[9] TCC_REQ[9] TCC_HIT[10] TCC_MISS[10] TCC_READ[10] TCC_REQ[10] TCC_HIT[11] TCC_MISS[11] TCC_READ[11] TCC_REQ[11] TCC_HIT[12] TCC_MISS[12] TCC_READ[12] TCC_REQ[12] TCC_HIT[13] TCC_MISS[13] TCC_READ[13] TCC_REQ[13] TCC_HIT[14] TCC_MISS[14] TCC_READ[14] TCC_REQ[14] TCC_HIT[15] TCC_MISS[15] TCC_READ[15] TCC_REQ[15] TCC_HIT[16] TCC_MISS[16] TCC_READ[16] TCC_REQ[16] TCC_HIT[17] TCC_MISS[17] TCC_READ[17] TCC_REQ[17] TCC_HIT[18] TCC_MISS[18] TCC_READ[18] TCC_REQ[18] TCC_HIT[19] TCC_MISS[19] TCC_READ[19] TCC_REQ[19] TCC_HIT[20] TCC_MISS[20] TCC_READ[20] TCC_REQ[20] TCC_HIT[21] TCC_MISS[21] TCC_READ[21] TCC_REQ[21] TCC_HIT[22] TCC_MISS[22] TCC_READ[22] TCC_REQ[22] TCC_HIT[23] TCC_MISS[23] TCC_READ[23] TCC_REQ[23] TCC_HIT[24] TCC_MISS[24] TCC_READ[24] TCC_REQ[24] TCC_HIT[25] TCC_MISS[25] TCC_READ[25] TCC_REQ[25] TCC_HIT[26] TCC_MISS[26] TCC_READ[26] TCC_REQ[26] TCC_HIT[27] TCC_MISS[27] TCC_READ[27] TCC_REQ[27] TCC_HIT[28] TCC_MISS[28] TCC_READ[28] TCC_REQ[28] TCC_HIT[29] TCC_MISS[29] TCC_READ[29] TCC_REQ[29] TCC_HIT[30] TCC_MISS[30] TCC_READ[30] TCC_REQ[30] TCC_HIT[31] TCC_MISS[31] TCC_READ[31] TCC_REQ[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_18.txt b/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_18.txt new file mode 100644 index 0000000000..a74cefd281 --- /dev/null +++ b/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_18.txt @@ -0,0 +1,5 @@ +pmc: TCC_RW_REQ[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_RW_REQ[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_WRITE[1] TCC_RW_REQ[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_WRITE[2] TCC_RW_REQ[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_WRITE[3] TCC_RW_REQ[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_WRITE[4] TCC_RW_REQ[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_WRITE[5] TCC_RW_REQ[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_WRITE[6] TCC_RW_REQ[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_WRITE[7] TCC_RW_REQ[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_WRITE[8] TCC_RW_REQ[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_WRITE[9] TCC_RW_REQ[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_WRITE[10] TCC_RW_REQ[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_WRITE[11] TCC_RW_REQ[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_WRITE[12] TCC_RW_REQ[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_WRITE[13] TCC_RW_REQ[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_WRITE[14] TCC_RW_REQ[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_WRITE[15] TCC_RW_REQ[16] TCC_TOO_MANY_EA_WRREQS_STALL[16] TCC_WRITE[16] TCC_RW_REQ[17] TCC_TOO_MANY_EA_WRREQS_STALL[17] TCC_WRITE[17] TCC_RW_REQ[18] TCC_TOO_MANY_EA_WRREQS_STALL[18] TCC_WRITE[18] TCC_RW_REQ[19] TCC_TOO_MANY_EA_WRREQS_STALL[19] TCC_WRITE[19] TCC_RW_REQ[20] TCC_TOO_MANY_EA_WRREQS_STALL[20] TCC_WRITE[20] TCC_RW_REQ[21] TCC_TOO_MANY_EA_WRREQS_STALL[21] TCC_WRITE[21] TCC_RW_REQ[22] TCC_TOO_MANY_EA_WRREQS_STALL[22] TCC_WRITE[22] TCC_RW_REQ[23] TCC_TOO_MANY_EA_WRREQS_STALL[23] TCC_WRITE[23] TCC_RW_REQ[24] TCC_TOO_MANY_EA_WRREQS_STALL[24] TCC_WRITE[24] TCC_RW_REQ[25] TCC_TOO_MANY_EA_WRREQS_STALL[25] TCC_WRITE[25] TCC_RW_REQ[26] TCC_TOO_MANY_EA_WRREQS_STALL[26] TCC_WRITE[26] TCC_RW_REQ[27] TCC_TOO_MANY_EA_WRREQS_STALL[27] TCC_WRITE[27] TCC_RW_REQ[28] TCC_TOO_MANY_EA_WRREQS_STALL[28] TCC_WRITE[28] TCC_RW_REQ[29] TCC_TOO_MANY_EA_WRREQS_STALL[29] TCC_WRITE[29] TCC_RW_REQ[30] TCC_TOO_MANY_EA_WRREQS_STALL[30] TCC_WRITE[30] TCC_RW_REQ[31] TCC_TOO_MANY_EA_WRREQS_STALL[31] TCC_WRITE[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_2.txt b/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_2.txt new file mode 100644 index 0000000000..70b69f8928 --- /dev/null +++ b/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_2.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_MUL_F32 SQ_INSTS_VALU_FMA_F32 SQ_INSTS_VALU_TRANS_F32 SQ_INSTS_VALU_ADD_F64 SQ_INSTS_VALU_MUL_F64 SQ_INSTS_VALU_FMA_F64 SQ_INSTS_VALU_TRANS_F64 SQ_INSTS_VALU_INT32 TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum TA_BUFFER_ATOMIC_WAVEFRONTS_sum TA_BUFFER_TOTAL_CYCLES_sum TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_3.txt b/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_3.txt new file mode 100644 index 0000000000..e47f8e33c9 --- /dev/null +++ b/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_3.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_INT64 SQ_INSTS_SMEM SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum TD_COALESCABLE_WAVEFRONT_sum SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE CPF_CMP_UTCL1_STALL_ON_TRANSLATION TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_4.txt b/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_4.txt new file mode 100644 index 0000000000..2d96f365a9 --- /dev/null +++ b/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_4.txt @@ -0,0 +1,5 @@ +pmc: SQ_WAVE_CYCLES SQ_WAIT_ANY SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_BUSY_CU_CYCLES SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE TCC_EA_WRREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WR_UNCACHED_32B_sum TCC_EA_WRREQ_DRAM_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_5.txt b/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_5.txt new file mode 100644 index 0000000000..e50beed390 --- /dev/null +++ b/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_5.txt @@ -0,0 +1,5 @@ +pmc: SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU TCP_TCP_LATENCY_sum TCP_TCC_READ_REQ_LATENCY_sum TCP_TCC_WRITE_REQ_LATENCY_sum TCP_TCC_READ_REQ_sum TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN CPC_ME1_DC0_SPI_BUSY TCC_EA_WRREQ_STALL_sum TCC_EA_RDREQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RD_UNCACHED_32B_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_6.txt b/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_6.txt new file mode 100644 index 0000000000..15a2277c1b --- /dev/null +++ b/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_6.txt @@ -0,0 +1,5 @@ +pmc: SQ_THREAD_CYCLES_VALU SQ_IFETCH SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TCP_TCC_NC_READ_REQ_sum TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN TCC_EA_RDREQ_DRAM_sum TCC_TAG_STALL_sum TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_7.txt b/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_7.txt new file mode 100644 index 0000000000..b42ce91618 --- /dev/null +++ b/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_7.txt @@ -0,0 +1,5 @@ +pmc: SQ_WAVES_LT_32 SQ_WAVES_LT_16 SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TCP_TCC_UC_WRITE_REQ_sum TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR TCC_NORMAL_EVICT_sum TCC_ALL_TC_OP_INV_EVICT_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA_ATOMIC_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_8.txt b/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_8.txt new file mode 100644 index 0000000000..21d4c7a998 --- /dev/null +++ b/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_8.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM_NORM SQ_INSTS_MFMA SQ_INSTS_VALU_MFMA_I8 SQ_INSTS_VALU_MFMA_F16 SQ_INSTS_VALU_MFMA_BF16 SQ_INSTS_VALU_MFMA_F32 SQ_INSTS_VALU_MFMA_F64 SQ_VALU_MFMA_BUSY_CYCLES TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TCP_TCC_CC_ATOMIC_REQ_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN TCC_EA_RDREQ_LEVEL_sum TCC_EA_WRREQ_LEVEL_sum TCC_EA_ATOMIC_LEVEL_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_9.txt b/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_9.txt new file mode 100644 index 0000000000..9ffe5778c3 --- /dev/null +++ b/tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_9.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_FLAT_LDS_ONLY SQ_INSTS_VALU_MFMA_MOPS_I8 SQ_INSTS_VALU_MFMA_MOPS_F16 SQ_INSTS_VALU_MFMA_MOPS_BF16 SQ_INSTS_VALU_MFMA_MOPS_F32 SQ_INSTS_VALU_MFMA_MOPS_F64 SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum TCP_PENDING_STALL_CYCLES_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/join_type_kernel/MI200/perfmon/timestamps.txt b/tests/workloads/join_type_kernel/MI200/perfmon/timestamps.txt new file mode 100644 index 0000000000..676cca1b80 --- /dev/null +++ b/tests/workloads/join_type_kernel/MI200/perfmon/timestamps.txt @@ -0,0 +1,5 @@ +pmc: + +gpu: +range: +kernel: diff --git a/tests/workloads/join_type_kernel/MI200/pmc_perf.csv b/tests/workloads/join_type_kernel/MI200/pmc_perf.csv new file mode 100644 index 0000000000..237ce3d740 --- /dev/null +++ b/tests/workloads/join_type_kernel/MI200/pmc_perf.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_1,obj_1,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_2,obj_2,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,wave_size_3,obj_3,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_4,obj_4,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_5,obj_5,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,TD_COALESCABLE_WAVEFRONT_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_6,obj_6,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_7,obj_7,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,TCC_EA_ATOMIC_LEVEL_sum,wave_size_8,obj_8,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_9,obj_9,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_10,obj_10,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_11,obj_11,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_12,obj_12,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,wave_size_13,obj_13,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_14,obj_14,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_15,obj_15,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_16,obj_16,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_17,obj_17,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_18,obj_18,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_DRAM_sum,TCC_TAG_STALL_sum,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f11a8ec4ec0,0,0,0,1007315,39,0,0,1189616,0,0,0,983513,0,0,0,1163357,34,0,0,1147616,53,0,0,1304235,0,0,0,1077073,0,0,0,1214153,0,0,0,1022398,0,0,0,1068386,0,0,0,1105803,0,0,0,1116189,0,0,0,1070696,27,0,0,1071708,0,0,0,1207237,0,0,0,1120617,0,0,0,1112790,0,0,0,1059857,0,0,0,1139084,0,0,0,1098929,0,0,0,1066184,0,0,0,1133197,140,0,0,1300501,64,0,0,1196834,8,0,0,1119984,0,0,0,1064790,0,0,0,1011992,0,0,0,1267494,0,0,0,1101867,15,0,0,1136857,0,0,0,1086574,61,0,0,1329069,64,0x7f2565a40ec0,0,1238939,4096,4096,0,1321796,4096,4096,0,1141522,4096,4096,0,1279820,4096,4096,0,1086877,4096,4096,0,1365916,4096,4096,0,1185993,4096,4096,0,1280162,4096,4096,0,1333014,4096,4096,0,1118567,4096,4096,0,1144647,4096,4096,0,1083558,4096,4096,0,1006637,4096,4096,0,1438187,4096,4096,0,1299268,4096,4096,0,1353210,4096,4096,0,1385738,4096,4096,0,1209166,4096,4096,0,1009855,4096,4096,0,1262748,4096,4096,0,1126406,4096,4096,0,1135359,4096,4096,0,1421713,4096,4096,0,1139755,4096,4096,0,1505235,4096,4096,0,1201582,4096,4096,0,1286286,4096,4096,0,1227006,4096,4096,0,1129740,4096,4096,0,1136219,4096,4096,0,1051905,4096,4096,0,1406964,4096,4096,64,0x7f5315864ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65551.0,0.0,0.0,0.0,64,0x7f57d2d58ec0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,64,0x7ff75c550ec0,226816,128040,16384,0,16384,16384,32768,49152,28351,28351,1942270.0,1348362.0,3425.0,160830.0,1054361.0,0.0,1340808.0,1041641.0,225105,136176,28351,0,28351,0,907232.0,489526.0,0.0,0.0,64,0x7f49b0804ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,10546,0,814,28606,0,73239.0,131072.0,0.0,65568.0,64,0x7fbb4b638ec0,1311,117096,0,0,65536,63800,56,1680,64,0x7fc7a1990ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,37032652.0,33925784.0,0.0,64,0x7f77b9620ec0,2247,4096,2247,6343,2316,4096,2316,6412,2307,4096,2307,6403,2258,4096,2258,6354,2305,4096,2305,6401,2321,4096,2321,6417,2268,4096,2268,6364,2303,4096,2303,6399,2305,4096,2305,6401,2248,4096,2248,6344,2322,4096,2322,6418,2309,4100,2313,6409,2263,4096,2263,6359,2309,4096,2309,6405,2378,4097,2379,6475,2272,4096,2272,6368,2270,4096,2270,6366,2321,4096,2321,6417,2271,4096,2271,6367,2299,4096,2299,6395,2279,4096,2279,6375,2285,4096,2285,6381,2273,4097,2274,6370,2432,4098,2434,6530,2266,4096,2266,6362,2269,4096,2269,6365,2321,4096,2321,6417,2273,4096,2273,6369,2296,4096,2296,6392,2276,4096,2276,6372,2287,4097,2288,6384,2278,4096,2278,6374,64,0x7fc48fcfcec0,32768,32768,0,64,0x7f758889cec0,0,0,0,224,0,65536,64195,56,64,0x7f65ea01cec0,10536395,9608540,583791,344064,1591722,0,0,163840,832.0,515136.0,0.0,524288.0,303839.0,32768.0,439353,0,0,10677,131072.0,131072.0,0.0,131072.0,64,0x7f010467cec0,114688,0,32768,32768,16384,16384,65536,49152,28113989.0,87706208.0,39298511.0,131072.0,0.0,251262.0,0,0,15324,317.0,131081.0,0.0,10.0,64,0x7f4cdd6c0ec0,6356,0,4096,6449,0,4096,6342,0,4096,6397,0,4096,6393,0,4096,6409,0,4096,6406,0,4096,6413,0,4096,6412,0,4096,6361,0,4096,6450,0,4096,6343,0,4096,6400,0,4096,6392,0,4096,6419,0,4096,6404,0,4096,6365,0,4096,6397,0,4096,6400,0,4096,6393,0,4096,6391,0,4096,6395,0,4096,6403,0,4096,6556,0,4096,6392,0,4096,6369,0,4096,6397,0,4096,6399,0,4096,6396,0,4096,6390,0,4096,6395,0,4096,6407,0,4096,64,0x7f1533aa4ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13188,19029,7031,545,0,26645,204262.0,0.0,73181.0,131081.0,64,0x7f47a23e8ec0,4096,0,0,0,4096,0,96,0,4096,0,3,0,4096,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,4,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,9,0,4096,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4099,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,64,0x7f60839d8ec0,0,0,0,0,0,0,168,56,131072.0,131072.0,0.0,966657.0,64,0x7f8798ba0ec0,0,393216,163840,0,0,0,0,0,17846,0.0,0.0,0.0,32768.0,0.0,0.0,406.0,32768.0,4096,16384,352,28073,1977,0,56.0,6.0,0.0,204188.0,64,0x7f58eb278ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131079.0,34822.0,46066.0,19470.0,197534469403014,197534469423814 +1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f11a8ec4ec0,0,0,0,1681864,1157,0,0,2336782,0,0,0,1880973,0,0,0,1739457,0,0,0,2105791,98,0,0,2009773,0,0,0,1417692,0,0,0,1569072,45,0,0,1787526,0,0,0,1664234,327,0,0,2201628,0,0,0,1505290,0,0,0,1645125,0,0,0,1790717,399,0,0,1969953,0,0,0,1808482,0,0,0,2109567,0,0,0,1639341,0,0,0,1611493,27,0,0,2029072,45,0,0,2037365,0,0,0,1964090,0,0,0,1548459,0,0,0,1590182,0,0,0,1681430,0,0,0,1508421,0,0,0,1594495,0,0,0,2017490,294,0,0,2323506,0,0,0,1541346,0,0,0,1708532,0,0,0,1671681,64,0x7f2565a40ec0,0,4104088,2832,2832,0,3377787,2888,2888,0,3154501,2864,2864,0,3691821,2846,2846,0,4274405,2848,2848,0,4078805,2840,2840,0,3832564,2860,2860,0,4344106,2816,2816,0,3777759,2812,2812,0,4215638,2832,2832,0,3372974,2892,2892,0,3513156,2864,2864,0,3319756,2844,2844,0,3725769,2844,2844,0,5032648,2836,2836,0,4076490,2864,2864,0,4442759,2788,2788,0,3998065,2844,2844,0,3291996,2860,2860,0,3732274,2858,2858,0,3725579,2832,2832,0,3790802,2876,2876,0,4323988,2812,2812,0,4531118,2792,2792,0,4215108,2800,2800,0,3480650,2788,2788,0,4051515,2848,2848,0,3345974,2864,2864,0,3962030,2860,2860,0,3277791,2832,2832,0,3759086,2876,2876,0,4003262,2812,2812,64,0x7f5315864ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65550.0,0.0,0.0,0.0,64,0x7f57d2d58ec0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,64,0x7ff75c550ec0,304808,208114,16384,0,16384,16384,32768,49152,38100,38100,2981450.0,2420731.0,4870.0,349336.0,1696772.0,0.0,2409153.0,2100771.0,304800,217129,38100,0,38100,0,1219200.0,782406.0,0.0,0.0,64,0x7f49b0804ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,20028,0,2682,38394,0,69683.0,131072.0,0.0,45702.0,64,0x7fbb4b638ec0,0,183466,0,0,65536,63800,56,1680,64,0x7fc7a1990ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,120711565.0,61038459.0,0.0,64,0x7f77b9620ec0,2178,4096,2178,6274,2156,4096,2156,6252,2178,4096,2178,6274,2192,4096,2192,6288,2167,4096,2167,6263,2188,4096,2188,6284,2170,4097,2171,6267,2170,4096,2170,6266,2172,4096,2172,6268,2178,4096,2178,6274,2157,4096,2157,6253,2176,4099,2179,6275,2192,4098,2194,6290,2170,4096,2170,6266,2249,4097,2250,6346,2173,4096,2173,6269,2189,4096,2189,6285,2185,4096,2185,6281,2177,4096,2177,6273,2189,4096,2189,6285,2179,4096,2179,6275,2201,4096,2201,6297,2176,4098,2178,6274,2189,4096,2189,6285,2194,4096,2194,6290,2188,4096,2188,6284,2190,4096,2190,6286,2177,4096,2177,6273,2188,4096,2188,6284,2176,4096,2176,6272,2204,4097,2205,6301,2180,4096,2180,6276,64,0x7fc48fcfcec0,32768,32768,0,64,0x7f758889cec0,0,0,0,56,0,65536,65536,0,64,0x7f65ea01cec0,18105127,17480878,280185,344064,2621959,0,0,163840,0.0,524288.0,0.0,524288.0,450660.0,32768.0,811541,0,0,11440,91086.0,91086.0,0.0,91086.0,64,0x7f010467cec0,114688,0,32768,32768,16384,16384,65536,49152,58171621.0,205626661.0,50069959.0,131072.0,0.0,611898.0,0,0,25318,21712.0,131081.0,0.0,16.0,64,0x7f4cdd6c0ec0,6275,0,4096,6271,0,4096,6253,0,4096,6292,0,4096,6312,0,4096,6297,0,4096,6244,0,4096,6310,0,4096,6306,0,4096,6278,0,4096,6270,0,4096,6255,0,4096,6298,0,4096,6318,0,4096,6298,0,4096,6244,0,4096,6258,0,4096,6272,0,4096,6307,0,4096,6295,0,4096,6298,0,4096,6283,0,4096,6290,0,4096,6308,0,4096,6309,0,4096,6262,0,4096,6274,0,4096,6305,0,4096,6296,0,4096,6300,0,4096,6290,0,4096,6293,0,4096,64,0x7f1533aa4ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,35077,27652,9637,2428,0,41696,200942.0,0.0,69860.0,131082.0,64,0x7f47a23e8ec0,4096,0,655,0,4096,0,2647,0,4096,0,0,0,4096,0,384,0,4097,0,200,0,4096,0,786,0,4096,0,0,0,4096,0,1515,0,4096,0,140,0,4096,0,0,0,4097,0,379,0,4097,0,10,0,4097,0,7,0,4096,0,129,0,4097,0,0,0,4096,0,0,0,4096,0,671,0,4096,0,379,0,4097,0,0,0,4096,0,251,0,4096,0,17,0,4096,0,336,0,4096,0,634,0,4096,0,485,0,4096,0,384,0,4096,0,10,0,4096,0,2050,0,4096,0,0,0,4096,0,0,0,4098,0,0,0,4096,0,77,0,4096,0,0,0,64,0x7f60839d8ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2067361.0,64,0x7f8798ba0ec0,0,393216,163840,0,0,0,0,0,29500,0.0,0.0,0.0,32768.0,0.0,0.0,229.0,32768.0,4096,16384,302,40644,2105,0,56.0,10.0,0.0,200748.0,64,0x7f58eb278ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131072.0,94206.0,45662.0,0.0,197534469442374,197534469458214 +2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f11a8ec4ec0,0,0,0,1676454,2428,0,0,2483059,727,0,0,2334287,83,0,0,1904635,1843,0,0,2594182,525,0,0,2145105,1210,0,0,2029494,605,0,0,2044622,272,0,0,2110620,133,0,0,1724892,463,0,0,1964694,81,0,0,1864282,99,0,0,1984387,23,0,0,1692604,300,0,0,1768711,365,0,0,2071225,990,0,0,2056212,775,0,0,2085514,0,0,0,1792482,642,0,0,2009626,0,0,0,1713394,73,0,0,1794106,99,0,0,1728848,384,0,0,2034476,110,0,0,1996001,354,0,0,1938879,1189,0,0,1895653,432,0,0,2095128,2816,0,0,2406156,0,0,0,1435593,546,0,0,2094062,204,0,0,1915341,64,0x7f2565a40ec0,0,3592130,2824,2824,0,3698511,2880,2880,0,3497819,2864,2864,0,4380389,2856,2856,0,4988869,2892,2892,0,4209329,2844,2844,0,3240813,2878,2878,0,4263186,2840,2840,0,3708697,2840,2840,0,3411640,2828,2828,0,3100503,2880,2880,0,3842991,2864,2864,0,4218852,2856,2856,0,4227496,2892,2892,0,4021193,2844,2844,0,3606101,2880,2880,0,3715972,2824,2824,0,3782859,2880,2880,0,3622843,2844,2844,0,4120590,2828,2828,0,3724007,2848,2848,0,3860902,2880,2880,0,4457536,2826,2826,0,4703301,2816,2816,0,4309151,2820,2820,0,3726238,2824,2824,0,3711726,2876,2876,0,3926718,2848,2848,0,3807224,2832,2832,0,3491191,2850,2850,0,3645776,2884,2884,0,3988806,2826,2826,64,0x7f5315864ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65552.0,0.0,0.0,0.0,64,0x7f57d2d58ec0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,64,0x7ff75c550ec0,331000,222485,16384,0,16384,16384,32768,49152,41374,41374,3169657.0,2441507.0,4418.0,376238.0,1761790.0,0.0,2429080.0,2119462.0,330992,231875,41374,0,41374,0,1323968.0,775441.0,0.0,0.0,64,0x7f49b0804ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,20411,0,2658,38528,0,69749.0,131072.0,0.0,45660.0,64,0x7fbb4b638ec0,0,182840,0,0,65536,63800,56,1680,64,0x7fc7a1990ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,119592813.0,61322433.0,0.0,64,0x7f77b9620ec0,2156,4096,2156,6252,2194,4096,2194,6290,2182,4096,2182,6278,2183,4096,2183,6279,2161,4096,2161,6257,2199,4096,2199,6295,2211,4097,2212,6308,2155,4096,2155,6251,2158,4096,2158,6254,2158,4096,2158,6254,2195,4096,2195,6291,2186,4099,2189,6285,2183,4098,2185,6281,2157,4096,2157,6253,2256,4097,2257,6353,2213,4096,2213,6309,2172,4096,2172,6268,2169,4096,2169,6265,2193,4096,2193,6289,2191,4096,2191,6287,2159,4096,2159,6255,2165,4096,2165,6261,2193,4098,2195,6291,2164,4096,2164,6260,2169,4096,2169,6265,2177,4096,2177,6273,2171,4096,2171,6267,2198,4096,2198,6294,2191,4096,2191,6287,2165,4096,2165,6261,2168,4097,2169,6265,2196,4096,2196,6292,64,0x7fc48fcfcec0,32768,32768,0,64,0x7f758889cec0,0,0,0,56,0,65536,65536,0,64,0x7f65ea01cec0,18870452,17817949,708439,344064,2697996,0,0,163840,832.0,515136.0,0.0,524288.0,724474.0,32768.0,906239,0,0,13414,91254.0,91254.0,0.0,91254.0,64,0x7f010467cec0,114688,0,32768,32768,16384,16384,65536,49152,59663501.0,198207422.0,49042649.0,131072.0,0.0,599383.0,0,0,26243,5758.0,131082.0,0.0,18.0,64,0x7f4cdd6c0ec0,6255,0,4096,6276,0,4096,6279,0,4096,6285,0,4096,6314,0,4096,6292,0,4096,6270,0,4096,6267,0,4096,6267,0,4096,6255,0,4096,6275,0,4096,6278,0,4096,6288,0,4096,6312,0,4096,6294,0,4096,6268,0,4096,6262,0,4096,6286,0,4096,6269,0,4096,6281,0,4096,6272,0,4096,6268,0,4096,6273,0,4096,6299,0,4096,6300,0,4096,6264,0,4096,6290,0,4096,6268,0,4096,6286,0,4096,6273,0,4096,6267,0,4096,6275,0,4096,64,0x7f1533aa4ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,31105,26693,9697,2761,0,40064,200968.0,0.0,69885.0,131083.0,64,0x7f47a23e8ec0,4096,0,120,0,4096,0,153,0,4096,0,89,0,4096,0,241,0,4097,0,245,0,4096,0,578,0,4096,0,16,0,4096,0,856,0,4096,0,304,0,4096,0,0,0,4097,0,288,0,4097,0,285,0,4097,0,119,0,4096,0,912,0,4097,0,531,0,4096,0,421,0,4096,0,0,0,4096,0,8,0,4097,0,90,0,4096,0,1574,0,4096,0,727,0,4096,0,395,0,4096,0,493,0,4096,0,372,0,4096,0,4,0,4096,0,0,0,4096,0,261,0,4096,0,247,0,4096,0,0,0,4098,0,0,0,4096,0,0,0,4096,0,425,0,64,0x7f60839d8ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,1994953.0,64,0x7f8798ba0ec0,0,393216,163840,0,0,0,0,0,29389,0.0,0.0,0.0,32768.0,0.0,0.0,222.0,32768.0,4096,16384,302,40513,2024,0,56.0,9.0,0.0,200689.0,64,0x7f58eb278ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131080.0,93329.0,45635.0,0.0,197534469518374,197534469534854 diff --git a/tests/workloads/join_type_kernel/MI200/roofline.csv b/tests/workloads/join_type_kernel/MI200/roofline.csv new file mode 100644 index 0000000000..7b3165d959 --- /dev/null +++ b/tests/workloads/join_type_kernel/MI200/roofline.csv @@ -0,0 +1,5 @@ +device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh +0,1388.448,1387.9089,1388.9871,5016.7466,5013.8638,5019.6294,9226.7217,9226.0068,9227.4365,18059.045,18058.148,18059.941,20942.623,20882.143,21003.104,20269.439,20268.814,20270.064,170476.59,170471.94,170481.25,164897.83,164892.17,164903.48,41427.602,41426.875,41428.328,41486.352,41485.453,41487.25,166360.88,165867.45,166854.3 +1,1389.4307,1388.9183,1389.943,5028.0605,5026.0166,5030.1045,9234.3291,9233.6504,9235.0078,18092.57,18089.195,18095.945,20972.26,20905.045,21039.475,20293.436,20292.846,20294.025,170832.91,170827.86,170837.95,165101.39,165098.03,165104.75,41481.762,41480.953,41482.57,41539.949,41538.82,41541.078,166855.14,166852.22,166858.06 +2,1388.6045,1387.962,1389.2469,5036.2583,5033.9248,5038.5918,9262.8096,9262.124,9263.4951,18108.311,18107.41,18109.211,21047.432,21047.041,21047.822,20350.363,20349.795,20350.932,171113.05,171108.91,171117.19,165496.91,165492.88,165500.94,41579.336,41578.238,41580.434,41638.969,41637.676,41640.262,166966.22,166370.66,167561.78 +3,1388.9966,1388.4054,1389.5878,5031.7676,5030.1387,5033.3965,9239.9658,9239.4111,9240.5205,18026.248,18022.998,18029.498,21033.547,21033.039,21034.055,20311.645,20310.9,20312.389,171005.2,171001.67,171008.73,165217.73,165214.55,165220.92,41441.426,41287.215,41595.637,41579.938,41579.328,41580.547,167016.2,167014.12,167018.28 diff --git a/tests/workloads/join_type_kernel/MI200/sysinfo.csv b/tests/workloads/join_type_kernel/MI200/sysinfo.csv new file mode 100644 index 0000000000..bc3b3ff1cf --- /dev/null +++ b/tests/workloads/join_type_kernel/MI200/sysinfo.csv @@ -0,0 +1,2 @@ +workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd +join_type_kernel,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 02:03:08 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/join_type_kernel/MI200/timestamps.csv b/tests/workloads/join_type_kernel/MI200/timestamps.csv new file mode 100644 index 0000000000..3e4c203ff4 --- /dev/null +++ b/tests/workloads/join_type_kernel/MI200/timestamps.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,260525,260525,1048576,256,0,0,8,0,16,64,0x0,0x7fb4f00c4ec0,197534469378582,197534469403014,197534469423814,197534469440359 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,260525,260525,1048576,256,0,0,8,0,16,64,0x0,0x7fb4f00c4ec0,197534469434578,197534469442374,197534469458214,197534469515060 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,260525,260525,1048576,256,0,0,8,0,16,64,0x0,0x7fb4f00c4ec0,197534469468642,197534469518374,197534469534854,197534469536010 diff --git a/tests/workloads/kernel/MI100/pmc_perf_16.csv b/tests/workloads/kernel/MI100/SQ_IFETCH_LEVEL.csv similarity index 100% rename from tests/workloads/kernel/MI100/pmc_perf_16.csv rename to tests/workloads/kernel/MI100/SQ_IFETCH_LEVEL.csv diff --git a/tests/workloads/kernel/MI100/perfmon/SQ_IFETCH_LEVEL.txt b/tests/workloads/kernel/MI100/perfmon/SQ_IFETCH_LEVEL.txt index 293092f641..7000361619 100644 --- a/tests/workloads/kernel/MI100/perfmon/SQ_IFETCH_LEVEL.txt +++ b/tests/workloads/kernel/MI100/perfmon/SQ_IFETCH_LEVEL.txt @@ -2,4 +2,4 @@ pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PRE gpu: range: -kernel: +kernel: "vecCopy(double*,,double*,,double*,,int,,int),[clone,.kd]" diff --git a/tests/workloads/kernel/MI100/perfmon/pmc_perf_16.txt b/tests/workloads/kernel/MI100/perfmon/pmc_perf_16.txt index 1010989b60..a74cefd281 100644 --- a/tests/workloads/kernel/MI100/perfmon/pmc_perf_16.txt +++ b/tests/workloads/kernel/MI100/perfmon/pmc_perf_16.txt @@ -2,4 +2,4 @@ pmc: TCC_RW_REQ[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_RW_REQ[1] T gpu: range: -kernel: "vecCopy(double*,,double*,,double*,,int,,int),[clone,.kd]" +kernel: diff --git a/tests/workloads/kernel/MI200/SQ_IFETCH_LEVEL.csv b/tests/workloads/kernel/MI200/SQ_IFETCH_LEVEL.csv new file mode 100644 index 0000000000..22456dbcab --- /dev/null +++ b/tests/workloads/kernel/MI200/SQ_IFETCH_LEVEL.csv @@ -0,0 +1 @@ +Index,KernelName diff --git a/tests/workloads/kernel/MI200/perfmon/SQ_IFETCH_LEVEL.txt b/tests/workloads/kernel/MI200/perfmon/SQ_IFETCH_LEVEL.txt new file mode 100644 index 0000000000..7000361619 --- /dev/null +++ b/tests/workloads/kernel/MI200/perfmon/SQ_IFETCH_LEVEL.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: "vecCopy(double*,,double*,,double*,,int,,int),[clone,.kd]" diff --git a/tests/workloads/kernel/MI200/perfmon/SQ_INST_LEVEL_LDS.txt b/tests/workloads/kernel/MI200/perfmon/SQ_INST_LEVEL_LDS.txt new file mode 100644 index 0000000000..08439eedce --- /dev/null +++ b/tests/workloads/kernel/MI200/perfmon/SQ_INST_LEVEL_LDS.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt b/tests/workloads/kernel/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt new file mode 100644 index 0000000000..6cca322d4e --- /dev/null +++ b/tests/workloads/kernel/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt b/tests/workloads/kernel/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt new file mode 100644 index 0000000000..e527ad31ba --- /dev/null +++ b/tests/workloads/kernel/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel/MI200/perfmon/SQ_LEVEL_WAVES.txt b/tests/workloads/kernel/MI200/perfmon/SQ_LEVEL_WAVES.txt new file mode 100644 index 0000000000..3f8e04adb3 --- /dev/null +++ b/tests/workloads/kernel/MI200/perfmon/SQ_LEVEL_WAVES.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel/MI200/perfmon/pmc_perf_0.txt b/tests/workloads/kernel/MI200/perfmon/pmc_perf_0.txt new file mode 100644 index 0000000000..4ffdc32149 --- /dev/null +++ b/tests/workloads/kernel/MI200/perfmon/pmc_perf_0.txt @@ -0,0 +1,5 @@ +pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES SQ_INSTS_VALU_CVT SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU GRBM_COUNT GRBM_GUI_ACTIVE TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum TA_TA_BUSY_sum TA_BUFFER_WAVEFRONTS_sum TD_TD_BUSY_sum TD_TC_STALL_sum SPI_CSN_WINDOW_VALID SPI_CSN_BUSY CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel/MI200/perfmon/pmc_perf_1.txt b/tests/workloads/kernel/MI200/perfmon/pmc_perf_1.txt new file mode 100644 index 0000000000..6c277f4a37 --- /dev/null +++ b/tests/workloads/kernel/MI200/perfmon/pmc_perf_1.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VSKIPPED SQ_INSTS SQ_INSTS_VALU SQ_INSTS_VALU_ADD_F16 SQ_INSTS_VALU_MUL_F16 SQ_INSTS_VALU_FMA_F16 SQ_INSTS_VALU_TRANS_F16 SQ_INSTS_VALU_ADD_F32 GRBM_SPI_BUSY TCP_READ_TAGCONFLICT_STALL_CYCLES_sum TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum TCP_TA_TCP_STATE_READ_sum TA_BUFFER_READ_WAVEFRONTS_sum TA_BUFFER_WRITE_WAVEFRONTS_sum TD_SPI_STALL_sum TD_LOAD_WAVEFRONT_sum SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel/MI200/perfmon/pmc_perf_10.txt b/tests/workloads/kernel/MI200/perfmon/pmc_perf_10.txt new file mode 100644 index 0000000000..7053d4dce6 --- /dev/null +++ b/tests/workloads/kernel/MI200/perfmon/pmc_perf_10.txt @@ -0,0 +1,5 @@ +pmc: SQC_TC_DATA_WRITE_REQ SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel/MI200/perfmon/pmc_perf_11.txt b/tests/workloads/kernel/MI200/perfmon/pmc_perf_11.txt new file mode 100644 index 0000000000..77ae8b461f --- /dev/null +++ b/tests/workloads/kernel/MI200/perfmon/pmc_perf_11.txt @@ -0,0 +1,5 @@ +pmc: SQC_ICACHE_MISSES_DUPLICATE SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel/MI200/perfmon/pmc_perf_12.txt b/tests/workloads/kernel/MI200/perfmon/pmc_perf_12.txt new file mode 100644 index 0000000000..dfb2cf65e5 --- /dev/null +++ b/tests/workloads/kernel/MI200/perfmon/pmc_perf_12.txt @@ -0,0 +1,5 @@ +pmc: SQC_DCACHE_REQ_READ_1 SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel/MI200/perfmon/pmc_perf_13.txt b/tests/workloads/kernel/MI200/perfmon/pmc_perf_13.txt new file mode 100644 index 0000000000..062fc9644a --- /dev/null +++ b/tests/workloads/kernel/MI200/perfmon/pmc_perf_13.txt @@ -0,0 +1,5 @@ +pmc: TCC_ATOMIC[0] TCC_CYCLE[0] TCC_EA_ATOMIC[0] TCC_EA_ATOMIC_LEVEL[0] TCC_ATOMIC[1] TCC_CYCLE[1] TCC_EA_ATOMIC[1] TCC_EA_ATOMIC_LEVEL[1] TCC_ATOMIC[2] TCC_CYCLE[2] TCC_EA_ATOMIC[2] TCC_EA_ATOMIC_LEVEL[2] TCC_ATOMIC[3] TCC_CYCLE[3] TCC_EA_ATOMIC[3] TCC_EA_ATOMIC_LEVEL[3] TCC_ATOMIC[4] TCC_CYCLE[4] TCC_EA_ATOMIC[4] TCC_EA_ATOMIC_LEVEL[4] TCC_ATOMIC[5] TCC_CYCLE[5] TCC_EA_ATOMIC[5] TCC_EA_ATOMIC_LEVEL[5] TCC_ATOMIC[6] TCC_CYCLE[6] TCC_EA_ATOMIC[6] TCC_EA_ATOMIC_LEVEL[6] TCC_ATOMIC[7] TCC_CYCLE[7] TCC_EA_ATOMIC[7] TCC_EA_ATOMIC_LEVEL[7] TCC_ATOMIC[8] TCC_CYCLE[8] TCC_EA_ATOMIC[8] TCC_EA_ATOMIC_LEVEL[8] TCC_ATOMIC[9] TCC_CYCLE[9] TCC_EA_ATOMIC[9] TCC_EA_ATOMIC_LEVEL[9] TCC_ATOMIC[10] TCC_CYCLE[10] TCC_EA_ATOMIC[10] TCC_EA_ATOMIC_LEVEL[10] TCC_ATOMIC[11] TCC_CYCLE[11] TCC_EA_ATOMIC[11] TCC_EA_ATOMIC_LEVEL[11] TCC_ATOMIC[12] TCC_CYCLE[12] TCC_EA_ATOMIC[12] TCC_EA_ATOMIC_LEVEL[12] TCC_ATOMIC[13] TCC_CYCLE[13] TCC_EA_ATOMIC[13] TCC_EA_ATOMIC_LEVEL[13] TCC_ATOMIC[14] TCC_CYCLE[14] TCC_EA_ATOMIC[14] TCC_EA_ATOMIC_LEVEL[14] TCC_ATOMIC[15] TCC_CYCLE[15] TCC_EA_ATOMIC[15] TCC_EA_ATOMIC_LEVEL[15] TCC_ATOMIC[16] TCC_CYCLE[16] TCC_EA_ATOMIC[16] TCC_EA_ATOMIC_LEVEL[16] TCC_ATOMIC[17] TCC_CYCLE[17] TCC_EA_ATOMIC[17] TCC_EA_ATOMIC_LEVEL[17] TCC_ATOMIC[18] TCC_CYCLE[18] TCC_EA_ATOMIC[18] TCC_EA_ATOMIC_LEVEL[18] TCC_ATOMIC[19] TCC_CYCLE[19] TCC_EA_ATOMIC[19] TCC_EA_ATOMIC_LEVEL[19] TCC_ATOMIC[20] TCC_CYCLE[20] TCC_EA_ATOMIC[20] TCC_EA_ATOMIC_LEVEL[20] TCC_ATOMIC[21] TCC_CYCLE[21] TCC_EA_ATOMIC[21] TCC_EA_ATOMIC_LEVEL[21] TCC_ATOMIC[22] TCC_CYCLE[22] TCC_EA_ATOMIC[22] TCC_EA_ATOMIC_LEVEL[22] TCC_ATOMIC[23] TCC_CYCLE[23] TCC_EA_ATOMIC[23] TCC_EA_ATOMIC_LEVEL[23] TCC_ATOMIC[24] TCC_CYCLE[24] TCC_EA_ATOMIC[24] TCC_EA_ATOMIC_LEVEL[24] TCC_ATOMIC[25] TCC_CYCLE[25] TCC_EA_ATOMIC[25] TCC_EA_ATOMIC_LEVEL[25] TCC_ATOMIC[26] TCC_CYCLE[26] TCC_EA_ATOMIC[26] TCC_EA_ATOMIC_LEVEL[26] TCC_ATOMIC[27] TCC_CYCLE[27] TCC_EA_ATOMIC[27] TCC_EA_ATOMIC_LEVEL[27] TCC_ATOMIC[28] TCC_CYCLE[28] TCC_EA_ATOMIC[28] TCC_EA_ATOMIC_LEVEL[28] TCC_ATOMIC[29] TCC_CYCLE[29] TCC_EA_ATOMIC[29] TCC_EA_ATOMIC_LEVEL[29] TCC_ATOMIC[30] TCC_CYCLE[30] TCC_EA_ATOMIC[30] TCC_EA_ATOMIC_LEVEL[30] TCC_ATOMIC[31] TCC_CYCLE[31] TCC_EA_ATOMIC[31] TCC_EA_ATOMIC_LEVEL[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel/MI200/perfmon/pmc_perf_14.txt b/tests/workloads/kernel/MI200/perfmon/pmc_perf_14.txt new file mode 100644 index 0000000000..e0698dbf57 --- /dev/null +++ b/tests/workloads/kernel/MI200/perfmon/pmc_perf_14.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_EA_RDREQ_GMI_CREDIT_STALL[0] TCC_EA_RDREQ[1] TCC_EA_RDREQ_32B[1] TCC_EA_RDREQ_DRAM_CREDIT_STALL[1] TCC_EA_RDREQ_GMI_CREDIT_STALL[1] TCC_EA_RDREQ[2] TCC_EA_RDREQ_32B[2] TCC_EA_RDREQ_DRAM_CREDIT_STALL[2] TCC_EA_RDREQ_GMI_CREDIT_STALL[2] TCC_EA_RDREQ[3] TCC_EA_RDREQ_32B[3] TCC_EA_RDREQ_DRAM_CREDIT_STALL[3] TCC_EA_RDREQ_GMI_CREDIT_STALL[3] TCC_EA_RDREQ[4] TCC_EA_RDREQ_32B[4] TCC_EA_RDREQ_DRAM_CREDIT_STALL[4] TCC_EA_RDREQ_GMI_CREDIT_STALL[4] TCC_EA_RDREQ[5] TCC_EA_RDREQ_32B[5] TCC_EA_RDREQ_DRAM_CREDIT_STALL[5] TCC_EA_RDREQ_GMI_CREDIT_STALL[5] TCC_EA_RDREQ[6] TCC_EA_RDREQ_32B[6] TCC_EA_RDREQ_DRAM_CREDIT_STALL[6] TCC_EA_RDREQ_GMI_CREDIT_STALL[6] TCC_EA_RDREQ[7] TCC_EA_RDREQ_32B[7] TCC_EA_RDREQ_DRAM_CREDIT_STALL[7] TCC_EA_RDREQ_GMI_CREDIT_STALL[7] TCC_EA_RDREQ[8] TCC_EA_RDREQ_32B[8] TCC_EA_RDREQ_DRAM_CREDIT_STALL[8] TCC_EA_RDREQ_GMI_CREDIT_STALL[8] TCC_EA_RDREQ[9] TCC_EA_RDREQ_32B[9] TCC_EA_RDREQ_DRAM_CREDIT_STALL[9] TCC_EA_RDREQ_GMI_CREDIT_STALL[9] TCC_EA_RDREQ[10] TCC_EA_RDREQ_32B[10] TCC_EA_RDREQ_DRAM_CREDIT_STALL[10] TCC_EA_RDREQ_GMI_CREDIT_STALL[10] TCC_EA_RDREQ[11] TCC_EA_RDREQ_32B[11] TCC_EA_RDREQ_DRAM_CREDIT_STALL[11] TCC_EA_RDREQ_GMI_CREDIT_STALL[11] TCC_EA_RDREQ[12] TCC_EA_RDREQ_32B[12] TCC_EA_RDREQ_DRAM_CREDIT_STALL[12] TCC_EA_RDREQ_GMI_CREDIT_STALL[12] TCC_EA_RDREQ[13] TCC_EA_RDREQ_32B[13] TCC_EA_RDREQ_DRAM_CREDIT_STALL[13] TCC_EA_RDREQ_GMI_CREDIT_STALL[13] TCC_EA_RDREQ[14] TCC_EA_RDREQ_32B[14] TCC_EA_RDREQ_DRAM_CREDIT_STALL[14] TCC_EA_RDREQ_GMI_CREDIT_STALL[14] TCC_EA_RDREQ[15] TCC_EA_RDREQ_32B[15] TCC_EA_RDREQ_DRAM_CREDIT_STALL[15] TCC_EA_RDREQ_GMI_CREDIT_STALL[15] TCC_EA_RDREQ[16] TCC_EA_RDREQ_32B[16] TCC_EA_RDREQ_DRAM_CREDIT_STALL[16] TCC_EA_RDREQ_GMI_CREDIT_STALL[16] TCC_EA_RDREQ[17] TCC_EA_RDREQ_32B[17] TCC_EA_RDREQ_DRAM_CREDIT_STALL[17] TCC_EA_RDREQ_GMI_CREDIT_STALL[17] TCC_EA_RDREQ[18] TCC_EA_RDREQ_32B[18] TCC_EA_RDREQ_DRAM_CREDIT_STALL[18] TCC_EA_RDREQ_GMI_CREDIT_STALL[18] TCC_EA_RDREQ[19] TCC_EA_RDREQ_32B[19] TCC_EA_RDREQ_DRAM_CREDIT_STALL[19] TCC_EA_RDREQ_GMI_CREDIT_STALL[19] TCC_EA_RDREQ[20] TCC_EA_RDREQ_32B[20] TCC_EA_RDREQ_DRAM_CREDIT_STALL[20] TCC_EA_RDREQ_GMI_CREDIT_STALL[20] TCC_EA_RDREQ[21] TCC_EA_RDREQ_32B[21] TCC_EA_RDREQ_DRAM_CREDIT_STALL[21] TCC_EA_RDREQ_GMI_CREDIT_STALL[21] TCC_EA_RDREQ[22] TCC_EA_RDREQ_32B[22] TCC_EA_RDREQ_DRAM_CREDIT_STALL[22] TCC_EA_RDREQ_GMI_CREDIT_STALL[22] TCC_EA_RDREQ[23] TCC_EA_RDREQ_32B[23] TCC_EA_RDREQ_DRAM_CREDIT_STALL[23] TCC_EA_RDREQ_GMI_CREDIT_STALL[23] TCC_EA_RDREQ[24] TCC_EA_RDREQ_32B[24] TCC_EA_RDREQ_DRAM_CREDIT_STALL[24] TCC_EA_RDREQ_GMI_CREDIT_STALL[24] TCC_EA_RDREQ[25] TCC_EA_RDREQ_32B[25] TCC_EA_RDREQ_DRAM_CREDIT_STALL[25] TCC_EA_RDREQ_GMI_CREDIT_STALL[25] TCC_EA_RDREQ[26] TCC_EA_RDREQ_32B[26] TCC_EA_RDREQ_DRAM_CREDIT_STALL[26] TCC_EA_RDREQ_GMI_CREDIT_STALL[26] TCC_EA_RDREQ[27] TCC_EA_RDREQ_32B[27] TCC_EA_RDREQ_DRAM_CREDIT_STALL[27] TCC_EA_RDREQ_GMI_CREDIT_STALL[27] TCC_EA_RDREQ[28] TCC_EA_RDREQ_32B[28] TCC_EA_RDREQ_DRAM_CREDIT_STALL[28] TCC_EA_RDREQ_GMI_CREDIT_STALL[28] TCC_EA_RDREQ[29] TCC_EA_RDREQ_32B[29] TCC_EA_RDREQ_DRAM_CREDIT_STALL[29] TCC_EA_RDREQ_GMI_CREDIT_STALL[29] TCC_EA_RDREQ[30] TCC_EA_RDREQ_32B[30] TCC_EA_RDREQ_DRAM_CREDIT_STALL[30] TCC_EA_RDREQ_GMI_CREDIT_STALL[30] TCC_EA_RDREQ[31] TCC_EA_RDREQ_32B[31] TCC_EA_RDREQ_DRAM_CREDIT_STALL[31] TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel/MI200/perfmon/pmc_perf_15.txt b/tests/workloads/kernel/MI200/perfmon/pmc_perf_15.txt new file mode 100644 index 0000000000..77ad088669 --- /dev/null +++ b/tests/workloads/kernel/MI200/perfmon/pmc_perf_15.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ[0] TCC_EA_WRREQ_64B[0] TCC_EA_RDREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_LEVEL[1] TCC_EA_WRREQ[1] TCC_EA_WRREQ_64B[1] TCC_EA_RDREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_LEVEL[2] TCC_EA_WRREQ[2] TCC_EA_WRREQ_64B[2] TCC_EA_RDREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_LEVEL[3] TCC_EA_WRREQ[3] TCC_EA_WRREQ_64B[3] TCC_EA_RDREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_LEVEL[4] TCC_EA_WRREQ[4] TCC_EA_WRREQ_64B[4] TCC_EA_RDREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_LEVEL[5] TCC_EA_WRREQ[5] TCC_EA_WRREQ_64B[5] TCC_EA_RDREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_LEVEL[6] TCC_EA_WRREQ[6] TCC_EA_WRREQ_64B[6] TCC_EA_RDREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_LEVEL[7] TCC_EA_WRREQ[7] TCC_EA_WRREQ_64B[7] TCC_EA_RDREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_LEVEL[8] TCC_EA_WRREQ[8] TCC_EA_WRREQ_64B[8] TCC_EA_RDREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_LEVEL[9] TCC_EA_WRREQ[9] TCC_EA_WRREQ_64B[9] TCC_EA_RDREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_LEVEL[10] TCC_EA_WRREQ[10] TCC_EA_WRREQ_64B[10] TCC_EA_RDREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_LEVEL[11] TCC_EA_WRREQ[11] TCC_EA_WRREQ_64B[11] TCC_EA_RDREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_LEVEL[12] TCC_EA_WRREQ[12] TCC_EA_WRREQ_64B[12] TCC_EA_RDREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_LEVEL[13] TCC_EA_WRREQ[13] TCC_EA_WRREQ_64B[13] TCC_EA_RDREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_LEVEL[14] TCC_EA_WRREQ[14] TCC_EA_WRREQ_64B[14] TCC_EA_RDREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_LEVEL[15] TCC_EA_WRREQ[15] TCC_EA_WRREQ_64B[15] TCC_EA_RDREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_LEVEL[16] TCC_EA_WRREQ[16] TCC_EA_WRREQ_64B[16] TCC_EA_RDREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_LEVEL[17] TCC_EA_WRREQ[17] TCC_EA_WRREQ_64B[17] TCC_EA_RDREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_LEVEL[18] TCC_EA_WRREQ[18] TCC_EA_WRREQ_64B[18] TCC_EA_RDREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_LEVEL[19] TCC_EA_WRREQ[19] TCC_EA_WRREQ_64B[19] TCC_EA_RDREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_LEVEL[20] TCC_EA_WRREQ[20] TCC_EA_WRREQ_64B[20] TCC_EA_RDREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_LEVEL[21] TCC_EA_WRREQ[21] TCC_EA_WRREQ_64B[21] TCC_EA_RDREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_LEVEL[22] TCC_EA_WRREQ[22] TCC_EA_WRREQ_64B[22] TCC_EA_RDREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_LEVEL[23] TCC_EA_WRREQ[23] TCC_EA_WRREQ_64B[23] TCC_EA_RDREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_LEVEL[24] TCC_EA_WRREQ[24] TCC_EA_WRREQ_64B[24] TCC_EA_RDREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_LEVEL[25] TCC_EA_WRREQ[25] TCC_EA_WRREQ_64B[25] TCC_EA_RDREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_LEVEL[26] TCC_EA_WRREQ[26] TCC_EA_WRREQ_64B[26] TCC_EA_RDREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_LEVEL[27] TCC_EA_WRREQ[27] TCC_EA_WRREQ_64B[27] TCC_EA_RDREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_LEVEL[28] TCC_EA_WRREQ[28] TCC_EA_WRREQ_64B[28] TCC_EA_RDREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_LEVEL[29] TCC_EA_WRREQ[29] TCC_EA_WRREQ_64B[29] TCC_EA_RDREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_LEVEL[30] TCC_EA_WRREQ[30] TCC_EA_WRREQ_64B[30] TCC_EA_RDREQ_IO_CREDIT_STALL[31] TCC_EA_RDREQ_LEVEL[31] TCC_EA_WRREQ[31] TCC_EA_WRREQ_64B[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel/MI200/perfmon/pmc_perf_16.txt b/tests/workloads/kernel/MI200/perfmon/pmc_perf_16.txt new file mode 100644 index 0000000000..d0628bb948 --- /dev/null +++ b/tests/workloads/kernel/MI200/perfmon/pmc_perf_16.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_WRREQ_IO_CREDIT_STALL[0] TCC_EA_WRREQ_LEVEL[0] TCC_EA_WRREQ_DRAM_CREDIT_STALL[1] TCC_EA_WRREQ_GMI_CREDIT_STALL[1] TCC_EA_WRREQ_IO_CREDIT_STALL[1] TCC_EA_WRREQ_LEVEL[1] TCC_EA_WRREQ_DRAM_CREDIT_STALL[2] TCC_EA_WRREQ_GMI_CREDIT_STALL[2] TCC_EA_WRREQ_IO_CREDIT_STALL[2] TCC_EA_WRREQ_LEVEL[2] TCC_EA_WRREQ_DRAM_CREDIT_STALL[3] TCC_EA_WRREQ_GMI_CREDIT_STALL[3] TCC_EA_WRREQ_IO_CREDIT_STALL[3] TCC_EA_WRREQ_LEVEL[3] TCC_EA_WRREQ_DRAM_CREDIT_STALL[4] TCC_EA_WRREQ_GMI_CREDIT_STALL[4] TCC_EA_WRREQ_IO_CREDIT_STALL[4] TCC_EA_WRREQ_LEVEL[4] TCC_EA_WRREQ_DRAM_CREDIT_STALL[5] TCC_EA_WRREQ_GMI_CREDIT_STALL[5] TCC_EA_WRREQ_IO_CREDIT_STALL[5] TCC_EA_WRREQ_LEVEL[5] TCC_EA_WRREQ_DRAM_CREDIT_STALL[6] TCC_EA_WRREQ_GMI_CREDIT_STALL[6] TCC_EA_WRREQ_IO_CREDIT_STALL[6] TCC_EA_WRREQ_LEVEL[6] TCC_EA_WRREQ_DRAM_CREDIT_STALL[7] TCC_EA_WRREQ_GMI_CREDIT_STALL[7] TCC_EA_WRREQ_IO_CREDIT_STALL[7] TCC_EA_WRREQ_LEVEL[7] TCC_EA_WRREQ_DRAM_CREDIT_STALL[8] TCC_EA_WRREQ_GMI_CREDIT_STALL[8] TCC_EA_WRREQ_IO_CREDIT_STALL[8] TCC_EA_WRREQ_LEVEL[8] TCC_EA_WRREQ_DRAM_CREDIT_STALL[9] TCC_EA_WRREQ_GMI_CREDIT_STALL[9] TCC_EA_WRREQ_IO_CREDIT_STALL[9] TCC_EA_WRREQ_LEVEL[9] TCC_EA_WRREQ_DRAM_CREDIT_STALL[10] TCC_EA_WRREQ_GMI_CREDIT_STALL[10] TCC_EA_WRREQ_IO_CREDIT_STALL[10] TCC_EA_WRREQ_LEVEL[10] TCC_EA_WRREQ_DRAM_CREDIT_STALL[11] TCC_EA_WRREQ_GMI_CREDIT_STALL[11] TCC_EA_WRREQ_IO_CREDIT_STALL[11] TCC_EA_WRREQ_LEVEL[11] TCC_EA_WRREQ_DRAM_CREDIT_STALL[12] TCC_EA_WRREQ_GMI_CREDIT_STALL[12] TCC_EA_WRREQ_IO_CREDIT_STALL[12] TCC_EA_WRREQ_LEVEL[12] TCC_EA_WRREQ_DRAM_CREDIT_STALL[13] TCC_EA_WRREQ_GMI_CREDIT_STALL[13] TCC_EA_WRREQ_IO_CREDIT_STALL[13] TCC_EA_WRREQ_LEVEL[13] TCC_EA_WRREQ_DRAM_CREDIT_STALL[14] TCC_EA_WRREQ_GMI_CREDIT_STALL[14] TCC_EA_WRREQ_IO_CREDIT_STALL[14] TCC_EA_WRREQ_LEVEL[14] TCC_EA_WRREQ_DRAM_CREDIT_STALL[15] TCC_EA_WRREQ_GMI_CREDIT_STALL[15] TCC_EA_WRREQ_IO_CREDIT_STALL[15] TCC_EA_WRREQ_LEVEL[15] TCC_EA_WRREQ_DRAM_CREDIT_STALL[16] TCC_EA_WRREQ_GMI_CREDIT_STALL[16] TCC_EA_WRREQ_IO_CREDIT_STALL[16] TCC_EA_WRREQ_LEVEL[16] TCC_EA_WRREQ_DRAM_CREDIT_STALL[17] TCC_EA_WRREQ_GMI_CREDIT_STALL[17] TCC_EA_WRREQ_IO_CREDIT_STALL[17] TCC_EA_WRREQ_LEVEL[17] TCC_EA_WRREQ_DRAM_CREDIT_STALL[18] TCC_EA_WRREQ_GMI_CREDIT_STALL[18] TCC_EA_WRREQ_IO_CREDIT_STALL[18] TCC_EA_WRREQ_LEVEL[18] TCC_EA_WRREQ_DRAM_CREDIT_STALL[19] TCC_EA_WRREQ_GMI_CREDIT_STALL[19] TCC_EA_WRREQ_IO_CREDIT_STALL[19] TCC_EA_WRREQ_LEVEL[19] TCC_EA_WRREQ_DRAM_CREDIT_STALL[20] TCC_EA_WRREQ_GMI_CREDIT_STALL[20] TCC_EA_WRREQ_IO_CREDIT_STALL[20] TCC_EA_WRREQ_LEVEL[20] TCC_EA_WRREQ_DRAM_CREDIT_STALL[21] TCC_EA_WRREQ_GMI_CREDIT_STALL[21] TCC_EA_WRREQ_IO_CREDIT_STALL[21] TCC_EA_WRREQ_LEVEL[21] TCC_EA_WRREQ_DRAM_CREDIT_STALL[22] TCC_EA_WRREQ_GMI_CREDIT_STALL[22] TCC_EA_WRREQ_IO_CREDIT_STALL[22] TCC_EA_WRREQ_LEVEL[22] TCC_EA_WRREQ_DRAM_CREDIT_STALL[23] TCC_EA_WRREQ_GMI_CREDIT_STALL[23] TCC_EA_WRREQ_IO_CREDIT_STALL[23] TCC_EA_WRREQ_LEVEL[23] TCC_EA_WRREQ_DRAM_CREDIT_STALL[24] TCC_EA_WRREQ_GMI_CREDIT_STALL[24] TCC_EA_WRREQ_IO_CREDIT_STALL[24] TCC_EA_WRREQ_LEVEL[24] TCC_EA_WRREQ_DRAM_CREDIT_STALL[25] TCC_EA_WRREQ_GMI_CREDIT_STALL[25] TCC_EA_WRREQ_IO_CREDIT_STALL[25] TCC_EA_WRREQ_LEVEL[25] TCC_EA_WRREQ_DRAM_CREDIT_STALL[26] TCC_EA_WRREQ_GMI_CREDIT_STALL[26] TCC_EA_WRREQ_IO_CREDIT_STALL[26] TCC_EA_WRREQ_LEVEL[26] TCC_EA_WRREQ_DRAM_CREDIT_STALL[27] TCC_EA_WRREQ_GMI_CREDIT_STALL[27] TCC_EA_WRREQ_IO_CREDIT_STALL[27] TCC_EA_WRREQ_LEVEL[27] TCC_EA_WRREQ_DRAM_CREDIT_STALL[28] TCC_EA_WRREQ_GMI_CREDIT_STALL[28] TCC_EA_WRREQ_IO_CREDIT_STALL[28] TCC_EA_WRREQ_LEVEL[28] TCC_EA_WRREQ_DRAM_CREDIT_STALL[29] TCC_EA_WRREQ_GMI_CREDIT_STALL[29] TCC_EA_WRREQ_IO_CREDIT_STALL[29] TCC_EA_WRREQ_LEVEL[29] TCC_EA_WRREQ_DRAM_CREDIT_STALL[30] TCC_EA_WRREQ_GMI_CREDIT_STALL[30] TCC_EA_WRREQ_IO_CREDIT_STALL[30] TCC_EA_WRREQ_LEVEL[30] TCC_EA_WRREQ_DRAM_CREDIT_STALL[31] TCC_EA_WRREQ_GMI_CREDIT_STALL[31] TCC_EA_WRREQ_IO_CREDIT_STALL[31] TCC_EA_WRREQ_LEVEL[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel/MI200/perfmon/pmc_perf_17.txt b/tests/workloads/kernel/MI200/perfmon/pmc_perf_17.txt new file mode 100644 index 0000000000..343869c5f1 --- /dev/null +++ b/tests/workloads/kernel/MI200/perfmon/pmc_perf_17.txt @@ -0,0 +1,5 @@ +pmc: TCC_HIT[0] TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_HIT[1] TCC_MISS[1] TCC_READ[1] TCC_REQ[1] TCC_HIT[2] TCC_MISS[2] TCC_READ[2] TCC_REQ[2] TCC_HIT[3] TCC_MISS[3] TCC_READ[3] TCC_REQ[3] TCC_HIT[4] TCC_MISS[4] TCC_READ[4] TCC_REQ[4] TCC_HIT[5] TCC_MISS[5] TCC_READ[5] TCC_REQ[5] TCC_HIT[6] TCC_MISS[6] TCC_READ[6] TCC_REQ[6] TCC_HIT[7] TCC_MISS[7] TCC_READ[7] TCC_REQ[7] TCC_HIT[8] TCC_MISS[8] TCC_READ[8] TCC_REQ[8] TCC_HIT[9] TCC_MISS[9] TCC_READ[9] TCC_REQ[9] TCC_HIT[10] TCC_MISS[10] TCC_READ[10] TCC_REQ[10] TCC_HIT[11] TCC_MISS[11] TCC_READ[11] TCC_REQ[11] TCC_HIT[12] TCC_MISS[12] TCC_READ[12] TCC_REQ[12] TCC_HIT[13] TCC_MISS[13] TCC_READ[13] TCC_REQ[13] TCC_HIT[14] TCC_MISS[14] TCC_READ[14] TCC_REQ[14] TCC_HIT[15] TCC_MISS[15] TCC_READ[15] TCC_REQ[15] TCC_HIT[16] TCC_MISS[16] TCC_READ[16] TCC_REQ[16] TCC_HIT[17] TCC_MISS[17] TCC_READ[17] TCC_REQ[17] TCC_HIT[18] TCC_MISS[18] TCC_READ[18] TCC_REQ[18] TCC_HIT[19] TCC_MISS[19] TCC_READ[19] TCC_REQ[19] TCC_HIT[20] TCC_MISS[20] TCC_READ[20] TCC_REQ[20] TCC_HIT[21] TCC_MISS[21] TCC_READ[21] TCC_REQ[21] TCC_HIT[22] TCC_MISS[22] TCC_READ[22] TCC_REQ[22] TCC_HIT[23] TCC_MISS[23] TCC_READ[23] TCC_REQ[23] TCC_HIT[24] TCC_MISS[24] TCC_READ[24] TCC_REQ[24] TCC_HIT[25] TCC_MISS[25] TCC_READ[25] TCC_REQ[25] TCC_HIT[26] TCC_MISS[26] TCC_READ[26] TCC_REQ[26] TCC_HIT[27] TCC_MISS[27] TCC_READ[27] TCC_REQ[27] TCC_HIT[28] TCC_MISS[28] TCC_READ[28] TCC_REQ[28] TCC_HIT[29] TCC_MISS[29] TCC_READ[29] TCC_REQ[29] TCC_HIT[30] TCC_MISS[30] TCC_READ[30] TCC_REQ[30] TCC_HIT[31] TCC_MISS[31] TCC_READ[31] TCC_REQ[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel/MI200/perfmon/pmc_perf_18.txt b/tests/workloads/kernel/MI200/perfmon/pmc_perf_18.txt new file mode 100644 index 0000000000..a74cefd281 --- /dev/null +++ b/tests/workloads/kernel/MI200/perfmon/pmc_perf_18.txt @@ -0,0 +1,5 @@ +pmc: TCC_RW_REQ[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_RW_REQ[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_WRITE[1] TCC_RW_REQ[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_WRITE[2] TCC_RW_REQ[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_WRITE[3] TCC_RW_REQ[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_WRITE[4] TCC_RW_REQ[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_WRITE[5] TCC_RW_REQ[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_WRITE[6] TCC_RW_REQ[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_WRITE[7] TCC_RW_REQ[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_WRITE[8] TCC_RW_REQ[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_WRITE[9] TCC_RW_REQ[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_WRITE[10] TCC_RW_REQ[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_WRITE[11] TCC_RW_REQ[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_WRITE[12] TCC_RW_REQ[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_WRITE[13] TCC_RW_REQ[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_WRITE[14] TCC_RW_REQ[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_WRITE[15] TCC_RW_REQ[16] TCC_TOO_MANY_EA_WRREQS_STALL[16] TCC_WRITE[16] TCC_RW_REQ[17] TCC_TOO_MANY_EA_WRREQS_STALL[17] TCC_WRITE[17] TCC_RW_REQ[18] TCC_TOO_MANY_EA_WRREQS_STALL[18] TCC_WRITE[18] TCC_RW_REQ[19] TCC_TOO_MANY_EA_WRREQS_STALL[19] TCC_WRITE[19] TCC_RW_REQ[20] TCC_TOO_MANY_EA_WRREQS_STALL[20] TCC_WRITE[20] TCC_RW_REQ[21] TCC_TOO_MANY_EA_WRREQS_STALL[21] TCC_WRITE[21] TCC_RW_REQ[22] TCC_TOO_MANY_EA_WRREQS_STALL[22] TCC_WRITE[22] TCC_RW_REQ[23] TCC_TOO_MANY_EA_WRREQS_STALL[23] TCC_WRITE[23] TCC_RW_REQ[24] TCC_TOO_MANY_EA_WRREQS_STALL[24] TCC_WRITE[24] TCC_RW_REQ[25] TCC_TOO_MANY_EA_WRREQS_STALL[25] TCC_WRITE[25] TCC_RW_REQ[26] TCC_TOO_MANY_EA_WRREQS_STALL[26] TCC_WRITE[26] TCC_RW_REQ[27] TCC_TOO_MANY_EA_WRREQS_STALL[27] TCC_WRITE[27] TCC_RW_REQ[28] TCC_TOO_MANY_EA_WRREQS_STALL[28] TCC_WRITE[28] TCC_RW_REQ[29] TCC_TOO_MANY_EA_WRREQS_STALL[29] TCC_WRITE[29] TCC_RW_REQ[30] TCC_TOO_MANY_EA_WRREQS_STALL[30] TCC_WRITE[30] TCC_RW_REQ[31] TCC_TOO_MANY_EA_WRREQS_STALL[31] TCC_WRITE[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel/MI200/perfmon/pmc_perf_2.txt b/tests/workloads/kernel/MI200/perfmon/pmc_perf_2.txt new file mode 100644 index 0000000000..70b69f8928 --- /dev/null +++ b/tests/workloads/kernel/MI200/perfmon/pmc_perf_2.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_MUL_F32 SQ_INSTS_VALU_FMA_F32 SQ_INSTS_VALU_TRANS_F32 SQ_INSTS_VALU_ADD_F64 SQ_INSTS_VALU_MUL_F64 SQ_INSTS_VALU_FMA_F64 SQ_INSTS_VALU_TRANS_F64 SQ_INSTS_VALU_INT32 TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum TA_BUFFER_ATOMIC_WAVEFRONTS_sum TA_BUFFER_TOTAL_CYCLES_sum TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel/MI200/perfmon/pmc_perf_3.txt b/tests/workloads/kernel/MI200/perfmon/pmc_perf_3.txt new file mode 100644 index 0000000000..e47f8e33c9 --- /dev/null +++ b/tests/workloads/kernel/MI200/perfmon/pmc_perf_3.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_INT64 SQ_INSTS_SMEM SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum TD_COALESCABLE_WAVEFRONT_sum SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE CPF_CMP_UTCL1_STALL_ON_TRANSLATION TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel/MI200/perfmon/pmc_perf_4.txt b/tests/workloads/kernel/MI200/perfmon/pmc_perf_4.txt new file mode 100644 index 0000000000..2d96f365a9 --- /dev/null +++ b/tests/workloads/kernel/MI200/perfmon/pmc_perf_4.txt @@ -0,0 +1,5 @@ +pmc: SQ_WAVE_CYCLES SQ_WAIT_ANY SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_BUSY_CU_CYCLES SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE TCC_EA_WRREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WR_UNCACHED_32B_sum TCC_EA_WRREQ_DRAM_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel/MI200/perfmon/pmc_perf_5.txt b/tests/workloads/kernel/MI200/perfmon/pmc_perf_5.txt new file mode 100644 index 0000000000..e50beed390 --- /dev/null +++ b/tests/workloads/kernel/MI200/perfmon/pmc_perf_5.txt @@ -0,0 +1,5 @@ +pmc: SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU TCP_TCP_LATENCY_sum TCP_TCC_READ_REQ_LATENCY_sum TCP_TCC_WRITE_REQ_LATENCY_sum TCP_TCC_READ_REQ_sum TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN CPC_ME1_DC0_SPI_BUSY TCC_EA_WRREQ_STALL_sum TCC_EA_RDREQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RD_UNCACHED_32B_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel/MI200/perfmon/pmc_perf_6.txt b/tests/workloads/kernel/MI200/perfmon/pmc_perf_6.txt new file mode 100644 index 0000000000..15a2277c1b --- /dev/null +++ b/tests/workloads/kernel/MI200/perfmon/pmc_perf_6.txt @@ -0,0 +1,5 @@ +pmc: SQ_THREAD_CYCLES_VALU SQ_IFETCH SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TCP_TCC_NC_READ_REQ_sum TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN TCC_EA_RDREQ_DRAM_sum TCC_TAG_STALL_sum TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel/MI200/perfmon/pmc_perf_7.txt b/tests/workloads/kernel/MI200/perfmon/pmc_perf_7.txt new file mode 100644 index 0000000000..b42ce91618 --- /dev/null +++ b/tests/workloads/kernel/MI200/perfmon/pmc_perf_7.txt @@ -0,0 +1,5 @@ +pmc: SQ_WAVES_LT_32 SQ_WAVES_LT_16 SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TCP_TCC_UC_WRITE_REQ_sum TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR TCC_NORMAL_EVICT_sum TCC_ALL_TC_OP_INV_EVICT_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA_ATOMIC_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel/MI200/perfmon/pmc_perf_8.txt b/tests/workloads/kernel/MI200/perfmon/pmc_perf_8.txt new file mode 100644 index 0000000000..21d4c7a998 --- /dev/null +++ b/tests/workloads/kernel/MI200/perfmon/pmc_perf_8.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM_NORM SQ_INSTS_MFMA SQ_INSTS_VALU_MFMA_I8 SQ_INSTS_VALU_MFMA_F16 SQ_INSTS_VALU_MFMA_BF16 SQ_INSTS_VALU_MFMA_F32 SQ_INSTS_VALU_MFMA_F64 SQ_VALU_MFMA_BUSY_CYCLES TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TCP_TCC_CC_ATOMIC_REQ_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN TCC_EA_RDREQ_LEVEL_sum TCC_EA_WRREQ_LEVEL_sum TCC_EA_ATOMIC_LEVEL_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel/MI200/perfmon/pmc_perf_9.txt b/tests/workloads/kernel/MI200/perfmon/pmc_perf_9.txt new file mode 100644 index 0000000000..9ffe5778c3 --- /dev/null +++ b/tests/workloads/kernel/MI200/perfmon/pmc_perf_9.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_FLAT_LDS_ONLY SQ_INSTS_VALU_MFMA_MOPS_I8 SQ_INSTS_VALU_MFMA_MOPS_F16 SQ_INSTS_VALU_MFMA_MOPS_BF16 SQ_INSTS_VALU_MFMA_MOPS_F32 SQ_INSTS_VALU_MFMA_MOPS_F64 SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum TCP_PENDING_STALL_CYCLES_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel/MI200/perfmon/timestamps.txt b/tests/workloads/kernel/MI200/perfmon/timestamps.txt new file mode 100644 index 0000000000..676cca1b80 --- /dev/null +++ b/tests/workloads/kernel/MI200/perfmon/timestamps.txt @@ -0,0 +1,5 @@ +pmc: + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_inv_int/MI100/sysinfo.csv b/tests/workloads/kernel_inv_int/MI100/sysinfo.csv index 66cbc54826..b5ef0b1e21 100644 --- a/tests/workloads/kernel_inv_int/MI100/sysinfo.csv +++ b/tests/workloads/kernel_inv_int/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -kernel_inv_int,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Fri Mar 1 16:44:00 2024 (CST),1,t006-003.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651240,,5.7.1-98,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +kernel_inv_int,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 07 Mar 2024 01:06:32 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/kernel_inv_int/MI200/SQ_IFETCH_LEVEL.csv b/tests/workloads/kernel_inv_int/MI200/SQ_IFETCH_LEVEL.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/kernel_inv_int/MI200/SQ_IFETCH_LEVEL.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/kernel_inv_int/MI200/SQ_INST_LEVEL_LDS.csv b/tests/workloads/kernel_inv_int/MI200/SQ_INST_LEVEL_LDS.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/kernel_inv_int/MI200/SQ_INST_LEVEL_LDS.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/kernel_inv_int/MI200/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/kernel_inv_int/MI200/SQ_INST_LEVEL_SMEM.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/kernel_inv_int/MI200/SQ_INST_LEVEL_SMEM.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/kernel_inv_int/MI200/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/kernel_inv_int/MI200/SQ_INST_LEVEL_VMEM.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/kernel_inv_int/MI200/SQ_INST_LEVEL_VMEM.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/kernel_inv_int/MI200/SQ_LEVEL_WAVES.csv b/tests/workloads/kernel_inv_int/MI200/SQ_LEVEL_WAVES.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/kernel_inv_int/MI200/SQ_LEVEL_WAVES.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/kernel_inv_int/MI200/perfmon/SQ_IFETCH_LEVEL.txt b/tests/workloads/kernel_inv_int/MI200/perfmon/SQ_IFETCH_LEVEL.txt new file mode 100644 index 0000000000..a55111636d --- /dev/null +++ b/tests/workloads/kernel_inv_int/MI200/perfmon/SQ_IFETCH_LEVEL.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: 42 diff --git a/tests/workloads/kernel_inv_int/MI200/perfmon/SQ_INST_LEVEL_LDS.txt b/tests/workloads/kernel_inv_int/MI200/perfmon/SQ_INST_LEVEL_LDS.txt new file mode 100644 index 0000000000..77c4c17fdb --- /dev/null +++ b/tests/workloads/kernel_inv_int/MI200/perfmon/SQ_INST_LEVEL_LDS.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: 42 diff --git a/tests/workloads/kernel_inv_int/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt b/tests/workloads/kernel_inv_int/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt new file mode 100644 index 0000000000..75cf851833 --- /dev/null +++ b/tests/workloads/kernel_inv_int/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: 42 diff --git a/tests/workloads/kernel_inv_int/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt b/tests/workloads/kernel_inv_int/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt new file mode 100644 index 0000000000..6aec712f85 --- /dev/null +++ b/tests/workloads/kernel_inv_int/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: 42 diff --git a/tests/workloads/kernel_inv_int/MI200/perfmon/SQ_LEVEL_WAVES.txt b/tests/workloads/kernel_inv_int/MI200/perfmon/SQ_LEVEL_WAVES.txt new file mode 100644 index 0000000000..c22a1b77ca --- /dev/null +++ b/tests/workloads/kernel_inv_int/MI200/perfmon/SQ_LEVEL_WAVES.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: 42 diff --git a/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_0.txt b/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_0.txt new file mode 100644 index 0000000000..abc4f1cdb2 --- /dev/null +++ b/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_0.txt @@ -0,0 +1,5 @@ +pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES SQ_INSTS_VALU_CVT SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU GRBM_COUNT GRBM_GUI_ACTIVE TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum TA_TA_BUSY_sum TA_BUFFER_WAVEFRONTS_sum TD_TD_BUSY_sum TD_TC_STALL_sum SPI_CSN_WINDOW_VALID SPI_CSN_BUSY CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum + +gpu: +range: +kernel: 42 diff --git a/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_1.txt b/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_1.txt new file mode 100644 index 0000000000..87464193cf --- /dev/null +++ b/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_1.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VSKIPPED SQ_INSTS SQ_INSTS_VALU SQ_INSTS_VALU_ADD_F16 SQ_INSTS_VALU_MUL_F16 SQ_INSTS_VALU_FMA_F16 SQ_INSTS_VALU_TRANS_F16 SQ_INSTS_VALU_ADD_F32 GRBM_SPI_BUSY TCP_READ_TAGCONFLICT_STALL_CYCLES_sum TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum TCP_TA_TCP_STATE_READ_sum TA_BUFFER_READ_WAVEFRONTS_sum TA_BUFFER_WRITE_WAVEFRONTS_sum TD_SPI_STALL_sum TD_LOAD_WAVEFRONT_sum SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum + +gpu: +range: +kernel: 42 diff --git a/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_10.txt b/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_10.txt new file mode 100644 index 0000000000..714303765d --- /dev/null +++ b/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_10.txt @@ -0,0 +1,5 @@ +pmc: SQC_TC_DATA_WRITE_REQ SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES + +gpu: +range: +kernel: 42 diff --git a/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_11.txt b/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_11.txt new file mode 100644 index 0000000000..c387848f48 --- /dev/null +++ b/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_11.txt @@ -0,0 +1,5 @@ +pmc: SQC_ICACHE_MISSES_DUPLICATE SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE + +gpu: +range: +kernel: 42 diff --git a/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_12.txt b/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_12.txt new file mode 100644 index 0000000000..0929bda605 --- /dev/null +++ b/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_12.txt @@ -0,0 +1,5 @@ +pmc: SQC_DCACHE_REQ_READ_1 SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 + +gpu: +range: +kernel: 42 diff --git a/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_13.txt b/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_13.txt new file mode 100644 index 0000000000..e1f9c02c69 --- /dev/null +++ b/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_13.txt @@ -0,0 +1,5 @@ +pmc: TCC_ATOMIC[0] TCC_CYCLE[0] TCC_EA_ATOMIC[0] TCC_EA_ATOMIC_LEVEL[0] TCC_ATOMIC[1] TCC_CYCLE[1] TCC_EA_ATOMIC[1] TCC_EA_ATOMIC_LEVEL[1] TCC_ATOMIC[2] TCC_CYCLE[2] TCC_EA_ATOMIC[2] TCC_EA_ATOMIC_LEVEL[2] TCC_ATOMIC[3] TCC_CYCLE[3] TCC_EA_ATOMIC[3] TCC_EA_ATOMIC_LEVEL[3] TCC_ATOMIC[4] TCC_CYCLE[4] TCC_EA_ATOMIC[4] TCC_EA_ATOMIC_LEVEL[4] TCC_ATOMIC[5] TCC_CYCLE[5] TCC_EA_ATOMIC[5] TCC_EA_ATOMIC_LEVEL[5] TCC_ATOMIC[6] TCC_CYCLE[6] TCC_EA_ATOMIC[6] TCC_EA_ATOMIC_LEVEL[6] TCC_ATOMIC[7] TCC_CYCLE[7] TCC_EA_ATOMIC[7] TCC_EA_ATOMIC_LEVEL[7] TCC_ATOMIC[8] TCC_CYCLE[8] TCC_EA_ATOMIC[8] TCC_EA_ATOMIC_LEVEL[8] TCC_ATOMIC[9] TCC_CYCLE[9] TCC_EA_ATOMIC[9] TCC_EA_ATOMIC_LEVEL[9] TCC_ATOMIC[10] TCC_CYCLE[10] TCC_EA_ATOMIC[10] TCC_EA_ATOMIC_LEVEL[10] TCC_ATOMIC[11] TCC_CYCLE[11] TCC_EA_ATOMIC[11] TCC_EA_ATOMIC_LEVEL[11] TCC_ATOMIC[12] TCC_CYCLE[12] TCC_EA_ATOMIC[12] TCC_EA_ATOMIC_LEVEL[12] TCC_ATOMIC[13] TCC_CYCLE[13] TCC_EA_ATOMIC[13] TCC_EA_ATOMIC_LEVEL[13] TCC_ATOMIC[14] TCC_CYCLE[14] TCC_EA_ATOMIC[14] TCC_EA_ATOMIC_LEVEL[14] TCC_ATOMIC[15] TCC_CYCLE[15] TCC_EA_ATOMIC[15] TCC_EA_ATOMIC_LEVEL[15] TCC_ATOMIC[16] TCC_CYCLE[16] TCC_EA_ATOMIC[16] TCC_EA_ATOMIC_LEVEL[16] TCC_ATOMIC[17] TCC_CYCLE[17] TCC_EA_ATOMIC[17] TCC_EA_ATOMIC_LEVEL[17] TCC_ATOMIC[18] TCC_CYCLE[18] TCC_EA_ATOMIC[18] TCC_EA_ATOMIC_LEVEL[18] TCC_ATOMIC[19] TCC_CYCLE[19] TCC_EA_ATOMIC[19] TCC_EA_ATOMIC_LEVEL[19] TCC_ATOMIC[20] TCC_CYCLE[20] TCC_EA_ATOMIC[20] TCC_EA_ATOMIC_LEVEL[20] TCC_ATOMIC[21] TCC_CYCLE[21] TCC_EA_ATOMIC[21] TCC_EA_ATOMIC_LEVEL[21] TCC_ATOMIC[22] TCC_CYCLE[22] TCC_EA_ATOMIC[22] TCC_EA_ATOMIC_LEVEL[22] TCC_ATOMIC[23] TCC_CYCLE[23] TCC_EA_ATOMIC[23] TCC_EA_ATOMIC_LEVEL[23] TCC_ATOMIC[24] TCC_CYCLE[24] TCC_EA_ATOMIC[24] TCC_EA_ATOMIC_LEVEL[24] TCC_ATOMIC[25] TCC_CYCLE[25] TCC_EA_ATOMIC[25] TCC_EA_ATOMIC_LEVEL[25] TCC_ATOMIC[26] TCC_CYCLE[26] TCC_EA_ATOMIC[26] TCC_EA_ATOMIC_LEVEL[26] TCC_ATOMIC[27] TCC_CYCLE[27] TCC_EA_ATOMIC[27] TCC_EA_ATOMIC_LEVEL[27] TCC_ATOMIC[28] TCC_CYCLE[28] TCC_EA_ATOMIC[28] TCC_EA_ATOMIC_LEVEL[28] TCC_ATOMIC[29] TCC_CYCLE[29] TCC_EA_ATOMIC[29] TCC_EA_ATOMIC_LEVEL[29] TCC_ATOMIC[30] TCC_CYCLE[30] TCC_EA_ATOMIC[30] TCC_EA_ATOMIC_LEVEL[30] TCC_ATOMIC[31] TCC_CYCLE[31] TCC_EA_ATOMIC[31] TCC_EA_ATOMIC_LEVEL[31] + +gpu: +range: +kernel: 42 diff --git a/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_14.txt b/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_14.txt new file mode 100644 index 0000000000..7785698396 --- /dev/null +++ b/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_14.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_EA_RDREQ_GMI_CREDIT_STALL[0] TCC_EA_RDREQ[1] TCC_EA_RDREQ_32B[1] TCC_EA_RDREQ_DRAM_CREDIT_STALL[1] TCC_EA_RDREQ_GMI_CREDIT_STALL[1] TCC_EA_RDREQ[2] TCC_EA_RDREQ_32B[2] TCC_EA_RDREQ_DRAM_CREDIT_STALL[2] TCC_EA_RDREQ_GMI_CREDIT_STALL[2] TCC_EA_RDREQ[3] TCC_EA_RDREQ_32B[3] TCC_EA_RDREQ_DRAM_CREDIT_STALL[3] TCC_EA_RDREQ_GMI_CREDIT_STALL[3] TCC_EA_RDREQ[4] TCC_EA_RDREQ_32B[4] TCC_EA_RDREQ_DRAM_CREDIT_STALL[4] TCC_EA_RDREQ_GMI_CREDIT_STALL[4] TCC_EA_RDREQ[5] TCC_EA_RDREQ_32B[5] TCC_EA_RDREQ_DRAM_CREDIT_STALL[5] TCC_EA_RDREQ_GMI_CREDIT_STALL[5] TCC_EA_RDREQ[6] TCC_EA_RDREQ_32B[6] TCC_EA_RDREQ_DRAM_CREDIT_STALL[6] TCC_EA_RDREQ_GMI_CREDIT_STALL[6] TCC_EA_RDREQ[7] TCC_EA_RDREQ_32B[7] TCC_EA_RDREQ_DRAM_CREDIT_STALL[7] TCC_EA_RDREQ_GMI_CREDIT_STALL[7] TCC_EA_RDREQ[8] TCC_EA_RDREQ_32B[8] TCC_EA_RDREQ_DRAM_CREDIT_STALL[8] TCC_EA_RDREQ_GMI_CREDIT_STALL[8] TCC_EA_RDREQ[9] TCC_EA_RDREQ_32B[9] TCC_EA_RDREQ_DRAM_CREDIT_STALL[9] TCC_EA_RDREQ_GMI_CREDIT_STALL[9] TCC_EA_RDREQ[10] TCC_EA_RDREQ_32B[10] TCC_EA_RDREQ_DRAM_CREDIT_STALL[10] TCC_EA_RDREQ_GMI_CREDIT_STALL[10] TCC_EA_RDREQ[11] TCC_EA_RDREQ_32B[11] TCC_EA_RDREQ_DRAM_CREDIT_STALL[11] TCC_EA_RDREQ_GMI_CREDIT_STALL[11] TCC_EA_RDREQ[12] TCC_EA_RDREQ_32B[12] TCC_EA_RDREQ_DRAM_CREDIT_STALL[12] TCC_EA_RDREQ_GMI_CREDIT_STALL[12] TCC_EA_RDREQ[13] TCC_EA_RDREQ_32B[13] TCC_EA_RDREQ_DRAM_CREDIT_STALL[13] TCC_EA_RDREQ_GMI_CREDIT_STALL[13] TCC_EA_RDREQ[14] TCC_EA_RDREQ_32B[14] TCC_EA_RDREQ_DRAM_CREDIT_STALL[14] TCC_EA_RDREQ_GMI_CREDIT_STALL[14] TCC_EA_RDREQ[15] TCC_EA_RDREQ_32B[15] TCC_EA_RDREQ_DRAM_CREDIT_STALL[15] TCC_EA_RDREQ_GMI_CREDIT_STALL[15] TCC_EA_RDREQ[16] TCC_EA_RDREQ_32B[16] TCC_EA_RDREQ_DRAM_CREDIT_STALL[16] TCC_EA_RDREQ_GMI_CREDIT_STALL[16] TCC_EA_RDREQ[17] TCC_EA_RDREQ_32B[17] TCC_EA_RDREQ_DRAM_CREDIT_STALL[17] TCC_EA_RDREQ_GMI_CREDIT_STALL[17] TCC_EA_RDREQ[18] TCC_EA_RDREQ_32B[18] TCC_EA_RDREQ_DRAM_CREDIT_STALL[18] TCC_EA_RDREQ_GMI_CREDIT_STALL[18] TCC_EA_RDREQ[19] TCC_EA_RDREQ_32B[19] TCC_EA_RDREQ_DRAM_CREDIT_STALL[19] TCC_EA_RDREQ_GMI_CREDIT_STALL[19] TCC_EA_RDREQ[20] TCC_EA_RDREQ_32B[20] TCC_EA_RDREQ_DRAM_CREDIT_STALL[20] TCC_EA_RDREQ_GMI_CREDIT_STALL[20] TCC_EA_RDREQ[21] TCC_EA_RDREQ_32B[21] TCC_EA_RDREQ_DRAM_CREDIT_STALL[21] TCC_EA_RDREQ_GMI_CREDIT_STALL[21] TCC_EA_RDREQ[22] TCC_EA_RDREQ_32B[22] TCC_EA_RDREQ_DRAM_CREDIT_STALL[22] TCC_EA_RDREQ_GMI_CREDIT_STALL[22] TCC_EA_RDREQ[23] TCC_EA_RDREQ_32B[23] TCC_EA_RDREQ_DRAM_CREDIT_STALL[23] TCC_EA_RDREQ_GMI_CREDIT_STALL[23] TCC_EA_RDREQ[24] TCC_EA_RDREQ_32B[24] TCC_EA_RDREQ_DRAM_CREDIT_STALL[24] TCC_EA_RDREQ_GMI_CREDIT_STALL[24] TCC_EA_RDREQ[25] TCC_EA_RDREQ_32B[25] TCC_EA_RDREQ_DRAM_CREDIT_STALL[25] TCC_EA_RDREQ_GMI_CREDIT_STALL[25] TCC_EA_RDREQ[26] TCC_EA_RDREQ_32B[26] TCC_EA_RDREQ_DRAM_CREDIT_STALL[26] TCC_EA_RDREQ_GMI_CREDIT_STALL[26] TCC_EA_RDREQ[27] TCC_EA_RDREQ_32B[27] TCC_EA_RDREQ_DRAM_CREDIT_STALL[27] TCC_EA_RDREQ_GMI_CREDIT_STALL[27] TCC_EA_RDREQ[28] TCC_EA_RDREQ_32B[28] TCC_EA_RDREQ_DRAM_CREDIT_STALL[28] TCC_EA_RDREQ_GMI_CREDIT_STALL[28] TCC_EA_RDREQ[29] TCC_EA_RDREQ_32B[29] TCC_EA_RDREQ_DRAM_CREDIT_STALL[29] TCC_EA_RDREQ_GMI_CREDIT_STALL[29] TCC_EA_RDREQ[30] TCC_EA_RDREQ_32B[30] TCC_EA_RDREQ_DRAM_CREDIT_STALL[30] TCC_EA_RDREQ_GMI_CREDIT_STALL[30] TCC_EA_RDREQ[31] TCC_EA_RDREQ_32B[31] TCC_EA_RDREQ_DRAM_CREDIT_STALL[31] TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + +gpu: +range: +kernel: 42 diff --git a/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_15.txt b/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_15.txt new file mode 100644 index 0000000000..ea48b43129 --- /dev/null +++ b/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_15.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ[0] TCC_EA_WRREQ_64B[0] TCC_EA_RDREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_LEVEL[1] TCC_EA_WRREQ[1] TCC_EA_WRREQ_64B[1] TCC_EA_RDREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_LEVEL[2] TCC_EA_WRREQ[2] TCC_EA_WRREQ_64B[2] TCC_EA_RDREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_LEVEL[3] TCC_EA_WRREQ[3] TCC_EA_WRREQ_64B[3] TCC_EA_RDREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_LEVEL[4] TCC_EA_WRREQ[4] TCC_EA_WRREQ_64B[4] TCC_EA_RDREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_LEVEL[5] TCC_EA_WRREQ[5] TCC_EA_WRREQ_64B[5] TCC_EA_RDREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_LEVEL[6] TCC_EA_WRREQ[6] TCC_EA_WRREQ_64B[6] TCC_EA_RDREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_LEVEL[7] TCC_EA_WRREQ[7] TCC_EA_WRREQ_64B[7] TCC_EA_RDREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_LEVEL[8] TCC_EA_WRREQ[8] TCC_EA_WRREQ_64B[8] TCC_EA_RDREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_LEVEL[9] TCC_EA_WRREQ[9] TCC_EA_WRREQ_64B[9] TCC_EA_RDREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_LEVEL[10] TCC_EA_WRREQ[10] TCC_EA_WRREQ_64B[10] TCC_EA_RDREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_LEVEL[11] TCC_EA_WRREQ[11] TCC_EA_WRREQ_64B[11] TCC_EA_RDREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_LEVEL[12] TCC_EA_WRREQ[12] TCC_EA_WRREQ_64B[12] TCC_EA_RDREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_LEVEL[13] TCC_EA_WRREQ[13] TCC_EA_WRREQ_64B[13] TCC_EA_RDREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_LEVEL[14] TCC_EA_WRREQ[14] TCC_EA_WRREQ_64B[14] TCC_EA_RDREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_LEVEL[15] TCC_EA_WRREQ[15] TCC_EA_WRREQ_64B[15] TCC_EA_RDREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_LEVEL[16] TCC_EA_WRREQ[16] TCC_EA_WRREQ_64B[16] TCC_EA_RDREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_LEVEL[17] TCC_EA_WRREQ[17] TCC_EA_WRREQ_64B[17] TCC_EA_RDREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_LEVEL[18] TCC_EA_WRREQ[18] TCC_EA_WRREQ_64B[18] TCC_EA_RDREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_LEVEL[19] TCC_EA_WRREQ[19] TCC_EA_WRREQ_64B[19] TCC_EA_RDREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_LEVEL[20] TCC_EA_WRREQ[20] TCC_EA_WRREQ_64B[20] TCC_EA_RDREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_LEVEL[21] TCC_EA_WRREQ[21] TCC_EA_WRREQ_64B[21] TCC_EA_RDREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_LEVEL[22] TCC_EA_WRREQ[22] TCC_EA_WRREQ_64B[22] TCC_EA_RDREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_LEVEL[23] TCC_EA_WRREQ[23] TCC_EA_WRREQ_64B[23] TCC_EA_RDREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_LEVEL[24] TCC_EA_WRREQ[24] TCC_EA_WRREQ_64B[24] TCC_EA_RDREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_LEVEL[25] TCC_EA_WRREQ[25] TCC_EA_WRREQ_64B[25] TCC_EA_RDREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_LEVEL[26] TCC_EA_WRREQ[26] TCC_EA_WRREQ_64B[26] TCC_EA_RDREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_LEVEL[27] TCC_EA_WRREQ[27] TCC_EA_WRREQ_64B[27] TCC_EA_RDREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_LEVEL[28] TCC_EA_WRREQ[28] TCC_EA_WRREQ_64B[28] TCC_EA_RDREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_LEVEL[29] TCC_EA_WRREQ[29] TCC_EA_WRREQ_64B[29] TCC_EA_RDREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_LEVEL[30] TCC_EA_WRREQ[30] TCC_EA_WRREQ_64B[30] TCC_EA_RDREQ_IO_CREDIT_STALL[31] TCC_EA_RDREQ_LEVEL[31] TCC_EA_WRREQ[31] TCC_EA_WRREQ_64B[31] + +gpu: +range: +kernel: 42 diff --git a/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_16.txt b/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_16.txt new file mode 100644 index 0000000000..2821daee94 --- /dev/null +++ b/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_16.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_WRREQ_IO_CREDIT_STALL[0] TCC_EA_WRREQ_LEVEL[0] TCC_EA_WRREQ_DRAM_CREDIT_STALL[1] TCC_EA_WRREQ_GMI_CREDIT_STALL[1] TCC_EA_WRREQ_IO_CREDIT_STALL[1] TCC_EA_WRREQ_LEVEL[1] TCC_EA_WRREQ_DRAM_CREDIT_STALL[2] TCC_EA_WRREQ_GMI_CREDIT_STALL[2] TCC_EA_WRREQ_IO_CREDIT_STALL[2] TCC_EA_WRREQ_LEVEL[2] TCC_EA_WRREQ_DRAM_CREDIT_STALL[3] TCC_EA_WRREQ_GMI_CREDIT_STALL[3] TCC_EA_WRREQ_IO_CREDIT_STALL[3] TCC_EA_WRREQ_LEVEL[3] TCC_EA_WRREQ_DRAM_CREDIT_STALL[4] TCC_EA_WRREQ_GMI_CREDIT_STALL[4] TCC_EA_WRREQ_IO_CREDIT_STALL[4] TCC_EA_WRREQ_LEVEL[4] TCC_EA_WRREQ_DRAM_CREDIT_STALL[5] TCC_EA_WRREQ_GMI_CREDIT_STALL[5] TCC_EA_WRREQ_IO_CREDIT_STALL[5] TCC_EA_WRREQ_LEVEL[5] TCC_EA_WRREQ_DRAM_CREDIT_STALL[6] TCC_EA_WRREQ_GMI_CREDIT_STALL[6] TCC_EA_WRREQ_IO_CREDIT_STALL[6] TCC_EA_WRREQ_LEVEL[6] TCC_EA_WRREQ_DRAM_CREDIT_STALL[7] TCC_EA_WRREQ_GMI_CREDIT_STALL[7] TCC_EA_WRREQ_IO_CREDIT_STALL[7] TCC_EA_WRREQ_LEVEL[7] TCC_EA_WRREQ_DRAM_CREDIT_STALL[8] TCC_EA_WRREQ_GMI_CREDIT_STALL[8] TCC_EA_WRREQ_IO_CREDIT_STALL[8] TCC_EA_WRREQ_LEVEL[8] TCC_EA_WRREQ_DRAM_CREDIT_STALL[9] TCC_EA_WRREQ_GMI_CREDIT_STALL[9] TCC_EA_WRREQ_IO_CREDIT_STALL[9] TCC_EA_WRREQ_LEVEL[9] TCC_EA_WRREQ_DRAM_CREDIT_STALL[10] TCC_EA_WRREQ_GMI_CREDIT_STALL[10] TCC_EA_WRREQ_IO_CREDIT_STALL[10] TCC_EA_WRREQ_LEVEL[10] TCC_EA_WRREQ_DRAM_CREDIT_STALL[11] TCC_EA_WRREQ_GMI_CREDIT_STALL[11] TCC_EA_WRREQ_IO_CREDIT_STALL[11] TCC_EA_WRREQ_LEVEL[11] TCC_EA_WRREQ_DRAM_CREDIT_STALL[12] TCC_EA_WRREQ_GMI_CREDIT_STALL[12] TCC_EA_WRREQ_IO_CREDIT_STALL[12] TCC_EA_WRREQ_LEVEL[12] TCC_EA_WRREQ_DRAM_CREDIT_STALL[13] TCC_EA_WRREQ_GMI_CREDIT_STALL[13] TCC_EA_WRREQ_IO_CREDIT_STALL[13] TCC_EA_WRREQ_LEVEL[13] TCC_EA_WRREQ_DRAM_CREDIT_STALL[14] TCC_EA_WRREQ_GMI_CREDIT_STALL[14] TCC_EA_WRREQ_IO_CREDIT_STALL[14] TCC_EA_WRREQ_LEVEL[14] TCC_EA_WRREQ_DRAM_CREDIT_STALL[15] TCC_EA_WRREQ_GMI_CREDIT_STALL[15] TCC_EA_WRREQ_IO_CREDIT_STALL[15] TCC_EA_WRREQ_LEVEL[15] TCC_EA_WRREQ_DRAM_CREDIT_STALL[16] TCC_EA_WRREQ_GMI_CREDIT_STALL[16] TCC_EA_WRREQ_IO_CREDIT_STALL[16] TCC_EA_WRREQ_LEVEL[16] TCC_EA_WRREQ_DRAM_CREDIT_STALL[17] TCC_EA_WRREQ_GMI_CREDIT_STALL[17] TCC_EA_WRREQ_IO_CREDIT_STALL[17] TCC_EA_WRREQ_LEVEL[17] TCC_EA_WRREQ_DRAM_CREDIT_STALL[18] TCC_EA_WRREQ_GMI_CREDIT_STALL[18] TCC_EA_WRREQ_IO_CREDIT_STALL[18] TCC_EA_WRREQ_LEVEL[18] TCC_EA_WRREQ_DRAM_CREDIT_STALL[19] TCC_EA_WRREQ_GMI_CREDIT_STALL[19] TCC_EA_WRREQ_IO_CREDIT_STALL[19] TCC_EA_WRREQ_LEVEL[19] TCC_EA_WRREQ_DRAM_CREDIT_STALL[20] TCC_EA_WRREQ_GMI_CREDIT_STALL[20] TCC_EA_WRREQ_IO_CREDIT_STALL[20] TCC_EA_WRREQ_LEVEL[20] TCC_EA_WRREQ_DRAM_CREDIT_STALL[21] TCC_EA_WRREQ_GMI_CREDIT_STALL[21] TCC_EA_WRREQ_IO_CREDIT_STALL[21] TCC_EA_WRREQ_LEVEL[21] TCC_EA_WRREQ_DRAM_CREDIT_STALL[22] TCC_EA_WRREQ_GMI_CREDIT_STALL[22] TCC_EA_WRREQ_IO_CREDIT_STALL[22] TCC_EA_WRREQ_LEVEL[22] TCC_EA_WRREQ_DRAM_CREDIT_STALL[23] TCC_EA_WRREQ_GMI_CREDIT_STALL[23] TCC_EA_WRREQ_IO_CREDIT_STALL[23] TCC_EA_WRREQ_LEVEL[23] TCC_EA_WRREQ_DRAM_CREDIT_STALL[24] TCC_EA_WRREQ_GMI_CREDIT_STALL[24] TCC_EA_WRREQ_IO_CREDIT_STALL[24] TCC_EA_WRREQ_LEVEL[24] TCC_EA_WRREQ_DRAM_CREDIT_STALL[25] TCC_EA_WRREQ_GMI_CREDIT_STALL[25] TCC_EA_WRREQ_IO_CREDIT_STALL[25] TCC_EA_WRREQ_LEVEL[25] TCC_EA_WRREQ_DRAM_CREDIT_STALL[26] TCC_EA_WRREQ_GMI_CREDIT_STALL[26] TCC_EA_WRREQ_IO_CREDIT_STALL[26] TCC_EA_WRREQ_LEVEL[26] TCC_EA_WRREQ_DRAM_CREDIT_STALL[27] TCC_EA_WRREQ_GMI_CREDIT_STALL[27] TCC_EA_WRREQ_IO_CREDIT_STALL[27] TCC_EA_WRREQ_LEVEL[27] TCC_EA_WRREQ_DRAM_CREDIT_STALL[28] TCC_EA_WRREQ_GMI_CREDIT_STALL[28] TCC_EA_WRREQ_IO_CREDIT_STALL[28] TCC_EA_WRREQ_LEVEL[28] TCC_EA_WRREQ_DRAM_CREDIT_STALL[29] TCC_EA_WRREQ_GMI_CREDIT_STALL[29] TCC_EA_WRREQ_IO_CREDIT_STALL[29] TCC_EA_WRREQ_LEVEL[29] TCC_EA_WRREQ_DRAM_CREDIT_STALL[30] TCC_EA_WRREQ_GMI_CREDIT_STALL[30] TCC_EA_WRREQ_IO_CREDIT_STALL[30] TCC_EA_WRREQ_LEVEL[30] TCC_EA_WRREQ_DRAM_CREDIT_STALL[31] TCC_EA_WRREQ_GMI_CREDIT_STALL[31] TCC_EA_WRREQ_IO_CREDIT_STALL[31] TCC_EA_WRREQ_LEVEL[31] + +gpu: +range: +kernel: 42 diff --git a/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_17.txt b/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_17.txt new file mode 100644 index 0000000000..60e4d63a8b --- /dev/null +++ b/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_17.txt @@ -0,0 +1,5 @@ +pmc: TCC_HIT[0] TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_HIT[1] TCC_MISS[1] TCC_READ[1] TCC_REQ[1] TCC_HIT[2] TCC_MISS[2] TCC_READ[2] TCC_REQ[2] TCC_HIT[3] TCC_MISS[3] TCC_READ[3] TCC_REQ[3] TCC_HIT[4] TCC_MISS[4] TCC_READ[4] TCC_REQ[4] TCC_HIT[5] TCC_MISS[5] TCC_READ[5] TCC_REQ[5] TCC_HIT[6] TCC_MISS[6] TCC_READ[6] TCC_REQ[6] TCC_HIT[7] TCC_MISS[7] TCC_READ[7] TCC_REQ[7] TCC_HIT[8] TCC_MISS[8] TCC_READ[8] TCC_REQ[8] TCC_HIT[9] TCC_MISS[9] TCC_READ[9] TCC_REQ[9] TCC_HIT[10] TCC_MISS[10] TCC_READ[10] TCC_REQ[10] TCC_HIT[11] TCC_MISS[11] TCC_READ[11] TCC_REQ[11] TCC_HIT[12] TCC_MISS[12] TCC_READ[12] TCC_REQ[12] TCC_HIT[13] TCC_MISS[13] TCC_READ[13] TCC_REQ[13] TCC_HIT[14] TCC_MISS[14] TCC_READ[14] TCC_REQ[14] TCC_HIT[15] TCC_MISS[15] TCC_READ[15] TCC_REQ[15] TCC_HIT[16] TCC_MISS[16] TCC_READ[16] TCC_REQ[16] TCC_HIT[17] TCC_MISS[17] TCC_READ[17] TCC_REQ[17] TCC_HIT[18] TCC_MISS[18] TCC_READ[18] TCC_REQ[18] TCC_HIT[19] TCC_MISS[19] TCC_READ[19] TCC_REQ[19] TCC_HIT[20] TCC_MISS[20] TCC_READ[20] TCC_REQ[20] TCC_HIT[21] TCC_MISS[21] TCC_READ[21] TCC_REQ[21] TCC_HIT[22] TCC_MISS[22] TCC_READ[22] TCC_REQ[22] TCC_HIT[23] TCC_MISS[23] TCC_READ[23] TCC_REQ[23] TCC_HIT[24] TCC_MISS[24] TCC_READ[24] TCC_REQ[24] TCC_HIT[25] TCC_MISS[25] TCC_READ[25] TCC_REQ[25] TCC_HIT[26] TCC_MISS[26] TCC_READ[26] TCC_REQ[26] TCC_HIT[27] TCC_MISS[27] TCC_READ[27] TCC_REQ[27] TCC_HIT[28] TCC_MISS[28] TCC_READ[28] TCC_REQ[28] TCC_HIT[29] TCC_MISS[29] TCC_READ[29] TCC_REQ[29] TCC_HIT[30] TCC_MISS[30] TCC_READ[30] TCC_REQ[30] TCC_HIT[31] TCC_MISS[31] TCC_READ[31] TCC_REQ[31] + +gpu: +range: +kernel: 42 diff --git a/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_18.txt b/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_18.txt new file mode 100644 index 0000000000..47ee30f3a6 --- /dev/null +++ b/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_18.txt @@ -0,0 +1,5 @@ +pmc: TCC_RW_REQ[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_RW_REQ[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_WRITE[1] TCC_RW_REQ[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_WRITE[2] TCC_RW_REQ[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_WRITE[3] TCC_RW_REQ[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_WRITE[4] TCC_RW_REQ[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_WRITE[5] TCC_RW_REQ[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_WRITE[6] TCC_RW_REQ[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_WRITE[7] TCC_RW_REQ[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_WRITE[8] TCC_RW_REQ[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_WRITE[9] TCC_RW_REQ[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_WRITE[10] TCC_RW_REQ[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_WRITE[11] TCC_RW_REQ[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_WRITE[12] TCC_RW_REQ[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_WRITE[13] TCC_RW_REQ[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_WRITE[14] TCC_RW_REQ[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_WRITE[15] TCC_RW_REQ[16] TCC_TOO_MANY_EA_WRREQS_STALL[16] TCC_WRITE[16] TCC_RW_REQ[17] TCC_TOO_MANY_EA_WRREQS_STALL[17] TCC_WRITE[17] TCC_RW_REQ[18] TCC_TOO_MANY_EA_WRREQS_STALL[18] TCC_WRITE[18] TCC_RW_REQ[19] TCC_TOO_MANY_EA_WRREQS_STALL[19] TCC_WRITE[19] TCC_RW_REQ[20] TCC_TOO_MANY_EA_WRREQS_STALL[20] TCC_WRITE[20] TCC_RW_REQ[21] TCC_TOO_MANY_EA_WRREQS_STALL[21] TCC_WRITE[21] TCC_RW_REQ[22] TCC_TOO_MANY_EA_WRREQS_STALL[22] TCC_WRITE[22] TCC_RW_REQ[23] TCC_TOO_MANY_EA_WRREQS_STALL[23] TCC_WRITE[23] TCC_RW_REQ[24] TCC_TOO_MANY_EA_WRREQS_STALL[24] TCC_WRITE[24] TCC_RW_REQ[25] TCC_TOO_MANY_EA_WRREQS_STALL[25] TCC_WRITE[25] TCC_RW_REQ[26] TCC_TOO_MANY_EA_WRREQS_STALL[26] TCC_WRITE[26] TCC_RW_REQ[27] TCC_TOO_MANY_EA_WRREQS_STALL[27] TCC_WRITE[27] TCC_RW_REQ[28] TCC_TOO_MANY_EA_WRREQS_STALL[28] TCC_WRITE[28] TCC_RW_REQ[29] TCC_TOO_MANY_EA_WRREQS_STALL[29] TCC_WRITE[29] TCC_RW_REQ[30] TCC_TOO_MANY_EA_WRREQS_STALL[30] TCC_WRITE[30] TCC_RW_REQ[31] TCC_TOO_MANY_EA_WRREQS_STALL[31] TCC_WRITE[31] + +gpu: +range: +kernel: 42 diff --git a/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_2.txt b/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_2.txt new file mode 100644 index 0000000000..246c73d69f --- /dev/null +++ b/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_2.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_MUL_F32 SQ_INSTS_VALU_FMA_F32 SQ_INSTS_VALU_TRANS_F32 SQ_INSTS_VALU_ADD_F64 SQ_INSTS_VALU_MUL_F64 SQ_INSTS_VALU_FMA_F64 SQ_INSTS_VALU_TRANS_F64 SQ_INSTS_VALU_INT32 TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum TA_BUFFER_ATOMIC_WAVEFRONTS_sum TA_BUFFER_TOTAL_CYCLES_sum TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum + +gpu: +range: +kernel: 42 diff --git a/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_3.txt b/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_3.txt new file mode 100644 index 0000000000..acff344e26 --- /dev/null +++ b/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_3.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_INT64 SQ_INSTS_SMEM SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum TD_COALESCABLE_WAVEFRONT_sum SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE CPF_CMP_UTCL1_STALL_ON_TRANSLATION TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum + +gpu: +range: +kernel: 42 diff --git a/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_4.txt b/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_4.txt new file mode 100644 index 0000000000..5c21181958 --- /dev/null +++ b/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_4.txt @@ -0,0 +1,5 @@ +pmc: SQ_WAVE_CYCLES SQ_WAIT_ANY SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_BUSY_CU_CYCLES SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE TCC_EA_WRREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WR_UNCACHED_32B_sum TCC_EA_WRREQ_DRAM_sum + +gpu: +range: +kernel: 42 diff --git a/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_5.txt b/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_5.txt new file mode 100644 index 0000000000..095a9b040f --- /dev/null +++ b/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_5.txt @@ -0,0 +1,5 @@ +pmc: SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU TCP_TCP_LATENCY_sum TCP_TCC_READ_REQ_LATENCY_sum TCP_TCC_WRITE_REQ_LATENCY_sum TCP_TCC_READ_REQ_sum TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN CPC_ME1_DC0_SPI_BUSY TCC_EA_WRREQ_STALL_sum TCC_EA_RDREQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RD_UNCACHED_32B_sum + +gpu: +range: +kernel: 42 diff --git a/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_6.txt b/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_6.txt new file mode 100644 index 0000000000..742f44a272 --- /dev/null +++ b/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_6.txt @@ -0,0 +1,5 @@ +pmc: SQ_THREAD_CYCLES_VALU SQ_IFETCH SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TCP_TCC_NC_READ_REQ_sum TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN TCC_EA_RDREQ_DRAM_sum TCC_TAG_STALL_sum TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum + +gpu: +range: +kernel: 42 diff --git a/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_7.txt b/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_7.txt new file mode 100644 index 0000000000..39c7bc0a26 --- /dev/null +++ b/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_7.txt @@ -0,0 +1,5 @@ +pmc: SQ_WAVES_LT_32 SQ_WAVES_LT_16 SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TCP_TCC_UC_WRITE_REQ_sum TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR TCC_NORMAL_EVICT_sum TCC_ALL_TC_OP_INV_EVICT_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA_ATOMIC_sum + +gpu: +range: +kernel: 42 diff --git a/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_8.txt b/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_8.txt new file mode 100644 index 0000000000..1aa90d7ac1 --- /dev/null +++ b/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_8.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM_NORM SQ_INSTS_MFMA SQ_INSTS_VALU_MFMA_I8 SQ_INSTS_VALU_MFMA_F16 SQ_INSTS_VALU_MFMA_BF16 SQ_INSTS_VALU_MFMA_F32 SQ_INSTS_VALU_MFMA_F64 SQ_VALU_MFMA_BUSY_CYCLES TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TCP_TCC_CC_ATOMIC_REQ_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN TCC_EA_RDREQ_LEVEL_sum TCC_EA_WRREQ_LEVEL_sum TCC_EA_ATOMIC_LEVEL_sum + +gpu: +range: +kernel: 42 diff --git a/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_9.txt b/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_9.txt new file mode 100644 index 0000000000..f503e29b71 --- /dev/null +++ b/tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_9.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_FLAT_LDS_ONLY SQ_INSTS_VALU_MFMA_MOPS_I8 SQ_INSTS_VALU_MFMA_MOPS_F16 SQ_INSTS_VALU_MFMA_MOPS_BF16 SQ_INSTS_VALU_MFMA_MOPS_F32 SQ_INSTS_VALU_MFMA_MOPS_F64 SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum TCP_PENDING_STALL_CYCLES_sum + +gpu: +range: +kernel: 42 diff --git a/tests/workloads/kernel_inv_int/MI200/perfmon/timestamps.txt b/tests/workloads/kernel_inv_int/MI200/perfmon/timestamps.txt new file mode 100644 index 0000000000..54a64b6ee1 --- /dev/null +++ b/tests/workloads/kernel_inv_int/MI200/perfmon/timestamps.txt @@ -0,0 +1,5 @@ +pmc: + +gpu: +range: +kernel: 42 diff --git a/tests/workloads/kernel_inv_int/MI200/pmc_perf_0.csv b/tests/workloads/kernel_inv_int/MI200/pmc_perf_0.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/kernel_inv_int/MI200/pmc_perf_0.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/kernel_inv_int/MI200/pmc_perf_1.csv b/tests/workloads/kernel_inv_int/MI200/pmc_perf_1.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/kernel_inv_int/MI200/pmc_perf_1.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/kernel_inv_int/MI200/pmc_perf_10.csv b/tests/workloads/kernel_inv_int/MI200/pmc_perf_10.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/kernel_inv_int/MI200/pmc_perf_10.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/kernel_inv_int/MI200/pmc_perf_11.csv b/tests/workloads/kernel_inv_int/MI200/pmc_perf_11.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/kernel_inv_int/MI200/pmc_perf_11.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/kernel_inv_int/MI200/pmc_perf_12.csv b/tests/workloads/kernel_inv_int/MI200/pmc_perf_12.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/kernel_inv_int/MI200/pmc_perf_12.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/kernel_inv_int/MI200/pmc_perf_13.csv b/tests/workloads/kernel_inv_int/MI200/pmc_perf_13.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/kernel_inv_int/MI200/pmc_perf_13.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/kernel_inv_int/MI200/pmc_perf_14.csv b/tests/workloads/kernel_inv_int/MI200/pmc_perf_14.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/kernel_inv_int/MI200/pmc_perf_14.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/kernel_inv_int/MI200/pmc_perf_15.csv b/tests/workloads/kernel_inv_int/MI200/pmc_perf_15.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/kernel_inv_int/MI200/pmc_perf_15.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/kernel_inv_int/MI200/pmc_perf_16.csv b/tests/workloads/kernel_inv_int/MI200/pmc_perf_16.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/kernel_inv_int/MI200/pmc_perf_16.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/kernel_inv_int/MI200/pmc_perf_17.csv b/tests/workloads/kernel_inv_int/MI200/pmc_perf_17.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/kernel_inv_int/MI200/pmc_perf_17.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/kernel_inv_int/MI200/pmc_perf_18.csv b/tests/workloads/kernel_inv_int/MI200/pmc_perf_18.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/kernel_inv_int/MI200/pmc_perf_18.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/kernel_inv_int/MI200/pmc_perf_2.csv b/tests/workloads/kernel_inv_int/MI200/pmc_perf_2.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/kernel_inv_int/MI200/pmc_perf_2.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/kernel_inv_int/MI200/pmc_perf_3.csv b/tests/workloads/kernel_inv_int/MI200/pmc_perf_3.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/kernel_inv_int/MI200/pmc_perf_3.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/kernel_inv_int/MI200/pmc_perf_4.csv b/tests/workloads/kernel_inv_int/MI200/pmc_perf_4.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/kernel_inv_int/MI200/pmc_perf_4.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/kernel_inv_int/MI200/pmc_perf_5.csv b/tests/workloads/kernel_inv_int/MI200/pmc_perf_5.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/kernel_inv_int/MI200/pmc_perf_5.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/kernel_inv_int/MI200/pmc_perf_6.csv b/tests/workloads/kernel_inv_int/MI200/pmc_perf_6.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/kernel_inv_int/MI200/pmc_perf_6.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/kernel_inv_int/MI200/pmc_perf_7.csv b/tests/workloads/kernel_inv_int/MI200/pmc_perf_7.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/kernel_inv_int/MI200/pmc_perf_7.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/kernel_inv_int/MI200/pmc_perf_8.csv b/tests/workloads/kernel_inv_int/MI200/pmc_perf_8.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/kernel_inv_int/MI200/pmc_perf_8.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/kernel_inv_int/MI200/pmc_perf_9.csv b/tests/workloads/kernel_inv_int/MI200/pmc_perf_9.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/kernel_inv_int/MI200/pmc_perf_9.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/kernel_inv_int/MI200/sysinfo.csv b/tests/workloads/kernel_inv_int/MI200/sysinfo.csv new file mode 100644 index 0000000000..35738cba51 --- /dev/null +++ b/tests/workloads/kernel_inv_int/MI200/sysinfo.csv @@ -0,0 +1,2 @@ +workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd +kernel_inv_int,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 02:11:46 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/kernel_inv_int/MI200/timestamps.csv b/tests/workloads/kernel_inv_int/MI200/timestamps.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/kernel_inv_int/MI200/timestamps.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/kernel_inv_str/MI100/sysinfo.csv b/tests/workloads/kernel_inv_str/MI100/sysinfo.csv index 0a427aa834..69ce6185cc 100644 --- a/tests/workloads/kernel_inv_str/MI100/sysinfo.csv +++ b/tests/workloads/kernel_inv_str/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -kernel_inv_str,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Fri Mar 1 16:46:00 2024 (CST),1,t006-003.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651240,,5.7.1-98,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +kernel_inv_str,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 07 Mar 2024 01:08:44 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/kernel_inv_str/MI200/SQ_IFETCH_LEVEL.csv b/tests/workloads/kernel_inv_str/MI200/SQ_IFETCH_LEVEL.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/kernel_inv_str/MI200/SQ_IFETCH_LEVEL.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/kernel_inv_str/MI200/SQ_INST_LEVEL_LDS.csv b/tests/workloads/kernel_inv_str/MI200/SQ_INST_LEVEL_LDS.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/kernel_inv_str/MI200/SQ_INST_LEVEL_LDS.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/kernel_inv_str/MI200/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/kernel_inv_str/MI200/SQ_INST_LEVEL_SMEM.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/kernel_inv_str/MI200/SQ_INST_LEVEL_SMEM.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/kernel_inv_str/MI200/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/kernel_inv_str/MI200/SQ_INST_LEVEL_VMEM.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/kernel_inv_str/MI200/SQ_INST_LEVEL_VMEM.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/kernel_inv_str/MI200/SQ_LEVEL_WAVES.csv b/tests/workloads/kernel_inv_str/MI200/SQ_LEVEL_WAVES.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/kernel_inv_str/MI200/SQ_LEVEL_WAVES.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/kernel_inv_str/MI200/perfmon/SQ_IFETCH_LEVEL.txt b/tests/workloads/kernel_inv_str/MI200/perfmon/SQ_IFETCH_LEVEL.txt new file mode 100644 index 0000000000..81471d9699 --- /dev/null +++ b/tests/workloads/kernel_inv_str/MI200/perfmon/SQ_IFETCH_LEVEL.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: vecPaste diff --git a/tests/workloads/kernel_inv_str/MI200/perfmon/SQ_INST_LEVEL_LDS.txt b/tests/workloads/kernel_inv_str/MI200/perfmon/SQ_INST_LEVEL_LDS.txt new file mode 100644 index 0000000000..62d58aac7b --- /dev/null +++ b/tests/workloads/kernel_inv_str/MI200/perfmon/SQ_INST_LEVEL_LDS.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: vecPaste diff --git a/tests/workloads/kernel_inv_str/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt b/tests/workloads/kernel_inv_str/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt new file mode 100644 index 0000000000..e94af03dba --- /dev/null +++ b/tests/workloads/kernel_inv_str/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: vecPaste diff --git a/tests/workloads/kernel_inv_str/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt b/tests/workloads/kernel_inv_str/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt new file mode 100644 index 0000000000..cebcd0ec74 --- /dev/null +++ b/tests/workloads/kernel_inv_str/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: vecPaste diff --git a/tests/workloads/kernel_inv_str/MI200/perfmon/SQ_LEVEL_WAVES.txt b/tests/workloads/kernel_inv_str/MI200/perfmon/SQ_LEVEL_WAVES.txt new file mode 100644 index 0000000000..69a540e9e1 --- /dev/null +++ b/tests/workloads/kernel_inv_str/MI200/perfmon/SQ_LEVEL_WAVES.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: vecPaste diff --git a/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_0.txt b/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_0.txt new file mode 100644 index 0000000000..a5d3190508 --- /dev/null +++ b/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_0.txt @@ -0,0 +1,5 @@ +pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES SQ_INSTS_VALU_CVT SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU GRBM_COUNT GRBM_GUI_ACTIVE TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum TA_TA_BUSY_sum TA_BUFFER_WAVEFRONTS_sum TD_TD_BUSY_sum TD_TC_STALL_sum SPI_CSN_WINDOW_VALID SPI_CSN_BUSY CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum + +gpu: +range: +kernel: vecPaste diff --git a/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_1.txt b/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_1.txt new file mode 100644 index 0000000000..3f642dbdeb --- /dev/null +++ b/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_1.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VSKIPPED SQ_INSTS SQ_INSTS_VALU SQ_INSTS_VALU_ADD_F16 SQ_INSTS_VALU_MUL_F16 SQ_INSTS_VALU_FMA_F16 SQ_INSTS_VALU_TRANS_F16 SQ_INSTS_VALU_ADD_F32 GRBM_SPI_BUSY TCP_READ_TAGCONFLICT_STALL_CYCLES_sum TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum TCP_TA_TCP_STATE_READ_sum TA_BUFFER_READ_WAVEFRONTS_sum TA_BUFFER_WRITE_WAVEFRONTS_sum TD_SPI_STALL_sum TD_LOAD_WAVEFRONT_sum SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum + +gpu: +range: +kernel: vecPaste diff --git a/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_10.txt b/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_10.txt new file mode 100644 index 0000000000..22de6cc58c --- /dev/null +++ b/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_10.txt @@ -0,0 +1,5 @@ +pmc: SQC_TC_DATA_WRITE_REQ SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES + +gpu: +range: +kernel: vecPaste diff --git a/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_11.txt b/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_11.txt new file mode 100644 index 0000000000..7e3e47757a --- /dev/null +++ b/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_11.txt @@ -0,0 +1,5 @@ +pmc: SQC_ICACHE_MISSES_DUPLICATE SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE + +gpu: +range: +kernel: vecPaste diff --git a/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_12.txt b/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_12.txt new file mode 100644 index 0000000000..a3a99f1826 --- /dev/null +++ b/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_12.txt @@ -0,0 +1,5 @@ +pmc: SQC_DCACHE_REQ_READ_1 SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 + +gpu: +range: +kernel: vecPaste diff --git a/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_13.txt b/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_13.txt new file mode 100644 index 0000000000..ff548bf042 --- /dev/null +++ b/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_13.txt @@ -0,0 +1,5 @@ +pmc: TCC_ATOMIC[0] TCC_CYCLE[0] TCC_EA_ATOMIC[0] TCC_EA_ATOMIC_LEVEL[0] TCC_ATOMIC[1] TCC_CYCLE[1] TCC_EA_ATOMIC[1] TCC_EA_ATOMIC_LEVEL[1] TCC_ATOMIC[2] TCC_CYCLE[2] TCC_EA_ATOMIC[2] TCC_EA_ATOMIC_LEVEL[2] TCC_ATOMIC[3] TCC_CYCLE[3] TCC_EA_ATOMIC[3] TCC_EA_ATOMIC_LEVEL[3] TCC_ATOMIC[4] TCC_CYCLE[4] TCC_EA_ATOMIC[4] TCC_EA_ATOMIC_LEVEL[4] TCC_ATOMIC[5] TCC_CYCLE[5] TCC_EA_ATOMIC[5] TCC_EA_ATOMIC_LEVEL[5] TCC_ATOMIC[6] TCC_CYCLE[6] TCC_EA_ATOMIC[6] TCC_EA_ATOMIC_LEVEL[6] TCC_ATOMIC[7] TCC_CYCLE[7] TCC_EA_ATOMIC[7] TCC_EA_ATOMIC_LEVEL[7] TCC_ATOMIC[8] TCC_CYCLE[8] TCC_EA_ATOMIC[8] TCC_EA_ATOMIC_LEVEL[8] TCC_ATOMIC[9] TCC_CYCLE[9] TCC_EA_ATOMIC[9] TCC_EA_ATOMIC_LEVEL[9] TCC_ATOMIC[10] TCC_CYCLE[10] TCC_EA_ATOMIC[10] TCC_EA_ATOMIC_LEVEL[10] TCC_ATOMIC[11] TCC_CYCLE[11] TCC_EA_ATOMIC[11] TCC_EA_ATOMIC_LEVEL[11] TCC_ATOMIC[12] TCC_CYCLE[12] TCC_EA_ATOMIC[12] TCC_EA_ATOMIC_LEVEL[12] TCC_ATOMIC[13] TCC_CYCLE[13] TCC_EA_ATOMIC[13] TCC_EA_ATOMIC_LEVEL[13] TCC_ATOMIC[14] TCC_CYCLE[14] TCC_EA_ATOMIC[14] TCC_EA_ATOMIC_LEVEL[14] TCC_ATOMIC[15] TCC_CYCLE[15] TCC_EA_ATOMIC[15] TCC_EA_ATOMIC_LEVEL[15] TCC_ATOMIC[16] TCC_CYCLE[16] TCC_EA_ATOMIC[16] TCC_EA_ATOMIC_LEVEL[16] TCC_ATOMIC[17] TCC_CYCLE[17] TCC_EA_ATOMIC[17] TCC_EA_ATOMIC_LEVEL[17] TCC_ATOMIC[18] TCC_CYCLE[18] TCC_EA_ATOMIC[18] TCC_EA_ATOMIC_LEVEL[18] TCC_ATOMIC[19] TCC_CYCLE[19] TCC_EA_ATOMIC[19] TCC_EA_ATOMIC_LEVEL[19] TCC_ATOMIC[20] TCC_CYCLE[20] TCC_EA_ATOMIC[20] TCC_EA_ATOMIC_LEVEL[20] TCC_ATOMIC[21] TCC_CYCLE[21] TCC_EA_ATOMIC[21] TCC_EA_ATOMIC_LEVEL[21] TCC_ATOMIC[22] TCC_CYCLE[22] TCC_EA_ATOMIC[22] TCC_EA_ATOMIC_LEVEL[22] TCC_ATOMIC[23] TCC_CYCLE[23] TCC_EA_ATOMIC[23] TCC_EA_ATOMIC_LEVEL[23] TCC_ATOMIC[24] TCC_CYCLE[24] TCC_EA_ATOMIC[24] TCC_EA_ATOMIC_LEVEL[24] TCC_ATOMIC[25] TCC_CYCLE[25] TCC_EA_ATOMIC[25] TCC_EA_ATOMIC_LEVEL[25] TCC_ATOMIC[26] TCC_CYCLE[26] TCC_EA_ATOMIC[26] TCC_EA_ATOMIC_LEVEL[26] TCC_ATOMIC[27] TCC_CYCLE[27] TCC_EA_ATOMIC[27] TCC_EA_ATOMIC_LEVEL[27] TCC_ATOMIC[28] TCC_CYCLE[28] TCC_EA_ATOMIC[28] TCC_EA_ATOMIC_LEVEL[28] TCC_ATOMIC[29] TCC_CYCLE[29] TCC_EA_ATOMIC[29] TCC_EA_ATOMIC_LEVEL[29] TCC_ATOMIC[30] TCC_CYCLE[30] TCC_EA_ATOMIC[30] TCC_EA_ATOMIC_LEVEL[30] TCC_ATOMIC[31] TCC_CYCLE[31] TCC_EA_ATOMIC[31] TCC_EA_ATOMIC_LEVEL[31] + +gpu: +range: +kernel: vecPaste diff --git a/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_14.txt b/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_14.txt new file mode 100644 index 0000000000..d2e5bd9f50 --- /dev/null +++ b/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_14.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_EA_RDREQ_GMI_CREDIT_STALL[0] TCC_EA_RDREQ[1] TCC_EA_RDREQ_32B[1] TCC_EA_RDREQ_DRAM_CREDIT_STALL[1] TCC_EA_RDREQ_GMI_CREDIT_STALL[1] TCC_EA_RDREQ[2] TCC_EA_RDREQ_32B[2] TCC_EA_RDREQ_DRAM_CREDIT_STALL[2] TCC_EA_RDREQ_GMI_CREDIT_STALL[2] TCC_EA_RDREQ[3] TCC_EA_RDREQ_32B[3] TCC_EA_RDREQ_DRAM_CREDIT_STALL[3] TCC_EA_RDREQ_GMI_CREDIT_STALL[3] TCC_EA_RDREQ[4] TCC_EA_RDREQ_32B[4] TCC_EA_RDREQ_DRAM_CREDIT_STALL[4] TCC_EA_RDREQ_GMI_CREDIT_STALL[4] TCC_EA_RDREQ[5] TCC_EA_RDREQ_32B[5] TCC_EA_RDREQ_DRAM_CREDIT_STALL[5] TCC_EA_RDREQ_GMI_CREDIT_STALL[5] TCC_EA_RDREQ[6] TCC_EA_RDREQ_32B[6] TCC_EA_RDREQ_DRAM_CREDIT_STALL[6] TCC_EA_RDREQ_GMI_CREDIT_STALL[6] TCC_EA_RDREQ[7] TCC_EA_RDREQ_32B[7] TCC_EA_RDREQ_DRAM_CREDIT_STALL[7] TCC_EA_RDREQ_GMI_CREDIT_STALL[7] TCC_EA_RDREQ[8] TCC_EA_RDREQ_32B[8] TCC_EA_RDREQ_DRAM_CREDIT_STALL[8] TCC_EA_RDREQ_GMI_CREDIT_STALL[8] TCC_EA_RDREQ[9] TCC_EA_RDREQ_32B[9] TCC_EA_RDREQ_DRAM_CREDIT_STALL[9] TCC_EA_RDREQ_GMI_CREDIT_STALL[9] TCC_EA_RDREQ[10] TCC_EA_RDREQ_32B[10] TCC_EA_RDREQ_DRAM_CREDIT_STALL[10] TCC_EA_RDREQ_GMI_CREDIT_STALL[10] TCC_EA_RDREQ[11] TCC_EA_RDREQ_32B[11] TCC_EA_RDREQ_DRAM_CREDIT_STALL[11] TCC_EA_RDREQ_GMI_CREDIT_STALL[11] TCC_EA_RDREQ[12] TCC_EA_RDREQ_32B[12] TCC_EA_RDREQ_DRAM_CREDIT_STALL[12] TCC_EA_RDREQ_GMI_CREDIT_STALL[12] TCC_EA_RDREQ[13] TCC_EA_RDREQ_32B[13] TCC_EA_RDREQ_DRAM_CREDIT_STALL[13] TCC_EA_RDREQ_GMI_CREDIT_STALL[13] TCC_EA_RDREQ[14] TCC_EA_RDREQ_32B[14] TCC_EA_RDREQ_DRAM_CREDIT_STALL[14] TCC_EA_RDREQ_GMI_CREDIT_STALL[14] TCC_EA_RDREQ[15] TCC_EA_RDREQ_32B[15] TCC_EA_RDREQ_DRAM_CREDIT_STALL[15] TCC_EA_RDREQ_GMI_CREDIT_STALL[15] TCC_EA_RDREQ[16] TCC_EA_RDREQ_32B[16] TCC_EA_RDREQ_DRAM_CREDIT_STALL[16] TCC_EA_RDREQ_GMI_CREDIT_STALL[16] TCC_EA_RDREQ[17] TCC_EA_RDREQ_32B[17] TCC_EA_RDREQ_DRAM_CREDIT_STALL[17] TCC_EA_RDREQ_GMI_CREDIT_STALL[17] TCC_EA_RDREQ[18] TCC_EA_RDREQ_32B[18] TCC_EA_RDREQ_DRAM_CREDIT_STALL[18] TCC_EA_RDREQ_GMI_CREDIT_STALL[18] TCC_EA_RDREQ[19] TCC_EA_RDREQ_32B[19] TCC_EA_RDREQ_DRAM_CREDIT_STALL[19] TCC_EA_RDREQ_GMI_CREDIT_STALL[19] TCC_EA_RDREQ[20] TCC_EA_RDREQ_32B[20] TCC_EA_RDREQ_DRAM_CREDIT_STALL[20] TCC_EA_RDREQ_GMI_CREDIT_STALL[20] TCC_EA_RDREQ[21] TCC_EA_RDREQ_32B[21] TCC_EA_RDREQ_DRAM_CREDIT_STALL[21] TCC_EA_RDREQ_GMI_CREDIT_STALL[21] TCC_EA_RDREQ[22] TCC_EA_RDREQ_32B[22] TCC_EA_RDREQ_DRAM_CREDIT_STALL[22] TCC_EA_RDREQ_GMI_CREDIT_STALL[22] TCC_EA_RDREQ[23] TCC_EA_RDREQ_32B[23] TCC_EA_RDREQ_DRAM_CREDIT_STALL[23] TCC_EA_RDREQ_GMI_CREDIT_STALL[23] TCC_EA_RDREQ[24] TCC_EA_RDREQ_32B[24] TCC_EA_RDREQ_DRAM_CREDIT_STALL[24] TCC_EA_RDREQ_GMI_CREDIT_STALL[24] TCC_EA_RDREQ[25] TCC_EA_RDREQ_32B[25] TCC_EA_RDREQ_DRAM_CREDIT_STALL[25] TCC_EA_RDREQ_GMI_CREDIT_STALL[25] TCC_EA_RDREQ[26] TCC_EA_RDREQ_32B[26] TCC_EA_RDREQ_DRAM_CREDIT_STALL[26] TCC_EA_RDREQ_GMI_CREDIT_STALL[26] TCC_EA_RDREQ[27] TCC_EA_RDREQ_32B[27] TCC_EA_RDREQ_DRAM_CREDIT_STALL[27] TCC_EA_RDREQ_GMI_CREDIT_STALL[27] TCC_EA_RDREQ[28] TCC_EA_RDREQ_32B[28] TCC_EA_RDREQ_DRAM_CREDIT_STALL[28] TCC_EA_RDREQ_GMI_CREDIT_STALL[28] TCC_EA_RDREQ[29] TCC_EA_RDREQ_32B[29] TCC_EA_RDREQ_DRAM_CREDIT_STALL[29] TCC_EA_RDREQ_GMI_CREDIT_STALL[29] TCC_EA_RDREQ[30] TCC_EA_RDREQ_32B[30] TCC_EA_RDREQ_DRAM_CREDIT_STALL[30] TCC_EA_RDREQ_GMI_CREDIT_STALL[30] TCC_EA_RDREQ[31] TCC_EA_RDREQ_32B[31] TCC_EA_RDREQ_DRAM_CREDIT_STALL[31] TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + +gpu: +range: +kernel: vecPaste diff --git a/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_15.txt b/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_15.txt new file mode 100644 index 0000000000..3a61ee943e --- /dev/null +++ b/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_15.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ[0] TCC_EA_WRREQ_64B[0] TCC_EA_RDREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_LEVEL[1] TCC_EA_WRREQ[1] TCC_EA_WRREQ_64B[1] TCC_EA_RDREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_LEVEL[2] TCC_EA_WRREQ[2] TCC_EA_WRREQ_64B[2] TCC_EA_RDREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_LEVEL[3] TCC_EA_WRREQ[3] TCC_EA_WRREQ_64B[3] TCC_EA_RDREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_LEVEL[4] TCC_EA_WRREQ[4] TCC_EA_WRREQ_64B[4] TCC_EA_RDREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_LEVEL[5] TCC_EA_WRREQ[5] TCC_EA_WRREQ_64B[5] TCC_EA_RDREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_LEVEL[6] TCC_EA_WRREQ[6] TCC_EA_WRREQ_64B[6] TCC_EA_RDREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_LEVEL[7] TCC_EA_WRREQ[7] TCC_EA_WRREQ_64B[7] TCC_EA_RDREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_LEVEL[8] TCC_EA_WRREQ[8] TCC_EA_WRREQ_64B[8] TCC_EA_RDREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_LEVEL[9] TCC_EA_WRREQ[9] TCC_EA_WRREQ_64B[9] TCC_EA_RDREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_LEVEL[10] TCC_EA_WRREQ[10] TCC_EA_WRREQ_64B[10] TCC_EA_RDREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_LEVEL[11] TCC_EA_WRREQ[11] TCC_EA_WRREQ_64B[11] TCC_EA_RDREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_LEVEL[12] TCC_EA_WRREQ[12] TCC_EA_WRREQ_64B[12] TCC_EA_RDREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_LEVEL[13] TCC_EA_WRREQ[13] TCC_EA_WRREQ_64B[13] TCC_EA_RDREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_LEVEL[14] TCC_EA_WRREQ[14] TCC_EA_WRREQ_64B[14] TCC_EA_RDREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_LEVEL[15] TCC_EA_WRREQ[15] TCC_EA_WRREQ_64B[15] TCC_EA_RDREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_LEVEL[16] TCC_EA_WRREQ[16] TCC_EA_WRREQ_64B[16] TCC_EA_RDREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_LEVEL[17] TCC_EA_WRREQ[17] TCC_EA_WRREQ_64B[17] TCC_EA_RDREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_LEVEL[18] TCC_EA_WRREQ[18] TCC_EA_WRREQ_64B[18] TCC_EA_RDREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_LEVEL[19] TCC_EA_WRREQ[19] TCC_EA_WRREQ_64B[19] TCC_EA_RDREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_LEVEL[20] TCC_EA_WRREQ[20] TCC_EA_WRREQ_64B[20] TCC_EA_RDREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_LEVEL[21] TCC_EA_WRREQ[21] TCC_EA_WRREQ_64B[21] TCC_EA_RDREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_LEVEL[22] TCC_EA_WRREQ[22] TCC_EA_WRREQ_64B[22] TCC_EA_RDREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_LEVEL[23] TCC_EA_WRREQ[23] TCC_EA_WRREQ_64B[23] TCC_EA_RDREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_LEVEL[24] TCC_EA_WRREQ[24] TCC_EA_WRREQ_64B[24] TCC_EA_RDREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_LEVEL[25] TCC_EA_WRREQ[25] TCC_EA_WRREQ_64B[25] TCC_EA_RDREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_LEVEL[26] TCC_EA_WRREQ[26] TCC_EA_WRREQ_64B[26] TCC_EA_RDREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_LEVEL[27] TCC_EA_WRREQ[27] TCC_EA_WRREQ_64B[27] TCC_EA_RDREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_LEVEL[28] TCC_EA_WRREQ[28] TCC_EA_WRREQ_64B[28] TCC_EA_RDREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_LEVEL[29] TCC_EA_WRREQ[29] TCC_EA_WRREQ_64B[29] TCC_EA_RDREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_LEVEL[30] TCC_EA_WRREQ[30] TCC_EA_WRREQ_64B[30] TCC_EA_RDREQ_IO_CREDIT_STALL[31] TCC_EA_RDREQ_LEVEL[31] TCC_EA_WRREQ[31] TCC_EA_WRREQ_64B[31] + +gpu: +range: +kernel: vecPaste diff --git a/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_16.txt b/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_16.txt new file mode 100644 index 0000000000..aa1261ea82 --- /dev/null +++ b/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_16.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_WRREQ_IO_CREDIT_STALL[0] TCC_EA_WRREQ_LEVEL[0] TCC_EA_WRREQ_DRAM_CREDIT_STALL[1] TCC_EA_WRREQ_GMI_CREDIT_STALL[1] TCC_EA_WRREQ_IO_CREDIT_STALL[1] TCC_EA_WRREQ_LEVEL[1] TCC_EA_WRREQ_DRAM_CREDIT_STALL[2] TCC_EA_WRREQ_GMI_CREDIT_STALL[2] TCC_EA_WRREQ_IO_CREDIT_STALL[2] TCC_EA_WRREQ_LEVEL[2] TCC_EA_WRREQ_DRAM_CREDIT_STALL[3] TCC_EA_WRREQ_GMI_CREDIT_STALL[3] TCC_EA_WRREQ_IO_CREDIT_STALL[3] TCC_EA_WRREQ_LEVEL[3] TCC_EA_WRREQ_DRAM_CREDIT_STALL[4] TCC_EA_WRREQ_GMI_CREDIT_STALL[4] TCC_EA_WRREQ_IO_CREDIT_STALL[4] TCC_EA_WRREQ_LEVEL[4] TCC_EA_WRREQ_DRAM_CREDIT_STALL[5] TCC_EA_WRREQ_GMI_CREDIT_STALL[5] TCC_EA_WRREQ_IO_CREDIT_STALL[5] TCC_EA_WRREQ_LEVEL[5] TCC_EA_WRREQ_DRAM_CREDIT_STALL[6] TCC_EA_WRREQ_GMI_CREDIT_STALL[6] TCC_EA_WRREQ_IO_CREDIT_STALL[6] TCC_EA_WRREQ_LEVEL[6] TCC_EA_WRREQ_DRAM_CREDIT_STALL[7] TCC_EA_WRREQ_GMI_CREDIT_STALL[7] TCC_EA_WRREQ_IO_CREDIT_STALL[7] TCC_EA_WRREQ_LEVEL[7] TCC_EA_WRREQ_DRAM_CREDIT_STALL[8] TCC_EA_WRREQ_GMI_CREDIT_STALL[8] TCC_EA_WRREQ_IO_CREDIT_STALL[8] TCC_EA_WRREQ_LEVEL[8] TCC_EA_WRREQ_DRAM_CREDIT_STALL[9] TCC_EA_WRREQ_GMI_CREDIT_STALL[9] TCC_EA_WRREQ_IO_CREDIT_STALL[9] TCC_EA_WRREQ_LEVEL[9] TCC_EA_WRREQ_DRAM_CREDIT_STALL[10] TCC_EA_WRREQ_GMI_CREDIT_STALL[10] TCC_EA_WRREQ_IO_CREDIT_STALL[10] TCC_EA_WRREQ_LEVEL[10] TCC_EA_WRREQ_DRAM_CREDIT_STALL[11] TCC_EA_WRREQ_GMI_CREDIT_STALL[11] TCC_EA_WRREQ_IO_CREDIT_STALL[11] TCC_EA_WRREQ_LEVEL[11] TCC_EA_WRREQ_DRAM_CREDIT_STALL[12] TCC_EA_WRREQ_GMI_CREDIT_STALL[12] TCC_EA_WRREQ_IO_CREDIT_STALL[12] TCC_EA_WRREQ_LEVEL[12] TCC_EA_WRREQ_DRAM_CREDIT_STALL[13] TCC_EA_WRREQ_GMI_CREDIT_STALL[13] TCC_EA_WRREQ_IO_CREDIT_STALL[13] TCC_EA_WRREQ_LEVEL[13] TCC_EA_WRREQ_DRAM_CREDIT_STALL[14] TCC_EA_WRREQ_GMI_CREDIT_STALL[14] TCC_EA_WRREQ_IO_CREDIT_STALL[14] TCC_EA_WRREQ_LEVEL[14] TCC_EA_WRREQ_DRAM_CREDIT_STALL[15] TCC_EA_WRREQ_GMI_CREDIT_STALL[15] TCC_EA_WRREQ_IO_CREDIT_STALL[15] TCC_EA_WRREQ_LEVEL[15] TCC_EA_WRREQ_DRAM_CREDIT_STALL[16] TCC_EA_WRREQ_GMI_CREDIT_STALL[16] TCC_EA_WRREQ_IO_CREDIT_STALL[16] TCC_EA_WRREQ_LEVEL[16] TCC_EA_WRREQ_DRAM_CREDIT_STALL[17] TCC_EA_WRREQ_GMI_CREDIT_STALL[17] TCC_EA_WRREQ_IO_CREDIT_STALL[17] TCC_EA_WRREQ_LEVEL[17] TCC_EA_WRREQ_DRAM_CREDIT_STALL[18] TCC_EA_WRREQ_GMI_CREDIT_STALL[18] TCC_EA_WRREQ_IO_CREDIT_STALL[18] TCC_EA_WRREQ_LEVEL[18] TCC_EA_WRREQ_DRAM_CREDIT_STALL[19] TCC_EA_WRREQ_GMI_CREDIT_STALL[19] TCC_EA_WRREQ_IO_CREDIT_STALL[19] TCC_EA_WRREQ_LEVEL[19] TCC_EA_WRREQ_DRAM_CREDIT_STALL[20] TCC_EA_WRREQ_GMI_CREDIT_STALL[20] TCC_EA_WRREQ_IO_CREDIT_STALL[20] TCC_EA_WRREQ_LEVEL[20] TCC_EA_WRREQ_DRAM_CREDIT_STALL[21] TCC_EA_WRREQ_GMI_CREDIT_STALL[21] TCC_EA_WRREQ_IO_CREDIT_STALL[21] TCC_EA_WRREQ_LEVEL[21] TCC_EA_WRREQ_DRAM_CREDIT_STALL[22] TCC_EA_WRREQ_GMI_CREDIT_STALL[22] TCC_EA_WRREQ_IO_CREDIT_STALL[22] TCC_EA_WRREQ_LEVEL[22] TCC_EA_WRREQ_DRAM_CREDIT_STALL[23] TCC_EA_WRREQ_GMI_CREDIT_STALL[23] TCC_EA_WRREQ_IO_CREDIT_STALL[23] TCC_EA_WRREQ_LEVEL[23] TCC_EA_WRREQ_DRAM_CREDIT_STALL[24] TCC_EA_WRREQ_GMI_CREDIT_STALL[24] TCC_EA_WRREQ_IO_CREDIT_STALL[24] TCC_EA_WRREQ_LEVEL[24] TCC_EA_WRREQ_DRAM_CREDIT_STALL[25] TCC_EA_WRREQ_GMI_CREDIT_STALL[25] TCC_EA_WRREQ_IO_CREDIT_STALL[25] TCC_EA_WRREQ_LEVEL[25] TCC_EA_WRREQ_DRAM_CREDIT_STALL[26] TCC_EA_WRREQ_GMI_CREDIT_STALL[26] TCC_EA_WRREQ_IO_CREDIT_STALL[26] TCC_EA_WRREQ_LEVEL[26] TCC_EA_WRREQ_DRAM_CREDIT_STALL[27] TCC_EA_WRREQ_GMI_CREDIT_STALL[27] TCC_EA_WRREQ_IO_CREDIT_STALL[27] TCC_EA_WRREQ_LEVEL[27] TCC_EA_WRREQ_DRAM_CREDIT_STALL[28] TCC_EA_WRREQ_GMI_CREDIT_STALL[28] TCC_EA_WRREQ_IO_CREDIT_STALL[28] TCC_EA_WRREQ_LEVEL[28] TCC_EA_WRREQ_DRAM_CREDIT_STALL[29] TCC_EA_WRREQ_GMI_CREDIT_STALL[29] TCC_EA_WRREQ_IO_CREDIT_STALL[29] TCC_EA_WRREQ_LEVEL[29] TCC_EA_WRREQ_DRAM_CREDIT_STALL[30] TCC_EA_WRREQ_GMI_CREDIT_STALL[30] TCC_EA_WRREQ_IO_CREDIT_STALL[30] TCC_EA_WRREQ_LEVEL[30] TCC_EA_WRREQ_DRAM_CREDIT_STALL[31] TCC_EA_WRREQ_GMI_CREDIT_STALL[31] TCC_EA_WRREQ_IO_CREDIT_STALL[31] TCC_EA_WRREQ_LEVEL[31] + +gpu: +range: +kernel: vecPaste diff --git a/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_17.txt b/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_17.txt new file mode 100644 index 0000000000..a669a4ef3f --- /dev/null +++ b/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_17.txt @@ -0,0 +1,5 @@ +pmc: TCC_HIT[0] TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_HIT[1] TCC_MISS[1] TCC_READ[1] TCC_REQ[1] TCC_HIT[2] TCC_MISS[2] TCC_READ[2] TCC_REQ[2] TCC_HIT[3] TCC_MISS[3] TCC_READ[3] TCC_REQ[3] TCC_HIT[4] TCC_MISS[4] TCC_READ[4] TCC_REQ[4] TCC_HIT[5] TCC_MISS[5] TCC_READ[5] TCC_REQ[5] TCC_HIT[6] TCC_MISS[6] TCC_READ[6] TCC_REQ[6] TCC_HIT[7] TCC_MISS[7] TCC_READ[7] TCC_REQ[7] TCC_HIT[8] TCC_MISS[8] TCC_READ[8] TCC_REQ[8] TCC_HIT[9] TCC_MISS[9] TCC_READ[9] TCC_REQ[9] TCC_HIT[10] TCC_MISS[10] TCC_READ[10] TCC_REQ[10] TCC_HIT[11] TCC_MISS[11] TCC_READ[11] TCC_REQ[11] TCC_HIT[12] TCC_MISS[12] TCC_READ[12] TCC_REQ[12] TCC_HIT[13] TCC_MISS[13] TCC_READ[13] TCC_REQ[13] TCC_HIT[14] TCC_MISS[14] TCC_READ[14] TCC_REQ[14] TCC_HIT[15] TCC_MISS[15] TCC_READ[15] TCC_REQ[15] TCC_HIT[16] TCC_MISS[16] TCC_READ[16] TCC_REQ[16] TCC_HIT[17] TCC_MISS[17] TCC_READ[17] TCC_REQ[17] TCC_HIT[18] TCC_MISS[18] TCC_READ[18] TCC_REQ[18] TCC_HIT[19] TCC_MISS[19] TCC_READ[19] TCC_REQ[19] TCC_HIT[20] TCC_MISS[20] TCC_READ[20] TCC_REQ[20] TCC_HIT[21] TCC_MISS[21] TCC_READ[21] TCC_REQ[21] TCC_HIT[22] TCC_MISS[22] TCC_READ[22] TCC_REQ[22] TCC_HIT[23] TCC_MISS[23] TCC_READ[23] TCC_REQ[23] TCC_HIT[24] TCC_MISS[24] TCC_READ[24] TCC_REQ[24] TCC_HIT[25] TCC_MISS[25] TCC_READ[25] TCC_REQ[25] TCC_HIT[26] TCC_MISS[26] TCC_READ[26] TCC_REQ[26] TCC_HIT[27] TCC_MISS[27] TCC_READ[27] TCC_REQ[27] TCC_HIT[28] TCC_MISS[28] TCC_READ[28] TCC_REQ[28] TCC_HIT[29] TCC_MISS[29] TCC_READ[29] TCC_REQ[29] TCC_HIT[30] TCC_MISS[30] TCC_READ[30] TCC_REQ[30] TCC_HIT[31] TCC_MISS[31] TCC_READ[31] TCC_REQ[31] + +gpu: +range: +kernel: vecPaste diff --git a/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_18.txt b/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_18.txt new file mode 100644 index 0000000000..f25a9b3a4a --- /dev/null +++ b/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_18.txt @@ -0,0 +1,5 @@ +pmc: TCC_RW_REQ[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_RW_REQ[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_WRITE[1] TCC_RW_REQ[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_WRITE[2] TCC_RW_REQ[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_WRITE[3] TCC_RW_REQ[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_WRITE[4] TCC_RW_REQ[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_WRITE[5] TCC_RW_REQ[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_WRITE[6] TCC_RW_REQ[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_WRITE[7] TCC_RW_REQ[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_WRITE[8] TCC_RW_REQ[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_WRITE[9] TCC_RW_REQ[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_WRITE[10] TCC_RW_REQ[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_WRITE[11] TCC_RW_REQ[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_WRITE[12] TCC_RW_REQ[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_WRITE[13] TCC_RW_REQ[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_WRITE[14] TCC_RW_REQ[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_WRITE[15] TCC_RW_REQ[16] TCC_TOO_MANY_EA_WRREQS_STALL[16] TCC_WRITE[16] TCC_RW_REQ[17] TCC_TOO_MANY_EA_WRREQS_STALL[17] TCC_WRITE[17] TCC_RW_REQ[18] TCC_TOO_MANY_EA_WRREQS_STALL[18] TCC_WRITE[18] TCC_RW_REQ[19] TCC_TOO_MANY_EA_WRREQS_STALL[19] TCC_WRITE[19] TCC_RW_REQ[20] TCC_TOO_MANY_EA_WRREQS_STALL[20] TCC_WRITE[20] TCC_RW_REQ[21] TCC_TOO_MANY_EA_WRREQS_STALL[21] TCC_WRITE[21] TCC_RW_REQ[22] TCC_TOO_MANY_EA_WRREQS_STALL[22] TCC_WRITE[22] TCC_RW_REQ[23] TCC_TOO_MANY_EA_WRREQS_STALL[23] TCC_WRITE[23] TCC_RW_REQ[24] TCC_TOO_MANY_EA_WRREQS_STALL[24] TCC_WRITE[24] TCC_RW_REQ[25] TCC_TOO_MANY_EA_WRREQS_STALL[25] TCC_WRITE[25] TCC_RW_REQ[26] TCC_TOO_MANY_EA_WRREQS_STALL[26] TCC_WRITE[26] TCC_RW_REQ[27] TCC_TOO_MANY_EA_WRREQS_STALL[27] TCC_WRITE[27] TCC_RW_REQ[28] TCC_TOO_MANY_EA_WRREQS_STALL[28] TCC_WRITE[28] TCC_RW_REQ[29] TCC_TOO_MANY_EA_WRREQS_STALL[29] TCC_WRITE[29] TCC_RW_REQ[30] TCC_TOO_MANY_EA_WRREQS_STALL[30] TCC_WRITE[30] TCC_RW_REQ[31] TCC_TOO_MANY_EA_WRREQS_STALL[31] TCC_WRITE[31] + +gpu: +range: +kernel: vecPaste diff --git a/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_2.txt b/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_2.txt new file mode 100644 index 0000000000..fcb7248e04 --- /dev/null +++ b/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_2.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_MUL_F32 SQ_INSTS_VALU_FMA_F32 SQ_INSTS_VALU_TRANS_F32 SQ_INSTS_VALU_ADD_F64 SQ_INSTS_VALU_MUL_F64 SQ_INSTS_VALU_FMA_F64 SQ_INSTS_VALU_TRANS_F64 SQ_INSTS_VALU_INT32 TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum TA_BUFFER_ATOMIC_WAVEFRONTS_sum TA_BUFFER_TOTAL_CYCLES_sum TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum + +gpu: +range: +kernel: vecPaste diff --git a/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_3.txt b/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_3.txt new file mode 100644 index 0000000000..2ad16d9c51 --- /dev/null +++ b/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_3.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_INT64 SQ_INSTS_SMEM SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum TD_COALESCABLE_WAVEFRONT_sum SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE CPF_CMP_UTCL1_STALL_ON_TRANSLATION TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum + +gpu: +range: +kernel: vecPaste diff --git a/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_4.txt b/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_4.txt new file mode 100644 index 0000000000..af59a68d8d --- /dev/null +++ b/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_4.txt @@ -0,0 +1,5 @@ +pmc: SQ_WAVE_CYCLES SQ_WAIT_ANY SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_BUSY_CU_CYCLES SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE TCC_EA_WRREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WR_UNCACHED_32B_sum TCC_EA_WRREQ_DRAM_sum + +gpu: +range: +kernel: vecPaste diff --git a/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_5.txt b/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_5.txt new file mode 100644 index 0000000000..6a4ffa5cc9 --- /dev/null +++ b/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_5.txt @@ -0,0 +1,5 @@ +pmc: SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU TCP_TCP_LATENCY_sum TCP_TCC_READ_REQ_LATENCY_sum TCP_TCC_WRITE_REQ_LATENCY_sum TCP_TCC_READ_REQ_sum TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN CPC_ME1_DC0_SPI_BUSY TCC_EA_WRREQ_STALL_sum TCC_EA_RDREQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RD_UNCACHED_32B_sum + +gpu: +range: +kernel: vecPaste diff --git a/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_6.txt b/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_6.txt new file mode 100644 index 0000000000..13e43578e2 --- /dev/null +++ b/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_6.txt @@ -0,0 +1,5 @@ +pmc: SQ_THREAD_CYCLES_VALU SQ_IFETCH SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TCP_TCC_NC_READ_REQ_sum TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN TCC_EA_RDREQ_DRAM_sum TCC_TAG_STALL_sum TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum + +gpu: +range: +kernel: vecPaste diff --git a/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_7.txt b/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_7.txt new file mode 100644 index 0000000000..d697ce21b7 --- /dev/null +++ b/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_7.txt @@ -0,0 +1,5 @@ +pmc: SQ_WAVES_LT_32 SQ_WAVES_LT_16 SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TCP_TCC_UC_WRITE_REQ_sum TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR TCC_NORMAL_EVICT_sum TCC_ALL_TC_OP_INV_EVICT_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA_ATOMIC_sum + +gpu: +range: +kernel: vecPaste diff --git a/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_8.txt b/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_8.txt new file mode 100644 index 0000000000..849bdbf1b9 --- /dev/null +++ b/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_8.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM_NORM SQ_INSTS_MFMA SQ_INSTS_VALU_MFMA_I8 SQ_INSTS_VALU_MFMA_F16 SQ_INSTS_VALU_MFMA_BF16 SQ_INSTS_VALU_MFMA_F32 SQ_INSTS_VALU_MFMA_F64 SQ_VALU_MFMA_BUSY_CYCLES TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TCP_TCC_CC_ATOMIC_REQ_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN TCC_EA_RDREQ_LEVEL_sum TCC_EA_WRREQ_LEVEL_sum TCC_EA_ATOMIC_LEVEL_sum + +gpu: +range: +kernel: vecPaste diff --git a/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_9.txt b/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_9.txt new file mode 100644 index 0000000000..e309ff20bc --- /dev/null +++ b/tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_9.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_FLAT_LDS_ONLY SQ_INSTS_VALU_MFMA_MOPS_I8 SQ_INSTS_VALU_MFMA_MOPS_F16 SQ_INSTS_VALU_MFMA_MOPS_BF16 SQ_INSTS_VALU_MFMA_MOPS_F32 SQ_INSTS_VALU_MFMA_MOPS_F64 SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum TCP_PENDING_STALL_CYCLES_sum + +gpu: +range: +kernel: vecPaste diff --git a/tests/workloads/kernel_inv_str/MI200/perfmon/timestamps.txt b/tests/workloads/kernel_inv_str/MI200/perfmon/timestamps.txt new file mode 100644 index 0000000000..be80a68d72 --- /dev/null +++ b/tests/workloads/kernel_inv_str/MI200/perfmon/timestamps.txt @@ -0,0 +1,5 @@ +pmc: + +gpu: +range: +kernel: vecPaste diff --git a/tests/workloads/kernel_inv_str/MI200/pmc_perf_0.csv b/tests/workloads/kernel_inv_str/MI200/pmc_perf_0.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/kernel_inv_str/MI200/pmc_perf_0.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/kernel_inv_str/MI200/pmc_perf_1.csv b/tests/workloads/kernel_inv_str/MI200/pmc_perf_1.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/kernel_inv_str/MI200/pmc_perf_1.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/kernel_inv_str/MI200/pmc_perf_10.csv b/tests/workloads/kernel_inv_str/MI200/pmc_perf_10.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/kernel_inv_str/MI200/pmc_perf_10.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/kernel_inv_str/MI200/pmc_perf_11.csv b/tests/workloads/kernel_inv_str/MI200/pmc_perf_11.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/kernel_inv_str/MI200/pmc_perf_11.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/kernel_inv_str/MI200/pmc_perf_12.csv b/tests/workloads/kernel_inv_str/MI200/pmc_perf_12.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/kernel_inv_str/MI200/pmc_perf_12.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/kernel_inv_str/MI200/pmc_perf_13.csv b/tests/workloads/kernel_inv_str/MI200/pmc_perf_13.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/kernel_inv_str/MI200/pmc_perf_13.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/kernel_inv_str/MI200/pmc_perf_14.csv b/tests/workloads/kernel_inv_str/MI200/pmc_perf_14.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/kernel_inv_str/MI200/pmc_perf_14.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/kernel_inv_str/MI200/pmc_perf_15.csv b/tests/workloads/kernel_inv_str/MI200/pmc_perf_15.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/kernel_inv_str/MI200/pmc_perf_15.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/kernel_inv_str/MI200/pmc_perf_16.csv b/tests/workloads/kernel_inv_str/MI200/pmc_perf_16.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/kernel_inv_str/MI200/pmc_perf_16.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/kernel_inv_str/MI200/pmc_perf_17.csv b/tests/workloads/kernel_inv_str/MI200/pmc_perf_17.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/kernel_inv_str/MI200/pmc_perf_17.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/kernel_inv_str/MI200/pmc_perf_18.csv b/tests/workloads/kernel_inv_str/MI200/pmc_perf_18.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/kernel_inv_str/MI200/pmc_perf_18.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/kernel_inv_str/MI200/pmc_perf_2.csv b/tests/workloads/kernel_inv_str/MI200/pmc_perf_2.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/kernel_inv_str/MI200/pmc_perf_2.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/kernel_inv_str/MI200/pmc_perf_3.csv b/tests/workloads/kernel_inv_str/MI200/pmc_perf_3.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/kernel_inv_str/MI200/pmc_perf_3.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/kernel_inv_str/MI200/pmc_perf_4.csv b/tests/workloads/kernel_inv_str/MI200/pmc_perf_4.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/kernel_inv_str/MI200/pmc_perf_4.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/kernel_inv_str/MI200/pmc_perf_5.csv b/tests/workloads/kernel_inv_str/MI200/pmc_perf_5.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/kernel_inv_str/MI200/pmc_perf_5.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/kernel_inv_str/MI200/pmc_perf_6.csv b/tests/workloads/kernel_inv_str/MI200/pmc_perf_6.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/kernel_inv_str/MI200/pmc_perf_6.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/kernel_inv_str/MI200/pmc_perf_7.csv b/tests/workloads/kernel_inv_str/MI200/pmc_perf_7.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/kernel_inv_str/MI200/pmc_perf_7.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/kernel_inv_str/MI200/pmc_perf_8.csv b/tests/workloads/kernel_inv_str/MI200/pmc_perf_8.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/kernel_inv_str/MI200/pmc_perf_8.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/kernel_inv_str/MI200/pmc_perf_9.csv b/tests/workloads/kernel_inv_str/MI200/pmc_perf_9.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/kernel_inv_str/MI200/pmc_perf_9.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/kernel_inv_str/MI200/sysinfo.csv b/tests/workloads/kernel_inv_str/MI200/sysinfo.csv new file mode 100644 index 0000000000..f7a3faddb6 --- /dev/null +++ b/tests/workloads/kernel_inv_str/MI200/sysinfo.csv @@ -0,0 +1,2 @@ +workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd +kernel_inv_str,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 02:29:22 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/kernel_inv_str/MI200/timestamps.csv b/tests/workloads/kernel_inv_str/MI200/timestamps.csv new file mode 100644 index 0000000000..74a6d81e5d --- /dev/null +++ b/tests/workloads/kernel_inv_str/MI200/timestamps.csv @@ -0,0 +1 @@ +Dispatch_ID,Kernel_Name diff --git a/tests/workloads/kernel_names/MI200/empirRoof_gpu-0_fp32.pdf b/tests/workloads/kernel_names/MI200/empirRoof_gpu-0_fp32.pdf new file mode 100644 index 0000000000000000000000000000000000000000..222229e7cbbea1502508122795adfd32adb4bb46 GIT binary patch literal 13328 zcmb801z1#D_wZE&6r}}ehHjW(W*AbsQM#nNYv>RG>F!2Sx79p(PeSKbNSZ zi2>5i5x^{J?r3LY;cUZ##r4Y3&e++=1SM3qvM}I6wFTJl@Sr~UL)pU4R?Glt0$>*7 z1p~p{KnM_yI)Z=@HXx7*^@q}vw=@3VRRjgGOl*zsh5-3{C`JYV5Ehq+Jb+8V&e6ue z`fnxfzm-IV@09*jl@kR3vAE=9{&-ivlgrBixUsmDg#k!MXOsWg7WDtg7WfZasQ3TX z7X1Ii*8go>Jb&Agu&_p=W}i#K8a2;iCPsF~C|~4EY|W7701y-o6%+(GAyN0u2Fopd zM{Cyh2Mo`9QhmMAmn0U_a$o%IRPa%{%Ud7cv^?g`2lBVn>!dpUI?`JwBbx6|$}KEd z9NbpF+V{~EvghB7T6*y%T<86Yui9BsK60hQEejEDoZzu@xHxURI0-uC;-_m_xm+Ef zBui0i6MADElxC-w=1N_3efg4$&3umcnbgIISJ#=iPGPcPNvt!@tpMi6PM+g#?9Klw1r^g6ldy5_<}HQq_VU0Ym*yR;C8HMd*Exs{z(IgDc| zwp=_3158cSf1O#WuZ_PdRnFIC?JIdH)Af|^yr5D|G}T3`zoUqj1EKa*=m;7hPTm7Y z5*fTL9SPYi+~{Xpl<7)WD2}9uy%v3%qA^4#2maFDb0VI;6I7?}cz=#ywk)D`d1pNn z8Vh&{njuzrY^xHQ`kVQU(zK|^bH!>kzN5e|Da5D#ihEe3*!1!l%*iA?Tg@t3N3zNrdqLOPOYuqQ(UGjsXG#? z3ld7j4YEmof*`?r$b5b;v66=QC9AAsxH{+4WsRXPDcZ3Rf71RCX71Sdaym&P(05j* z%m;4M6@ED6*@!4)rRt68Yj!CK&RxYH8eIvIi)dZ@Jl3m`ji{Q z)RcZ2&qK&980b{?;a=#T=wn1$;C`YyduehH!6u@}{P-8-k=69xo-DQj&4M2s;TJ;# zkIelInray$d7yooZHC#Mh0xfe+1u9+3w*d4tout}Yho_>z+_IK+D$2`QGNF%TFA%! zvUeTXXE80nrYU4=du)sBQ5r3JQJ$rlG1=zxSKB9fMZQqwzPTEgm@i{~@$p7+v2|9_ zE(^~#UUBdQfSxhWBzI50Q!G%bvw!%I8b+S6BukG$67VD>Li;Xi;=D0W=s1n z>}+aGhJH<8ke^X(Vwd5G?jI4;!|=sf#D3W-ny>^uL>Cc@r7;>V#tUb91jHicvXr-^ zCZ8r$FlQS7#uF5H$Z563A*xKo&_naQ@`WXyrj5(l)bdagEakoU<&O=&<*NRJ!DI+j zV(`T?-Ceazq!mF^#C(&g`CKZ&TvOW|8FY>{WDa9#F4eh-h|R_D=fbt-^o3@DHI2z; zHQz2|6c)s@rCkVN`9ak5yuujU$z2ofbgN_Fue6~V^15bvGb7o1XSg`JjB^sd+_EP7 zlJ(_Qx^0U7xV}{ZW$DfD-usa(;qHVgI~o3F0abJ9hFC`E^-m_;?SywY3R}_ZZk=8| zx#6Q<5Pu~q@=Z!5!$(bj;6NujuN}SqW5+4+)XmY`oqQ&5J+h64U?d|ik*L&|BfZI} zV~&^$YdX1KX1ZkTd#2`^*qXC;29nDI65kf1-buY}h%m%4^2Mph-1SIW+faAq$jWDW(GEJJvNgN&_G`5l?J%mIb!(+Qnu}R|*D%k`|BB0WBP4~H>!n4< z_ivSJQ{`DBBxfdG{o5Z_^{SpLA?}LpUlrr8vJ3vZ+NikOn*g|88JMApjFO3yowK8n zi4y>|H9&0xjFe4~0PR0^09-02Zb$%^v<*s8oE=g{{UG=^@g97eq@7)<3a925%Pz9b#!p;_X*FpjYfc+`ElggVITNsGgxdF6+ zC?OOK8*vCEGU#pH^o@s4OduF*WQ}m*(0V(hlY4FyL#Vi#_ z8Dq6rnHOI%hKhz_Y!Y!pxzPu{_OU2KXe<0uCu6xk%)WQAgAd9KVu0<01~|JG&q}>< zaK>BDyl*{(_NGf)+pYGX{6jUF7B;Z#06ex#dXdZ1K@a<#-XG`zujuBT1>E%1+SQet zzkc>07m3fr#g>|z7LQ9wK;SVIvol%Sd)qbKi-PbVT>Fabb7Nt=kA5X$Z|~$ zhRbnTMG}tG!zY#)6;ckyF3#;KCmeiumqLn`9G8+9xOz{s&#yY-e|*5oTl&H+68p_y z?#OsI{$MzF_ZnwQe(FZ9bF7P$BP%8*p!W6^KUcC~+xzC#tVgqYbYjH(k1e8)GWZ$V zn?spA4$&_Hjbo`Kau8gZmG78&mgNOy$Fe$HZ?v|MhWBvkZcii!d3H;0=N0y8WT-O)|r)xaD>N-gd5YaFbqYT^*iOomeP^;NmPez(@FMy zUUoX9ym$w;ELh;qEEvf|-Wx11vJlLW%gP(w7(FJ{l7^4yAgKjJgbK1o_tv?>L69eA z2kZ$a#%LNa@`1x?<5T*yZ<(e;l`{1)JBGif@DoFjMEaT``D9PZiQc=2@FaG!Mtp5h zfB(Nf`cY~kaMnfc)!Pz^R``yaO#pPkYA0DZ0SadCd}_TZxL3-+YkZ=pVj zz9;B=zHrZn{NVdN!C;<&D0wu8c>^CZIe$De%zgi0>c_u2gM+pp)4w$?CyNa3fw!zn2-o1NY4m z;fMLI0jQpLIN`6M+v6`D+~>!2@VPf6$xq{(CBYB!4a0wl^^2e<4$bZD>B;xc5v{5% zcn5^Ng6!yQ-c|g8CLa0%bjwZ?G?%PIlC(ZNzH^7T6WNz=)%5T)>c>CYF%S0d`8;z_ zyB8(G&+hwK|EF~w7uL+NS@vvG%DR^d$C>Tcanm8YneFy* z)1PH9XUjB;k24f1v&%+lAID)YjndFu>tf{h3T>j_j5b@QtyK-u5D7R~T&;TpG?bX0AgV%P0jl48iUVEviWNFE|jYDG^j@mlGfYcVUk z_y-rFEWqWAE1JD+IG8@i^;iE~EM1PPuU(WIErj2*hfu8SCAf$1@g7YVBxi!juouQo zJ~WCF-)=k>y|o3iq)DdYCiBT@des2+JlUTk=J5ZjU6kpe0vK1kk9a5cqgWPzHb1K=gAz2z}O&- zauSL>(l1F2yWMHaz%?&uy<^h}}eqDZ$?zgiH{zi*jeaOO;CXGL` z_+D8W#Ab-Ql#zSL5`MMy%8{v$rRi;^#OCR+_%gdY75zk%^?S3J3c}^*)sLz*K*h>r z1Cp0fiy9v)Z+VrN4Q$0u0&3`6g2t9!8;v{B*Cq`We}*cBL(F0ZWy%)6_bjrD7;0}A z%)Bq{9T&ik>f}BT=S(!rw^0&O+D*E*9PLQqnX#U`Jc{UR<_Yatx2}&D{TOGLPcf)L z@mru1|6604Ksd!p9GZqHo7!>_pUzX+7^MU5*z}R7(XmxRk?&I~Hs@5NnBwq>40e@8 zXG9rTKF6r|Bz!yMnsRDAW;lGUpkArh$Fd%AnZ%_du1Sd5*%Gon&RqR4Jl2KE3VL)p zRC0<?O3n6gGG;R$pt3lSI3WKVDrz)-q$+PyTzQ-Sgb!w+k91 z$g?=@_c2cR4ATerJUK5#cHx3e%g+xVFXiO4I6Mz3-YC?W{SX_1Oqdxq3m8%Ulus7) z5a2K{r|aVCxmo}bI8VH3k(vjXnFGC}GmQmL39S4cS1LQod}>FeF0=EiEgjSws(P>* zjW4|<3zgK9FXE|v8Z|#N*UlGd5w+2~?y~MPe4R5iyw|ft?oSlO5LhM=ap1E=cEV$j zYBe+Kkvv(F*e@}uV0rG=K_VNK6`~!H_TMVA&zmDD~8B{{u48@U7869wi%g{pY<@zu9kyWk5>L2-Y_yn-STVu4Y!VTPh-i& z%TlQ-Lc)#h8s?$6I@7p7UmY4@kD8Mo9h>h<7o5d@Iu;HDza1wgBGgO5Pf{Yc)@fdR zD38seVxSNtKo85zcdd0b70-Y2oTI$BRHH_%>dm01Zev%o-c2Ue#o~i9yN(Okl9%%M z#Sg(SiLW2Bd-Rk1Y9Fp`Ib5GM2wQZzeDJq0;_F#BN_ zF3lculE(@5ZJtt&qB3jTX4_^TUOI8A1~ zN5a?^HcMd}S;>_@Go7J1S%k^V&S1N3($I}nsK$rt#4sg<2M*d}nyNNH{uhPf@RIET zQD;usXASB2**v$-Rk}&#aE*$B? z2iQd;7IUFbg44)K%^tAHeZqo|{T7e)&?&?N2Z!&}`-&Up@=DGwBkfYLSH5iAyLmwQ zCLPCorbUN!TYa|TVB3Y_o_7fMJ%mdPc3VK@{-a0E)5alF#+qL$+YGghiXBV4H2Q*7 zhYIJ34AB`zX1FV7QlOQ*JX^zW$0JK6V+im(f>OQKqX*}qF9s6xisRijhq+>PYQXhy1$nVKtNV2HW}AojY9b zXPftL>!#w___}K|b<-bj4l~E>=Dn?Dh3Rjp8ug;Kbb^0;q(N`P=^@SI8gG;p5LQ)C zPOz<8EIura)X8UewUv45f{t$=(6}g|_MGPjFN5ME8lIAbHyK}qu}Ndt^UGG0yMCx5-9|$ z_uFxyom5?jb1SkyQk3;DhqDy<^!Zt`#z;NJ2yt8~elpHr?_euqGGmNe>cfn6{mbYB z8fDn-g4sx8Wpb)Li!(Rbh_!h~y@ocDmpNTA^V?9Szy!b6DNH9oS>9sSjc5=N&Q^P0 zof(%Uiayu7N~xh&%`)O?#RyMvsjPfyC_9j2(mE2$K~bO~c)nOnGi^O%%doYZTI*fi zF9OZ23M@2Y;_!j)t?LrH^eFkhbRNp(aufU#2db{rk{N8fNvWlC(wn9AZbC^akE@fV z&wA8{GKpR;d~d!PE~vNvX1bkTLO8tql6kUq*7GU1b|B_bW<0AWW}&SC@Ge;^qB^?8^YUz7{#m4d+n<~i*PL2=Li`1$6#Xx zAq|XJq-#$SY@U)#(H}ntmt*$57%pNXvl{L9fQr!He%lE}C%b_KicsSe(2%{R(_Z7G z^EzD!XT{@mP59kU_&!yIjckngH3^w)?#IsT)d~gW`Etv#Y;wm5iJ)X}(JNl@;39(|YTbL=HA}+qtff?61YO1lv2*Ioxas z+Z~oL+N&CW7K=Youh4BUC-St@(VT92E;}$`;%O-}f4SfNQO1%VB>6??dNu9kK-Bji zq)(oI>+mD1xrbmCjTBLh2pMnaHfMQUGGZ4~+&7}{n&7Ou?^w~h5{eT_3j%S*6$7Pw ztmH0JZ+{eXb)FdP1yYCdEb~6QuvKZ*u9@@cxGAH2WyD+3WP=ONEss8qq#vwc03FmO zaKv{e`A^`A32dkx^*p~~tn(3nJ9D0Pb@=|I*6c;nk3xnqv7PBC#ep-uQGIB7>sRUs zLo02lv>SDa+mm7sY6162SL!N*?@0`dhEMA@gkM@eZH>|Oe=CU(cZPkp`h<4;G8Jnf z!#IQ3m67)6c)v&Zn-dz5Dv#H^qu)2f#sE%RIoH{$a}TNTm6t$DykC+GvWZQHHEM~$ z>0fEljS<5Zg^4WhjrbL7fugdDh^K2VXN@i}7v zV+IFmxcKUs=;|UyCP9$>nyS1zzrFr{+3XVtC_)7yQ!+xBa?wdF4K#awXuy+ zta>UBrwxgqwVtEBTeL~cjf4`kW0!q|^gA4uI?EK*m&-t9R)-Dx=G6PybLSzVOXdBK zl^#DakAZ8oGAcD)^2&d(y4%$*zM6SkpG%{Cp{3iEwVJSw z6;NyF;6f>VJe`0QqN;y$+N4%MhTM(SeY7gq`bOz%t0g-|x|;KBP7jrT%pf{@P2**Q zecyFG+?BYkxN;?jonMT8WAg|P;ivXO?A^pos7+E$SBp$De<*%ZS#CTrnQ5irzPWkR zn93fUAw3`qABXl+m?G;;fmGQy6)b#R*sBeC%2m%~Z^qlEP`hQw2AKB}QJkXny*6BL zMd&-g@{QN5W|O6r)4_LxV|3nkg3@~HlV^5Dj^}z8l2=AI>J?c|jeL%_fE_O!8+1<{ z+9$_Y)f}$Fipz8B>Y*yC8~Ax+#;FgFl4qtz#GZ+tM%4^OQQJid@1{-GwDi)u)Hbpm zM9Hg{OgjX%E@LwW#)%yo5`kh0N%K+_m9tpHPy16GBVTj2v$Gi@DTqE>$zg@l$@e-K zFP@N&=Vx=SOVEppvB!{c=ba;2Qsv|y$4kX#@tASPo_s6-@dT#YERuwhe+I_3pY!_3 z=Z*u(O|%^D7mRLwr(Aa?^}t5sh=$i<)OvDzXjU}jWqQ#6pjVU92*eBMlNPZ}Yqva} zc@bX30({~>gkiAFTi^-~Vw9pDT7*)`x6J466-rOOG(6IXF^y~s;22{ct1#{)fWE+s z@YR^XA*i)MQd;2lO+Yyt-LR zPJIS$^;20HvMJUr+YINLh+3X_-xj>zV-(_Kg1^~+t-0Z(&E?~AQ?hDPh-Mg7htCl6 zBJ=bFNSZR;k@G`Qi*j^5WtK7_8!pz!z{K!Pox)0l%~}avb4kZUd!A9o&R)`7N=_`f zv6b;F{%Eg9ITeG;W221Cuu{t|?~|mG3A&GCT~}yb9q0*NehL<2RIY}Oi=rVUnB%Xd z19;D<>6iLzp_i!t7QBp{KAhMtb85dN7aFRNyQ#`6G`QTt{4zo0?VKKX#lJy)xO&Fx z%9;YTZQ*0z7!}C!iHW^3$ZC_#^l{AOtG&*ql;r&Ml%<=4BX9-d0rjMLt{^|0Ny z8Gjok~B%Py>846tmg~Ng&ucGA@e^ zb_vQ>4;oIwHWzeE^^v(fa5z%D*dD~&&_*iN=D(Gc!D%D(&R7{*hAvB1Pvr7R?&LRk z##6v=zquwRg{9{`s;g{O2_OwgqUgw|n8nM1#7&CC^VSS1Z_ck3hn3ZF;DTcD9zi#1 zG2rHu-iyP`3YivC@+VC7C#bIo*;Q1EM^f7AF-`(01StdwiwXyMVjp^rW%k7{bG&S` zK0n_H>kt1L{sn2~0nUXOfeEn)h$R!n6B-BjO@_ma)EHG5Udsks?##>-)rl&oMDl%( zBh^!9AzTm2L=X5^DmWGb=unjkotvZd0gbL{!1rIjb8 zM)i@{k^C23owOPztEzU}eA8YQ2 zYTBq#tT(^T3*&ma8BVODQ|Q!~4>PnOshXvJ1ZADsZ;Rb+$&kQVG4tS%i)YO`y@drr^Vsxb6K|r|;+F(M zjj3+;#;bd`L{Vss?z7QkG6i+71K1h@4f2w>{NhI#VjIV5#q`YLHbv|Yx}YwE8*A%? zwl+=iGn<+hCnXbE6b_&nF2(LuZ+<>h$7qkgn24dXGil>K z@8rl$9ZsB4Hkp!O@itQ$`K0`TlaawDDoix+>zG3Gr_kH`*|niDte7DH^fsQwye6d` zg6RvggspJo8}p3TiH09U3&vU>5}z8o$WkYzDvg)eDLjn1k^kxZhB#}Atr}3xdf44( z730V?5_W3Xn%+vg?2>A1Q(d0n!5q^{6=tH{UVl-v<{f8pK5+(|CMDTHv zmpd6=$n6GP>b1!W#nh=|qVch64%vzEl`J?#AL3eah2jXqRq;?2?Be3V?IWLiH?Hn|BZ1NgsNIaL)+DNYpVsUI@^ zy#6X~NyTYGBTbJ3Kd-3yR-dK9Wxgde!`YeCZqRG((d>^alG**kK>xI~foGCOfd}qF zSYd9M@4%RAM0-wgUZyMWj~Nji#>ELzdS!J*L8(PLmIT71#YY=pXGGJ3jM7!Hs>M&A z`RdN&9BtKDBJHGoqfU4-sk{|))Xq&J2KN%se&;l}cPF6G6>o52ZJ+*y6p8Z;k4UH$JlV;Tz zBi|ofq?Vq)3w)qVaclXgPlhn$lt@(Ka*?Q+b4(;&Dq>WFc;oF%Fq(lHc9mwW7Q<*k zopF=MFz8cpqa2|rWV5-SN`O;GJx((FQQQ0YhOZ5N4G9jaZdVMuBCloBaiF5(=xZ65 z4%&+8KH}2bPUZ{bm|F!y>_4^O-lw5u&d#mHYhUN?%dQPxUa)1uDoUSQcEhZ_4!F`% z2lCQ&2z$R->Fn??1A>uF+E%z%RTH|F<1=%JZ@B5(A3e6NxIDrLpVXar7Nqc0^a*3? z<7k;NIrnPC_|I^NcI<8+rG1=jo6wEuNCkXCTm z(7{NmLTfs333Tb*ZQ8xu4cwLR4{|f7u*$VFGAEDUmU5}bwj~_z%~+QXkCbH|Pa>0v z$Y*RmX9609>Vkan<@7P0XwW?EqIvLIDUXu|QKi0^+_Tsd+mjHY8Zt>B3UW_9osCxy zx%U1t``83?0K<;F5xFr1ZQcC%# zFB`Wd)+)yc9P5~UcpGMVJY;u%T@#EE`D>RJ*7G5(P(QcE0$-26a)0OJkS#k~9DLt( zAgv@3NB8XTGy8}1(`S&M12v!rYj{s|R-5&5O?b(x)@?8ZXozbDMc5hBhQ)e5S&xt( zOQdza9|Dph)eNHte%aJ4_>NnHH=VKY%EYTlN*8ZAE=%8zYn>!G0;&V;gaSx48Sa0!SS?81Vl!HrEk@{E@LCK{B8p=&Y?Kd>n`lC{FQrE`bDMdZCGscsI z^j!dQY*T-R0NxbU>Mt}NL7fIq;X&F2QWTaUl81dE4eBSGOHUnoA1Z4*X@`BDNXZ*T zCer5j=^SS~%?Q_#(;3v^V5$Ed9CewD>lOR*ltnP&Wm@)D?wgLWpFe&s)|kZ5ARm!q zq$m}nmpvUdwxS*u$e}hRF{Ln|GU%^e8TEoG3ib2%#~QJX2%7kOsgCE*)wb5Ker>5` zscY#jtZq;UEQeIoSi`JgyTH9lm07_`oyxkY-rU1})6H8hPWuSEh5aa*o5=N;804KKf#E9Zw_^%Js)J@bItl3yV|!Frx28I$ zS?wwJ;6=UF7vDU$Y5TiIQYB(*e5tbTu6{b;cgr2bAEdEz zVHhPJ9J}5wv(*P;hQeZpb4)8GKWXuc-pUzK7yTT@n^rijDyKbNypHfGMF^jU{2nnGxuhiW&@W|* zDZ*p3K8GJs0M3d_fLPU11SwMCo4@Ct_pIr}#-T5%dYxs{(0!T|iN$#idiV5^zKoyr z=X=C@4{M+3H!QUwF%zYk9UfNF3VH!r``y4P%dytrxTl}C;_~ng+`yC-i?ZoVAwhYu zIP};oLmihYhvz!p{2x8$qK2^gD7FzHaxVl;3-$KG=|VOivAE^YkcDydd{mFycc)3* z;8EjD@r(DAdP8AG@ok0XEQV=+KRU=RLbY(BcS-d-?8%V(l+x`Rpw$QM8q)>28vF8o zRy{%$UdO7T+qrO8Cn22K)#BU;bs3eA;h0E0(SVP-mrelED;FA=968LM7-fb7)%$g75P)oQOQ{5F|DE`(R-f(WbE zuJ2KTePp+p%lT)obEME!MmN*cRosRB=~uMF=?nYS`#jeU0bZ%ypYiwcgK!aE9Sao{ z3aVZGgo=mKI7~Ue+*m1=?2W7B1sDC!{IWB<4RH1x-GaJlaNaD~M|aOs;Mh+M8DwE^ z%CtIC2Fjj3 zmosGh$3lYZYG>q*i+j-X`q>32{bilRRPTZ+jyA%&s@oJN4VJnhUsO5#v|?G92v$@a zkc6;y>kl5r(FJ#1KJQ*Wao=C$Ex9rzDXr;x;^CIrJtGs>k|>)0n6*+_oS{_HCULU% z?YOC1Ilfxi53Y*E%4)Cp7Du5{_LwhOCtp@_-~V6|*m_4qk;t_L;99FJMdSCk7IdO! z*D;Jv;?;j#pzoH;jw_?6l&`B{?Jwk@QTv^dYq9b>#uJ`+d*;<&R_-1*UKbWPM{C_J z{LEh*zliH54;bJCefSETeN=M{jOz}UV73m}hya%1WAVtX?9&G^d5#h@~!vgTAuJJo08Zz9En=o(QC|Viu!^k(@*gxIS&lnA9 zUJ=Kqk==?jlP{vAU6CG-X+yZ?0?fk+27_TRER@=xA`UPF%E<#k z@Z3?oND~`105|FybqV1?@k9ppQYIE==12ep%ENi5gwm2mAww2M!nS7CCU>~<-AF|K z0Gv2LKroOK3WW23036&fFv<)N1_6NJ2nZ)P6b=A^Az)5!Fo=f-MLyj%LqS9)V89=g z(H%kc7u*E;7m)f-y6H~$&lZ2XjIwq|H=)RA11FO^g@5;4+1U{J2Ms1FEq3?mogpyF zA!#ucJ4tCVc>{YC@MVme6APsKA7W*9CzSWnwx)J>440CLnFR_na|bXBqu6c}6bSy( z(b&Y%!qyDH{EucRp|Z2Ry|szW-PEFpCoC@YJIYHN1_W{f5pdWY1qK8_KyXeTI0%T) zx%2c6{z3pbK@b=mLESPq0*tsL+Tc7WDG&ic^$mn@0>N;Ug*$Ix5N=L542rs~ zC>;pOA_M|OpvLjnh;#rbueG7TKU6{gF!y&OC^v$W2gnV(1I=I{D9R~RoS}jX1ybC_ z%^w{=IN^7J0|3KO69>6-^UfgzYB(V1ze*7(*FY#*AJskNA8lZ$pZy zU4bBAR5(IWfr&uCP`VHVs;|5F)VaJ7gqm&!`)Ex z|F5*0j?#dwKM=3wh)A#?=n*iGoiq2tOH2?ZuWzv`uD3J#9rp+{oUWwx^bZdJ0 zpuD@9S5@LA`<1`N!l>x_pJUE*ngRXGbp*`wQPJ8QhlWe+N*b+%D#;YUY5fR`&)I_!D<1*cWiR!Lp^cmEWPXV1`;zq{v8_O?LGZKDQU(x;e4@>kfrYmUg<=$j`h#z-3{NT{1z|R-zrotY) zhxhm`b3b1GW7^Kg8Tk1OIdk_*Ny715;R2tlKM0K@?r~+_zr~H_2F2L4Y3SO*^b;we1*YWx~NT-iKHcF zqe9UezBZS4GnL^6?wn_&10_yAE$0RH+Ppg77uGLjN1Kve8hZ7uE| zVgP{tKtcabT5gUerdUAKGYwe4f4%@PC=>z(m;(MO1EH|dyBEOrA2Kiy_FpnooTIG& zyB=y~qhk6$WMCL-ss5V`wUF*m6^a6P?d(tp>)rB2CHFt_@!ev+ Zs}D{{14rZ^6Ac0*pdc&;2Jx2?{|Dl~(mVhF literal 0 HcmV?d00001 diff --git a/tests/workloads/kernel_names/MI200/empirRoof_gpu-0_int8_fp16.pdf b/tests/workloads/kernel_names/MI200/empirRoof_gpu-0_int8_fp16.pdf new file mode 100644 index 0000000000000000000000000000000000000000..27ad9f226b87185633e4e9b68d0116ef0a87bab3 GIT binary patch literal 13142 zcmb801yqz<_wX+&AV?}9Ar6fK!z439Dcuc%Ajr_&NDD}J3J3^Fcb8JqASvBQcX#>? z-uu4yjsN<8-#3dj&og`W-skM|?6c3FwSF)wh=_55fiQgL!Hu;!d@uk6u+lZf=i}oN zwlzT8TiF8GgpF;jEKD3Mp5SvS*jnj3=ow&y%4Q~LE{rX}0*Si4_aja*g+0K?}}76jPaIvD)VzTp2)z97GSVc!2& zUx@z?U;npxA^-LzW@2uSS$!@sbIdx680cB)V`7mpur#ta27tMd5CH*zojvBcS>QV* zZD~%1O>&dCkE*SH@qB3O*L+WbtOHo;ELZdV89-KvZ2Fe$ug9w)Y@O+xow2gw#$_`d zr4ICcN%VczZ9%s}uJVR2M{_pWU6gPp!nt~8LzC`2s7)P-xIN>3HFS9{d_kEaTpx5k zNt|-ZGWdPAZ)fswZX<5F$JM;ya;gP84D83(XPKi~66R#q=Z;RjChuy2EK?(`VXxLM83`%|ew+ z%f@hNJ^QO_X>Cgrnf7(=_CF17vyI1_IR3n{s6*^~2OrR`tkNOa2V$~MC^CeeeiemY z04?yv2C^cpGrzesYdH%%aZje@YpL;HS?-C}TbNkslTmv7Q&tn;{MO{{V%<{D-f;wX zs7ABq%p!Gv!j$~h!Q-Bq6@z$OL-l}&&%42BJo0z@i#nYI>T~SiW}DuY>G%&31l=7* zv=4)-z-i7F15cyCO}nL5%#_r~UJxmXpdcBWt4(ACfe7EeSo5+KEkmyvqBquLKZ%yZ zm~`(a=>##UwV-H}=(=1t?Kk~{6$@&5q22;U-_ObKLmUJ&+1qPW{S>jzE^$ZFC^#-&&&%~YWgha++|6&R z$Rd-+Uvk@i>?Dyxg%9V+U_vfkGKy-JI&xhF3vv;Dx7<5v{~?#9x)s5vw=x(}%r#j} zPd;nPxMI6LLO$-xJprc~eX!p1!nxOBWBJFu7g(<1s%RK7X$pmJ3!~tLYPw=^~OF zaR9tb3-SGf#;J@UCCAp25wBF9in%L^Wus{>(;yT0#L>!-4QIs5HQXoJM|{S!DywX* zoK>a1rBdM96*i_x_>>4OgFeI(nN__*ARq-t7!N>_o;zF78l7<#B^A)ZYqghZJ_fp_ z(6R`(Aih_;@V?y@n+u?ui%C*u1aS~WxSx+Lt`MK-6F$;N;o%3IjV+$Cbbp}oHjp8E zJ=K%6wyd#A;j&@)*}+cC{^0nH-H?45)0=xCj&?I^hP7jX9)m~GC4*nO$5P*ybZuAn zbx+XF>sz6Fjjh$jv|mL{$5+KUK#yk01=vE9LpnGUYi9x{SLAxQONW;DnqHbw$fPWp zBo8uEcJr9`R&;JOaPfI_e}5RMHn)vF7ik+&OZ5&RALHgw)fU}S9m2fvQoxNad$7ks zQ`=A(ORs_tnVVkxoQyE4$DhnAuEU=^;V_@sQUpY2J)a}mpS}u;`!V**@GMVfHDO?-;+NvOMwGc=6khtf6H-kY z1+NHr7~9L5Yf0s7#7_g21{OXeuHw0{-UDB=Q0w#EUva%2xY$=sz900rhHu~z(gopfnu&Fp(8vwWz&_nf>*&n4<)FRpBV(}Q44 z#i4+k9zqG9OB@EcX%uem;DDQB{^kw=xH+ViFueqqn3bjdjfEIDfcsC`ja1e^-vljW z38U@N=2k{G;}~I<>OY17 z|4SqHXMX?&fFTHOBqrGZrH4QwV2FS1A%f+Ud5;wBR`~;X)Se#7o zwrBtv8S5-K7eiI{wI@+7fV4~hB&If1D79H6q(NsKw$$j0y>>5Oi$oW--aXXme3snc zaq%S9hHt?A>5KT3A0Gkf3r{#$Wj=z98eMn9r@WTBkk?7LMsnYShg$3Wwjy0@oy2C| z39b1+f+OV4)Q<&X5PG)ey#=$nXIx{~GIQOjD2vC@Ha_-rjN6pG$*;!5Pq=(OQj##- zOZI_vWKGv){CY#~sIrebOVE$3XGy(KnLP@>+XkT#S$Z486|Jc*=TxLN^fz0(=>C`NF)ktQkS{wqz@7VCq z*StFg%;y6Hd``Ck0wJf#fVbp(9RPuMNM6sLX6qS6Eb8uN(r}`AUeZ~b7DkeA#j-J8 z^;3ca@eXO&Wn0?k}5t1KP3oI9g7y_so-auD`h*Gqj)t`Ed760m;EmLL_~{ zNi;17q$}8aw^|-}JJHWe3SNTdF9AR?K2!iDJ@D>)Ye3eWJ;s1692>lO6Tw$OPA()| zKN?7`Jxx6Q;uzlc!y+4qnOLUEz1hA<{tq&c)H=2br$L8QGUwB*E2d- zoB{23_S^%?ypgzj*??qEcX2a!#s1|6{AuoP=9bzNdy(=4g@dkufX_VHXF7#7Gt2Kc zEQl@(dp=_>+E&U%6(1bxdPoaou_~Qa%?|EXqTG~e#xK8);G7{EK36#3nxq}>PeTmX zWgcl#Y_@mY`617>d&frnarsN+yru_8xA}3%>2eQaZbM~wz-k+5W34QW4a>1W=27AE za@CD19apQETW7*gK#LzQ>323AAxx=`yS+V8jH!+hRz=l}(95GB-hhc6{UF}^BlJzL zMYbGULLQA9Uw&lX2Ar4i5^U8(-t8MDe!%!v=6PH6D~6ngRCD{x&`enoD;^ylp^#{?1C)`JM4L8J#-aO($~Ad;|x#;}ur|ijSHEy6LeR zzJTI)#DOW_%xG-^CJB)~Fr)c+;fPp{B*$C5ik=HSE%o;%C*JW4Vxy=%hls_cFhQp4 zJniMyEH~l(wX(JhKU*N~0XQr&WsY_NO9QvRDS2h0StSW4#bcwts2{NKOR}p|=1&R& zqlt?RP$;|_CL#YQ`+Vj_#-S~CSmI_o*hP_bD?^!yAvEGx`b5HEKy(eZMo%u8mGLSk zAhVgmxxDta9hcL+qgCWy1dmG?S)}(aVR|###8aPsDfzq1d^J7*?=5ev0ND9`E zl2Yp68eFrPSoyTL*#HQyq}*W7;qCNofRTQ+Y^A5$V$p+NKP%xMx0Bij!`&0{sPuVKbwliqBY_IC zPi>e&UuXDVLXW4I+`ahJ28K6{Y^iZR&5%pPDU7s8g2Wh#R>@x85|cD4Du_MvTO2*# zp<8e_GB=OwZD4n?;IZQD%!P9uj#N|_ghr+=mQe1w?x)AWPrk?#VRM4bgkatZ71L&wH$JK`46u8w%>g8b-e z-sh9j9x-j7dvOMo7e#IT{04Z}o-7;5mr=yua%GBB*{>O5Fw)cTUsG+(JXB^eUE|^j zGKnaZVdB4dt@JRH^00v#M`yy!m>ZTiJ-in$pi=ZuoNAQ1fvl4Z?b6QiT7K5_A}X}V zwPAOn5O1XZ8EN=3jaATe(c3Y|6l7!FIM@k2{MeA~wNCA{M+8cALc-d47QnD`RctEUrb`NI_}kr>gN?Yj=Zp zzCpgCT#DyQGrD3&Rn!V*KOyVquYlT%?m##3aQC-i+^{*fN$dI#6K-@3s;tX{in{g^ z^e*oXj_UR?zg5;g6U9ZZ&DZckzLr=Z^;I2u_6@qo#2@UqZrjaV)Z9BP2&P=4L7EEi zw@ZydVtlUt7;j;cVwz;lf?=imwS3h*c&W01U1^@UEAx1vPrFHUQmq3b#wbzkb1*HW zl%V9AUNisf`seN5*4%P~QgtDdnfRMZGK@ zT>E3l1i6I|Z`C%qY8J~HdPz1^X5MJ$igclw&`dLrQ-_cep(X`-s@07ap;%SyPia>g z7)J8;q@uT!o`&kZNo3^jL06Tuz;vr3Pmz0FFDzZoO)dql4&kOh)rzzh)N%xS=d;e9 zbZ6Pj+fRgMj_xvOw{!$-3GfYf+P)+UVe& z*tgw;)gLP%9I1yG-;@st2zh5+r4<{X6`LV5S$2H1OueFk=Z;^J6Oy|PqG9_{8H=tc z+(cJ=9zP+>b1Bi-wM+fG_@qDy5ui#nA}9yMR0peu$h$eX`B=v7V~lC z@(KCVu?hu=3@#)KFF&zk3{G9H-h2MA1ZHb8q;w)z3jLleZ0pt`BIY=d_PA$tgkC`I zhrwamnn_ew&MMhE%k87sIkvXLTHX})#NEbs{(T{52|Tznl#NB36BT9xT9dAAe)I=< zP^)JS(i5XrQw?>X1P}iytEMBM&^B+BkcZklzG4?aGQ>(EwCk0gdRDbr?Z*7*)4W%j z(L&SocaliAiL?`GlIXmnn0!bQrh6L%7an7KPBO?SS7x@chsstK0msXIlq56W3cr;} zX6;LS%pOTgEvzN?gu75!SBwBM@aT(FCKZ!@{qE66kKHWTAVqo}If{%|yM>I*ZGFbZ{>?=mF2>iOcL{m2p-7hTE$p zi)>{A$AkMGFu3=JKjNWy4;|nTUuGOrr9jOe(kwl(4lMniTA%MB*^ge>#xd*_t(fceh^=9b_cpYj8%pL zGrZb_zCJ<}^Uu&FV&NOb810rBg;#~expS_}*-M|xX$#xUwvbPRu*ZbQh)3^TJ3Ub{ z;wlprA6ZR;SK>qS=%u^!>?d`brc|&IiWX8K1->)Yz)G6U&$62ouNX9&nM=G{iQ1Ot z2)%|$+uDKpaA!ebxpLbnZBhK?8(lC*oLMLuZMOW1&WWyPrgyAEXOr07F^!%NmXo4 zc_)Bd#pk-(U#3Y^>g#~_=rsJ&-_`Dvc-FnOVVGb@NJ8KR7x!niwc75@quAGT^8y2!Xx2m9NjW*^BoyHT_Y`FB?AF)5%TwP|iEk!Eki<}h>Ez*RqyqmnLw~nz)ReCU( z(N@B3s5(C~WUVa3TE*UI0snL)_P{bURH~u^2GcSz9=J1EuU4VNHI#9dF`*I#beaK&vOv^~nZT-_*omdhu0u*{*wg9|n7zQ34F zi^3m;v1qRZellQ66`KYQM+7Ozhgw*yK27P}3L^}px3RG-%LGZht&u+u`ZZL@^_h^= zN`x+yXI+5$N=(LEysFD)Y%lb-f}V@<*R8uHp9&*FESdN}G21*c=GA2L=JK5)?${3b&^PNO?a}sjK!nmQ-WTk2ddL=oD$G!FehA zYm|hAEYE7;L*^UJbkv6p%Bz#Db(Y<+YIp4i8K`R+_6kT|Z*El-SfB0*Q(l0e_>l~j zH<=XUm@$u^!H3NL9CNIX?G%mXCiRwH^+|;~8JVnO(F&Zt*xhjfv;d0varE23Gp9Z5 zk&P?zf(I{>-g6d^7FVG@#O^X@r?lH-!RS|9bldIbwysa_DrHdT(n=e@KY!P5IaC&L zH(Z8eTLINHJ^Xx%=n2Irv;bS{%PwOAyT$$QdwWGG7Ve+TInyben@lSMpZ5be@t`O{2G64@9 za8NVGIojnql}wgQ`FvpvPx)Tvl$>O1AwZa=Wnx5K>238hBWPTts#4QQySL*IW*>qdeV*Hj_1yYjdPxG(6#%v2C$_-(ECHo>HL! zO75!}x?4d*mNFS2w1Kzp_CVt0A9meKuZMRz-GEw>?a$;Kp!YOi>`Py|QVTsI-sF=W z-8SZ=LInv(8uk0HMtkF4=?MXU(RhS6^!-}CXAL|N>uD4T(9RS)1edQb^W@V+Hs9{JRbOv+6_ztscOP$d*hiXuqdHNB6RAm0{2;CYyz zWjR;KNH|<(L>|#S$kkF;Or5)`{Bx-Gegaku-&dBH`&&YkgZC$vIJIq~;$R&{nuoj6 zcBPvp^!H7!Z#l;HH-}pyU#g%aRDbG|qGkQ>#&N#V+wzO{RVcFGl8Jn%0N?T7;d0!+8`=MWlNbZQ=>cSeJOFDG|Kw}}06 zlpx=|3K#MamalqT2OJCW&I|V**h+28KIYOo=O_4l=yrq1BaG9X>WB{ zr98EQZs_U;OjCdG*0%Js*QJkY3MpcDNO8Eb$zH&uP`G@OPb3|gKR+JQWu9B-^B@Vy z>VLDtMF`}9qc6G+9QiJno}Ff0&L2LO3Qja^u&#E~+lym09+MxumYz9&5x$*qz#@Ar z!sKE9Gp$cqdFBz)xRsHZbKl1i_4Pts4|nRBg)E?HH z(8bzg`TDFZdd`6q@)gSxb?T%^Q&G1MQaqt_*mGTSoSj^q!;FZ3?y z8b%*)gm(q?26gW1JD2H}&6nQ4_aII@u06)}d)-n=*TM+X2$Qy4h{?{xOirD!rA#5~ zXd;c~L*>;chZJqGZ80uVbr~gd2(iqn0lMQ;0#Zx+Z>LZAkK3SfY`nIXeNi9eM@EN_ zp4IC1b&iowv``i^%cD;y|R}yFK5$KF&Rq8PGBqfQJD8cX|y?`)!Zwd4jAUdv$3StuHEb6 z((-ZAPUFnq*gr;5Gd+aAvvWm0MIa@qmYp7ps#F1Y>k-#=@N<**09CpBzN|BM=2QJ3 zSNP*ceD6184;7s1(t69kKU>iAyHXBieXgwY*JJu3QIzSOdP?4**4u;55IiX0&qLsH{>pnux~K6RVXJZu7AQ$Fg1N zC)qd+pSp!R)EhJ_6{D}6ePg2uDVB=A3++0gBaRI7Y^s%!{HjR)G;5b;Q%-6M+?IMm zPInq=+KD#O?cq0gebr7B$e)e|Urb*$sQ@B>s02e5A_sl%m%TP+ot9KSbv>%6aDAp){bfzvYckEsbB5;=<2$kiwQvIv(%SXZKH`#sa=eWExnJ@KfILXya-|p zoc4+}dtE3UoHf6NRUr~l_)$hUk(+>BE#sUVSc zo z`SOV8QsT>~DcK5wsiU2RR$f#yCcUaFD8Gz7DF4w}`9lF^E~sa-zPDgxPWoz2G64kV z9enG9;B02w8&{5Lk~rxm*~#*1w|6Zn?rhTflD4I9VeC4}hoa{7wK1w4;cKHMrq14P z+3kKld5#w2W3~4Y$w^DfXWF>T%!x3|^;}Z&t<}gGvhX4NsbtTF0iUzs|cx?`QxBK4f9L#bVNRKc6O2S1b_V79mHq~ z&v{R!PJjyA>)7|6{R%ok2cwyv^6h_AH_Ue+J#bsmcdPC*Ypg)ti@SaXu3P)aif_KC z)9x(YD0sPT4U^eRNU;!<&*MjIOjhj$QHL<=R1n;iBEgPY`)+?|uADy`RQrJ*4wsSOc^!Sj1mBN&!SjNsq zoAfbZ>uL6k;JT~>gMh924vxRs&zvS{555w%nm&XV_I z!H?jiag3XYXEa~duq=L@^Vj5!Y>k&~LmYOc<9@Yze0qa)+&kS1e%)|zj7U7?tqt@D zH_WEgpkdvjiXb2m#ouBY-cbpujuK<58locFP!W|s^roFJc~@E0ubqryCRn`Ak1!JQ zk-0^2iSY7iROpN7O-#-!+HtpbmQX`%I*!THnN0i7v&A!YAtz-HA6qS$2QKP@q^PL~ zqQtH#m_EPGiAXXi46>e6b8~1Al{^tyTIz@k4u42YWwM7o!xLYqMoF0xM@giP zMM0->Cs(;0M4>a|W8*{Z{o-4Cn|ctJz&MuTFjH~8tOzorpgd*c_V}=5CMzX#A>9ue zh8)oMA0EvUOSO@yg5TkF>tL~u0d6tS<4-A-(}S6FJO+HyqtXY`;gWF4xacPEr{tpx zYni}bC)WAA--%v?jiCxtb?48o2`7uL?WPimDQLSiznbn_{@P|0_@&wSHs{w&*rT$t zD`8#EkIDIC_5guv39+`Z8h?Ycd^}ZY#Lkaoow*+oS8P^dobByWzd?ka;=eENE zkl28k<>I@XqqM>ryXiDecY}`4T0Pw=mQq{HH~ay2RWHzXouWE4@7+i)_$(Ow z(<0PlzPqs1%fniGpm6^LZ8HCI+rYQOrS*?x1$ehPv^^2pEj&~+M7nI_XR~f!G4;w+ z+vrX9oj}lcmb6x5!Ze^^w7G5kI*dm)GFHNjLGn50o|HBUuTN0`-WabV1#>L5FLl}C zm%!=K$x+IkQr@!Mv|KmYHdr%|t(XQ>h+Gi>Lf;;HH> z6?9>-ih2r6g(^>mhLfgXGGtPwhO?%i;<#b5Z+vnyTJcQ(9wDFGj=XQQgwcjr{_FDX z#<}selG?sRd%j1%mWLeaW{}k!n$$l^>F9=L68n38{_s&h9VSlPsSLTQ^4PLVADr;m z_iFe%@gpXcmS=~cd&=o7wQ9+?z4D=USUh^g9E8<>1%T$ zXZn)P;MOx@`8i3iyz)p|wE@XUhRB7@>*pU|Jfqy;!kHvu6&=8Bn2!FKe%bfs%Nb*2 zCCipeB$?ifx5qeZ|5vm4il6`sztq^-h`G^NDF1)s53Ns^4A zQ0-WAL*fePi>jtCZ3j!I{!_3?A6*Jr5tSs6B1mmd?p;{O1FHfFoL4O>5LmzyJm%?l z>X(|+sDL>?mo*%YXzO_bUD3-Y@;DKl`aGSCX`Qbi_lt-l8Cs${&1-{Bgy|Txqr|>O z*{Ab8=z@0MMjY*F?>O+zuru8&S%E>Y&*IbSlp%pkCXDI2QsOXD%>YNw%(*Lu?lPNv zKFIASCsFjsUZ$ijX-h_8-Tf%n!f@5}_bdyl{oKSJ2PGNj9w4)mjWWXpnFH&>HR{*O zFrNM5zF*TJ2)k!^lglP)vLh~wCbZ5rWb|Kz%%P<1AN{s!$2?eile4CkE2{8!2an~q zv<5vchDww?CgDUqa;L+%4e5=;rl;e#p4n74%{931reR;J62`gjHm6l}KC`Y?A)Hkc zR))Hb63p73W+L1^;!&d9-s4bGi+`ug{Y*;39p-cJI&`i0^XoZXr0X)#*`_Yi4%cn>ZOkQ>|4G_Uexe=QQ(pfD8>ALt zmRws$7BVTs>w$@NQgg}Do3nVD8GK(HA}d=b@8%8KFk7e4W>TUeTV(efiNE)oY_5aO zBieOs6w|1U)6(;>%kT6~87e%xYAJ4j_E{X<%YoPK#VO5Q!^Ppv(zK?i+77gpK&_4! ze~tTovfEf)7yZt0BM_G_T;$m-0WXTL9gXY1MKsoi-k=Dsg%eh){~UMAZe)QE?-Ka; z$S3wsHV(3k9jf@$K6#uxVH}+jgxXV_0wrZhJ(!{2Q zL}UBus4FHD8?fa-9&=PRzeaLsn#RT1sGIsT(@LRYtaq#UOPxwC@A|g}qZI|njA|Bj zAMHV=O;;r5}KkZ%uWl;qspx;2dP5p$3peVkUxkhy-&t`kqOg?uenFWvoSf)`3 z%fFL$A0;yniWJti>ag(JW9gW)e(Y~U+ZLv{RMG zMvMD3^UGDc8V9%`{5cq>TG1^Zxt;I$^ICwCnnAVDkmi1RZfE1W1cBUL!sehc0!QnI zDulQ5(0}+(zN9=mHtgWLQ$=|Dng2EI`Sg0k1!``j{>9k~+`}!s*o*VY{Qh==I@IBO zf0@7X_Ba9m*U3dXxz%KJOwA;q`R=qXV4A?B>fsWMsOlj-yp=60fxh*wR?Wl3Lhe;v z&t8*=sZLhb72zx<|EW$~Nut&G)o9)soIruqpV04*@_#~wZuvVA*}Mo470`S1vj8NqPcu=du|u%J%gdWCaSgSa^l8!C2f;k_2c-_DwT`->mgj`0^(P0I z$C+uu<*#P{%LbO8^3Q(!x-Fv=t@__^4~CWb4`StpvJo+`)3Y_P#&E@dQa5sF3k>%o zVql7X;h>DR#DFjuwAIM&hSe3c)5D-N02BlXgg_wN-1r!^KSi7nC>)4{qL4S_ti6H7 z3jhrB8S@c}!CQpU))EFLM#lC4C>#mAQNn0RVptgyJwZz&bAuZs_+}FbDzy z!a)cm7{CeRhG5))xS;?r0tE%a;0O#e1BC!#5HJ#nL4Iz`F!YQ81n?WLxj~2iqI$sp z0xSQC_1x(GY4LZ+7;iUN4~9NQ+Zo&_{Cnie4!ZWgF(_e4k(+OC96>MvNs6dgiA##e zqOCEclRjomOzfS1iU%C$$^ANs}7{0)kKo?i>6G1b~7OKqLYTLTTMZdP6;-KtM2* z8-a!?pLt#J!H=G-)1;E6o2?zZag8yOo z&#wV+7z&64!MJZ&DsC_wGkr`(VbTZ!1l?rFZ&y$t;wD7^5Cmq4pf>^COdW+87!3bc zDGCz=7{k7!FvI`Dh8qk9BEj6S8#W6BfMGs?p%6^s!7(X_LUChsp(xB)H<_%3$$QLH zQD97T+?eFUWS@xI?+5mejQbbz{eL66Fd_Ua(50o+W$6tfsl8x#lOZPM626Z|4^NLo z9)2Ep`^T7ckV=R_hgU;Uo%H=22~WdXXz~#cTb^>p#RuHSZ(`uxwHpay`*aGOe#MqN5(F@UT^s-o}M>ziAM0s-IjNbdEbuDn-H@GTh{LI zWlEfWDDg{0YwVA9E*9OI&_9S3DhpyXcUBBGVBtYUt$&1*ipPkB;j;`%6o=OT(ItFB z#`mlyOXt&Y!%>Wi1*->j@Ni%rQ8SW*FUT>#=Xs2Nz`&iz0KAW+8O*8ESdK5RQdbRs zN!Yb~jrhL6ACyL-SRTbXp-Ce3L`Y=OOCpzyD$+;0(Z!uw}ltsADA6+~+K`aQ!IaiFxV)~=7e&V80>jtzT zOnYhe8TN9?AOBtaZj$@oXuUtn!9RES&DO@$q5ruKh+1N}{+n(4&)v=`@sHxCkH(ZB zOl`m*g1>8y5+*TJtW+&cZvGVj0RBxm{#}-wYz++YK>#ouAN0=`fEx~n!U2YWf6BlZ zBJ$=1u>6M%0> z?f4Hp2<)a*{JSj#hWM{>A@KjQ1%shCrRCpj!C*M*Kj#95K>l?Mds{T7$lKoh4~(*j v3uaZ}7$()q3PWe!Y+FqE{#|izHu22~U}ulEwg0`)H+&@=pP5-yUhMw>+Bm{+ literal 0 HcmV?d00001 diff --git a/tests/workloads/kernel_names/MI200/kernelName_legend.pdf b/tests/workloads/kernel_names/MI200/kernelName_legend.pdf new file mode 100644 index 0000000000000000000000000000000000000000..9bc1ff0f7ea5b3d9e4b7316211905d2ef087a3e0 GIT binary patch literal 10637 zcmbVy1yoe+_CAV$w4kKKs36i43^M~rcXv31G(*SGB?yQ}NlP1)BHbV%rBX_VfV4<= z!~cxmckg%ackjCExBjzOoOAZsd%t_{_ubDdcs9Gbv@9=#Pk@AdU}brR1OftsoXl)V zL`3+dTrEwpPOhMPQZ}wm4j6X_P7;1~S0@X1b4x&|Wrs242W&wONF?y$w=%}bQQ8!1 z3A!gO1O-C{z%VcZxI(}%ZZMbw_yP1(oGkvgil``wrK1Hd1lV7pn45wiB>a*pAbwRR zR|ix3zmx?2Qj(IuDgB|UECm9S@GC3+{;h|Tt0;p6NcgoRKv-9I%m3~R{(tfX{Xh9a z{N+m)V~+(Y#xH9R)JEFU+{pr1U)j>p8fybWA_PQ5L2g)})D9$G=^ykaqHmzc{ELe} z!Q!MGdu1d=z=oMYN&EPzp+mMr80!m@SvGeC=vpd`ne>6SXJ!1T=+Y>Aj7MWdGSn-c zCBVmga4+DlZsZS8G}os4L|#S(VbhoA~~AQ;NHZxv3b_F zZLn)$)Gf4yy4g^sF;HisE2L{OgkHe2x6$oA3@Ppx?Zb?(}oX~(i`@`DAuU*!r&@M z?hQMeuwQ&N7N(Xdex(ua(jw13UacFvLDsq$CC3mlvtAdua;AJR;9ngs-(c-x6gKEn z#oQA8)_m=-SjjpE1}__7nDk!%Zj!9=Tq;MSRz+p7s;D5YLOzZz4nHp8rUFR5Lx~#B zrY>(Z_1r!VdrLt)uJUdHkNjKKI?hU(AoT<`8vf7js+vl%gTidp3<}H&nk)U|BP-9P z)?AKaeYY#*a^y@YTk@EQ+9{FDLMo#iJw&f4hU64I_c5#3R12{RMr@YFWN2OiVJ>fL zOUvXni;>J+NhTO`KdU&ix-fyj-p4l=5_8h);zxW0D&(l-=37f_+gmrX_aLC6h-lSU z5u6b=s@cy(6e2yAIre1=q;=F3#S7_5D;!r!ZpGT_7OuzZUOSPsFO3hlk*2r0bH=$j zqNZl(?w(O=&-}K6^oQ(8NRE)kcls0Qt;MniKh_x&qee4A+g5g)9-$|(hLLX{HK$^9 zlTQ{BYq_1GN@ptTPCqo%pI+$i84`PEIBbtCbP_YHWGQykHheoqyL!i^xVZY~8pa(| z?tMwQLRX>MK@;UtGdd$Fyv1yFj3~+L(LDec9jpZ4TavFw1$NvI|D2MA${4j(RUY;ah#n)*j*d&i!5edJH7gkOS zi-SYJR1OBh!I>rrznlOFhgrBgI0%P0ngE#b%Q`t?aeA_XAi+OmIH`)I1;$j;$qR%A z140BG41$5dfNLp0+tLy12Ew5X;7JR>G;^%Fsq1ec0DOPkf{=f@|1(G2{7Ln7hN>=7+zM-l$L+*Mteh@+JBVNLqYjTqUGGLLNXTfB;>-BG z35rX4Y3dWIuGG~gz{*q(-Sf&9AyM3qt$;dB_V+Gl3h9nl61`Y5RHF=OXSOScta;Qe zUHBiIoL^iVtU=O!&lY_nAxli=e6ddW_;_^w@_2V-=cnp0)-8|mx@B{|RZk@d{~Fsp z@4AuqCV^A)V`At7&<=Rt?w5@x!7iLN#8I55us?+ zWAfE{%Mg!y!E~cAxSv`*yk%V6d!o==DMHhPr=Bc!p6IHt-F|oQ#~RPZ&oYPCl^YN&AQ?r{{CDy9_=m_0&92W{xBIF8WM`q1a<*Mewf6O&DE?lf( zhHW;9{Vt)vp9sHnT9KPbgmvXLT7$&zHYN#e+k0G73%Pin^0>q3RID1d2cAgndv}-$ zDdNuZQ3;q)OF1B_k=zfF(5ugt?=i!B6GW~nPEZ&o_XCn2##_Sd@i72N);V+kkkpT0 z8q&*D2wVBmKlV^COvP-#fGVwP-HLP!-yZ(XN_Z^5BZb*|qqM1{c+@l9jcB90ej6*A z5;GHjh&66o+O9v6JjXNXd3U7Rn8mu-=}qxjM-p>C=YitJWzd@Hsxro2T-I^om4#g7 zuKS4QzXWGT;VSEahU*iSCDW2#n%AZk534{dN?v72tr-68CiPeTF%RlReM+}& z+HS11gQ=kcNOM*;}|IhQ3G zLN+5ojakm7*OI9+8QPSH=?J!u zfXplJl2fmH-2d^1kL=SJ!?}u7yy#mZqTzFGh$7qiwVbL&-X_zJ7i`H7GL@LYvqeE#V(p*wR1+b zJZqVSSR;yY*Fa!)r3q{{#~yC6tsM@PO z0xR;DChunEr{6!6O>JpoI&Hf;0AgiZlPildn=qRodApXqc29q8Y`^qJsZ)ubRETk5 z@gp0?7TGfLP=aAEbOLV&t@VmSeTzpuZ=Y2WLp+oH{i|^zQuev__9xdbuF8B@q1LyQ z)|oX7_Bc6tJRF?%?JnZ;x0S^hk|@aMN)YFxgAd@Uz~Wz?#(EX1SqpRzR{QDOp(t!kYgb$l{oNy_;|EpMKK z-|tnRS_jGq4$v&XDt<{;G$35R5#I(&DBE-&Cv}o!8Z0eWCwa1^)ZI*oNtu6C?nQFY zyd?0fwu8fzc{Las*WMcOGCg@~OWRd4{gwO&f{23i8xy@#9Lp5tiOz(X;!k6O*H+1v z-KiTNC#H0DVUA#4RG$NbJA`D;s>KVWJsEO?TI#hJ6x7^QDE&Gfs=3^4PR>rZ>J2q= z%~;i-#?TI!^_7?xDoo+QH$|s{NH_cJ6BF*OCCRqbd5}I7Eqq;Co#H=#yD9{WsO@IT znC4z6zrUH2P^_F+YJz~jLQ!sRz0sf&P_NVTc&>^+##MM*p=X>PnG^ZkM=Ov~!a()` z{tffH-R#=3o{4nX9J;MSjGWoU-_`u&?pG^j#r3X?ww?+jLt8;K5pSMZ*lprXy8Vc~ zO-hV<%p$7CtHx-gzrugm->$Jo)g~__*s`B@Hvh_u)nDY?Zo- zil@7*IsxP5avr@FCJrl`rY#yzmMCAB5yum!qPTLmXId}2FTSa~{q#Jlw|K87WevUd zAOrcZ(r)ol=31sQfvRFW z;Lg$=IV-O>t{Fi6+_*+}$b8~{LG<&4@`0m^a;e{yMgGs;n{;7J5s|h9@~fAx5D1+( z^wY!^gLM+zh;TeOP*iUn(sa_x`gezmWwiEwHygsP%R>Qzm|BeRc4oQiR}Dbt2Ym^Y+xWDp`^ta zUpq2Kp|<)3c2aY)RTe?Rtv96Y zf-Gs#>rZN?kO)j?cZo&aO#1eDZO@s#v{<;Da#}{pv9QRX(luw*5lWbG)<(a%x3s!P zN;hgJ@GHuXjOBW=_>qQxIuxqf@b1yr z8z=26dkywQTSr|gMb9uiK`VTovUOMy~vFh zGV}C#k=2|TW(;lq`m#|Pw%YWGvYfstyru``PkQ{1I3Eek+vfwAA^YTE~`d6P9WzBJ4rT&abp)z0YRdpT9_W+37n+E*Qpx z+~F0>wH#q7z-mwCFT#9n9`#qb-F_hu9nyH-yFV?oZ+FvuA3e(NKo+QNGGXwvLMpX$ z=*6HazxQ#ChD12E?ZP}&VXE|jP*DL@<@%j7jn|_Tg3o%agk|Hjoi2yhUb^YGqNd?~ zi&Q4rGN_J?t%&p%xekF`$TZrbh0Vb78^}O~K@IV%BEyFg>KTV2ZD;p?T_X)vm{wNs zl91`xK8^84#@EQKwP{I5jK>_%_zyn!3#l>4_+-7+erjAAC&o5h5VONEMEafkwT%A! zy-4kluvF?G&R6x{RhGH;X#5wH*?T;$ALq<`tSFUop0?*BR;8S5 z=teZx3&l#3XA$YdD$z-Vb`}s}gTfpIN=p4mimWM9*nqArn0Ua7onpW$Uft!bD(OhW z_tzm9BX7O-JnWF)16FpewASQpsO8hD^kQ{gn-y=4rv{Kn8PnSN zz4&F=W#;~LL1G{5XrcCsgL3<$a^iAxxwMwka6GU1LgCVi?2*Fj290!##@3U?_1i@R zY&PctHDXYCH&ULhPOdisb9IHEq!e^CwLdA(eA6@u#SV_Ucay9~6xw;nJVdk^sPyz7 zZ=Zj;C#w0P^;yD#;qwPy-n%IbbG!8C^-Sid6}LSXuzT^WgsO~Sl)c?Eg- zdXj0glE7?ZtaCAYok#xXUV)OT%BuFNhSB^Sq8zt4YT3MXlr8No4Rea20XiR#=TqmE zK9@2Z2@APnKgIOKbR8^oCbuQEB_1lyCU^41px4nXtk320L?rfoge>12e0aV$a2>Xs zz=7>q9YEX>Ems?9yJGN}sT6pq9k()J3#&K4% zm#oIvZa*dEo2mZeADOR$^*kGQBkKKBij95a;?dnTJ}LHqFddXcKTv z@BU&qJSva5zhC&`0V~6%-`K?0;eC&>9sFM_-W&0BeCco6I_YTX$vY_9$O%I06&MLg z$9rc89<<8S&&C9k?8naMmx#R?TG90P%2>WV=|R81pvt%H_v9ItA(_AKJOI+;Mr&1-yb7%;7Aso_6c6C@%tgd!I>q%Qe+hAM6O*c+ivY=b`S6OG7so8z*eHfZbVtD|$ zQEq0u${Sra&kH7JV(o$!kxNxvN_g~*rl4VgV4^_EO-(s#Yu%{Ba_)+f!%-xs`|0wN zszKqyiUK*c-R1HoH05v>h9`2;-tT+Oa`XAxVy|Cf`WkgvrT5&*y5}dkoTZmRq`8V< zN%zWF^sSxDJnqoxUuB29s3bq7r=i1XeyBAer`dPz(wgUqjAJ`F%hi-xA=8R;nEC6P z7cN-4M=H!SDxp*(PpWq=zzwzbxl;97vyAOk7MWai@8Z3vvT~9%mC-Hl+V1=!H0Bj7 zP;;qf7^q2{H6XdGWF@_#`pr&oapJ9WqBc8AZcQZtg41`?z(w8L=t%sCg@5LtpS_@* z;a#_SqA79BYU`fJ^2+epX_3-@nWM*$<&*d`YKoS-j<$Dd$N70N z0rg6UGSQ#t*k`Fx>yN&DdRVs9nVbDSfqq<#7(6tsga^7?u^TFHrJy8=m@1KS4 zt2Fz1V=BidJ1ar0H}exTpEQ-t9>}fG@jW&C-Q4=ub@FRPjAmiU_R zMfgUU`A6C8u(37jh<7bu zHD3Se0=p4hq~(Tikz9QBkDSbtrenM-+lCv znY&aSux+zKTA?ok3&|df;QW%FJr*|;92h&-D`2|JnFJULg?qSXNwI+6pW4#?Pu++m)8Kw%0FSXmwaFv7zei4NLt^3TuV z%bBY9FGd&`-Nm(Z)9czylD!}bo6Duy_GBqv#omS z)WY$GqwTJDwU=&@j)_L!TZdl{cN$eoxgN7mc}1$24@5I~3Md`%*4At&MqzGkOXr5B z+eckk$t=(^r>8m&;iXed606obmOnmn9tHkAH}GE9A%D`=B}hkmR*AyyahGW|hL%CX zT~YPjyGft1O50|$VT$Xi$cG;~nw65DCDn3zW%L0wfHG% zJ;re)&GjLM9b;5zWdC{JG1^fzYbs_K6rZPndDS#LGCndqow@MIHFp^ilyy{_HRX7= z=2ZPlz029*jemuC#X#}WN2Fl1S{oCmoN^ooSNz}vPc`QH`|A!`Oj_wEA1dzI@=8=R zs@Ly>@`pZ`ta1`vw61~P*xOZ|Xs#uzF4+~?3EEEDCB7BD3FA&<>-Xo;0lH2D*8LI0 zL@T{eOdqA`qRgGgPV^^-{p352pL@a)gjM`=tBCb!=-b!qN%7y-qKd%Jd^D1w-s395;B+TzdnBg&X9Iy(+xG5hUO_PjPDdk-b zr2KmRx(VL2pM2#8?`(EbKOb@Tbvm1-vvD6Pio^ubvptP-6!p;Jh3Q4&@vTK+DDw*G zX08pU^Wr9((Ie&4W`UIDTGlTdXG7y=vBwYgk7}8jh!St!pv) zb~8AI*zG0W-Im)a;(hfm6E>Cg<@-?T%HFJRr1(EQ3IHc;w>yux`}^tnPAa>zmxTEA z1{u8RydUJWnR2Nhh^jvvc2y;hcJUy;`{l8wA}OZua*A5q$wPrC*yF|R78P*JDA8PT zv<~B^o;P`%6K2OeZ<5BvAa>L5$`|{UpJ9q>FMY5gn7@}TdSMMSE)aN}xf$uw%6b{#ZrL|QP8W(mry)7+ZXmac*COdV-3xM3!40Dzn*42a=-TGWO5PPA4-IR^j>YvtwO_kY)^ggS16dN+zDBPQaC7> zTco;j9tX-(6YZQjczxwRyG2Y%e`p48eE4IBaG3GX7yp26c7v(L$tiABFWmQ_rhSU- z`&`G8{LiISm+GKC#>2=UwR)H2Ahk7YcwWCt9)2J?96tCam(i2H#y?HP9^sruUMV-KUK>5p97`caFAmCOjuyr`kWL&7IsA_NHJW~r4Q_Ka#PKWJrS z;pv{7^O-AV@{WR;5lhjIQViQnD`An*fKnmcS%u$F#kQ!C_#I1G1Q(^KMY|$bK2IA- znYIjdQU8_+nPIIY9XGk*%elvde29|o;(-(RT}e-g$PBBGmVeBf^hBf{RHClR&Rouh-wlV^Co++aWsG)v-J z(<3LFgD<5_M-JGhSpQffRE0Z#u~1RQbbMx<8s^meo)jHVmM#xdV~VIXPH#3ele`jr z@S_G|YL*^^(mjm|GIw%+T1q(e>m!=1J2%xHzcbR~DZ~^h)WIiP@0`Fa$B2Bz_(X3G zjPJB~zrCjixqEdgAu0g>2|e;qwwivm4@nPenu{Uw4IBmVS4M`7ycfbH^X#y2>jKG#HOnhj!!pyswf;eIJy_33+TJ zvDML;RclxOObRJ*R8~->=0upfQhTVBMHHzjmzmMwUnf^~HWOK9*pM~3)d4r>DY%9X zhj>KZC6&ENKNOkq#Ei}IHhJW|Hs>Sdsd^113=vW=gD`kC4 zh^%5lh`2sT(AHrkL>C`U_kc{h;Dv4WtVHcK_O}T(L|)Gozlp1QPhEdO+9IyoNuqbZ zyYAvbd@~UJ$RsD_;xeWIQvaW`Gc5MHFW?8VQEWS zQ(bp0Q%8U?1x7in-Ei|H5^m-I=L$kWk$g}nR1n}eamF|iFBAsnL&8u<+|&uy(m@v_ z06YVaFeJdZnmWr{VytbjAQ&9Uhf@Ny6aZEgV=m!nZEuMiTfs#l`J4RZg@B=8J~$YG zgn)Pj1fhT%upkTsL7-rK0&oNf0);{O1fUQk65xh$W&qD>2?hNoVsY&9pY$)}KR9lj z?jII^r40IA6M$5fGI+Fh~$4$Onai1rUGT8G&F(z&8rmL7;|!HvvK55f0}=2toi~U=R|hI06MlAwUQL zBp+Bn5U4Xq5N8AV#|uH20H6*BHU%z#;zI&DC}4qq$OIv9U{PS>{|o|(03wG$!MKS4 zI0D570Yl(|pueOjga97|7@NZRfbk)4yA2YAK=_alK>^6W_yvOm04W3p1yO)(bo9#W&9`Io9 zO@mA~7Qf@40`;LznR{Nr9JCF>SQl{7t;B zs>=PX0OP90#phd<`ah@*Vxt)0%2hf)9=H)EJqe%@5j)lagO5%8&nhU&?_@ED zL3v`MrP4E_1&MzTC6EaBQ(?3coAwwzcS=e5KsAu(x6{TsT2ZZRCh+f|n*_J#hQEyX=b56u-Dp`c8Q#Y3Ix0xpngI z7sSHjmA3xpcq6_Xqg literal 0 HcmV?d00001 diff --git a/tests/workloads/kernel_names/MI200/perfmon/pmc_perf_0.txt b/tests/workloads/kernel_names/MI200/perfmon/pmc_perf_0.txt new file mode 100644 index 0000000000..dfc38b8643 --- /dev/null +++ b/tests/workloads/kernel_names/MI200/perfmon/pmc_perf_0.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_ADD_F16 SQ_INSTS_VALU_MUL_F16 SQ_INSTS_VALU_FMA_F16 SQ_INSTS_VALU_TRANS_F16 SQ_INSTS_VALU_ADD_F32 SQ_INSTS_VALU_MUL_F32 SQ_INSTS_VALU_FMA_F32 SQ_INSTS_VALU_TRANS_F32 TCP_TCC_READ_REQ_sum TCP_TOTAL_CACHE_ACCESSES_sum TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RDREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WRREQ_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_names/MI200/perfmon/pmc_perf_1.txt b/tests/workloads/kernel_names/MI200/perfmon/pmc_perf_1.txt new file mode 100644 index 0000000000..cd7a1d5f55 --- /dev/null +++ b/tests/workloads/kernel_names/MI200/perfmon/pmc_perf_1.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_ADD_F64 SQ_INSTS_VALU_MUL_F64 SQ_INSTS_VALU_FMA_F64 SQ_INSTS_VALU_TRANS_F64 SQ_INSTS_VALU_MFMA_MOPS_F16 SQ_INSTS_VALU_MFMA_MOPS_BF16 SQ_INSTS_VALU_MFMA_MOPS_F32 SQ_INSTS_VALU_MFMA_MOPS_F64 TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_names/MI200/perfmon/pmc_perf_2.txt b/tests/workloads/kernel_names/MI200/perfmon/pmc_perf_2.txt new file mode 100644 index 0000000000..952da7fef3 --- /dev/null +++ b/tests/workloads/kernel_names/MI200/perfmon/pmc_perf_2.txt @@ -0,0 +1,5 @@ +pmc: SQ_LDS_IDX_ACTIVE SQ_LDS_BANK_CONFLICT + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_names/MI200/perfmon/timestamps.txt b/tests/workloads/kernel_names/MI200/perfmon/timestamps.txt new file mode 100644 index 0000000000..676cca1b80 --- /dev/null +++ b/tests/workloads/kernel_names/MI200/perfmon/timestamps.txt @@ -0,0 +1,5 @@ +pmc: + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_names/MI200/pmc_perf.csv b/tests/workloads/kernel_names/MI200/pmc_perf.csv new file mode 100644 index 0000000000..65578bf14f --- /dev/null +++ b/tests/workloads/kernel_names/MI200/pmc_perf.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_LDS_IDX_ACTIVE,SQ_LDS_BANK_CONFLICT,wave_size_1,obj_1,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,wave_size_2,obj_2,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,TCP_TCC_READ_REQ_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RDREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WRREQ_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f7d7f73cec0,0,0,64,0x7fd57baa8ec0,0,0,0,0,0,0,0,0,0.0,64,0x7fd63f95cec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131082.0,131072.0,131072.0,197002149949822,197002149970142 +1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f7d7f73cec0,0,0,64,0x7fd57baa8ec0,0,0,0,0,0,0,0,0,0.0,64,0x7fd63f95cec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131073.0,91410.0,91410.0,197002149989022,197002150004702 +2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f7d7f73cec0,0,0,64,0x7fd57baa8ec0,0,0,0,0,0,0,0,0,0.0,64,0x7fd63f95cec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131083.0,90882.0,90882.0,197002150063742,197002150080062 diff --git a/tests/workloads/kernel_names/MI200/roofline.csv b/tests/workloads/kernel_names/MI200/roofline.csv new file mode 100644 index 0000000000..9778ed8285 --- /dev/null +++ b/tests/workloads/kernel_names/MI200/roofline.csv @@ -0,0 +1,5 @@ +device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh +0,1388.5958,1388.0493,1389.1423,5016.0552,5013.2388,5018.8716,9224.002,9223.4004,9224.6035,17646.789,17645.832,17647.746,20937.551,20877.023,20998.078,20265.363,20264.518,20266.209,170441.44,170436.91,170445.97,164875.34,164870.25,164880.44,41419.012,41418.453,41419.57,41478.145,41477.512,41478.777,166343.12,165853.14,166833.11 +1,1389.3785,1388.7844,1389.9727,5026.104,5024.2295,5027.9785,9231.624,9231.0449,9232.2031,18072.625,18071.354,18073.896,20969.863,20903.061,21036.666,20290.215,20289.688,20290.742,170813.73,170809.58,170817.89,165053.16,165048.22,165058.09,41467.996,41467.258,41468.734,41523.824,41522.836,41524.812,166816.73,166813.39,166820.08 +2,1389.1305,1388.6124,1389.6486,5036.9468,5034.8271,5039.0664,9263.2686,9262.5059,9264.0312,18272.225,18271.135,18273.314,21051.234,21050.822,21051.646,20356.029,20355.484,20356.574,171144.91,171141.19,171148.62,165540.94,165536.42,165545.45,41592.703,41591.672,41593.734,41649.43,41648.234,41650.625,166973,166376.17,167569.83 +3,1389.0021,1388.4742,1389.5299,5030.1553,5028.6445,5031.666,9238.5254,9237.9639,9239.0869,18325.27,18323.295,18327.244,21027.713,21027.381,21028.045,20309.979,20309.316,20310.641,170994.94,170990.62,170999.25,165209.19,165206.78,165211.59,41440.266,41286.492,41594.039,41583.148,41582.602,41583.695,167001.05,166998.64,167003.45 diff --git a/tests/workloads/kernel_names/MI200/sysinfo.csv b/tests/workloads/kernel_names/MI200/sysinfo.csv new file mode 100644 index 0000000000..08d4869367 --- /dev/null +++ b/tests/workloads/kernel_names/MI200/sysinfo.csv @@ -0,0 +1,2 @@ +workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd +kernel_names,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 02:21:00 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/kernel_names/MI200/timestamps.csv b/tests/workloads/kernel_names/MI200/timestamps.csv new file mode 100644 index 0000000000..9d5f8a6afc --- /dev/null +++ b/tests/workloads/kernel_names/MI200/timestamps.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,239056,239056,1048576,256,0,0,8,0,16,64,0x0,0x7f78041f8ec0,197002149924520,197002149949822,197002149970142,197002149986197 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,239056,239056,1048576,256,0,0,8,0,16,64,0x0,0x7f78041f8ec0,197002149981117,197002149989022,197002150004702,197002150061159 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,239056,239056,1048576,256,0,0,8,0,16,64,0x0,0x7f78041f8ec0,197002150015272,197002150063742,197002150080062,197002150081206 diff --git a/tests/workloads/kernel_substr/MI100/SQ_IFETCH_LEVEL.csv b/tests/workloads/kernel_substr/MI100/SQ_IFETCH_LEVEL.csv index 50d6d144d9..06b6066476 100644 --- a/tests/workloads/kernel_substr/MI100/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/kernel_substr/MI100/SQ_IFETCH_LEVEL.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2836054,2836054,1048576,256,0,0,8,8,16,64,0x0,0x7f6ed7a82e80,48021,48021,16384,65536,12934,1687980,2187769696640836,2187770153039589,2187770153063749,2187769704195328 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2836054,2836054,1048576,256,0,0,8,8,16,64,0x0,0x7f6ed7a82e80,43919,43919,16384,65536,8143,1048580,2187769704219062,2187770153157189,2187770153176229,2187769704517543 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2836054,2836054,1048576,256,0,0,8,8,16,64,0x0,0x7f6ed7a82e80,42855,42855,16384,65536,8405,1048620,2187769704549483,2187770153197349,2187770153216709,2187769704705115 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,137526,137526,1048576,256,0,0,8,8,16,64,0x0,0x7ff7d60b8e80,48136,48136,16384,65536,12547,1608968,194163174117052,194175534630063,194175534654063,194163181897573 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,137526,137526,1048576,256,0,0,8,8,16,64,0x0,0x7ff7d60b8e80,43175,43175,16384,65536,8463,1048596,194163181922491,194175534674223,194175534693583,194163182207089 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,137526,137526,1048576,256,0,0,8,8,16,64,0x0,0x7ff7d60b8e80,44071,44071,16384,65536,8088,1048576,194163182239821,194175534779503,194175534798543,194163182401738 diff --git a/tests/workloads/kernel_substr/MI100/SQ_INST_LEVEL_LDS.csv b/tests/workloads/kernel_substr/MI100/SQ_INST_LEVEL_LDS.csv index 108c5545b6..9540492999 100644 --- a/tests/workloads/kernel_substr/MI100/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/kernel_substr/MI100/SQ_INST_LEVEL_LDS.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2836603,2836603,1048576,256,0,0,8,8,16,64,0x0,0x7f5948092e80,0,0,0,2187771300749952,2187770153039589,2187770153063749,2187771308278485 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2836603,2836603,1048576,256,0,0,8,8,16,64,0x0,0x7f5948092e80,0,0,0,2187771308299725,2187770153157189,2187770153176229,2187771308585822 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2836603,2836603,1048576,256,0,0,8,8,16,64,0x0,0x7f5948092e80,0,0,0,2187771308614426,2187770153197349,2187770153216709,2187771308783663 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,137714,137714,1048576,256,0,0,8,8,16,64,0x0,0x7f3cb4fe8e80,0,0,0,194163677587142,194175534630063,194175534654063,194163685530482 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,137714,137714,1048576,256,0,0,8,8,16,64,0x0,0x7f3cb4fe8e80,0,0,0,194163685548716,194175534674223,194175534693583,194163685853083 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,137714,137714,1048576,256,0,0,8,8,16,64,0x0,0x7f3cb4fe8e80,0,0,0,194163685881677,194175534779503,194175534798543,194163686052871 diff --git a/tests/workloads/kernel_substr/MI100/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/kernel_substr/MI100/SQ_INST_LEVEL_SMEM.csv index 0d07c97f26..94f7a15a3e 100644 --- a/tests/workloads/kernel_substr/MI100/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/kernel_substr/MI100/SQ_INST_LEVEL_SMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2835871,2835871,1048576,256,0,0,8,8,16,64,0x0,0x7f3df6fdce80,65536,201602,25951040,2187769240096984,2187770153039589,2187770153063749,2187769247791258 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2835871,2835871,1048576,256,0,0,8,8,16,64,0x0,0x7f3df6fdce80,65536,187442,24081592,2187769247811146,2187770153157189,2187770153176229,2187769248133701 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2835871,2835871,1048576,256,0,0,8,8,16,64,0x0,0x7f3df6fdce80,65536,177588,22725384,2187769248162956,2187770153197349,2187770153216709,2187769248335169 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,137904,137904,1048576,256,0,0,8,8,16,64,0x0,0x7f071b3dce80,65536,188508,24142904,194164172303568,194175534630063,194175534654063,194164179881035 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,137904,137904,1048576,256,0,0,8,8,16,64,0x0,0x7f071b3dce80,65536,169170,21619920,194164179900282,194175534674223,194175534693583,194164180246938 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,137904,137904,1048576,256,0,0,8,8,16,64,0x0,0x7f071b3dce80,65536,168242,21557048,194164180274780,194175534779503,194175534798543,194164180454190 diff --git a/tests/workloads/kernel_substr/MI100/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/kernel_substr/MI100/SQ_INST_LEVEL_VMEM.csv index a26322d8ed..7f3c32976d 100644 --- a/tests/workloads/kernel_substr/MI100/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/kernel_substr/MI100/SQ_INST_LEVEL_VMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2837335,2837335,1048576,256,0,0,8,8,16,64,0x0,0x7f505984ce80,32768,666558,85325644,2187773130816574,2187770153039589,2187770153063749,2187773138365636 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2837335,2837335,1048576,256,0,0,8,8,16,64,0x0,0x7f505984ce80,32768,667867,85503424,2187773138386926,2187770153157189,2187770153176229,2187773138681358 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2837335,2837335,1048576,256,0,0,8,8,16,64,0x0,0x7f505984ce80,32768,655830,83946444,2187773138709522,2187770153197349,2187770153216709,2187773138879962 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,138091,138091,1048576,256,0,0,8,8,16,64,0x0,0x7f290d802e80,32768,655161,83871140,194164678008099,194175534630063,194175534654063,194164686165985 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,138091,138091,1048576,256,0,0,8,8,16,64,0x0,0x7f290d802e80,32768,672735,86120852,194164686184760,194175534674223,194175534693583,194164686503344 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,138091,138091,1048576,256,0,0,8,8,16,64,0x0,0x7f290d802e80,32768,657649,84175780,194164686531978,194175534779503,194175534798543,194164686707520 diff --git a/tests/workloads/kernel_substr/MI100/SQ_LEVEL_WAVES.csv b/tests/workloads/kernel_substr/MI100/SQ_LEVEL_WAVES.csv index 7aa32f6295..d236147e08 100644 --- a/tests/workloads/kernel_substr/MI100/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/kernel_substr/MI100/SQ_LEVEL_WAVES.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2837702,2837702,1048576,256,0,0,8,8,16,64,0x0,0x7fca353b2e80,48056,48056,17112,384456,16384,24538298,233738,0,98639592,2187774290395852,2187770153039589,2187770153063749,2187774297961515 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2837702,2837702,1048576,256,0,0,8,8,16,64,0x0,0x7fca353b2e80,42197,42197,13955,337584,16384,23746856,227641,0,95474444,2187774297971513,2187770153157189,2187770153176229,2187774298393586 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2837702,2837702,1048576,256,0,0,8,8,16,64,0x0,0x7fca353b2e80,43173,43173,14204,345392,16384,23959905,227347,0,96331984,2187774298432208,2187770153197349,2187770153216709,2187774298619610 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,138275,138275,1048576,256,0,0,8,8,16,64,0x0,0x7f5d7a4c8e80,47598,47598,16289,380792,16384,24789627,229303,0,99653036,194165181026564,194175534630063,194175534654063,194165189084451 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,138275,138275,1048576,256,0,0,8,8,16,64,0x0,0x7f5d7a4c8e80,42421,42421,14055,339376,16384,24679834,225411,0,99219160,194165189106292,194175534674223,194175534693583,194165189431618 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,138275,138275,1048576,256,0,0,8,8,16,64,0x0,0x7f5d7a4c8e80,41925,41925,13806,335408,16384,24141356,225187,0,97056972,194165189469360,194175534779503,194175534798543,194165189654570 diff --git a/tests/workloads/kernel_substr/MI100/pmc_dispatch_info.csv b/tests/workloads/kernel_substr/MI100/pmc_dispatch_info.csv new file mode 100644 index 0000000000..17300ae9af --- /dev/null +++ b/tests/workloads/kernel_substr/MI100/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) ",2 +1,"vecCopy(double*, double*, double*, int, int) ",2 +2,"vecCopy(double*, double*, double*, int, int) ",2 diff --git a/tests/workloads/kernel_substr/MI100/pmc_perf.csv b/tests/workloads/kernel_substr/MI100/pmc_perf.csv index 6e62d75d4b..ac83c58934 100644 --- a/tests/workloads/kernel_substr/MI100/pmc_perf.csv +++ b/tests/workloads/kernel_substr/MI100/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_1,obj_1,TCC_EA_ATOMIC_LEVEL_sum,wave_size_2,obj_2,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_3,obj_3,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_4,obj_4,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_5,obj_5,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_6,obj_6,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_7,obj_7,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_8,obj_8,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_9,obj_9,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_10,obj_10,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_11,obj_11,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_12,obj_12,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_13,obj_13,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_14,obj_14,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_15,obj_15,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_16,obj_16,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7ff571ad6e80,4096,0,3443,0,4096,0,1157,0,4096,0,4130,0,4096,0,1573,0,4096,0,174,0,4096,0,4836,0,4096,0,596,0,4097,0,1861,0,4096,0,1135,0,4096,0,2655,0,4096,0,1125,0,4096,0,3237,0,4096,0,1154,0,4096,0,4433,0,4096,0,3342,0,4144,0,0,0,4096,0,1273,0,4096,0,2689,0,4096,0,682,0,4096,0,2984,0,4096,0,2688,0,4097,0,6045,0,4096,0,1633,0,4096,0,725,0,4096,0,722,0,4216,0,3802,0,4144,0,2001,0,4096,0,399,0,4096,0,1991,0,4099,0,2121,0,4096,0,1707,0,4096,0,946,0,64,0x7fd1f4592e80,0.0,64,0x7f84dc044e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,60492.0,128721.0,64,0x7f68a83eae80,1592678,360448,163840,0,0,180224,114688,0,69952499.0,194144477.0,75201923.0,131072.0,0.0,626345.0,0,0,26249,79015.0,0.0,0.0,79015.0,64,0x7f00b5ba4e80,32768,0,0,0,16384,16384,393216,22788521,960.0,513840.0,0.0,524288.0,994899.0,32768.0,0,0,0,16606,131072.0,131072.0,0.0,131072.0,64,0x7f73d15b0e80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8360,4264,8360,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,141,8195,4240,8336,0,8192,4096,8192,0,8192,4096,8192,64,0x7f8e6204ee80,131072.0,131072.0,0.0,2518393.0,0.0,0.0,123067363.0,60136975.0,64,0x7fa610f6ee80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86280.0,44792.0,131111.0,0.0,64,0x7ffbaa404e80,0,0,192,0,65536,64516,48,1322,32212,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,539,48118,1769,0,48.0,336.0,0.0,262288.0,64,0x7fba52a34e80,0,51871,0,0,0,51871,0,0,0,51871,0,0,0,51871,0,0,0,51871,0,0,0,51871,0,0,0,51871,0,0,0,51871,0,0,0,51871,0,0,0,51871,0,0,0,51871,0,0,0,51871,0,0,0,51871,0,0,0,51871,0,0,0,51871,0,0,0,51871,0,0,0,51871,0,0,0,51871,0,0,0,51871,0,0,0,51871,0,0,0,51871,0,0,0,51871,0,0,0,51871,0,0,0,51871,0,0,0,51871,0,0,0,51871,0,0,0,51871,0,0,0,51871,0,0,0,51871,0,0,0,51871,0,0,0,51871,0,0,0,51871,0,0,64,0x7f202b39ae80,3608,0,0,1990857,2439,0,0,1911747,1681,0,0,1824261,4722,0,0,2064370,2094,0,0,1766871,3115,0,0,1861568,3890,0,0,2006627,5414,0,0,2175893,2347,0,0,1905274,2306,0,0,1999492,2594,0,0,1859260,2358,0,0,1803208,6298,0,0,2197759,4054,0,0,1965604,2196,0,0,1865258,5016,0,0,2097258,2223,0,0,1846290,4301,0,0,2057438,3394,0,0,1993244,4542,0,0,2015504,1991,0,0,1699269,5987,0,0,2214967,3206,0,0,1972926,3063,0,0,1961934,5345,0,0,1991939,1882,0,0,1851837,2438,0,0,1843573,3611,0,0,1932431,4088,0,0,1954494,3158,0,0,1990569,5143,0,0,2166418,1591,0,0,1797513,64,0x7efe6534ee80,385200,235123,3425822,16384,25231955,144,48,0,48149,48149,3879686.0,3001835.0,6755.0,1100056.0,2079689.0,0.0,2992906.0,2681303.0,383487,245062,48149,0,48149,0,1540768.0,961788.0,0.0,0.0,64,0x7f70cb65ee80,0,3795954,4096,4096,0,3168303,4096,4096,0,3942584,4096,4096,0,2870922,4096,4096,0,3504329,4096,4096,0,3075561,4096,4096,0,3820575,4096,4096,0,3582506,4096,4096,0,3675772,4096,4096,0,3459978,4096,4096,0,3468680,4096,4096,0,4936444,4096,4096,0,3497050,4096,4096,0,3404795,4096,4096,0,3391701,4096,4096,0,3219885,4096,4096,0,4108812,4096,4096,0,4217713,4096,4096,0,3280018,4096,4096,0,3286185,4096,4096,0,3381267,4096,4096,0,3635427,4096,4096,0,4347830,4096,4096,0,3729323,4096,4096,0,3126123,4096,4096,0,3136475,4096,4096,0,3839895,4096,4096,0,3042150,4096,4096,0,3729788,4096,4096,0,3074817,4096,4096,0,3301463,4096,4096,0,3471018,4096,4096,64,0x7fa47a8ace80,204643,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,12831,29215,9943,550,0,46725,262679.0,0.0,188.0,262491.0,64,0x7f9fe3c32e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131436.0,0.0,720.0,131435.0,64,0x7f3ae95ace80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,47638,0,131602.0,131072.0,0.0,131104.0,64,0x7efb96f16e80,8192,0,4096,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,2187770153039589,2187770153063749 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7ff571ad6e80,4096,0,4512,0,4096,0,0,0,4096,0,5213,0,4096,0,1386,0,4096,0,2481,0,4096,0,584,0,4096,0,2080,0,4097,0,4945,0,4098,0,2983,0,4096,0,607,0,4100,0,1664,0,4096,0,1600,0,4096,0,2881,0,4096,0,4692,0,4096,0,2222,0,4144,0,258,0,4096,0,835,0,4096,0,457,0,4096,0,5185,0,4096,0,1243,0,4096,0,1994,0,4101,0,1931,0,4096,0,6584,0,4096,0,9,0,4096,0,1448,0,4216,0,5848,0,4144,0,1532,0,4096,0,1882,0,4096,0,1735,0,4096,0,520,0,4096,0,2304,0,4096,0,42,0,64,0x7fd1f4592e80,0.0,64,0x7f84dc044e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,70149.0,142189.0,64,0x7f68a83eae80,1198699,360448,163840,0,0,180224,114688,0,70543809.0,202818248.0,78627277.0,131072.0,0.0,598205.0,0,0,25503,77820.0,0.0,0.0,77820.0,64,0x7f00b5ba4e80,32768,0,0,0,16384,16384,393216,23205870,977.0,513783.0,0.0,524288.0,1110414.0,32768.0,0,0,0,22785,130424.0,130424.0,0.0,130424.0,64,0x7f73d15b0e80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8193,4097,8193,0,8241,4145,8241,0,8360,4264,8360,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f8e6204ee80,131072.0,131072.0,0.0,2704912.0,0.0,0.0,127283433.0,46238301.0,64,0x7fa610f6ee80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,87146.0,0.0,131112.0,0.0,64,0x7ffbaa404e80,0,0,48,0,65536,65536,0,0,31679,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,457,42958,1676,0,48.0,342.0,0.0,262144.0,64,0x7fba52a34e80,0,45589,0,0,0,45589,0,0,0,45589,0,0,0,45589,0,0,0,45589,0,0,0,45589,0,0,0,45589,0,0,0,45589,0,0,0,45589,0,0,0,45589,0,0,0,45589,0,0,0,45589,0,0,0,45589,0,0,0,45589,0,0,0,45589,0,0,0,45589,0,0,0,45589,0,0,0,45589,0,0,0,45589,0,0,0,45589,0,0,0,45589,0,0,0,45589,0,0,0,45589,0,0,0,45589,0,0,0,45589,0,0,0,45589,0,0,0,45589,0,0,0,45589,0,0,0,45589,0,0,0,45589,0,0,0,45589,0,0,0,45589,0,0,64,0x7f202b39ae80,2987,0,0,1491492,3270,0,0,1550886,1959,0,0,1345023,4643,0,0,1708515,1557,0,0,1408634,2287,0,0,1506174,1517,0,0,1388796,3802,0,0,1591863,2566,0,0,1461601,1474,0,0,1479585,1041,0,0,1282054,2384,0,0,1463316,3555,0,0,1627309,2349,0,0,1525766,2473,0,0,1497314,4278,0,0,1643892,3050,0,0,1542165,3024,0,0,1609720,1372,0,0,1349475,3273,0,0,1507709,3656,0,0,1604481,4428,0,0,1766407,1590,0,0,1323868,1879,0,0,1430960,2947,0,0,1472375,4068,0,0,1653921,2695,0,0,1455320,4046,0,0,1584700,3258,0,0,1517758,2282,0,0,1469440,1969,0,0,1420792,2346,0,0,1441309,64,0x7efe6534ee80,343056,230356,3362613,16384,24386396,0,48,0,42881,42881,3745298.0,3025524.0,6821.0,1191830.0,2096223.0,0.0,3016462.0,2704457.0,343048,239837,42881,0,42881,0,1372192.0,816238.0,0.0,0.0,64,0x7f70cb65ee80,0,3652804,2728,2728,0,2637279,2724,2724,0,3462131,2667,2667,0,3251822,2766,2766,0,2729710,2720,2720,0,2600050,2750,2750,0,2796527,2696,2696,0,2684289,2754,2754,0,3707285,2702,2702,0,2694044,2721,2721,0,3217135,2712,2712,0,3993831,2760,2760,0,2730332,2722,2722,0,3251703,2716,2716,0,2946643,2652,2652,0,3315391,2722,2722,0,3105750,2716,2716,0,5491960,2731,2731,0,3016600,2668,2668,0,2924733,2724,2724,0,3466340,2712,2712,0,3297904,2777,2777,0,2472927,2680,2680,0,3224869,2710,2710,0,3529877,2736,2736,0,2610772,2744,2744,0,2397608,2710,2710,0,2798964,2752,2752,0,2662454,2702,2702,0,2911047,2729,2729,0,2957621,2708,2708,0,2753926,2728,2728,64,0x7fa47a8ace80,148235,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13341,29725,9088,5598,0,42783,262605.0,0.0,47.0,262558.0,64,0x7f9fe3c32e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131445.0,0.0,744.0,131444.0,64,0x7f3ae95ace80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,240.0,524288.0,0.0,0.0,0,0,5483,47093,1064,131479.0,131072.0,0.0,131103.0,64,0x7efb96f16e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,2187770153157189,2187770153176229 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7ff571ad6e80,4096,0,296,0,4096,0,4466,0,4096,0,2331,0,4096,0,1005,0,4096,0,2451,0,4096,0,1395,0,4096,0,635,0,4097,0,1863,0,4098,0,1012,0,4096,0,2201,0,4100,0,0,0,4096,0,8006,0,4096,0,5034,0,4096,0,130,0,4096,0,3761,0,4144,0,141,0,4096,0,2567,0,4096,0,3012,0,4096,0,246,0,4096,0,776,0,4096,0,41,0,4102,0,1405,0,4096,0,2854,0,4096,0,1262,0,4096,0,54,0,4216,0,1988,0,4144,0,1280,0,4096,0,507,0,4096,0,0,0,4096,0,1802,0,4096,0,589,0,4096,0,1872,0,64,0x7fd1f4592e80,0.0,64,0x7f84dc044e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,22223.0,98044.0,64,0x7f68a83eae80,1427617,360448,163840,0,0,180224,114688,0,68962215.0,180811549.0,72307380.0,131072.0,0.0,602859.0,0,0,25508,100198.0,0.0,0.0,100198.0,64,0x7f00b5ba4e80,32768,0,0,0,16384,16384,393216,23155391,960.0,513920.0,0.0,524288.0,979258.0,32768.0,0,0,0,13630,86538.0,86538.0,0.0,86538.0,64,0x7f73d15b0e80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8193,4097,8193,0,8241,4145,8241,0,8360,4264,8360,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f8e6204ee80,131072.0,131072.0,0.0,2581012.0,0.0,0.0,125151202.0,47738389.0,64,0x7fa610f6ee80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86729.0,0.0,131112.0,0.0,64,0x7ffbaa404e80,0,0,48,0,65536,65536,0,0,30392,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,458,41697,1726,0,48.0,342.0,0.0,262144.0,64,0x7fba52a34e80,0,45160,0,0,0,45160,0,0,0,45160,0,0,0,45160,0,0,0,45160,0,0,0,45160,0,0,0,45160,0,0,0,45160,0,0,0,45160,0,0,0,45160,0,0,0,45160,0,0,0,45160,0,0,0,45160,0,0,0,45160,0,0,0,45160,0,0,0,45160,0,0,0,45160,0,0,0,45160,0,0,0,45160,0,0,0,45160,0,0,0,45160,0,0,0,45160,0,0,0,45160,0,0,0,45160,0,0,0,45160,0,0,0,45160,0,0,0,45160,0,0,0,45160,0,0,0,45160,0,0,0,45160,0,0,0,45160,0,0,0,45160,0,0,64,0x7f202b39ae80,3051,0,0,1510105,616,0,0,1255232,3364,0,0,1593260,2178,0,0,1394123,2954,0,0,1554667,1026,0,0,1367144,2756,0,0,1487091,2892,0,0,1530302,3852,0,0,1660573,1539,0,0,1358676,1772,0,0,1380763,1256,0,0,1390256,3468,0,0,1561955,419,0,0,1199671,2271,0,0,1421408,3982,0,0,1572638,3346,0,0,1541496,1317,0,0,1285190,692,0,0,1354519,1365,0,0,1284476,2491,0,0,1509015,2553,0,0,1620237,1626,0,0,1369134,2699,0,0,1480476,4310,0,0,1562218,1498,0,0,1380604,2496,0,0,1451387,4420,0,0,1602068,3822,0,0,1585312,796,0,0,1293089,2131,0,0,1456549,3474,0,0,1582087,64,0x7efe6534ee80,342624,229952,3363455,16384,24905053,0,48,0,42827,42827,3739141.0,3015977.0,7504.0,1095654.0,2108003.0,0.0,3006817.0,2696417.0,342616,239537,42827,0,42827,0,1370464.0,812549.0,0.0,0.0,64,0x7f70cb65ee80,0,3865380,2736,2736,0,2922624,2734,2734,0,4121532,2712,2712,0,2779635,2729,2729,0,3350672,2720,2720,0,2813936,2738,2738,0,3422615,2760,2760,0,2854627,2752,2752,0,2584349,2668,2668,0,3220852,2702,2702,0,3055966,2750,2750,0,5238778,2740,2740,0,3233980,2696,2696,0,2797174,2722,2722,0,3456838,2746,2746,0,2704227,2732,2732,0,3031718,2708,2708,0,3160033,2716,2716,0,3068653,2728,2728,0,2518622,2740,2740,0,2328744,2692,2692,0,2617418,2763,2763,0,3075440,2740,2740,0,2743417,2718,2718,0,2719672,2718,2718,0,2841533,2722,2722,0,3141947,2761,2761,0,2639713,2718,2718,0,3074631,2690,2690,0,2265885,2724,2724,0,2790808,2775,2775,0,2640847,2720,2720,64,0x7fa47a8ace80,205119,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13361,29745,8621,3339,0,40912,262536.0,0.0,47.0,262489.0,64,0x7f9fe3c32e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131418.0,0.0,690.0,131417.0,64,0x7f3ae95ace80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,3873,39380,0,131462.0,131072.0,0.0,87078.0,64,0x7efb96f16e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,2187770153197349,2187770153216709 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_1,obj_1,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_2,obj_2,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_3,obj_3,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_4,obj_4,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_5,obj_5,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_6,obj_6,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_7,obj_7,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_8,obj_8,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_9,obj_9,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_10,obj_10,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_11,obj_11,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_12,obj_12,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_13,obj_13,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_14,obj_14,TCC_EA_ATOMIC_LEVEL_sum,wave_size_15,obj_15,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_16,obj_16,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f2ff3a2ce80,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f38f5026e80,0,4918466,4096,4096,0,4386322,4096,4096,0,3618875,4096,4096,0,3646552,4096,4096,0,3230998,4096,4096,0,3667123,4096,4096,0,3378349,4096,4096,0,3500357,4096,4096,0,2951144,4096,4096,0,4847587,4096,4096,0,3769941,4096,4096,0,4270450,4096,4096,0,3490697,4096,4096,0,4909128,4096,4096,0,3707545,4096,4096,0,2888229,4096,4096,0,5159646,4096,4096,0,3719452,4096,4096,0,5017223,4096,4096,0,2647461,4096,4096,0,2952867,4096,4096,0,4754845,4096,4096,0,3215894,4096,4096,0,3130743,4096,4096,0,3450164,4096,4096,0,4150606,4096,4096,0,3080691,4096,4096,0,3667284,4096,4096,0,4444846,4096,4096,0,3304170,4096,4096,0,3631015,4096,4096,0,2774500,4096,4096,64,0x7f2651730e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,47208,0,131516.0,131072.0,0.0,131104.0,64,0x7f10a1dace80,186415,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13588,29972,9930,550,0,46965,262603.0,0.0,188.0,262415.0,64,0x7f54835f8e80,0,0,192,0,65536,64517,48,1355,32344,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,538,48169,1784,0,48.0,267.0,0.0,262288.0,64,0x7f198b1aae80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131499.0,0.0,846.0,131498.0,64,0x7f2f2cb3ae80,131072.0,131072.0,0.0,2568521.0,0.0,0.0,118890799.0,60770673.0,64,0x7fc916404e80,32768,0,0,0,16384,16384,393216,23843256,960.0,513869.0,0.0,524288.0,1196279.0,32768.0,0,0,0,16802,131072.0,131072.0,0.0,131072.0,64,0x7f68399ece80,0,8192,4096,8192,0,8192,4096,8192,141,8195,4240,8336,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8312,4216,8312,0,8240,4144,8240,47,8241,4192,8288,0,8192,4096,8192,0,8322,4226,8322,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f04bf79ce80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,83775.0,151157.0,64,0x7f7d506f8e80,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,64,0x7f7b2b544e80,381040,231164,3385172,16384,24968233,144,48,0,47629,47629,3820148.0,2957388.0,5424.0,990164.0,2034069.0,0.0,2948190.0,2636777.0,379647,241114,47629,0,47629,0,1524128.0,947184.0,0.0,0.0,64,0x7ff4f36e8e80,4096,0,978,0,4158,0,1001,0,4096,0,414,0,4096,0,0,0,4096,0,1458,0,4096,0,0,0,4096,0,0,0,4096,0,1092,0,4096,0,2987,0,4096,0,76,0,4096,0,83,0,4147,0,343,0,4097,0,609,0,4264,0,1179,0,4096,0,7370,0,4096,0,0,0,4096,0,785,0,4096,0,5350,0,4096,0,706,0,4096,0,1201,0,4144,0,0,0,4096,0,1058,0,4096,0,548,0,4096,0,36,0,4096,0,0,0,4096,0,6958,0,4096,0,0,0,4096,0,7,0,4096,0,1878,0,4096,0,8,0,4096,0,374,0,4096,0,3352,0,64,0x7fdaab01ee80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86816.0,44256.0,131111.0,0.0,64,0x7f9df031ce80,0.0,64,0x7f386c6e8e80,1910718,360448,163840,0,0,180224,114688,0,66539140.0,174421414.0,69256432.0,131072.0,0.0,580885.0,0,0,26416,97053.0,0.0,0.0,97053.0,64,0x7f3181e46e80,3750,0,0,2061528,4846,0,0,2080547,514,0,0,1597659,7024,0,0,2252326,1970,0,0,1894437,2134,0,0,1868633,2647,0,0,1916586,1238,0,0,1785532,2938,0,0,1948555,3066,0,0,1995087,1252,0,0,1779475,2203,0,0,1929115,786,0,0,1678182,2342,0,0,1917609,1229,0,0,1758845,4634,0,0,2114935,1336,0,0,1794762,3775,0,0,1990163,1944,0,0,1824254,4676,0,0,2077567,3157,0,0,1905990,3482,0,0,2009873,1780,0,0,1840598,2690,0,0,1943182,2748,0,0,1949612,1478,0,0,1780467,844,0,0,1690141,3646,0,0,1990961,2463,0,0,1940602,2871,0,0,1942940,822,0,0,1629396,2696,0,0,1855922,194175534630063,194175534654063 +1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f2ff3a2ce80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f38f5026e80,0,3730758,2710,2710,0,2857500,2714,2714,0,3320981,2684,2684,0,3627348,2699,2699,0,4631889,2680,2680,0,3092063,2716,2716,0,4451987,2726,2726,0,3029416,2704,2704,0,2767081,2694,2694,0,3629576,2672,2672,0,3461007,2732,2732,0,4807161,2734,2734,0,3027758,2689,2689,0,2820472,2690,2690,0,5184852,2696,2696,0,3357257,2696,2696,0,3122965,2684,2684,0,3645606,2696,2696,0,3775492,2714,2714,0,5505112,2708,2708,0,2980985,2710,2710,0,2962877,2751,2751,0,3885791,2700,2700,0,3420854,2678,2678,0,3643768,2704,2704,0,2954889,2702,2702,0,3699972,2770,2770,0,3494429,2712,2712,0,5008264,2696,2696,0,2361236,2703,2703,0,3052037,2736,2736,0,3315948,2692,2692,64,0x7f2651730e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,37896,0,131120.0,131072.0,0.0,86566.0,64,0x7f10a1dace80,188416,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,14948,31332,8504,2935,0,41565,262480.0,0.0,47.0,262433.0,64,0x7f54835f8e80,0,0,48,0,65536,65536,0,0,30911,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,458,42159,1785,0,48.0,269.0,0.0,262144.0,64,0x7f198b1aae80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131502.0,0.0,858.0,131501.0,64,0x7f2f2cb3ae80,131072.0,131072.0,0.0,2608589.0,0.0,0.0,131582951.0,47551352.0,64,0x7fc916404e80,32768,0,0,0,16384,16384,393216,23044109,960.0,513965.0,0.0,524288.0,1029652.0,32768.0,0,0,0,17369,86880.0,86880.0,0.0,86880.0,64,0x7f68399ece80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8312,4216,8312,0,8240,4144,8240,47,8241,4192,8288,0,8192,4096,8192,0,8318,4222,8318,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f04bf79ce80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,64651.0,132167.0,64,0x7f7d506f8e80,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,64,0x7f7b2b544e80,345736,230713,3366319,16384,24790999,0,48,0,43216,43216,3750746.0,3029503.0,6947.0,1039487.0,1983035.0,0.0,3020525.0,2708717.0,345728,240499,43216,0,43216,0,1382912.0,809587.0,0.0,0.0,64,0x7ff4f36e8e80,4096,0,5891,0,4101,0,1534,0,4096,0,879,0,4097,0,1291,0,4096,0,2092,0,4096,0,995,0,4096,0,0,0,4096,0,124,0,4096,0,802,0,4097,0,907,0,4096,0,0,0,4144,0,306,0,4097,0,500,0,4264,0,2372,0,4096,0,737,0,4096,0,0,0,4096,0,487,0,4096,0,4067,0,4096,0,788,0,4097,0,0,0,4144,0,387,0,4098,0,8199,0,4096,0,366,0,4096,0,0,0,4096,0,243,0,4096,0,409,0,4096,0,123,0,4096,0,312,0,4096,0,457,0,4096,0,107,0,4096,0,0,0,4096,0,0,0,64,0x7fdaab01ee80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86987.0,0.0,131112.0,0.0,64,0x7f9df031ce80,0.0,64,0x7f386c6e8e80,1864794,360448,163840,0,0,180224,114688,0,75023055.0,181388560.0,87290481.0,131072.0,0.0,1263903.0,0,0,25952,78370.0,0.0,0.0,78370.0,64,0x7f3181e46e80,1617,0,0,1446712,1768,0,0,1399721,778,0,0,1282477,2725,0,0,1531793,1029,0,0,1309542,1118,0,0,1316644,2165,0,0,1466185,1964,0,0,1523918,584,0,0,1314175,1262,0,0,1346603,386,0,0,1209320,690,0,0,1242367,3651,0,0,1633179,1765,0,0,1435961,1484,0,0,1381723,787,0,0,1285247,1835,0,0,1424774,1178,0,0,1361958,2350,0,0,1459414,273,0,0,1237649,189,0,0,1187320,1491,0,0,1421555,2789,0,0,1523250,744,0,0,1261382,2044,0,0,1550260,1322,0,0,1379589,1369,0,0,1339007,3946,0,0,1568806,1197,0,0,1360930,4167,0,0,1673404,1069,0,0,1314914,1252,0,0,1295860,194175534674223,194175534693583 +2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f2ff3a2ce80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f38f5026e80,0,4039275,2704,2704,0,4218459,2720,2720,0,3524312,2670,2670,0,3860485,2706,2706,0,4373901,2686,2686,0,4390180,2752,2752,0,3689027,2692,2692,0,4776511,2688,2688,0,3537225,2700,2700,0,3735470,2696,2696,0,2920512,2696,2696,0,4649975,2740,2740,0,3693519,2696,2696,0,4326681,2685,2685,0,3189227,2702,2702,0,3640645,2686,2686,0,3816684,2678,2678,0,4811703,2720,2720,0,3945291,2674,2674,0,3852008,2696,2696,0,3814103,2702,2702,0,4344788,2732,2732,0,4555691,2680,2680,0,3329113,2680,2680,0,3585353,2660,2660,0,3987490,2698,2698,0,3424274,2730,2730,0,3841736,2684,2684,0,4695746,2703,2703,0,3509414,2693,2693,0,3533763,2686,2686,0,3726479,2696,2696,64,0x7f2651730e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,3254,38225,0,131432.0,131072.0,0.0,86863.0,64,0x7f10a1dace80,187879,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13677,30061,8577,2931,0,40757,262448.0,0.0,47.0,262401.0,64,0x7f54835f8e80,0,0,48,0,65536,65536,0,0,30529,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,458,41969,1694,0,48.0,269.0,0.0,262144.0,64,0x7f198b1aae80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131513.0,0.0,880.0,131512.0,64,0x7f2f2cb3ae80,131072.0,131072.0,0.0,2561610.0,0.0,0.0,122364251.0,46993469.0,64,0x7fc916404e80,32768,0,0,0,16384,16384,393216,23716225,960.0,513941.0,0.0,524288.0,1219967.0,32768.0,0,0,0,14300,86593.0,86593.0,0.0,86593.0,64,0x7f68399ece80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8312,4216,8312,0,8240,4144,8240,47,8241,4192,8288,0,8192,4096,8192,0,8323,4227,8323,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f04bf79ce80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,39985.0,105962.0,64,0x7f7d506f8e80,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,64,0x7f7b2b544e80,343144,231940,3377112,16384,24588238,0,48,0,42892,42892,3763830.0,3044981.0,5993.0,1281767.0,2075963.0,0.0,3035894.0,2726534.0,343136,240048,42892,0,42892,0,1372544.0,816637.0,0.0,0.0,64,0x7ff4f36e8e80,4096,0,1856,0,4131,0,1295,0,4096,0,2148,0,4097,0,2166,0,4096,0,1325,0,4096,0,1073,0,4096,0,1187,0,4096,0,671,0,4096,0,1182,0,4097,0,721,0,4096,0,509,0,4144,0,1724,0,4097,0,3309,0,4264,0,7334,0,4096,0,807,0,4096,0,308,0,4096,0,2053,0,4096,0,4881,0,4096,0,1255,0,4097,0,220,0,4144,0,3038,0,4098,0,1136,0,4096,0,2457,0,4096,0,763,0,4096,0,161,0,4096,0,2087,0,4096,0,3291,0,4096,0,143,0,4096,0,114,0,4096,0,29,0,4096,0,580,0,4096,0,1265,0,64,0x7fdaab01ee80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86738.0,0.0,131112.0,0.0,64,0x7f9df031ce80,0.0,64,0x7f386c6e8e80,1616194,360448,163840,0,0,180224,114688,0,70097697.0,201432489.0,69154637.0,131072.0,0.0,808778.0,0,0,26015,91632.0,0.0,0.0,91632.0,64,0x7f3181e46e80,1882,0,0,1459609,899,0,0,1264047,3515,0,0,1637505,4640,0,0,1673873,1149,0,0,1346630,3027,0,0,1604086,3867,0,0,1649127,2210,0,0,1492681,896,0,0,1384333,1860,0,0,1481329,1826,0,0,1445826,581,0,0,1299729,3116,0,0,1597195,787,0,0,1318848,1228,0,0,1347218,4675,0,0,1676980,1131,0,0,1323690,100,0,0,1202894,866,0,0,1372352,3110,0,0,1616044,1060,0,0,1360500,1397,0,0,1455057,2844,0,0,1539021,1756,0,0,1442569,2682,0,0,1547143,1149,0,0,1339255,4079,0,0,1662855,3832,0,0,1622283,3414,0,0,1629849,1533,0,0,1379329,4458,0,0,1734060,2138,0,0,1429122,194175534779503,194175534798543 diff --git a/tests/workloads/kernel_substr/MI100/sysinfo.csv b/tests/workloads/kernel_substr/MI100/sysinfo.csv index 244e3a0046..05fc83f224 100644 --- a/tests/workloads/kernel_substr/MI100/sysinfo.csv +++ b/tests/workloads/kernel_substr/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -kernel_substr,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Fri Mar 1 16:44:33 2024 (CST),1,t006-003.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651240,,5.7.1-98,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +kernel_substr,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 07 Mar 2024 01:07:08 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/kernel_substr/MI100/timestamps.csv b/tests/workloads/kernel_substr/MI100/timestamps.csv index 458115dfb5..0bb2631ecf 100644 --- a/tests/workloads/kernel_substr/MI100/timestamps.csv +++ b/tests/workloads/kernel_substr/MI100/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,2836237,2836237,1048576,256,0,0,8,8,16,64,0x0,0x7f9c41858e80,2187770153013918,2187770153039589,2187770153063749,2187770153075112 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,2836237,2836237,1048576,256,0,0,8,8,16,64,0x0,0x7f9c41858e80,2187770153076695,2187770153157189,2187770153176229,2187770153177465 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,2836237,2836237,1048576,256,0,0,8,8,16,64,0x0,0x7f9c41858e80,2187770153189046,2187770153197349,2187770153216709,2187770153218061 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,141682,141682,1048576,256,0,0,8,8,16,64,0x0,0x7feb54db6e80,194175534602589,194175534630063,194175534654063,194175534670638 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,141682,141682,1048576,256,0,0,8,8,16,64,0x0,0x7feb54db6e80,194175534666220,194175534674223,194175534693583,194175534776909 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,141682,141682,1048576,256,0,0,8,8,16,64,0x0,0x7feb54db6e80,194175534704713,194175534779503,194175534798543,194175534799382 diff --git a/tests/workloads/kernel_substr/MI200/SQ_IFETCH_LEVEL.csv b/tests/workloads/kernel_substr/MI200/SQ_IFETCH_LEVEL.csv new file mode 100644 index 0000000000..8b70492427 --- /dev/null +++ b/tests/workloads/kernel_substr/MI200/SQ_IFETCH_LEVEL.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,291276,291276,1048576,256,0,0,8,0,16,64,0x0,0x7f1828160ec0,27737,27737,16384,65536,13722,1525308,198261588061508,198274458325591,198274458345911,198261603806363 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,291276,291276,1048576,256,0,0,8,0,16,64,0x0,0x7f1828160ec0,41413,41413,16384,65536,9460,1048596,198261603830830,198274458365591,198274458381111,198261604082847 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,291276,291276,1048576,256,0,0,8,0,16,64,0x0,0x7f1828160ec0,40275,40275,16384,65536,9096,1048700,198261604112302,198274458443671,198274458459991,198261604256605 diff --git a/tests/workloads/kernel_substr/MI200/SQ_INST_LEVEL_LDS.csv b/tests/workloads/kernel_substr/MI200/SQ_INST_LEVEL_LDS.csv new file mode 100644 index 0000000000..c71c742441 --- /dev/null +++ b/tests/workloads/kernel_substr/MI200/SQ_INST_LEVEL_LDS.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,291478,291478,1048576,256,0,0,8,0,16,64,0x0,0x7f1f8e050ec0,0,0,0,198262073743594,198274458325591,198274458345911,198262089831408 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,291478,291478,1048576,256,0,0,8,0,16,64,0x0,0x7f1f8e050ec0,0,0,0,198262089848571,198274458365591,198274458381111,198262090150562 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,291478,291478,1048576,256,0,0,8,0,16,64,0x0,0x7f1f8e050ec0,0,0,0,198262090176932,198274458443671,198274458459991,198262090341423 diff --git a/tests/workloads/kernel_substr/MI200/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/kernel_substr/MI200/SQ_INST_LEVEL_SMEM.csv new file mode 100644 index 0000000000..53d0c0d4e9 --- /dev/null +++ b/tests/workloads/kernel_substr/MI200/SQ_INST_LEVEL_SMEM.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,291685,291685,1048576,256,0,0,8,0,16,64,0x0,0x7fddd2fc4ec0,65536,187092,20917768,198262558091736,198274458325591,198274458345911,198262574290691 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,291685,291685,1048576,256,0,0,8,0,16,64,0x0,0x7fddd2fc4ec0,65536,245200,27582200,198262574309346,198274458365591,198274458381111,198262574602852 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,291685,291685,1048576,256,0,0,8,0,16,64,0x0,0x7fddd2fc4ec0,65536,263490,29654280,198262574629011,198274458443671,198274458459991,198262574756552 diff --git a/tests/workloads/kernel_substr/MI200/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/kernel_substr/MI200/SQ_INST_LEVEL_VMEM.csv new file mode 100644 index 0000000000..1ead472d42 --- /dev/null +++ b/tests/workloads/kernel_substr/MI200/SQ_INST_LEVEL_VMEM.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,291870,291870,1048576,256,0,0,8,0,16,64,0x0,0x7f5a50b30ec0,32768,288882,32369320,198263038694323,198274458325591,198274458345911,198263054914017 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,291870,291870,1048576,256,0,0,8,0,16,64,0x0,0x7f5a50b30ec0,32768,596098,66767128,198263054932602,198274458365591,198274458381111,198263055228652 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,291870,291870,1048576,256,0,0,8,0,16,64,0x0,0x7f5a50b30ec0,32768,572975,64171428,198263055254551,198274458443671,198274458459991,198263055412490 diff --git a/tests/workloads/kernel_substr/MI200/SQ_LEVEL_WAVES.csv b/tests/workloads/kernel_substr/MI200/SQ_LEVEL_WAVES.csv new file mode 100644 index 0000000000..5a7e560ed0 --- /dev/null +++ b/tests/workloads/kernel_substr/MI200/SQ_LEVEL_WAVES.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,292068,292068,1048576,256,0,0,8,0,16,64,0x0,0x7f06a0314ec0,27371,27371,10912,218976,16384,10605927,126253,0,42923692,198263526253279,198274458325591,198274458345911,198263542014035 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,292068,292068,1048576,256,0,0,8,0,16,64,0x0,0x7f06a0314ec0,41749,41749,13458,334000,16384,19718416,225192,0,79338420,198263542042509,198274458365591,198274458381111,198263542340142 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,292068,292068,1048576,256,0,0,8,0,16,64,0x0,0x7f06a0314ec0,41423,41423,13486,331392,16384,19225946,220329,0,77380152,198263542374808,198274458443671,198274458459991,198263542550089 diff --git a/tests/workloads/kernel_substr/MI200/perfmon/SQ_IFETCH_LEVEL.txt b/tests/workloads/kernel_substr/MI200/perfmon/SQ_IFETCH_LEVEL.txt new file mode 100644 index 0000000000..3b68e4a38c --- /dev/null +++ b/tests/workloads/kernel_substr/MI200/perfmon/SQ_IFETCH_LEVEL.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: vecCopy diff --git a/tests/workloads/kernel_substr/MI200/perfmon/SQ_INST_LEVEL_LDS.txt b/tests/workloads/kernel_substr/MI200/perfmon/SQ_INST_LEVEL_LDS.txt new file mode 100644 index 0000000000..f0b07be064 --- /dev/null +++ b/tests/workloads/kernel_substr/MI200/perfmon/SQ_INST_LEVEL_LDS.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: vecCopy diff --git a/tests/workloads/kernel_substr/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt b/tests/workloads/kernel_substr/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt new file mode 100644 index 0000000000..b65eec769f --- /dev/null +++ b/tests/workloads/kernel_substr/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: vecCopy diff --git a/tests/workloads/kernel_substr/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt b/tests/workloads/kernel_substr/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt new file mode 100644 index 0000000000..3fa3c03388 --- /dev/null +++ b/tests/workloads/kernel_substr/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: vecCopy diff --git a/tests/workloads/kernel_substr/MI200/perfmon/SQ_LEVEL_WAVES.txt b/tests/workloads/kernel_substr/MI200/perfmon/SQ_LEVEL_WAVES.txt new file mode 100644 index 0000000000..8661e665cb --- /dev/null +++ b/tests/workloads/kernel_substr/MI200/perfmon/SQ_LEVEL_WAVES.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: vecCopy diff --git a/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_0.txt b/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_0.txt new file mode 100644 index 0000000000..69f342e7c8 --- /dev/null +++ b/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_0.txt @@ -0,0 +1,5 @@ +pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES SQ_INSTS_VALU_CVT SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU GRBM_COUNT GRBM_GUI_ACTIVE TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum TA_TA_BUSY_sum TA_BUFFER_WAVEFRONTS_sum TD_TD_BUSY_sum TD_TC_STALL_sum SPI_CSN_WINDOW_VALID SPI_CSN_BUSY CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum + +gpu: +range: +kernel: vecCopy diff --git a/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_1.txt b/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_1.txt new file mode 100644 index 0000000000..0b6980af5f --- /dev/null +++ b/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_1.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VSKIPPED SQ_INSTS SQ_INSTS_VALU SQ_INSTS_VALU_ADD_F16 SQ_INSTS_VALU_MUL_F16 SQ_INSTS_VALU_FMA_F16 SQ_INSTS_VALU_TRANS_F16 SQ_INSTS_VALU_ADD_F32 GRBM_SPI_BUSY TCP_READ_TAGCONFLICT_STALL_CYCLES_sum TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum TCP_TA_TCP_STATE_READ_sum TA_BUFFER_READ_WAVEFRONTS_sum TA_BUFFER_WRITE_WAVEFRONTS_sum TD_SPI_STALL_sum TD_LOAD_WAVEFRONT_sum SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum + +gpu: +range: +kernel: vecCopy diff --git a/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_10.txt b/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_10.txt new file mode 100644 index 0000000000..273f5e8845 --- /dev/null +++ b/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_10.txt @@ -0,0 +1,5 @@ +pmc: SQC_TC_DATA_WRITE_REQ SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES + +gpu: +range: +kernel: vecCopy diff --git a/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_11.txt b/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_11.txt new file mode 100644 index 0000000000..44076517f1 --- /dev/null +++ b/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_11.txt @@ -0,0 +1,5 @@ +pmc: SQC_ICACHE_MISSES_DUPLICATE SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE + +gpu: +range: +kernel: vecCopy diff --git a/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_12.txt b/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_12.txt new file mode 100644 index 0000000000..227e3e928b --- /dev/null +++ b/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_12.txt @@ -0,0 +1,5 @@ +pmc: SQC_DCACHE_REQ_READ_1 SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 + +gpu: +range: +kernel: vecCopy diff --git a/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_13.txt b/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_13.txt new file mode 100644 index 0000000000..91838b92f1 --- /dev/null +++ b/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_13.txt @@ -0,0 +1,5 @@ +pmc: TCC_ATOMIC[0] TCC_CYCLE[0] TCC_EA_ATOMIC[0] TCC_EA_ATOMIC_LEVEL[0] TCC_ATOMIC[1] TCC_CYCLE[1] TCC_EA_ATOMIC[1] TCC_EA_ATOMIC_LEVEL[1] TCC_ATOMIC[2] TCC_CYCLE[2] TCC_EA_ATOMIC[2] TCC_EA_ATOMIC_LEVEL[2] TCC_ATOMIC[3] TCC_CYCLE[3] TCC_EA_ATOMIC[3] TCC_EA_ATOMIC_LEVEL[3] TCC_ATOMIC[4] TCC_CYCLE[4] TCC_EA_ATOMIC[4] TCC_EA_ATOMIC_LEVEL[4] TCC_ATOMIC[5] TCC_CYCLE[5] TCC_EA_ATOMIC[5] TCC_EA_ATOMIC_LEVEL[5] TCC_ATOMIC[6] TCC_CYCLE[6] TCC_EA_ATOMIC[6] TCC_EA_ATOMIC_LEVEL[6] TCC_ATOMIC[7] TCC_CYCLE[7] TCC_EA_ATOMIC[7] TCC_EA_ATOMIC_LEVEL[7] TCC_ATOMIC[8] TCC_CYCLE[8] TCC_EA_ATOMIC[8] TCC_EA_ATOMIC_LEVEL[8] TCC_ATOMIC[9] TCC_CYCLE[9] TCC_EA_ATOMIC[9] TCC_EA_ATOMIC_LEVEL[9] TCC_ATOMIC[10] TCC_CYCLE[10] TCC_EA_ATOMIC[10] TCC_EA_ATOMIC_LEVEL[10] TCC_ATOMIC[11] TCC_CYCLE[11] TCC_EA_ATOMIC[11] TCC_EA_ATOMIC_LEVEL[11] TCC_ATOMIC[12] TCC_CYCLE[12] TCC_EA_ATOMIC[12] TCC_EA_ATOMIC_LEVEL[12] TCC_ATOMIC[13] TCC_CYCLE[13] TCC_EA_ATOMIC[13] TCC_EA_ATOMIC_LEVEL[13] TCC_ATOMIC[14] TCC_CYCLE[14] TCC_EA_ATOMIC[14] TCC_EA_ATOMIC_LEVEL[14] TCC_ATOMIC[15] TCC_CYCLE[15] TCC_EA_ATOMIC[15] TCC_EA_ATOMIC_LEVEL[15] TCC_ATOMIC[16] TCC_CYCLE[16] TCC_EA_ATOMIC[16] TCC_EA_ATOMIC_LEVEL[16] TCC_ATOMIC[17] TCC_CYCLE[17] TCC_EA_ATOMIC[17] TCC_EA_ATOMIC_LEVEL[17] TCC_ATOMIC[18] TCC_CYCLE[18] TCC_EA_ATOMIC[18] TCC_EA_ATOMIC_LEVEL[18] TCC_ATOMIC[19] TCC_CYCLE[19] TCC_EA_ATOMIC[19] TCC_EA_ATOMIC_LEVEL[19] TCC_ATOMIC[20] TCC_CYCLE[20] TCC_EA_ATOMIC[20] TCC_EA_ATOMIC_LEVEL[20] TCC_ATOMIC[21] TCC_CYCLE[21] TCC_EA_ATOMIC[21] TCC_EA_ATOMIC_LEVEL[21] TCC_ATOMIC[22] TCC_CYCLE[22] TCC_EA_ATOMIC[22] TCC_EA_ATOMIC_LEVEL[22] TCC_ATOMIC[23] TCC_CYCLE[23] TCC_EA_ATOMIC[23] TCC_EA_ATOMIC_LEVEL[23] TCC_ATOMIC[24] TCC_CYCLE[24] TCC_EA_ATOMIC[24] TCC_EA_ATOMIC_LEVEL[24] TCC_ATOMIC[25] TCC_CYCLE[25] TCC_EA_ATOMIC[25] TCC_EA_ATOMIC_LEVEL[25] TCC_ATOMIC[26] TCC_CYCLE[26] TCC_EA_ATOMIC[26] TCC_EA_ATOMIC_LEVEL[26] TCC_ATOMIC[27] TCC_CYCLE[27] TCC_EA_ATOMIC[27] TCC_EA_ATOMIC_LEVEL[27] TCC_ATOMIC[28] TCC_CYCLE[28] TCC_EA_ATOMIC[28] TCC_EA_ATOMIC_LEVEL[28] TCC_ATOMIC[29] TCC_CYCLE[29] TCC_EA_ATOMIC[29] TCC_EA_ATOMIC_LEVEL[29] TCC_ATOMIC[30] TCC_CYCLE[30] TCC_EA_ATOMIC[30] TCC_EA_ATOMIC_LEVEL[30] TCC_ATOMIC[31] TCC_CYCLE[31] TCC_EA_ATOMIC[31] TCC_EA_ATOMIC_LEVEL[31] + +gpu: +range: +kernel: vecCopy diff --git a/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_14.txt b/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_14.txt new file mode 100644 index 0000000000..3f8f0de0e8 --- /dev/null +++ b/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_14.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_EA_RDREQ_GMI_CREDIT_STALL[0] TCC_EA_RDREQ[1] TCC_EA_RDREQ_32B[1] TCC_EA_RDREQ_DRAM_CREDIT_STALL[1] TCC_EA_RDREQ_GMI_CREDIT_STALL[1] TCC_EA_RDREQ[2] TCC_EA_RDREQ_32B[2] TCC_EA_RDREQ_DRAM_CREDIT_STALL[2] TCC_EA_RDREQ_GMI_CREDIT_STALL[2] TCC_EA_RDREQ[3] TCC_EA_RDREQ_32B[3] TCC_EA_RDREQ_DRAM_CREDIT_STALL[3] TCC_EA_RDREQ_GMI_CREDIT_STALL[3] TCC_EA_RDREQ[4] TCC_EA_RDREQ_32B[4] TCC_EA_RDREQ_DRAM_CREDIT_STALL[4] TCC_EA_RDREQ_GMI_CREDIT_STALL[4] TCC_EA_RDREQ[5] TCC_EA_RDREQ_32B[5] TCC_EA_RDREQ_DRAM_CREDIT_STALL[5] TCC_EA_RDREQ_GMI_CREDIT_STALL[5] TCC_EA_RDREQ[6] TCC_EA_RDREQ_32B[6] TCC_EA_RDREQ_DRAM_CREDIT_STALL[6] TCC_EA_RDREQ_GMI_CREDIT_STALL[6] TCC_EA_RDREQ[7] TCC_EA_RDREQ_32B[7] TCC_EA_RDREQ_DRAM_CREDIT_STALL[7] TCC_EA_RDREQ_GMI_CREDIT_STALL[7] TCC_EA_RDREQ[8] TCC_EA_RDREQ_32B[8] TCC_EA_RDREQ_DRAM_CREDIT_STALL[8] TCC_EA_RDREQ_GMI_CREDIT_STALL[8] TCC_EA_RDREQ[9] TCC_EA_RDREQ_32B[9] TCC_EA_RDREQ_DRAM_CREDIT_STALL[9] TCC_EA_RDREQ_GMI_CREDIT_STALL[9] TCC_EA_RDREQ[10] TCC_EA_RDREQ_32B[10] TCC_EA_RDREQ_DRAM_CREDIT_STALL[10] TCC_EA_RDREQ_GMI_CREDIT_STALL[10] TCC_EA_RDREQ[11] TCC_EA_RDREQ_32B[11] TCC_EA_RDREQ_DRAM_CREDIT_STALL[11] TCC_EA_RDREQ_GMI_CREDIT_STALL[11] TCC_EA_RDREQ[12] TCC_EA_RDREQ_32B[12] TCC_EA_RDREQ_DRAM_CREDIT_STALL[12] TCC_EA_RDREQ_GMI_CREDIT_STALL[12] TCC_EA_RDREQ[13] TCC_EA_RDREQ_32B[13] TCC_EA_RDREQ_DRAM_CREDIT_STALL[13] TCC_EA_RDREQ_GMI_CREDIT_STALL[13] TCC_EA_RDREQ[14] TCC_EA_RDREQ_32B[14] TCC_EA_RDREQ_DRAM_CREDIT_STALL[14] TCC_EA_RDREQ_GMI_CREDIT_STALL[14] TCC_EA_RDREQ[15] TCC_EA_RDREQ_32B[15] TCC_EA_RDREQ_DRAM_CREDIT_STALL[15] TCC_EA_RDREQ_GMI_CREDIT_STALL[15] TCC_EA_RDREQ[16] TCC_EA_RDREQ_32B[16] TCC_EA_RDREQ_DRAM_CREDIT_STALL[16] TCC_EA_RDREQ_GMI_CREDIT_STALL[16] TCC_EA_RDREQ[17] TCC_EA_RDREQ_32B[17] TCC_EA_RDREQ_DRAM_CREDIT_STALL[17] TCC_EA_RDREQ_GMI_CREDIT_STALL[17] TCC_EA_RDREQ[18] TCC_EA_RDREQ_32B[18] TCC_EA_RDREQ_DRAM_CREDIT_STALL[18] TCC_EA_RDREQ_GMI_CREDIT_STALL[18] TCC_EA_RDREQ[19] TCC_EA_RDREQ_32B[19] TCC_EA_RDREQ_DRAM_CREDIT_STALL[19] TCC_EA_RDREQ_GMI_CREDIT_STALL[19] TCC_EA_RDREQ[20] TCC_EA_RDREQ_32B[20] TCC_EA_RDREQ_DRAM_CREDIT_STALL[20] TCC_EA_RDREQ_GMI_CREDIT_STALL[20] TCC_EA_RDREQ[21] TCC_EA_RDREQ_32B[21] TCC_EA_RDREQ_DRAM_CREDIT_STALL[21] TCC_EA_RDREQ_GMI_CREDIT_STALL[21] TCC_EA_RDREQ[22] TCC_EA_RDREQ_32B[22] TCC_EA_RDREQ_DRAM_CREDIT_STALL[22] TCC_EA_RDREQ_GMI_CREDIT_STALL[22] TCC_EA_RDREQ[23] TCC_EA_RDREQ_32B[23] TCC_EA_RDREQ_DRAM_CREDIT_STALL[23] TCC_EA_RDREQ_GMI_CREDIT_STALL[23] TCC_EA_RDREQ[24] TCC_EA_RDREQ_32B[24] TCC_EA_RDREQ_DRAM_CREDIT_STALL[24] TCC_EA_RDREQ_GMI_CREDIT_STALL[24] TCC_EA_RDREQ[25] TCC_EA_RDREQ_32B[25] TCC_EA_RDREQ_DRAM_CREDIT_STALL[25] TCC_EA_RDREQ_GMI_CREDIT_STALL[25] TCC_EA_RDREQ[26] TCC_EA_RDREQ_32B[26] TCC_EA_RDREQ_DRAM_CREDIT_STALL[26] TCC_EA_RDREQ_GMI_CREDIT_STALL[26] TCC_EA_RDREQ[27] TCC_EA_RDREQ_32B[27] TCC_EA_RDREQ_DRAM_CREDIT_STALL[27] TCC_EA_RDREQ_GMI_CREDIT_STALL[27] TCC_EA_RDREQ[28] TCC_EA_RDREQ_32B[28] TCC_EA_RDREQ_DRAM_CREDIT_STALL[28] TCC_EA_RDREQ_GMI_CREDIT_STALL[28] TCC_EA_RDREQ[29] TCC_EA_RDREQ_32B[29] TCC_EA_RDREQ_DRAM_CREDIT_STALL[29] TCC_EA_RDREQ_GMI_CREDIT_STALL[29] TCC_EA_RDREQ[30] TCC_EA_RDREQ_32B[30] TCC_EA_RDREQ_DRAM_CREDIT_STALL[30] TCC_EA_RDREQ_GMI_CREDIT_STALL[30] TCC_EA_RDREQ[31] TCC_EA_RDREQ_32B[31] TCC_EA_RDREQ_DRAM_CREDIT_STALL[31] TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + +gpu: +range: +kernel: vecCopy diff --git a/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_15.txt b/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_15.txt new file mode 100644 index 0000000000..8e4abc1269 --- /dev/null +++ b/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_15.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ[0] TCC_EA_WRREQ_64B[0] TCC_EA_RDREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_LEVEL[1] TCC_EA_WRREQ[1] TCC_EA_WRREQ_64B[1] TCC_EA_RDREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_LEVEL[2] TCC_EA_WRREQ[2] TCC_EA_WRREQ_64B[2] TCC_EA_RDREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_LEVEL[3] TCC_EA_WRREQ[3] TCC_EA_WRREQ_64B[3] TCC_EA_RDREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_LEVEL[4] TCC_EA_WRREQ[4] TCC_EA_WRREQ_64B[4] TCC_EA_RDREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_LEVEL[5] TCC_EA_WRREQ[5] TCC_EA_WRREQ_64B[5] TCC_EA_RDREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_LEVEL[6] TCC_EA_WRREQ[6] TCC_EA_WRREQ_64B[6] TCC_EA_RDREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_LEVEL[7] TCC_EA_WRREQ[7] TCC_EA_WRREQ_64B[7] TCC_EA_RDREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_LEVEL[8] TCC_EA_WRREQ[8] TCC_EA_WRREQ_64B[8] TCC_EA_RDREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_LEVEL[9] TCC_EA_WRREQ[9] TCC_EA_WRREQ_64B[9] TCC_EA_RDREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_LEVEL[10] TCC_EA_WRREQ[10] TCC_EA_WRREQ_64B[10] TCC_EA_RDREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_LEVEL[11] TCC_EA_WRREQ[11] TCC_EA_WRREQ_64B[11] TCC_EA_RDREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_LEVEL[12] TCC_EA_WRREQ[12] TCC_EA_WRREQ_64B[12] TCC_EA_RDREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_LEVEL[13] TCC_EA_WRREQ[13] TCC_EA_WRREQ_64B[13] TCC_EA_RDREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_LEVEL[14] TCC_EA_WRREQ[14] TCC_EA_WRREQ_64B[14] TCC_EA_RDREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_LEVEL[15] TCC_EA_WRREQ[15] TCC_EA_WRREQ_64B[15] TCC_EA_RDREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_LEVEL[16] TCC_EA_WRREQ[16] TCC_EA_WRREQ_64B[16] TCC_EA_RDREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_LEVEL[17] TCC_EA_WRREQ[17] TCC_EA_WRREQ_64B[17] TCC_EA_RDREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_LEVEL[18] TCC_EA_WRREQ[18] TCC_EA_WRREQ_64B[18] TCC_EA_RDREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_LEVEL[19] TCC_EA_WRREQ[19] TCC_EA_WRREQ_64B[19] TCC_EA_RDREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_LEVEL[20] TCC_EA_WRREQ[20] TCC_EA_WRREQ_64B[20] TCC_EA_RDREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_LEVEL[21] TCC_EA_WRREQ[21] TCC_EA_WRREQ_64B[21] TCC_EA_RDREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_LEVEL[22] TCC_EA_WRREQ[22] TCC_EA_WRREQ_64B[22] TCC_EA_RDREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_LEVEL[23] TCC_EA_WRREQ[23] TCC_EA_WRREQ_64B[23] TCC_EA_RDREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_LEVEL[24] TCC_EA_WRREQ[24] TCC_EA_WRREQ_64B[24] TCC_EA_RDREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_LEVEL[25] TCC_EA_WRREQ[25] TCC_EA_WRREQ_64B[25] TCC_EA_RDREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_LEVEL[26] TCC_EA_WRREQ[26] TCC_EA_WRREQ_64B[26] TCC_EA_RDREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_LEVEL[27] TCC_EA_WRREQ[27] TCC_EA_WRREQ_64B[27] TCC_EA_RDREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_LEVEL[28] TCC_EA_WRREQ[28] TCC_EA_WRREQ_64B[28] TCC_EA_RDREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_LEVEL[29] TCC_EA_WRREQ[29] TCC_EA_WRREQ_64B[29] TCC_EA_RDREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_LEVEL[30] TCC_EA_WRREQ[30] TCC_EA_WRREQ_64B[30] TCC_EA_RDREQ_IO_CREDIT_STALL[31] TCC_EA_RDREQ_LEVEL[31] TCC_EA_WRREQ[31] TCC_EA_WRREQ_64B[31] + +gpu: +range: +kernel: vecCopy diff --git a/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_16.txt b/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_16.txt new file mode 100644 index 0000000000..19aada1248 --- /dev/null +++ b/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_16.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_WRREQ_IO_CREDIT_STALL[0] TCC_EA_WRREQ_LEVEL[0] TCC_EA_WRREQ_DRAM_CREDIT_STALL[1] TCC_EA_WRREQ_GMI_CREDIT_STALL[1] TCC_EA_WRREQ_IO_CREDIT_STALL[1] TCC_EA_WRREQ_LEVEL[1] TCC_EA_WRREQ_DRAM_CREDIT_STALL[2] TCC_EA_WRREQ_GMI_CREDIT_STALL[2] TCC_EA_WRREQ_IO_CREDIT_STALL[2] TCC_EA_WRREQ_LEVEL[2] TCC_EA_WRREQ_DRAM_CREDIT_STALL[3] TCC_EA_WRREQ_GMI_CREDIT_STALL[3] TCC_EA_WRREQ_IO_CREDIT_STALL[3] TCC_EA_WRREQ_LEVEL[3] TCC_EA_WRREQ_DRAM_CREDIT_STALL[4] TCC_EA_WRREQ_GMI_CREDIT_STALL[4] TCC_EA_WRREQ_IO_CREDIT_STALL[4] TCC_EA_WRREQ_LEVEL[4] TCC_EA_WRREQ_DRAM_CREDIT_STALL[5] TCC_EA_WRREQ_GMI_CREDIT_STALL[5] TCC_EA_WRREQ_IO_CREDIT_STALL[5] TCC_EA_WRREQ_LEVEL[5] TCC_EA_WRREQ_DRAM_CREDIT_STALL[6] TCC_EA_WRREQ_GMI_CREDIT_STALL[6] TCC_EA_WRREQ_IO_CREDIT_STALL[6] TCC_EA_WRREQ_LEVEL[6] TCC_EA_WRREQ_DRAM_CREDIT_STALL[7] TCC_EA_WRREQ_GMI_CREDIT_STALL[7] TCC_EA_WRREQ_IO_CREDIT_STALL[7] TCC_EA_WRREQ_LEVEL[7] TCC_EA_WRREQ_DRAM_CREDIT_STALL[8] TCC_EA_WRREQ_GMI_CREDIT_STALL[8] TCC_EA_WRREQ_IO_CREDIT_STALL[8] TCC_EA_WRREQ_LEVEL[8] TCC_EA_WRREQ_DRAM_CREDIT_STALL[9] TCC_EA_WRREQ_GMI_CREDIT_STALL[9] TCC_EA_WRREQ_IO_CREDIT_STALL[9] TCC_EA_WRREQ_LEVEL[9] TCC_EA_WRREQ_DRAM_CREDIT_STALL[10] TCC_EA_WRREQ_GMI_CREDIT_STALL[10] TCC_EA_WRREQ_IO_CREDIT_STALL[10] TCC_EA_WRREQ_LEVEL[10] TCC_EA_WRREQ_DRAM_CREDIT_STALL[11] TCC_EA_WRREQ_GMI_CREDIT_STALL[11] TCC_EA_WRREQ_IO_CREDIT_STALL[11] TCC_EA_WRREQ_LEVEL[11] TCC_EA_WRREQ_DRAM_CREDIT_STALL[12] TCC_EA_WRREQ_GMI_CREDIT_STALL[12] TCC_EA_WRREQ_IO_CREDIT_STALL[12] TCC_EA_WRREQ_LEVEL[12] TCC_EA_WRREQ_DRAM_CREDIT_STALL[13] TCC_EA_WRREQ_GMI_CREDIT_STALL[13] TCC_EA_WRREQ_IO_CREDIT_STALL[13] TCC_EA_WRREQ_LEVEL[13] TCC_EA_WRREQ_DRAM_CREDIT_STALL[14] TCC_EA_WRREQ_GMI_CREDIT_STALL[14] TCC_EA_WRREQ_IO_CREDIT_STALL[14] TCC_EA_WRREQ_LEVEL[14] TCC_EA_WRREQ_DRAM_CREDIT_STALL[15] TCC_EA_WRREQ_GMI_CREDIT_STALL[15] TCC_EA_WRREQ_IO_CREDIT_STALL[15] TCC_EA_WRREQ_LEVEL[15] TCC_EA_WRREQ_DRAM_CREDIT_STALL[16] TCC_EA_WRREQ_GMI_CREDIT_STALL[16] TCC_EA_WRREQ_IO_CREDIT_STALL[16] TCC_EA_WRREQ_LEVEL[16] TCC_EA_WRREQ_DRAM_CREDIT_STALL[17] TCC_EA_WRREQ_GMI_CREDIT_STALL[17] TCC_EA_WRREQ_IO_CREDIT_STALL[17] TCC_EA_WRREQ_LEVEL[17] TCC_EA_WRREQ_DRAM_CREDIT_STALL[18] TCC_EA_WRREQ_GMI_CREDIT_STALL[18] TCC_EA_WRREQ_IO_CREDIT_STALL[18] TCC_EA_WRREQ_LEVEL[18] TCC_EA_WRREQ_DRAM_CREDIT_STALL[19] TCC_EA_WRREQ_GMI_CREDIT_STALL[19] TCC_EA_WRREQ_IO_CREDIT_STALL[19] TCC_EA_WRREQ_LEVEL[19] TCC_EA_WRREQ_DRAM_CREDIT_STALL[20] TCC_EA_WRREQ_GMI_CREDIT_STALL[20] TCC_EA_WRREQ_IO_CREDIT_STALL[20] TCC_EA_WRREQ_LEVEL[20] TCC_EA_WRREQ_DRAM_CREDIT_STALL[21] TCC_EA_WRREQ_GMI_CREDIT_STALL[21] TCC_EA_WRREQ_IO_CREDIT_STALL[21] TCC_EA_WRREQ_LEVEL[21] TCC_EA_WRREQ_DRAM_CREDIT_STALL[22] TCC_EA_WRREQ_GMI_CREDIT_STALL[22] TCC_EA_WRREQ_IO_CREDIT_STALL[22] TCC_EA_WRREQ_LEVEL[22] TCC_EA_WRREQ_DRAM_CREDIT_STALL[23] TCC_EA_WRREQ_GMI_CREDIT_STALL[23] TCC_EA_WRREQ_IO_CREDIT_STALL[23] TCC_EA_WRREQ_LEVEL[23] TCC_EA_WRREQ_DRAM_CREDIT_STALL[24] TCC_EA_WRREQ_GMI_CREDIT_STALL[24] TCC_EA_WRREQ_IO_CREDIT_STALL[24] TCC_EA_WRREQ_LEVEL[24] TCC_EA_WRREQ_DRAM_CREDIT_STALL[25] TCC_EA_WRREQ_GMI_CREDIT_STALL[25] TCC_EA_WRREQ_IO_CREDIT_STALL[25] TCC_EA_WRREQ_LEVEL[25] TCC_EA_WRREQ_DRAM_CREDIT_STALL[26] TCC_EA_WRREQ_GMI_CREDIT_STALL[26] TCC_EA_WRREQ_IO_CREDIT_STALL[26] TCC_EA_WRREQ_LEVEL[26] TCC_EA_WRREQ_DRAM_CREDIT_STALL[27] TCC_EA_WRREQ_GMI_CREDIT_STALL[27] TCC_EA_WRREQ_IO_CREDIT_STALL[27] TCC_EA_WRREQ_LEVEL[27] TCC_EA_WRREQ_DRAM_CREDIT_STALL[28] TCC_EA_WRREQ_GMI_CREDIT_STALL[28] TCC_EA_WRREQ_IO_CREDIT_STALL[28] TCC_EA_WRREQ_LEVEL[28] TCC_EA_WRREQ_DRAM_CREDIT_STALL[29] TCC_EA_WRREQ_GMI_CREDIT_STALL[29] TCC_EA_WRREQ_IO_CREDIT_STALL[29] TCC_EA_WRREQ_LEVEL[29] TCC_EA_WRREQ_DRAM_CREDIT_STALL[30] TCC_EA_WRREQ_GMI_CREDIT_STALL[30] TCC_EA_WRREQ_IO_CREDIT_STALL[30] TCC_EA_WRREQ_LEVEL[30] TCC_EA_WRREQ_DRAM_CREDIT_STALL[31] TCC_EA_WRREQ_GMI_CREDIT_STALL[31] TCC_EA_WRREQ_IO_CREDIT_STALL[31] TCC_EA_WRREQ_LEVEL[31] + +gpu: +range: +kernel: vecCopy diff --git a/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_17.txt b/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_17.txt new file mode 100644 index 0000000000..d25d8f61df --- /dev/null +++ b/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_17.txt @@ -0,0 +1,5 @@ +pmc: TCC_HIT[0] TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_HIT[1] TCC_MISS[1] TCC_READ[1] TCC_REQ[1] TCC_HIT[2] TCC_MISS[2] TCC_READ[2] TCC_REQ[2] TCC_HIT[3] TCC_MISS[3] TCC_READ[3] TCC_REQ[3] TCC_HIT[4] TCC_MISS[4] TCC_READ[4] TCC_REQ[4] TCC_HIT[5] TCC_MISS[5] TCC_READ[5] TCC_REQ[5] TCC_HIT[6] TCC_MISS[6] TCC_READ[6] TCC_REQ[6] TCC_HIT[7] TCC_MISS[7] TCC_READ[7] TCC_REQ[7] TCC_HIT[8] TCC_MISS[8] TCC_READ[8] TCC_REQ[8] TCC_HIT[9] TCC_MISS[9] TCC_READ[9] TCC_REQ[9] TCC_HIT[10] TCC_MISS[10] TCC_READ[10] TCC_REQ[10] TCC_HIT[11] TCC_MISS[11] TCC_READ[11] TCC_REQ[11] TCC_HIT[12] TCC_MISS[12] TCC_READ[12] TCC_REQ[12] TCC_HIT[13] TCC_MISS[13] TCC_READ[13] TCC_REQ[13] TCC_HIT[14] TCC_MISS[14] TCC_READ[14] TCC_REQ[14] TCC_HIT[15] TCC_MISS[15] TCC_READ[15] TCC_REQ[15] TCC_HIT[16] TCC_MISS[16] TCC_READ[16] TCC_REQ[16] TCC_HIT[17] TCC_MISS[17] TCC_READ[17] TCC_REQ[17] TCC_HIT[18] TCC_MISS[18] TCC_READ[18] TCC_REQ[18] TCC_HIT[19] TCC_MISS[19] TCC_READ[19] TCC_REQ[19] TCC_HIT[20] TCC_MISS[20] TCC_READ[20] TCC_REQ[20] TCC_HIT[21] TCC_MISS[21] TCC_READ[21] TCC_REQ[21] TCC_HIT[22] TCC_MISS[22] TCC_READ[22] TCC_REQ[22] TCC_HIT[23] TCC_MISS[23] TCC_READ[23] TCC_REQ[23] TCC_HIT[24] TCC_MISS[24] TCC_READ[24] TCC_REQ[24] TCC_HIT[25] TCC_MISS[25] TCC_READ[25] TCC_REQ[25] TCC_HIT[26] TCC_MISS[26] TCC_READ[26] TCC_REQ[26] TCC_HIT[27] TCC_MISS[27] TCC_READ[27] TCC_REQ[27] TCC_HIT[28] TCC_MISS[28] TCC_READ[28] TCC_REQ[28] TCC_HIT[29] TCC_MISS[29] TCC_READ[29] TCC_REQ[29] TCC_HIT[30] TCC_MISS[30] TCC_READ[30] TCC_REQ[30] TCC_HIT[31] TCC_MISS[31] TCC_READ[31] TCC_REQ[31] + +gpu: +range: +kernel: vecCopy diff --git a/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_18.txt b/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_18.txt new file mode 100644 index 0000000000..8f3a4cf638 --- /dev/null +++ b/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_18.txt @@ -0,0 +1,5 @@ +pmc: TCC_RW_REQ[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_RW_REQ[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_WRITE[1] TCC_RW_REQ[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_WRITE[2] TCC_RW_REQ[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_WRITE[3] TCC_RW_REQ[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_WRITE[4] TCC_RW_REQ[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_WRITE[5] TCC_RW_REQ[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_WRITE[6] TCC_RW_REQ[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_WRITE[7] TCC_RW_REQ[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_WRITE[8] TCC_RW_REQ[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_WRITE[9] TCC_RW_REQ[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_WRITE[10] TCC_RW_REQ[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_WRITE[11] TCC_RW_REQ[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_WRITE[12] TCC_RW_REQ[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_WRITE[13] TCC_RW_REQ[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_WRITE[14] TCC_RW_REQ[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_WRITE[15] TCC_RW_REQ[16] TCC_TOO_MANY_EA_WRREQS_STALL[16] TCC_WRITE[16] TCC_RW_REQ[17] TCC_TOO_MANY_EA_WRREQS_STALL[17] TCC_WRITE[17] TCC_RW_REQ[18] TCC_TOO_MANY_EA_WRREQS_STALL[18] TCC_WRITE[18] TCC_RW_REQ[19] TCC_TOO_MANY_EA_WRREQS_STALL[19] TCC_WRITE[19] TCC_RW_REQ[20] TCC_TOO_MANY_EA_WRREQS_STALL[20] TCC_WRITE[20] TCC_RW_REQ[21] TCC_TOO_MANY_EA_WRREQS_STALL[21] TCC_WRITE[21] TCC_RW_REQ[22] TCC_TOO_MANY_EA_WRREQS_STALL[22] TCC_WRITE[22] TCC_RW_REQ[23] TCC_TOO_MANY_EA_WRREQS_STALL[23] TCC_WRITE[23] TCC_RW_REQ[24] TCC_TOO_MANY_EA_WRREQS_STALL[24] TCC_WRITE[24] TCC_RW_REQ[25] TCC_TOO_MANY_EA_WRREQS_STALL[25] TCC_WRITE[25] TCC_RW_REQ[26] TCC_TOO_MANY_EA_WRREQS_STALL[26] TCC_WRITE[26] TCC_RW_REQ[27] TCC_TOO_MANY_EA_WRREQS_STALL[27] TCC_WRITE[27] TCC_RW_REQ[28] TCC_TOO_MANY_EA_WRREQS_STALL[28] TCC_WRITE[28] TCC_RW_REQ[29] TCC_TOO_MANY_EA_WRREQS_STALL[29] TCC_WRITE[29] TCC_RW_REQ[30] TCC_TOO_MANY_EA_WRREQS_STALL[30] TCC_WRITE[30] TCC_RW_REQ[31] TCC_TOO_MANY_EA_WRREQS_STALL[31] TCC_WRITE[31] + +gpu: +range: +kernel: vecCopy diff --git a/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_2.txt b/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_2.txt new file mode 100644 index 0000000000..7db4b6a839 --- /dev/null +++ b/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_2.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_MUL_F32 SQ_INSTS_VALU_FMA_F32 SQ_INSTS_VALU_TRANS_F32 SQ_INSTS_VALU_ADD_F64 SQ_INSTS_VALU_MUL_F64 SQ_INSTS_VALU_FMA_F64 SQ_INSTS_VALU_TRANS_F64 SQ_INSTS_VALU_INT32 TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum TA_BUFFER_ATOMIC_WAVEFRONTS_sum TA_BUFFER_TOTAL_CYCLES_sum TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum + +gpu: +range: +kernel: vecCopy diff --git a/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_3.txt b/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_3.txt new file mode 100644 index 0000000000..52db85736f --- /dev/null +++ b/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_3.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_INT64 SQ_INSTS_SMEM SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum TD_COALESCABLE_WAVEFRONT_sum SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE CPF_CMP_UTCL1_STALL_ON_TRANSLATION TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum + +gpu: +range: +kernel: vecCopy diff --git a/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_4.txt b/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_4.txt new file mode 100644 index 0000000000..33da211e5f --- /dev/null +++ b/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_4.txt @@ -0,0 +1,5 @@ +pmc: SQ_WAVE_CYCLES SQ_WAIT_ANY SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_BUSY_CU_CYCLES SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE TCC_EA_WRREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WR_UNCACHED_32B_sum TCC_EA_WRREQ_DRAM_sum + +gpu: +range: +kernel: vecCopy diff --git a/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_5.txt b/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_5.txt new file mode 100644 index 0000000000..b6ed310959 --- /dev/null +++ b/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_5.txt @@ -0,0 +1,5 @@ +pmc: SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU TCP_TCP_LATENCY_sum TCP_TCC_READ_REQ_LATENCY_sum TCP_TCC_WRITE_REQ_LATENCY_sum TCP_TCC_READ_REQ_sum TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN CPC_ME1_DC0_SPI_BUSY TCC_EA_WRREQ_STALL_sum TCC_EA_RDREQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RD_UNCACHED_32B_sum + +gpu: +range: +kernel: vecCopy diff --git a/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_6.txt b/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_6.txt new file mode 100644 index 0000000000..91a56b0bc3 --- /dev/null +++ b/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_6.txt @@ -0,0 +1,5 @@ +pmc: SQ_THREAD_CYCLES_VALU SQ_IFETCH SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TCP_TCC_NC_READ_REQ_sum TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN TCC_EA_RDREQ_DRAM_sum TCC_TAG_STALL_sum TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum + +gpu: +range: +kernel: vecCopy diff --git a/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_7.txt b/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_7.txt new file mode 100644 index 0000000000..4ad70275a5 --- /dev/null +++ b/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_7.txt @@ -0,0 +1,5 @@ +pmc: SQ_WAVES_LT_32 SQ_WAVES_LT_16 SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TCP_TCC_UC_WRITE_REQ_sum TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR TCC_NORMAL_EVICT_sum TCC_ALL_TC_OP_INV_EVICT_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA_ATOMIC_sum + +gpu: +range: +kernel: vecCopy diff --git a/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_8.txt b/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_8.txt new file mode 100644 index 0000000000..68e1a43fe9 --- /dev/null +++ b/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_8.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM_NORM SQ_INSTS_MFMA SQ_INSTS_VALU_MFMA_I8 SQ_INSTS_VALU_MFMA_F16 SQ_INSTS_VALU_MFMA_BF16 SQ_INSTS_VALU_MFMA_F32 SQ_INSTS_VALU_MFMA_F64 SQ_VALU_MFMA_BUSY_CYCLES TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TCP_TCC_CC_ATOMIC_REQ_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN TCC_EA_RDREQ_LEVEL_sum TCC_EA_WRREQ_LEVEL_sum TCC_EA_ATOMIC_LEVEL_sum + +gpu: +range: +kernel: vecCopy diff --git a/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_9.txt b/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_9.txt new file mode 100644 index 0000000000..24450898ad --- /dev/null +++ b/tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_9.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_FLAT_LDS_ONLY SQ_INSTS_VALU_MFMA_MOPS_I8 SQ_INSTS_VALU_MFMA_MOPS_F16 SQ_INSTS_VALU_MFMA_MOPS_BF16 SQ_INSTS_VALU_MFMA_MOPS_F32 SQ_INSTS_VALU_MFMA_MOPS_F64 SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum TCP_PENDING_STALL_CYCLES_sum + +gpu: +range: +kernel: vecCopy diff --git a/tests/workloads/kernel_substr/MI200/perfmon/timestamps.txt b/tests/workloads/kernel_substr/MI200/perfmon/timestamps.txt new file mode 100644 index 0000000000..2970e26c4e --- /dev/null +++ b/tests/workloads/kernel_substr/MI200/perfmon/timestamps.txt @@ -0,0 +1,5 @@ +pmc: + +gpu: +range: +kernel: vecCopy diff --git a/tests/workloads/kernel_substr/MI200/pmc_perf.csv b/tests/workloads/kernel_substr/MI200/pmc_perf.csv new file mode 100644 index 0000000000..51c316491f --- /dev/null +++ b/tests/workloads/kernel_substr/MI200/pmc_perf.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_1,obj_1,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_2,obj_2,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_3,obj_3,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,wave_size_4,obj_4,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_DRAM_sum,TCC_TAG_STALL_sum,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,wave_size_5,obj_5,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_6,obj_6,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_7,obj_7,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_8,obj_8,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,wave_size_9,obj_9,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_10,obj_10,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_11,obj_11,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_12,obj_12,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,TCC_EA_ATOMIC_LEVEL_sum,wave_size_13,obj_13,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_14,obj_14,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_15,obj_15,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_16,obj_16,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_17,obj_17,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_18,obj_18,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,TD_COALESCABLE_WAVEFRONT_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7fc7904dcec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13004,18932,7874,549,0,26619,204514.0,0.0,73434.0,131080.0,64,0x7faff393cec0,0,0,0,224,0,65536,64188,56,64,0x7f223ef64ec0,1313,119251,0,0,65536,63800,56,1680,64,0x7f19107b0ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65551.0,0.0,0.0,0.0,64,0x7feea913cec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131081.0,33283.0,46226.0,19310.0,64,0x7f9ffc0b4ec0,6376,0,4096,6386,0,4096,6344,0,4096,6398,0,4096,6382,0,4096,6417,0,4096,6351,0,4096,6378,0,4096,6385,0,4096,6376,0,4096,6387,0,4096,6343,0,4096,6400,0,4096,6386,0,4096,6419,0,4096,6352,0,4096,6372,0,4096,6422,0,4096,6367,0,4096,6373,0,4096,6391,0,4096,6384,0,4096,6375,0,4096,6566,0,4096,6400,0,4096,6373,0,4096,6419,0,4096,6366,0,4096,6377,0,4096,6395,0,4096,6384,0,4096,6377,0,4096,64,0x7f67db69cec0,32768,32768,0,64,0x7f049309cec0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,64,0x7fc6c1854ec0,114688,0,32768,32768,16384,16384,65536,49152,27257494.0,85490762.0,39095499.0,131072.0,0.0,268787.0,0,0,14989,1702.0,131084.0,0.0,16.0,64,0x7fe9e6918ec0,0,1033742,4096,4096,0,1019599,4096,4096,0,1054388,4096,4096,0,1453904,4096,4096,0,1240436,4096,4096,0,1635037,4096,4096,0,1121779,4096,4096,0,1702478,4096,4096,0,1093607,4096,4096,0,1143623,4096,4096,0,1345115,4096,4096,0,1189783,4096,4096,0,1193569,4096,4096,0,1269702,4096,4096,0,1284594,4096,4096,0,1094663,4096,4096,0,1122970,4096,4096,0,1234759,4096,4096,0,1061768,4096,4096,0,1284004,4096,4096,0,1082447,4096,4096,0,1051924,4096,4096,0,1100095,4096,4096,0,1183188,4096,4096,0,1206288,4096,4096,0,978759,4096,4096,0,990566,4096,4096,0,1215900,4096,4096,0,1238654,4096,4096,0,1146068,4096,4096,0,956874,4096,4096,0,1492576,4096,4096,64,0x7f199c754ec0,0,0,0,985896,0,0,0,994973,0,0,0,1041563,0,0,0,1103413,0,0,0,1058256,13,0,0,1173206,0,0,0,1226489,0,0,0,1172264,0,0,0,1064170,0,0,0,1002555,0,0,0,951994,0,0,0,1100200,0,0,0,1106245,0,0,0,1108103,0,0,0,1063005,0,0,0,1159874,0,0,0,1069785,0,0,0,1013227,0,0,0,1025809,0,0,0,1074738,0,0,0,1036234,0,0,0,1169822,0,0,0,1036439,0,0,0,1059264,0,0,0,1052678,0,0,0,1067493,0,0,0,970020,0,0,0,1047972,0,0,0,1048722,0,0,0,1041952,46,0,0,1217914,0,0,0,1149545,64,0x7f1d333e8ec0,2278,4096,2278,6374,2307,4096,2307,6403,2220,4096,2220,6316,2288,4096,2288,6384,2318,4096,2318,6414,2265,4096,2265,6361,2276,4096,2276,6372,2309,4096,2309,6405,2312,4096,2312,6408,2282,4096,2282,6378,2304,4096,2304,6400,2217,4096,2217,6313,2288,4096,2288,6384,2318,4096,2318,6414,2268,4096,2268,6364,2281,4098,2283,6379,2253,4096,2253,6349,2278,4096,2278,6374,2292,4097,2293,6389,2287,4096,2287,6383,2370,4097,2371,6467,2275,4096,2275,6371,2262,4096,2262,6358,2447,4098,2449,6545,2280,4096,2280,6376,2253,4096,2253,6349,2278,4096,2278,6374,2296,4096,2296,6392,2285,4096,2285,6381,2315,4096,2315,6411,2270,4096,2270,6366,2261,4096,2261,6357,64,0x7f9d86b3cec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,41959520.0,35169861.0,0.0,64,0x7f593fb84ec0,230704,128479,16384,0,16384,16384,32768,49152,28837,28837,1947964.0,1347970.0,3594.0,169822.0,1056685.0,0.0,1340330.0,1041593.0,228993,136622,28837,0,28837,0,922784.0,488635.0,0.0,0.0,64,0x7fd2e13d4ec0,10634719,9719648,571007,344064,1629318,0,0,163840,832.0,515136.0,0.0,524288.0,271923.0,32768.0,438720,0,0,10880,131072.0,131072.0,0.0,131072.0,64,0x7f08042a8ec0,0,0,0,0,0,0,168,56,131072.0,131072.0,0.0,965696.0,64,0x7f44d6ac8ec0,4100,0,0,0,4096,0,0,0,4096,0,15,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,44,0,4096,0,40,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,25,0,4097,0,369,0,4096,0,0,0,4099,0,41,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,64,0x7f9b671d0ec0,0,393216,163840,0,0,0,0,0,18304,0.0,0.0,0.0,32768.0,0.0,0.0,384.0,32768.0,4096,16384,352,28478,1930,0,56.0,10.0,0.0,204259.0,64,0x7f21ee0dcec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,10357,0,814,27948,0,73468.0,131072.0,0.0,65568.0,198274458325591,198274458345911 +1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7fc7904dcec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,30552,27524,9616,2391,0,38508,200318.0,0.0,69236.0,131082.0,64,0x7faff393cec0,0,0,0,56,0,65536,65536,0,64,0x7f223ef64ec0,0,187903,0,0,65536,63800,56,1680,64,0x7f19107b0ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65552.0,0.0,0.0,0.0,64,0x7feea913cec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131083.0,96946.0,45623.0,0.0,64,0x7f9ffc0b4ec0,6245,0,4096,6263,0,4096,6252,0,4096,6229,0,4096,6259,0,4096,6266,0,4096,6258,0,4096,6301,0,4096,6296,0,4096,6242,0,4096,6268,0,4096,6256,0,4096,6230,0,4096,6262,0,4096,6268,0,4096,6259,0,4096,6287,0,4096,6300,0,4096,6299,0,4096,6284,0,4096,6276,0,4096,6254,0,4096,6268,0,4096,6247,0,4096,6244,0,4096,6289,0,4096,6304,0,4096,6304,0,4096,6290,0,4096,6278,0,4096,6251,0,4096,6274,0,4096,64,0x7f67db69cec0,32768,32768,0,64,0x7f049309cec0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,64,0x7fc6c1854ec0,114688,0,32768,32768,16384,16384,65536,49152,58698711.0,195304384.0,50451452.0,131072.0,0.0,466162.0,0,0,23491,8909.0,131075.0,0.0,4.0,64,0x7fe9e6918ec0,0,2881157,2828,2828,0,3745023,2856,2856,0,2739060,2872,2872,0,5238866,2880,2880,0,3755192,2880,2880,0,4952010,2856,2856,0,3114359,2856,2856,0,4224218,2796,2796,0,3223435,2796,2796,0,3529313,2828,2828,0,4109685,2856,2856,0,3392227,2882,2882,0,3544484,2880,2880,0,3728617,2884,2884,0,4695870,2856,2856,0,3189513,2856,2856,0,3192664,2808,2808,0,5010406,2826,2826,0,2791750,2864,2864,0,3472889,2880,2880,0,2935072,2848,2848,0,3539950,2900,2900,0,3298391,2828,2828,0,3487321,2832,2832,0,4840777,2832,2832,0,2895087,2808,2808,0,2906623,2836,2836,0,4249521,2864,2864,0,3905343,2878,2878,0,3175579,2846,2846,0,3128286,2900,2900,0,3998597,2828,2828,64,0x7f199c754ec0,0,0,0,1643563,127,0,0,2125780,55,0,0,2172061,447,0,0,2132887,0,0,0,1493116,414,0,0,2044416,13,0,0,1599927,0,0,0,1885384,0,0,0,1792428,0,0,0,1818619,0,0,0,1674757,0,0,0,1642989,0,0,0,1679671,0,0,0,1524889,267,0,0,2107507,0,0,0,1690633,0,0,0,1821482,0,0,0,1913169,0,0,0,1752794,0,0,0,2089516,65,0,0,1787600,278,0,0,2075529,0,0,0,1735512,207,0,0,1962830,111,0,0,2000643,0,0,0,1633525,450,0,0,2168429,0,0,0,1828094,70,0,0,2079901,0,0,0,1571734,247,0,0,2138705,0,0,0,1649740,64,0x7f1d333e8ec0,2151,4096,2151,6247,2194,4096,2194,6290,2157,4096,2157,6253,2162,4096,2162,6258,2150,4096,2150,6246,2164,4096,2164,6260,2180,4096,2180,6276,2180,4096,2180,6276,2184,4096,2184,6280,2154,4096,2154,6250,2197,4096,2197,6293,2159,4097,2160,6256,2169,4097,2170,6266,2151,4096,2151,6247,2168,4096,2168,6264,2186,4098,2188,6284,2172,4096,2172,6268,2167,4096,2167,6263,2179,4097,2180,6276,2191,4096,2191,6287,2261,4097,2262,6358,2177,4096,2177,6273,2181,4096,2181,6277,2190,4096,2190,6286,2191,4096,2191,6287,2169,4096,2169,6265,2172,4096,2172,6268,2181,4096,2181,6277,2190,4096,2190,6286,2209,4096,2209,6305,2184,4098,2186,6282,2183,4096,2183,6279,64,0x7f9d86b3cec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,117590644.0,61488183.0,0.0,64,0x7f593fb84ec0,348752,236962,16384,0,16384,16384,32768,49152,43593,43593,3356834.0,2551636.0,4303.0,412372.0,1766757.0,0.0,2540480.0,2233898.0,348744,246019,43593,0,43593,0,1394976.0,800157.0,0.0,0.0,64,0x7fd2e13d4ec0,18659369,17583236,732069,344064,2688784,0,0,163840,832.0,515136.0,0.0,524288.0,583967.0,32768.0,873113,0,0,13746,91358.0,91358.0,0.0,91358.0,64,0x7f08042a8ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2086319.0,64,0x7f44d6ac8ec0,4099,0,32,0,4096,0,351,0,4096,0,377,0,4096,0,479,0,4096,0,580,0,4096,0,923,0,4096,0,593,0,4096,0,1158,0,4096,0,381,0,4096,0,769,0,4097,0,570,0,4096,0,112,0,4096,0,29,0,4096,0,218,0,4096,0,145,0,4096,0,799,0,4096,0,455,0,4096,0,1376,0,4098,0,404,0,4099,0,447,0,4096,0,656,0,4097,0,364,0,4096,0,716,0,4096,0,1693,0,4096,0,1162,0,4096,0,236,0,4096,0,266,0,4096,0,391,0,4096,0,458,0,4096,0,239,0,4096,0,262,0,4096,0,1285,0,64,0x7f9b671d0ec0,0,393216,163840,0,0,0,0,0,28042,0.0,0.0,0.0,32768.0,0.0,0.0,265.0,32768.0,4096,16384,302,37155,2067,0,56.0,0.0,0.0,200137.0,64,0x7f21ee0dcec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,21254,0,2679,38933,0,68994.0,131072.0,0.0,45739.0,198274458365591,198274458381111 +2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7fc7904dcec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,29573,26124,9671,3081,0,39425,200697.0,0.0,69616.0,131081.0,64,0x7faff393cec0,0,0,0,56,0,65536,65536,0,64,0x7f223ef64ec0,0,187181,0,0,65536,63800,56,1680,64,0x7f19107b0ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65552.0,0.0,0.0,0.0,64,0x7feea913cec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131084.0,79654.0,45543.0,0.0,64,0x7f9ffc0b4ec0,6298,0,4096,6309,0,4096,6286,0,4096,6264,0,4096,6284,0,4096,6294,0,4096,6241,0,4096,6284,0,4096,6283,0,4096,6299,0,4096,6316,0,4096,6291,0,4096,6264,0,4096,6289,0,4096,6292,0,4096,6240,0,4096,6250,0,4096,6292,0,4096,6290,0,4096,6301,0,4096,6277,0,4096,6271,0,4096,6284,0,4096,6302,0,4096,6301,0,4096,6253,0,4096,6295,0,4096,6290,0,4096,6305,0,4096,6275,0,4096,6272,0,4096,6285,0,4096,64,0x7f67db69cec0,32768,32768,0,64,0x7f049309cec0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,64,0x7fc6c1854ec0,114688,0,32768,32768,16384,16384,65536,49152,58212958.0,197519865.0,49132344.0,131072.0,0.0,533879.0,0,0,24937,5851.0,131085.0,0.0,24.0,64,0x7fe9e6918ec0,0,4356472,2828,2828,0,3288185,2884,2884,0,3816220,2870,2870,0,3605685,2878,2878,0,4402901,2840,2840,0,4215553,2804,2804,0,3078132,2868,2868,0,5340439,2828,2828,0,4019367,2828,2828,0,3343309,2832,2832,0,3769122,2880,2880,0,3647927,2876,2876,0,3273461,2876,2876,0,2952778,2840,2840,0,3434794,2800,2800,0,3142437,2868,2868,0,3618008,2832,2832,0,4261142,2882,2882,0,2772119,2860,2860,0,3881202,2862,2862,0,2959369,2864,2864,0,3880458,2900,2900,0,3372624,2800,2800,0,4267076,2800,2800,0,3074208,2808,2808,0,4323476,2832,2832,0,4159107,2882,2882,0,3376068,2860,2860,0,3354840,2860,2860,0,3243808,2864,2864,0,2743939,2900,2900,0,3744213,2800,2800,64,0x7f199c754ec0,330,0,0,2015523,329,0,0,1934009,0,0,0,1698775,0,0,0,1830600,0,0,0,1570437,0,0,0,1723781,0,0,0,1628088,0,0,0,1803509,196,0,0,1835850,0,0,0,1838590,72,0,0,1820132,0,0,0,1512457,0,0,0,1700082,0,0,0,1718959,773,0,0,2246371,0,0,0,1921622,0,0,0,1441712,0,0,0,1743923,0,0,0,1557593,367,0,0,2014000,0,0,0,1655504,0,0,0,1973003,0,0,0,1898184,2418,0,0,2858471,0,0,0,1826583,0,0,0,1646209,0,0,0,1554784,0,0,0,1762517,10,0,0,1971514,0,0,0,1522047,803,0,0,2397542,0,0,0,1839256,64,0x7f1d333e8ec0,2205,4096,2205,6301,2197,4096,2197,6293,2139,4096,2139,6235,2167,4096,2167,6263,2156,4096,2156,6252,2183,4096,2183,6279,2180,4096,2180,6276,2185,4096,2185,6281,2190,4096,2190,6286,2209,4096,2209,6305,2199,4096,2199,6295,2139,4097,2140,6236,2168,4097,2169,6265,2159,4096,2159,6255,2187,4096,2187,6283,2182,4098,2184,6280,2186,4096,2186,6282,2170,4096,2170,6266,2179,4097,2180,6276,2181,4096,2181,6277,2231,4097,2232,6328,2167,4096,2167,6263,2176,4096,2176,6272,2170,4096,2170,6266,2174,4096,2174,6270,2189,4096,2189,6285,2174,4096,2174,6270,2182,4096,2182,6278,2182,4096,2182,6278,2185,4096,2185,6281,2171,4098,2173,6269,2174,4096,2174,6270,64,0x7f9d86b3cec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,124672508.0,68439286.0,0.0,64,0x7f593fb84ec0,327280,217804,16384,0,16384,16384,32768,49152,40909,40909,3108602.0,2423817.0,4712.0,332028.0,1803004.0,0.0,2412312.0,2101451.0,327272,227089,40909,0,40909,0,1309088.0,774275.0,0.0,0.0,64,0x7fd2e13d4ec0,18667839,17597573,726202,344064,2674403,0,0,163840,830.0,515158.0,0.0,524288.0,686997.0,32768.0,893984,0,0,14181,90870.0,90870.0,0.0,90870.0,64,0x7f08042a8ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2048412.0,64,0x7f44d6ac8ec0,4100,0,474,0,4096,0,469,0,4096,0,806,0,4096,0,2529,0,4096,0,525,0,4096,0,1198,0,4096,0,1121,0,4096,0,973,0,4096,0,1198,0,4096,0,683,0,4097,0,410,0,4096,0,153,0,4096,0,335,0,4096,0,1511,0,4096,0,0,0,4096,0,1533,0,4096,0,1828,0,4096,0,1185,0,4098,0,1938,0,4099,0,387,0,4096,0,1060,0,4097,0,708,0,4096,0,1694,0,4096,0,1100,0,4096,0,618,0,4096,0,778,0,4096,0,741,0,4096,0,2023,0,4096,0,1887,0,4096,0,293,0,4096,0,832,0,4096,0,822,0,64,0x7f9b671d0ec0,0,393216,163840,0,0,0,0,0,30732,0.0,0.0,0.0,32768.0,0.0,0.0,224.0,32768.0,4096,16384,302,42229,1958,0,56.0,11.0,0.0,201241.0,64,0x7f21ee0dcec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,21087,0,2674,38799,0,69906.0,131072.0,0.0,45562.0,198274458443671,198274458459991 diff --git a/tests/workloads/kernel_substr/MI200/roofline.csv b/tests/workloads/kernel_substr/MI200/roofline.csv new file mode 100644 index 0000000000..5b47ca7e0f --- /dev/null +++ b/tests/workloads/kernel_substr/MI200/roofline.csv @@ -0,0 +1,5 @@ +device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh +0,1388.4747,1387.9553,1388.9941,5014.9604,5012.063,5017.8579,9222.5117,9221.9268,9223.0967,18050.73,18049.891,18051.57,20930.57,20869.91,20991.23,20265.133,20264.418,20265.848,170420.36,170416.08,170424.64,164859.31,164854.41,164864.22,41417.266,41416.672,41417.859,41477.48,41476.703,41478.258,166330.06,165840.5,166819.62 +1,1389.7251,1389.1949,1390.2552,5028.3931,5026.2188,5030.5674,9234.2783,9233.5322,9235.0244,18087.188,18083.588,18090.787,20971.094,20904.305,21037.883,20291.975,20291.318,20292.631,170824.14,170818.92,170829.36,165082.02,165078.61,165085.42,41468.77,41467.949,41469.59,41525.664,41524.758,41526.57,166822.78,166819.69,166825.88 +2,1388.7198,1388.2028,1389.2369,5036.1206,5033.917,5038.3242,9261.9297,9261.1611,9262.6982,18106.574,18105.59,18107.559,21049.045,21048.621,21049.469,20356.066,20355.422,20356.711,171138.38,171134.81,171141.94,165494.95,165491.14,165498.77,41581.402,41580.301,41582.504,41641.324,41640.227,41642.422,166971.16,166374.72,167567.59 +3,1388.6997,1388.0704,1389.329,5030.8838,5029.3442,5032.4233,9239.749,9239.2314,9240.2666,18025.273,18022.016,18028.531,21030.592,21030.15,21031.033,20311.781,20311.162,20312.4,171031.81,171027.84,171035.78,165235.41,165231.41,165239.41,41440.09,41286.125,41594.055,41580.582,41580.031,41581.133,167008.56,167006.89,167010.23 diff --git a/tests/workloads/kernel_substr/MI200/sysinfo.csv b/tests/workloads/kernel_substr/MI200/sysinfo.csv new file mode 100644 index 0000000000..8015b33c74 --- /dev/null +++ b/tests/workloads/kernel_substr/MI200/sysinfo.csv @@ -0,0 +1,2 @@ +workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd +kernel_substr,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 02:15:28 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/kernel_substr/MI200/timestamps.csv b/tests/workloads/kernel_substr/MI200/timestamps.csv new file mode 100644 index 0000000000..010b4e7495 --- /dev/null +++ b/tests/workloads/kernel_substr/MI200/timestamps.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,295872,295872,1048576,256,0,0,8,0,16,64,0x0,0x7f38a4160ec0,198274458301241,198274458325591,198274458345911,198274458362076 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,295872,295872,1048576,256,0,0,8,0,16,64,0x0,0x7f38a4160ec0,198274458356796,198274458365591,198274458381111,198274458440294 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,295872,295872,1048576,256,0,0,8,0,16,64,0x0,0x7f38a4160ec0,198274458391411,198274458443671,198274458459991,198274458461033 diff --git a/tests/workloads/kernel_summaries/MI100/SQ_IFETCH_LEVEL.csv b/tests/workloads/kernel_summaries/MI100/SQ_IFETCH_LEVEL.csv index 0f11dff116..2b541b8403 100644 --- a/tests/workloads/kernel_summaries/MI100/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/kernel_summaries/MI100/SQ_IFETCH_LEVEL.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2911429,2911429,1048576,256,0,0,8,8,16,64,0x0,0x7f73d713ee80,48680,48680,16384,65536,13197,1683860,2187995332896795,2187996407671736,2187996407696536,2187995340523802 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2911429,2911429,1048576,256,0,0,8,8,16,64,0x0,0x7f73d713ee80,43013,43013,16384,65536,8264,1048580,2187995340548439,2187996407882136,2187996407900856,2187995340843853 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2911429,2911429,1048576,256,0,0,8,8,16,64,0x0,0x7f73d713ee80,41628,41628,16384,65536,8269,1048584,2187995340876504,2187996407921176,2187996407940376,2187995341064708 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,215990,215990,1048576,256,0,0,8,8,16,64,0x0,0x7faa16204e80,48096,48096,16384,65536,14355,1831748,194416751403173,194428972583416,194428972607736,194416759267063 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,215990,215990,1048576,256,0,0,8,8,16,64,0x0,0x7faa16204e80,43657,43657,16384,65536,8199,1048580,194416759288023,194428972707576,194428972726776,194416759622877 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,215990,215990,1048576,256,0,0,8,8,16,64,0x0,0x7faa16204e80,41833,41833,16384,65536,8226,1048580,194416759655488,194428972748536,194428972767576,194416759834237 diff --git a/tests/workloads/kernel_summaries/MI100/SQ_INST_LEVEL_LDS.csv b/tests/workloads/kernel_summaries/MI100/SQ_INST_LEVEL_LDS.csv index 2a0fd4b9c7..0dbf0c6197 100644 --- a/tests/workloads/kernel_summaries/MI100/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/kernel_summaries/MI100/SQ_INST_LEVEL_LDS.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2913255,2913255,1048576,256,0,0,8,8,16,64,0x0,0x7fe8fbe7ee80,0,0,0,2188000224776521,2187996407671736,2187996407696536,2188000232282722 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2913255,2913255,1048576,256,0,0,8,8,16,64,0x0,0x7fe8fbe7ee80,0,0,0,2188000232301918,2187996407882136,2187996407900856,2188000232602552 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2913255,2913255,1048576,256,0,0,8,8,16,64,0x0,0x7fe8fbe7ee80,0,0,0,2188000232631326,2187996407921176,2187996407940376,2188000232798109 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,216173,216173,1048576,256,0,0,8,8,16,64,0x0,0x7fa816e2ce80,0,0,0,194417244983698,194428972583416,194428972607736,194417252760674 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,216173,216173,1048576,256,0,0,8,8,16,64,0x0,0x7fa816e2ce80,0,0,0,194417252781453,194428972707576,194428972726776,194417253062866 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,216173,216173,1048576,256,0,0,8,8,16,64,0x0,0x7fa816e2ce80,0,0,0,194417253091119,194428972748536,194428972767576,194417253271030 diff --git a/tests/workloads/kernel_summaries/MI100/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/kernel_summaries/MI100/SQ_INST_LEVEL_SMEM.csv index 31719897c8..9191db990b 100644 --- a/tests/workloads/kernel_summaries/MI100/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/kernel_summaries/MI100/SQ_INST_LEVEL_SMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2913619,2913619,1048576,256,0,0,8,8,16,64,0x0,0x7fdf9fbb2e80,65536,206090,26387464,2188001370013330,2187996407671736,2187996407696536,2188001377531583 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2913619,2913619,1048576,256,0,0,8,8,16,64,0x0,0x7fdf9fbb2e80,65536,192926,24727120,2188001377551070,2187996407882136,2187996407900856,2188001377858407 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2913619,2913619,1048576,256,0,0,8,8,16,64,0x0,0x7fdf9fbb2e80,65536,171964,22030232,2188001377887662,2187996407921176,2187996407940376,2188001378070264 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,216356,216356,1048576,256,0,0,8,8,16,64,0x0,0x7f9e5d034e80,65536,198380,25401768,194417733358146,194428972583416,194428972607736,194417741014643 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,216356,216356,1048576,256,0,0,8,8,16,64,0x0,0x7f9e5d034e80,65536,168952,21660192,194417741033098,194428972707576,194428972726776,194417741359927 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,216356,216356,1048576,256,0,0,8,8,16,64,0x0,0x7f9e5d034e80,65536,168730,21630264,194417741388111,194428972748536,194428972767576,194417741559796 diff --git a/tests/workloads/kernel_summaries/MI100/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/kernel_summaries/MI100/SQ_INST_LEVEL_VMEM.csv index 35faabccd1..035466fbd8 100644 --- a/tests/workloads/kernel_summaries/MI100/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/kernel_summaries/MI100/SQ_INST_LEVEL_VMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2912157,2912157,1048576,256,0,0,8,8,16,64,0x0,0x7fc39176ee80,32768,654116,83715840,2187997291326340,2187996407671736,2187996407696536,2187997299000557 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2912157,2912157,1048576,256,0,0,8,8,16,64,0x0,0x7fc39176ee80,32768,656755,84065048,2187997299020695,2187996407882136,2187996407900856,2187997299280332 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2912157,2912157,1048576,256,0,0,8,8,16,64,0x0,0x7fc39176ee80,32768,656830,84085068,2187997299309847,2187996407921176,2187996407940376,2187997299462384 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,216539,216539,1048576,256,0,0,8,8,16,64,0x0,0x7f022c520e80,32768,669548,85698544,194418219490729,194428972583416,194428972607736,194418227310776 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,216539,216539,1048576,256,0,0,8,8,16,64,0x0,0x7f022c520e80,32768,673709,86240076,194418227329812,194428972707576,194428972726776,194418227630281 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,216539,216539,1048576,256,0,0,8,8,16,64,0x0,0x7f022c520e80,32768,661351,84660532,194418227658024,194428972748536,194428972767576,194418227830230 diff --git a/tests/workloads/kernel_summaries/MI100/SQ_LEVEL_WAVES.csv b/tests/workloads/kernel_summaries/MI100/SQ_LEVEL_WAVES.csv index b6d1bf0094..82606048b6 100644 --- a/tests/workloads/kernel_summaries/MI100/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/kernel_summaries/MI100/SQ_LEVEL_WAVES.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2912890,2912890,1048576,256,0,0,8,8,16,64,0x0,0x7feab9c62e80,48390,48390,17527,387128,16384,24999492,233430,0,100489672,2187999330234252,2187996407671736,2187996407696536,2187999337691872 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2912890,2912890,1048576,256,0,0,8,8,16,64,0x0,0x7feab9c62e80,42914,42914,14264,343320,16384,25006025,229253,0,100520044,2187999337723401,2187996407882136,2187996407900856,2187999338033684 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2912890,2912890,1048576,256,0,0,8,8,16,64,0x0,0x7feab9c62e80,43018,43018,13664,344152,16384,24849687,232346,0,99900132,2187999338072697,2187996407921176,2187996407940376,2187999338263545 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,216722,216722,1048576,256,0,0,8,8,16,64,0x0,0x7f26d9ffae80,48339,48339,16433,386720,16384,25179289,237134,0,101213380,194418712048118,194428972583416,194428972607736,194418719919130 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,216722,216722,1048576,256,0,0,8,8,16,64,0x0,0x7f26d9ffae80,42466,42466,13655,339736,16384,24728801,227275,0,99412392,194418719949498,194428972707576,194428972726776,194418720265226 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,216722,216722,1048576,256,0,0,8,8,16,64,0x0,0x7f26d9ffae80,42418,42418,13366,339352,16384,24564212,229221,0,98746920,194418720303188,194428972748536,194428972767576,194418720487567 diff --git a/tests/workloads/kernel_summaries/MI100/pmc_dispatch_info.csv b/tests/workloads/kernel_summaries/MI100/pmc_dispatch_info.csv new file mode 100644 index 0000000000..17300ae9af --- /dev/null +++ b/tests/workloads/kernel_summaries/MI100/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) ",2 +1,"vecCopy(double*, double*, double*, int, int) ",2 +2,"vecCopy(double*, double*, double*, int, int) ",2 diff --git a/tests/workloads/kernel_summaries/MI100/pmc_perf.csv b/tests/workloads/kernel_summaries/MI100/pmc_perf.csv index 2ab5cb8573..a1f4beda8f 100644 --- a/tests/workloads/kernel_summaries/MI100/pmc_perf.csv +++ b/tests/workloads/kernel_summaries/MI100/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_1,obj_1,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_2,obj_2,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_3,obj_3,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_4,obj_4,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_5,obj_5,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_6,obj_6,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_7,obj_7,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_8,obj_8,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_9,obj_9,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_10,obj_10,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_11,obj_11,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_12,obj_12,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_13,obj_13,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_14,obj_14,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_15,obj_15,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_16,obj_16,TCC_EA_ATOMIC_LEVEL_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f8412fc8e80,186825,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,11074,27458,9922,550,0,47101,262712.0,0.0,188.0,262524.0,64,0x7fdf6c916e80,131072.0,131072.0,0.0,2558023.0,0.0,0.0,127023529.0,60345597.0,64,0x7f0922774e80,0,48815,0,0,0,48815,0,0,0,48815,0,0,0,48815,0,0,0,48815,0,0,0,48815,0,0,0,48815,0,0,0,48815,0,0,0,48815,0,0,0,48815,0,0,0,48815,0,0,0,48815,0,0,0,48815,0,0,0,48815,0,0,0,48815,0,0,0,48815,0,0,0,48815,0,0,0,48815,0,0,0,48815,0,0,0,48815,0,0,0,48815,0,0,0,48815,0,0,0,48815,0,0,0,48815,0,0,0,48815,0,0,0,48815,0,0,0,48815,0,0,0,48815,0,0,0,48815,0,0,0,48815,0,0,0,48815,0,0,0,48815,0,0,64,0x7fcb1574ee80,386416,234030,3415264,16384,24944014,144,48,0,48301,48301,3862876.0,3038171.0,6520.0,1019762.0,2082162.0,0.0,3029200.0,2717600.0,384895,243954,48301,0,48301,0,1545632.0,957397.0,0.0,0.0,64,0x7f2d453cce80,4096,0,543,0,4096,0,2067,0,4144,0,860,0,4096,0,1398,0,4096,0,2534,0,4096,0,833,0,4096,0,32,0,4096,0,2313,0,4096,0,1237,0,4096,0,1021,0,4096,0,939,0,4096,0,2529,0,4096,0,349,0,4097,0,1847,0,4096,0,2704,0,4096,0,123,0,4096,0,3381,0,4096,0,2470,0,4096,0,2504,0,4096,0,1019,0,4096,0,362,0,4096,0,972,0,4261,0,614,0,4096,0,219,0,4096,0,789,0,4096,0,1142,0,4183,0,180,0,4096,0,1183,0,4096,0,0,0,4099,0,0,0,4096,0,1814,0,4096,0,1466,0,64,0x7f3c65c88e80,8192,0,4096,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f9d8826ee80,0,4180366,4096,4096,0,2874586,4096,4096,0,3075944,4096,4096,0,3013277,4096,4096,0,3412841,4096,4096,0,4859740,4096,4096,0,2339441,4096,4096,0,3446188,4096,4096,0,3763206,4096,4096,0,3905679,4096,4096,0,2947711,4096,4096,0,3654169,4096,4096,0,3012353,4096,4096,0,3436346,4096,4096,0,3085720,4096,4096,0,3150197,4096,4096,0,3148618,4096,4096,0,4274562,4096,4096,0,5465057,4096,4096,0,3632677,4096,4096,0,2927835,4096,4096,0,3038373,4096,4096,0,2435476,4096,4096,0,3855620,4096,4096,0,2607385,4096,4096,0,4725988,4096,4096,0,2971436,4096,4096,0,3139293,4096,4096,0,3756601,4096,4096,0,3352721,4096,4096,0,2402776,4096,4096,0,2949475,4096,4096,64,0x7f696f89ae80,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,141,8195,4240,8336,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8315,4219,8315,0,8312,4216,8312,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f7cebebae80,3909,0,0,1977265,3844,0,0,2019819,1930,0,0,1789143,4223,0,0,1967117,3603,0,0,1958180,4083,0,0,1958479,1957,0,0,1798523,3573,0,0,1989386,3253,0,0,1922402,2704,0,0,1899500,1540,0,0,1733793,2905,0,0,1925769,6422,0,0,2231934,4552,0,0,1993293,4017,0,0,2087554,6016,0,0,2133530,3776,0,0,1934102,4931,0,0,2048275,1833,0,0,1788348,6087,0,0,2056097,4281,0,0,2019720,3099,0,0,1999278,2724,0,0,1877081,5529,0,0,2054344,5198,0,0,2094519,2950,0,0,1934906,5134,0,0,2111817,5472,0,0,2043874,6366,0,0,2186219,2540,0,0,1866273,3135,0,0,1982044,4385,0,0,2061571,64,0x7f1f18b66e80,2567993,360448,163840,0,0,180224,114688,0,61876203.0,177995926.0,70965208.0,131072.0,0.0,796863.0,0,0,26530,99186.0,0.0,0.0,99186.0,64,0x7f9da09e6e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,47024,0,131446.0,131072.0,0.0,131104.0,64,0x7f272ef50e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86714.0,44358.0,131112.0,0.0,64,0x7fedc31a6e80,0,0,192,0,65536,64457,48,1333,32609,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,538,48640,1751,0,48.0,334.0,0.0,262288.0,64,0x7f071c60ce80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,79950.0,148455.0,64,0x7f903c388e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131410.0,0.0,668.0,131409.0,64,0x7fb082f1ae80,32768,0,0,0,16384,16384,393216,22677258,960.0,513934.0,0.0,524288.0,928237.0,32768.0,0,0,0,16477,131072.0,131072.0,0.0,131072.0,64,0x7fd1a625ae80,0.0,2187996407671736,2187996407696536 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f8412fc8e80,185962,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13135,29519,8462,2382,0,41728,262614.0,0.0,47.0,262567.0,64,0x7fdf6c916e80,131072.0,131072.0,0.0,2672928.0,0.0,0.0,125999337.0,47389233.0,64,0x7f0922774e80,0,43588,0,0,0,43588,0,0,0,43588,0,0,0,43588,0,0,0,43588,0,0,0,43588,0,0,0,43588,0,0,0,43588,0,0,0,43588,0,0,0,43588,0,0,0,43588,0,0,0,43588,0,0,0,43588,0,0,0,43588,0,0,0,43588,0,0,0,43588,0,0,0,43588,0,0,0,43588,0,0,0,43588,0,0,0,43588,0,0,0,43588,0,0,0,43588,0,0,0,43588,0,0,0,43588,0,0,0,43588,0,0,0,43588,0,0,0,43588,0,0,0,43588,0,0,0,43588,0,0,0,43588,0,0,0,43588,0,0,0,43588,0,0,64,0x7fcb1574ee80,375984,231936,3395870,16384,25192199,0,96,0,46997,46997,3769104.0,3073022.0,6916.0,909739.0,2128210.0,0.0,3064357.0,2753534.0,375976,241663,46997,0,46997,1088,1503904.0,834692.0,0.0,0.0,64,0x7f2d453cce80,4096,0,3112,0,4096,0,27,0,4144,0,1582,0,4096,0,132,0,4096,0,1149,0,4096,0,412,0,4096,0,1138,0,4096,0,737,0,4096,0,2535,0,4096,0,1783,0,4096,0,1401,0,4098,0,1994,0,4096,0,1628,0,4097,0,721,0,4096,0,2159,0,4096,0,1201,0,4098,0,1756,0,4097,0,2855,0,4097,0,1676,0,4096,0,884,0,4096,0,803,0,4096,0,2430,0,4238,0,0,0,4096,0,0,0,4096,0,1813,0,4096,0,2126,0,4180,0,1243,0,4096,0,88,0,4096,0,56,0,4096,0,2495,0,4096,0,1008,0,4096,0,6,0,64,0x7f3c65c88e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f9d8826ee80,0,4112242,2680,2680,0,3863500,2705,2705,0,4407585,2686,2686,0,4252485,2712,2712,0,3800158,2654,2654,0,3033219,2724,2724,0,4057038,2722,2722,0,4785682,2726,2726,0,4522383,2672,2672,0,3851679,2655,2655,0,4391754,2712,2712,0,4993938,2739,2739,0,3809950,2674,2674,0,4604909,2671,2671,0,3999811,2692,2692,0,3325269,2704,2704,0,4043731,2674,2674,0,4928305,2710,2710,0,2790721,2698,2698,0,4800271,2722,2722,0,3906625,2692,2692,0,4183147,2720,2720,0,3457207,2692,2692,0,2790471,2709,2709,0,3757248,2654,2654,0,3158938,2684,2684,0,2936930,2735,2735,0,4107542,2726,2726,0,3345018,2690,2690,0,4632240,2695,2695,0,4173213,2728,2728,0,3352383,2698,2698,64,0x7f696f89ae80,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8194,4098,8194,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8315,4219,8315,0,8312,4216,8312,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8241,4145,8241,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f7cebebae80,2721,0,0,1550392,3017,0,0,1536273,1431,0,0,1409927,5323,0,0,1711381,2253,0,0,1414923,4744,0,0,1648483,2594,0,0,1472915,4669,0,0,1710822,2336,0,0,1509785,1773,0,0,1411402,4099,0,0,1637509,3859,0,0,1695951,2741,0,0,1560553,4779,0,0,1642148,1902,0,0,1419030,5337,0,0,1646928,3431,0,0,1557110,3097,0,0,1560557,1282,0,0,1376260,5069,0,0,1683768,3463,0,0,1564221,4021,0,0,1745991,729,0,0,1214433,2480,0,0,1543217,2106,0,0,1408586,1949,0,0,1438494,4260,0,0,1663659,5306,0,0,1652092,3556,0,0,1499581,3862,0,0,1634569,1706,0,0,1443231,1768,0,0,1453159,64,0x7f1f18b66e80,1857495,360448,163840,0,0,180224,114688,0,63274672.0,181194250.0,71365090.0,131072.0,0.0,717082.0,0,0,25524,84638.0,0.0,0.0,84638.0,64,0x7f9da09e6e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,240.0,524288.0,0.0,0.0,0,0,7892,44031,1056,131752.0,131072.0,0.0,108913.0,64,0x7f272ef50e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,69678.0,39424.0,96558.0,0.0,64,0x7fedc31a6e80,0,0,48,0,65536,65536,0,0,30524,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,457,42458,1710,0,48.0,319.0,0.0,262144.0,64,0x7f071c60ce80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,40193.0,111729.0,64,0x7f903c388e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131352.0,0.0,558.0,131351.0,64,0x7fb082f1ae80,32768,0,0,0,16384,16384,393216,23165431,960.0,513942.0,0.0,524288.0,946452.0,32768.0,0,0,0,14352,86769.0,86769.0,0.0,86769.0,64,0x7fd1a625ae80,0.0,2187996407882136,2187996407900856 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f8412fc8e80,185127,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13644,30028,8510,2377,0,41325,262537.0,0.0,47.0,262490.0,64,0x7fdf6c916e80,131072.0,131072.0,0.0,2580409.0,0.0,0.0,121992978.0,44716858.0,64,0x7f0922774e80,0,43391,0,0,0,43391,0,0,0,43391,0,0,0,43391,0,0,0,43391,0,0,0,43391,0,0,0,43391,0,0,0,43391,0,0,0,43391,0,0,0,43391,0,0,0,43391,0,0,0,43391,0,0,0,43391,0,0,0,43391,0,0,0,43391,0,0,0,43391,0,0,0,43391,0,0,0,43391,0,0,0,43391,0,0,0,43391,0,0,0,43391,0,0,0,43391,0,0,0,43391,0,0,0,43391,0,0,0,43391,0,0,0,43391,0,0,0,43391,0,0,0,43391,0,0,0,43391,0,0,0,43391,0,0,0,43391,0,0,0,43391,0,0,64,0x7fcb1574ee80,344064,228311,3341172,16384,24614234,0,48,0,43007,43007,3714601.0,3034428.0,6270.0,909934.0,2050343.0,0.0,3025624.0,2714733.0,344056,237909,43007,0,43007,0,1376224.0,799140.0,0.0,0.0,64,0x7f2d453cce80,4096,0,1864,0,4096,0,1082,0,4144,0,3132,0,4096,0,240,0,4096,0,0,0,4096,0,1289,0,4096,0,3181,0,4096,0,478,0,4096,0,1224,0,4096,0,1041,0,4096,0,1700,0,4098,0,2192,0,4096,0,150,0,4097,0,578,0,4096,0,301,0,4096,0,1433,0,4098,0,905,0,4097,0,1561,0,4097,0,1898,0,4096,0,2456,0,4096,0,457,0,4096,0,1994,0,4263,0,619,0,4096,0,509,0,4096,0,0,0,4096,0,558,0,4161,0,0,0,4096,0,3215,0,4096,0,68,0,4096,0,1172,0,4096,0,651,0,4096,0,767,0,64,0x7f3c65c88e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f9d8826ee80,0,3830305,2705,2705,0,2803864,2701,2701,0,4545362,2695,2695,0,4057284,2700,2700,0,4105946,2692,2692,0,3184503,2720,2720,0,4512645,2740,2740,0,3223273,2708,2708,0,3702912,2684,2684,0,3431519,2690,2690,0,4571899,2732,2732,0,5010375,2720,2720,0,3309003,2716,2716,0,3705645,2700,2700,0,4526243,2700,2700,0,2900849,2700,2700,0,3639833,2708,2708,0,4220560,2688,2688,0,4730503,2695,2695,0,3957353,2696,2696,0,3535314,2696,2696,0,3560044,2767,2767,0,4545853,2689,2689,0,4913597,2678,2678,0,3547254,2692,2692,0,3485510,2713,2713,0,4066248,2734,2734,0,3041477,2711,2711,0,3576830,2708,2708,0,2873331,2695,2695,0,3834027,2718,2718,0,4768149,2700,2700,64,0x7f696f89ae80,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8194,4098,8194,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8313,4217,8313,0,8312,4216,8312,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8241,4145,8241,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f7cebebae80,4753,0,0,1651227,3787,0,0,1560562,2378,0,0,1363605,4269,0,0,1553672,2199,0,0,1443834,4918,0,0,1608888,2005,0,0,1401354,4088,0,0,1589590,4468,0,0,1618498,1857,0,0,1493917,4711,0,0,1590406,5878,0,0,1801772,4520,0,0,1717326,5406,0,0,1683875,2008,0,0,1374171,3882,0,0,1590766,3790,0,0,1609343,2835,0,0,1523149,2712,0,0,1547322,4313,0,0,1608572,5076,0,0,1622270,3937,0,0,1727650,3251,0,0,1462399,2260,0,0,1455624,4786,0,0,1611774,922,0,0,1400431,2850,0,0,1470792,5367,0,0,1636852,5366,0,0,1714276,3444,0,0,1558079,3669,0,0,1595237,2764,0,0,1466904,64,0x7f1f18b66e80,1585277,360448,163840,0,0,180224,114688,0,61465912.0,164117482.0,62853412.0,131072.0,0.0,608867.0,0,0,25086,79661.0,0.0,0.0,79661.0,64,0x7f9da09e6e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,3689,37680,0,131345.0,131072.0,0.0,86431.0,64,0x7f272ef50e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86729.0,0.0,131113.0,0.0,64,0x7fedc31a6e80,0,0,48,0,65536,65536,0,0,30655,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,457,42354,1718,0,48.0,276.0,0.0,262144.0,64,0x7f071c60ce80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,62328.0,126347.0,64,0x7f903c388e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131409.0,0.0,672.0,131408.0,64,0x7fb082f1ae80,32768,0,0,0,16384,16384,393216,22185185,960.0,513879.0,0.0,524288.0,1020645.0,32768.0,0,0,0,13942,86447.0,86447.0,0.0,86447.0,64,0x7fd1a625ae80,0.0,2187996407921176,2187996407940376 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_1,obj_1,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_2,obj_2,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_3,obj_3,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_4,obj_4,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_5,obj_5,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_6,obj_6,TCC_EA_ATOMIC_LEVEL_sum,wave_size_7,obj_7,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_8,obj_8,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_9,obj_9,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_10,obj_10,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_11,obj_11,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_12,obj_12,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_13,obj_13,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_14,obj_14,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_15,obj_15,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_16,obj_16,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f8f33d5ae80,227103,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,11234,27618,9940,550,0,47416,262635.0,0.0,188.0,262447.0,64,0x7f361ebb6e80,2146,0,0,1808402,2097,0,0,1821650,4088,0,0,2131814,2646,0,0,1804199,2374,0,0,1879783,4209,0,0,1966661,2784,0,0,1906887,2573,0,0,1981464,3467,0,0,2099779,2884,0,0,1917234,4670,0,0,2009231,2168,0,0,1804542,1675,0,0,1755146,3936,0,0,1931652,4647,0,0,2038922,4788,0,0,2152189,3261,0,0,1999103,2376,0,0,1863769,3260,0,0,1908826,2578,0,0,1937213,3457,0,0,1876113,2866,0,0,1870040,4246,0,0,1978765,1960,0,0,1803352,4711,0,0,2075358,2054,0,0,1709292,3629,0,0,1990811,2856,0,0,1817385,5279,0,0,2199211,1177,0,0,1582758,5374,0,0,2070196,2227,0,0,1807925,64,0x7f175e00ee80,0,0,192,0,65536,64413,48,1353,31457,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,538,47589,1700,0,48.0,297.0,0.0,262288.0,64,0x7f5e77b24e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86278.0,44794.0,131111.0,0.0,64,0x7fe574ab8e80,2080266,360448,163840,0,0,180224,114688,0,69187372.0,191887911.0,75981985.0,131072.0,0.0,586995.0,0,0,27123,79738.0,0.0,0.0,79738.0,64,0x7f90004bce80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,70744.0,134054.0,64,0x7f11a7a0ee80,0.0,64,0x7f9f92604e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,47446,0,131606.0,131072.0,0.0,131104.0,64,0x7f7ad2b34e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131342.0,0.0,532.0,131341.0,64,0x7f5a02362e80,4096,0,6870,0,4096,0,0,0,4099,0,0,0,4096,0,218,0,4096,0,69,0,4144,0,0,0,4096,0,0,0,4096,0,1263,0,4096,0,832,0,4279,0,7617,0,4096,0,4272,0,4144,0,277,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,345,0,4096,0,2269,0,4096,0,914,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,72,0,4096,0,510,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,286,0,64,0x7f995aa2ce80,389768,238747,3503367,16384,25774112,144,48,0,48720,48720,3933806.0,3110584.0,5413.0,953200.0,2146723.0,0.0,3100100.0,2789501.0,388055,248670,48720,0,48720,0,1559040.0,979443.0,0.0,0.0,64,0x7fbd89c80e80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8369,4273,8369,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,141,8243,4288,8384,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,64,0x7f5856196e80,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,64,0x7fece9b6ce80,131072.0,131072.0,0.0,2587371.0,0.0,0.0,126476725.0,59826737.0,64,0x7f09c32aae80,0,4127573,4096,4096,0,3032811,4096,4096,0,2887574,4096,4096,0,2883533,4096,4096,0,3072917,4096,4096,0,3128750,4096,4096,0,3807876,4096,4096,0,3092432,4096,4096,0,4714417,4096,4096,0,3296230,4096,4096,0,4704445,4096,4096,0,3158300,4096,4096,0,3027247,4096,4096,0,2909968,4096,4096,0,2820318,4096,4096,0,2675544,4096,4096,0,5503921,4096,4096,0,3342055,4096,4096,0,3439995,4096,4096,0,2290420,4096,4096,0,2995275,4096,4096,0,2826112,4096,4096,0,3310670,4096,4096,0,2997572,4096,4096,0,3106011,4096,4096,0,3038899,4096,4096,0,3110998,4096,4096,0,3129811,4096,4096,0,3015764,4096,4096,0,4064076,4096,4096,0,3267338,4096,4096,0,2891996,4096,4096,64,0x7feb195a4e80,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f4178150e80,32768,0,0,0,16384,16384,393216,21620542,960.0,513873.0,0.0,524288.0,1135474.0,32768.0,0,0,0,16561,131072.0,131072.0,0.0,131072.0,194428972583416,194428972607736 +1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f8f33d5ae80,186788,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13116,29500,8523,3037,0,41701,262528.0,0.0,47.0,262481.0,64,0x7f361ebb6e80,1163,0,0,1360327,3375,0,0,1513861,5672,0,0,1780543,3356,0,0,1640753,4308,0,0,1670873,2351,0,0,1553395,5650,0,0,1681734,2514,0,0,1525301,2497,0,0,1567802,1990,0,0,1481875,5536,0,0,1685328,2033,0,0,1499998,4098,0,0,1638739,1731,0,0,1502036,4802,0,0,1727667,4148,0,0,1749367,1255,0,0,1352659,3266,0,0,1582524,4463,0,0,1681027,2898,0,0,1510856,2336,0,0,1476567,3205,0,0,1628110,4934,0,0,1715010,1968,0,0,1467369,4558,0,0,1623526,1540,0,0,1424142,5726,0,0,1689428,5183,0,0,1699838,5870,0,0,1741910,2497,0,0,1442370,4417,0,0,1671023,1282,0,0,1421149,64,0x7f175e00ee80,0,0,48,0,65536,65536,0,0,30776,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,458,42101,1740,0,48.0,268.0,0.0,262144.0,64,0x7f5e77b24e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86864.0,0.0,131110.0,0.0,64,0x7fe574ab8e80,1794650,360448,163840,0,0,180224,114688,0,71876897.0,199760619.0,77775106.0,131072.0,0.0,611118.0,0,0,26432,62322.0,0.0,0.0,62322.0,64,0x7f90004bce80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,66658.0,134718.0,64,0x7f11a7a0ee80,0.0,64,0x7f9f92604e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,240.0,524288.0,0.0,0.0,0,0,4540,47638,1086,131557.0,131072.0,0.0,131103.0,64,0x7f7ad2b34e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131235.0,0.0,324.0,131234.0,64,0x7f5a02362e80,4096,0,5,0,4096,0,1360,0,4096,0,713,0,4096,0,1639,0,4096,0,0,0,4145,0,2036,0,4096,0,1733,0,4096,0,2308,0,4096,0,0,0,4262,0,3082,0,4096,0,377,0,4144,0,6983,0,4096,0,280,0,4096,0,591,0,4096,0,1600,0,4096,0,177,0,4096,0,0,0,4096,0,1242,0,4096,0,1206,0,4096,0,176,0,4096,0,0,0,4096,0,1418,0,4096,0,693,0,4097,0,0,0,4096,0,0,0,4097,0,1873,0,4096,0,74,0,4096,0,1570,0,4096,0,615,0,4096,0,559,0,4096,0,2405,0,4098,0,454,0,64,0x7f995aa2ce80,347840,236056,3428358,16384,24709920,0,48,0,43479,43479,3830906.0,3116003.0,7087.0,1274157.0,2192707.0,0.0,3106082.0,2794446.0,347832,245843,43479,0,43479,0,1391328.0,830777.0,0.0,0.0,64,0x7fbd89c80e80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8324,4228,8324,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8194,4098,8194,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,64,0x7f5856196e80,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,64,0x7fece9b6ce80,131072.0,131072.0,0.0,2541167.0,0.0,0.0,89178084.0,31665435.0,64,0x7f09c32aae80,0,4116291,2732,2732,0,3252725,2708,2708,0,3849005,2691,2691,0,3627731,2688,2688,0,3910497,2684,2684,0,3631585,2703,2703,0,3278098,2694,2694,0,3814972,2690,2690,0,5352424,2732,2732,0,4067071,2680,2680,0,3722341,2700,2700,0,3887840,2698,2698,0,3811211,2746,2746,0,3853787,2680,2680,0,4058700,2696,2696,0,3257937,2676,2676,0,4640786,2702,2702,0,4718048,2692,2692,0,3752690,2679,2679,0,3705766,2700,2700,0,3795072,2696,2696,0,4233340,2717,2717,0,3619676,2680,2680,0,3118514,2678,2678,0,4079647,2682,2682,0,3850344,2719,2719,0,3330379,2732,2732,0,3140054,2691,2691,0,3417002,2686,2686,0,3802025,2708,2708,0,3388474,2700,2700,0,4085759,2709,2709,64,0x7feb195a4e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f4178150e80,32768,0,0,0,16384,16384,393216,22088765,960.0,513801.0,0.0,524288.0,1081150.0,32768.0,0,0,0,20561,131072.0,131072.0,0.0,131072.0,194428972707576,194428972726776 +2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f8f33d5ae80,189308,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,12192,28576,8591,2892,0,41359,262510.0,0.0,47.0,262463.0,64,0x7f361ebb6e80,2200,0,0,1558656,1625,0,0,1428661,775,0,0,1198382,4987,0,0,1646295,2347,0,0,1487446,2383,0,0,1488255,5143,0,0,1755371,4941,0,0,1714648,1791,0,0,1477395,1368,0,0,1357791,867,0,0,1267605,4188,0,0,1660009,4527,0,0,1743705,2073,0,0,1476549,1795,0,0,1437860,5834,0,0,1771618,2238,0,0,1518407,1992,0,0,1501434,357,0,0,1230896,2555,0,0,1505969,1297,0,0,1387408,4429,0,0,1740819,1088,0,0,1356738,2497,0,0,1554961,2666,0,0,1570082,1905,0,0,1540741,1375,0,0,1400125,5801,0,0,1686132,4301,0,0,1695396,1378,0,0,1464804,6403,0,0,1840368,3949,0,0,1617117,64,0x7f175e00ee80,0,0,48,0,65536,65536,0,0,30524,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,458,41801,1734,0,48.0,248.0,0.0,262144.0,64,0x7f5e77b24e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86628.0,0.0,131112.0,0.0,64,0x7fe574ab8e80,1571814,360448,163840,0,0,180224,114688,0,71130386.0,198922639.0,76388082.0,131072.0,0.0,574386.0,0,0,25633,59310.0,0.0,0.0,59310.0,64,0x7f90004bce80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,56875.0,126786.0,64,0x7f11a7a0ee80,0.0,64,0x7f9f92604e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,2817,39064,0,131478.0,131072.0,0.0,86480.0,64,0x7f7ad2b34e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131295.0,0.0,444.0,131294.0,64,0x7f5a02362e80,4096,0,0,0,4096,0,27,0,4096,0,1517,0,4096,0,0,0,4096,0,0,0,4145,0,83,0,4096,0,0,0,4096,0,40,0,4096,0,0,0,4313,0,1857,0,4096,0,0,0,4144,0,6050,0,4096,0,0,0,4096,0,0,0,4096,0,40,0,4096,0,0,0,4096,0,0,0,4096,0,189,0,4096,0,170,0,4096,0,49,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,7600,0,4096,0,0,0,4096,0,0,0,4096,0,47,0,4096,0,0,0,4098,0,4615,0,64,0x7f995aa2ce80,339560,230588,3367343,16384,24823366,0,48,0,42444,42444,3748721.0,3021150.0,6105.0,1024913.0,2098265.0,0.0,3012141.0,2700847.0,339552,240363,42444,0,42444,0,1358208.0,804988.0,0.0,0.0,64,0x7fbd89c80e80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8323,4227,8323,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8194,4098,8194,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,64,0x7f5856196e80,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,64,0x7fece9b6ce80,131072.0,131072.0,0.0,2593715.0,0.0,0.0,124711205.0,46829716.0,64,0x7f09c32aae80,0,3613810,2722,2722,0,3600345,2716,2716,0,3872972,2722,2722,0,3465453,2692,2692,0,4052686,2692,2692,0,3918874,2720,2720,0,3370372,2738,2738,0,3773864,2694,2694,0,4830770,2730,2730,0,3832483,2707,2707,0,3699633,2752,2752,0,3210547,2694,2694,0,3794410,2764,2764,0,3559899,2690,2690,0,3874334,2728,2728,0,3251099,2710,2710,0,3787803,2724,2724,0,4392611,2736,2736,0,3852238,2721,2721,0,3721220,2724,2724,0,3479881,2712,2712,0,3595018,2734,2734,0,3811545,2726,2726,0,3112084,2680,2680,0,3492028,2703,2703,0,3666391,2718,2718,0,3661520,2746,2746,0,3537302,2704,2704,0,3646969,2718,2718,0,3739465,2726,2726,0,3287047,2728,2728,0,3119468,2695,2695,64,0x7feb195a4e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f4178150e80,32768,0,0,0,16384,16384,393216,22223735,960.0,513847.0,0.0,524288.0,1101968.0,32768.0,0,0,0,14853,86426.0,86426.0,0.0,86426.0,194428972748536,194428972767576 diff --git a/tests/workloads/kernel_summaries/MI100/sysinfo.csv b/tests/workloads/kernel_summaries/MI100/sysinfo.csv index d840bfbb24..839cbfe9e1 100644 --- a/tests/workloads/kernel_summaries/MI100/sysinfo.csv +++ b/tests/workloads/kernel_summaries/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -kernel_summaries,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Fri Mar 1 16:48:23 2024 (CST),1,t006-003.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651240,,5.7.1-98,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +kernel_summaries,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 07 Mar 2024 01:11:21 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/kernel_summaries/MI100/timestamps.csv b/tests/workloads/kernel_summaries/MI100/timestamps.csv index 5d94a7264c..5f7181ff0c 100644 --- a/tests/workloads/kernel_summaries/MI100/timestamps.csv +++ b/tests/workloads/kernel_summaries/MI100/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,2911793,2911793,1048576,256,0,0,8,8,16,64,0x0,0x7f7f55288e80,2187996407646046,2187996407671736,2187996407696536,2187996407706539 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,2911793,2911793,1048576,256,0,0,8,8,16,64,0x0,0x7f7f55288e80,2187996407709345,2187996407882136,2187996407900856,2187996407902006 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,2911793,2911793,1048576,256,0,0,8,8,16,64,0x0,0x7f7f55288e80,2187996407913047,2187996407921176,2187996407940376,2187996407941551 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,220054,220054,1048576,256,0,0,8,8,16,64,0x0,0x7f57d82c2e80,194428972558481,194428972583416,194428972607736,194428972621691 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,220054,220054,1048576,256,0,0,8,8,16,64,0x0,0x7f57d82c2e80,194428972621020,194428972707576,194428972726776,194428972727672 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,220054,220054,1048576,256,0,0,8,8,16,64,0x0,0x7f57d82c2e80,194428972739344,194428972748536,194428972767576,194428972768459 diff --git a/tests/workloads/kernel_summaries/MI200/SQ_IFETCH_LEVEL.csv b/tests/workloads/kernel_summaries/MI200/SQ_IFETCH_LEVEL.csv new file mode 100644 index 0000000000..a95e012907 --- /dev/null +++ b/tests/workloads/kernel_summaries/MI200/SQ_IFETCH_LEVEL.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,388043,388043,1048576,256,0,0,8,0,16,64,0x0,0x7f44da594ec0,27706,27706,16384,65536,13955,1561732,200774954022403,200787787628212,200787787648052,200774969747581 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,388043,388043,1048576,256,0,0,8,0,16,64,0x0,0x7f44da594ec0,43615,43615,16384,65536,9579,1048696,200774969768270,200787787740532,200787787757172,200774970075581 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,388043,388043,1048576,256,0,0,8,0,16,64,0x0,0x7f44da594ec0,41391,41391,16384,65536,9373,1048716,200774970104546,200787787778292,200787787794132,200774970287072 diff --git a/tests/workloads/kernel_summaries/MI200/SQ_INST_LEVEL_LDS.csv b/tests/workloads/kernel_summaries/MI200/SQ_INST_LEVEL_LDS.csv new file mode 100644 index 0000000000..dedff7ad47 --- /dev/null +++ b/tests/workloads/kernel_summaries/MI200/SQ_INST_LEVEL_LDS.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,388244,388244,1048576,256,0,0,8,0,16,64,0x0,0x7f6f6dcfcec0,0,0,0,200775440849287,200787787628212,200787787648052,200775457043843 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,388244,388244,1048576,256,0,0,8,0,16,64,0x0,0x7f6f6dcfcec0,0,0,0,200775457064502,200787787740532,200787787757172,200775457366523 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,388244,388244,1048576,256,0,0,8,0,16,64,0x0,0x7f6f6dcfcec0,0,0,0,200775457392963,200787787778292,200787787794132,200775457550962 diff --git a/tests/workloads/kernel_summaries/MI200/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/kernel_summaries/MI200/SQ_INST_LEVEL_SMEM.csv new file mode 100644 index 0000000000..e9dc2f421c --- /dev/null +++ b/tests/workloads/kernel_summaries/MI200/SQ_INST_LEVEL_SMEM.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,388445,388445,1048576,256,0,0,8,0,16,64,0x0,0x7f873d2c8ec0,65536,174940,19568128,200775923006598,200787787628212,200787787648052,200775938896186 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,388445,388445,1048576,256,0,0,8,0,16,64,0x0,0x7f873d2c8ec0,65536,230260,25754984,200775938915122,200787787740532,200787787757172,200775939338744 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,388445,388445,1048576,256,0,0,8,0,16,64,0x0,0x7f873d2c8ec0,65536,231676,25918432,200775939364603,200787787778292,200787787794132,200775939527411 diff --git a/tests/workloads/kernel_summaries/MI200/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/kernel_summaries/MI200/SQ_INST_LEVEL_VMEM.csv new file mode 100644 index 0000000000..5e45abb3dd --- /dev/null +++ b/tests/workloads/kernel_summaries/MI200/SQ_INST_LEVEL_VMEM.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,388642,388642,1048576,256,0,0,8,0,16,64,0x0,0x7f12be2e4ec0,32768,285164,31937516,200776399169028,200787787628212,200787787648052,200776414972784 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,388642,388642,1048576,256,0,0,8,0,16,64,0x0,0x7f12be2e4ec0,32768,594483,66577344,200776414990778,200787787740532,200787787757172,200776415312347 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,388642,388642,1048576,256,0,0,8,0,16,64,0x0,0x7f12be2e4ec0,32768,575084,64410468,200776415338215,200787787778292,200787787794132,200776415496445 diff --git a/tests/workloads/kernel_summaries/MI200/SQ_LEVEL_WAVES.csv b/tests/workloads/kernel_summaries/MI200/SQ_LEVEL_WAVES.csv new file mode 100644 index 0000000000..8bbe3dd834 --- /dev/null +++ b/tests/workloads/kernel_summaries/MI200/SQ_LEVEL_WAVES.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,388843,388843,1048576,256,0,0,8,0,16,64,0x0,0x7f97cce0cec0,27576,27576,11203,220616,16384,10747459,127575,0,43502216,200776883476275,200787787628212,200787787648052,200776899925873 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,388843,388843,1048576,256,0,0,8,0,16,64,0x0,0x7f97cce0cec0,41396,41396,13324,331176,16384,19796869,227124,0,79670720,200776899952965,200787787740532,200787787757172,200776900260296 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,388843,388843,1048576,256,0,0,8,0,16,64,0x0,0x7f97cce0cec0,40594,40594,12845,324760,16384,19530583,223102,0,78594672,200776900295272,200787787778292,200787787794132,200776900472668 diff --git a/tests/workloads/kernel_summaries/MI200/perfmon/SQ_IFETCH_LEVEL.txt b/tests/workloads/kernel_summaries/MI200/perfmon/SQ_IFETCH_LEVEL.txt new file mode 100644 index 0000000000..293092f641 --- /dev/null +++ b/tests/workloads/kernel_summaries/MI200/perfmon/SQ_IFETCH_LEVEL.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_summaries/MI200/perfmon/SQ_INST_LEVEL_LDS.txt b/tests/workloads/kernel_summaries/MI200/perfmon/SQ_INST_LEVEL_LDS.txt new file mode 100644 index 0000000000..08439eedce --- /dev/null +++ b/tests/workloads/kernel_summaries/MI200/perfmon/SQ_INST_LEVEL_LDS.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_summaries/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt b/tests/workloads/kernel_summaries/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt new file mode 100644 index 0000000000..6cca322d4e --- /dev/null +++ b/tests/workloads/kernel_summaries/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_summaries/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt b/tests/workloads/kernel_summaries/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt new file mode 100644 index 0000000000..e527ad31ba --- /dev/null +++ b/tests/workloads/kernel_summaries/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_summaries/MI200/perfmon/SQ_LEVEL_WAVES.txt b/tests/workloads/kernel_summaries/MI200/perfmon/SQ_LEVEL_WAVES.txt new file mode 100644 index 0000000000..3f8e04adb3 --- /dev/null +++ b/tests/workloads/kernel_summaries/MI200/perfmon/SQ_LEVEL_WAVES.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_0.txt b/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_0.txt new file mode 100644 index 0000000000..4ffdc32149 --- /dev/null +++ b/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_0.txt @@ -0,0 +1,5 @@ +pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES SQ_INSTS_VALU_CVT SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU GRBM_COUNT GRBM_GUI_ACTIVE TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum TA_TA_BUSY_sum TA_BUFFER_WAVEFRONTS_sum TD_TD_BUSY_sum TD_TC_STALL_sum SPI_CSN_WINDOW_VALID SPI_CSN_BUSY CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_1.txt b/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_1.txt new file mode 100644 index 0000000000..6c277f4a37 --- /dev/null +++ b/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_1.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VSKIPPED SQ_INSTS SQ_INSTS_VALU SQ_INSTS_VALU_ADD_F16 SQ_INSTS_VALU_MUL_F16 SQ_INSTS_VALU_FMA_F16 SQ_INSTS_VALU_TRANS_F16 SQ_INSTS_VALU_ADD_F32 GRBM_SPI_BUSY TCP_READ_TAGCONFLICT_STALL_CYCLES_sum TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum TCP_TA_TCP_STATE_READ_sum TA_BUFFER_READ_WAVEFRONTS_sum TA_BUFFER_WRITE_WAVEFRONTS_sum TD_SPI_STALL_sum TD_LOAD_WAVEFRONT_sum SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_10.txt b/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_10.txt new file mode 100644 index 0000000000..7053d4dce6 --- /dev/null +++ b/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_10.txt @@ -0,0 +1,5 @@ +pmc: SQC_TC_DATA_WRITE_REQ SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_11.txt b/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_11.txt new file mode 100644 index 0000000000..77ae8b461f --- /dev/null +++ b/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_11.txt @@ -0,0 +1,5 @@ +pmc: SQC_ICACHE_MISSES_DUPLICATE SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_12.txt b/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_12.txt new file mode 100644 index 0000000000..dfb2cf65e5 --- /dev/null +++ b/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_12.txt @@ -0,0 +1,5 @@ +pmc: SQC_DCACHE_REQ_READ_1 SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_13.txt b/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_13.txt new file mode 100644 index 0000000000..062fc9644a --- /dev/null +++ b/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_13.txt @@ -0,0 +1,5 @@ +pmc: TCC_ATOMIC[0] TCC_CYCLE[0] TCC_EA_ATOMIC[0] TCC_EA_ATOMIC_LEVEL[0] TCC_ATOMIC[1] TCC_CYCLE[1] TCC_EA_ATOMIC[1] TCC_EA_ATOMIC_LEVEL[1] TCC_ATOMIC[2] TCC_CYCLE[2] TCC_EA_ATOMIC[2] TCC_EA_ATOMIC_LEVEL[2] TCC_ATOMIC[3] TCC_CYCLE[3] TCC_EA_ATOMIC[3] TCC_EA_ATOMIC_LEVEL[3] TCC_ATOMIC[4] TCC_CYCLE[4] TCC_EA_ATOMIC[4] TCC_EA_ATOMIC_LEVEL[4] TCC_ATOMIC[5] TCC_CYCLE[5] TCC_EA_ATOMIC[5] TCC_EA_ATOMIC_LEVEL[5] TCC_ATOMIC[6] TCC_CYCLE[6] TCC_EA_ATOMIC[6] TCC_EA_ATOMIC_LEVEL[6] TCC_ATOMIC[7] TCC_CYCLE[7] TCC_EA_ATOMIC[7] TCC_EA_ATOMIC_LEVEL[7] TCC_ATOMIC[8] TCC_CYCLE[8] TCC_EA_ATOMIC[8] TCC_EA_ATOMIC_LEVEL[8] TCC_ATOMIC[9] TCC_CYCLE[9] TCC_EA_ATOMIC[9] TCC_EA_ATOMIC_LEVEL[9] TCC_ATOMIC[10] TCC_CYCLE[10] TCC_EA_ATOMIC[10] TCC_EA_ATOMIC_LEVEL[10] TCC_ATOMIC[11] TCC_CYCLE[11] TCC_EA_ATOMIC[11] TCC_EA_ATOMIC_LEVEL[11] TCC_ATOMIC[12] TCC_CYCLE[12] TCC_EA_ATOMIC[12] TCC_EA_ATOMIC_LEVEL[12] TCC_ATOMIC[13] TCC_CYCLE[13] TCC_EA_ATOMIC[13] TCC_EA_ATOMIC_LEVEL[13] TCC_ATOMIC[14] TCC_CYCLE[14] TCC_EA_ATOMIC[14] TCC_EA_ATOMIC_LEVEL[14] TCC_ATOMIC[15] TCC_CYCLE[15] TCC_EA_ATOMIC[15] TCC_EA_ATOMIC_LEVEL[15] TCC_ATOMIC[16] TCC_CYCLE[16] TCC_EA_ATOMIC[16] TCC_EA_ATOMIC_LEVEL[16] TCC_ATOMIC[17] TCC_CYCLE[17] TCC_EA_ATOMIC[17] TCC_EA_ATOMIC_LEVEL[17] TCC_ATOMIC[18] TCC_CYCLE[18] TCC_EA_ATOMIC[18] TCC_EA_ATOMIC_LEVEL[18] TCC_ATOMIC[19] TCC_CYCLE[19] TCC_EA_ATOMIC[19] TCC_EA_ATOMIC_LEVEL[19] TCC_ATOMIC[20] TCC_CYCLE[20] TCC_EA_ATOMIC[20] TCC_EA_ATOMIC_LEVEL[20] TCC_ATOMIC[21] TCC_CYCLE[21] TCC_EA_ATOMIC[21] TCC_EA_ATOMIC_LEVEL[21] TCC_ATOMIC[22] TCC_CYCLE[22] TCC_EA_ATOMIC[22] TCC_EA_ATOMIC_LEVEL[22] TCC_ATOMIC[23] TCC_CYCLE[23] TCC_EA_ATOMIC[23] TCC_EA_ATOMIC_LEVEL[23] TCC_ATOMIC[24] TCC_CYCLE[24] TCC_EA_ATOMIC[24] TCC_EA_ATOMIC_LEVEL[24] TCC_ATOMIC[25] TCC_CYCLE[25] TCC_EA_ATOMIC[25] TCC_EA_ATOMIC_LEVEL[25] TCC_ATOMIC[26] TCC_CYCLE[26] TCC_EA_ATOMIC[26] TCC_EA_ATOMIC_LEVEL[26] TCC_ATOMIC[27] TCC_CYCLE[27] TCC_EA_ATOMIC[27] TCC_EA_ATOMIC_LEVEL[27] TCC_ATOMIC[28] TCC_CYCLE[28] TCC_EA_ATOMIC[28] TCC_EA_ATOMIC_LEVEL[28] TCC_ATOMIC[29] TCC_CYCLE[29] TCC_EA_ATOMIC[29] TCC_EA_ATOMIC_LEVEL[29] TCC_ATOMIC[30] TCC_CYCLE[30] TCC_EA_ATOMIC[30] TCC_EA_ATOMIC_LEVEL[30] TCC_ATOMIC[31] TCC_CYCLE[31] TCC_EA_ATOMIC[31] TCC_EA_ATOMIC_LEVEL[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_14.txt b/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_14.txt new file mode 100644 index 0000000000..e0698dbf57 --- /dev/null +++ b/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_14.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_EA_RDREQ_GMI_CREDIT_STALL[0] TCC_EA_RDREQ[1] TCC_EA_RDREQ_32B[1] TCC_EA_RDREQ_DRAM_CREDIT_STALL[1] TCC_EA_RDREQ_GMI_CREDIT_STALL[1] TCC_EA_RDREQ[2] TCC_EA_RDREQ_32B[2] TCC_EA_RDREQ_DRAM_CREDIT_STALL[2] TCC_EA_RDREQ_GMI_CREDIT_STALL[2] TCC_EA_RDREQ[3] TCC_EA_RDREQ_32B[3] TCC_EA_RDREQ_DRAM_CREDIT_STALL[3] TCC_EA_RDREQ_GMI_CREDIT_STALL[3] TCC_EA_RDREQ[4] TCC_EA_RDREQ_32B[4] TCC_EA_RDREQ_DRAM_CREDIT_STALL[4] TCC_EA_RDREQ_GMI_CREDIT_STALL[4] TCC_EA_RDREQ[5] TCC_EA_RDREQ_32B[5] TCC_EA_RDREQ_DRAM_CREDIT_STALL[5] TCC_EA_RDREQ_GMI_CREDIT_STALL[5] TCC_EA_RDREQ[6] TCC_EA_RDREQ_32B[6] TCC_EA_RDREQ_DRAM_CREDIT_STALL[6] TCC_EA_RDREQ_GMI_CREDIT_STALL[6] TCC_EA_RDREQ[7] TCC_EA_RDREQ_32B[7] TCC_EA_RDREQ_DRAM_CREDIT_STALL[7] TCC_EA_RDREQ_GMI_CREDIT_STALL[7] TCC_EA_RDREQ[8] TCC_EA_RDREQ_32B[8] TCC_EA_RDREQ_DRAM_CREDIT_STALL[8] TCC_EA_RDREQ_GMI_CREDIT_STALL[8] TCC_EA_RDREQ[9] TCC_EA_RDREQ_32B[9] TCC_EA_RDREQ_DRAM_CREDIT_STALL[9] TCC_EA_RDREQ_GMI_CREDIT_STALL[9] TCC_EA_RDREQ[10] TCC_EA_RDREQ_32B[10] TCC_EA_RDREQ_DRAM_CREDIT_STALL[10] TCC_EA_RDREQ_GMI_CREDIT_STALL[10] TCC_EA_RDREQ[11] TCC_EA_RDREQ_32B[11] TCC_EA_RDREQ_DRAM_CREDIT_STALL[11] TCC_EA_RDREQ_GMI_CREDIT_STALL[11] TCC_EA_RDREQ[12] TCC_EA_RDREQ_32B[12] TCC_EA_RDREQ_DRAM_CREDIT_STALL[12] TCC_EA_RDREQ_GMI_CREDIT_STALL[12] TCC_EA_RDREQ[13] TCC_EA_RDREQ_32B[13] TCC_EA_RDREQ_DRAM_CREDIT_STALL[13] TCC_EA_RDREQ_GMI_CREDIT_STALL[13] TCC_EA_RDREQ[14] TCC_EA_RDREQ_32B[14] TCC_EA_RDREQ_DRAM_CREDIT_STALL[14] TCC_EA_RDREQ_GMI_CREDIT_STALL[14] TCC_EA_RDREQ[15] TCC_EA_RDREQ_32B[15] TCC_EA_RDREQ_DRAM_CREDIT_STALL[15] TCC_EA_RDREQ_GMI_CREDIT_STALL[15] TCC_EA_RDREQ[16] TCC_EA_RDREQ_32B[16] TCC_EA_RDREQ_DRAM_CREDIT_STALL[16] TCC_EA_RDREQ_GMI_CREDIT_STALL[16] TCC_EA_RDREQ[17] TCC_EA_RDREQ_32B[17] TCC_EA_RDREQ_DRAM_CREDIT_STALL[17] TCC_EA_RDREQ_GMI_CREDIT_STALL[17] TCC_EA_RDREQ[18] TCC_EA_RDREQ_32B[18] TCC_EA_RDREQ_DRAM_CREDIT_STALL[18] TCC_EA_RDREQ_GMI_CREDIT_STALL[18] TCC_EA_RDREQ[19] TCC_EA_RDREQ_32B[19] TCC_EA_RDREQ_DRAM_CREDIT_STALL[19] TCC_EA_RDREQ_GMI_CREDIT_STALL[19] TCC_EA_RDREQ[20] TCC_EA_RDREQ_32B[20] TCC_EA_RDREQ_DRAM_CREDIT_STALL[20] TCC_EA_RDREQ_GMI_CREDIT_STALL[20] TCC_EA_RDREQ[21] TCC_EA_RDREQ_32B[21] TCC_EA_RDREQ_DRAM_CREDIT_STALL[21] TCC_EA_RDREQ_GMI_CREDIT_STALL[21] TCC_EA_RDREQ[22] TCC_EA_RDREQ_32B[22] TCC_EA_RDREQ_DRAM_CREDIT_STALL[22] TCC_EA_RDREQ_GMI_CREDIT_STALL[22] TCC_EA_RDREQ[23] TCC_EA_RDREQ_32B[23] TCC_EA_RDREQ_DRAM_CREDIT_STALL[23] TCC_EA_RDREQ_GMI_CREDIT_STALL[23] TCC_EA_RDREQ[24] TCC_EA_RDREQ_32B[24] TCC_EA_RDREQ_DRAM_CREDIT_STALL[24] TCC_EA_RDREQ_GMI_CREDIT_STALL[24] TCC_EA_RDREQ[25] TCC_EA_RDREQ_32B[25] TCC_EA_RDREQ_DRAM_CREDIT_STALL[25] TCC_EA_RDREQ_GMI_CREDIT_STALL[25] TCC_EA_RDREQ[26] TCC_EA_RDREQ_32B[26] TCC_EA_RDREQ_DRAM_CREDIT_STALL[26] TCC_EA_RDREQ_GMI_CREDIT_STALL[26] TCC_EA_RDREQ[27] TCC_EA_RDREQ_32B[27] TCC_EA_RDREQ_DRAM_CREDIT_STALL[27] TCC_EA_RDREQ_GMI_CREDIT_STALL[27] TCC_EA_RDREQ[28] TCC_EA_RDREQ_32B[28] TCC_EA_RDREQ_DRAM_CREDIT_STALL[28] TCC_EA_RDREQ_GMI_CREDIT_STALL[28] TCC_EA_RDREQ[29] TCC_EA_RDREQ_32B[29] TCC_EA_RDREQ_DRAM_CREDIT_STALL[29] TCC_EA_RDREQ_GMI_CREDIT_STALL[29] TCC_EA_RDREQ[30] TCC_EA_RDREQ_32B[30] TCC_EA_RDREQ_DRAM_CREDIT_STALL[30] TCC_EA_RDREQ_GMI_CREDIT_STALL[30] TCC_EA_RDREQ[31] TCC_EA_RDREQ_32B[31] TCC_EA_RDREQ_DRAM_CREDIT_STALL[31] TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_15.txt b/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_15.txt new file mode 100644 index 0000000000..77ad088669 --- /dev/null +++ b/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_15.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ[0] TCC_EA_WRREQ_64B[0] TCC_EA_RDREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_LEVEL[1] TCC_EA_WRREQ[1] TCC_EA_WRREQ_64B[1] TCC_EA_RDREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_LEVEL[2] TCC_EA_WRREQ[2] TCC_EA_WRREQ_64B[2] TCC_EA_RDREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_LEVEL[3] TCC_EA_WRREQ[3] TCC_EA_WRREQ_64B[3] TCC_EA_RDREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_LEVEL[4] TCC_EA_WRREQ[4] TCC_EA_WRREQ_64B[4] TCC_EA_RDREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_LEVEL[5] TCC_EA_WRREQ[5] TCC_EA_WRREQ_64B[5] TCC_EA_RDREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_LEVEL[6] TCC_EA_WRREQ[6] TCC_EA_WRREQ_64B[6] TCC_EA_RDREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_LEVEL[7] TCC_EA_WRREQ[7] TCC_EA_WRREQ_64B[7] TCC_EA_RDREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_LEVEL[8] TCC_EA_WRREQ[8] TCC_EA_WRREQ_64B[8] TCC_EA_RDREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_LEVEL[9] TCC_EA_WRREQ[9] TCC_EA_WRREQ_64B[9] TCC_EA_RDREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_LEVEL[10] TCC_EA_WRREQ[10] TCC_EA_WRREQ_64B[10] TCC_EA_RDREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_LEVEL[11] TCC_EA_WRREQ[11] TCC_EA_WRREQ_64B[11] TCC_EA_RDREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_LEVEL[12] TCC_EA_WRREQ[12] TCC_EA_WRREQ_64B[12] TCC_EA_RDREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_LEVEL[13] TCC_EA_WRREQ[13] TCC_EA_WRREQ_64B[13] TCC_EA_RDREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_LEVEL[14] TCC_EA_WRREQ[14] TCC_EA_WRREQ_64B[14] TCC_EA_RDREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_LEVEL[15] TCC_EA_WRREQ[15] TCC_EA_WRREQ_64B[15] TCC_EA_RDREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_LEVEL[16] TCC_EA_WRREQ[16] TCC_EA_WRREQ_64B[16] TCC_EA_RDREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_LEVEL[17] TCC_EA_WRREQ[17] TCC_EA_WRREQ_64B[17] TCC_EA_RDREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_LEVEL[18] TCC_EA_WRREQ[18] TCC_EA_WRREQ_64B[18] TCC_EA_RDREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_LEVEL[19] TCC_EA_WRREQ[19] TCC_EA_WRREQ_64B[19] TCC_EA_RDREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_LEVEL[20] TCC_EA_WRREQ[20] TCC_EA_WRREQ_64B[20] TCC_EA_RDREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_LEVEL[21] TCC_EA_WRREQ[21] TCC_EA_WRREQ_64B[21] TCC_EA_RDREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_LEVEL[22] TCC_EA_WRREQ[22] TCC_EA_WRREQ_64B[22] TCC_EA_RDREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_LEVEL[23] TCC_EA_WRREQ[23] TCC_EA_WRREQ_64B[23] TCC_EA_RDREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_LEVEL[24] TCC_EA_WRREQ[24] TCC_EA_WRREQ_64B[24] TCC_EA_RDREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_LEVEL[25] TCC_EA_WRREQ[25] TCC_EA_WRREQ_64B[25] TCC_EA_RDREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_LEVEL[26] TCC_EA_WRREQ[26] TCC_EA_WRREQ_64B[26] TCC_EA_RDREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_LEVEL[27] TCC_EA_WRREQ[27] TCC_EA_WRREQ_64B[27] TCC_EA_RDREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_LEVEL[28] TCC_EA_WRREQ[28] TCC_EA_WRREQ_64B[28] TCC_EA_RDREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_LEVEL[29] TCC_EA_WRREQ[29] TCC_EA_WRREQ_64B[29] TCC_EA_RDREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_LEVEL[30] TCC_EA_WRREQ[30] TCC_EA_WRREQ_64B[30] TCC_EA_RDREQ_IO_CREDIT_STALL[31] TCC_EA_RDREQ_LEVEL[31] TCC_EA_WRREQ[31] TCC_EA_WRREQ_64B[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_16.txt b/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_16.txt new file mode 100644 index 0000000000..d0628bb948 --- /dev/null +++ b/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_16.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_WRREQ_IO_CREDIT_STALL[0] TCC_EA_WRREQ_LEVEL[0] TCC_EA_WRREQ_DRAM_CREDIT_STALL[1] TCC_EA_WRREQ_GMI_CREDIT_STALL[1] TCC_EA_WRREQ_IO_CREDIT_STALL[1] TCC_EA_WRREQ_LEVEL[1] TCC_EA_WRREQ_DRAM_CREDIT_STALL[2] TCC_EA_WRREQ_GMI_CREDIT_STALL[2] TCC_EA_WRREQ_IO_CREDIT_STALL[2] TCC_EA_WRREQ_LEVEL[2] TCC_EA_WRREQ_DRAM_CREDIT_STALL[3] TCC_EA_WRREQ_GMI_CREDIT_STALL[3] TCC_EA_WRREQ_IO_CREDIT_STALL[3] TCC_EA_WRREQ_LEVEL[3] TCC_EA_WRREQ_DRAM_CREDIT_STALL[4] TCC_EA_WRREQ_GMI_CREDIT_STALL[4] TCC_EA_WRREQ_IO_CREDIT_STALL[4] TCC_EA_WRREQ_LEVEL[4] TCC_EA_WRREQ_DRAM_CREDIT_STALL[5] TCC_EA_WRREQ_GMI_CREDIT_STALL[5] TCC_EA_WRREQ_IO_CREDIT_STALL[5] TCC_EA_WRREQ_LEVEL[5] TCC_EA_WRREQ_DRAM_CREDIT_STALL[6] TCC_EA_WRREQ_GMI_CREDIT_STALL[6] TCC_EA_WRREQ_IO_CREDIT_STALL[6] TCC_EA_WRREQ_LEVEL[6] TCC_EA_WRREQ_DRAM_CREDIT_STALL[7] TCC_EA_WRREQ_GMI_CREDIT_STALL[7] TCC_EA_WRREQ_IO_CREDIT_STALL[7] TCC_EA_WRREQ_LEVEL[7] TCC_EA_WRREQ_DRAM_CREDIT_STALL[8] TCC_EA_WRREQ_GMI_CREDIT_STALL[8] TCC_EA_WRREQ_IO_CREDIT_STALL[8] TCC_EA_WRREQ_LEVEL[8] TCC_EA_WRREQ_DRAM_CREDIT_STALL[9] TCC_EA_WRREQ_GMI_CREDIT_STALL[9] TCC_EA_WRREQ_IO_CREDIT_STALL[9] TCC_EA_WRREQ_LEVEL[9] TCC_EA_WRREQ_DRAM_CREDIT_STALL[10] TCC_EA_WRREQ_GMI_CREDIT_STALL[10] TCC_EA_WRREQ_IO_CREDIT_STALL[10] TCC_EA_WRREQ_LEVEL[10] TCC_EA_WRREQ_DRAM_CREDIT_STALL[11] TCC_EA_WRREQ_GMI_CREDIT_STALL[11] TCC_EA_WRREQ_IO_CREDIT_STALL[11] TCC_EA_WRREQ_LEVEL[11] TCC_EA_WRREQ_DRAM_CREDIT_STALL[12] TCC_EA_WRREQ_GMI_CREDIT_STALL[12] TCC_EA_WRREQ_IO_CREDIT_STALL[12] TCC_EA_WRREQ_LEVEL[12] TCC_EA_WRREQ_DRAM_CREDIT_STALL[13] TCC_EA_WRREQ_GMI_CREDIT_STALL[13] TCC_EA_WRREQ_IO_CREDIT_STALL[13] TCC_EA_WRREQ_LEVEL[13] TCC_EA_WRREQ_DRAM_CREDIT_STALL[14] TCC_EA_WRREQ_GMI_CREDIT_STALL[14] TCC_EA_WRREQ_IO_CREDIT_STALL[14] TCC_EA_WRREQ_LEVEL[14] TCC_EA_WRREQ_DRAM_CREDIT_STALL[15] TCC_EA_WRREQ_GMI_CREDIT_STALL[15] TCC_EA_WRREQ_IO_CREDIT_STALL[15] TCC_EA_WRREQ_LEVEL[15] TCC_EA_WRREQ_DRAM_CREDIT_STALL[16] TCC_EA_WRREQ_GMI_CREDIT_STALL[16] TCC_EA_WRREQ_IO_CREDIT_STALL[16] TCC_EA_WRREQ_LEVEL[16] TCC_EA_WRREQ_DRAM_CREDIT_STALL[17] TCC_EA_WRREQ_GMI_CREDIT_STALL[17] TCC_EA_WRREQ_IO_CREDIT_STALL[17] TCC_EA_WRREQ_LEVEL[17] TCC_EA_WRREQ_DRAM_CREDIT_STALL[18] TCC_EA_WRREQ_GMI_CREDIT_STALL[18] TCC_EA_WRREQ_IO_CREDIT_STALL[18] TCC_EA_WRREQ_LEVEL[18] TCC_EA_WRREQ_DRAM_CREDIT_STALL[19] TCC_EA_WRREQ_GMI_CREDIT_STALL[19] TCC_EA_WRREQ_IO_CREDIT_STALL[19] TCC_EA_WRREQ_LEVEL[19] TCC_EA_WRREQ_DRAM_CREDIT_STALL[20] TCC_EA_WRREQ_GMI_CREDIT_STALL[20] TCC_EA_WRREQ_IO_CREDIT_STALL[20] TCC_EA_WRREQ_LEVEL[20] TCC_EA_WRREQ_DRAM_CREDIT_STALL[21] TCC_EA_WRREQ_GMI_CREDIT_STALL[21] TCC_EA_WRREQ_IO_CREDIT_STALL[21] TCC_EA_WRREQ_LEVEL[21] TCC_EA_WRREQ_DRAM_CREDIT_STALL[22] TCC_EA_WRREQ_GMI_CREDIT_STALL[22] TCC_EA_WRREQ_IO_CREDIT_STALL[22] TCC_EA_WRREQ_LEVEL[22] TCC_EA_WRREQ_DRAM_CREDIT_STALL[23] TCC_EA_WRREQ_GMI_CREDIT_STALL[23] TCC_EA_WRREQ_IO_CREDIT_STALL[23] TCC_EA_WRREQ_LEVEL[23] TCC_EA_WRREQ_DRAM_CREDIT_STALL[24] TCC_EA_WRREQ_GMI_CREDIT_STALL[24] TCC_EA_WRREQ_IO_CREDIT_STALL[24] TCC_EA_WRREQ_LEVEL[24] TCC_EA_WRREQ_DRAM_CREDIT_STALL[25] TCC_EA_WRREQ_GMI_CREDIT_STALL[25] TCC_EA_WRREQ_IO_CREDIT_STALL[25] TCC_EA_WRREQ_LEVEL[25] TCC_EA_WRREQ_DRAM_CREDIT_STALL[26] TCC_EA_WRREQ_GMI_CREDIT_STALL[26] TCC_EA_WRREQ_IO_CREDIT_STALL[26] TCC_EA_WRREQ_LEVEL[26] TCC_EA_WRREQ_DRAM_CREDIT_STALL[27] TCC_EA_WRREQ_GMI_CREDIT_STALL[27] TCC_EA_WRREQ_IO_CREDIT_STALL[27] TCC_EA_WRREQ_LEVEL[27] TCC_EA_WRREQ_DRAM_CREDIT_STALL[28] TCC_EA_WRREQ_GMI_CREDIT_STALL[28] TCC_EA_WRREQ_IO_CREDIT_STALL[28] TCC_EA_WRREQ_LEVEL[28] TCC_EA_WRREQ_DRAM_CREDIT_STALL[29] TCC_EA_WRREQ_GMI_CREDIT_STALL[29] TCC_EA_WRREQ_IO_CREDIT_STALL[29] TCC_EA_WRREQ_LEVEL[29] TCC_EA_WRREQ_DRAM_CREDIT_STALL[30] TCC_EA_WRREQ_GMI_CREDIT_STALL[30] TCC_EA_WRREQ_IO_CREDIT_STALL[30] TCC_EA_WRREQ_LEVEL[30] TCC_EA_WRREQ_DRAM_CREDIT_STALL[31] TCC_EA_WRREQ_GMI_CREDIT_STALL[31] TCC_EA_WRREQ_IO_CREDIT_STALL[31] TCC_EA_WRREQ_LEVEL[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_17.txt b/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_17.txt new file mode 100644 index 0000000000..343869c5f1 --- /dev/null +++ b/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_17.txt @@ -0,0 +1,5 @@ +pmc: TCC_HIT[0] TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_HIT[1] TCC_MISS[1] TCC_READ[1] TCC_REQ[1] TCC_HIT[2] TCC_MISS[2] TCC_READ[2] TCC_REQ[2] TCC_HIT[3] TCC_MISS[3] TCC_READ[3] TCC_REQ[3] TCC_HIT[4] TCC_MISS[4] TCC_READ[4] TCC_REQ[4] TCC_HIT[5] TCC_MISS[5] TCC_READ[5] TCC_REQ[5] TCC_HIT[6] TCC_MISS[6] TCC_READ[6] TCC_REQ[6] TCC_HIT[7] TCC_MISS[7] TCC_READ[7] TCC_REQ[7] TCC_HIT[8] TCC_MISS[8] TCC_READ[8] TCC_REQ[8] TCC_HIT[9] TCC_MISS[9] TCC_READ[9] TCC_REQ[9] TCC_HIT[10] TCC_MISS[10] TCC_READ[10] TCC_REQ[10] TCC_HIT[11] TCC_MISS[11] TCC_READ[11] TCC_REQ[11] TCC_HIT[12] TCC_MISS[12] TCC_READ[12] TCC_REQ[12] TCC_HIT[13] TCC_MISS[13] TCC_READ[13] TCC_REQ[13] TCC_HIT[14] TCC_MISS[14] TCC_READ[14] TCC_REQ[14] TCC_HIT[15] TCC_MISS[15] TCC_READ[15] TCC_REQ[15] TCC_HIT[16] TCC_MISS[16] TCC_READ[16] TCC_REQ[16] TCC_HIT[17] TCC_MISS[17] TCC_READ[17] TCC_REQ[17] TCC_HIT[18] TCC_MISS[18] TCC_READ[18] TCC_REQ[18] TCC_HIT[19] TCC_MISS[19] TCC_READ[19] TCC_REQ[19] TCC_HIT[20] TCC_MISS[20] TCC_READ[20] TCC_REQ[20] TCC_HIT[21] TCC_MISS[21] TCC_READ[21] TCC_REQ[21] TCC_HIT[22] TCC_MISS[22] TCC_READ[22] TCC_REQ[22] TCC_HIT[23] TCC_MISS[23] TCC_READ[23] TCC_REQ[23] TCC_HIT[24] TCC_MISS[24] TCC_READ[24] TCC_REQ[24] TCC_HIT[25] TCC_MISS[25] TCC_READ[25] TCC_REQ[25] TCC_HIT[26] TCC_MISS[26] TCC_READ[26] TCC_REQ[26] TCC_HIT[27] TCC_MISS[27] TCC_READ[27] TCC_REQ[27] TCC_HIT[28] TCC_MISS[28] TCC_READ[28] TCC_REQ[28] TCC_HIT[29] TCC_MISS[29] TCC_READ[29] TCC_REQ[29] TCC_HIT[30] TCC_MISS[30] TCC_READ[30] TCC_REQ[30] TCC_HIT[31] TCC_MISS[31] TCC_READ[31] TCC_REQ[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_18.txt b/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_18.txt new file mode 100644 index 0000000000..a74cefd281 --- /dev/null +++ b/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_18.txt @@ -0,0 +1,5 @@ +pmc: TCC_RW_REQ[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_RW_REQ[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_WRITE[1] TCC_RW_REQ[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_WRITE[2] TCC_RW_REQ[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_WRITE[3] TCC_RW_REQ[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_WRITE[4] TCC_RW_REQ[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_WRITE[5] TCC_RW_REQ[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_WRITE[6] TCC_RW_REQ[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_WRITE[7] TCC_RW_REQ[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_WRITE[8] TCC_RW_REQ[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_WRITE[9] TCC_RW_REQ[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_WRITE[10] TCC_RW_REQ[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_WRITE[11] TCC_RW_REQ[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_WRITE[12] TCC_RW_REQ[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_WRITE[13] TCC_RW_REQ[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_WRITE[14] TCC_RW_REQ[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_WRITE[15] TCC_RW_REQ[16] TCC_TOO_MANY_EA_WRREQS_STALL[16] TCC_WRITE[16] TCC_RW_REQ[17] TCC_TOO_MANY_EA_WRREQS_STALL[17] TCC_WRITE[17] TCC_RW_REQ[18] TCC_TOO_MANY_EA_WRREQS_STALL[18] TCC_WRITE[18] TCC_RW_REQ[19] TCC_TOO_MANY_EA_WRREQS_STALL[19] TCC_WRITE[19] TCC_RW_REQ[20] TCC_TOO_MANY_EA_WRREQS_STALL[20] TCC_WRITE[20] TCC_RW_REQ[21] TCC_TOO_MANY_EA_WRREQS_STALL[21] TCC_WRITE[21] TCC_RW_REQ[22] TCC_TOO_MANY_EA_WRREQS_STALL[22] TCC_WRITE[22] TCC_RW_REQ[23] TCC_TOO_MANY_EA_WRREQS_STALL[23] TCC_WRITE[23] TCC_RW_REQ[24] TCC_TOO_MANY_EA_WRREQS_STALL[24] TCC_WRITE[24] TCC_RW_REQ[25] TCC_TOO_MANY_EA_WRREQS_STALL[25] TCC_WRITE[25] TCC_RW_REQ[26] TCC_TOO_MANY_EA_WRREQS_STALL[26] TCC_WRITE[26] TCC_RW_REQ[27] TCC_TOO_MANY_EA_WRREQS_STALL[27] TCC_WRITE[27] TCC_RW_REQ[28] TCC_TOO_MANY_EA_WRREQS_STALL[28] TCC_WRITE[28] TCC_RW_REQ[29] TCC_TOO_MANY_EA_WRREQS_STALL[29] TCC_WRITE[29] TCC_RW_REQ[30] TCC_TOO_MANY_EA_WRREQS_STALL[30] TCC_WRITE[30] TCC_RW_REQ[31] TCC_TOO_MANY_EA_WRREQS_STALL[31] TCC_WRITE[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_2.txt b/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_2.txt new file mode 100644 index 0000000000..70b69f8928 --- /dev/null +++ b/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_2.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_MUL_F32 SQ_INSTS_VALU_FMA_F32 SQ_INSTS_VALU_TRANS_F32 SQ_INSTS_VALU_ADD_F64 SQ_INSTS_VALU_MUL_F64 SQ_INSTS_VALU_FMA_F64 SQ_INSTS_VALU_TRANS_F64 SQ_INSTS_VALU_INT32 TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum TA_BUFFER_ATOMIC_WAVEFRONTS_sum TA_BUFFER_TOTAL_CYCLES_sum TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_3.txt b/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_3.txt new file mode 100644 index 0000000000..e47f8e33c9 --- /dev/null +++ b/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_3.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_INT64 SQ_INSTS_SMEM SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum TD_COALESCABLE_WAVEFRONT_sum SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE CPF_CMP_UTCL1_STALL_ON_TRANSLATION TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_4.txt b/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_4.txt new file mode 100644 index 0000000000..2d96f365a9 --- /dev/null +++ b/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_4.txt @@ -0,0 +1,5 @@ +pmc: SQ_WAVE_CYCLES SQ_WAIT_ANY SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_BUSY_CU_CYCLES SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE TCC_EA_WRREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WR_UNCACHED_32B_sum TCC_EA_WRREQ_DRAM_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_5.txt b/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_5.txt new file mode 100644 index 0000000000..e50beed390 --- /dev/null +++ b/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_5.txt @@ -0,0 +1,5 @@ +pmc: SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU TCP_TCP_LATENCY_sum TCP_TCC_READ_REQ_LATENCY_sum TCP_TCC_WRITE_REQ_LATENCY_sum TCP_TCC_READ_REQ_sum TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN CPC_ME1_DC0_SPI_BUSY TCC_EA_WRREQ_STALL_sum TCC_EA_RDREQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RD_UNCACHED_32B_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_6.txt b/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_6.txt new file mode 100644 index 0000000000..15a2277c1b --- /dev/null +++ b/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_6.txt @@ -0,0 +1,5 @@ +pmc: SQ_THREAD_CYCLES_VALU SQ_IFETCH SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TCP_TCC_NC_READ_REQ_sum TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN TCC_EA_RDREQ_DRAM_sum TCC_TAG_STALL_sum TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_7.txt b/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_7.txt new file mode 100644 index 0000000000..b42ce91618 --- /dev/null +++ b/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_7.txt @@ -0,0 +1,5 @@ +pmc: SQ_WAVES_LT_32 SQ_WAVES_LT_16 SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TCP_TCC_UC_WRITE_REQ_sum TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR TCC_NORMAL_EVICT_sum TCC_ALL_TC_OP_INV_EVICT_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA_ATOMIC_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_8.txt b/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_8.txt new file mode 100644 index 0000000000..21d4c7a998 --- /dev/null +++ b/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_8.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM_NORM SQ_INSTS_MFMA SQ_INSTS_VALU_MFMA_I8 SQ_INSTS_VALU_MFMA_F16 SQ_INSTS_VALU_MFMA_BF16 SQ_INSTS_VALU_MFMA_F32 SQ_INSTS_VALU_MFMA_F64 SQ_VALU_MFMA_BUSY_CYCLES TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TCP_TCC_CC_ATOMIC_REQ_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN TCC_EA_RDREQ_LEVEL_sum TCC_EA_WRREQ_LEVEL_sum TCC_EA_ATOMIC_LEVEL_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_9.txt b/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_9.txt new file mode 100644 index 0000000000..9ffe5778c3 --- /dev/null +++ b/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_9.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_FLAT_LDS_ONLY SQ_INSTS_VALU_MFMA_MOPS_I8 SQ_INSTS_VALU_MFMA_MOPS_F16 SQ_INSTS_VALU_MFMA_MOPS_BF16 SQ_INSTS_VALU_MFMA_MOPS_F32 SQ_INSTS_VALU_MFMA_MOPS_F64 SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum TCP_PENDING_STALL_CYCLES_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_summaries/MI200/perfmon/timestamps.txt b/tests/workloads/kernel_summaries/MI200/perfmon/timestamps.txt new file mode 100644 index 0000000000..676cca1b80 --- /dev/null +++ b/tests/workloads/kernel_summaries/MI200/perfmon/timestamps.txt @@ -0,0 +1,5 @@ +pmc: + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_summaries/MI200/pmc_perf.csv b/tests/workloads/kernel_summaries/MI200/pmc_perf.csv new file mode 100644 index 0000000000..d97416aabb --- /dev/null +++ b/tests/workloads/kernel_summaries/MI200/pmc_perf.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,TD_COALESCABLE_WAVEFRONT_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_1,obj_1,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_2,obj_2,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_3,obj_3,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_4,obj_4,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_5,obj_5,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_6,obj_6,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,TCC_EA_ATOMIC_LEVEL_sum,wave_size_7,obj_7,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,wave_size_8,obj_8,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_9,obj_9,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_10,obj_10,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_DRAM_sum,TCC_TAG_STALL_sum,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,wave_size_11,obj_11,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_12,obj_12,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_13,obj_13,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_14,obj_14,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_15,obj_15,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_16,obj_16,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_17,obj_17,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_18,obj_18,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f8cb5680ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,9941,0,815,28305,0,72771.0,131072.0,0.0,65568.0,64,0x7f4dc6f04ec0,4096,0,50,0,4096,0,0,0,4096,0,0,0,4100,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,83,0,4096,0,77,0,4096,0,91,0,4096,0,96,0,4096,0,0,0,4096,0,128,0,4096,0,7,0,4097,0,0,0,4097,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,96,0,4096,0,0,0,4096,0,0,0,4096,0,66,0,4099,0,28,0,4096,0,88,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,71,0,4096,0,0,0,4096,0,0,0,4096,0,10,0,64,0x7f12d755cec0,32768,32768,0,64,0x7fc427340ec0,1280,120072,0,0,65536,63800,56,1680,64,0x7f0ede0a8ec0,10792683,9709413,739206,344064,1634345,0,0,163840,832.0,515146.0,0.0,524288.0,283214.0,32768.0,470483,0,0,10679,131072.0,131072.0,0.0,131072.0,64,0x7fd053b44ec0,0,0,0,0,0,0,168,56,131072.0,131072.0,0.0,952369.0,64,0x7ff1c88bcec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,40067951.0,35212390.0,0.0,64,0x7f27f1d84ec0,114688,0,32768,32768,16384,16384,65536,49152,28005946.0,84730216.0,39691226.0,131072.0,0.0,231750.0,0,0,15405,326.0,131082.0,0.0,12.0,64,0x7f02bc090ec0,0,0,0,224,0,65536,64201,56,64,0x7f71fb6c4ec0,0,0,0,1062890,0,0,0,1161710,0,0,0,1005251,0,0,0,1146937,126,0,0,1173208,155,0,0,1181359,0,0,0,1083314,0,0,0,1141285,0,0,0,1024216,0,0,0,1008006,51,0,0,1068883,0,0,0,1139113,0,0,0,1143369,0,0,0,967772,0,0,0,1059054,0,0,0,1225094,0,0,0,1073672,172,0,0,1151115,0,0,0,975037,0,0,0,1106246,0,0,0,1048663,0,0,0,1127460,19,0,0,1010370,0,0,0,1042960,0,0,0,982746,209,0,0,1382108,0,0,0,972810,0,0,0,1045236,103,0,0,1319196,0,0,0,1105676,0,0,0,1105274,0,0,0,1179278,64,0x7f5c86b64ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131080.0,34601.0,46044.0,19492.0,64,0x7fe59bab8ec0,6377,0,4096,6325,0,4096,6367,0,4096,6400,0,4096,6329,0,4096,6346,0,4096,6386,0,4096,6414,0,4096,6417,0,4096,6378,0,4096,6329,0,4096,6369,0,4096,6399,0,4096,6325,0,4096,6347,0,4096,6386,0,4096,6433,0,4096,6385,0,4096,6391,0,4096,6387,0,4096,6412,0,4096,6414,0,4096,6384,0,4096,6529,0,4096,6361,0,4096,6434,0,4096,6388,0,4096,6393,0,4096,6390,0,4096,6414,0,4096,6414,0,4096,6387,0,4096,64,0x7f00e0898ec0,2223,4096,2223,6319,2278,4096,2278,6374,2268,4096,2268,6364,2300,4096,2300,6396,2227,4096,2227,6323,2267,4096,2267,6363,2303,4096,2303,6399,2311,4097,2312,6408,2309,4096,2309,6405,2225,4096,2225,6321,2278,4096,2278,6374,2270,4096,2270,6366,2296,4096,2296,6392,2229,4096,2229,6325,2269,4096,2269,6365,2298,4096,2298,6394,2251,4096,2251,6347,2291,4096,2291,6387,2279,4097,2280,6376,2278,4100,2282,6378,2280,4096,2280,6376,2317,4096,2317,6413,2299,4096,2299,6395,2424,4098,2426,6522,2254,4096,2254,6350,2305,4097,2306,6402,2291,4096,2291,6387,2287,4096,2287,6383,2281,4096,2281,6377,2281,4096,2281,6377,2315,4096,2315,6411,2303,4096,2303,6399,64,0x7f34907d8ec0,227904,126692,16384,0,16384,16384,32768,49152,28487,28487,1924642.0,1335880.0,3355.0,166343.0,1034129.0,0.0,1327872.0,1029460.0,226193,134828,28487,0,28487,0,911584.0,485326.0,0.0,0.0,64,0x7f9df37d0ec0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,64,0x7fb93c8acec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,12880,19043,8143,546,0,26860,204615.0,0.0,73534.0,131081.0,64,0x7f6090dc4ec0,0,393216,163840,0,0,0,0,0,17856,0.0,0.0,0.0,32768.0,0.0,0.0,409.0,32768.0,4096,16384,352,27100,1303,0,56.0,7.0,0.0,204738.0,64,0x7f0809060ec0,0,1186912,4096,4096,0,1223532,4096,4096,0,1219258,4096,4096,0,1658359,4096,4096,0,1251900,4096,4096,0,1347923,4096,4096,0,1019107,4096,4096,0,1325625,4096,4096,0,1163495,4096,4096,0,1111185,4096,4096,0,1268906,4096,4096,0,1205246,4096,4096,0,1109719,4096,4096,0,1234891,4096,4096,0,1379125,4096,4096,0,1279839,4096,4096,0,1088528,4096,4096,0,1462495,4096,4096,0,1204649,4096,4096,0,1343330,4096,4096,0,1555603,4096,4096,0,1315112,4096,4096,0,1486839,4096,4096,0,1133925,4096,4096,0,1285809,4096,4096,0,1027697,4096,4096,0,1075842,4096,4096,0,1319145,4096,4096,0,1231380,4096,4096,0,1161654,4096,4096,0,1105658,4096,4096,0,1555341,4096,4096,64,0x7fc4fdbbcec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65551.0,0.0,0.0,0.0,200787787628212,200787787648052 +1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f8cb5680ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,19790,0,2696,38352,0,69472.0,131072.0,0.0,45644.0,64,0x7f4dc6f04ec0,4096,0,206,0,4096,0,777,0,4096,0,102,0,4100,0,562,0,4096,0,464,0,4096,0,2656,0,4096,0,491,0,4096,0,631,0,4096,0,322,0,4097,0,44,0,4096,0,282,0,4096,0,264,0,4096,0,525,0,4096,0,503,0,4096,0,536,0,4097,0,414,0,4097,0,227,0,4096,0,1186,0,4100,0,885,0,4096,0,720,0,4096,0,0,0,4096,0,12,0,4096,0,1515,0,4096,0,324,0,4096,0,268,0,4096,0,428,0,4096,0,0,0,4096,0,1081,0,4096,0,0,0,4097,0,16,0,4096,0,1100,0,4096,0,629,0,64,0x7f12d755cec0,32768,32768,0,64,0x7fc427340ec0,0,194575,0,0,65536,63800,56,1680,64,0x7f0ede0a8ec0,19029679,18003150,682465,344064,2744016,0,0,163840,832.0,515140.0,0.0,524288.0,633468.0,32768.0,892489,0,0,13912,91218.0,91218.0,0.0,91218.0,64,0x7fd053b44ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2058821.0,64,0x7ff1c88bcec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,125741030.0,60350525.0,0.0,64,0x7f27f1d84ec0,114688,0,32768,32768,16384,16384,65536,49152,58716240.0,197706597.0,48130227.0,131072.0,0.0,479796.0,0,0,23433,4016.0,131073.0,0.0,0.0,64,0x7f02bc090ec0,0,0,0,56,0,65536,65536,0,64,0x7f71fb6c4ec0,0,0,0,1384594,69,0,0,2255638,83,0,0,1702593,0,0,0,2066209,0,0,0,1653195,0,0,0,2054875,279,0,0,1781753,0,0,0,1804358,0,0,0,1454844,0,0,0,1687793,0,0,0,1875678,0,0,0,1555374,0,0,0,1574007,0,0,0,1709013,396,0,0,1978961,12,0,0,1939986,0,0,0,1505907,90,0,0,1885483,0,0,0,1666838,0,0,0,1925293,0,0,0,1920417,1335,0,0,2479208,0,0,0,1395676,0,0,0,1834744,0,0,0,1650194,0,0,0,1775081,0,0,0,1501214,27,0,0,1727673,230,0,0,2102609,0,0,0,1705891,0,0,0,1899545,0,0,0,1854229,64,0x7f5c86b64ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131072.0,93345.0,45562.0,0.0,64,0x7fe59bab8ec0,6254,0,4096,6261,0,4096,6268,0,4096,6290,0,4096,6258,0,4096,6321,0,4096,6261,0,4096,6277,0,4096,6276,0,4096,6258,0,4096,6266,0,4096,6270,0,4096,6290,0,4096,6263,0,4096,6323,0,4096,6266,0,4096,6254,0,4096,6263,0,4096,6283,0,4096,6276,0,4096,6270,0,4096,6307,0,4096,6266,0,4096,6299,0,4096,6298,0,4096,6255,0,4096,6264,0,4096,6288,0,4096,6281,0,4096,6271,0,4096,6310,0,4096,6265,0,4096,64,0x7f00e0898ec0,2155,4096,2155,6251,2146,4096,2146,6242,2177,4096,2177,6273,2172,4097,2173,6269,2181,4096,2181,6277,2174,4096,2174,6270,2180,4096,2180,6276,2178,4097,2179,6275,2178,4096,2178,6274,2155,4096,2155,6251,2146,4096,2146,6242,2182,4096,2182,6278,2175,4096,2175,6271,2184,4096,2184,6280,2174,4096,2174,6270,2183,4096,2183,6279,2206,4096,2206,6302,2197,4096,2197,6293,2176,4097,2177,6273,2160,4099,2163,6259,2180,4096,2180,6276,2196,4096,2196,6292,2157,4096,2157,6253,2127,4096,2127,6223,2130,4096,2130,6226,2258,4097,2259,6355,2198,4096,2198,6294,2178,4096,2178,6274,2161,4097,2162,6258,2180,4098,2182,6278,2199,4096,2199,6295,2157,4096,2157,6253,64,0x7f34907d8ec0,332152,222737,16384,0,16384,16384,32768,49152,41518,41518,3172936.0,2484232.0,5314.0,338169.0,1704683.0,0.0,2471654.0,2163784.0,332144,232463,41518,0,41518,0,1328576.0,771607.0,0.0,0.0,64,0x7f9df37d0ec0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,64,0x7fb93c8acec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,30907,27235,9652,2476,0,39335,201008.0,0.0,69925.0,131083.0,64,0x7f6090dc4ec0,0,393216,163840,0,0,0,0,0,30057,0.0,0.0,0.0,32768.0,0.0,0.0,209.0,32768.0,4096,16384,302,41040,1954,0,56.0,12.0,0.0,200750.0,64,0x7f0809060ec0,0,3159295,2840,2840,0,4074954,2860,2860,0,3442000,2860,2860,0,4663990,2858,2858,0,3821061,2900,2900,0,4015918,2852,2852,0,2863952,2884,2884,0,3690902,2816,2816,0,3351559,2816,2816,0,3271066,2840,2840,0,3218057,2864,2864,0,3910547,2860,2860,0,3194412,2846,2846,0,3424184,2900,2900,0,4028667,2848,2848,0,4020056,2884,2884,0,3931060,2812,2812,0,3076775,2852,2852,0,3577935,2852,2852,0,3691164,2832,2832,0,4011722,2844,2844,0,3902622,2892,2892,0,4221938,2840,2840,0,4603345,2832,2832,0,4021856,2832,2832,0,3345800,2806,2806,0,4412748,2854,2854,0,3985792,2852,2852,0,3464193,2832,2832,0,3753271,2844,2844,0,3840056,2888,2888,0,3976717,2840,2840,64,0x7fc4fdbbcec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65550.0,0.0,0.0,0.0,200787787740532,200787787757172 +2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f8cb5680ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,20724,0,2747,38187,0,69831.0,131072.0,0.0,45541.0,64,0x7f4dc6f04ec0,4096,0,311,0,4096,0,615,0,4096,0,1391,0,4100,0,43,0,4096,0,275,0,4096,0,2396,0,4096,0,16,0,4096,0,410,0,4096,0,1204,0,4097,0,230,0,4096,0,597,0,4096,0,934,0,4096,0,100,0,4096,0,357,0,4096,0,0,0,4097,0,809,0,4097,0,31,0,4096,0,449,0,4100,0,6,0,4096,0,774,0,4096,0,875,0,4096,0,255,0,4096,0,899,0,4096,0,1262,0,4096,0,323,0,4096,0,112,0,4096,0,1126,0,4096,0,26,0,4096,0,304,0,4097,0,1390,0,4096,0,232,0,4096,0,801,0,64,0x7f12d755cec0,32768,32768,0,64,0x7fc427340ec0,0,189365,0,0,65536,63800,56,1680,64,0x7f0ede0a8ec0,18947510,17743741,859705,344064,2733105,0,0,163840,832.0,515146.0,0.0,524288.0,763947.0,32768.0,915724,0,0,13414,91226.0,91226.0,0.0,91226.0,64,0x7fd053b44ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2059084.0,64,0x7ff1c88bcec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,121626219.0,58024359.0,0.0,64,0x7f27f1d84ec0,114688,0,32768,32768,16384,16384,65536,49152,58310809.0,202035406.0,51471400.0,131072.0,0.0,463313.0,0,0,24953,7663.0,131082.0,0.0,18.0,64,0x7f02bc090ec0,0,0,0,56,0,65536,65536,0,64,0x7f71fb6c4ec0,580,0,0,2384547,573,0,0,2076195,0,0,0,1707563,257,0,0,2027051,0,0,0,1778158,175,0,0,2022828,129,0,0,1861580,0,0,0,1651189,76,0,0,1688029,0,0,0,1818496,766,0,0,2405585,227,0,0,1964580,125,0,0,1555538,0,0,0,1940908,194,0,0,1980412,0,0,0,1704595,0,0,0,1626585,0,0,0,1753379,583,0,0,2180781,123,0,0,1770314,0,0,0,1794918,191,0,0,2197482,0,0,0,1513569,0,0,0,1936410,0,0,0,1748736,277,0,0,1856561,0,0,0,1361974,568,0,0,2334526,1027,0,0,2735105,0,0,0,1756245,0,0,0,1697920,0,0,0,2054955,64,0x7f5c86b64ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131081.0,89139.0,45580.0,0.0,64,0x7fe59bab8ec0,6285,0,4096,6280,0,4096,6270,0,4096,6284,0,4096,6260,0,4096,6268,0,4096,6292,0,4096,6318,0,4096,6326,0,4096,6288,0,4096,6285,0,4096,6275,0,4096,6291,0,4096,6268,0,4096,6271,0,4096,6290,0,4096,6293,0,4096,6329,0,4096,6279,0,4096,6305,0,4096,6270,0,4096,6301,0,4096,6313,0,4096,6258,0,4096,6263,0,4096,6297,0,4096,6334,0,4096,6284,0,4096,6306,0,4096,6271,0,4096,6305,0,4096,6313,0,4096,64,0x7f00e0898ec0,2158,4096,2158,6254,2170,4096,2170,6266,2158,4096,2158,6254,2157,4097,2158,6254,2176,4096,2176,6272,2182,4096,2182,6278,2170,4096,2170,6266,2152,4097,2153,6249,2154,4096,2154,6250,2157,4096,2157,6253,2173,4096,2173,6269,2158,4096,2158,6254,2162,4096,2162,6258,2185,4096,2185,6281,2180,4096,2180,6276,2163,4096,2163,6259,2150,4096,2150,6246,2174,4096,2174,6270,2158,4097,2159,6255,2154,4100,2158,6254,2168,4096,2168,6264,2173,4096,2173,6269,2174,4096,2174,6270,2157,4096,2157,6253,2165,4096,2165,6261,2206,4097,2207,6303,2177,4096,2177,6273,2158,4096,2158,6254,2158,4097,2159,6255,2167,4098,2169,6265,2172,4096,2172,6268,2181,4096,2181,6277,64,0x7f34907d8ec0,333192,218989,16384,0,16384,16384,32768,49152,41648,41648,3124107.0,2462013.0,4550.0,384500.0,1781440.0,0.0,2450479.0,2141151.0,333184,228267,41648,0,41648,0,1332736.0,776559.0,0.0,0.0,64,0x7f9df37d0ec0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,64,0x7fb93c8acec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,30738,27293,9514,2578,0,39521,200737.0,0.0,69654.0,131083.0,64,0x7f6090dc4ec0,0,393216,163840,0,0,0,0,0,30390,0.0,0.0,0.0,32768.0,0.0,0.0,242.0,32768.0,4096,16384,302,41321,1977,0,56.0,11.0,0.0,200900.0,64,0x7f0809060ec0,0,3296459,2832,2832,0,3372524,2860,2860,0,4222254,2848,2848,0,3878328,2856,2856,0,3774522,2880,2880,0,3831094,2844,2844,0,3260405,2876,2876,0,4057262,2830,2830,0,4273330,2836,2836,0,2725887,2832,2832,0,3234063,2860,2860,0,3333475,2852,2852,0,3604070,2852,2852,0,3326805,2876,2876,0,3142407,2840,2840,0,3714948,2876,2876,0,2930790,2804,2804,0,3635042,2868,2868,0,3668097,2840,2840,0,5045459,2848,2848,0,4655237,2812,2812,0,3073880,2868,2868,0,2615458,2808,2808,0,4182335,2816,2816,0,3381199,2816,2816,0,3942930,2810,2810,0,4447030,2868,2868,0,4492459,2842,2842,0,3600791,2852,2852,0,3522880,2808,2808,0,3130714,2868,2868,0,4177317,2808,2808,64,0x7fc4fdbbcec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65552.0,0.0,0.0,0.0,200787787778292,200787787794132 diff --git a/tests/workloads/kernel_summaries/MI200/roofline.csv b/tests/workloads/kernel_summaries/MI200/roofline.csv new file mode 100644 index 0000000000..e69de29bb2 diff --git a/tests/workloads/kernel_summaries/MI200/sysinfo.csv b/tests/workloads/kernel_summaries/MI200/sysinfo.csv new file mode 100644 index 0000000000..6b1421bb87 --- /dev/null +++ b/tests/workloads/kernel_summaries/MI200/sysinfo.csv @@ -0,0 +1,2 @@ +workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd +kernel_summaries,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 02:57:22 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/kernel_summaries/MI200/timestamps.csv b/tests/workloads/kernel_summaries/MI200/timestamps.csv new file mode 100644 index 0000000000..543a02dd02 --- /dev/null +++ b/tests/workloads/kernel_summaries/MI200/timestamps.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,392801,392801,1048576,256,0,0,8,0,16,64,0x0,0x7ffa15fd4ec0,200787787600454,200787787628212,200787787648052,200787787659796 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,392801,392801,1048576,256,0,0,8,0,16,64,0x0,0x7ffa15fd4ec0,200787787659115,200787787740532,200787787757172,200787787758633 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,392801,392801,1048576,256,0,0,8,0,16,64,0x0,0x7ffa15fd4ec0,200787787768803,200787787778292,200787787794132,200787787795423 diff --git a/tests/workloads/kernel_verbose_0/MI100/SQ_IFETCH_LEVEL.csv b/tests/workloads/kernel_verbose_0/MI100/SQ_IFETCH_LEVEL.csv index e9a06973a6..48b3eb80b7 100644 --- a/tests/workloads/kernel_verbose_0/MI100/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/kernel_verbose_0/MI100/SQ_IFETCH_LEVEL.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,2891585,2891585,1048576,256,0,0,8,8,16,64,0x0,0x7f982f76ee80,49266,49266,16384,65536,13079,1685220,2187934163624397,2187927658864610,2187927658888930,2187934171251575 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,2891585,2891585,1048576,256,0,0,8,8,16,64,0x0,0x7f982f76ee80,42823,42823,16384,65536,8191,1048580,2187934171275750,2187927658989730,2187927659008610,2187934171569632 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,2891585,2891585,1048576,256,0,0,8,8,16,64,0x0,0x7f982f76ee80,42655,42655,16384,65536,8461,1048588,2187934171602303,2187927659032130,2187927659051170,2187934171777572 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,193490,193490,1048576,256,0,0,8,8,16,64,0x0,0x7fb2f1f4ae80,48621,48621,16384,65536,14647,1866684,194341379773374,194353571654480,194353571678800,194341387566400 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,193490,193490,1048576,256,0,0,8,8,16,64,0x0,0x7fb2f1f4ae80,43436,43436,16384,65536,8195,1048580,194341387591237,194353571699280,194353571718320,194341387859034 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,193490,193490,1048576,256,0,0,8,8,16,64,0x0,0x7fb2f1f4ae80,42100,42100,16384,65536,8187,1048596,194341387891245,194353571787600,194353571806320,194341388042942 diff --git a/tests/workloads/kernel_verbose_0/MI100/SQ_INST_LEVEL_LDS.csv b/tests/workloads/kernel_verbose_0/MI100/SQ_INST_LEVEL_LDS.csv index 2c4d549e75..8f20936a8a 100644 --- a/tests/workloads/kernel_verbose_0/MI100/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/kernel_verbose_0/MI100/SQ_INST_LEVEL_LDS.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,2889217,2889217,1048576,256,0,0,8,8,16,64,0x0,0x7f57d2b76e80,0,0,0,2187927214763094,2187927658864610,2187927658888930,2187927222469460 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,2889217,2889217,1048576,256,0,0,8,8,16,64,0x0,0x7f57d2b76e80,0,0,0,2187927222488817,2187927658989730,2187927659008610,2187927222797446 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,2889217,2889217,1048576,256,0,0,8,8,16,64,0x0,0x7f57d2b76e80,0,0,0,2187927222826230,2187927659032130,2187927659051170,2187927222987122 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,193674,193674,1048576,256,0,0,8,8,16,64,0x0,0x7fae69f00e80,0,0,0,194341874444885,194353571654480,194353571678800,194341883176307 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,193674,193674,1048576,256,0,0,8,8,16,64,0x0,0x7fae69f00e80,0,0,0,194341883193961,194353571699280,194353571718320,194341883612814 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,193674,193674,1048576,256,0,0,8,8,16,64,0x0,0x7fae69f00e80,0,0,0,194341883642380,194353571787600,194353571806320,194341883808895 diff --git a/tests/workloads/kernel_verbose_0/MI100/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/kernel_verbose_0/MI100/SQ_INST_LEVEL_SMEM.csv index 5beef97f0b..828e62e38c 100644 --- a/tests/workloads/kernel_verbose_0/MI100/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/kernel_verbose_0/MI100/SQ_INST_LEVEL_SMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,2888487,2888487,1048576,256,0,0,8,8,16,64,0x0,0x7fc752772e80,65536,202590,25941856,2187925177912649,2187927658864610,2187927658888930,2187925185483391 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,2888487,2888487,1048576,256,0,0,8,8,16,64,0x0,0x7fc752772e80,65536,171480,22033168,2187925185502126,2187927658989730,2187927659008610,2187925185810034 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,2888487,2888487,1048576,256,0,0,8,8,16,64,0x0,0x7fc752772e80,65536,173670,22217344,2187925185838858,2187927659032130,2187927659051170,2187925186027983 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,193861,193861,1048576,256,0,0,8,8,16,64,0x0,0x7ff8500b4e80,65536,225500,28899672,194342366867588,194353571654480,194353571678800,194342374487095 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,193861,193861,1048576,256,0,0,8,8,16,64,0x0,0x7ff8500b4e80,65536,194502,24913400,194342374506732,194353571699280,194353571718320,194342374802732 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,193861,193861,1048576,256,0,0,8,8,16,64,0x0,0x7ff8500b4e80,65536,192152,24574592,194342374831306,194353571787600,194353571806320,194342375002130 diff --git a/tests/workloads/kernel_verbose_0/MI100/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/kernel_verbose_0/MI100/SQ_INST_LEVEL_VMEM.csv index 46f5ee28b6..4cd2c1dd12 100644 --- a/tests/workloads/kernel_verbose_0/MI100/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/kernel_verbose_0/MI100/SQ_INST_LEVEL_VMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,2888669,2888669,1048576,256,0,0,8,8,16,64,0x0,0x7f8a1b484e80,32768,648790,83056120,2187925630169613,2187927658864610,2187927658888930,2187925637730477 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,2888669,2888669,1048576,256,0,0,8,8,16,64,0x0,0x7f8a1b484e80,32768,659029,84365020,2187925637751526,2187927658989730,2187927659008610,2187925638062540 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,2888669,2888669,1048576,256,0,0,8,8,16,64,0x0,0x7f8a1b484e80,32768,637026,81537752,2187925638091024,2187927659032130,2187927659051170,2187925638271262 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,194046,194046,1048576,256,0,0,8,8,16,64,0x0,0x7f79e60bce80,32768,651688,83428332,194342851989768,194353571654480,194353571678800,194342859796379 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,194046,194046,1048576,256,0,0,8,8,16,64,0x0,0x7f79e60bce80,32768,670969,85898616,194342859817529,194353571699280,194353571718320,194342860100144 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,194046,194046,1048576,256,0,0,8,8,16,64,0x0,0x7f79e60bce80,32768,680763,87111400,194342860128348,194353571787600,194353571806320,194342860305774 diff --git a/tests/workloads/kernel_verbose_0/MI100/SQ_LEVEL_WAVES.csv b/tests/workloads/kernel_verbose_0/MI100/SQ_LEVEL_WAVES.csv index afefd73272..732ae2294b 100644 --- a/tests/workloads/kernel_verbose_0/MI100/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/kernel_verbose_0/MI100/SQ_LEVEL_WAVES.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,2891949,2891949,1048576,256,0,0,8,8,16,64,0x0,0x7f349755ee80,49232,49232,16506,393864,16384,25316432,244401,0,101760184,2187935060473477,2187927658864610,2187927658888930,2187935068065429 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,2891949,2891949,1048576,256,0,0,8,8,16,64,0x0,0x7f349755ee80,43207,43207,12981,345664,16384,25308938,240759,0,101716688,2187935068093752,2187927658989730,2187927659008610,2187935068423561 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,2891949,2891949,1048576,256,0,0,8,8,16,64,0x0,0x7f349755ee80,42095,42095,11882,336768,16384,25104755,235146,0,100910296,2187935068462674,2187927659032130,2187927659051170,2187935068645748 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,194231,194231,1048576,256,0,0,8,8,16,64,0x0,0x7fef30a7ce80,48338,48338,16316,386712,16384,26132632,237677,0,105025452,194343342503857,194353571654480,194353571678800,194343350941192 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,194231,194231,1048576,256,0,0,8,8,16,64,0x0,0x7fef30a7ce80,42449,42449,13321,339600,16384,24522860,230609,0,98588116,194343350972872,194353571699280,194353571718320,194343351286887 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,194231,194231,1048576,256,0,0,8,8,16,64,0x0,0x7fef30a7ce80,42737,42737,13550,341904,16384,25012620,230778,0,100534524,194343351324829,194353571787600,194353571806320,194343351496614 diff --git a/tests/workloads/kernel_verbose_0/MI100/pmc_dispatch_info.csv b/tests/workloads/kernel_verbose_0/MI100/pmc_dispatch_info.csv new file mode 100644 index 0000000000..2166cd6fad --- /dev/null +++ b/tests/workloads/kernel_verbose_0/MI100/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/kernel_verbose_0/MI100/pmc_perf.csv b/tests/workloads/kernel_verbose_0/MI100/pmc_perf.csv index eaeaeddc1e..7f60854eda 100644 --- a/tests/workloads/kernel_verbose_0/MI100/pmc_perf.csv +++ b/tests/workloads/kernel_verbose_0/MI100/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_1,obj_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_2,obj_2,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_3,obj_3,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_4,obj_4,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_5,obj_5,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_6,obj_6,TCC_EA_ATOMIC_LEVEL_sum,wave_size_7,obj_7,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_8,obj_8,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_9,obj_9,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_10,obj_10,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_11,obj_11,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_12,obj_12,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_13,obj_13,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_14,obj_14,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_15,obj_15,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_16,obj_16,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f12bd3f8e80,0,48475,0,0,0,48475,0,0,0,48475,0,0,0,48475,0,0,0,48475,0,0,0,48475,0,0,0,48475,0,0,0,48475,0,0,0,48475,0,0,0,48475,0,0,0,48475,0,0,0,48475,0,0,0,48475,0,0,0,48475,0,0,0,48475,0,0,0,48475,0,0,0,48475,0,0,0,48475,0,0,0,48475,0,0,0,48475,0,0,0,48475,0,0,0,48475,0,0,0,48475,0,0,0,48475,0,0,0,48475,0,0,0,48475,0,0,0,48475,0,0,0,48475,0,0,0,48475,0,0,0,48475,0,0,0,48475,0,0,0,48475,0,0,64,0x7f2ee4d8ae80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,46676,0,131457.0,131072.0,0.0,131104.0,64,0x7f723da44e80,32768,0,0,0,16384,16384,393216,23245492,960.0,513958.0,0.0,524288.0,864612.0,32768.0,0,0,0,16688,131072.0,131072.0,0.0,131072.0,64,0x7f765377ce80,3803,0,0,2050751,2948,0,0,1907601,4438,0,0,2009672,2506,0,0,1846516,3553,0,0,2063265,3122,0,0,2001634,6281,0,0,2188123,4631,0,0,1971154,4775,0,0,2093927,3614,0,0,2007124,4597,0,0,2016215,2488,0,0,1868344,7225,0,0,2333755,5246,0,0,2154204,3683,0,0,1825353,3452,0,0,1954749,2750,0,0,1912391,2426,0,0,1905874,5256,0,0,2058377,3648,0,0,1922036,1547,0,0,1801613,4405,0,0,2005810,4918,0,0,2077046,4546,0,0,2032713,3648,0,0,1924672,3039,0,0,1873915,4101,0,0,1915983,3887,0,0,1981375,2121,0,0,1900717,3129,0,0,1907824,3754,0,0,1946808,4578,0,0,2009432,64,0x7f6deb08ae80,0,4045610,4096,4096,0,2754344,4096,4096,0,3323405,4096,4096,0,3527872,4096,4096,0,3406980,4096,4096,0,3174374,4096,4096,0,3334181,4096,4096,0,3509505,4096,4096,0,3404632,4096,4096,0,3215697,4096,4096,0,3347082,4096,4096,0,3380165,4096,4096,0,3376779,4096,4096,0,3101938,4096,4096,0,3610518,4096,4096,0,3756848,4096,4096,0,3674020,4096,4096,0,3557150,4096,4096,0,3976795,4096,4096,0,3370194,4096,4096,0,2932604,4096,4096,0,4858757,4096,4096,0,3944008,4096,4096,0,3434283,4096,4096,0,3246129,4096,4096,0,3538331,4096,4096,0,3852946,4096,4096,0,3229022,4096,4096,0,3290823,4096,4096,0,3388016,4096,4096,0,3514130,4096,4096,0,3292753,4096,4096,64,0x7fb825d5ee80,390992,235328,3440250,16384,25374933,144,48,0,48873,48873,3882836.0,2994659.0,6362.0,1019222.0,2059199.0,0.0,2985375.0,2674492.0,389279,245268,48873,0,48873,0,1563936.0,956160.0,0.0,0.0,64,0x7fe2687fce80,0.0,64,0x7f828a3bce80,131072.0,131072.0,0.0,2463975.0,0.0,0.0,103714313.0,62067519.0,64,0x7f07ae27ee80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,64,0x7f66a97eae80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86451.0,44621.0,131111.0,0.0,64,0x7f065ce4ce80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131350.0,0.0,548.0,131349.0,64,0x7f4dc183ae80,1333803,360448,163840,0,0,180224,114688,0,72411040.0,189696272.0,76711798.0,131072.0,0.0,555164.0,0,0,25978,106998.0,0.0,0.0,106998.0,64,0x7f945a6c2e80,0,0,192,0,65536,64488,48,1338,31834,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,539,48479,1751,0,48.0,264.0,0.0,262288.0,64,0x7f13640cae80,4096,0,753,0,4096,0,1566,0,4096,0,1776,0,4099,0,74,0,4096,0,222,0,4096,0,400,0,4096,0,893,0,4096,0,2135,0,4096,0,357,0,4096,0,1004,0,4096,0,1223,0,4096,0,1793,0,4096,0,1361,0,4096,0,74,0,4096,0,843,0,4367,0,4956,0,4096,0,2375,0,4096,0,1645,0,4144,0,1991,0,4096,0,2263,0,4096,0,1389,0,4096,0,450,0,4096,0,714,0,4096,0,21,0,4096,0,2600,0,4096,0,1004,0,4096,0,427,0,4144,0,441,0,4096,0,3006,0,4096,0,554,0,4096,0,850,0,4217,0,763,0,64,0x7fa388310e80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,141,8195,4240,8336,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8431,4335,8431,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,64,0x7f052e260e80,189671,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13199,29583,10023,550,0,46827,262552.0,0.0,188.0,262364.0,64,0x7fabca440e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,25189.0,98683.0,2187927658864610,2187927658888930 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f12bd3f8e80,0,43227,0,0,0,43227,0,0,0,43227,0,0,0,43227,0,0,0,43227,0,0,0,43227,0,0,0,43227,0,0,0,43227,0,0,0,43227,0,0,0,43227,0,0,0,43227,0,0,0,43227,0,0,0,43227,0,0,0,43227,0,0,0,43227,0,0,0,43227,0,0,0,43227,0,0,0,43227,0,0,0,43227,0,0,0,43227,0,0,0,43227,0,0,0,43227,0,0,0,43227,0,0,0,43227,0,0,0,43227,0,0,0,43227,0,0,0,43227,0,0,0,43227,0,0,0,43227,0,0,0,43227,0,0,0,43227,0,0,0,43227,0,0,64,0x7f2ee4d8ae80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,240.0,524288.0,0.0,0.0,0,0,7127,45750,1071,131850.0,131072.0,0.0,116749.0,64,0x7f723da44e80,32768,0,0,0,16384,16384,393216,22801818,960.0,514040.0,0.0,524288.0,884750.0,32768.0,0,0,0,13892,86738.0,86738.0,0.0,86738.0,64,0x7f765377ce80,4435,0,0,1660266,4059,0,0,1603955,3778,0,0,1673562,3475,0,0,1529857,1747,0,0,1406300,3331,0,0,1566248,3043,0,0,1533691,3761,0,0,1738262,4105,0,0,1631101,3849,0,0,1628099,2862,0,0,1531975,2602,0,0,1466753,4795,0,0,1660650,5820,0,0,1792830,1765,0,0,1365104,2671,0,0,1503614,4432,0,0,1701802,2982,0,0,1491383,5058,0,0,1769697,4246,0,0,1699349,4080,0,0,1606513,3500,0,0,1591112,4331,0,0,1625843,4137,0,0,1624402,3371,0,0,1460907,3916,0,0,1553880,3278,0,0,1514425,4048,0,0,1612443,2810,0,0,1534713,5500,0,0,1720567,4236,0,0,1676296,3276,0,0,1548912,64,0x7f6deb08ae80,0,4036927,2710,2710,0,3683883,2700,2700,0,3183247,2656,2656,0,3070843,2738,2738,0,3626307,2684,2684,0,3430827,2724,2724,0,3525718,2681,2681,0,3734955,2730,2730,0,3318904,2720,2720,0,3553739,2721,2721,0,3181715,2704,2704,0,3657438,2742,2742,0,3860523,2728,2728,0,3850930,2698,2698,0,3500847,2682,2682,0,3602211,2744,2744,0,3885341,2688,2688,0,3820603,2752,2752,0,3491388,2691,2691,0,3800725,2748,2748,0,3572555,2704,2704,0,4944388,2776,2776,0,3322215,2652,2652,0,3258427,2700,2700,0,3445778,2676,2676,0,3488305,2727,2727,0,3359497,2672,2672,0,2988778,2726,2726,0,3187009,2708,2708,0,3456296,2700,2700,0,3435387,2701,2701,0,3798215,2714,2714,64,0x7fb825d5ee80,355176,236794,3460725,16384,25071742,0,48,0,44396,44396,3841500.0,3083567.0,7562.0,1177895.0,2062339.0,0.0,3074189.0,2763113.0,355168,246131,44396,0,44396,0,1420672.0,826304.0,0.0,0.0,64,0x7fe2687fce80,0.0,64,0x7f828a3bce80,131072.0,131072.0,0.0,2533366.0,0.0,0.0,100543267.0,48215300.0,64,0x7f07ae27ee80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f66a97eae80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,70450.0,16338.0,82263.0,0.0,64,0x7f065ce4ce80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131273.0,0.0,400.0,131272.0,64,0x7f4dc183ae80,241651,360448,163840,0,0,180224,114688,0,74133268.0,204464778.0,78437280.0,131072.0,0.0,636199.0,0,0,23740,50376.0,0.0,0.0,50376.0,64,0x7f945a6c2e80,0,0,48,0,65536,65536,0,0,30908,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,457,42350,1684,0,48.0,270.0,0.0,262144.0,64,0x7f13640cae80,4096,0,538,0,4096,0,180,0,4096,0,3991,0,4096,0,210,0,4096,0,1849,0,4096,0,0,0,4096,0,1310,0,4096,0,0,0,4098,0,1131,0,4096,0,1347,0,4097,0,2559,0,4096,0,2430,0,4096,0,143,0,4096,0,278,0,4096,0,3293,0,4315,0,4328,0,4096,0,1154,0,4096,0,402,0,4144,0,2784,0,4096,0,3052,0,4096,0,467,0,4096,0,101,0,4096,0,2197,0,4096,0,233,0,4096,0,153,0,4096,0,125,0,4096,0,1703,0,4144,0,317,0,4096,0,881,0,4096,0,245,0,4099,0,397,0,4217,0,0,0,64,0x7fa388310e80,0,8193,4097,8193,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8403,4307,8403,0,8193,4097,8193,0,8192,4096,8192,0,8193,4097,8193,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,64,0x7f052e260e80,188744,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13436,29820,8486,2567,0,40349,262412.0,0.0,47.0,262365.0,64,0x7fabca440e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,71629.0,150071.0,2187927658989730,2187927659008610 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f12bd3f8e80,0,42896,0,0,0,42896,0,0,0,42896,0,0,0,42896,0,0,0,42896,0,0,0,42896,0,0,0,42896,0,0,0,42896,0,0,0,42896,0,0,0,42896,0,0,0,42896,0,0,0,42896,0,0,0,42896,0,0,0,42896,0,0,0,42896,0,0,0,42896,0,0,0,42896,0,0,0,42896,0,0,0,42896,0,0,0,42896,0,0,0,42896,0,0,0,42896,0,0,0,42896,0,0,0,42896,0,0,0,42896,0,0,0,42896,0,0,0,42896,0,0,0,42896,0,0,0,42896,0,0,0,42896,0,0,0,42896,0,0,0,42896,0,0,64,0x7f2ee4d8ae80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,4098,38321,0,131315.0,131072.0,0.0,86584.0,64,0x7f723da44e80,32768,0,0,0,16384,16384,393216,22387728,960.0,513941.0,0.0,524288.0,888268.0,32768.0,0,0,0,14588,86632.0,86632.0,0.0,86632.0,64,0x7f765377ce80,3527,0,0,1522569,2677,0,0,1424653,3316,0,0,1437550,4607,0,0,1625227,2178,0,0,1438530,2519,0,0,1518288,3340,0,0,1611803,4969,0,0,1731968,3270,0,0,1552064,2818,0,0,1511385,3180,0,0,1417421,3638,0,0,1589113,2443,0,0,1452583,2254,0,0,1456660,3278,0,0,1453422,4205,0,0,1641308,3123,0,0,1531545,2385,0,0,1438183,4749,0,0,1677203,3548,0,0,1485085,3079,0,0,1452001,3904,0,0,1608432,3098,0,0,1564134,4573,0,0,1637351,3476,0,0,1469354,3591,0,0,1536708,3897,0,0,1555865,4468,0,0,1655286,1227,0,0,1355103,6129,0,0,1791661,4356,0,0,1630443,3432,0,0,1559875,64,0x7f6deb08ae80,0,4547015,2742,2742,0,3300216,2706,2706,0,4210457,2684,2684,0,3897271,2680,2680,0,3856939,2672,2672,0,3568738,2746,2746,0,3854516,2691,2691,0,3820386,2692,2692,0,4194161,2708,2708,0,3479657,2718,2718,0,3561451,2686,2686,0,4232110,2670,2670,0,3661315,2734,2734,0,3321032,2732,2732,0,3949113,2707,2707,0,3759284,2656,2656,0,3612117,2732,2732,0,3700399,2726,2726,0,3729587,2678,2678,0,3327015,2712,2712,0,3625581,2698,2698,0,4476780,2765,2765,0,4233949,2698,2698,0,3760499,2698,2698,0,3607673,2700,2700,0,3290136,2718,2718,0,3458330,2722,2722,0,3564144,2688,2688,0,4334022,2704,2704,0,3388638,2728,2728,0,3530672,2690,2690,0,3593272,2676,2676,64,0x7fb825d5ee80,343248,230566,3373952,16384,24814803,0,48,0,42905,42905,3748388.0,3007908.0,7725.0,1100199.0,2106009.0,0.0,2999174.0,2688771.0,343240,240043,42905,0,42905,0,1372960.0,808808.0,0.0,0.0,64,0x7fe2687fce80,0.0,64,0x7f828a3bce80,131072.0,131072.0,0.0,2339866.0,0.0,0.0,86391680.0,45120910.0,64,0x7f07ae27ee80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f66a97eae80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86550.0,0.0,131112.0,0.0,64,0x7f065ce4ce80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131260.0,0.0,374.0,131259.0,64,0x7f4dc183ae80,635880,360448,163840,0,0,180224,114688,0,72143762.0,187442625.0,74842958.0,131072.0,0.0,595381.0,0,0,24262,76911.0,0.0,0.0,76911.0,64,0x7f945a6c2e80,0,0,48,0,65536,65536,0,0,30399,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,457,41717,1760,0,48.0,270.0,0.0,262144.0,64,0x7f13640cae80,4096,0,2464,0,4096,0,3459,0,4096,0,351,0,4096,0,1214,0,4096,0,1875,0,4096,0,2434,0,4096,0,1577,0,4096,0,1596,0,4098,0,2592,0,4096,0,2353,0,4097,0,1267,0,4096,0,2149,0,4096,0,2439,0,4096,0,921,0,4096,0,1524,0,4330,0,2147,0,4096,0,1599,0,4096,0,2486,0,4144,0,1516,0,4096,0,1420,0,4096,0,1726,0,4096,0,1726,0,4096,0,837,0,4096,0,914,0,4096,0,1192,0,4096,0,2227,0,4096,0,836,0,4144,0,1524,0,4096,0,1617,0,4096,0,1823,0,4099,0,512,0,4217,0,2180,0,64,0x7fa388310e80,0,8193,4097,8193,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8433,4337,8433,0,8193,4097,8193,0,8192,4096,8192,0,8193,4097,8193,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,64,0x7f052e260e80,187070,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,12966,29350,8623,2692,0,40901,262412.0,0.0,47.0,262365.0,64,0x7fabca440e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,48058.0,116690.0,2187927659032130,2187927659051170 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_1,obj_1,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_2,obj_2,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_3,obj_3,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_4,obj_4,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_5,obj_5,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_6,obj_6,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_7,obj_7,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_8,obj_8,TCC_EA_ATOMIC_LEVEL_sum,wave_size_9,obj_9,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_10,obj_10,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_11,obj_11,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_12,obj_12,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_13,obj_13,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_14,obj_14,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_15,obj_15,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_16,obj_16,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7fd385a04e80,2006833,360448,163840,0,0,180224,114688,0,68715404.0,172990277.0,68125891.0,131072.0,0.0,625896.0,0,0,26767,113863.0,0.0,0.0,113863.0,64,0x7f9e98b4ae80,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fb7a9a86e80,194132,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13587,29971,9968,550,0,46178,262586.0,0.0,188.0,262398.0,64,0x7f6a2f3ece80,0,8192,4096,8192,0,8192,4096,8192,141,8195,4240,8336,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8313,4264,8360,0,8192,4096,8192,0,8192,4096,8192,64,0x7f3713cfce80,32768,0,0,0,16384,16384,393216,23243666,960.0,513920.0,0.0,524288.0,905506.0,32768.0,0,0,0,16088,131072.0,131072.0,0.0,131072.0,64,0x7f0c1e818e80,0,0,192,0,65536,64467,48,1381,31324,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,539,47160,1670,0,48.0,263.0,0.0,262288.0,64,0x7f3250ba2e80,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,64,0x7fed10890e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,47696,0,131584.0,131072.0,0.0,131104.0,64,0x7f5553c0ce80,0.0,64,0x7f16ce836e80,387368,239224,3490962,16384,25872794,144,48,0,48420,48420,3941246.0,3118196.0,5739.0,953182.0,2123489.0,0.0,3109146.0,2800453.0,385655,249166,48420,0,48420,0,1549440.0,993517.0,0.0,0.0,64,0x7fb3e5fa0e80,4096,0,4462,0,4096,0,409,0,4099,0,4376,0,4096,0,226,0,4096,0,3731,0,4096,0,1797,0,4096,0,2805,0,4096,0,1669,0,4096,0,1739,0,4096,0,4257,0,4096,0,3622,0,4310,0,3660,0,4096,0,109,0,4096,0,1494,0,4096,0,5047,0,4144,0,3070,0,4096,0,1670,0,4096,0,1445,0,4096,0,4884,0,4096,0,2740,0,4096,0,1035,0,4096,0,3302,0,4096,0,3960,0,4096,0,529,0,4096,0,3569,0,4096,0,1691,0,4096,0,3186,0,4096,0,1192,0,4096,0,119,0,4097,0,533,0,4096,0,1668,0,4096,0,3003,0,64,0x7f209d1cee80,683,0,0,1681084,5739,0,0,2192455,1326,0,0,1749948,4875,0,0,2106330,3977,0,0,1986884,2440,0,0,1876324,1614,0,0,1814035,824,0,0,1861178,2548,0,0,1798354,2070,0,0,1845346,2259,0,0,1856629,1037,0,0,1660772,3060,0,0,1931718,2301,0,0,1793728,2724,0,0,1943004,6640,0,0,2198193,3152,0,0,1888080,1849,0,0,1811706,2712,0,0,1981406,5295,0,0,2037812,2893,0,0,1929244,2281,0,0,1948298,3962,0,0,2025022,4303,0,0,2065531,4729,0,0,2047026,1984,0,0,1835190,551,0,0,1645298,6476,0,0,2171387,3957,0,0,2033716,2261,0,0,1891349,4993,0,0,2156620,4404,0,0,1972354,64,0x7fe28285ce80,0,3730368,4096,4096,0,3655095,4096,4096,0,3163009,4096,4096,0,3948395,4096,4096,0,3286143,4096,4096,0,5034301,4096,4096,0,3571898,4096,4096,0,4076582,4096,4096,0,4932830,4096,4096,0,3783152,4096,4096,0,4546871,4096,4096,0,3752739,4096,4096,0,3223245,4096,4096,0,4381348,4096,4096,0,3702046,4096,4096,0,4420403,4096,4096,0,3786309,4096,4096,0,4054829,4096,4096,0,3082527,4096,4096,0,3126263,4096,4096,0,4153912,4096,4096,0,3204802,4096,4096,0,4239022,4096,4096,0,2843960,4096,4096,0,3922575,4096,4096,0,3560485,4096,4096,0,3311424,4096,4096,0,3735645,4096,4096,0,3893362,4096,4096,0,4405362,4096,4096,0,3139392,4096,4096,0,4193590,4096,4096,64,0x7f5352440e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86386.0,44686.0,131111.0,0.0,64,0x7f8185804e80,131072.0,131072.0,0.0,2336661.0,0.0,0.0,137127129.0,60488149.0,64,0x7f750354ae80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,64647.0,130388.0,64,0x7fcd8cecee80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131376.0,0.0,600.0,131375.0,194353571654480,194353571678800 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7fd385a04e80,1346773,360448,163840,0,0,180224,114688,0,72054641.0,203418176.0,74077908.0,131072.0,0.0,657109.0,0,0,26308,64781.0,0.0,0.0,64781.0,64,0x7f9e98b4ae80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fb7a9a86e80,190604,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,14139,30523,8420,2397,0,40405,262426.0,0.0,47.0,262379.0,64,0x7f6a2f3ece80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8232,4136,8232,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8314,4265,8361,0,8192,4096,8192,0,8192,4096,8192,64,0x7f3713cfce80,32768,0,0,0,16384,16384,393216,23247664,960.0,513946.0,0.0,524288.0,1013134.0,32768.0,0,0,0,14099,86383.0,86383.0,0.0,86383.0,64,0x7f0c1e818e80,0,0,48,0,65536,65536,0,0,30401,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,458,42131,1751,0,48.0,245.0,0.0,262144.0,64,0x7f3250ba2e80,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,64,0x7fed10890e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,240.0,524288.0,0.0,0.0,0,0,5707,47024,1080,131866.0,131072.0,0.0,115949.0,64,0x7f5553c0ce80,0.0,64,0x7f16ce836e80,345248,229414,3369784,16384,24865119,0,48,0,43155,43155,3731153.0,3088880.0,5937.0,907196.0,2054685.0,0.0,3079687.0,2770511.0,345240,238889,43155,0,43155,0,1380960.0,821879.0,0.0,0.0,64,0x7fb3e5fa0e80,4096,0,906,0,4096,0,744,0,4096,0,2991,0,4096,0,2057,0,4096,0,1432,0,4096,0,6560,0,4096,0,1091,0,4096,0,4975,0,4096,0,34,0,4096,0,1294,0,4096,0,306,0,4270,0,3078,0,4096,0,764,0,4096,0,19,0,4096,0,361,0,4144,0,145,0,4096,0,1995,0,4096,0,2156,0,4096,0,1427,0,4096,0,1794,0,4097,0,0,0,4096,0,1099,0,4096,0,750,0,4096,0,28,0,4096,0,2330,0,4096,0,2719,0,4096,0,608,0,4097,0,719,0,4096,0,213,0,4100,0,7519,0,4096,0,2179,0,4096,0,2965,0,64,0x7f209d1cee80,2149,0,0,1529798,4769,0,0,1775466,809,0,0,1293469,3323,0,0,1581991,1355,0,0,1437536,2507,0,0,1525460,955,0,0,1290002,2763,0,0,1544569,1542,0,0,1383729,2377,0,0,1558005,3026,0,0,1626699,1429,0,0,1451597,2715,0,0,1567633,3543,0,0,1679118,1966,0,0,1480065,4848,0,0,1755619,1319,0,0,1440911,1117,0,0,1365875,1677,0,0,1476115,2531,0,0,1475491,3166,0,0,1515185,1306,0,0,1414787,2218,0,0,1556401,6554,0,0,1857795,1715,0,0,1476033,3349,0,0,1698064,1038,0,0,1358600,5224,0,0,1739257,1471,0,0,1421995,5136,0,0,1753385,1510,0,0,1449180,1596,0,0,1382884,64,0x7fe28285ce80,0,4425069,2700,2700,0,4036778,2708,2708,0,4504980,2680,2680,0,3666830,2712,2712,0,3306629,2684,2684,0,2736295,2678,2678,0,5116273,2704,2704,0,3165010,2706,2706,0,2787842,2711,2711,0,4286214,2685,2685,0,3722374,2714,2714,0,5103837,2741,2741,0,3026756,2708,2708,0,3022760,2680,2680,0,4737002,2692,2692,0,2928740,2704,2704,0,3401400,2686,2686,0,3970324,2688,2688,0,3395899,2704,2704,0,5058727,2714,2714,0,3203562,2703,2703,0,4337607,2749,2749,0,4320317,2680,2680,0,3082350,2692,2692,0,2932808,2676,2676,0,4111799,2706,2706,0,4412749,2730,2730,0,4819919,2718,2718,0,3413705,2706,2706,0,3689644,2691,2691,0,4642279,2704,2704,0,4839472,2710,2710,64,0x7f5352440e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86484.0,0.0,131112.0,0.0,64,0x7f8185804e80,131072.0,131072.0,0.0,2680005.0,0.0,0.0,105353275.0,37782076.0,64,0x7f750354ae80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,71485.0,140507.0,64,0x7fcd8cecee80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131451.0,0.0,756.0,131450.0,194353571699280,194353571718320 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7fd385a04e80,1436338,360448,163840,0,0,180224,114688,0,69699642.0,187307657.0,69545746.0,131072.0,0.0,665131.0,0,0,25460,50890.0,0.0,0.0,50890.0,64,0x7f9e98b4ae80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fb7a9a86e80,193254,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,11286,27670,8593,2405,0,41864,262459.0,0.0,47.0,262412.0,64,0x7f6a2f3ece80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8198,4102,8198,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8314,4265,8361,0,8192,4096,8192,0,8192,4096,8192,64,0x7f3713cfce80,32768,0,0,0,16384,16384,393216,22808406,960.0,513845.0,0.0,524288.0,1058785.0,32768.0,0,0,0,13916,86647.0,86647.0,0.0,86647.0,64,0x7f0c1e818e80,0,0,48,0,65536,65536,0,0,31544,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,458,42897,1726,0,48.0,276.0,0.0,262144.0,64,0x7f3250ba2e80,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,64,0x7fed10890e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,2896,40667,0,131461.0,131072.0,0.0,86668.0,64,0x7f5553c0ce80,0.0,64,0x7f16ce836e80,343696,227035,3332340,16384,24268612,0,48,0,42961,42961,3695291.0,3049265.0,5055.0,919004.0,2067958.0,0.0,3040489.0,2731456.0,343688,236801,42961,0,42961,0,1374752.0,809016.0,0.0,0.0,64,0x7fb3e5fa0e80,4096,0,2920,0,4096,0,153,0,4096,0,2717,0,4096,0,1261,0,4096,0,6504,0,4096,0,4404,0,4096,0,2970,0,4096,0,325,0,4096,0,3404,0,4096,0,1411,0,4096,0,4443,0,4323,0,2573,0,4096,0,572,0,4096,0,1241,0,4096,0,4975,0,4144,0,244,0,4096,0,3326,0,4096,0,2453,0,4096,0,4944,0,4096,0,2365,0,4097,0,637,0,4096,0,699,0,4096,0,1917,0,4096,0,3516,0,4096,0,308,0,4096,0,1241,0,4096,0,4157,0,4097,0,2653,0,4096,0,88,0,4100,0,272,0,4096,0,1774,0,4096,0,0,0,64,0x7f209d1cee80,1105,0,0,1389999,2196,0,0,1478769,1978,0,0,1420854,3005,0,0,1572715,1708,0,0,1429400,1416,0,0,1389753,1490,0,0,1395001,2225,0,0,1499468,1655,0,0,1445943,2945,0,0,1591288,3047,0,0,1561401,930,0,0,1394091,4036,0,0,1744397,5554,0,0,1702932,1961,0,0,1442125,3798,0,0,1623435,5558,0,0,1760973,1059,0,0,1432582,3124,0,0,1584883,1381,0,0,1379178,2362,0,0,1515193,1650,0,0,1507077,3266,0,0,1561604,2699,0,0,1523282,1951,0,0,1468214,2466,0,0,1507468,2150,0,0,1474605,3618,0,0,1624888,2796,0,0,1576234,3507,0,0,1590909,5663,0,0,1810246,1636,0,0,1461062,64,0x7fe28285ce80,0,3578293,2712,2712,0,4907688,2728,2728,0,3596146,2685,2685,0,4201515,2702,2702,0,3951803,2660,2660,0,4265151,2714,2714,0,4503718,2699,2699,0,5018693,2692,2692,0,3935995,2716,2716,0,4686136,2683,2683,0,4362814,2700,2700,0,4666937,2710,2710,0,5053364,2706,2706,0,3697139,2696,2696,0,3992805,2698,2698,0,4189689,2684,2684,0,3711908,2667,2667,0,5088538,2702,2702,0,4014027,2696,2696,0,4757445,2702,2702,0,3557373,2691,2691,0,3491927,2739,2739,0,3533736,2694,2694,0,3713251,2690,2690,0,3517338,2668,2668,0,3889139,2692,2692,0,4315516,2730,2730,0,3731959,2694,2694,0,3050714,2690,2690,0,3954401,2705,2705,0,3036695,2698,2698,0,4778210,2693,2693,64,0x7f5352440e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86496.0,0.0,131112.0,0.0,64,0x7f8185804e80,131072.0,131072.0,0.0,2408704.0,0.0,0.0,130898481.0,47722039.0,64,0x7f750354ae80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,75460.0,143313.0,64,0x7fcd8cecee80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131370.0,0.0,594.0,131369.0,194353571787600,194353571806320 diff --git a/tests/workloads/kernel_verbose_0/MI100/sysinfo.csv b/tests/workloads/kernel_verbose_0/MI100/sysinfo.csv index 28e4dc8fa5..4a04b073c6 100644 --- a/tests/workloads/kernel_verbose_0/MI100/sysinfo.csv +++ b/tests/workloads/kernel_verbose_0/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -kernel_verbose_0,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Fri Mar 1 16:47:15 2024 (CST),1,t006-003.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651240,,5.7.1-98,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +kernel_verbose_0,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 07 Mar 2024 01:10:06 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/kernel_verbose_0/MI100/timestamps.csv b/tests/workloads/kernel_verbose_0/MI100/timestamps.csv index 515b360712..9e0c9e65c0 100644 --- a/tests/workloads/kernel_verbose_0/MI100/timestamps.csv +++ b/tests/workloads/kernel_verbose_0/MI100/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,2889399,2889399,1048576,256,0,0,8,8,16,64,0x0,0x7fd921952e80,2187927658839892,2187927658864610,2187927658888930,2187927658899875 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,2889399,2889399,1048576,256,0,0,8,8,16,64,0x0,0x7fd921952e80,2187927658901378,2187927658989730,2187927659008610,2187927659009891 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,2889399,2889399,1048576,256,0,0,8,8,16,64,0x0,0x7fd921952e80,2187927659020982,2187927659032130,2187927659051170,2187927659052421 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,197559,197559,1048576,256,0,0,8,8,16,64,0x0,0x7fd5bf49ee80,194353571628315,194353571654480,194353571678800,194353571697315 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,197559,197559,1048576,256,0,0,8,8,16,64,0x0,0x7fd5bf49ee80,194353571691414,194353571699280,194353571718320,194353571785462 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,197559,197559,1048576,256,0,0,8,8,16,64,0x0,0x7fd5bf49ee80,194353571729666,194353571787600,194353571806320,194353571807423 diff --git a/tests/workloads/kernel_verbose_0/MI200/SQ_IFETCH_LEVEL.csv b/tests/workloads/kernel_verbose_0/MI200/SQ_IFETCH_LEVEL.csv new file mode 100644 index 0000000000..1305a9cec1 --- /dev/null +++ b/tests/workloads/kernel_verbose_0/MI200/SQ_IFETCH_LEVEL.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,358385,358385,1048576,256,0,0,8,0,16,64,0x0,0x7f4c05fb0ec0,27667,27667,16384,65536,13532,1531332,199948894773455,199961732754864,199961732775184,199948910717487 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,358385,358385,1048576,256,0,0,8,0,16,64,0x0,0x7f4c05fb0ec0,40465,40465,16384,65536,9379,1048736,199948910739288,199961732860464,199961732876784,199948911142290 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,358385,358385,1048576,256,0,0,8,0,16,64,0x0,0x7f4c05fb0ec0,41265,41265,16384,65536,8936,1048696,199948911163951,199961732897264,199961732913104,199948911336488 diff --git a/tests/workloads/kernel_verbose_0/MI200/SQ_INST_LEVEL_LDS.csv b/tests/workloads/kernel_verbose_0/MI200/SQ_INST_LEVEL_LDS.csv new file mode 100644 index 0000000000..f883ac47e7 --- /dev/null +++ b/tests/workloads/kernel_verbose_0/MI200/SQ_INST_LEVEL_LDS.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,358586,358586,1048576,256,0,0,8,0,16,64,0x0,0x7fce8eef4ec0,0,0,0,199949379551109,199961732754864,199961732775184,199949395620397 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,358586,358586,1048576,256,0,0,8,0,16,64,0x0,0x7fce8eef4ec0,0,0,0,199949395646166,199961732860464,199961732876784,199949395893174 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,358586,358586,1048576,256,0,0,8,0,16,64,0x0,0x7fce8eef4ec0,0,0,0,199949395919734,199961732897264,199961732913104,199949396052224 diff --git a/tests/workloads/kernel_verbose_0/MI200/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/kernel_verbose_0/MI200/SQ_INST_LEVEL_SMEM.csv new file mode 100644 index 0000000000..fc6baf80e9 --- /dev/null +++ b/tests/workloads/kernel_verbose_0/MI200/SQ_INST_LEVEL_SMEM.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,358785,358785,1048576,256,0,0,8,0,16,64,0x0,0x7f4fb6f60ec0,65536,192650,21532128,199949862529729,199961732754864,199961732775184,199949878310071 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,358785,358785,1048576,256,0,0,8,0,16,64,0x0,0x7f4fb6f60ec0,65536,261854,29352464,199949878328526,199961732860464,199961732876784,199949878604739 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,358785,358785,1048576,256,0,0,8,0,16,64,0x0,0x7f4fb6f60ec0,65536,262932,29314240,199949878631169,199961732897264,199961732913104,199949878784980 diff --git a/tests/workloads/kernel_verbose_0/MI200/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/kernel_verbose_0/MI200/SQ_INST_LEVEL_VMEM.csv new file mode 100644 index 0000000000..edb7528078 --- /dev/null +++ b/tests/workloads/kernel_verbose_0/MI200/SQ_INST_LEVEL_VMEM.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,358986,358986,1048576,256,0,0,8,0,16,64,0x0,0x7fdb72218ec0,32768,298276,33407688,199950343316353,199961732754864,199961732775184,199950359262619 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,358986,358986,1048576,256,0,0,8,0,16,64,0x0,0x7fdb72218ec0,32768,596987,66845280,199950359277127,199961732860464,199961732876784,199950359582544 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,358986,358986,1048576,256,0,0,8,0,16,64,0x0,0x7fdb72218ec0,32768,597482,66917436,199950359609075,199961732897264,199961732913104,199950359763046 diff --git a/tests/workloads/kernel_verbose_0/MI200/SQ_LEVEL_WAVES.csv b/tests/workloads/kernel_verbose_0/MI200/SQ_LEVEL_WAVES.csv new file mode 100644 index 0000000000..b8641b7245 --- /dev/null +++ b/tests/workloads/kernel_verbose_0/MI200/SQ_LEVEL_WAVES.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,359171,359171,1048576,256,0,0,8,0,16,64,0x0,0x7f5d6a584ec0,28053,28053,11278,224432,16384,11062997,129980,0,44746892,199950845453276,199961732754864,199961732775184,199950861414300 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,359171,359171,1048576,256,0,0,8,0,16,64,0x0,0x7f5d6a584ec0,40430,40430,12754,323448,16384,19776698,224617,0,79579868,199950861440600,199961732860464,199961732876784,199950861744164 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,359171,359171,1048576,256,0,0,8,0,16,64,0x0,0x7f5d6a584ec0,40804,40804,12443,326440,16384,19963790,227939,0,80332968,199950861779430,199961732897264,199961732913104,199950861943731 diff --git a/tests/workloads/kernel_verbose_0/MI200/perfmon/SQ_IFETCH_LEVEL.txt b/tests/workloads/kernel_verbose_0/MI200/perfmon/SQ_IFETCH_LEVEL.txt new file mode 100644 index 0000000000..293092f641 --- /dev/null +++ b/tests/workloads/kernel_verbose_0/MI200/perfmon/SQ_IFETCH_LEVEL.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_0/MI200/perfmon/SQ_INST_LEVEL_LDS.txt b/tests/workloads/kernel_verbose_0/MI200/perfmon/SQ_INST_LEVEL_LDS.txt new file mode 100644 index 0000000000..08439eedce --- /dev/null +++ b/tests/workloads/kernel_verbose_0/MI200/perfmon/SQ_INST_LEVEL_LDS.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_0/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt b/tests/workloads/kernel_verbose_0/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt new file mode 100644 index 0000000000..6cca322d4e --- /dev/null +++ b/tests/workloads/kernel_verbose_0/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_0/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt b/tests/workloads/kernel_verbose_0/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt new file mode 100644 index 0000000000..e527ad31ba --- /dev/null +++ b/tests/workloads/kernel_verbose_0/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_0/MI200/perfmon/SQ_LEVEL_WAVES.txt b/tests/workloads/kernel_verbose_0/MI200/perfmon/SQ_LEVEL_WAVES.txt new file mode 100644 index 0000000000..3f8e04adb3 --- /dev/null +++ b/tests/workloads/kernel_verbose_0/MI200/perfmon/SQ_LEVEL_WAVES.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_0.txt b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_0.txt new file mode 100644 index 0000000000..4ffdc32149 --- /dev/null +++ b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_0.txt @@ -0,0 +1,5 @@ +pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES SQ_INSTS_VALU_CVT SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU GRBM_COUNT GRBM_GUI_ACTIVE TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum TA_TA_BUSY_sum TA_BUFFER_WAVEFRONTS_sum TD_TD_BUSY_sum TD_TC_STALL_sum SPI_CSN_WINDOW_VALID SPI_CSN_BUSY CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_1.txt b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_1.txt new file mode 100644 index 0000000000..6c277f4a37 --- /dev/null +++ b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_1.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VSKIPPED SQ_INSTS SQ_INSTS_VALU SQ_INSTS_VALU_ADD_F16 SQ_INSTS_VALU_MUL_F16 SQ_INSTS_VALU_FMA_F16 SQ_INSTS_VALU_TRANS_F16 SQ_INSTS_VALU_ADD_F32 GRBM_SPI_BUSY TCP_READ_TAGCONFLICT_STALL_CYCLES_sum TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum TCP_TA_TCP_STATE_READ_sum TA_BUFFER_READ_WAVEFRONTS_sum TA_BUFFER_WRITE_WAVEFRONTS_sum TD_SPI_STALL_sum TD_LOAD_WAVEFRONT_sum SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_10.txt b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_10.txt new file mode 100644 index 0000000000..7053d4dce6 --- /dev/null +++ b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_10.txt @@ -0,0 +1,5 @@ +pmc: SQC_TC_DATA_WRITE_REQ SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_11.txt b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_11.txt new file mode 100644 index 0000000000..77ae8b461f --- /dev/null +++ b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_11.txt @@ -0,0 +1,5 @@ +pmc: SQC_ICACHE_MISSES_DUPLICATE SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_12.txt b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_12.txt new file mode 100644 index 0000000000..dfb2cf65e5 --- /dev/null +++ b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_12.txt @@ -0,0 +1,5 @@ +pmc: SQC_DCACHE_REQ_READ_1 SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_13.txt b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_13.txt new file mode 100644 index 0000000000..062fc9644a --- /dev/null +++ b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_13.txt @@ -0,0 +1,5 @@ +pmc: TCC_ATOMIC[0] TCC_CYCLE[0] TCC_EA_ATOMIC[0] TCC_EA_ATOMIC_LEVEL[0] TCC_ATOMIC[1] TCC_CYCLE[1] TCC_EA_ATOMIC[1] TCC_EA_ATOMIC_LEVEL[1] TCC_ATOMIC[2] TCC_CYCLE[2] TCC_EA_ATOMIC[2] TCC_EA_ATOMIC_LEVEL[2] TCC_ATOMIC[3] TCC_CYCLE[3] TCC_EA_ATOMIC[3] TCC_EA_ATOMIC_LEVEL[3] TCC_ATOMIC[4] TCC_CYCLE[4] TCC_EA_ATOMIC[4] TCC_EA_ATOMIC_LEVEL[4] TCC_ATOMIC[5] TCC_CYCLE[5] TCC_EA_ATOMIC[5] TCC_EA_ATOMIC_LEVEL[5] TCC_ATOMIC[6] TCC_CYCLE[6] TCC_EA_ATOMIC[6] TCC_EA_ATOMIC_LEVEL[6] TCC_ATOMIC[7] TCC_CYCLE[7] TCC_EA_ATOMIC[7] TCC_EA_ATOMIC_LEVEL[7] TCC_ATOMIC[8] TCC_CYCLE[8] TCC_EA_ATOMIC[8] TCC_EA_ATOMIC_LEVEL[8] TCC_ATOMIC[9] TCC_CYCLE[9] TCC_EA_ATOMIC[9] TCC_EA_ATOMIC_LEVEL[9] TCC_ATOMIC[10] TCC_CYCLE[10] TCC_EA_ATOMIC[10] TCC_EA_ATOMIC_LEVEL[10] TCC_ATOMIC[11] TCC_CYCLE[11] TCC_EA_ATOMIC[11] TCC_EA_ATOMIC_LEVEL[11] TCC_ATOMIC[12] TCC_CYCLE[12] TCC_EA_ATOMIC[12] TCC_EA_ATOMIC_LEVEL[12] TCC_ATOMIC[13] TCC_CYCLE[13] TCC_EA_ATOMIC[13] TCC_EA_ATOMIC_LEVEL[13] TCC_ATOMIC[14] TCC_CYCLE[14] TCC_EA_ATOMIC[14] TCC_EA_ATOMIC_LEVEL[14] TCC_ATOMIC[15] TCC_CYCLE[15] TCC_EA_ATOMIC[15] TCC_EA_ATOMIC_LEVEL[15] TCC_ATOMIC[16] TCC_CYCLE[16] TCC_EA_ATOMIC[16] TCC_EA_ATOMIC_LEVEL[16] TCC_ATOMIC[17] TCC_CYCLE[17] TCC_EA_ATOMIC[17] TCC_EA_ATOMIC_LEVEL[17] TCC_ATOMIC[18] TCC_CYCLE[18] TCC_EA_ATOMIC[18] TCC_EA_ATOMIC_LEVEL[18] TCC_ATOMIC[19] TCC_CYCLE[19] TCC_EA_ATOMIC[19] TCC_EA_ATOMIC_LEVEL[19] TCC_ATOMIC[20] TCC_CYCLE[20] TCC_EA_ATOMIC[20] TCC_EA_ATOMIC_LEVEL[20] TCC_ATOMIC[21] TCC_CYCLE[21] TCC_EA_ATOMIC[21] TCC_EA_ATOMIC_LEVEL[21] TCC_ATOMIC[22] TCC_CYCLE[22] TCC_EA_ATOMIC[22] TCC_EA_ATOMIC_LEVEL[22] TCC_ATOMIC[23] TCC_CYCLE[23] TCC_EA_ATOMIC[23] TCC_EA_ATOMIC_LEVEL[23] TCC_ATOMIC[24] TCC_CYCLE[24] TCC_EA_ATOMIC[24] TCC_EA_ATOMIC_LEVEL[24] TCC_ATOMIC[25] TCC_CYCLE[25] TCC_EA_ATOMIC[25] TCC_EA_ATOMIC_LEVEL[25] TCC_ATOMIC[26] TCC_CYCLE[26] TCC_EA_ATOMIC[26] TCC_EA_ATOMIC_LEVEL[26] TCC_ATOMIC[27] TCC_CYCLE[27] TCC_EA_ATOMIC[27] TCC_EA_ATOMIC_LEVEL[27] TCC_ATOMIC[28] TCC_CYCLE[28] TCC_EA_ATOMIC[28] TCC_EA_ATOMIC_LEVEL[28] TCC_ATOMIC[29] TCC_CYCLE[29] TCC_EA_ATOMIC[29] TCC_EA_ATOMIC_LEVEL[29] TCC_ATOMIC[30] TCC_CYCLE[30] TCC_EA_ATOMIC[30] TCC_EA_ATOMIC_LEVEL[30] TCC_ATOMIC[31] TCC_CYCLE[31] TCC_EA_ATOMIC[31] TCC_EA_ATOMIC_LEVEL[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_14.txt b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_14.txt new file mode 100644 index 0000000000..e0698dbf57 --- /dev/null +++ b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_14.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_EA_RDREQ_GMI_CREDIT_STALL[0] TCC_EA_RDREQ[1] TCC_EA_RDREQ_32B[1] TCC_EA_RDREQ_DRAM_CREDIT_STALL[1] TCC_EA_RDREQ_GMI_CREDIT_STALL[1] TCC_EA_RDREQ[2] TCC_EA_RDREQ_32B[2] TCC_EA_RDREQ_DRAM_CREDIT_STALL[2] TCC_EA_RDREQ_GMI_CREDIT_STALL[2] TCC_EA_RDREQ[3] TCC_EA_RDREQ_32B[3] TCC_EA_RDREQ_DRAM_CREDIT_STALL[3] TCC_EA_RDREQ_GMI_CREDIT_STALL[3] TCC_EA_RDREQ[4] TCC_EA_RDREQ_32B[4] TCC_EA_RDREQ_DRAM_CREDIT_STALL[4] TCC_EA_RDREQ_GMI_CREDIT_STALL[4] TCC_EA_RDREQ[5] TCC_EA_RDREQ_32B[5] TCC_EA_RDREQ_DRAM_CREDIT_STALL[5] TCC_EA_RDREQ_GMI_CREDIT_STALL[5] TCC_EA_RDREQ[6] TCC_EA_RDREQ_32B[6] TCC_EA_RDREQ_DRAM_CREDIT_STALL[6] TCC_EA_RDREQ_GMI_CREDIT_STALL[6] TCC_EA_RDREQ[7] TCC_EA_RDREQ_32B[7] TCC_EA_RDREQ_DRAM_CREDIT_STALL[7] TCC_EA_RDREQ_GMI_CREDIT_STALL[7] TCC_EA_RDREQ[8] TCC_EA_RDREQ_32B[8] TCC_EA_RDREQ_DRAM_CREDIT_STALL[8] TCC_EA_RDREQ_GMI_CREDIT_STALL[8] TCC_EA_RDREQ[9] TCC_EA_RDREQ_32B[9] TCC_EA_RDREQ_DRAM_CREDIT_STALL[9] TCC_EA_RDREQ_GMI_CREDIT_STALL[9] TCC_EA_RDREQ[10] TCC_EA_RDREQ_32B[10] TCC_EA_RDREQ_DRAM_CREDIT_STALL[10] TCC_EA_RDREQ_GMI_CREDIT_STALL[10] TCC_EA_RDREQ[11] TCC_EA_RDREQ_32B[11] TCC_EA_RDREQ_DRAM_CREDIT_STALL[11] TCC_EA_RDREQ_GMI_CREDIT_STALL[11] TCC_EA_RDREQ[12] TCC_EA_RDREQ_32B[12] TCC_EA_RDREQ_DRAM_CREDIT_STALL[12] TCC_EA_RDREQ_GMI_CREDIT_STALL[12] TCC_EA_RDREQ[13] TCC_EA_RDREQ_32B[13] TCC_EA_RDREQ_DRAM_CREDIT_STALL[13] TCC_EA_RDREQ_GMI_CREDIT_STALL[13] TCC_EA_RDREQ[14] TCC_EA_RDREQ_32B[14] TCC_EA_RDREQ_DRAM_CREDIT_STALL[14] TCC_EA_RDREQ_GMI_CREDIT_STALL[14] TCC_EA_RDREQ[15] TCC_EA_RDREQ_32B[15] TCC_EA_RDREQ_DRAM_CREDIT_STALL[15] TCC_EA_RDREQ_GMI_CREDIT_STALL[15] TCC_EA_RDREQ[16] TCC_EA_RDREQ_32B[16] TCC_EA_RDREQ_DRAM_CREDIT_STALL[16] TCC_EA_RDREQ_GMI_CREDIT_STALL[16] TCC_EA_RDREQ[17] TCC_EA_RDREQ_32B[17] TCC_EA_RDREQ_DRAM_CREDIT_STALL[17] TCC_EA_RDREQ_GMI_CREDIT_STALL[17] TCC_EA_RDREQ[18] TCC_EA_RDREQ_32B[18] TCC_EA_RDREQ_DRAM_CREDIT_STALL[18] TCC_EA_RDREQ_GMI_CREDIT_STALL[18] TCC_EA_RDREQ[19] TCC_EA_RDREQ_32B[19] TCC_EA_RDREQ_DRAM_CREDIT_STALL[19] TCC_EA_RDREQ_GMI_CREDIT_STALL[19] TCC_EA_RDREQ[20] TCC_EA_RDREQ_32B[20] TCC_EA_RDREQ_DRAM_CREDIT_STALL[20] TCC_EA_RDREQ_GMI_CREDIT_STALL[20] TCC_EA_RDREQ[21] TCC_EA_RDREQ_32B[21] TCC_EA_RDREQ_DRAM_CREDIT_STALL[21] TCC_EA_RDREQ_GMI_CREDIT_STALL[21] TCC_EA_RDREQ[22] TCC_EA_RDREQ_32B[22] TCC_EA_RDREQ_DRAM_CREDIT_STALL[22] TCC_EA_RDREQ_GMI_CREDIT_STALL[22] TCC_EA_RDREQ[23] TCC_EA_RDREQ_32B[23] TCC_EA_RDREQ_DRAM_CREDIT_STALL[23] TCC_EA_RDREQ_GMI_CREDIT_STALL[23] TCC_EA_RDREQ[24] TCC_EA_RDREQ_32B[24] TCC_EA_RDREQ_DRAM_CREDIT_STALL[24] TCC_EA_RDREQ_GMI_CREDIT_STALL[24] TCC_EA_RDREQ[25] TCC_EA_RDREQ_32B[25] TCC_EA_RDREQ_DRAM_CREDIT_STALL[25] TCC_EA_RDREQ_GMI_CREDIT_STALL[25] TCC_EA_RDREQ[26] TCC_EA_RDREQ_32B[26] TCC_EA_RDREQ_DRAM_CREDIT_STALL[26] TCC_EA_RDREQ_GMI_CREDIT_STALL[26] TCC_EA_RDREQ[27] TCC_EA_RDREQ_32B[27] TCC_EA_RDREQ_DRAM_CREDIT_STALL[27] TCC_EA_RDREQ_GMI_CREDIT_STALL[27] TCC_EA_RDREQ[28] TCC_EA_RDREQ_32B[28] TCC_EA_RDREQ_DRAM_CREDIT_STALL[28] TCC_EA_RDREQ_GMI_CREDIT_STALL[28] TCC_EA_RDREQ[29] TCC_EA_RDREQ_32B[29] TCC_EA_RDREQ_DRAM_CREDIT_STALL[29] TCC_EA_RDREQ_GMI_CREDIT_STALL[29] TCC_EA_RDREQ[30] TCC_EA_RDREQ_32B[30] TCC_EA_RDREQ_DRAM_CREDIT_STALL[30] TCC_EA_RDREQ_GMI_CREDIT_STALL[30] TCC_EA_RDREQ[31] TCC_EA_RDREQ_32B[31] TCC_EA_RDREQ_DRAM_CREDIT_STALL[31] TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_15.txt b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_15.txt new file mode 100644 index 0000000000..77ad088669 --- /dev/null +++ b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_15.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ[0] TCC_EA_WRREQ_64B[0] TCC_EA_RDREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_LEVEL[1] TCC_EA_WRREQ[1] TCC_EA_WRREQ_64B[1] TCC_EA_RDREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_LEVEL[2] TCC_EA_WRREQ[2] TCC_EA_WRREQ_64B[2] TCC_EA_RDREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_LEVEL[3] TCC_EA_WRREQ[3] TCC_EA_WRREQ_64B[3] TCC_EA_RDREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_LEVEL[4] TCC_EA_WRREQ[4] TCC_EA_WRREQ_64B[4] TCC_EA_RDREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_LEVEL[5] TCC_EA_WRREQ[5] TCC_EA_WRREQ_64B[5] TCC_EA_RDREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_LEVEL[6] TCC_EA_WRREQ[6] TCC_EA_WRREQ_64B[6] TCC_EA_RDREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_LEVEL[7] TCC_EA_WRREQ[7] TCC_EA_WRREQ_64B[7] TCC_EA_RDREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_LEVEL[8] TCC_EA_WRREQ[8] TCC_EA_WRREQ_64B[8] TCC_EA_RDREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_LEVEL[9] TCC_EA_WRREQ[9] TCC_EA_WRREQ_64B[9] TCC_EA_RDREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_LEVEL[10] TCC_EA_WRREQ[10] TCC_EA_WRREQ_64B[10] TCC_EA_RDREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_LEVEL[11] TCC_EA_WRREQ[11] TCC_EA_WRREQ_64B[11] TCC_EA_RDREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_LEVEL[12] TCC_EA_WRREQ[12] TCC_EA_WRREQ_64B[12] TCC_EA_RDREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_LEVEL[13] TCC_EA_WRREQ[13] TCC_EA_WRREQ_64B[13] TCC_EA_RDREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_LEVEL[14] TCC_EA_WRREQ[14] TCC_EA_WRREQ_64B[14] TCC_EA_RDREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_LEVEL[15] TCC_EA_WRREQ[15] TCC_EA_WRREQ_64B[15] TCC_EA_RDREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_LEVEL[16] TCC_EA_WRREQ[16] TCC_EA_WRREQ_64B[16] TCC_EA_RDREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_LEVEL[17] TCC_EA_WRREQ[17] TCC_EA_WRREQ_64B[17] TCC_EA_RDREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_LEVEL[18] TCC_EA_WRREQ[18] TCC_EA_WRREQ_64B[18] TCC_EA_RDREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_LEVEL[19] TCC_EA_WRREQ[19] TCC_EA_WRREQ_64B[19] TCC_EA_RDREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_LEVEL[20] TCC_EA_WRREQ[20] TCC_EA_WRREQ_64B[20] TCC_EA_RDREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_LEVEL[21] TCC_EA_WRREQ[21] TCC_EA_WRREQ_64B[21] TCC_EA_RDREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_LEVEL[22] TCC_EA_WRREQ[22] TCC_EA_WRREQ_64B[22] TCC_EA_RDREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_LEVEL[23] TCC_EA_WRREQ[23] TCC_EA_WRREQ_64B[23] TCC_EA_RDREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_LEVEL[24] TCC_EA_WRREQ[24] TCC_EA_WRREQ_64B[24] TCC_EA_RDREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_LEVEL[25] TCC_EA_WRREQ[25] TCC_EA_WRREQ_64B[25] TCC_EA_RDREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_LEVEL[26] TCC_EA_WRREQ[26] TCC_EA_WRREQ_64B[26] TCC_EA_RDREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_LEVEL[27] TCC_EA_WRREQ[27] TCC_EA_WRREQ_64B[27] TCC_EA_RDREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_LEVEL[28] TCC_EA_WRREQ[28] TCC_EA_WRREQ_64B[28] TCC_EA_RDREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_LEVEL[29] TCC_EA_WRREQ[29] TCC_EA_WRREQ_64B[29] TCC_EA_RDREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_LEVEL[30] TCC_EA_WRREQ[30] TCC_EA_WRREQ_64B[30] TCC_EA_RDREQ_IO_CREDIT_STALL[31] TCC_EA_RDREQ_LEVEL[31] TCC_EA_WRREQ[31] TCC_EA_WRREQ_64B[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_16.txt b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_16.txt new file mode 100644 index 0000000000..d0628bb948 --- /dev/null +++ b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_16.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_WRREQ_IO_CREDIT_STALL[0] TCC_EA_WRREQ_LEVEL[0] TCC_EA_WRREQ_DRAM_CREDIT_STALL[1] TCC_EA_WRREQ_GMI_CREDIT_STALL[1] TCC_EA_WRREQ_IO_CREDIT_STALL[1] TCC_EA_WRREQ_LEVEL[1] TCC_EA_WRREQ_DRAM_CREDIT_STALL[2] TCC_EA_WRREQ_GMI_CREDIT_STALL[2] TCC_EA_WRREQ_IO_CREDIT_STALL[2] TCC_EA_WRREQ_LEVEL[2] TCC_EA_WRREQ_DRAM_CREDIT_STALL[3] TCC_EA_WRREQ_GMI_CREDIT_STALL[3] TCC_EA_WRREQ_IO_CREDIT_STALL[3] TCC_EA_WRREQ_LEVEL[3] TCC_EA_WRREQ_DRAM_CREDIT_STALL[4] TCC_EA_WRREQ_GMI_CREDIT_STALL[4] TCC_EA_WRREQ_IO_CREDIT_STALL[4] TCC_EA_WRREQ_LEVEL[4] TCC_EA_WRREQ_DRAM_CREDIT_STALL[5] TCC_EA_WRREQ_GMI_CREDIT_STALL[5] TCC_EA_WRREQ_IO_CREDIT_STALL[5] TCC_EA_WRREQ_LEVEL[5] TCC_EA_WRREQ_DRAM_CREDIT_STALL[6] TCC_EA_WRREQ_GMI_CREDIT_STALL[6] TCC_EA_WRREQ_IO_CREDIT_STALL[6] TCC_EA_WRREQ_LEVEL[6] TCC_EA_WRREQ_DRAM_CREDIT_STALL[7] TCC_EA_WRREQ_GMI_CREDIT_STALL[7] TCC_EA_WRREQ_IO_CREDIT_STALL[7] TCC_EA_WRREQ_LEVEL[7] TCC_EA_WRREQ_DRAM_CREDIT_STALL[8] TCC_EA_WRREQ_GMI_CREDIT_STALL[8] TCC_EA_WRREQ_IO_CREDIT_STALL[8] TCC_EA_WRREQ_LEVEL[8] TCC_EA_WRREQ_DRAM_CREDIT_STALL[9] TCC_EA_WRREQ_GMI_CREDIT_STALL[9] TCC_EA_WRREQ_IO_CREDIT_STALL[9] TCC_EA_WRREQ_LEVEL[9] TCC_EA_WRREQ_DRAM_CREDIT_STALL[10] TCC_EA_WRREQ_GMI_CREDIT_STALL[10] TCC_EA_WRREQ_IO_CREDIT_STALL[10] TCC_EA_WRREQ_LEVEL[10] TCC_EA_WRREQ_DRAM_CREDIT_STALL[11] TCC_EA_WRREQ_GMI_CREDIT_STALL[11] TCC_EA_WRREQ_IO_CREDIT_STALL[11] TCC_EA_WRREQ_LEVEL[11] TCC_EA_WRREQ_DRAM_CREDIT_STALL[12] TCC_EA_WRREQ_GMI_CREDIT_STALL[12] TCC_EA_WRREQ_IO_CREDIT_STALL[12] TCC_EA_WRREQ_LEVEL[12] TCC_EA_WRREQ_DRAM_CREDIT_STALL[13] TCC_EA_WRREQ_GMI_CREDIT_STALL[13] TCC_EA_WRREQ_IO_CREDIT_STALL[13] TCC_EA_WRREQ_LEVEL[13] TCC_EA_WRREQ_DRAM_CREDIT_STALL[14] TCC_EA_WRREQ_GMI_CREDIT_STALL[14] TCC_EA_WRREQ_IO_CREDIT_STALL[14] TCC_EA_WRREQ_LEVEL[14] TCC_EA_WRREQ_DRAM_CREDIT_STALL[15] TCC_EA_WRREQ_GMI_CREDIT_STALL[15] TCC_EA_WRREQ_IO_CREDIT_STALL[15] TCC_EA_WRREQ_LEVEL[15] TCC_EA_WRREQ_DRAM_CREDIT_STALL[16] TCC_EA_WRREQ_GMI_CREDIT_STALL[16] TCC_EA_WRREQ_IO_CREDIT_STALL[16] TCC_EA_WRREQ_LEVEL[16] TCC_EA_WRREQ_DRAM_CREDIT_STALL[17] TCC_EA_WRREQ_GMI_CREDIT_STALL[17] TCC_EA_WRREQ_IO_CREDIT_STALL[17] TCC_EA_WRREQ_LEVEL[17] TCC_EA_WRREQ_DRAM_CREDIT_STALL[18] TCC_EA_WRREQ_GMI_CREDIT_STALL[18] TCC_EA_WRREQ_IO_CREDIT_STALL[18] TCC_EA_WRREQ_LEVEL[18] TCC_EA_WRREQ_DRAM_CREDIT_STALL[19] TCC_EA_WRREQ_GMI_CREDIT_STALL[19] TCC_EA_WRREQ_IO_CREDIT_STALL[19] TCC_EA_WRREQ_LEVEL[19] TCC_EA_WRREQ_DRAM_CREDIT_STALL[20] TCC_EA_WRREQ_GMI_CREDIT_STALL[20] TCC_EA_WRREQ_IO_CREDIT_STALL[20] TCC_EA_WRREQ_LEVEL[20] TCC_EA_WRREQ_DRAM_CREDIT_STALL[21] TCC_EA_WRREQ_GMI_CREDIT_STALL[21] TCC_EA_WRREQ_IO_CREDIT_STALL[21] TCC_EA_WRREQ_LEVEL[21] TCC_EA_WRREQ_DRAM_CREDIT_STALL[22] TCC_EA_WRREQ_GMI_CREDIT_STALL[22] TCC_EA_WRREQ_IO_CREDIT_STALL[22] TCC_EA_WRREQ_LEVEL[22] TCC_EA_WRREQ_DRAM_CREDIT_STALL[23] TCC_EA_WRREQ_GMI_CREDIT_STALL[23] TCC_EA_WRREQ_IO_CREDIT_STALL[23] TCC_EA_WRREQ_LEVEL[23] TCC_EA_WRREQ_DRAM_CREDIT_STALL[24] TCC_EA_WRREQ_GMI_CREDIT_STALL[24] TCC_EA_WRREQ_IO_CREDIT_STALL[24] TCC_EA_WRREQ_LEVEL[24] TCC_EA_WRREQ_DRAM_CREDIT_STALL[25] TCC_EA_WRREQ_GMI_CREDIT_STALL[25] TCC_EA_WRREQ_IO_CREDIT_STALL[25] TCC_EA_WRREQ_LEVEL[25] TCC_EA_WRREQ_DRAM_CREDIT_STALL[26] TCC_EA_WRREQ_GMI_CREDIT_STALL[26] TCC_EA_WRREQ_IO_CREDIT_STALL[26] TCC_EA_WRREQ_LEVEL[26] TCC_EA_WRREQ_DRAM_CREDIT_STALL[27] TCC_EA_WRREQ_GMI_CREDIT_STALL[27] TCC_EA_WRREQ_IO_CREDIT_STALL[27] TCC_EA_WRREQ_LEVEL[27] TCC_EA_WRREQ_DRAM_CREDIT_STALL[28] TCC_EA_WRREQ_GMI_CREDIT_STALL[28] TCC_EA_WRREQ_IO_CREDIT_STALL[28] TCC_EA_WRREQ_LEVEL[28] TCC_EA_WRREQ_DRAM_CREDIT_STALL[29] TCC_EA_WRREQ_GMI_CREDIT_STALL[29] TCC_EA_WRREQ_IO_CREDIT_STALL[29] TCC_EA_WRREQ_LEVEL[29] TCC_EA_WRREQ_DRAM_CREDIT_STALL[30] TCC_EA_WRREQ_GMI_CREDIT_STALL[30] TCC_EA_WRREQ_IO_CREDIT_STALL[30] TCC_EA_WRREQ_LEVEL[30] TCC_EA_WRREQ_DRAM_CREDIT_STALL[31] TCC_EA_WRREQ_GMI_CREDIT_STALL[31] TCC_EA_WRREQ_IO_CREDIT_STALL[31] TCC_EA_WRREQ_LEVEL[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_17.txt b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_17.txt new file mode 100644 index 0000000000..343869c5f1 --- /dev/null +++ b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_17.txt @@ -0,0 +1,5 @@ +pmc: TCC_HIT[0] TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_HIT[1] TCC_MISS[1] TCC_READ[1] TCC_REQ[1] TCC_HIT[2] TCC_MISS[2] TCC_READ[2] TCC_REQ[2] TCC_HIT[3] TCC_MISS[3] TCC_READ[3] TCC_REQ[3] TCC_HIT[4] TCC_MISS[4] TCC_READ[4] TCC_REQ[4] TCC_HIT[5] TCC_MISS[5] TCC_READ[5] TCC_REQ[5] TCC_HIT[6] TCC_MISS[6] TCC_READ[6] TCC_REQ[6] TCC_HIT[7] TCC_MISS[7] TCC_READ[7] TCC_REQ[7] TCC_HIT[8] TCC_MISS[8] TCC_READ[8] TCC_REQ[8] TCC_HIT[9] TCC_MISS[9] TCC_READ[9] TCC_REQ[9] TCC_HIT[10] TCC_MISS[10] TCC_READ[10] TCC_REQ[10] TCC_HIT[11] TCC_MISS[11] TCC_READ[11] TCC_REQ[11] TCC_HIT[12] TCC_MISS[12] TCC_READ[12] TCC_REQ[12] TCC_HIT[13] TCC_MISS[13] TCC_READ[13] TCC_REQ[13] TCC_HIT[14] TCC_MISS[14] TCC_READ[14] TCC_REQ[14] TCC_HIT[15] TCC_MISS[15] TCC_READ[15] TCC_REQ[15] TCC_HIT[16] TCC_MISS[16] TCC_READ[16] TCC_REQ[16] TCC_HIT[17] TCC_MISS[17] TCC_READ[17] TCC_REQ[17] TCC_HIT[18] TCC_MISS[18] TCC_READ[18] TCC_REQ[18] TCC_HIT[19] TCC_MISS[19] TCC_READ[19] TCC_REQ[19] TCC_HIT[20] TCC_MISS[20] TCC_READ[20] TCC_REQ[20] TCC_HIT[21] TCC_MISS[21] TCC_READ[21] TCC_REQ[21] TCC_HIT[22] TCC_MISS[22] TCC_READ[22] TCC_REQ[22] TCC_HIT[23] TCC_MISS[23] TCC_READ[23] TCC_REQ[23] TCC_HIT[24] TCC_MISS[24] TCC_READ[24] TCC_REQ[24] TCC_HIT[25] TCC_MISS[25] TCC_READ[25] TCC_REQ[25] TCC_HIT[26] TCC_MISS[26] TCC_READ[26] TCC_REQ[26] TCC_HIT[27] TCC_MISS[27] TCC_READ[27] TCC_REQ[27] TCC_HIT[28] TCC_MISS[28] TCC_READ[28] TCC_REQ[28] TCC_HIT[29] TCC_MISS[29] TCC_READ[29] TCC_REQ[29] TCC_HIT[30] TCC_MISS[30] TCC_READ[30] TCC_REQ[30] TCC_HIT[31] TCC_MISS[31] TCC_READ[31] TCC_REQ[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_18.txt b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_18.txt new file mode 100644 index 0000000000..a74cefd281 --- /dev/null +++ b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_18.txt @@ -0,0 +1,5 @@ +pmc: TCC_RW_REQ[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_RW_REQ[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_WRITE[1] TCC_RW_REQ[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_WRITE[2] TCC_RW_REQ[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_WRITE[3] TCC_RW_REQ[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_WRITE[4] TCC_RW_REQ[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_WRITE[5] TCC_RW_REQ[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_WRITE[6] TCC_RW_REQ[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_WRITE[7] TCC_RW_REQ[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_WRITE[8] TCC_RW_REQ[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_WRITE[9] TCC_RW_REQ[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_WRITE[10] TCC_RW_REQ[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_WRITE[11] TCC_RW_REQ[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_WRITE[12] TCC_RW_REQ[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_WRITE[13] TCC_RW_REQ[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_WRITE[14] TCC_RW_REQ[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_WRITE[15] TCC_RW_REQ[16] TCC_TOO_MANY_EA_WRREQS_STALL[16] TCC_WRITE[16] TCC_RW_REQ[17] TCC_TOO_MANY_EA_WRREQS_STALL[17] TCC_WRITE[17] TCC_RW_REQ[18] TCC_TOO_MANY_EA_WRREQS_STALL[18] TCC_WRITE[18] TCC_RW_REQ[19] TCC_TOO_MANY_EA_WRREQS_STALL[19] TCC_WRITE[19] TCC_RW_REQ[20] TCC_TOO_MANY_EA_WRREQS_STALL[20] TCC_WRITE[20] TCC_RW_REQ[21] TCC_TOO_MANY_EA_WRREQS_STALL[21] TCC_WRITE[21] TCC_RW_REQ[22] TCC_TOO_MANY_EA_WRREQS_STALL[22] TCC_WRITE[22] TCC_RW_REQ[23] TCC_TOO_MANY_EA_WRREQS_STALL[23] TCC_WRITE[23] TCC_RW_REQ[24] TCC_TOO_MANY_EA_WRREQS_STALL[24] TCC_WRITE[24] TCC_RW_REQ[25] TCC_TOO_MANY_EA_WRREQS_STALL[25] TCC_WRITE[25] TCC_RW_REQ[26] TCC_TOO_MANY_EA_WRREQS_STALL[26] TCC_WRITE[26] TCC_RW_REQ[27] TCC_TOO_MANY_EA_WRREQS_STALL[27] TCC_WRITE[27] TCC_RW_REQ[28] TCC_TOO_MANY_EA_WRREQS_STALL[28] TCC_WRITE[28] TCC_RW_REQ[29] TCC_TOO_MANY_EA_WRREQS_STALL[29] TCC_WRITE[29] TCC_RW_REQ[30] TCC_TOO_MANY_EA_WRREQS_STALL[30] TCC_WRITE[30] TCC_RW_REQ[31] TCC_TOO_MANY_EA_WRREQS_STALL[31] TCC_WRITE[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_2.txt b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_2.txt new file mode 100644 index 0000000000..70b69f8928 --- /dev/null +++ b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_2.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_MUL_F32 SQ_INSTS_VALU_FMA_F32 SQ_INSTS_VALU_TRANS_F32 SQ_INSTS_VALU_ADD_F64 SQ_INSTS_VALU_MUL_F64 SQ_INSTS_VALU_FMA_F64 SQ_INSTS_VALU_TRANS_F64 SQ_INSTS_VALU_INT32 TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum TA_BUFFER_ATOMIC_WAVEFRONTS_sum TA_BUFFER_TOTAL_CYCLES_sum TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_3.txt b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_3.txt new file mode 100644 index 0000000000..e47f8e33c9 --- /dev/null +++ b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_3.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_INT64 SQ_INSTS_SMEM SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum TD_COALESCABLE_WAVEFRONT_sum SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE CPF_CMP_UTCL1_STALL_ON_TRANSLATION TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_4.txt b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_4.txt new file mode 100644 index 0000000000..2d96f365a9 --- /dev/null +++ b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_4.txt @@ -0,0 +1,5 @@ +pmc: SQ_WAVE_CYCLES SQ_WAIT_ANY SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_BUSY_CU_CYCLES SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE TCC_EA_WRREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WR_UNCACHED_32B_sum TCC_EA_WRREQ_DRAM_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_5.txt b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_5.txt new file mode 100644 index 0000000000..e50beed390 --- /dev/null +++ b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_5.txt @@ -0,0 +1,5 @@ +pmc: SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU TCP_TCP_LATENCY_sum TCP_TCC_READ_REQ_LATENCY_sum TCP_TCC_WRITE_REQ_LATENCY_sum TCP_TCC_READ_REQ_sum TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN CPC_ME1_DC0_SPI_BUSY TCC_EA_WRREQ_STALL_sum TCC_EA_RDREQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RD_UNCACHED_32B_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_6.txt b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_6.txt new file mode 100644 index 0000000000..15a2277c1b --- /dev/null +++ b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_6.txt @@ -0,0 +1,5 @@ +pmc: SQ_THREAD_CYCLES_VALU SQ_IFETCH SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TCP_TCC_NC_READ_REQ_sum TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN TCC_EA_RDREQ_DRAM_sum TCC_TAG_STALL_sum TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_7.txt b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_7.txt new file mode 100644 index 0000000000..b42ce91618 --- /dev/null +++ b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_7.txt @@ -0,0 +1,5 @@ +pmc: SQ_WAVES_LT_32 SQ_WAVES_LT_16 SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TCP_TCC_UC_WRITE_REQ_sum TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR TCC_NORMAL_EVICT_sum TCC_ALL_TC_OP_INV_EVICT_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA_ATOMIC_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_8.txt b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_8.txt new file mode 100644 index 0000000000..21d4c7a998 --- /dev/null +++ b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_8.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM_NORM SQ_INSTS_MFMA SQ_INSTS_VALU_MFMA_I8 SQ_INSTS_VALU_MFMA_F16 SQ_INSTS_VALU_MFMA_BF16 SQ_INSTS_VALU_MFMA_F32 SQ_INSTS_VALU_MFMA_F64 SQ_VALU_MFMA_BUSY_CYCLES TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TCP_TCC_CC_ATOMIC_REQ_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN TCC_EA_RDREQ_LEVEL_sum TCC_EA_WRREQ_LEVEL_sum TCC_EA_ATOMIC_LEVEL_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_9.txt b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_9.txt new file mode 100644 index 0000000000..9ffe5778c3 --- /dev/null +++ b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_9.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_FLAT_LDS_ONLY SQ_INSTS_VALU_MFMA_MOPS_I8 SQ_INSTS_VALU_MFMA_MOPS_F16 SQ_INSTS_VALU_MFMA_MOPS_BF16 SQ_INSTS_VALU_MFMA_MOPS_F32 SQ_INSTS_VALU_MFMA_MOPS_F64 SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum TCP_PENDING_STALL_CYCLES_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_0/MI200/perfmon/timestamps.txt b/tests/workloads/kernel_verbose_0/MI200/perfmon/timestamps.txt new file mode 100644 index 0000000000..676cca1b80 --- /dev/null +++ b/tests/workloads/kernel_verbose_0/MI200/perfmon/timestamps.txt @@ -0,0 +1,5 @@ +pmc: + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_0/MI200/pmc_perf.csv b/tests/workloads/kernel_verbose_0/MI200/pmc_perf.csv new file mode 100644 index 0000000000..4a4a70b1d3 --- /dev/null +++ b/tests/workloads/kernel_verbose_0/MI200/pmc_perf.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,wave_size_1,obj_1,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_2,obj_2,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,TD_COALESCABLE_WAVEFRONT_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_3,obj_3,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_4,obj_4,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_5,obj_5,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,wave_size_6,obj_6,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_7,obj_7,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_8,obj_8,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_9,obj_9,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_10,obj_10,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_11,obj_11,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_12,obj_12,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_13,obj_13,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,TCC_EA_ATOMIC_LEVEL_sum,wave_size_14,obj_14,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_15,obj_15,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_DRAM_sum,TCC_TAG_STALL_sum,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,wave_size_16,obj_16,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_17,obj_17,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_18,obj_18,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f8012a88ec0,114688,0,32768,32768,16384,16384,65536,49152,27615177.0,87807843.0,40484884.0,131072.0,0.0,196518.0,0,0,14809,38.0,131083.0,0.0,14.0,64,0x7f7fece10ec0,2262,4096,2262,6358,2310,4096,2310,6406,2254,4096,2254,6350,2299,4096,2299,6395,2305,4097,2306,6402,2306,4099,2309,6405,2309,4096,2309,6405,2281,4096,2281,6377,2285,4096,2285,6381,2262,4096,2262,6358,2309,4096,2309,6405,2254,4096,2254,6350,2300,4096,2300,6396,2251,4096,2251,6347,2307,4096,2307,6403,2311,4096,2311,6407,2267,4096,2267,6363,2310,4096,2310,6406,2249,4097,2250,6346,2295,4096,2295,6391,2262,4096,2262,6358,2297,4096,2297,6393,2291,4096,2291,6387,2444,4099,2447,6543,2277,4096,2277,6373,2268,4096,2268,6364,2306,4096,2306,6402,2253,4096,2253,6349,2291,4096,2291,6387,2262,4096,2262,6358,2303,4096,2303,6399,2298,4096,2298,6394,64,0x7f8e70438ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,10643,0,814,27527,0,73464.0,131072.0,0.0,65568.0,64,0x7ff35030cec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,11416,18608,8076,549,0,26136,204284.0,0.0,73203.0,131081.0,64,0x7f98f7dd4ec0,1293,115127,0,0,65536,63800,56,1680,64,0x7f3382d3cec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65551.0,0.0,0.0,0.0,64,0x7fb474a04ec0,0,393216,163840,0,0,0,0,0,18528,0.0,0.0,0.0,32768.0,0.0,0.0,397.0,32768.0,4096,16384,352,29010,1938,0,56.0,6.0,0.0,204757.0,64,0x7f90a9bbcec0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,120,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4099,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4099,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,64,0x7f65ed360ec0,229488,128849,16384,0,16384,16384,32768,49152,28685,28685,1952618.0,1308857.0,3414.0,129435.0,1034941.0,0.0,1300622.0,1002465.0,227777,136980,28685,0,28685,0,917920.0,491095.0,0.0,0.0,64,0x7fc8d388cec0,32768,32768,0,64,0x7f7bd52a0ec0,0,0,0,224,0,65536,64183,56,64,0x7fe95a08cec0,0,0,0,1032925,0,0,0,1116636,0,0,0,1077888,15,0,0,1249287,0,0,0,1057034,64,0,0,1230430,59,0,0,1083685,61,0,0,1216586,16,0,0,1069244,0,0,0,1121576,0,0,0,1008544,0,0,0,1130056,0,0,0,1095521,49,0,0,1156927,0,0,0,1083565,0,0,0,1205235,0,0,0,1056906,6,0,0,1093588,0,0,0,1049037,0,0,0,1147696,24,0,0,1121366,0,0,0,1128214,9,0,0,1194933,0,0,0,1146147,0,0,0,1041055,106,0,0,1175478,0,0,0,1106738,0,0,0,1189854,10,0,0,1089377,184,0,0,1141140,0,0,0,1096664,0,0,0,1173028,64,0x7f8da5ce4ec0,6363,0,4096,6401,0,4096,6373,0,4096,6424,0,4096,6354,0,4096,6419,0,4096,6338,0,4096,6371,0,4096,6370,0,4096,6362,0,4096,6402,0,4096,6374,0,4096,6425,0,4096,6356,0,4096,6424,0,4096,6338,0,4096,6372,0,4096,6341,0,4096,6354,0,4096,6383,0,4096,6385,0,4096,6367,0,4096,6387,0,4096,6531,0,4096,6365,0,4096,6371,0,4096,6339,0,4096,6355,0,4096,6383,0,4096,6385,0,4096,6369,0,4096,6387,0,4096,64,0x7fe9c17d0ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,39045272.0,34791701.0,0.0,64,0x7fa461318ec0,0,1144758,4096,4096,0,1198859,4096,4096,0,1169355,4096,4096,0,1417969,4096,4096,0,1295789,4096,4096,0,1447915,4096,4096,0,1212133,4096,4096,0,1489792,4096,4096,0,1400337,4096,4096,0,1222110,4096,4096,0,1177960,4096,4096,0,1421251,4096,4096,0,1041792,4096,4096,0,1200010,4096,4096,0,1236139,4096,4096,0,1269052,4096,4096,0,1192839,4096,4096,0,1276429,4096,4096,0,1036663,4096,4096,0,1279176,4096,4096,0,1196150,4096,4096,0,1186095,4096,4096,0,1392935,4096,4096,0,1159360,4096,4096,0,1243849,4096,4096,0,1181254,4096,4096,0,1180725,4096,4096,0,1203109,4096,4096,0,1343890,4096,4096,0,1018493,4096,4096,0,1152072,4096,4096,0,1517163,4096,4096,64,0x7f4286e30ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131078.0,34051.0,46157.0,19379.0,64,0x7f2ad94fcec0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,64,0x7f8a94e90ec0,0,0,0,0,0,0,168,56,131072.0,131072.0,0.0,983917.0,64,0x7fe3d4124ec0,11180534,9957449,879021,344064,1678545,0,0,163840,832.0,515136.0,0.0,524288.0,333998.0,32768.0,503855,0,0,11694,131072.0,131072.0,0.0,131072.0,199961732754864,199961732775184 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f8012a88ec0,114688,0,32768,32768,16384,16384,65536,49152,59635919.0,204377227.0,52566171.0,131072.0,0.0,421089.0,0,0,23370,3887.0,131073.0,0.0,0.0,64,0x7f7fece10ec0,2188,4096,2188,6284,2174,4096,2174,6270,2176,4099,2179,6275,2136,4096,2136,6232,2225,4097,2226,6322,2204,4098,2206,6302,2142,4096,2142,6238,2177,4096,2177,6273,2181,4096,2181,6277,2185,4096,2185,6281,2174,4096,2174,6270,2177,4096,2177,6273,2140,4096,2140,6236,2167,4096,2167,6263,2212,4096,2212,6308,2148,4096,2148,6244,2158,4096,2158,6254,2165,4096,2165,6261,2169,4097,2170,6266,2156,4096,2156,6252,2164,4096,2164,6260,2126,4096,2126,6222,2188,4096,2188,6284,2198,4097,2199,6295,2202,4096,2202,6298,2162,4096,2162,6258,2166,4096,2166,6262,2174,4097,2175,6271,2159,4096,2159,6255,2164,4096,2164,6260,2127,4096,2127,6223,2192,4096,2192,6288,64,0x7f8e70438ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,15930,0,819,36570,0,69577.0,131072.0,0.0,45480.0,64,0x7ff35030cec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,32570,28382,9568,2425,0,38970,200878.0,0.0,69795.0,131083.0,64,0x7f98f7dd4ec0,0,188622,0,0,65536,63800,56,1680,64,0x7f3382d3cec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65550.0,0.0,0.0,0.0,64,0x7fb474a04ec0,0,393216,163840,0,0,0,0,0,30838,0.0,0.0,0.0,32768.0,0.0,0.0,202.0,32768.0,4096,16384,302,41968,2083,0,56.0,11.0,0.0,200840.0,64,0x7f90a9bbcec0,4096,0,529,0,4096,0,19,0,4096,0,1248,0,4096,0,790,0,4096,0,264,0,4096,0,461,0,4096,0,758,0,4096,0,733,0,4096,0,530,0,4096,0,290,0,4097,0,179,0,4099,0,1111,0,4096,0,494,0,4096,0,423,0,4096,0,584,0,4096,0,744,0,4096,0,14,0,4097,0,234,0,4097,0,47,0,4096,0,729,0,4096,0,644,0,4096,0,615,0,4096,0,360,0,4096,0,859,0,4096,0,2255,0,4097,0,265,0,4096,0,216,0,4096,0,25,0,4097,0,22,0,4098,0,293,0,4096,0,785,0,4096,0,2172,0,64,0x7f65ed360ec0,328344,221036,16384,0,16384,16384,32768,49152,41042,41042,3150055.0,2415775.0,4039.0,278343.0,1633554.0,0.0,2403693.0,2095396.0,328336,230159,41042,0,41042,0,1313344.0,778018.0,0.0,0.0,64,0x7fc8d388cec0,32768,32768,0,64,0x7f7bd52a0ec0,0,0,0,56,0,65536,65536,0,64,0x7fe95a08cec0,787,0,0,2133833,553,0,0,2069105,262,0,0,1852036,307,0,0,1953299,1010,0,0,2438948,1550,0,0,2234417,0,0,0,1692453,181,0,0,1899948,105,0,0,1933065,625,0,0,1988865,257,0,0,1629841,292,0,0,1721025,268,0,0,1726583,816,0,0,1928842,754,0,0,2100554,84,0,0,1894588,36,0,0,1589513,84,0,0,1577650,586,0,0,1806706,1386,0,0,2120762,316,0,0,2136687,418,0,0,2011421,1311,0,0,2146658,572,0,0,2040442,216,0,0,1927918,578,0,0,1802792,155,0,0,2078166,1263,0,0,1796692,764,0,0,1726683,282,0,0,1708020,446,0,0,2000506,1001,0,0,1927813,64,0x7f8da5ce4ec0,6284,0,4096,6279,0,4096,6273,0,4096,6257,0,4096,6263,0,4096,6292,0,4096,6298,0,4096,6280,0,4096,6284,0,4096,6281,0,4096,6284,0,4096,6278,0,4096,6256,0,4096,6262,0,4096,6293,0,4096,6296,0,4096,6303,0,4096,6282,0,4096,6282,0,4096,6260,0,4096,6291,0,4096,6272,0,4096,6256,0,4096,6259,0,4096,6262,0,4096,6303,0,4096,6287,0,4096,6288,0,4096,6261,0,4096,6293,0,4096,6273,0,4096,6260,0,4096,64,0x7fe9c17d0ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,117684210.0,60329209.0,0.0,64,0x7fa461318ec0,0,3178627,2832,2832,0,3739317,2872,2872,0,3441328,2860,2860,0,4901048,2848,2848,0,4023958,2892,2892,0,3722092,2840,2840,0,2962120,2872,2872,0,4583360,2832,2832,0,3103569,2836,2836,0,4358587,2824,2824,0,3624303,2872,2872,0,3147139,2856,2856,0,3851139,2848,2848,0,3651378,2894,2894,0,4128605,2840,2840,0,3375854,2864,2864,0,3725421,2820,2820,0,4082832,2856,2856,0,3796158,2848,2848,0,3407282,2844,2844,0,4215144,2848,2848,0,3900469,2868,2868,0,3493863,2828,2828,0,3897504,2824,2824,0,3428842,2828,2828,0,3416021,2820,2820,0,3973811,2860,2860,0,3639781,2848,2848,0,4238154,2848,2848,0,3746299,2848,2848,0,3582366,2864,2864,0,4382424,2830,2830,64,0x7f4286e30ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131079.0,107751.0,45571.0,0.0,64,0x7f2ad94fcec0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,64,0x7f8a94e90ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2074694.0,64,0x7fe3d4124ec0,19929676,18414865,1170747,344064,2869779,0,0,163840,832.0,515150.0,0.0,524288.0,678901.0,32768.0,1079587,0,0,13692,90874.0,90874.0,0.0,90874.0,199961732860464,199961732876784 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f8012a88ec0,114688,0,32768,32768,16384,16384,65536,49152,57632606.0,194401316.0,47256923.0,131072.0,0.0,495511.0,0,0,25157,6922.0,131084.0,0.0,22.0,64,0x7f7fece10ec0,2170,4096,2170,6266,2196,4096,2196,6292,2177,4099,2180,6276,2172,4096,2172,6268,2254,4097,2255,6351,2198,4099,2201,6297,2153,4096,2153,6249,2174,4096,2174,6270,2170,4096,2170,6266,2174,4096,2174,6270,2200,4096,2200,6296,2177,4096,2177,6273,2176,4096,2176,6272,2202,4096,2202,6298,2198,4096,2198,6294,2156,4096,2156,6252,2173,4096,2173,6269,2167,4096,2167,6263,2158,4097,2159,6255,2154,4096,2154,6250,2181,4096,2181,6277,2165,4096,2165,6261,2175,4096,2175,6271,2194,4097,2195,6291,2189,4096,2189,6285,2173,4096,2173,6269,2174,4096,2174,6270,2159,4097,2160,6256,2157,4096,2157,6253,2183,4096,2183,6279,2166,4096,2166,6262,2177,4096,2177,6273,64,0x7f8e70438ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,23205,0,2664,39565,0,69837.0,131072.0,0.0,45573.0,64,0x7ff35030cec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,30520,26936,9680,2389,0,38821,200332.0,0.0,69250.0,131082.0,64,0x7f98f7dd4ec0,0,188959,0,0,65536,63800,56,1680,64,0x7f3382d3cec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65552.0,0.0,0.0,0.0,64,0x7fb474a04ec0,0,393216,163840,0,0,0,0,0,30062,0.0,0.0,0.0,32768.0,0.0,0.0,197.0,32768.0,4096,16384,302,41498,2031,0,56.0,10.0,0.0,200301.0,64,0x7f90a9bbcec0,4096,0,388,0,4096,0,28,0,4096,0,740,0,4096,0,187,0,4096,0,0,0,4096,0,278,0,4096,0,311,0,4096,0,42,0,4096,0,56,0,4096,0,936,0,4098,0,1,0,4099,0,636,0,4096,0,131,0,4096,0,1277,0,4096,0,381,0,4096,0,3,0,4096,0,107,0,4097,0,478,0,4097,0,148,0,4096,0,1099,0,4096,0,858,0,4096,0,505,0,4096,0,368,0,4096,0,2281,0,4096,0,82,0,4097,0,1,0,4096,0,1,0,4096,0,151,0,4097,0,247,0,4098,0,335,0,4096,0,498,0,4096,0,0,0,64,0x7f65ed360ec0,323336,216717,16384,0,16384,16384,32768,49152,40416,40416,3093355.0,2372241.0,3631.0,304293.0,1757267.0,0.0,2360052.0,2051749.0,323328,225731,40416,0,40416,0,1293312.0,766992.0,0.0,0.0,64,0x7fc8d388cec0,32768,32768,0,64,0x7f7bd52a0ec0,0,0,0,56,0,65536,65536,0,64,0x7fe95a08cec0,731,0,0,1945323,1560,0,0,2438847,133,0,0,2120827,3498,0,0,2635765,0,0,0,1936784,1748,0,0,2566494,314,0,0,1787260,59,0,0,2046095,0,0,0,1820194,281,0,0,1771976,27,0,0,1753515,0,0,0,1844134,1028,0,0,2331648,818,0,0,2104644,1005,0,0,2078374,668,0,0,2133213,34,0,0,1942244,138,0,0,1944518,249,0,0,1986452,1513,0,0,2296875,1265,0,0,2302691,1025,0,0,2475075,2049,0,0,2565441,212,0,0,2260746,803,0,0,2335438,0,0,0,1711706,649,0,0,2031873,1070,0,0,2115952,1283,0,0,2029529,1407,0,0,2134321,473,0,0,2089453,800,0,0,2150600,64,0x7f8da5ce4ec0,6285,0,4096,6273,0,4096,6243,0,4096,6275,0,4096,6283,0,4096,6251,0,4096,6270,0,4096,6314,0,4096,6309,0,4096,6289,0,4096,6275,0,4096,6242,0,4096,6277,0,4096,6283,0,4096,6256,0,4096,6275,0,4096,6319,0,4096,6318,0,4096,6276,0,4096,6283,0,4096,6261,0,4096,6281,0,4096,6283,0,4096,6259,0,4096,6262,0,4096,6326,0,4096,6317,0,4096,6276,0,4096,6283,0,4096,6264,0,4096,6279,0,4096,6284,0,4096,64,0x7fe9c17d0ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,120659866.0,59415420.0,0.0,64,0x7fa461318ec0,0,3248042,2840,2840,0,4491416,2876,2876,0,3529715,2852,2852,0,3365992,2872,2872,0,4157333,2872,2872,0,4344622,2828,2828,0,3326338,2860,2860,0,4526060,2824,2824,0,4197751,2824,2824,0,3396200,2840,2840,0,3667208,2876,2876,0,3541353,2852,2852,0,2942008,2868,2868,0,3693904,2882,2882,0,3878014,2828,2828,0,3703272,2860,2860,0,4026373,2800,2800,0,4312805,2844,2844,0,3339296,2872,2872,0,4300410,2864,2864,0,3773833,2840,2840,0,3680806,2880,2880,0,3721011,2820,2820,0,4519666,2812,2812,0,3389306,2808,2808,0,4268449,2796,2796,0,4590185,2848,2848,0,3665564,2876,2876,0,3600059,2868,2868,0,3340209,2844,2844,0,2859877,2876,2876,0,4227424,2824,2824,64,0x7f4286e30ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131081.0,90911.0,45585.0,0.0,64,0x7f2ad94fcec0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,64,0x7f8a94e90ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2093024.0,64,0x7fe3d4124ec0,19352365,18025139,983162,344064,2774252,0,0,163840,832.0,515136.0,0.0,524288.0,725062.0,32768.0,999100,0,0,13869,91032.0,91032.0,0.0,91032.0,199961732897264,199961732913104 diff --git a/tests/workloads/kernel_verbose_0/MI200/roofline.csv b/tests/workloads/kernel_verbose_0/MI200/roofline.csv new file mode 100644 index 0000000000..f4cc3e612c --- /dev/null +++ b/tests/workloads/kernel_verbose_0/MI200/roofline.csv @@ -0,0 +1,5 @@ +device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh +0,1388.5713,1387.9775,1389.165,5015.2139,5012.1392,5018.2886,9224.082,9223.3262,9224.8379,18052.5,18051.562,18053.438,20937.758,20877.43,20998.086,20264.014,20263.346,20264.682,170404.42,170401.03,170407.81,164866.61,164862.56,164870.66,41418.559,41418.07,41419.047,41474.844,41474.246,41475.441,166332.06,165839.12,166825 +1,1389.4777,1388.9285,1390.0269,5028.5171,5026.5938,5030.4404,9235.2178,9234.4756,9235.96,18097.75,18092.523,18102.977,20976.178,20909.389,21042.967,20293.092,20292.469,20293.715,170832.12,170828.16,170836.09,165102.62,165099.02,165106.23,41483.664,41483.043,41484.285,41542.723,41541.859,41543.586,166911.92,166908.61,166915.23 +2,1389.0422,1388.4388,1389.6456,5034.1714,5031.7939,5036.5488,9256.9932,9256.2656,9257.7207,18100.01,18099.045,18100.975,21039.893,21039.441,21040.344,20342.699,20342.092,20343.307,171059.3,171055.52,171063.08,165431.02,165426.25,165435.78,41559.031,41558.309,41559.754,41618.191,41617.215,41619.168,166881.56,166290.81,167472.31 +3,1388.8164,1388.1942,1389.4386,5033.0767,5031.8364,5034.3169,9240.877,9240.2109,9241.543,18023.621,18020.01,18027.232,21032.256,21031.824,21032.688,20313.984,20313.314,20314.654,171042.12,171037.98,171046.27,165238.38,165233.67,165243.08,41444.531,41290.031,41599.031,41588.297,41587.699,41588.895,167035.66,167033.28,167038.03 diff --git a/tests/workloads/kernel_verbose_0/MI200/sysinfo.csv b/tests/workloads/kernel_verbose_0/MI200/sysinfo.csv new file mode 100644 index 0000000000..5fbbbd2a6a --- /dev/null +++ b/tests/workloads/kernel_verbose_0/MI200/sysinfo.csv @@ -0,0 +1,2 @@ +workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd +kernel_verbose_0,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 02:43:35 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/kernel_verbose_0/MI200/timestamps.csv b/tests/workloads/kernel_verbose_0/MI200/timestamps.csv new file mode 100644 index 0000000000..4c39091298 --- /dev/null +++ b/tests/workloads/kernel_verbose_0/MI200/timestamps.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,363060,363060,1048576,256,0,0,8,0,16,64,0x0,0x7f803b148ec0,199961732731122,199961732754864,199961732775184,199961732787559 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,363060,363060,1048576,256,0,0,8,0,16,64,0x0,0x7f803b148ec0,199961732786176,199961732860464,199961732876784,199961732878270 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,363060,363060,1048576,256,0,0,8,0,16,64,0x0,0x7f803b148ec0,199961732888169,199961732897264,199961732913104,199961732914238 diff --git a/tests/workloads/kernel_verbose_1/MI100/SQ_IFETCH_LEVEL.csv b/tests/workloads/kernel_verbose_1/MI100/SQ_IFETCH_LEVEL.csv index d97bcf220b..701edf9ff4 100644 --- a/tests/workloads/kernel_verbose_1/MI100/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/kernel_verbose_1/MI100/SQ_IFETCH_LEVEL.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2894589,2894589,1048576,256,0,0,8,8,16,64,0x0,0x7f0c9229ce80,49016,49016,16384,65536,16202,2069888,2187942825014645,2187943271073379,2187943271097699,2187942832532678 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2894589,2894589,1048576,256,0,0,8,8,16,64,0x0,0x7f0c9229ce80,43367,43367,16384,65536,8347,1048576,2187942832555852,2187943271198499,2187943271217539,2187942832857148 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2894589,2894589,1048576,256,0,0,8,8,16,64,0x0,0x7f0c9229ce80,42671,42671,16384,65536,8303,1048580,2187942832889418,2187943271238819,2187943271257699,2187942833119740 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,197832,197832,1048576,256,0,0,8,8,16,64,0x0,0x7fe221dcce80,47387,47387,16384,65536,14667,1878708,194355159737813,194367370722111,194367370746271,194355167424447 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,197832,197832,1048576,256,0,0,8,8,16,64,0x0,0x7fe221dcce80,43050,43050,16384,65536,8225,1048584,194355167445587,194367370933951,194367370952671,194355167769981 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,197832,197832,1048576,256,0,0,8,8,16,64,0x0,0x7fe221dcce80,42530,42530,16384,65536,8263,1048580,194355167801541,194367370974911,194367370993791,194355167976562 diff --git a/tests/workloads/kernel_verbose_1/MI100/SQ_INST_LEVEL_LDS.csv b/tests/workloads/kernel_verbose_1/MI100/SQ_INST_LEVEL_LDS.csv index 83bb5b395f..6521ebdfb3 100644 --- a/tests/workloads/kernel_verbose_1/MI100/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/kernel_verbose_1/MI100/SQ_INST_LEVEL_LDS.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2893315,2893315,1048576,256,0,0,8,8,16,64,0x0,0x7f86213fae80,0,0,0,2187939184662374,2187943271073379,2187943271097699,2187939192221424 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2893315,2893315,1048576,256,0,0,8,8,16,64,0x0,0x7f86213fae80,0,0,0,2187939192238988,2187943271198499,2187943271217539,2187939192638708 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2893315,2893315,1048576,256,0,0,8,8,16,64,0x0,0x7f86213fae80,0,0,0,2187939192666781,2187943271238819,2187943271257699,2187939192836569 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,198017,198017,1048576,256,0,0,8,8,16,64,0x0,0x7f27260e2e80,0,0,0,194355644721069,194367370722111,194367370746271,194355652895216 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,198017,198017,1048576,256,0,0,8,8,16,64,0x0,0x7f27260e2e80,0,0,0,194355652913661,194367370933951,194367370952671,194355653353063 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,198017,198017,1048576,256,0,0,8,8,16,64,0x0,0x7f27260e2e80,0,0,0,194355653382178,194367370974911,194367370993791,194355653572268 diff --git a/tests/workloads/kernel_verbose_1/MI100/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/kernel_verbose_1/MI100/SQ_INST_LEVEL_SMEM.csv index e25ec045c9..b18aea553b 100644 --- a/tests/workloads/kernel_verbose_1/MI100/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/kernel_verbose_1/MI100/SQ_INST_LEVEL_SMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2893497,2893497,1048576,256,0,0,8,8,16,64,0x0,0x7ff4b8110e80,65536,223274,28549840,2187939636255032,2187943271073379,2187943271097699,2187939643930069 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2893497,2893497,1048576,256,0,0,8,8,16,64,0x0,0x7ff4b8110e80,65536,180564,23064920,2187939643952602,2187943271198499,2187943271217539,2187939644190599 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2893497,2893497,1048576,256,0,0,8,8,16,64,0x0,0x7ff4b8110e80,65536,183362,23399720,2187939644218771,2187943271238819,2187943271257699,2187939644394862 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,198204,198204,1048576,256,0,0,8,8,16,64,0x0,0x7f60d7434e80,65536,167008,21396328,194356143449181,194367370722111,194367370746271,194356151035335 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,198204,198204,1048576,256,0,0,8,8,16,64,0x0,0x7f60d7434e80,65536,167780,21442488,194356151053830,194367370933951,194367370952671,194356151409473 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,198204,198204,1048576,256,0,0,8,8,16,64,0x0,0x7f60d7434e80,65536,167906,21472200,194356151438879,194367370974911,194367370993791,194356151626464 diff --git a/tests/workloads/kernel_verbose_1/MI100/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/kernel_verbose_1/MI100/SQ_INST_LEVEL_VMEM.csv index 8607f1a2cd..84a1dec816 100644 --- a/tests/workloads/kernel_verbose_1/MI100/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/kernel_verbose_1/MI100/SQ_INST_LEVEL_VMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2894225,2894225,1048576,256,0,0,8,8,16,64,0x0,0x7fdd69170e80,32768,661960,84723208,2187941926304181,2187943271073379,2187943271097699,2187941933913015 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2894225,2894225,1048576,256,0,0,8,8,16,64,0x0,0x7fdd69170e80,32768,668695,85596968,2187941933931259,2187943271198499,2187943271217539,2187941934257782 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2894225,2894225,1048576,256,0,0,8,8,16,64,0x0,0x7fdd69170e80,32768,641711,82139904,2187941934286005,2187943271238819,2187943271257699,2187941934455914 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,198390,198390,1048576,256,0,0,8,8,16,64,0x0,0x7f4338698e80,32768,658286,84234268,194356645433769,194367370722111,194367370746271,194356653334939 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,198390,198390,1048576,256,0,0,8,8,16,64,0x0,0x7f4338698e80,32768,673258,86177260,194356653355528,194367370933951,194367370952671,194356653661497 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,198390,198390,1048576,256,0,0,8,8,16,64,0x0,0x7f4338698e80,32768,688731,88155632,194356653689400,194367370974911,194367370993791,194356653860985 diff --git a/tests/workloads/kernel_verbose_1/MI100/SQ_LEVEL_WAVES.csv b/tests/workloads/kernel_verbose_1/MI100/SQ_LEVEL_WAVES.csv index 0d404b0b34..ed76dacbe9 100644 --- a/tests/workloads/kernel_verbose_1/MI100/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/kernel_verbose_1/MI100/SQ_LEVEL_WAVES.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2892764,2892764,1048576,256,0,0,8,8,16,64,0x0,0x7f200e3d0e80,48606,48606,16977,388856,16384,24551813,239943,0,98695272,2187937833360708,2187943271073379,2187943271097699,2187937840982837 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2892764,2892764,1048576,256,0,0,8,8,16,64,0x0,0x7f200e3d0e80,42970,42970,13743,343768,16384,23870586,232854,0,95970168,2187937841010338,2187943271198499,2187943271217539,2187937841402735 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2892764,2892764,1048576,256,0,0,8,8,16,64,0x0,0x7f200e3d0e80,43413,43413,13274,347312,16384,23130829,231226,0,93014168,2187937841441759,2187943271238819,2187943271257699,2187937841634861 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,198575,198575,1048576,256,0,0,8,8,16,64,0x0,0x7f12a29a0e80,48960,48960,17780,391688,16384,25009693,239385,0,100519984,194357137744279,194367370722111,194367370746271,194357145390777 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,198575,198575,1048576,256,0,0,8,8,16,64,0x0,0x7f12a29a0e80,42895,42895,13804,343168,16384,24582159,231597,0,98810844,194357145421986,194367370933951,194367370952671,194357145708218 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,198575,198575,1048576,256,0,0,8,8,16,64,0x0,0x7f12a29a0e80,42679,42679,14357,341440,16384,24332023,228433,0,97816732,194357145746270,194367370974911,194367370993791,194357145934717 diff --git a/tests/workloads/kernel_verbose_1/MI100/pmc_dispatch_info.csv b/tests/workloads/kernel_verbose_1/MI100/pmc_dispatch_info.csv new file mode 100644 index 0000000000..17300ae9af --- /dev/null +++ b/tests/workloads/kernel_verbose_1/MI100/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) ",2 +1,"vecCopy(double*, double*, double*, int, int) ",2 +2,"vecCopy(double*, double*, double*, int, int) ",2 diff --git a/tests/workloads/kernel_verbose_1/MI100/pmc_perf.csv b/tests/workloads/kernel_verbose_1/MI100/pmc_perf.csv index 70d8fd56ad..77b20a63ca 100644 --- a/tests/workloads/kernel_verbose_1/MI100/pmc_perf.csv +++ b/tests/workloads/kernel_verbose_1/MI100/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_1,obj_1,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_2,obj_2,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_3,obj_3,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_4,obj_4,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_5,obj_5,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_6,obj_6,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_7,obj_7,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_8,obj_8,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_9,obj_9,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_10,obj_10,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_11,obj_11,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_12,obj_12,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_13,obj_13,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_14,obj_14,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_15,obj_15,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_16,obj_16,TCC_EA_ATOMIC_LEVEL_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fa1427fce80,0,3878725,4096,4096,0,4103994,4096,4096,0,3748355,4096,4096,0,3797819,4096,4096,0,3878923,4096,4096,0,3780268,4096,4096,0,4067104,4096,4096,0,4102862,4096,4096,0,3684344,4096,4096,0,5017328,4096,4096,0,4849838,4096,4096,0,4606563,4096,4096,0,2843411,4096,4096,0,3669854,4096,4096,0,4122786,4096,4096,0,3692928,4096,4096,0,3975208,4096,4096,0,5246071,4096,4096,0,4837605,4096,4096,0,5063441,4096,4096,0,3275576,4096,4096,0,3660812,4096,4096,0,3560743,4096,4096,0,4717799,4096,4096,0,3593196,4096,4096,0,3448332,4096,4096,0,3556395,4096,4096,0,2943212,4096,4096,0,4028854,4096,4096,0,3432132,4096,4096,0,3456849,4096,4096,0,3304151,4096,4096,64,0x7f67fc0e0e80,0,47267,0,0,0,47267,0,0,0,47267,0,0,0,47267,0,0,0,47267,0,0,0,47267,0,0,0,47267,0,0,0,47267,0,0,0,47267,0,0,0,47267,0,0,0,47267,0,0,0,47267,0,0,0,47267,0,0,0,47267,0,0,0,47267,0,0,0,47267,0,0,0,47267,0,0,0,47267,0,0,0,47267,0,0,0,47267,0,0,0,47267,0,0,0,47267,0,0,0,47267,0,0,0,47267,0,0,0,47267,0,0,0,47267,0,0,0,47267,0,0,0,47267,0,0,0,47267,0,0,0,47267,0,0,0,47267,0,0,0,47267,0,0,64,0x7f58d6496e80,171144,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,11073,27457,10001,550,0,48037,262691.0,0.0,188.0,262503.0,64,0x7fb6b8cd8e80,32768,0,0,0,16384,16384,393216,22342173,960.0,513969.0,0.0,524288.0,994552.0,32768.0,0,0,0,16591,131072.0,131072.0,0.0,131072.0,64,0x7fd27dddce80,8192,0,4096,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f989f5ece80,131072.0,131072.0,0.0,2263915.0,0.0,0.0,110282773.0,63143117.0,64,0x7f2f9a21ae80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,69777.0,135995.0,64,0x7f133e226e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,87017.0,44055.0,131112.0,0.0,64,0x7f5f9af14e80,2299913,360448,163840,0,0,180224,114688,0,69500298.0,173495453.0,73156049.0,131072.0,0.0,561985.0,0,0,26201,72246.0,0.0,0.0,72246.0,64,0x7f527e452e80,394800,245008,3586455,16384,26864125,144,48,0,49349,49349,4027696.0,3098693.0,5214.0,1011051.0,2213701.0,0.0,3088540.0,2778272.0,393279,254942,49349,0,49349,0,1579168.0,968348.0,0.0,0.0,64,0x7f81736bce80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131340.0,0.0,528.0,131339.0,64,0x7fd1b5a42e80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8312,4216,8312,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,141,8195,4240,8336,0,8192,4096,8192,47,8193,4144,8240,64,0x7f85a3448e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,47372,0,131528.0,131072.0,0.0,131104.0,64,0x7f7e31e62e80,1832,0,0,1838741,2571,0,0,1912474,3421,0,0,1997215,2534,0,0,1827649,2082,0,0,1823999,2379,0,0,1799530,5072,0,0,2220534,3380,0,0,1988286,1897,0,0,1848333,2837,0,0,1895637,2052,0,0,1848880,2788,0,0,1971805,2126,0,0,1797201,1963,0,0,1833184,2157,0,0,1875975,2679,0,0,1907076,3523,0,0,1988854,1455,0,0,1733155,4048,0,0,2088227,3015,0,0,1900036,1055,0,0,1677942,2765,0,0,1950987,3432,0,0,1985265,3488,0,0,1964706,3577,0,0,2000111,1458,0,0,1700260,5000,0,0,2128429,3984,0,0,1999890,5387,0,0,2120325,3221,0,0,1987919,4378,0,0,2127532,2696,0,0,1965941,64,0x7f0565a1ee80,4096,0,1447,0,4096,0,0,0,4096,0,3191,0,4099,0,0,0,4096,0,458,0,4096,0,423,0,4096,0,3597,0,4096,0,3839,0,4096,0,341,0,4096,0,6415,0,4096,0,440,0,4096,0,7837,0,4096,0,0,0,4096,0,541,0,4096,0,3461,0,4096,0,0,0,4096,0,120,0,4096,0,858,0,4096,0,2265,0,4216,0,319,0,4096,0,66,0,4096,0,171,0,4096,0,1804,0,4096,0,0,0,4096,0,265,0,4096,0,575,0,4096,0,1235,0,4192,0,3049,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4098,0,3501,0,64,0x7fcf21906e80,0,0,192,0,65536,64503,48,1317,31071,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,538,47163,1764,0,48.0,216.0,0.0,262288.0,64,0x7fd968430e80,0.0,2187943271073379,2187943271097699 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fa1427fce80,0,4918468,2696,2696,0,3890284,2716,2716,0,3993520,2676,2676,0,3975815,2706,2706,0,3375759,2668,2668,0,3862020,2714,2714,0,3850765,2699,2699,0,4657132,2714,2714,0,4715993,2698,2698,0,3958542,2668,2668,0,4790673,2714,2714,0,4138870,2734,2734,0,3419283,2706,2706,0,4144043,2696,2696,0,4397625,2694,2694,0,4083127,2686,2686,0,3154116,2684,2684,0,5243872,2712,2712,0,3474870,2690,2690,0,4406086,2716,2716,0,3752698,2704,2704,0,3056551,2737,2737,0,3729826,2676,2676,0,3437864,2685,2685,0,3132211,2672,2672,0,5022079,2680,2680,0,4320846,2722,2722,0,3567005,2714,2714,0,4382236,2714,2714,0,3257045,2707,2707,0,4143306,2719,2719,0,3386945,2704,2704,64,0x7f67fc0e0e80,0,43225,0,0,0,43225,0,0,0,43225,0,0,0,43225,0,0,0,43225,0,0,0,43225,0,0,0,43225,0,0,0,43225,0,0,0,43225,0,0,0,43225,0,0,0,43225,0,0,0,43225,0,0,0,43225,0,0,0,43225,0,0,0,43225,0,0,0,43225,0,0,0,43225,0,0,0,43225,0,0,0,43225,0,0,0,43225,0,0,0,43225,0,0,0,43225,0,0,0,43225,0,0,0,43225,0,0,0,43225,0,0,0,43225,0,0,0,43225,0,0,0,43225,0,0,0,43225,0,0,0,43225,0,0,0,43225,0,0,0,43225,0,0,64,0x7f58d6496e80,188004,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,11834,28218,8563,3270,0,41541,262554.0,0.0,47.0,262507.0,64,0x7fb6b8cd8e80,32768,0,0,0,16384,16384,393216,22688322,960.0,514030.0,0.0,524288.0,909941.0,32768.0,0,0,0,13020,86652.0,86652.0,0.0,86652.0,64,0x7fd27dddce80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f989f5ece80,131072.0,131072.0,0.0,2579851.0,0.0,0.0,102780109.0,31303553.0,64,0x7f2f9a21ae80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,48192.0,122001.0,64,0x7f133e226e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86688.0,0.0,131110.0,0.0,64,0x7f5f9af14e80,1714840,360448,163840,0,0,180224,114688,0,71540552.0,197113942.0,77080583.0,131072.0,0.0,605267.0,0,0,25715,66781.0,0.0,0.0,66781.0,64,0x7f527e452e80,349624,236434,3478250,16384,25323983,0,48,0,43702,43702,3835936.0,3104356.0,6681.0,950371.0,2086776.0,0.0,3093919.0,2783281.0,349616,245687,43702,0,43702,0,1398464.0,822274.0,0.0,0.0,64,0x7f81736bce80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131347.0,0.0,548.0,131346.0,64,0x7fd1b5a42e80,0,8194,4098,8194,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8312,4216,8312,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8195,4099,8195,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,64,0x7f85a3448e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,240.0,524288.0,0.0,0.0,0,0,5240,42207,1066,131557.0,131072.0,0.0,86653.0,64,0x7f7e31e62e80,3429,0,0,1660463,940,0,0,1403464,989,0,0,1298807,1573,0,0,1466149,668,0,0,1289601,116,0,0,1165810,1029,0,0,1361279,2123,0,0,1510575,1453,0,0,1450236,539,0,0,1255471,1298,0,0,1422329,1292,0,0,1394874,1628,0,0,1483064,733,0,0,1251835,496,0,0,1260705,3935,0,0,1718403,759,0,0,1405936,902,0,0,1401475,1581,0,0,1471398,3532,0,0,1674710,4232,0,0,1760350,5244,0,0,1859699,718,0,0,1321109,1755,0,0,1439483,1442,0,0,1392420,2078,0,0,1514953,928,0,0,1325711,3270,0,0,1619775,837,0,0,1363664,6018,0,0,1872100,1052,0,0,1312896,815,0,0,1344047,64,0x7f0565a1ee80,4096,0,826,0,4096,0,4971,0,4096,0,497,0,4096,0,967,0,4096,0,7753,0,4096,0,2081,0,4096,0,562,0,4096,0,1366,0,4096,0,2781,0,4096,0,337,0,4096,0,1592,0,4096,0,2448,0,4097,0,1518,0,4096,0,3602,0,4096,0,266,0,4096,0,589,0,4097,0,1791,0,4096,0,4248,0,4096,0,2125,0,4216,0,6793,0,4096,0,525,0,4096,0,1111,0,4096,0,422,0,4096,0,4902,0,4096,0,0,0,4096,0,1182,0,4096,0,838,0,4192,0,737,0,4096,0,0,0,4096,0,165,0,4101,0,193,0,4097,0,474,0,64,0x7fcf21906e80,0,0,48,0,65536,65536,0,0,29880,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,458,41649,1710,0,48.0,223.0,0.0,262144.0,64,0x7fd968430e80,0.0,2187943271198499,2187943271217539 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fa1427fce80,0,3878771,2752,2752,0,3523856,2708,2708,0,4606824,2670,2670,0,3368124,2692,2692,0,4756627,2708,2708,0,3057583,2724,2724,0,3215981,2728,2728,0,3806523,2682,2682,0,3308417,2732,2732,0,3333847,2704,2704,0,4271198,2716,2716,0,3497868,2720,2720,0,3437606,2732,2732,0,3309715,2688,2688,0,3274018,2686,2686,0,3369647,2684,2684,0,3089325,2720,2720,0,4977073,2701,2701,0,3894272,2680,2680,0,3848435,2714,2714,0,3611568,2732,2732,0,4051064,2752,2752,0,4247845,2724,2724,0,3317314,2668,2668,0,3104254,2718,2718,0,3676488,2680,2680,0,3294363,2748,2748,0,3057865,2674,2674,0,3460285,2736,2736,0,3545133,2714,2714,0,4584786,2720,2720,0,3227289,2658,2658,64,0x7f67fc0e0e80,0,42616,0,0,0,42616,0,0,0,42616,0,0,0,42616,0,0,0,42616,0,0,0,42616,0,0,0,42616,0,0,0,42616,0,0,0,42616,0,0,0,42616,0,0,0,42616,0,0,0,42616,0,0,0,42616,0,0,0,42616,0,0,0,42616,0,0,0,42616,0,0,0,42616,0,0,0,42616,0,0,0,42616,0,0,0,42616,0,0,0,42616,0,0,0,42616,0,0,0,42616,0,0,0,42616,0,0,0,42616,0,0,0,42616,0,0,0,42616,0,0,0,42616,0,0,0,42616,0,0,0,42616,0,0,0,42616,0,0,0,42616,0,0,64,0x7f58d6496e80,186079,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,11355,27739,8556,3714,0,42119,262542.0,0.0,47.0,262495.0,64,0x7fb6b8cd8e80,32768,0,0,0,16384,16384,393216,21962973,960.0,513958.0,0.0,524288.0,1155379.0,32768.0,0,0,0,13675,86855.0,86855.0,0.0,86855.0,64,0x7fd27dddce80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f989f5ece80,131072.0,131072.0,0.0,2352325.0,0.0,0.0,126352442.0,52021838.0,64,0x7f2f9a21ae80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,66644.0,138028.0,64,0x7f133e226e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86297.0,0.0,131112.0,0.0,64,0x7f5f9af14e80,2113987,360448,163840,0,0,180224,114688,0,66089601.0,176452209.0,75511968.0,131072.0,0.0,498972.0,0,0,26052,87866.0,0.0,0.0,87866.0,64,0x7f527e452e80,342280,228407,3332525,16384,24446733,0,48,0,42784,42784,3715949.0,3000643.0,8016.0,1284027.0,2083238.0,0.0,2991277.0,2679534.0,342272,238081,42784,0,42784,0,1369088.0,808240.0,0.0,0.0,64,0x7f81736bce80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131343.0,0.0,540.0,131342.0,64,0x7fd1b5a42e80,0,8194,4098,8194,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8312,4216,8312,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8198,4102,8198,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8195,4099,8195,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,64,0x7f85a3448e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,2759,39416,0,131388.0,131072.0,0.0,86618.0,64,0x7f7e31e62e80,610,0,0,1294455,1251,0,0,1318285,505,0,0,1286846,1544,0,0,1403768,95,0,0,1150966,1207,0,0,1304802,1306,0,0,1407656,2254,0,0,1502537,878,0,0,1300605,1190,0,0,1330596,3067,0,0,1579789,1599,0,0,1445184,642,0,0,1311476,863,0,0,1325861,456,0,0,1316738,4983,0,0,1758107,771,0,0,1304559,861,0,0,1313149,2615,0,0,1576439,928,0,0,1312032,5196,0,0,1799192,340,0,0,1150650,927,0,0,1327074,1642,0,0,1389385,1849,0,0,1416122,3959,0,0,1613856,1590,0,0,1373782,3544,0,0,1629172,2096,0,0,1464078,3246,0,0,1661032,1111,0,0,1356935,1004,0,0,1363389,64,0x7f0565a1ee80,4096,0,1011,0,4096,0,590,0,4096,0,2391,0,4096,0,1295,0,4096,0,2350,0,4096,0,405,0,4096,0,1217,0,4096,0,1423,0,4096,0,6368,0,4096,0,688,0,4096,0,2356,0,4096,0,1447,0,4097,0,7135,0,4096,0,956,0,4096,0,966,0,4096,0,1779,0,4097,0,625,0,4096,0,1725,0,4096,0,988,0,4216,0,4372,0,4096,0,1658,0,4096,0,449,0,4096,0,767,0,4096,0,598,0,4096,0,1287,0,4096,0,6367,0,4096,0,1604,0,4192,0,768,0,4096,0,670,0,4096,0,744,0,4101,0,101,0,4099,0,436,0,64,0x7fcf21906e80,0,0,48,0,65536,65536,0,0,30008,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,458,41764,1768,0,48.0,223.0,0.0,262144.0,64,0x7fd968430e80,0.0,2187943271238819,2187943271257699 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCC_EA_ATOMIC_LEVEL_sum,wave_size_1,obj_1,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_2,obj_2,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_3,obj_3,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_4,obj_4,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_5,obj_5,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_6,obj_6,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_7,obj_7,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_8,obj_8,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_9,obj_9,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_10,obj_10,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_11,obj_11,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_12,obj_12,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_13,obj_13,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_14,obj_14,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_15,obj_15,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_16,obj_16,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f7413ddce80,0.0,64,0x7f04b75cce80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86375.0,44697.0,131111.0,0.0,64,0x7f456805ce80,0,4192108,4096,4096,0,3817704,4096,4096,0,4759466,4096,4096,0,4107810,4096,4096,0,4790901,4096,4096,0,3195663,4096,4096,0,4439894,4096,4096,0,3392732,4096,4096,0,4218702,4096,4096,0,3296409,4096,4096,0,4509910,4096,4096,0,4058330,4096,4096,0,3380081,4096,4096,0,3311906,4096,4096,0,4910040,4096,4096,0,5162718,4096,4096,0,4789162,4096,4096,0,5164560,4096,4096,0,4770121,4096,4096,0,4754320,4096,4096,0,4026595,4096,4096,0,3446956,4096,4096,0,4606073,4096,4096,0,2978295,4096,4096,0,4365011,4096,4096,0,3293260,4096,4096,0,4472168,4096,4096,0,2455749,4096,4096,0,4345395,4096,4096,0,2915389,4096,4096,0,4204587,4096,4096,0,4056589,4096,4096,64,0x7f64d8c44e80,2263271,360448,163840,0,0,180224,114688,0,69526984.0,194355108.0,76807015.0,131072.0,0.0,596818.0,0,0,26073,76677.0,0.0,0.0,76677.0,64,0x7f79ddbace80,32768,0,0,0,16384,16384,393216,22869483,960.0,513946.0,0.0,524288.0,911169.0,32768.0,0,0,0,17344,131072.0,131072.0,0.0,131072.0,64,0x7f358e54ee80,0,0,192,0,65536,64522,48,1351,32220,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,539,48268,1668,0,48.0,303.0,0.0,262288.0,64,0x7fda121dce80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,47706,0,131488.0,131072.0,0.0,131104.0,64,0x7f8aa888ee80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,52045.0,127706.0,64,0x7fc4e07dce80,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fd199caee80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131318.0,0.0,484.0,131317.0,64,0x7f1d50fa2e80,4096,0,1673,0,4097,0,21,0,4099,0,1012,0,4096,0,1493,0,4096,0,174,0,4096,0,777,0,4096,0,2456,0,4096,0,6414,0,4096,0,3136,0,4096,0,95,0,4144,0,3210,0,4096,0,204,0,4096,0,219,0,4096,0,995,0,4096,0,2513,0,4096,0,205,0,4144,0,544,0,4096,0,397,0,4096,0,2663,0,4096,0,299,0,4096,0,501,0,4096,0,241,0,4096,0,1098,0,4096,0,101,0,4096,0,1030,0,4096,0,430,0,4096,0,74,0,4096,0,106,0,4096,0,69,0,4096,0,53,0,4265,0,2772,0,4096,0,3479,0,64,0x7f23ec544e80,131072.0,131072.0,0.0,2540068.0,0.0,0.0,126437381.0,61078005.0,64,0x7f785810ae80,1764,0,0,1895876,1569,0,0,1804049,1362,0,0,1829121,1900,0,0,1752756,2775,0,0,1964520,842,0,0,1575968,1863,0,0,1774296,1077,0,0,1660955,679,0,0,1588916,1304,0,0,1791103,4201,0,0,2117997,404,0,0,1520859,999,0,0,1709730,866,0,0,1613585,931,0,0,1680020,5637,0,0,2179901,3462,0,0,2031318,582,0,0,1625413,1568,0,0,1741736,371,0,0,1575750,1970,0,0,1744447,835,0,0,1670421,1850,0,0,1873930,902,0,0,1551335,692,0,0,1659834,619,0,0,1510890,2123,0,0,1815210,1486,0,0,1674237,916,0,0,1604129,1135,0,0,1680935,2334,0,0,1953579,680,0,0,1567243,64,0x7fd731586e80,186379,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,14010,30394,9854,550,0,47013,262624.0,0.0,188.0,262436.0,64,0x7f3a59806e80,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,64,0x7fb08e9c8e80,0,8192,4096,8192,0,8192,4096,8192,141,8243,4288,8384,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8312,4216,8312,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8315,4219,8315,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7fbbb9930e80,384168,233587,3418191,16384,25170789,144,48,0,48020,48020,3856166.0,3031473.0,6288.0,877839.0,2052891.0,0.0,3022741.0,2712888.0,382847,243520,48020,0,48020,0,1536640.0,969767.0,0.0,0.0,194367370722111,194367370746271 +1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f7413ddce80,0.0,64,0x7f04b75cce80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,85883.0,43666.0,129642.0,0.0,64,0x7f456805ce80,0,4216950,2692,2692,0,4206195,2724,2724,0,3588452,2684,2684,0,3845148,2716,2716,0,4168997,2696,2696,0,3352134,2718,2718,0,4371773,2736,2736,0,5281250,2708,2708,0,3459629,2699,2699,0,3820986,2673,2673,0,4141290,2718,2718,0,4881147,2724,2724,0,5037167,2702,2702,0,3102761,2685,2685,0,5181847,2714,2714,0,3285064,2704,2704,0,3833234,2676,2676,0,4253007,2706,2706,0,4152958,2708,2708,0,4995761,2708,2708,0,4401476,2696,2696,0,3819813,2730,2730,0,4286935,2720,2720,0,3787683,2688,2688,0,3397335,2666,2666,0,3873191,2682,2682,0,3142739,2752,2752,0,4554698,2696,2696,0,3945155,2704,2704,0,3818305,2706,2706,0,4285789,2716,2716,0,3694683,2705,2705,64,0x7f64d8c44e80,2101626,360448,163840,0,0,180224,114688,0,69886382.0,200025255.0,79222327.0,131072.0,0.0,592328.0,0,0,25822,68552.0,0.0,0.0,68552.0,64,0x7f79ddbace80,32768,0,0,0,16384,16384,393216,22318518,0.0,524288.0,0.0,524288.0,774010.0,32768.0,0,0,0,12098,86514.0,86514.0,0.0,86514.0,64,0x7f358e54ee80,0,0,48,0,65536,65536,0,0,30395,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,481,45124,3914,0,48.0,294.0,0.0,262144.0,64,0x7fda121dce80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,2792,39547,0,131359.0,131072.0,0.0,86688.0,64,0x7f8aa888ee80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,27849.0,111017.0,64,0x7fc4e07dce80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fd199caee80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131378.0,0.0,610.0,131377.0,64,0x7f1d50fa2e80,4096,0,3731,0,4097,0,2282,0,4096,0,1624,0,4096,0,1348,0,4096,0,1918,0,4096,0,2408,0,4096,0,811,0,4096,0,4156,0,4096,0,373,0,4096,0,978,0,4144,0,1371,0,4096,0,2643,0,4096,0,6733,0,4096,0,442,0,4096,0,1751,0,4096,0,425,0,4144,0,5050,0,4096,0,5406,0,4096,0,559,0,4096,0,346,0,4097,0,819,0,4096,0,3904,0,4096,0,642,0,4099,0,131,0,4096,0,666,0,4096,0,1059,0,4096,0,161,0,4097,0,4238,0,4096,0,447,0,4096,0,252,0,4263,0,1769,0,4096,0,363,0,64,0x7f23ec544e80,131072.0,131072.0,0.0,2685982.0,0.0,0.0,118623100.0,48409523.0,64,0x7f785810ae80,2773,0,0,1497824,3187,0,0,1588319,4089,0,0,1710491,3475,0,0,1650544,1968,0,0,1419914,2031,0,0,1463899,1673,0,0,1456764,3489,0,0,1682358,1154,0,0,1331657,1421,0,0,1391184,1119,0,0,1453064,1556,0,0,1467704,1324,0,0,1365971,2780,0,0,1555220,915,0,0,1350863,6037,0,0,1795936,2640,0,0,1481325,483,0,0,1255589,1145,0,0,1347347,2195,0,0,1555327,1418,0,0,1415848,3584,0,0,1629478,2265,0,0,1576474,4100,0,0,1703274,3017,0,0,1569810,872,0,0,1328952,1207,0,0,1360828,4425,0,0,1664706,2120,0,0,1414380,4190,0,0,1688824,2335,0,0,1483704,1956,0,0,1503244,64,0x7fd731586e80,184762,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13305,29689,8566,2357,0,41715,262483.0,0.0,47.0,262436.0,64,0x7f3a59806e80,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,64,0x7fb08e9c8e80,0,8192,4096,8192,0,8193,4097,8193,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8312,4216,8312,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8195,4099,8195,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8317,4221,8317,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7fbbb9930e80,351848,243417,3516962,16384,25880136,0,48,0,43980,43980,3940726.0,3170074.0,5255.0,1208458.0,2347503.0,0.0,3159784.0,2847676.0,351840,252679,43980,0,43980,0,1407360.0,855829.0,0.0,0.0,194367370933951,194367370952671 +2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f7413ddce80,0.0,64,0x7f04b75cce80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86753.0,0.0,131112.0,0.0,64,0x7f456805ce80,0,2451006,2682,2682,0,3387605,2738,2738,0,3548623,2662,2662,0,5319404,2720,2720,0,3217638,2636,2636,0,3168710,2760,2760,0,3421453,2712,2712,0,5429104,2732,2732,0,3881526,2674,2674,0,3120021,2695,2695,0,3343738,2710,2710,0,3570785,2746,2746,0,2901259,2680,2680,0,3543947,2715,2715,0,3756849,2704,2704,0,3430709,2704,2704,0,3193338,2666,2666,0,4440514,2724,2724,0,3381381,2684,2684,0,3653592,2719,2719,0,3610677,2703,2703,0,3645702,2785,2785,0,2610785,2698,2698,0,2329664,2680,2680,0,2726438,2656,2656,0,3630648,2748,2748,0,2851579,2732,2732,0,2992685,2700,2700,0,2694386,2668,2668,0,3347992,2720,2720,0,4324088,2734,2734,0,4465578,2690,2690,64,0x7f64d8c44e80,1992543,360448,163840,0,0,180224,114688,0,68926929.0,192250366.0,78109110.0,131072.0,0.0,570329.0,0,0,25394,51597.0,0.0,0.0,51597.0,64,0x7f79ddbace80,32768,0,0,0,16384,16384,393216,22662855,960.0,513954.0,0.0,524288.0,984036.0,32768.0,0,0,0,15337,86466.0,86466.0,0.0,86466.0,64,0x7f358e54ee80,0,0,48,0,65536,65536,0,0,30776,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,458,42053,1700,0,48.0,312.0,0.0,262144.0,64,0x7fda121dce80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,2771,39262,0,131356.0,131072.0,0.0,86473.0,64,0x7f8aa888ee80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,70894.0,139631.0,64,0x7fc4e07dce80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fd199caee80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131331.0,0.0,516.0,131330.0,64,0x7f1d50fa2e80,4096,0,1101,0,4097,0,3653,0,4096,0,1121,0,4096,0,727,0,4096,0,91,0,4096,0,4912,0,4096,0,3204,0,4096,0,1781,0,4096,0,2125,0,4096,0,0,0,4144,0,3678,0,4096,0,5951,0,4096,0,3209,0,4096,0,614,0,4096,0,6105,0,4096,0,215,0,4144,0,561,0,4096,0,1575,0,4096,0,2240,0,4096,0,685,0,4097,0,1941,0,4096,0,0,0,4096,0,5466,0,4099,0,1263,0,4096,0,5330,0,4096,0,1033,0,4096,0,1242,0,4097,0,922,0,4096,0,1359,0,4096,0,0,0,4249,0,2522,0,4096,0,1290,0,64,0x7f23ec544e80,131072.0,131072.0,0.0,2556858.0,0.0,0.0,121470381.0,48575777.0,64,0x7f785810ae80,1595,0,0,1374521,4687,0,0,1738220,1796,0,0,1388251,1881,0,0,1408386,1600,0,0,1411979,2396,0,0,1572015,721,0,0,1266501,1397,0,0,1423876,636,0,0,1312876,3380,0,0,1679604,379,0,0,1366359,1193,0,0,1404105,434,0,0,1272968,804,0,0,1339086,311,0,0,1246690,5414,0,0,1840197,1559,0,0,1340295,1210,0,0,1372430,1359,0,0,1406959,1159,0,0,1402329,770,0,0,1289463,4008,0,0,1663495,800,0,0,1320403,3753,0,0,1674779,1296,0,0,1366792,1433,0,0,1487244,355,0,0,1189678,3686,0,0,1645120,612,0,0,1240993,1469,0,0,1494455,555,0,0,1275442,2954,0,0,1541587,64,0x7fd731586e80,103057,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13054,29438,8438,2816,0,41461,262572.0,0.0,47.0,262525.0,64,0x7f3a59806e80,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,64,0x7fb08e9c8e80,0,8192,4096,8192,0,8193,4097,8193,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8312,4216,8312,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8195,4099,8195,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8317,4221,8317,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7fbbb9930e80,339352,230354,3340348,16384,24150798,0,48,0,42418,42418,3744972.0,3060409.0,5587.0,1010398.0,2102076.0,0.0,3050755.0,2740530.0,339344,239875,42418,0,42418,0,1357376.0,817781.0,0.0,0.0,194367370974911,194367370993791 diff --git a/tests/workloads/kernel_verbose_1/MI100/sysinfo.csv b/tests/workloads/kernel_verbose_1/MI100/sysinfo.csv index 1ef72165af..5cd2292750 100644 --- a/tests/workloads/kernel_verbose_1/MI100/sysinfo.csv +++ b/tests/workloads/kernel_verbose_1/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -kernel_verbose_1,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Fri Mar 1 16:47:28 2024 (CST),1,t006-003.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651240,,5.7.1-98,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +kernel_verbose_1,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 07 Mar 2024 01:10:20 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/kernel_verbose_1/MI100/timestamps.csv b/tests/workloads/kernel_verbose_1/MI100/timestamps.csv index 6ecd168ab8..3e6798f8fe 100644 --- a/tests/workloads/kernel_verbose_1/MI100/timestamps.csv +++ b/tests/workloads/kernel_verbose_1/MI100/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,2894771,2894771,1048576,256,0,0,8,8,16,64,0x0,0x7f57b6650e80,2187943271043418,2187943271073379,2187943271097699,2187943271110594 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,2894771,2894771,1048576,256,0,0,8,8,16,64,0x0,0x7f57b6650e80,2187943271110264,2187943271198499,2187943271217539,2187943271218416 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,2894771,2894771,1048576,256,0,0,8,8,16,64,0x0,0x7f57b6650e80,2187943271229207,2187943271238819,2187943271257699,2187943271258411 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,201908,201908,1048576,256,0,0,8,8,16,64,0x0,0x7f0fe9074e80,194367370695532,194367370722111,194367370746271,194367370760986 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,201908,201908,1048576,256,0,0,8,8,16,64,0x0,0x7f0fe9074e80,194367370758892,194367370933951,194367370952671,194367370953881 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,201908,201908,1048576,256,0,0,8,8,16,64,0x0,0x7f0fe9074e80,194367370964872,194367370974911,194367370993791,194367370994929 diff --git a/tests/workloads/kernel_verbose_1/MI200/SQ_IFETCH_LEVEL.csv b/tests/workloads/kernel_verbose_1/MI200/SQ_IFETCH_LEVEL.csv new file mode 100644 index 0000000000..bd6503d226 --- /dev/null +++ b/tests/workloads/kernel_verbose_1/MI200/SQ_IFETCH_LEVEL.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,363460,363460,1048576,256,0,0,8,0,16,64,0x0,0x7ff22c994ec0,27703,27703,16384,65536,13404,1537372,200055078848242,200067979162338,200067979182178,200055094559183 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,363460,363460,1048576,256,0,0,8,0,16,64,0x0,0x7ff22c994ec0,40119,40119,16384,65536,9550,1048624,200055094579321,200067979273538,200067979290178,200055094882795 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,363460,363460,1048576,256,0,0,8,0,16,64,0x0,0x7ff22c994ec0,42479,42479,16384,65536,9234,1048768,200055094912260,200067979310018,200067979325698,200055095070179 diff --git a/tests/workloads/kernel_verbose_1/MI200/SQ_INST_LEVEL_LDS.csv b/tests/workloads/kernel_verbose_1/MI200/SQ_INST_LEVEL_LDS.csv new file mode 100644 index 0000000000..6be79d2404 --- /dev/null +++ b/tests/workloads/kernel_verbose_1/MI200/SQ_INST_LEVEL_LDS.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,363661,363661,1048576,256,0,0,8,0,16,64,0x0,0x7f3124730ec0,0,0,0,200055561500194,200067979162338,200067979182178,200055577369855 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,363661,363661,1048576,256,0,0,8,0,16,64,0x0,0x7f3124730ec0,0,0,0,200055577387589,200067979273538,200067979290178,200055577688568 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,363661,363661,1048576,256,0,0,8,0,16,64,0x0,0x7f3124730ec0,0,0,0,200055577714908,200067979310018,200067979325698,200055577867657 diff --git a/tests/workloads/kernel_verbose_1/MI200/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/kernel_verbose_1/MI200/SQ_INST_LEVEL_SMEM.csv new file mode 100644 index 0000000000..260b14abf4 --- /dev/null +++ b/tests/workloads/kernel_verbose_1/MI200/SQ_INST_LEVEL_SMEM.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,363848,363848,1048576,256,0,0,8,0,16,64,0x0,0x7f2fbd3c8ec0,65536,169366,19139736,200056043039793,200067979162338,200067979182178,200056058877453 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,363848,363848,1048576,256,0,0,8,0,16,64,0x0,0x7f2fbd3c8ec0,65536,225964,25370840,200056058896139,200067979273538,200067979290178,200056059202949 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,363848,363848,1048576,256,0,0,8,0,16,64,0x0,0x7f2fbd3c8ec0,65536,292244,32717160,200056059229198,200067979310018,200067979325698,200056059383340 diff --git a/tests/workloads/kernel_verbose_1/MI200/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/kernel_verbose_1/MI200/SQ_INST_LEVEL_VMEM.csv new file mode 100644 index 0000000000..d1d30cf4f2 --- /dev/null +++ b/tests/workloads/kernel_verbose_1/MI200/SQ_INST_LEVEL_VMEM.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,364036,364036,1048576,256,0,0,8,0,16,64,0x0,0x7f9afaf64ec0,32768,296309,33183028,200056531297830,200067979162338,200067979182178,200056547311183 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,364036,364036,1048576,256,0,0,8,0,16,64,0x0,0x7f9afaf64ec0,32768,573512,64241388,200056547331662,200067979273538,200067979290178,200056547590842 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,364036,364036,1048576,256,0,0,8,0,16,64,0x0,0x7f9afaf64ec0,32768,580962,65069524,200056547616591,200067979310018,200067979325698,200056547773858 diff --git a/tests/workloads/kernel_verbose_1/MI200/SQ_LEVEL_WAVES.csv b/tests/workloads/kernel_verbose_1/MI200/SQ_LEVEL_WAVES.csv new file mode 100644 index 0000000000..37bc72388c --- /dev/null +++ b/tests/workloads/kernel_verbose_1/MI200/SQ_LEVEL_WAVES.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,364221,364221,1048576,256,0,0,8,0,16,64,0x0,0x7fcf1d938ec0,28004,28004,11221,224040,16384,10685818,128439,0,43260548,200057011816670,200067979162338,200067979182178,200057027542399 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,364221,364221,1048576,256,0,0,8,0,16,64,0x0,0x7fcf1d938ec0,40208,40208,12845,321672,16384,18938324,218514,0,76234636,200057027570592,200067979273538,200067979290178,200057027850292 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,364221,364221,1048576,256,0,0,8,0,16,64,0x0,0x7fcf1d938ec0,40263,40263,12057,322112,16384,19286850,220562,0,77628096,200057027885588,200067979310018,200067979325698,200057028049158 diff --git a/tests/workloads/kernel_verbose_1/MI200/perfmon/SQ_IFETCH_LEVEL.txt b/tests/workloads/kernel_verbose_1/MI200/perfmon/SQ_IFETCH_LEVEL.txt new file mode 100644 index 0000000000..293092f641 --- /dev/null +++ b/tests/workloads/kernel_verbose_1/MI200/perfmon/SQ_IFETCH_LEVEL.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_1/MI200/perfmon/SQ_INST_LEVEL_LDS.txt b/tests/workloads/kernel_verbose_1/MI200/perfmon/SQ_INST_LEVEL_LDS.txt new file mode 100644 index 0000000000..08439eedce --- /dev/null +++ b/tests/workloads/kernel_verbose_1/MI200/perfmon/SQ_INST_LEVEL_LDS.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_1/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt b/tests/workloads/kernel_verbose_1/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt new file mode 100644 index 0000000000..6cca322d4e --- /dev/null +++ b/tests/workloads/kernel_verbose_1/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_1/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt b/tests/workloads/kernel_verbose_1/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt new file mode 100644 index 0000000000..e527ad31ba --- /dev/null +++ b/tests/workloads/kernel_verbose_1/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_1/MI200/perfmon/SQ_LEVEL_WAVES.txt b/tests/workloads/kernel_verbose_1/MI200/perfmon/SQ_LEVEL_WAVES.txt new file mode 100644 index 0000000000..3f8e04adb3 --- /dev/null +++ b/tests/workloads/kernel_verbose_1/MI200/perfmon/SQ_LEVEL_WAVES.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_0.txt b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_0.txt new file mode 100644 index 0000000000..4ffdc32149 --- /dev/null +++ b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_0.txt @@ -0,0 +1,5 @@ +pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES SQ_INSTS_VALU_CVT SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU GRBM_COUNT GRBM_GUI_ACTIVE TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum TA_TA_BUSY_sum TA_BUFFER_WAVEFRONTS_sum TD_TD_BUSY_sum TD_TC_STALL_sum SPI_CSN_WINDOW_VALID SPI_CSN_BUSY CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_1.txt b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_1.txt new file mode 100644 index 0000000000..6c277f4a37 --- /dev/null +++ b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_1.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VSKIPPED SQ_INSTS SQ_INSTS_VALU SQ_INSTS_VALU_ADD_F16 SQ_INSTS_VALU_MUL_F16 SQ_INSTS_VALU_FMA_F16 SQ_INSTS_VALU_TRANS_F16 SQ_INSTS_VALU_ADD_F32 GRBM_SPI_BUSY TCP_READ_TAGCONFLICT_STALL_CYCLES_sum TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum TCP_TA_TCP_STATE_READ_sum TA_BUFFER_READ_WAVEFRONTS_sum TA_BUFFER_WRITE_WAVEFRONTS_sum TD_SPI_STALL_sum TD_LOAD_WAVEFRONT_sum SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_10.txt b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_10.txt new file mode 100644 index 0000000000..7053d4dce6 --- /dev/null +++ b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_10.txt @@ -0,0 +1,5 @@ +pmc: SQC_TC_DATA_WRITE_REQ SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_11.txt b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_11.txt new file mode 100644 index 0000000000..77ae8b461f --- /dev/null +++ b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_11.txt @@ -0,0 +1,5 @@ +pmc: SQC_ICACHE_MISSES_DUPLICATE SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_12.txt b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_12.txt new file mode 100644 index 0000000000..dfb2cf65e5 --- /dev/null +++ b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_12.txt @@ -0,0 +1,5 @@ +pmc: SQC_DCACHE_REQ_READ_1 SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_13.txt b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_13.txt new file mode 100644 index 0000000000..062fc9644a --- /dev/null +++ b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_13.txt @@ -0,0 +1,5 @@ +pmc: TCC_ATOMIC[0] TCC_CYCLE[0] TCC_EA_ATOMIC[0] TCC_EA_ATOMIC_LEVEL[0] TCC_ATOMIC[1] TCC_CYCLE[1] TCC_EA_ATOMIC[1] TCC_EA_ATOMIC_LEVEL[1] TCC_ATOMIC[2] TCC_CYCLE[2] TCC_EA_ATOMIC[2] TCC_EA_ATOMIC_LEVEL[2] TCC_ATOMIC[3] TCC_CYCLE[3] TCC_EA_ATOMIC[3] TCC_EA_ATOMIC_LEVEL[3] TCC_ATOMIC[4] TCC_CYCLE[4] TCC_EA_ATOMIC[4] TCC_EA_ATOMIC_LEVEL[4] TCC_ATOMIC[5] TCC_CYCLE[5] TCC_EA_ATOMIC[5] TCC_EA_ATOMIC_LEVEL[5] TCC_ATOMIC[6] TCC_CYCLE[6] TCC_EA_ATOMIC[6] TCC_EA_ATOMIC_LEVEL[6] TCC_ATOMIC[7] TCC_CYCLE[7] TCC_EA_ATOMIC[7] TCC_EA_ATOMIC_LEVEL[7] TCC_ATOMIC[8] TCC_CYCLE[8] TCC_EA_ATOMIC[8] TCC_EA_ATOMIC_LEVEL[8] TCC_ATOMIC[9] TCC_CYCLE[9] TCC_EA_ATOMIC[9] TCC_EA_ATOMIC_LEVEL[9] TCC_ATOMIC[10] TCC_CYCLE[10] TCC_EA_ATOMIC[10] TCC_EA_ATOMIC_LEVEL[10] TCC_ATOMIC[11] TCC_CYCLE[11] TCC_EA_ATOMIC[11] TCC_EA_ATOMIC_LEVEL[11] TCC_ATOMIC[12] TCC_CYCLE[12] TCC_EA_ATOMIC[12] TCC_EA_ATOMIC_LEVEL[12] TCC_ATOMIC[13] TCC_CYCLE[13] TCC_EA_ATOMIC[13] TCC_EA_ATOMIC_LEVEL[13] TCC_ATOMIC[14] TCC_CYCLE[14] TCC_EA_ATOMIC[14] TCC_EA_ATOMIC_LEVEL[14] TCC_ATOMIC[15] TCC_CYCLE[15] TCC_EA_ATOMIC[15] TCC_EA_ATOMIC_LEVEL[15] TCC_ATOMIC[16] TCC_CYCLE[16] TCC_EA_ATOMIC[16] TCC_EA_ATOMIC_LEVEL[16] TCC_ATOMIC[17] TCC_CYCLE[17] TCC_EA_ATOMIC[17] TCC_EA_ATOMIC_LEVEL[17] TCC_ATOMIC[18] TCC_CYCLE[18] TCC_EA_ATOMIC[18] TCC_EA_ATOMIC_LEVEL[18] TCC_ATOMIC[19] TCC_CYCLE[19] TCC_EA_ATOMIC[19] TCC_EA_ATOMIC_LEVEL[19] TCC_ATOMIC[20] TCC_CYCLE[20] TCC_EA_ATOMIC[20] TCC_EA_ATOMIC_LEVEL[20] TCC_ATOMIC[21] TCC_CYCLE[21] TCC_EA_ATOMIC[21] TCC_EA_ATOMIC_LEVEL[21] TCC_ATOMIC[22] TCC_CYCLE[22] TCC_EA_ATOMIC[22] TCC_EA_ATOMIC_LEVEL[22] TCC_ATOMIC[23] TCC_CYCLE[23] TCC_EA_ATOMIC[23] TCC_EA_ATOMIC_LEVEL[23] TCC_ATOMIC[24] TCC_CYCLE[24] TCC_EA_ATOMIC[24] TCC_EA_ATOMIC_LEVEL[24] TCC_ATOMIC[25] TCC_CYCLE[25] TCC_EA_ATOMIC[25] TCC_EA_ATOMIC_LEVEL[25] TCC_ATOMIC[26] TCC_CYCLE[26] TCC_EA_ATOMIC[26] TCC_EA_ATOMIC_LEVEL[26] TCC_ATOMIC[27] TCC_CYCLE[27] TCC_EA_ATOMIC[27] TCC_EA_ATOMIC_LEVEL[27] TCC_ATOMIC[28] TCC_CYCLE[28] TCC_EA_ATOMIC[28] TCC_EA_ATOMIC_LEVEL[28] TCC_ATOMIC[29] TCC_CYCLE[29] TCC_EA_ATOMIC[29] TCC_EA_ATOMIC_LEVEL[29] TCC_ATOMIC[30] TCC_CYCLE[30] TCC_EA_ATOMIC[30] TCC_EA_ATOMIC_LEVEL[30] TCC_ATOMIC[31] TCC_CYCLE[31] TCC_EA_ATOMIC[31] TCC_EA_ATOMIC_LEVEL[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_14.txt b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_14.txt new file mode 100644 index 0000000000..e0698dbf57 --- /dev/null +++ b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_14.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_EA_RDREQ_GMI_CREDIT_STALL[0] TCC_EA_RDREQ[1] TCC_EA_RDREQ_32B[1] TCC_EA_RDREQ_DRAM_CREDIT_STALL[1] TCC_EA_RDREQ_GMI_CREDIT_STALL[1] TCC_EA_RDREQ[2] TCC_EA_RDREQ_32B[2] TCC_EA_RDREQ_DRAM_CREDIT_STALL[2] TCC_EA_RDREQ_GMI_CREDIT_STALL[2] TCC_EA_RDREQ[3] TCC_EA_RDREQ_32B[3] TCC_EA_RDREQ_DRAM_CREDIT_STALL[3] TCC_EA_RDREQ_GMI_CREDIT_STALL[3] TCC_EA_RDREQ[4] TCC_EA_RDREQ_32B[4] TCC_EA_RDREQ_DRAM_CREDIT_STALL[4] TCC_EA_RDREQ_GMI_CREDIT_STALL[4] TCC_EA_RDREQ[5] TCC_EA_RDREQ_32B[5] TCC_EA_RDREQ_DRAM_CREDIT_STALL[5] TCC_EA_RDREQ_GMI_CREDIT_STALL[5] TCC_EA_RDREQ[6] TCC_EA_RDREQ_32B[6] TCC_EA_RDREQ_DRAM_CREDIT_STALL[6] TCC_EA_RDREQ_GMI_CREDIT_STALL[6] TCC_EA_RDREQ[7] TCC_EA_RDREQ_32B[7] TCC_EA_RDREQ_DRAM_CREDIT_STALL[7] TCC_EA_RDREQ_GMI_CREDIT_STALL[7] TCC_EA_RDREQ[8] TCC_EA_RDREQ_32B[8] TCC_EA_RDREQ_DRAM_CREDIT_STALL[8] TCC_EA_RDREQ_GMI_CREDIT_STALL[8] TCC_EA_RDREQ[9] TCC_EA_RDREQ_32B[9] TCC_EA_RDREQ_DRAM_CREDIT_STALL[9] TCC_EA_RDREQ_GMI_CREDIT_STALL[9] TCC_EA_RDREQ[10] TCC_EA_RDREQ_32B[10] TCC_EA_RDREQ_DRAM_CREDIT_STALL[10] TCC_EA_RDREQ_GMI_CREDIT_STALL[10] TCC_EA_RDREQ[11] TCC_EA_RDREQ_32B[11] TCC_EA_RDREQ_DRAM_CREDIT_STALL[11] TCC_EA_RDREQ_GMI_CREDIT_STALL[11] TCC_EA_RDREQ[12] TCC_EA_RDREQ_32B[12] TCC_EA_RDREQ_DRAM_CREDIT_STALL[12] TCC_EA_RDREQ_GMI_CREDIT_STALL[12] TCC_EA_RDREQ[13] TCC_EA_RDREQ_32B[13] TCC_EA_RDREQ_DRAM_CREDIT_STALL[13] TCC_EA_RDREQ_GMI_CREDIT_STALL[13] TCC_EA_RDREQ[14] TCC_EA_RDREQ_32B[14] TCC_EA_RDREQ_DRAM_CREDIT_STALL[14] TCC_EA_RDREQ_GMI_CREDIT_STALL[14] TCC_EA_RDREQ[15] TCC_EA_RDREQ_32B[15] TCC_EA_RDREQ_DRAM_CREDIT_STALL[15] TCC_EA_RDREQ_GMI_CREDIT_STALL[15] TCC_EA_RDREQ[16] TCC_EA_RDREQ_32B[16] TCC_EA_RDREQ_DRAM_CREDIT_STALL[16] TCC_EA_RDREQ_GMI_CREDIT_STALL[16] TCC_EA_RDREQ[17] TCC_EA_RDREQ_32B[17] TCC_EA_RDREQ_DRAM_CREDIT_STALL[17] TCC_EA_RDREQ_GMI_CREDIT_STALL[17] TCC_EA_RDREQ[18] TCC_EA_RDREQ_32B[18] TCC_EA_RDREQ_DRAM_CREDIT_STALL[18] TCC_EA_RDREQ_GMI_CREDIT_STALL[18] TCC_EA_RDREQ[19] TCC_EA_RDREQ_32B[19] TCC_EA_RDREQ_DRAM_CREDIT_STALL[19] TCC_EA_RDREQ_GMI_CREDIT_STALL[19] TCC_EA_RDREQ[20] TCC_EA_RDREQ_32B[20] TCC_EA_RDREQ_DRAM_CREDIT_STALL[20] TCC_EA_RDREQ_GMI_CREDIT_STALL[20] TCC_EA_RDREQ[21] TCC_EA_RDREQ_32B[21] TCC_EA_RDREQ_DRAM_CREDIT_STALL[21] TCC_EA_RDREQ_GMI_CREDIT_STALL[21] TCC_EA_RDREQ[22] TCC_EA_RDREQ_32B[22] TCC_EA_RDREQ_DRAM_CREDIT_STALL[22] TCC_EA_RDREQ_GMI_CREDIT_STALL[22] TCC_EA_RDREQ[23] TCC_EA_RDREQ_32B[23] TCC_EA_RDREQ_DRAM_CREDIT_STALL[23] TCC_EA_RDREQ_GMI_CREDIT_STALL[23] TCC_EA_RDREQ[24] TCC_EA_RDREQ_32B[24] TCC_EA_RDREQ_DRAM_CREDIT_STALL[24] TCC_EA_RDREQ_GMI_CREDIT_STALL[24] TCC_EA_RDREQ[25] TCC_EA_RDREQ_32B[25] TCC_EA_RDREQ_DRAM_CREDIT_STALL[25] TCC_EA_RDREQ_GMI_CREDIT_STALL[25] TCC_EA_RDREQ[26] TCC_EA_RDREQ_32B[26] TCC_EA_RDREQ_DRAM_CREDIT_STALL[26] TCC_EA_RDREQ_GMI_CREDIT_STALL[26] TCC_EA_RDREQ[27] TCC_EA_RDREQ_32B[27] TCC_EA_RDREQ_DRAM_CREDIT_STALL[27] TCC_EA_RDREQ_GMI_CREDIT_STALL[27] TCC_EA_RDREQ[28] TCC_EA_RDREQ_32B[28] TCC_EA_RDREQ_DRAM_CREDIT_STALL[28] TCC_EA_RDREQ_GMI_CREDIT_STALL[28] TCC_EA_RDREQ[29] TCC_EA_RDREQ_32B[29] TCC_EA_RDREQ_DRAM_CREDIT_STALL[29] TCC_EA_RDREQ_GMI_CREDIT_STALL[29] TCC_EA_RDREQ[30] TCC_EA_RDREQ_32B[30] TCC_EA_RDREQ_DRAM_CREDIT_STALL[30] TCC_EA_RDREQ_GMI_CREDIT_STALL[30] TCC_EA_RDREQ[31] TCC_EA_RDREQ_32B[31] TCC_EA_RDREQ_DRAM_CREDIT_STALL[31] TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_15.txt b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_15.txt new file mode 100644 index 0000000000..77ad088669 --- /dev/null +++ b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_15.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ[0] TCC_EA_WRREQ_64B[0] TCC_EA_RDREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_LEVEL[1] TCC_EA_WRREQ[1] TCC_EA_WRREQ_64B[1] TCC_EA_RDREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_LEVEL[2] TCC_EA_WRREQ[2] TCC_EA_WRREQ_64B[2] TCC_EA_RDREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_LEVEL[3] TCC_EA_WRREQ[3] TCC_EA_WRREQ_64B[3] TCC_EA_RDREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_LEVEL[4] TCC_EA_WRREQ[4] TCC_EA_WRREQ_64B[4] TCC_EA_RDREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_LEVEL[5] TCC_EA_WRREQ[5] TCC_EA_WRREQ_64B[5] TCC_EA_RDREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_LEVEL[6] TCC_EA_WRREQ[6] TCC_EA_WRREQ_64B[6] TCC_EA_RDREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_LEVEL[7] TCC_EA_WRREQ[7] TCC_EA_WRREQ_64B[7] TCC_EA_RDREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_LEVEL[8] TCC_EA_WRREQ[8] TCC_EA_WRREQ_64B[8] TCC_EA_RDREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_LEVEL[9] TCC_EA_WRREQ[9] TCC_EA_WRREQ_64B[9] TCC_EA_RDREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_LEVEL[10] TCC_EA_WRREQ[10] TCC_EA_WRREQ_64B[10] TCC_EA_RDREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_LEVEL[11] TCC_EA_WRREQ[11] TCC_EA_WRREQ_64B[11] TCC_EA_RDREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_LEVEL[12] TCC_EA_WRREQ[12] TCC_EA_WRREQ_64B[12] TCC_EA_RDREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_LEVEL[13] TCC_EA_WRREQ[13] TCC_EA_WRREQ_64B[13] TCC_EA_RDREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_LEVEL[14] TCC_EA_WRREQ[14] TCC_EA_WRREQ_64B[14] TCC_EA_RDREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_LEVEL[15] TCC_EA_WRREQ[15] TCC_EA_WRREQ_64B[15] TCC_EA_RDREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_LEVEL[16] TCC_EA_WRREQ[16] TCC_EA_WRREQ_64B[16] TCC_EA_RDREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_LEVEL[17] TCC_EA_WRREQ[17] TCC_EA_WRREQ_64B[17] TCC_EA_RDREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_LEVEL[18] TCC_EA_WRREQ[18] TCC_EA_WRREQ_64B[18] TCC_EA_RDREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_LEVEL[19] TCC_EA_WRREQ[19] TCC_EA_WRREQ_64B[19] TCC_EA_RDREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_LEVEL[20] TCC_EA_WRREQ[20] TCC_EA_WRREQ_64B[20] TCC_EA_RDREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_LEVEL[21] TCC_EA_WRREQ[21] TCC_EA_WRREQ_64B[21] TCC_EA_RDREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_LEVEL[22] TCC_EA_WRREQ[22] TCC_EA_WRREQ_64B[22] TCC_EA_RDREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_LEVEL[23] TCC_EA_WRREQ[23] TCC_EA_WRREQ_64B[23] TCC_EA_RDREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_LEVEL[24] TCC_EA_WRREQ[24] TCC_EA_WRREQ_64B[24] TCC_EA_RDREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_LEVEL[25] TCC_EA_WRREQ[25] TCC_EA_WRREQ_64B[25] TCC_EA_RDREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_LEVEL[26] TCC_EA_WRREQ[26] TCC_EA_WRREQ_64B[26] TCC_EA_RDREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_LEVEL[27] TCC_EA_WRREQ[27] TCC_EA_WRREQ_64B[27] TCC_EA_RDREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_LEVEL[28] TCC_EA_WRREQ[28] TCC_EA_WRREQ_64B[28] TCC_EA_RDREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_LEVEL[29] TCC_EA_WRREQ[29] TCC_EA_WRREQ_64B[29] TCC_EA_RDREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_LEVEL[30] TCC_EA_WRREQ[30] TCC_EA_WRREQ_64B[30] TCC_EA_RDREQ_IO_CREDIT_STALL[31] TCC_EA_RDREQ_LEVEL[31] TCC_EA_WRREQ[31] TCC_EA_WRREQ_64B[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_16.txt b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_16.txt new file mode 100644 index 0000000000..d0628bb948 --- /dev/null +++ b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_16.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_WRREQ_IO_CREDIT_STALL[0] TCC_EA_WRREQ_LEVEL[0] TCC_EA_WRREQ_DRAM_CREDIT_STALL[1] TCC_EA_WRREQ_GMI_CREDIT_STALL[1] TCC_EA_WRREQ_IO_CREDIT_STALL[1] TCC_EA_WRREQ_LEVEL[1] TCC_EA_WRREQ_DRAM_CREDIT_STALL[2] TCC_EA_WRREQ_GMI_CREDIT_STALL[2] TCC_EA_WRREQ_IO_CREDIT_STALL[2] TCC_EA_WRREQ_LEVEL[2] TCC_EA_WRREQ_DRAM_CREDIT_STALL[3] TCC_EA_WRREQ_GMI_CREDIT_STALL[3] TCC_EA_WRREQ_IO_CREDIT_STALL[3] TCC_EA_WRREQ_LEVEL[3] TCC_EA_WRREQ_DRAM_CREDIT_STALL[4] TCC_EA_WRREQ_GMI_CREDIT_STALL[4] TCC_EA_WRREQ_IO_CREDIT_STALL[4] TCC_EA_WRREQ_LEVEL[4] TCC_EA_WRREQ_DRAM_CREDIT_STALL[5] TCC_EA_WRREQ_GMI_CREDIT_STALL[5] TCC_EA_WRREQ_IO_CREDIT_STALL[5] TCC_EA_WRREQ_LEVEL[5] TCC_EA_WRREQ_DRAM_CREDIT_STALL[6] TCC_EA_WRREQ_GMI_CREDIT_STALL[6] TCC_EA_WRREQ_IO_CREDIT_STALL[6] TCC_EA_WRREQ_LEVEL[6] TCC_EA_WRREQ_DRAM_CREDIT_STALL[7] TCC_EA_WRREQ_GMI_CREDIT_STALL[7] TCC_EA_WRREQ_IO_CREDIT_STALL[7] TCC_EA_WRREQ_LEVEL[7] TCC_EA_WRREQ_DRAM_CREDIT_STALL[8] TCC_EA_WRREQ_GMI_CREDIT_STALL[8] TCC_EA_WRREQ_IO_CREDIT_STALL[8] TCC_EA_WRREQ_LEVEL[8] TCC_EA_WRREQ_DRAM_CREDIT_STALL[9] TCC_EA_WRREQ_GMI_CREDIT_STALL[9] TCC_EA_WRREQ_IO_CREDIT_STALL[9] TCC_EA_WRREQ_LEVEL[9] TCC_EA_WRREQ_DRAM_CREDIT_STALL[10] TCC_EA_WRREQ_GMI_CREDIT_STALL[10] TCC_EA_WRREQ_IO_CREDIT_STALL[10] TCC_EA_WRREQ_LEVEL[10] TCC_EA_WRREQ_DRAM_CREDIT_STALL[11] TCC_EA_WRREQ_GMI_CREDIT_STALL[11] TCC_EA_WRREQ_IO_CREDIT_STALL[11] TCC_EA_WRREQ_LEVEL[11] TCC_EA_WRREQ_DRAM_CREDIT_STALL[12] TCC_EA_WRREQ_GMI_CREDIT_STALL[12] TCC_EA_WRREQ_IO_CREDIT_STALL[12] TCC_EA_WRREQ_LEVEL[12] TCC_EA_WRREQ_DRAM_CREDIT_STALL[13] TCC_EA_WRREQ_GMI_CREDIT_STALL[13] TCC_EA_WRREQ_IO_CREDIT_STALL[13] TCC_EA_WRREQ_LEVEL[13] TCC_EA_WRREQ_DRAM_CREDIT_STALL[14] TCC_EA_WRREQ_GMI_CREDIT_STALL[14] TCC_EA_WRREQ_IO_CREDIT_STALL[14] TCC_EA_WRREQ_LEVEL[14] TCC_EA_WRREQ_DRAM_CREDIT_STALL[15] TCC_EA_WRREQ_GMI_CREDIT_STALL[15] TCC_EA_WRREQ_IO_CREDIT_STALL[15] TCC_EA_WRREQ_LEVEL[15] TCC_EA_WRREQ_DRAM_CREDIT_STALL[16] TCC_EA_WRREQ_GMI_CREDIT_STALL[16] TCC_EA_WRREQ_IO_CREDIT_STALL[16] TCC_EA_WRREQ_LEVEL[16] TCC_EA_WRREQ_DRAM_CREDIT_STALL[17] TCC_EA_WRREQ_GMI_CREDIT_STALL[17] TCC_EA_WRREQ_IO_CREDIT_STALL[17] TCC_EA_WRREQ_LEVEL[17] TCC_EA_WRREQ_DRAM_CREDIT_STALL[18] TCC_EA_WRREQ_GMI_CREDIT_STALL[18] TCC_EA_WRREQ_IO_CREDIT_STALL[18] TCC_EA_WRREQ_LEVEL[18] TCC_EA_WRREQ_DRAM_CREDIT_STALL[19] TCC_EA_WRREQ_GMI_CREDIT_STALL[19] TCC_EA_WRREQ_IO_CREDIT_STALL[19] TCC_EA_WRREQ_LEVEL[19] TCC_EA_WRREQ_DRAM_CREDIT_STALL[20] TCC_EA_WRREQ_GMI_CREDIT_STALL[20] TCC_EA_WRREQ_IO_CREDIT_STALL[20] TCC_EA_WRREQ_LEVEL[20] TCC_EA_WRREQ_DRAM_CREDIT_STALL[21] TCC_EA_WRREQ_GMI_CREDIT_STALL[21] TCC_EA_WRREQ_IO_CREDIT_STALL[21] TCC_EA_WRREQ_LEVEL[21] TCC_EA_WRREQ_DRAM_CREDIT_STALL[22] TCC_EA_WRREQ_GMI_CREDIT_STALL[22] TCC_EA_WRREQ_IO_CREDIT_STALL[22] TCC_EA_WRREQ_LEVEL[22] TCC_EA_WRREQ_DRAM_CREDIT_STALL[23] TCC_EA_WRREQ_GMI_CREDIT_STALL[23] TCC_EA_WRREQ_IO_CREDIT_STALL[23] TCC_EA_WRREQ_LEVEL[23] TCC_EA_WRREQ_DRAM_CREDIT_STALL[24] TCC_EA_WRREQ_GMI_CREDIT_STALL[24] TCC_EA_WRREQ_IO_CREDIT_STALL[24] TCC_EA_WRREQ_LEVEL[24] TCC_EA_WRREQ_DRAM_CREDIT_STALL[25] TCC_EA_WRREQ_GMI_CREDIT_STALL[25] TCC_EA_WRREQ_IO_CREDIT_STALL[25] TCC_EA_WRREQ_LEVEL[25] TCC_EA_WRREQ_DRAM_CREDIT_STALL[26] TCC_EA_WRREQ_GMI_CREDIT_STALL[26] TCC_EA_WRREQ_IO_CREDIT_STALL[26] TCC_EA_WRREQ_LEVEL[26] TCC_EA_WRREQ_DRAM_CREDIT_STALL[27] TCC_EA_WRREQ_GMI_CREDIT_STALL[27] TCC_EA_WRREQ_IO_CREDIT_STALL[27] TCC_EA_WRREQ_LEVEL[27] TCC_EA_WRREQ_DRAM_CREDIT_STALL[28] TCC_EA_WRREQ_GMI_CREDIT_STALL[28] TCC_EA_WRREQ_IO_CREDIT_STALL[28] TCC_EA_WRREQ_LEVEL[28] TCC_EA_WRREQ_DRAM_CREDIT_STALL[29] TCC_EA_WRREQ_GMI_CREDIT_STALL[29] TCC_EA_WRREQ_IO_CREDIT_STALL[29] TCC_EA_WRREQ_LEVEL[29] TCC_EA_WRREQ_DRAM_CREDIT_STALL[30] TCC_EA_WRREQ_GMI_CREDIT_STALL[30] TCC_EA_WRREQ_IO_CREDIT_STALL[30] TCC_EA_WRREQ_LEVEL[30] TCC_EA_WRREQ_DRAM_CREDIT_STALL[31] TCC_EA_WRREQ_GMI_CREDIT_STALL[31] TCC_EA_WRREQ_IO_CREDIT_STALL[31] TCC_EA_WRREQ_LEVEL[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_17.txt b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_17.txt new file mode 100644 index 0000000000..343869c5f1 --- /dev/null +++ b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_17.txt @@ -0,0 +1,5 @@ +pmc: TCC_HIT[0] TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_HIT[1] TCC_MISS[1] TCC_READ[1] TCC_REQ[1] TCC_HIT[2] TCC_MISS[2] TCC_READ[2] TCC_REQ[2] TCC_HIT[3] TCC_MISS[3] TCC_READ[3] TCC_REQ[3] TCC_HIT[4] TCC_MISS[4] TCC_READ[4] TCC_REQ[4] TCC_HIT[5] TCC_MISS[5] TCC_READ[5] TCC_REQ[5] TCC_HIT[6] TCC_MISS[6] TCC_READ[6] TCC_REQ[6] TCC_HIT[7] TCC_MISS[7] TCC_READ[7] TCC_REQ[7] TCC_HIT[8] TCC_MISS[8] TCC_READ[8] TCC_REQ[8] TCC_HIT[9] TCC_MISS[9] TCC_READ[9] TCC_REQ[9] TCC_HIT[10] TCC_MISS[10] TCC_READ[10] TCC_REQ[10] TCC_HIT[11] TCC_MISS[11] TCC_READ[11] TCC_REQ[11] TCC_HIT[12] TCC_MISS[12] TCC_READ[12] TCC_REQ[12] TCC_HIT[13] TCC_MISS[13] TCC_READ[13] TCC_REQ[13] TCC_HIT[14] TCC_MISS[14] TCC_READ[14] TCC_REQ[14] TCC_HIT[15] TCC_MISS[15] TCC_READ[15] TCC_REQ[15] TCC_HIT[16] TCC_MISS[16] TCC_READ[16] TCC_REQ[16] TCC_HIT[17] TCC_MISS[17] TCC_READ[17] TCC_REQ[17] TCC_HIT[18] TCC_MISS[18] TCC_READ[18] TCC_REQ[18] TCC_HIT[19] TCC_MISS[19] TCC_READ[19] TCC_REQ[19] TCC_HIT[20] TCC_MISS[20] TCC_READ[20] TCC_REQ[20] TCC_HIT[21] TCC_MISS[21] TCC_READ[21] TCC_REQ[21] TCC_HIT[22] TCC_MISS[22] TCC_READ[22] TCC_REQ[22] TCC_HIT[23] TCC_MISS[23] TCC_READ[23] TCC_REQ[23] TCC_HIT[24] TCC_MISS[24] TCC_READ[24] TCC_REQ[24] TCC_HIT[25] TCC_MISS[25] TCC_READ[25] TCC_REQ[25] TCC_HIT[26] TCC_MISS[26] TCC_READ[26] TCC_REQ[26] TCC_HIT[27] TCC_MISS[27] TCC_READ[27] TCC_REQ[27] TCC_HIT[28] TCC_MISS[28] TCC_READ[28] TCC_REQ[28] TCC_HIT[29] TCC_MISS[29] TCC_READ[29] TCC_REQ[29] TCC_HIT[30] TCC_MISS[30] TCC_READ[30] TCC_REQ[30] TCC_HIT[31] TCC_MISS[31] TCC_READ[31] TCC_REQ[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_18.txt b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_18.txt new file mode 100644 index 0000000000..a74cefd281 --- /dev/null +++ b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_18.txt @@ -0,0 +1,5 @@ +pmc: TCC_RW_REQ[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_RW_REQ[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_WRITE[1] TCC_RW_REQ[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_WRITE[2] TCC_RW_REQ[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_WRITE[3] TCC_RW_REQ[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_WRITE[4] TCC_RW_REQ[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_WRITE[5] TCC_RW_REQ[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_WRITE[6] TCC_RW_REQ[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_WRITE[7] TCC_RW_REQ[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_WRITE[8] TCC_RW_REQ[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_WRITE[9] TCC_RW_REQ[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_WRITE[10] TCC_RW_REQ[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_WRITE[11] TCC_RW_REQ[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_WRITE[12] TCC_RW_REQ[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_WRITE[13] TCC_RW_REQ[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_WRITE[14] TCC_RW_REQ[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_WRITE[15] TCC_RW_REQ[16] TCC_TOO_MANY_EA_WRREQS_STALL[16] TCC_WRITE[16] TCC_RW_REQ[17] TCC_TOO_MANY_EA_WRREQS_STALL[17] TCC_WRITE[17] TCC_RW_REQ[18] TCC_TOO_MANY_EA_WRREQS_STALL[18] TCC_WRITE[18] TCC_RW_REQ[19] TCC_TOO_MANY_EA_WRREQS_STALL[19] TCC_WRITE[19] TCC_RW_REQ[20] TCC_TOO_MANY_EA_WRREQS_STALL[20] TCC_WRITE[20] TCC_RW_REQ[21] TCC_TOO_MANY_EA_WRREQS_STALL[21] TCC_WRITE[21] TCC_RW_REQ[22] TCC_TOO_MANY_EA_WRREQS_STALL[22] TCC_WRITE[22] TCC_RW_REQ[23] TCC_TOO_MANY_EA_WRREQS_STALL[23] TCC_WRITE[23] TCC_RW_REQ[24] TCC_TOO_MANY_EA_WRREQS_STALL[24] TCC_WRITE[24] TCC_RW_REQ[25] TCC_TOO_MANY_EA_WRREQS_STALL[25] TCC_WRITE[25] TCC_RW_REQ[26] TCC_TOO_MANY_EA_WRREQS_STALL[26] TCC_WRITE[26] TCC_RW_REQ[27] TCC_TOO_MANY_EA_WRREQS_STALL[27] TCC_WRITE[27] TCC_RW_REQ[28] TCC_TOO_MANY_EA_WRREQS_STALL[28] TCC_WRITE[28] TCC_RW_REQ[29] TCC_TOO_MANY_EA_WRREQS_STALL[29] TCC_WRITE[29] TCC_RW_REQ[30] TCC_TOO_MANY_EA_WRREQS_STALL[30] TCC_WRITE[30] TCC_RW_REQ[31] TCC_TOO_MANY_EA_WRREQS_STALL[31] TCC_WRITE[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_2.txt b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_2.txt new file mode 100644 index 0000000000..70b69f8928 --- /dev/null +++ b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_2.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_MUL_F32 SQ_INSTS_VALU_FMA_F32 SQ_INSTS_VALU_TRANS_F32 SQ_INSTS_VALU_ADD_F64 SQ_INSTS_VALU_MUL_F64 SQ_INSTS_VALU_FMA_F64 SQ_INSTS_VALU_TRANS_F64 SQ_INSTS_VALU_INT32 TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum TA_BUFFER_ATOMIC_WAVEFRONTS_sum TA_BUFFER_TOTAL_CYCLES_sum TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_3.txt b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_3.txt new file mode 100644 index 0000000000..e47f8e33c9 --- /dev/null +++ b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_3.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_INT64 SQ_INSTS_SMEM SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum TD_COALESCABLE_WAVEFRONT_sum SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE CPF_CMP_UTCL1_STALL_ON_TRANSLATION TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_4.txt b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_4.txt new file mode 100644 index 0000000000..2d96f365a9 --- /dev/null +++ b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_4.txt @@ -0,0 +1,5 @@ +pmc: SQ_WAVE_CYCLES SQ_WAIT_ANY SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_BUSY_CU_CYCLES SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE TCC_EA_WRREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WR_UNCACHED_32B_sum TCC_EA_WRREQ_DRAM_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_5.txt b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_5.txt new file mode 100644 index 0000000000..e50beed390 --- /dev/null +++ b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_5.txt @@ -0,0 +1,5 @@ +pmc: SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU TCP_TCP_LATENCY_sum TCP_TCC_READ_REQ_LATENCY_sum TCP_TCC_WRITE_REQ_LATENCY_sum TCP_TCC_READ_REQ_sum TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN CPC_ME1_DC0_SPI_BUSY TCC_EA_WRREQ_STALL_sum TCC_EA_RDREQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RD_UNCACHED_32B_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_6.txt b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_6.txt new file mode 100644 index 0000000000..15a2277c1b --- /dev/null +++ b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_6.txt @@ -0,0 +1,5 @@ +pmc: SQ_THREAD_CYCLES_VALU SQ_IFETCH SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TCP_TCC_NC_READ_REQ_sum TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN TCC_EA_RDREQ_DRAM_sum TCC_TAG_STALL_sum TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_7.txt b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_7.txt new file mode 100644 index 0000000000..b42ce91618 --- /dev/null +++ b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_7.txt @@ -0,0 +1,5 @@ +pmc: SQ_WAVES_LT_32 SQ_WAVES_LT_16 SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TCP_TCC_UC_WRITE_REQ_sum TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR TCC_NORMAL_EVICT_sum TCC_ALL_TC_OP_INV_EVICT_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA_ATOMIC_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_8.txt b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_8.txt new file mode 100644 index 0000000000..21d4c7a998 --- /dev/null +++ b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_8.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM_NORM SQ_INSTS_MFMA SQ_INSTS_VALU_MFMA_I8 SQ_INSTS_VALU_MFMA_F16 SQ_INSTS_VALU_MFMA_BF16 SQ_INSTS_VALU_MFMA_F32 SQ_INSTS_VALU_MFMA_F64 SQ_VALU_MFMA_BUSY_CYCLES TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TCP_TCC_CC_ATOMIC_REQ_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN TCC_EA_RDREQ_LEVEL_sum TCC_EA_WRREQ_LEVEL_sum TCC_EA_ATOMIC_LEVEL_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_9.txt b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_9.txt new file mode 100644 index 0000000000..9ffe5778c3 --- /dev/null +++ b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_9.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_FLAT_LDS_ONLY SQ_INSTS_VALU_MFMA_MOPS_I8 SQ_INSTS_VALU_MFMA_MOPS_F16 SQ_INSTS_VALU_MFMA_MOPS_BF16 SQ_INSTS_VALU_MFMA_MOPS_F32 SQ_INSTS_VALU_MFMA_MOPS_F64 SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum TCP_PENDING_STALL_CYCLES_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_1/MI200/perfmon/timestamps.txt b/tests/workloads/kernel_verbose_1/MI200/perfmon/timestamps.txt new file mode 100644 index 0000000000..676cca1b80 --- /dev/null +++ b/tests/workloads/kernel_verbose_1/MI200/perfmon/timestamps.txt @@ -0,0 +1,5 @@ +pmc: + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_1/MI200/pmc_perf.csv b/tests/workloads/kernel_verbose_1/MI200/pmc_perf.csv new file mode 100644 index 0000000000..170881be1a --- /dev/null +++ b/tests/workloads/kernel_verbose_1/MI200/pmc_perf.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_1,obj_1,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_2,obj_2,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_3,obj_3,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,TD_COALESCABLE_WAVEFRONT_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_4,obj_4,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_5,obj_5,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_6,obj_6,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,wave_size_7,obj_7,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_8,obj_8,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_9,obj_9,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_10,obj_10,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,wave_size_11,obj_11,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_12,obj_12,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_13,obj_13,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_DRAM_sum,TCC_TAG_STALL_sum,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,wave_size_14,obj_14,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_15,obj_15,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_16,obj_16,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_17,obj_17,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_18,obj_18,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,TCC_EA_ATOMIC_LEVEL_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f2f30d60ec0,0,393216,163840,0,0,0,0,0,17747,0.0,0.0,0.0,32768.0,0.0,0.0,421.0,32768.0,4096,16384,352,28468,2266,0,56.0,7.0,0.0,204466.0,64,0x7fb5e5294ec0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,64,0x7f32c606cec0,0,0,0,0,0,0,168,56,131072.0,131072.0,0.0,1027000.0,64,0x7f095d840ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,10201,0,816,27563,0,73358.0,131072.0,0.0,65568.0,64,0x7f18088e4ec0,2261,4096,2261,6357,2290,4096,2290,6386,2316,4096,2316,6412,2293,4096,2293,6389,2230,4096,2230,6326,2271,4096,2271,6367,2282,4096,2282,6378,2310,4096,2310,6406,2311,4100,2315,6411,2264,4096,2264,6360,2288,4096,2288,6384,2318,4096,2318,6414,2292,4096,2292,6388,2232,4098,2234,6330,2270,4096,2270,6366,2286,4096,2286,6382,2291,4096,2291,6387,2270,4096,2270,6366,2368,4098,2370,6466,2313,4096,2313,6409,2275,4096,2275,6371,2280,4096,2280,6376,2287,4096,2287,6383,2447,4098,2449,6545,2279,4096,2279,6375,2290,4096,2290,6386,2269,4096,2269,6365,2316,4097,2317,6413,2315,4096,2315,6411,2279,4096,2279,6375,2280,4096,2280,6376,2290,4096,2290,6386,64,0x7f4fb5fd8ec0,0,0,0,224,0,65536,64182,56,64,0x7f42a6b3cec0,114688,0,32768,32768,16384,16384,65536,49152,27649860.0,87502975.0,39274438.0,131072.0,0.0,215108.0,0,0,14754,521.0,131081.0,0.0,10.0,64,0x7fb6d6754ec0,234048,132225,16384,0,16384,16384,32768,49152,29255,29255,1996337.0,1334650.0,3387.0,170996.0,1046881.0,0.0,1326318.0,1027943.0,232337,140340,29255,0,29255,0,936160.0,486100.0,0.0,0.0,64,0x7f4ccb2e8ec0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,301,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,100,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4099,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4098,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,64,0x7f707852cec0,0,1168245,4096,4096,0,1374737,4096,4096,0,1374113,4096,4096,0,1251333,4096,4096,0,1323182,4096,4096,0,1480557,4096,4096,0,1282383,4096,4096,0,1503021,4096,4096,0,1367890,4096,4096,0,1185330,4096,4096,0,1031338,4096,4096,0,1287324,4096,4096,0,1101961,4096,4096,0,1542256,4096,4096,0,1135142,4096,4096,0,1105766,4096,4096,0,1224038,4096,4096,0,1191336,4096,4096,0,1105875,4096,4096,0,1421596,4096,4096,0,1220864,4096,4096,0,1345222,4096,4096,0,1238044,4096,4096,0,1282389,4096,4096,0,1629687,4096,4096,0,1132579,4096,4096,0,1275299,4096,4096,0,1039849,4096,4096,0,1123301,4096,4096,0,1173075,4096,4096,0,1143817,4096,4096,0,1262905,4096,4096,64,0x7f8bc7a80ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65551.0,0.0,0.0,0.0,64,0x7fb5d5860ec0,32768,32768,0,64,0x7fa6a5348ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,12040,19189,8199,547,0,26241,204509.0,0.0,73429.0,131080.0,64,0x7fcd72e38ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131078.0,34952.0,46045.0,19491.0,64,0x7f12b11a8ec0,1315,116949,0,0,65536,63800,56,1680,64,0x7f16ec274ec0,11246562,9885575,1016923,344064,1685778,0,0,163840,832.0,515146.0,0.0,524288.0,313367.0,32768.0,532433,0,0,11249,131072.0,131072.0,0.0,131072.0,64,0x7f0fa95e8ec0,0,0,0,960793,0,0,0,1046335,0,0,0,1007179,0,0,0,1069013,11,0,0,1185365,131,0,0,1263233,0,0,0,1121946,0,0,0,1081571,0,0,0,1011187,0,0,0,1006260,0,0,0,1027593,0,0,0,1072598,0,0,0,1003114,0,0,0,1118865,95,0,0,1169897,111,0,0,1270909,0,0,0,1077659,0,0,0,1062317,0,0,0,1038773,437,0,0,1336872,0,0,0,1051285,0,0,0,1086019,0,0,0,1116459,0,0,0,1184759,0,0,0,1107126,0,0,0,1091346,0,0,0,1054377,0,0,0,1115638,65,0,0,1174159,0,0,0,1063579,0,0,0,1010761,0,0,0,1238908,64,0x7fb3dee04ec0,6360,0,4096,6398,0,4096,6407,0,4096,6397,0,4096,6344,0,4096,6385,0,4096,6341,0,4096,6375,0,4096,6380,0,4096,6364,0,4096,6398,0,4096,6409,0,4096,6399,0,4096,6341,0,4096,6389,0,4096,6345,0,4096,6363,0,4096,6412,0,4096,6384,0,4096,6375,0,4096,6364,0,4096,6372,0,4096,6385,0,4096,6531,0,4096,6363,0,4096,6359,0,4096,6419,0,4096,6387,0,4096,6379,0,4096,6364,0,4096,6374,0,4096,6388,0,4096,64,0x7f8ab4290ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,41246558.0,35325626.0,0.0,200067979162338,200067979182178 +1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f2f30d60ec0,0,393216,163840,0,0,0,0,0,28486,0.0,0.0,0.0,32768.0,0.0,0.0,220.0,32768.0,4096,16384,302,37723,1950,0,56.0,2.0,0.0,200260.0,64,0x7fb5e5294ec0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,64,0x7f32c606cec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2106996.0,64,0x7f095d840ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,18950,0,2726,38120,0,69389.0,131072.0,0.0,45663.0,64,0x7f18088e4ec0,2212,4096,2212,6308,2218,4096,2218,6314,2159,4096,2159,6255,2202,4096,2202,6298,2204,4096,2204,6300,2202,4097,2203,6299,2170,4096,2170,6266,2196,4096,2196,6292,2191,4098,2193,6289,2218,4099,2221,6317,2221,4096,2221,6317,2159,4096,2159,6255,2206,4096,2206,6302,2201,4097,2202,6298,2204,4096,2204,6300,2171,4096,2171,6267,2163,4096,2163,6259,2185,4096,2185,6281,2209,4099,2212,6308,2200,4096,2200,6296,2186,4096,2186,6282,2228,4096,2228,6324,2163,4096,2163,6259,2193,4096,2193,6289,2195,4096,2195,6291,2163,4096,2163,6259,2184,4096,2184,6280,2155,4097,2156,6252,2203,4096,2203,6299,2187,4096,2187,6283,2230,4096,2230,6326,2165,4096,2165,6261,64,0x7f4fb5fd8ec0,0,0,0,56,0,65536,65536,0,64,0x7f42a6b3cec0,114688,0,32768,32768,16384,16384,65536,49152,57390856.0,203960685.0,49843780.0,131072.0,0.0,431717.0,0,0,22700,4524.0,131075.0,0.0,4.0,64,0x7fb6d6754ec0,331432,223438,16384,0,16384,16384,32768,49152,41428,41428,3181987.0,2495637.0,4300.0,423158.0,1692058.0,0.0,2485217.0,2178896.0,331424,232703,41428,0,41428,0,1325696.0,781224.0,0.0,0.0,64,0x7f4ccb2e8ec0,4096,0,1653,0,4096,0,459,0,4097,0,912,0,4096,0,125,0,4096,0,573,0,4097,0,390,0,4096,0,448,0,4096,0,300,0,4096,0,31,0,4099,0,257,0,4096,0,159,0,4096,0,189,0,4096,0,336,0,4096,0,56,0,4096,0,166,0,4096,0,224,0,4096,0,9,0,4096,0,135,0,4097,0,520,0,4096,0,1802,0,4096,0,276,0,4096,0,1464,0,4096,0,823,0,4096,0,1003,0,4096,0,527,0,4096,0,36,0,4096,0,13,0,4098,0,287,0,4096,0,200,0,4096,0,10,0,4096,0,1289,0,4096,0,797,0,64,0x7f707852cec0,0,3622600,2804,2804,0,3628991,2854,2854,0,4031469,2846,2846,0,3480464,2854,2854,0,3057363,2876,2876,0,4283274,2832,2832,0,3048608,2868,2868,0,3743924,2828,2828,0,2992924,2828,2828,0,3222388,2808,2808,0,3243665,2852,2852,0,3245835,2840,2840,0,4202768,2852,2852,0,3406709,2872,2872,0,3907380,2832,2832,0,3164228,2868,2868,0,4223629,2816,2816,0,3747189,2860,2860,0,3804412,2818,2818,0,3605594,2804,2804,0,4814152,2840,2840,0,3897375,2860,2860,0,3522879,2812,2812,0,3923642,2812,2812,0,3892628,2812,2812,0,3517951,2824,2824,0,4275879,2860,2860,0,3508292,2824,2824,0,4193072,2800,2800,0,3321261,2840,2840,0,3287207,2864,2864,0,3327450,2812,2812,64,0x7f8bc7a80ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65554.0,0.0,0.0,0.0,64,0x7fb5d5860ec0,32768,32768,0,64,0x7fa6a5348ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,27685,25349,9618,2805,0,39619,200989.0,0.0,69903.0,131086.0,64,0x7fcd72e38ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131074.0,94908.0,45649.0,0.0,64,0x7f12b11a8ec0,0,185211,0,0,65536,63800,56,1680,64,0x7f16ec274ec0,18850381,17530827,975490,344064,2738187,0,0,163840,832.0,515136.0,0.0,524288.0,618227.0,32768.0,963178,0,0,13140,91094.0,91094.0,0.0,91094.0,64,0x7f0fa95e8ec0,276,0,0,2078425,718,0,0,2283622,128,0,0,1857323,30,0,0,1917834,65,0,0,1851409,127,0,0,2017291,0,0,0,1586952,0,0,0,1845882,39,0,0,1812700,68,0,0,1662973,506,0,0,2211686,0,0,0,1799130,0,0,0,1659931,89,0,0,2008008,1172,0,0,2195573,0,0,0,1802041,714,0,0,2323621,0,0,0,1850067,1600,0,0,2540949,14,0,0,2025056,0,0,0,1700205,58,0,0,1970555,580,0,0,2131441,0,0,0,1845730,36,0,0,1711716,0,0,0,1699576,0,0,0,1762701,344,0,0,2084798,268,0,0,2144912,0,0,0,1524111,15,0,0,1959758,68,0,0,1791707,64,0x7fb3dee04ec0,6286,0,4096,6327,0,4096,6293,0,4096,6289,0,4096,6316,0,4096,6277,0,4096,6253,0,4096,6294,0,4096,6289,0,4096,6290,0,4096,6328,0,4096,6291,0,4096,6293,0,4096,6321,0,4096,6277,0,4096,6254,0,4096,6267,0,4096,6284,0,4096,6305,0,4096,6330,0,4096,6276,0,4096,6281,0,4096,6271,0,4096,6258,0,4096,6256,0,4096,6265,0,4096,6289,0,4096,6307,0,4096,6328,0,4096,6285,0,4096,6283,0,4096,6268,0,4096,64,0x7f8ab4290ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,119329188.0,56654754.0,0.0,200067979273538,200067979290178 +2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f2f30d60ec0,0,393216,163840,0,0,0,0,0,28940,0.0,0.0,0.0,32768.0,0.0,0.0,207.0,32768.0,4096,16384,302,40717,1983,0,56.0,11.0,0.0,199940.0,64,0x7fb5e5294ec0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,64,0x7f32c606cec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2011197.0,64,0x7f095d840ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,20445,0,2660,38190,0,70095.0,131072.0,0.0,45563.0,64,0x7f18088e4ec0,2150,4096,2150,6246,2177,4096,2177,6273,2167,4096,2167,6263,2148,4096,2148,6244,2189,4096,2189,6285,2191,4097,2192,6288,2166,4096,2166,6262,2172,4096,2172,6268,2175,4099,2178,6274,2153,4099,2156,6252,2185,4096,2185,6281,2170,4096,2170,6266,2153,4096,2153,6249,2187,4097,2188,6284,2193,4096,2193,6289,2177,4096,2177,6273,2165,4096,2165,6261,2151,4096,2151,6247,2224,4099,2227,6323,2171,4096,2171,6267,2141,4096,2141,6237,2178,4096,2178,6274,2179,4096,2179,6275,2194,4096,2194,6290,2198,4096,2198,6294,2170,4096,2170,6266,2151,4096,2151,6247,2167,4097,2168,6264,2176,4096,2176,6272,2144,4096,2144,6240,2179,4096,2179,6275,2180,4096,2180,6276,64,0x7f4fb5fd8ec0,0,0,0,56,0,65536,65536,0,64,0x7f42a6b3cec0,114688,0,32768,32768,16384,16384,65536,49152,57765526.0,192978845.0,50819565.0,131072.0,0.0,604455.0,0,0,25175,23721.0,131085.0,0.0,24.0,64,0x7fb6d6754ec0,333064,224258,16384,0,16384,16384,32768,49152,41632,41632,3191915.0,2493074.0,4219.0,397854.0,1717635.0,0.0,2482516.0,2176088.0,333056,233379,41632,0,41632,0,1332224.0,788337.0,0.0,0.0,64,0x7f4ccb2e8ec0,4096,0,441,0,4096,0,36,0,4097,0,801,0,4096,0,1738,0,4096,0,1182,0,4097,0,325,0,4096,0,91,0,4096,0,368,0,4096,0,330,0,4099,0,95,0,4096,0,1080,0,4096,0,198,0,4096,0,349,0,4096,0,56,0,4096,0,70,0,4096,0,104,0,4096,0,398,0,4096,0,1146,0,4097,0,484,0,4096,0,416,0,4096,0,21,0,4096,0,1052,0,4096,0,261,0,4096,0,1429,0,4096,0,305,0,4096,0,866,0,4096,0,64,0,4098,0,1044,0,4096,0,1,0,4096,0,434,0,4096,0,408,0,4096,0,1556,0,64,0x7f707852cec0,0,3019414,2840,2840,0,3805566,2868,2868,0,2893168,2844,2844,0,4394570,2838,2838,0,3719139,2908,2908,0,3646514,2840,2840,0,2821869,2868,2868,0,3990068,2836,2836,0,3130074,2836,2836,0,4047865,2840,2840,0,4304105,2864,2864,0,3279555,2836,2836,0,3458266,2832,2832,0,3684432,2908,2908,0,3405072,2840,2840,0,3811030,2868,2868,0,3269281,2842,2842,0,3373001,2868,2868,0,5091322,2848,2848,0,3554058,2864,2864,0,4766885,2800,2800,0,3706149,2840,2840,0,3600606,2844,2844,0,4547252,2840,2840,0,4987512,2840,2840,0,2811187,2844,2844,0,3459144,2868,2868,0,5074160,2856,2856,0,4714888,2868,2868,0,3573994,2792,2792,0,3265947,2840,2840,0,3313355,2844,2844,64,0x7f8bc7a80ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65554.0,0.0,0.0,0.0,64,0x7fb5d5860ec0,32768,32768,0,64,0x7fa6a5348ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,27882,26189,9638,2476,0,38724,201429.0,0.0,70344.0,131085.0,64,0x7fcd72e38ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131081.0,107629.0,45685.0,0.0,64,0x7f12b11a8ec0,0,181934,0,0,65536,63800,56,1680,64,0x7f16ec274ec0,20228511,18668289,1216158,344064,2851023,0,0,163840,832.0,515156.0,0.0,524288.0,700661.0,32768.0,1080267,0,0,14023,91210.0,91210.0,0.0,91210.0,64,0x7f0fa95e8ec0,59,0,0,1657032,0,0,0,1681772,0,0,0,2118893,408,0,0,2262814,647,0,0,2130525,170,0,0,2065416,0,0,0,1548795,204,0,0,2122947,688,0,0,2112658,0,0,0,1382101,0,0,0,1548077,0,0,0,1878627,534,0,0,2026008,898,0,0,2307419,1835,0,0,2466622,571,0,0,1847218,0,0,0,1647624,959,0,0,2335257,0,0,0,1332561,0,0,0,1672615,438,0,0,2354054,1123,0,0,2533509,55,0,0,1837177,130,0,0,1918288,194,0,0,1926745,0,0,0,1631619,171,0,0,1895566,0,0,0,1345366,22,0,0,1859148,1593,0,0,2502870,1267,0,0,2554825,509,0,0,2172337,64,0x7fb3dee04ec0,6267,0,4096,6317,0,4096,6241,0,4096,6246,0,4096,6289,0,4096,6320,0,4096,6253,0,4096,6268,0,4096,6269,0,4096,6264,0,4096,6323,0,4096,6244,0,4096,6246,0,4096,6294,0,4096,6319,0,4096,6256,0,4096,6263,0,4096,6239,0,4096,6268,0,4096,6290,0,4096,6242,0,4096,6261,0,4096,6290,0,4096,6285,0,4096,6294,0,4096,6268,0,4096,6241,0,4096,6268,0,4096,6291,0,4096,6241,0,4096,6263,0,4096,6290,0,4096,64,0x7f8ab4290ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,121672689.0,58735129.0,0.0,200067979310018,200067979325698 diff --git a/tests/workloads/kernel_verbose_1/MI200/roofline.csv b/tests/workloads/kernel_verbose_1/MI200/roofline.csv new file mode 100644 index 0000000000..3573643cb0 --- /dev/null +++ b/tests/workloads/kernel_verbose_1/MI200/roofline.csv @@ -0,0 +1,5 @@ +device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh +0,1388.9409,1388.3834,1389.4984,5015.6914,5012.4653,5018.9175,9224.9053,9224.2285,9225.582,18054.15,18053.188,18055.113,20938.648,20877.58,20999.717,20266.691,20266.037,20267.346,170416.02,170412.12,170419.91,164870.83,164865.84,164875.81,41418.922,41418.492,41419.352,41477.297,41476.762,41477.832,166331.31,165841,166821.62 +1,1389.4838,1388.9222,1390.0453,5028.2129,5026.3608,5030.0649,9233.1123,9232.4492,9233.7754,18093.682,18088.578,18098.785,20972.543,20905.521,21039.564,20293.006,20292.27,20293.742,170840.12,170836,170844.25,165095.39,165091.75,165099.03,41482.512,41481.504,41483.52,41540.258,41539.344,41541.172,166864.66,166861.39,166867.92 +2,1388.2366,1387.7125,1388.7606,5035.1167,5032.833,5037.4004,9259.4932,9258.8311,9260.1553,18100.863,18098.338,18103.389,21041.74,21041.322,21042.158,20345.758,20345.221,20346.295,171069.66,171065.45,171073.86,165449.23,165445.14,165453.33,41565.84,41564.875,41566.805,41627.988,41626.949,41629.027,166897.69,166307.59,167487.78 +3,1388.8666,1388.2894,1389.4437,5032.5542,5031.2466,5033.8618,9241.6113,9241.0742,9242.1484,18025.863,18022.361,18029.365,21034.627,21034.064,21035.189,20313.65,20312.877,20314.424,171046.27,171041.16,171051.38,165240.64,165236.17,165245.11,41444.09,41289.723,41598.457,41586.117,41585.5,41586.734,167022.28,167020.55,167024.02 diff --git a/tests/workloads/kernel_verbose_1/MI200/sysinfo.csv b/tests/workloads/kernel_verbose_1/MI200/sysinfo.csv new file mode 100644 index 0000000000..2fc047efde --- /dev/null +++ b/tests/workloads/kernel_verbose_1/MI200/sysinfo.csv @@ -0,0 +1,2 @@ +workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd +kernel_verbose_1,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 02:45:22 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/kernel_verbose_1/MI200/timestamps.csv b/tests/workloads/kernel_verbose_1/MI200/timestamps.csv new file mode 100644 index 0000000000..6a139a2a7b --- /dev/null +++ b/tests/workloads/kernel_verbose_1/MI200/timestamps.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,368049,368049,1048576,256,0,0,8,0,16,64,0x0,0x7f2adce70ec0,200067979137309,200067979162338,200067979182178,200067979197333 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,368049,368049,1048576,256,0,0,8,0,16,64,0x0,0x7f2adce70ec0,200067979192984,200067979273538,200067979290178,200067979291451 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,368049,368049,1048576,256,0,0,8,0,16,64,0x0,0x7f2adce70ec0,200067979301109,200067979310018,200067979325698,200067979327008 diff --git a/tests/workloads/kernel_verbose_2/MI100/SQ_IFETCH_LEVEL.csv b/tests/workloads/kernel_verbose_2/MI100/SQ_IFETCH_LEVEL.csv index 98c976a3f6..f854ac49cb 100644 --- a/tests/workloads/kernel_verbose_2/MI100/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/kernel_verbose_2/MI100/SQ_IFETCH_LEVEL.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2900505,2900505,1048576,256,0,0,8,8,16,64,0x0,0x7f2c010c8e80,47746,47746,16384,65536,14273,1822376,2187960179232348,2187956421080542,2187956421105022,2187960186697422 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2900505,2900505,1048576,256,0,0,8,8,16,64,0x0,0x7f2c010c8e80,42297,42297,16384,65536,8082,1048584,2187960186722278,2187956421191582,2187956421210622,2187960186997445 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2900505,2900505,1048576,256,0,0,8,8,16,64,0x0,0x7f2c010c8e80,41769,41769,16384,65536,8245,1048576,2187960187030036,2187956421233342,2187956421252222,2187960187186841 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,202183,202183,1048576,256,0,0,8,8,16,64,0x0,0x7fc19df06e80,48930,48930,16384,65536,17387,2236868,194368956320546,194382200379108,194382200403588,194368964074598 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,202183,202183,1048576,256,0,0,8,8,16,64,0x0,0x7fc19df06e80,42369,42369,16384,65536,8129,1048576,194368964088674,194382200591908,194382200610788,194368964418298 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,202183,202183,1048576,256,0,0,8,8,16,64,0x0,0x7fc19df06e80,42036,42036,16384,65536,8251,1048576,194368964450570,194382200632548,194382200651908,194368964637223 diff --git a/tests/workloads/kernel_verbose_2/MI100/SQ_INST_LEVEL_LDS.csv b/tests/workloads/kernel_verbose_2/MI100/SQ_INST_LEVEL_LDS.csv index dd3a6e0f39..302b134e6f 100644 --- a/tests/workloads/kernel_verbose_2/MI100/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/kernel_verbose_2/MI100/SQ_INST_LEVEL_LDS.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2899957,2899957,1048576,256,0,0,8,8,16,64,0x0,0x7fbbd624ee80,0,0,0,2187958826538378,2187956421080542,2187956421105022,2187958834020253 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2899957,2899957,1048576,256,0,0,8,8,16,64,0x0,0x7fbbd624ee80,0,0,0,2187958834041484,2187956421191582,2187956421210622,2187958834340675 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2899957,2899957,1048576,256,0,0,8,8,16,64,0x0,0x7fbbd624ee80,0,0,0,2187958834370150,2187956421233342,2187956421252222,2187958834539098 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,202368,202368,1048576,256,0,0,8,8,16,64,0x0,0x7f56a412ce80,0,0,0,194369449081429,194382200379108,194382200403588,194369456955538 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,202368,202368,1048576,256,0,0,8,8,16,64,0x0,0x7f56a412ce80,0,0,0,194369456972621,194382200591908,194382200610788,194369457310971 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,202368,202368,1048576,256,0,0,8,8,16,64,0x0,0x7f56a412ce80,0,0,0,194369457339004,194382200632548,194382200651908,194369457513895 diff --git a/tests/workloads/kernel_verbose_2/MI100/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/kernel_verbose_2/MI100/SQ_INST_LEVEL_SMEM.csv index 408101e1c5..54604f023c 100644 --- a/tests/workloads/kernel_verbose_2/MI100/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/kernel_verbose_2/MI100/SQ_INST_LEVEL_SMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2898134,2898134,1048576,256,0,0,8,8,16,64,0x0,0x7f03e9ed4e80,65536,210154,26929072,2187953945818611,2187956421080542,2187956421105022,2187953953409471 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2898134,2898134,1048576,256,0,0,8,8,16,64,0x0,0x7f03e9ed4e80,65536,199674,25521392,2187953953429639,2187956421191582,2187956421210622,2187953953728620 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2898134,2898134,1048576,256,0,0,8,8,16,64,0x0,0x7f03e9ed4e80,65536,197510,25271496,2187953953757434,2187956421233342,2187956421252222,2187953953926903 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,202554,202554,1048576,256,0,0,8,8,16,64,0x0,0x7fa8b3c30e80,65536,190140,24309104,194369940413738,194382200379108,194382200403588,194369948055977 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,202554,202554,1048576,256,0,0,8,8,16,64,0x0,0x7fa8b3c30e80,65536,164948,21160952,194369948078049,194382200591908,194382200610788,194369948374541 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,202554,202554,1048576,256,0,0,8,8,16,64,0x0,0x7fa8b3c30e80,65536,192100,24628256,194369948402403,194382200632548,194382200651908,194369948574459 diff --git a/tests/workloads/kernel_verbose_2/MI100/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/kernel_verbose_2/MI100/SQ_INST_LEVEL_VMEM.csv index c317dd97b8..49429e3eec 100644 --- a/tests/workloads/kernel_verbose_2/MI100/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/kernel_verbose_2/MI100/SQ_INST_LEVEL_VMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2901051,2901051,1048576,256,0,0,8,8,16,64,0x0,0x7facd7016e80,32768,647550,82875084,2187961762991823,2187956421080542,2187956421105022,2187961770541516 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2901051,2901051,1048576,256,0,0,8,8,16,64,0x0,0x7facd7016e80,32768,664200,85035268,2187961770563016,2187956421191582,2187956421210622,2187961770852259 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2901051,2901051,1048576,256,0,0,8,8,16,64,0x0,0x7facd7016e80,32768,658638,84299072,2187961770881073,2187956421233342,2187956421252222,2187961771062684 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,202737,202737,1048576,256,0,0,8,8,16,64,0x0,0x7f36814e8e80,32768,653699,83684436,194370432681737,194382200379108,194382200403588,194370440420971 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,202737,202737,1048576,256,0,0,8,8,16,64,0x0,0x7f36814e8e80,32768,669006,85644320,194370440440017,194382200591908,194382200610788,194370440743191 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,202737,202737,1048576,256,0,0,8,8,16,64,0x0,0x7f36814e8e80,32768,683114,87439184,194370440771745,194382200632548,194382200651908,194370440942228 diff --git a/tests/workloads/kernel_verbose_2/MI100/SQ_LEVEL_WAVES.csv b/tests/workloads/kernel_verbose_2/MI100/SQ_LEVEL_WAVES.csv index 1a068e09ce..8426db5bcb 100644 --- a/tests/workloads/kernel_verbose_2/MI100/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/kernel_verbose_2/MI100/SQ_LEVEL_WAVES.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2897406,2897406,1048576,256,0,0,8,8,16,64,0x0,0x7fb39d5dce80,47984,47984,16726,383880,16384,25441686,231715,0,102257768,2187951912738785,2187956421080542,2187956421105022,2187951920318463 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2897406,2897406,1048576,256,0,0,8,8,16,64,0x0,0x7fb39d5dce80,43309,43309,14464,346480,16384,24768705,230365,0,99573884,2187951920345865,2187956421191582,2187956421210622,2187951920680142 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2897406,2897406,1048576,256,0,0,8,8,16,64,0x0,0x7fb39d5dce80,43149,43149,14208,345200,16384,25009147,231524,0,100530896,2187951920718785,2187956421233342,2187956421252222,2187951920903462 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,202926,202926,1048576,256,0,0,8,8,16,64,0x0,0x7f934e4eee80,48771,48771,18480,390176,16384,25511502,237172,0,102544652,194370925985268,194382200379108,194382200403588,194370933763826 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,202926,202926,1048576,256,0,0,8,8,16,64,0x0,0x7f934e4eee80,41866,41866,13148,334936,16384,24344497,229388,0,97861616,194370933793472,194382200591908,194382200610788,194370934145419 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,202926,202926,1048576,256,0,0,8,8,16,64,0x0,0x7f934e4eee80,41674,41674,12445,333400,16384,24426899,230891,0,98192152,194370934183962,194382200632548,194382200651908,194370934372258 diff --git a/tests/workloads/kernel_verbose_2/MI100/pmc_dispatch_info.csv b/tests/workloads/kernel_verbose_2/MI100/pmc_dispatch_info.csv new file mode 100644 index 0000000000..17300ae9af --- /dev/null +++ b/tests/workloads/kernel_verbose_2/MI100/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) ",2 +1,"vecCopy(double*, double*, double*, int, int) ",2 +2,"vecCopy(double*, double*, double*, int, int) ",2 diff --git a/tests/workloads/kernel_verbose_2/MI100/pmc_perf.csv b/tests/workloads/kernel_verbose_2/MI100/pmc_perf.csv index 3830d0b954..fc9c6e019e 100644 --- a/tests/workloads/kernel_verbose_2/MI100/pmc_perf.csv +++ b/tests/workloads/kernel_verbose_2/MI100/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_1,obj_1,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_2,obj_2,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_3,obj_3,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_4,obj_4,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_5,obj_5,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_6,obj_6,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_7,obj_7,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_8,obj_8,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_9,obj_9,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_10,obj_10,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_11,obj_11,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_12,obj_12,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_13,obj_13,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_14,obj_14,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_15,obj_15,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_16,obj_16,TCC_EA_ATOMIC_LEVEL_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f9fdf19ae80,385472,230163,3361145,16384,24571120,144,48,0,48183,48183,3805283.0,2972334.0,5053.0,1148522.0,2161357.0,0.0,2963565.0,2653716.0,383959,240114,48183,0,48183,0,1541856.0,957680.0,0.0,0.0,64,0x7fef60966e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131295.0,0.0,438.0,131294.0,64,0x7fbae49fae80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,141,8195,4240,8336,47,8269,4220,8316,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7fa5d1898e80,1220832,360448,163840,0,0,180224,114688,0,68687848.0,202602714.0,77658520.0,131072.0,0.0,679725.0,0,0,25576,92612.0,0.0,0.0,92612.0,64,0x7f9471fcee80,131072.0,131072.0,0.0,2411113.0,0.0,0.0,136939213.0,61902668.0,64,0x7f2ba4ddce80,8192,0,4096,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7efb49fdae80,32768,0,0,0,16384,16384,393216,22474247,960.0,513927.0,0.0,524288.0,916483.0,32768.0,0,0,0,16228,131072.0,131072.0,0.0,131072.0,64,0x7ff76f0a2e80,185201,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,12454,28838,9884,550,0,46130,262779.0,0.0,188.0,262591.0,64,0x7f2b89346e80,0,48500,0,0,0,48500,0,0,0,48500,0,0,0,48500,0,0,0,48500,0,0,0,48500,0,0,0,48500,0,0,0,48500,0,0,0,48500,0,0,0,48500,0,0,0,48500,0,0,0,48500,0,0,0,48500,0,0,0,48500,0,0,0,48500,0,0,0,48500,0,0,0,48500,0,0,0,48500,0,0,0,48500,0,0,0,48500,0,0,0,48500,0,0,0,48500,0,0,0,48500,0,0,0,48500,0,0,0,48500,0,0,0,48500,0,0,0,48500,0,0,0,48500,0,0,0,48500,0,0,0,48500,0,0,0,48500,0,0,0,48500,0,0,64,0x7fb2824eee80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,38335.0,128948.0,64,0x7f8bb0940e80,2819,0,0,1867607,2607,0,0,1840570,2337,0,0,1821433,1572,0,0,1719428,1362,0,0,1711844,2297,0,0,1861431,5848,0,0,2188286,3019,0,0,1964770,1300,0,0,1859226,2743,0,0,1940526,1259,0,0,1773816,610,0,0,1674588,1252,0,0,1708986,2819,0,0,1907276,1247,0,0,1734729,5209,0,0,2136917,665,0,0,1622106,870,0,0,1701724,2043,0,0,1942797,2430,0,0,1813504,1128,0,0,1707207,3370,0,0,2004885,2549,0,0,1902448,2904,0,0,1940106,4836,0,0,2135663,1112,0,0,1718965,3720,0,0,2025427,6003,0,0,2146261,7493,0,0,2269708,7037,0,0,2222721,4424,0,0,2080713,1917,0,0,1796322,64,0x7fe1a2330e80,0,0,192,0,65536,64471,48,1265,31962,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,538,48031,1745,0,48.0,341.0,0.0,262288.0,64,0x7f95fad26e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86640.0,44432.0,131112.0,0.0,64,0x7f0ea1118e80,0,2702465,4096,4096,0,2968342,4096,4096,0,3948384,4096,4096,0,2930229,4096,4096,0,2299303,4096,4096,0,2527980,4096,4096,0,4510200,4096,4096,0,3959030,4096,4096,0,2865890,4096,4096,0,2848581,4096,4096,0,2466468,4096,4096,0,3645585,4096,4096,0,2318990,4096,4096,0,3110714,4096,4096,0,2927073,4096,4096,0,4525752,4096,4096,0,2785635,4096,4096,0,3364282,4096,4096,0,5259951,4096,4096,0,3397334,4096,4096,0,2226473,4096,4096,0,4693524,4096,4096,0,2860226,4096,4096,0,3015175,4096,4096,0,2131512,4096,4096,0,2622864,4096,4096,0,3138845,4096,4096,0,2752440,4096,4096,0,3256783,4096,4096,0,2366614,4096,4096,0,2865592,4096,4096,0,3651969,4096,4096,64,0x7fb8efae6e80,4096,0,2336,0,4096,0,408,0,4096,0,0,0,4096,0,794,0,4096,0,1330,0,4096,0,7718,0,4096,0,0,0,4096,0,1893,0,4096,0,1662,0,4290,0,3189,0,4096,0,46,0,4096,0,1690,0,4096,0,511,0,4096,0,46,0,4096,0,4832,0,4096,0,815,0,4096,0,1244,0,4096,0,2854,0,4096,0,1330,0,4096,0,1294,0,4096,0,1790,0,4096,0,1624,0,4096,0,0,0,4096,0,919,0,4096,0,966,0,4096,0,1211,0,4144,0,1065,0,4096,0,1179,0,4096,0,508,0,4099,0,54,0,4096,0,0,0,4097,0,4335,0,64,0x7f0f2a89ae80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,47764,0,131603.0,131072.0,0.0,131104.0,64,0x7fc5e1a80e80,0.0,2187956421080542,2187956421105022 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f9fdf19ae80,344608,230842,3369715,16384,24398928,0,48,0,43075,43075,3752906.0,3050855.0,5063.0,1129650.0,2209154.0,0.0,3041493.0,2732182.0,344600,240637,43075,0,43075,0,1378400.0,820406.0,0.0,0.0,64,0x7fef60966e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131269.0,0.0,392.0,131268.0,64,0x7fbae49fae80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8258,4209,8305,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,64,0x7fa5d1898e80,700996,360448,163840,0,0,180224,114688,0,72911003.0,204421678.0,78034581.0,131072.0,0.0,629703.0,0,0,25052,53408.0,0.0,0.0,53408.0,64,0x7f9471fcee80,131072.0,131072.0,0.0,2591772.0,0.0,0.0,94620987.0,46570335.0,64,0x7f2ba4ddce80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7efb49fdae80,32768,0,0,0,16384,16384,393216,22231720,960.0,513967.0,0.0,524288.0,912117.0,32768.0,0,0,0,14283,86875.0,86875.0,0.0,86875.0,64,0x7ff76f0a2e80,186054,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,15031,31415,18658,6717,0,40931,262748.0,0.0,47.0,262701.0,64,0x7f2b89346e80,0,43615,0,0,0,43615,0,0,0,43615,0,0,0,43615,0,0,0,43615,0,0,0,43615,0,0,0,43615,0,0,0,43615,0,0,0,43615,0,0,0,43615,0,0,0,43615,0,0,0,43615,0,0,0,43615,0,0,0,43615,0,0,0,43615,0,0,0,43615,0,0,0,43615,0,0,0,43615,0,0,0,43615,0,0,0,43615,0,0,0,43615,0,0,0,43615,0,0,0,43615,0,0,0,43615,0,0,0,43615,0,0,0,43615,0,0,0,43615,0,0,0,43615,0,0,0,43615,0,0,0,43615,0,0,0,43615,0,0,0,43615,0,0,64,0x7fb2824eee80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,38636.0,131209.0,64,0x7f8bb0940e80,1907,0,0,1562547,1978,0,0,1488000,3995,0,0,1640439,3126,0,0,1522255,3954,0,0,1684634,2181,0,0,1458892,3040,0,0,1537078,3259,0,0,1622131,5741,0,0,1798129,2614,0,0,1660018,3999,0,0,1561617,2611,0,0,1563101,3329,0,0,1551755,5727,0,0,1761969,3631,0,0,1639616,5299,0,0,1744315,3630,0,0,1602835,1470,0,0,1433110,4868,0,0,1746851,3214,0,0,1581729,4516,0,0,1581310,2394,0,0,1555749,3653,0,0,1544430,2045,0,0,1547306,3914,0,0,1568848,1865,0,0,1504095,5058,0,0,1651877,4068,0,0,1655456,5445,0,0,1684476,1718,0,0,1451581,3199,0,0,1518015,3594,0,0,1623054,64,0x7fe1a2330e80,0,0,48,0,65536,65536,0,0,30529,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,457,42617,1751,0,48.0,339.0,0.0,262144.0,64,0x7f95fad26e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86747.0,44325.0,131114.0,0.0,64,0x7f0ea1118e80,0,4394178,2699,2699,0,3828136,2684,2684,0,5554649,2664,2664,0,2934992,2706,2706,0,2933309,2692,2692,0,3005210,2716,2716,0,4177724,2718,2718,0,4113707,2728,2728,0,3460435,2694,2694,0,3653003,2680,2680,0,4099559,2702,2702,0,5024661,2746,2746,0,3775368,2694,2694,0,3409539,2674,2674,0,3786684,2711,2711,0,3296458,2698,2698,0,4599812,2694,2694,0,3642696,2700,2700,0,3124988,2689,2689,0,4181755,2718,2718,0,3238100,2696,2696,0,3251622,2724,2724,0,4057205,2678,2678,0,2997968,2714,2714,0,3575373,2676,2676,0,3964742,2700,2700,0,2706825,2736,2736,0,2774947,2728,2728,0,2938074,2686,2686,0,4529475,2680,2680,0,2770085,2710,2710,0,4707613,2694,2694,64,0x7fb8efae6e80,4096,0,7493,0,4096,0,866,0,4096,0,301,0,4096,0,862,0,4096,0,1155,0,4098,0,1813,0,4096,0,1241,0,4096,0,538,0,4096,0,2378,0,4285,0,6217,0,4097,0,717,0,4096,0,7651,0,4096,0,543,0,4096,0,884,0,4096,0,6801,0,4096,0,0,0,4096,0,3534,0,4096,0,1400,0,4096,0,1533,0,4098,0,1373,0,4096,0,320,0,4096,0,944,0,4096,0,917,0,4096,0,0,0,4096,0,2027,0,4096,0,1037,0,4144,0,2597,0,4097,0,831,0,4096,0,1204,0,4096,0,779,0,4096,0,108,0,4097,0,4623,0,64,0x7f0f2a89ae80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,5728,38806,0,131468.0,131072.0,0.0,86486.0,64,0x7fc5e1a80e80,0.0,2187956421191582,2187956421210622 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f9fdf19ae80,355912,232243,3357922,16384,24494763,0,48,0,44488,44488,3773741.0,3065880.0,5821.0,1007650.0,2253718.0,0.0,3056986.0,2747829.0,355904,242031,44488,0,44488,0,1423616.0,833619.0,0.0,0.0,64,0x7fef60966e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131257.0,0.0,368.0,131256.0,64,0x7fbae49fae80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8298,4249,8345,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,64,0x7fa5d1898e80,836880,360448,163840,0,0,180224,114688,0,71761939.0,194898442.0,75315443.0,131072.0,0.0,573050.0,0,0,24810,74108.0,0.0,0.0,74108.0,64,0x7f9471fcee80,131072.0,131072.0,0.0,2463934.0,0.0,0.0,136608997.0,48171621.0,64,0x7f2ba4ddce80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7efb49fdae80,32768,0,0,0,16384,16384,393216,22950212,960.0,513939.0,0.0,524288.0,916518.0,32768.0,0,0,0,13658,86336.0,86336.0,0.0,86336.0,64,0x7ff76f0a2e80,188954,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13671,30055,8509,3310,0,41285,262639.0,0.0,47.0,262592.0,64,0x7f2b89346e80,0,42975,0,0,0,42975,0,0,0,42975,0,0,0,42975,0,0,0,42975,0,0,0,42975,0,0,0,42975,0,0,0,42975,0,0,0,42975,0,0,0,42975,0,0,0,42975,0,0,0,42975,0,0,0,42975,0,0,0,42975,0,0,0,42975,0,0,0,42975,0,0,0,42975,0,0,0,42975,0,0,0,42975,0,0,0,42975,0,0,0,42975,0,0,0,42975,0,0,0,42975,0,0,0,42975,0,0,0,42975,0,0,0,42975,0,0,0,42975,0,0,0,42975,0,0,0,42975,0,0,0,42975,0,0,0,42975,0,0,0,42975,0,0,64,0x7fb2824eee80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,47527.0,128478.0,64,0x7f8bb0940e80,2203,0,0,1450570,1367,0,0,1264215,2158,0,0,1458086,4094,0,0,1581867,1251,0,0,1357694,1862,0,0,1410380,2668,0,0,1483412,3200,0,0,1564150,2869,0,0,1547399,1200,0,0,1286749,1080,0,0,1343382,1137,0,0,1349544,1790,0,0,1402803,493,0,0,1244526,4246,0,0,1734795,3522,0,0,1611115,2342,0,0,1474327,203,0,0,1202956,2228,0,0,1510712,3818,0,0,1661125,4004,0,0,1532580,1563,0,0,1427336,4678,0,0,1776946,6665,0,0,1876195,4530,0,0,1675885,2283,0,0,1506745,2968,0,0,1557448,3918,0,0,1565434,3430,0,0,1561515,1040,0,0,1303631,1330,0,0,1340408,1764,0,0,1383282,64,0x7fe1a2330e80,0,0,48,0,65536,65536,0,0,31032,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,457,43169,1753,0,48.0,291.0,0.0,262144.0,64,0x7f95fad26e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86317.0,0.0,131112.0,0.0,64,0x7f0ea1118e80,0,3096100,2697,2697,0,3873452,2692,2692,0,5382216,2671,2671,0,5006954,2736,2736,0,4263879,2690,2690,0,3787930,2712,2712,0,4645021,2716,2716,0,4472086,2696,2696,0,3214361,2694,2694,0,4583128,2666,2666,0,3938062,2716,2716,0,4800212,2744,2744,0,3515474,2696,2696,0,4103906,2676,2676,0,4636889,2676,2676,0,3731415,2714,2714,0,3787790,2696,2696,0,4680795,2696,2696,0,4103360,2684,2684,0,4900447,2716,2716,0,3980081,2695,2695,0,4563054,2738,2738,0,3578749,2680,2680,0,3543195,2716,2716,0,2787290,2692,2692,0,3038717,2680,2680,0,4236860,2720,2720,0,3679305,2726,2726,0,3665649,2700,2700,0,2968461,2687,2687,0,4725569,2704,2704,0,4915911,2710,2710,64,0x7fb8efae6e80,4096,0,1785,0,4096,0,522,0,4096,0,246,0,4096,0,2062,0,4096,0,294,0,4098,0,1104,0,4096,0,4181,0,4096,0,6051,0,4096,0,1636,0,4281,0,4495,0,4097,0,1485,0,4096,0,2732,0,4096,0,122,0,4096,0,80,0,4096,0,4131,0,4096,0,192,0,4096,0,143,0,4096,0,815,0,4096,0,3630,0,4098,0,4681,0,4096,0,0,0,4096,0,4211,0,4096,0,312,0,4096,0,134,0,4096,0,564,0,4096,0,2296,0,4144,0,132,0,4097,0,239,0,4096,0,0,0,4096,0,832,0,4096,0,1783,0,4097,0,6402,0,64,0x7f0f2a89ae80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,3897,38884,0,131465.0,131072.0,0.0,86759.0,64,0x7fc5e1a80e80,0.0,2187956421233342,2187956421252222 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_1,obj_1,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_2,obj_2,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_3,obj_3,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_4,obj_4,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_5,obj_5,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_6,obj_6,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_7,obj_7,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_8,obj_8,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_9,obj_9,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_10,obj_10,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_11,obj_11,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_12,obj_12,TCC_EA_ATOMIC_LEVEL_sum,wave_size_13,obj_13,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_14,obj_14,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_15,obj_15,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_16,obj_16,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f156a44ae80,0,8192,4096,8192,0,8240,4144,8240,141,8195,4240,8336,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8414,4318,8414,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f76e1e78e80,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,64,0x7fb737450e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131232.0,0.0,312.0,131231.0,64,0x7f77cd934e80,4096,0,6931,0,4096,0,86,0,4099,0,4591,0,4144,0,4396,0,4096,0,2462,0,4096,0,1204,0,4096,0,240,0,4096,0,3053,0,4096,0,1650,0,4096,0,1004,0,4144,0,1807,0,4096,0,2289,0,4096,0,43,0,4096,0,0,0,4096,0,2384,0,4096,0,756,0,4096,0,830,0,4096,0,2200,0,4096,0,5759,0,4096,0,754,0,4096,0,1971,0,4096,0,975,0,4096,0,339,0,4096,0,277,0,4366,0,6200,0,4096,0,1188,0,4096,0,5341,0,4096,0,59,0,4097,0,0,0,4096,0,83,0,4096,0,31,0,4096,0,433,0,64,0x7f23fefece80,0,3973094,4096,4096,0,3575095,4096,4096,0,3090678,4096,4096,0,2557002,4096,4096,0,3684560,4096,4096,0,3032625,4096,4096,0,3145760,4096,4096,0,3469629,4096,4096,0,3888860,4096,4096,0,4837539,4096,4096,0,2450672,4096,4096,0,2740624,4096,4096,0,5153327,4096,4096,0,3254310,4096,4096,0,3042508,4096,4096,0,2569101,4096,4096,0,4718010,4096,4096,0,3977840,4096,4096,0,2877048,4096,4096,0,2531062,4096,4096,0,3926983,4096,4096,0,3297509,4096,4096,0,3423963,4096,4096,0,2482331,4096,4096,0,2530588,4096,4096,0,3609441,4096,4096,0,3337674,4096,4096,0,2641930,4096,4096,0,2908298,4096,4096,0,2965224,4096,4096,0,2802934,4096,4096,0,2879762,4096,4096,64,0x7ff447138e80,2224134,360448,163840,0,0,180224,114688,0,68011968.0,193155059.0,77936326.0,131072.0,0.0,698182.0,0,0,26674,131108.0,0.0,0.0,131108.0,64,0x7fe9eb506e80,381808,232935,3412645,16384,25113165,144,48,0,47725,47725,3846402.0,2986823.0,7299.0,1104437.0,2045534.0,0.0,2977750.0,2665854.0,380351,242860,47725,0,47725,0,1527200.0,956122.0,0.0,0.0,64,0x7fd2f5ab2e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86344.0,44728.0,131111.0,0.0,64,0x7f63c13d4e80,189379,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,11954,28338,9839,550,0,46475,262706.0,0.0,188.0,262518.0,64,0x7f8f2282ae80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,46926,0,131517.0,131072.0,0.0,131104.0,64,0x7fea86a3ee80,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f3459734e80,32768,0,0,0,16384,16384,393216,22921941,960.0,513901.0,0.0,524288.0,1098033.0,32768.0,0,0,0,17873,131072.0,131072.0,0.0,131072.0,64,0x7f35166c4e80,0.0,64,0x7f4fbfe06e80,0,0,192,0,65536,64369,48,1511,31068,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,538,47104,1767,0,48.0,219.0,0.0,262288.0,64,0x7f6057aaee80,5927,0,0,2166326,3261,0,0,1982388,6005,0,0,2255863,4438,0,0,1919764,4487,0,0,2102843,4740,0,0,2098259,6067,0,0,2136986,4192,0,0,1962012,3487,0,0,1943608,2487,0,0,1886355,5788,0,0,2053919,5772,0,0,2090662,3938,0,0,1996591,4695,0,0,2036435,5862,0,0,2145962,5951,0,0,2131657,3405,0,0,1997465,3068,0,0,1950682,4782,0,0,2166745,4975,0,0,2032355,5815,0,0,2129578,3946,0,0,2029762,6564,0,0,2212734,5237,0,0,2093705,5910,0,0,2166414,2014,0,0,1827861,5759,0,0,2055192,5235,0,0,1999912,5892,0,0,2183682,2944,0,0,1948454,5917,0,0,2141567,2711,0,0,1867756,64,0x7f70efdd8e80,131072.0,131072.0,0.0,2581687.0,0.0,0.0,121433529.0,60798872.0,64,0x7f97be568e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,48226.0,131089.0,194382200379108,194382200403588 +1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f156a44ae80,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8240,4144,8240,47,8193,4144,8240,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8429,4333,8429,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f76e1e78e80,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,64,0x7fb737450e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131320.0,0.0,494.0,131319.0,64,0x7f77cd934e80,4096,0,1905,0,4096,0,4711,0,4096,0,3579,0,4144,0,172,0,4096,0,1310,0,4096,0,19,0,4096,0,71,0,4096,0,0,0,4097,0,1396,0,4096,0,1499,0,4144,0,780,0,4096,0,815,0,4096,0,567,0,4096,0,1944,0,4096,0,675,0,4100,0,0,0,4096,0,3990,0,4096,0,6756,0,4096,0,210,0,4096,0,1110,0,4096,0,388,0,4096,0,6753,0,4096,0,1200,0,4096,0,0,0,4382,0,4061,0,4096,0,57,0,4096,0,208,0,4096,0,0,0,4097,0,596,0,4096,0,0,0,4096,0,521,0,4096,0,52,0,64,0x7f23fefece80,0,3024263,2724,2724,0,3189694,2724,2724,0,3359847,2708,2708,0,3204889,2722,2722,0,4239198,2712,2712,0,2762119,2708,2708,0,4362490,2746,2746,0,3494543,2710,2710,0,3305691,2738,2738,0,2719735,2698,2698,0,4323178,2759,2759,0,4032834,2720,2720,0,3455208,2702,2702,0,3023765,2698,2698,0,3166339,2748,2748,0,3185943,2712,2712,0,5100369,2704,2704,0,3467488,2732,2732,0,4596794,2744,2744,0,3330846,2716,2716,0,3553629,2708,2708,0,2840479,2766,2766,0,2800857,2730,2730,0,2691871,2700,2700,0,3117780,2702,2702,0,2872134,2705,2705,0,3983009,2773,2773,0,3227016,2702,2702,0,2978795,2737,2737,0,2716404,2723,2723,0,3975822,2756,2756,0,3357948,2706,2706,64,0x7ff447138e80,1498978,360448,163840,0,0,180224,114688,0,70684587.0,172980258.0,72840260.0,131072.0,0.0,669839.0,0,0,26021,65159.0,0.0,0.0,65159.0,64,0x7fe9eb506e80,349008,236258,3458074,16384,25329802,0,48,0,43625,43625,3833472.0,3059966.0,7249.0,1092242.0,2075811.0,0.0,3051125.0,2739341.0,349000,245775,43625,0,43625,0,1396000.0,816958.0,0.0,0.0,64,0x7fd2f5ab2e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,49778.0,36901.0,30414.0,0.0,64,0x7f63c13d4e80,183800,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,14772,31156,8646,2409,0,41077,262573.0,0.0,47.0,262526.0,64,0x7f8f2282ae80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,2779,40304,0,131359.0,131072.0,0.0,86739.0,64,0x7fea86a3ee80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f3459734e80,32768,0,0,0,16384,16384,393216,23804899,1120.0,512122.0,0.0,524288.0,1383396.0,32768.0,0,0,0,22988,129842.0,129842.0,0.0,129842.0,64,0x7f35166c4e80,0.0,64,0x7f4fbfe06e80,0,0,96,0,65536,65559,0,0,34236,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,505,49836,6552,0,96.0,439.0,0.0,262144.0,64,0x7f6057aaee80,1342,0,0,1357706,3088,0,0,1560245,1132,0,0,1425286,1786,0,0,1492138,406,0,0,1137309,1815,0,0,1491560,1686,0,0,1417614,3704,0,0,1639531,330,0,0,1118683,2116,0,0,1446658,1342,0,0,1345317,385,0,0,1287878,1411,0,0,1388963,1533,0,0,1554974,93,0,0,1202262,1847,0,0,1468069,640,0,0,1268551,1030,0,0,1486093,2230,0,0,1568133,2554,0,0,1393206,1138,0,0,1394563,2029,0,0,1418829,4734,0,0,1700618,1901,0,0,1532860,1723,0,0,1360382,1933,0,0,1427951,666,0,0,1290575,3725,0,0,1639430,702,0,0,1230480,5272,0,0,1740161,1313,0,0,1350818,2998,0,0,1550864,64,0x7f70efdd8e80,131072.0,131072.0,0.0,2765054.0,0.0,0.0,105015707.0,39728540.0,64,0x7f97be568e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,28341.0,88900.0,194382200591908,194382200610788 +2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f156a44ae80,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8240,4144,8240,47,8193,4144,8240,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8473,4377,8473,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f76e1e78e80,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,64,0x7fb737450e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131237.0,0.0,328.0,131236.0,64,0x7f77cd934e80,4096,0,3095,0,4096,0,3086,0,4096,0,2542,0,4144,0,1015,0,4096,0,3921,0,4096,0,2973,0,4096,0,3175,0,4096,0,925,0,4097,0,7725,0,4096,0,4269,0,4144,0,3359,0,4096,0,4690,0,4096,0,4468,0,4096,0,6071,0,4096,0,4591,0,4100,0,2176,0,4096,0,7363,0,4096,0,1908,0,4096,0,2715,0,4096,0,908,0,4096,0,3838,0,4096,0,3632,0,4096,0,1443,0,4096,0,510,0,4304,0,8034,0,4096,0,3350,0,4096,0,1958,0,4096,0,2337,0,4097,0,2420,0,4096,0,1224,0,4096,0,103,0,4096,0,800,0,64,0x7f23fefece80,0,3349150,2756,2756,0,3793384,2760,2760,0,3130678,2684,2684,0,3139875,2708,2708,0,4089862,2728,2728,0,3224165,2748,2748,0,2954370,2736,2736,0,3165260,2726,2726,0,4504655,2736,2736,0,3641152,2694,2694,0,3539525,2716,2716,0,3152590,2704,2704,0,3651449,2728,2728,0,3656055,2700,2700,0,3028050,2720,2720,0,3432579,2710,2710,0,4720728,2702,2702,0,4212986,2728,2728,0,3313882,2708,2708,0,3448004,2700,2700,0,3423245,2710,2710,0,3323042,2759,2759,0,3280038,2704,2704,0,2738710,2680,2680,0,2954379,2713,2713,0,3669247,2717,2717,0,2814013,2700,2700,0,3010430,2708,2708,0,3044370,2743,2743,0,4001444,2745,2745,0,3228176,2680,2680,0,3191296,2714,2714,64,0x7ff447138e80,2443266,360448,163840,0,0,180224,114688,0,64777445.0,179145628.0,71679788.0,131072.0,0.0,863837.0,0,0,25996,109718.0,0.0,0.0,109718.0,64,0x7fe9eb506e80,342280,230418,3382281,16384,24778089,0,48,0,42784,42784,3745777.0,3046045.0,6539.0,1086510.0,2113631.0,0.0,3037163.0,2725311.0,342272,239741,42784,0,42784,0,1369088.0,807240.0,0.0,0.0,64,0x7fd2f5ab2e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86383.0,0.0,131112.0,0.0,64,0x7f63c13d4e80,188456,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,11101,27485,8717,2465,0,42240,262548.0,0.0,47.0,262501.0,64,0x7f8f2282ae80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,2860,40281,0,131392.0,131072.0,0.0,86551.0,64,0x7fea86a3ee80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f3459734e80,32768,0,0,0,16384,16384,393216,23804305,960.0,513922.0,0.0,524288.0,1174041.0,32768.0,0,0,0,14263,86641.0,86641.0,0.0,86641.0,64,0x7f35166c4e80,0.0,64,0x7f4fbfe06e80,0,0,48,0,65536,65536,0,0,30145,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,457,41433,1743,0,48.0,270.0,0.0,262144.0,64,0x7f6057aaee80,4035,0,0,1623242,2124,0,0,1501904,2205,0,0,1476320,5433,0,0,1646903,2328,0,0,1484069,3395,0,0,1534251,3545,0,0,1574752,5006,0,0,1624070,3314,0,0,1600346,4030,0,0,1695220,3079,0,0,1538954,3129,0,0,1505311,3468,0,0,1511261,3188,0,0,1462399,1180,0,0,1352653,5031,0,0,1555926,4079,0,0,1636492,2597,0,0,1468386,549,0,0,1222899,4525,0,0,1539683,4307,0,0,1585037,3242,0,0,1555900,2048,0,0,1458957,4678,0,0,1597845,4747,0,0,1594757,3341,0,0,1570089,3538,0,0,1566549,4498,0,0,1526048,6115,0,0,1688727,2321,0,0,1476960,5009,0,0,1757596,4105,0,0,1615484,64,0x7f70efdd8e80,131072.0,131072.0,0.0,2557270.0,0.0,0.0,124629672.0,47819336.0,64,0x7f97be568e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,33750.0,115087.0,194382200632548,194382200651908 diff --git a/tests/workloads/kernel_verbose_2/MI100/sysinfo.csv b/tests/workloads/kernel_verbose_2/MI100/sysinfo.csv index 38735b85b1..630f57ae2a 100644 --- a/tests/workloads/kernel_verbose_2/MI100/sysinfo.csv +++ b/tests/workloads/kernel_verbose_2/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -kernel_verbose_2,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Fri Mar 1 16:47:41 2024 (CST),1,t006-003.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651240,,5.7.1-98,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +kernel_verbose_2,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 07 Mar 2024 01:10:33 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/kernel_verbose_2/MI100/timestamps.csv b/tests/workloads/kernel_verbose_2/MI100/timestamps.csv index c7f655164c..74c2c44d45 100644 --- a/tests/workloads/kernel_verbose_2/MI100/timestamps.csv +++ b/tests/workloads/kernel_verbose_2/MI100/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,2899047,2899047,1048576,256,0,0,8,8,16,64,0x0,0x7f06059fce80,2187956421054721,2187956421080542,2187956421105022,2187956421116136 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,2899047,2899047,1048576,256,0,0,8,8,16,64,0x0,0x7f06059fce80,2187956421118010,2187956421191582,2187956421210622,2187956421211836 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,2899047,2899047,1048576,256,0,0,8,8,16,64,0x0,0x7f06059fce80,2187956421222666,2187956421233342,2187956421252222,2187956421253264 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,206324,206324,1048576,256,0,0,8,8,16,64,0x0,0x7f7f525aee80,194382200353481,194382200379108,194382200403588,194382200418083 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,206324,206324,1048576,256,0,0,8,8,16,64,0x0,0x7f7f525aee80,194382200416540,194382200591908,194382200610788,194382200612441 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,206324,206324,1048576,256,0,0,8,8,16,64,0x0,0x7f7f525aee80,194382200623271,194382200632548,194382200651908,194382200653348 diff --git a/tests/workloads/kernel_verbose_2/MI200/SQ_IFETCH_LEVEL.csv b/tests/workloads/kernel_verbose_2/MI200/SQ_IFETCH_LEVEL.csv new file mode 100644 index 0000000000..94b724a48b --- /dev/null +++ b/tests/workloads/kernel_verbose_2/MI200/SQ_IFETCH_LEVEL.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,368475,368475,1048576,256,0,0,8,0,16,64,0x0,0x7ffb08e3cec0,27564,27564,16384,65536,13515,1533580,200161368579796,200174259821413,200174259842053,200161385412590 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,368475,368475,1048576,256,0,0,8,0,16,64,0x0,0x7ffb08e3cec0,41380,41380,16384,65536,9363,1048672,200161385434030,200174259860293,200174259876453,200161385706686 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,368475,368475,1048576,256,0,0,8,0,16,64,0x0,0x7ffb08e3cec0,42124,42124,16384,65536,9450,1048648,200161385736292,200174259950853,200174259967493,200161385875185 diff --git a/tests/workloads/kernel_verbose_2/MI200/SQ_INST_LEVEL_LDS.csv b/tests/workloads/kernel_verbose_2/MI200/SQ_INST_LEVEL_LDS.csv new file mode 100644 index 0000000000..4b91723d21 --- /dev/null +++ b/tests/workloads/kernel_verbose_2/MI200/SQ_INST_LEVEL_LDS.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,368658,368658,1048576,256,0,0,8,0,16,64,0x0,0x7f1d2a670ec0,0,0,0,200161856840122,200174259821413,200174259842053,200161872800946 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,368658,368658,1048576,256,0,0,8,0,16,64,0x0,0x7f1d2a670ec0,0,0,0,200161872820553,200174259860293,200174259876453,200161873098529 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,368658,368658,1048576,256,0,0,8,0,16,64,0x0,0x7f1d2a670ec0,0,0,0,200161873124929,200174259950853,200174259967493,200161873321250 diff --git a/tests/workloads/kernel_verbose_2/MI200/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/kernel_verbose_2/MI200/SQ_INST_LEVEL_SMEM.csv new file mode 100644 index 0000000000..ab70ba9365 --- /dev/null +++ b/tests/workloads/kernel_verbose_2/MI200/SQ_INST_LEVEL_SMEM.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,368859,368859,1048576,256,0,0,8,0,16,64,0x0,0x7f3ec6f68ec0,65536,192258,21467752,200162338737471,200174259821413,200174259842053,200162354523133 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,368859,368859,1048576,256,0,0,8,0,16,64,0x0,0x7f3ec6f68ec0,65536,262844,29388808,200162354541568,200174259860293,200174259876453,200162354807732 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,368859,368859,1048576,256,0,0,8,0,16,64,0x0,0x7f3ec6f68ec0,65536,256738,28673856,200162354833330,200174259950853,200174259967493,200162354984777 diff --git a/tests/workloads/kernel_verbose_2/MI200/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/kernel_verbose_2/MI200/SQ_INST_LEVEL_VMEM.csv new file mode 100644 index 0000000000..fce6e99566 --- /dev/null +++ b/tests/workloads/kernel_verbose_2/MI200/SQ_INST_LEVEL_VMEM.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,369043,369043,1048576,256,0,0,8,0,16,64,0x0,0x7f6e427c4ec0,32768,287066,32165360,200162820253779,200174259821413,200174259842053,200162835982564 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,369043,369043,1048576,256,0,0,8,0,16,64,0x0,0x7f6e427c4ec0,32768,568990,63732840,200162836000868,200174259860293,200174259876453,200162836321695 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,369043,369043,1048576,256,0,0,8,0,16,64,0x0,0x7f6e427c4ec0,32768,590916,66182320,200162836347424,200174259950853,200174259967493,200162836509170 diff --git a/tests/workloads/kernel_verbose_2/MI200/SQ_LEVEL_WAVES.csv b/tests/workloads/kernel_verbose_2/MI200/SQ_LEVEL_WAVES.csv new file mode 100644 index 0000000000..9cacae8857 --- /dev/null +++ b/tests/workloads/kernel_verbose_2/MI200/SQ_LEVEL_WAVES.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,369226,369226,1048576,256,0,0,8,0,16,64,0x0,0x7f982e044ec0,28181,28181,10938,225456,16384,11281842,134087,0,45624964,200163302335206,200174259821413,200174259842053,200163317930148 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,369226,369226,1048576,256,0,0,8,0,16,64,0x0,0x7f982e044ec0,41120,41120,13245,328968,16384,19597753,226880,0,78874180,200163317957940,200174259860293,200174259876453,200163318228011 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,369226,369226,1048576,256,0,0,8,0,16,64,0x0,0x7f982e044ec0,40436,40436,12974,323496,16384,19482902,222930,0,78428532,200163318263278,200174259950853,200174259967493,200163318411007 diff --git a/tests/workloads/kernel_verbose_2/MI200/perfmon/SQ_IFETCH_LEVEL.txt b/tests/workloads/kernel_verbose_2/MI200/perfmon/SQ_IFETCH_LEVEL.txt new file mode 100644 index 0000000000..293092f641 --- /dev/null +++ b/tests/workloads/kernel_verbose_2/MI200/perfmon/SQ_IFETCH_LEVEL.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_2/MI200/perfmon/SQ_INST_LEVEL_LDS.txt b/tests/workloads/kernel_verbose_2/MI200/perfmon/SQ_INST_LEVEL_LDS.txt new file mode 100644 index 0000000000..08439eedce --- /dev/null +++ b/tests/workloads/kernel_verbose_2/MI200/perfmon/SQ_INST_LEVEL_LDS.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_2/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt b/tests/workloads/kernel_verbose_2/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt new file mode 100644 index 0000000000..6cca322d4e --- /dev/null +++ b/tests/workloads/kernel_verbose_2/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_2/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt b/tests/workloads/kernel_verbose_2/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt new file mode 100644 index 0000000000..e527ad31ba --- /dev/null +++ b/tests/workloads/kernel_verbose_2/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_2/MI200/perfmon/SQ_LEVEL_WAVES.txt b/tests/workloads/kernel_verbose_2/MI200/perfmon/SQ_LEVEL_WAVES.txt new file mode 100644 index 0000000000..3f8e04adb3 --- /dev/null +++ b/tests/workloads/kernel_verbose_2/MI200/perfmon/SQ_LEVEL_WAVES.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_0.txt b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_0.txt new file mode 100644 index 0000000000..4ffdc32149 --- /dev/null +++ b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_0.txt @@ -0,0 +1,5 @@ +pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES SQ_INSTS_VALU_CVT SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU GRBM_COUNT GRBM_GUI_ACTIVE TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum TA_TA_BUSY_sum TA_BUFFER_WAVEFRONTS_sum TD_TD_BUSY_sum TD_TC_STALL_sum SPI_CSN_WINDOW_VALID SPI_CSN_BUSY CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_1.txt b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_1.txt new file mode 100644 index 0000000000..6c277f4a37 --- /dev/null +++ b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_1.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VSKIPPED SQ_INSTS SQ_INSTS_VALU SQ_INSTS_VALU_ADD_F16 SQ_INSTS_VALU_MUL_F16 SQ_INSTS_VALU_FMA_F16 SQ_INSTS_VALU_TRANS_F16 SQ_INSTS_VALU_ADD_F32 GRBM_SPI_BUSY TCP_READ_TAGCONFLICT_STALL_CYCLES_sum TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum TCP_TA_TCP_STATE_READ_sum TA_BUFFER_READ_WAVEFRONTS_sum TA_BUFFER_WRITE_WAVEFRONTS_sum TD_SPI_STALL_sum TD_LOAD_WAVEFRONT_sum SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_10.txt b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_10.txt new file mode 100644 index 0000000000..7053d4dce6 --- /dev/null +++ b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_10.txt @@ -0,0 +1,5 @@ +pmc: SQC_TC_DATA_WRITE_REQ SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_11.txt b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_11.txt new file mode 100644 index 0000000000..77ae8b461f --- /dev/null +++ b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_11.txt @@ -0,0 +1,5 @@ +pmc: SQC_ICACHE_MISSES_DUPLICATE SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_12.txt b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_12.txt new file mode 100644 index 0000000000..dfb2cf65e5 --- /dev/null +++ b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_12.txt @@ -0,0 +1,5 @@ +pmc: SQC_DCACHE_REQ_READ_1 SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_13.txt b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_13.txt new file mode 100644 index 0000000000..062fc9644a --- /dev/null +++ b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_13.txt @@ -0,0 +1,5 @@ +pmc: TCC_ATOMIC[0] TCC_CYCLE[0] TCC_EA_ATOMIC[0] TCC_EA_ATOMIC_LEVEL[0] TCC_ATOMIC[1] TCC_CYCLE[1] TCC_EA_ATOMIC[1] TCC_EA_ATOMIC_LEVEL[1] TCC_ATOMIC[2] TCC_CYCLE[2] TCC_EA_ATOMIC[2] TCC_EA_ATOMIC_LEVEL[2] TCC_ATOMIC[3] TCC_CYCLE[3] TCC_EA_ATOMIC[3] TCC_EA_ATOMIC_LEVEL[3] TCC_ATOMIC[4] TCC_CYCLE[4] TCC_EA_ATOMIC[4] TCC_EA_ATOMIC_LEVEL[4] TCC_ATOMIC[5] TCC_CYCLE[5] TCC_EA_ATOMIC[5] TCC_EA_ATOMIC_LEVEL[5] TCC_ATOMIC[6] TCC_CYCLE[6] TCC_EA_ATOMIC[6] TCC_EA_ATOMIC_LEVEL[6] TCC_ATOMIC[7] TCC_CYCLE[7] TCC_EA_ATOMIC[7] TCC_EA_ATOMIC_LEVEL[7] TCC_ATOMIC[8] TCC_CYCLE[8] TCC_EA_ATOMIC[8] TCC_EA_ATOMIC_LEVEL[8] TCC_ATOMIC[9] TCC_CYCLE[9] TCC_EA_ATOMIC[9] TCC_EA_ATOMIC_LEVEL[9] TCC_ATOMIC[10] TCC_CYCLE[10] TCC_EA_ATOMIC[10] TCC_EA_ATOMIC_LEVEL[10] TCC_ATOMIC[11] TCC_CYCLE[11] TCC_EA_ATOMIC[11] TCC_EA_ATOMIC_LEVEL[11] TCC_ATOMIC[12] TCC_CYCLE[12] TCC_EA_ATOMIC[12] TCC_EA_ATOMIC_LEVEL[12] TCC_ATOMIC[13] TCC_CYCLE[13] TCC_EA_ATOMIC[13] TCC_EA_ATOMIC_LEVEL[13] TCC_ATOMIC[14] TCC_CYCLE[14] TCC_EA_ATOMIC[14] TCC_EA_ATOMIC_LEVEL[14] TCC_ATOMIC[15] TCC_CYCLE[15] TCC_EA_ATOMIC[15] TCC_EA_ATOMIC_LEVEL[15] TCC_ATOMIC[16] TCC_CYCLE[16] TCC_EA_ATOMIC[16] TCC_EA_ATOMIC_LEVEL[16] TCC_ATOMIC[17] TCC_CYCLE[17] TCC_EA_ATOMIC[17] TCC_EA_ATOMIC_LEVEL[17] TCC_ATOMIC[18] TCC_CYCLE[18] TCC_EA_ATOMIC[18] TCC_EA_ATOMIC_LEVEL[18] TCC_ATOMIC[19] TCC_CYCLE[19] TCC_EA_ATOMIC[19] TCC_EA_ATOMIC_LEVEL[19] TCC_ATOMIC[20] TCC_CYCLE[20] TCC_EA_ATOMIC[20] TCC_EA_ATOMIC_LEVEL[20] TCC_ATOMIC[21] TCC_CYCLE[21] TCC_EA_ATOMIC[21] TCC_EA_ATOMIC_LEVEL[21] TCC_ATOMIC[22] TCC_CYCLE[22] TCC_EA_ATOMIC[22] TCC_EA_ATOMIC_LEVEL[22] TCC_ATOMIC[23] TCC_CYCLE[23] TCC_EA_ATOMIC[23] TCC_EA_ATOMIC_LEVEL[23] TCC_ATOMIC[24] TCC_CYCLE[24] TCC_EA_ATOMIC[24] TCC_EA_ATOMIC_LEVEL[24] TCC_ATOMIC[25] TCC_CYCLE[25] TCC_EA_ATOMIC[25] TCC_EA_ATOMIC_LEVEL[25] TCC_ATOMIC[26] TCC_CYCLE[26] TCC_EA_ATOMIC[26] TCC_EA_ATOMIC_LEVEL[26] TCC_ATOMIC[27] TCC_CYCLE[27] TCC_EA_ATOMIC[27] TCC_EA_ATOMIC_LEVEL[27] TCC_ATOMIC[28] TCC_CYCLE[28] TCC_EA_ATOMIC[28] TCC_EA_ATOMIC_LEVEL[28] TCC_ATOMIC[29] TCC_CYCLE[29] TCC_EA_ATOMIC[29] TCC_EA_ATOMIC_LEVEL[29] TCC_ATOMIC[30] TCC_CYCLE[30] TCC_EA_ATOMIC[30] TCC_EA_ATOMIC_LEVEL[30] TCC_ATOMIC[31] TCC_CYCLE[31] TCC_EA_ATOMIC[31] TCC_EA_ATOMIC_LEVEL[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_14.txt b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_14.txt new file mode 100644 index 0000000000..e0698dbf57 --- /dev/null +++ b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_14.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_EA_RDREQ_GMI_CREDIT_STALL[0] TCC_EA_RDREQ[1] TCC_EA_RDREQ_32B[1] TCC_EA_RDREQ_DRAM_CREDIT_STALL[1] TCC_EA_RDREQ_GMI_CREDIT_STALL[1] TCC_EA_RDREQ[2] TCC_EA_RDREQ_32B[2] TCC_EA_RDREQ_DRAM_CREDIT_STALL[2] TCC_EA_RDREQ_GMI_CREDIT_STALL[2] TCC_EA_RDREQ[3] TCC_EA_RDREQ_32B[3] TCC_EA_RDREQ_DRAM_CREDIT_STALL[3] TCC_EA_RDREQ_GMI_CREDIT_STALL[3] TCC_EA_RDREQ[4] TCC_EA_RDREQ_32B[4] TCC_EA_RDREQ_DRAM_CREDIT_STALL[4] TCC_EA_RDREQ_GMI_CREDIT_STALL[4] TCC_EA_RDREQ[5] TCC_EA_RDREQ_32B[5] TCC_EA_RDREQ_DRAM_CREDIT_STALL[5] TCC_EA_RDREQ_GMI_CREDIT_STALL[5] TCC_EA_RDREQ[6] TCC_EA_RDREQ_32B[6] TCC_EA_RDREQ_DRAM_CREDIT_STALL[6] TCC_EA_RDREQ_GMI_CREDIT_STALL[6] TCC_EA_RDREQ[7] TCC_EA_RDREQ_32B[7] TCC_EA_RDREQ_DRAM_CREDIT_STALL[7] TCC_EA_RDREQ_GMI_CREDIT_STALL[7] TCC_EA_RDREQ[8] TCC_EA_RDREQ_32B[8] TCC_EA_RDREQ_DRAM_CREDIT_STALL[8] TCC_EA_RDREQ_GMI_CREDIT_STALL[8] TCC_EA_RDREQ[9] TCC_EA_RDREQ_32B[9] TCC_EA_RDREQ_DRAM_CREDIT_STALL[9] TCC_EA_RDREQ_GMI_CREDIT_STALL[9] TCC_EA_RDREQ[10] TCC_EA_RDREQ_32B[10] TCC_EA_RDREQ_DRAM_CREDIT_STALL[10] TCC_EA_RDREQ_GMI_CREDIT_STALL[10] TCC_EA_RDREQ[11] TCC_EA_RDREQ_32B[11] TCC_EA_RDREQ_DRAM_CREDIT_STALL[11] TCC_EA_RDREQ_GMI_CREDIT_STALL[11] TCC_EA_RDREQ[12] TCC_EA_RDREQ_32B[12] TCC_EA_RDREQ_DRAM_CREDIT_STALL[12] TCC_EA_RDREQ_GMI_CREDIT_STALL[12] TCC_EA_RDREQ[13] TCC_EA_RDREQ_32B[13] TCC_EA_RDREQ_DRAM_CREDIT_STALL[13] TCC_EA_RDREQ_GMI_CREDIT_STALL[13] TCC_EA_RDREQ[14] TCC_EA_RDREQ_32B[14] TCC_EA_RDREQ_DRAM_CREDIT_STALL[14] TCC_EA_RDREQ_GMI_CREDIT_STALL[14] TCC_EA_RDREQ[15] TCC_EA_RDREQ_32B[15] TCC_EA_RDREQ_DRAM_CREDIT_STALL[15] TCC_EA_RDREQ_GMI_CREDIT_STALL[15] TCC_EA_RDREQ[16] TCC_EA_RDREQ_32B[16] TCC_EA_RDREQ_DRAM_CREDIT_STALL[16] TCC_EA_RDREQ_GMI_CREDIT_STALL[16] TCC_EA_RDREQ[17] TCC_EA_RDREQ_32B[17] TCC_EA_RDREQ_DRAM_CREDIT_STALL[17] TCC_EA_RDREQ_GMI_CREDIT_STALL[17] TCC_EA_RDREQ[18] TCC_EA_RDREQ_32B[18] TCC_EA_RDREQ_DRAM_CREDIT_STALL[18] TCC_EA_RDREQ_GMI_CREDIT_STALL[18] TCC_EA_RDREQ[19] TCC_EA_RDREQ_32B[19] TCC_EA_RDREQ_DRAM_CREDIT_STALL[19] TCC_EA_RDREQ_GMI_CREDIT_STALL[19] TCC_EA_RDREQ[20] TCC_EA_RDREQ_32B[20] TCC_EA_RDREQ_DRAM_CREDIT_STALL[20] TCC_EA_RDREQ_GMI_CREDIT_STALL[20] TCC_EA_RDREQ[21] TCC_EA_RDREQ_32B[21] TCC_EA_RDREQ_DRAM_CREDIT_STALL[21] TCC_EA_RDREQ_GMI_CREDIT_STALL[21] TCC_EA_RDREQ[22] TCC_EA_RDREQ_32B[22] TCC_EA_RDREQ_DRAM_CREDIT_STALL[22] TCC_EA_RDREQ_GMI_CREDIT_STALL[22] TCC_EA_RDREQ[23] TCC_EA_RDREQ_32B[23] TCC_EA_RDREQ_DRAM_CREDIT_STALL[23] TCC_EA_RDREQ_GMI_CREDIT_STALL[23] TCC_EA_RDREQ[24] TCC_EA_RDREQ_32B[24] TCC_EA_RDREQ_DRAM_CREDIT_STALL[24] TCC_EA_RDREQ_GMI_CREDIT_STALL[24] TCC_EA_RDREQ[25] TCC_EA_RDREQ_32B[25] TCC_EA_RDREQ_DRAM_CREDIT_STALL[25] TCC_EA_RDREQ_GMI_CREDIT_STALL[25] TCC_EA_RDREQ[26] TCC_EA_RDREQ_32B[26] TCC_EA_RDREQ_DRAM_CREDIT_STALL[26] TCC_EA_RDREQ_GMI_CREDIT_STALL[26] TCC_EA_RDREQ[27] TCC_EA_RDREQ_32B[27] TCC_EA_RDREQ_DRAM_CREDIT_STALL[27] TCC_EA_RDREQ_GMI_CREDIT_STALL[27] TCC_EA_RDREQ[28] TCC_EA_RDREQ_32B[28] TCC_EA_RDREQ_DRAM_CREDIT_STALL[28] TCC_EA_RDREQ_GMI_CREDIT_STALL[28] TCC_EA_RDREQ[29] TCC_EA_RDREQ_32B[29] TCC_EA_RDREQ_DRAM_CREDIT_STALL[29] TCC_EA_RDREQ_GMI_CREDIT_STALL[29] TCC_EA_RDREQ[30] TCC_EA_RDREQ_32B[30] TCC_EA_RDREQ_DRAM_CREDIT_STALL[30] TCC_EA_RDREQ_GMI_CREDIT_STALL[30] TCC_EA_RDREQ[31] TCC_EA_RDREQ_32B[31] TCC_EA_RDREQ_DRAM_CREDIT_STALL[31] TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_15.txt b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_15.txt new file mode 100644 index 0000000000..77ad088669 --- /dev/null +++ b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_15.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ[0] TCC_EA_WRREQ_64B[0] TCC_EA_RDREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_LEVEL[1] TCC_EA_WRREQ[1] TCC_EA_WRREQ_64B[1] TCC_EA_RDREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_LEVEL[2] TCC_EA_WRREQ[2] TCC_EA_WRREQ_64B[2] TCC_EA_RDREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_LEVEL[3] TCC_EA_WRREQ[3] TCC_EA_WRREQ_64B[3] TCC_EA_RDREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_LEVEL[4] TCC_EA_WRREQ[4] TCC_EA_WRREQ_64B[4] TCC_EA_RDREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_LEVEL[5] TCC_EA_WRREQ[5] TCC_EA_WRREQ_64B[5] TCC_EA_RDREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_LEVEL[6] TCC_EA_WRREQ[6] TCC_EA_WRREQ_64B[6] TCC_EA_RDREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_LEVEL[7] TCC_EA_WRREQ[7] TCC_EA_WRREQ_64B[7] TCC_EA_RDREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_LEVEL[8] TCC_EA_WRREQ[8] TCC_EA_WRREQ_64B[8] TCC_EA_RDREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_LEVEL[9] TCC_EA_WRREQ[9] TCC_EA_WRREQ_64B[9] TCC_EA_RDREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_LEVEL[10] TCC_EA_WRREQ[10] TCC_EA_WRREQ_64B[10] TCC_EA_RDREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_LEVEL[11] TCC_EA_WRREQ[11] TCC_EA_WRREQ_64B[11] TCC_EA_RDREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_LEVEL[12] TCC_EA_WRREQ[12] TCC_EA_WRREQ_64B[12] TCC_EA_RDREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_LEVEL[13] TCC_EA_WRREQ[13] TCC_EA_WRREQ_64B[13] TCC_EA_RDREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_LEVEL[14] TCC_EA_WRREQ[14] TCC_EA_WRREQ_64B[14] TCC_EA_RDREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_LEVEL[15] TCC_EA_WRREQ[15] TCC_EA_WRREQ_64B[15] TCC_EA_RDREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_LEVEL[16] TCC_EA_WRREQ[16] TCC_EA_WRREQ_64B[16] TCC_EA_RDREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_LEVEL[17] TCC_EA_WRREQ[17] TCC_EA_WRREQ_64B[17] TCC_EA_RDREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_LEVEL[18] TCC_EA_WRREQ[18] TCC_EA_WRREQ_64B[18] TCC_EA_RDREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_LEVEL[19] TCC_EA_WRREQ[19] TCC_EA_WRREQ_64B[19] TCC_EA_RDREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_LEVEL[20] TCC_EA_WRREQ[20] TCC_EA_WRREQ_64B[20] TCC_EA_RDREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_LEVEL[21] TCC_EA_WRREQ[21] TCC_EA_WRREQ_64B[21] TCC_EA_RDREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_LEVEL[22] TCC_EA_WRREQ[22] TCC_EA_WRREQ_64B[22] TCC_EA_RDREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_LEVEL[23] TCC_EA_WRREQ[23] TCC_EA_WRREQ_64B[23] TCC_EA_RDREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_LEVEL[24] TCC_EA_WRREQ[24] TCC_EA_WRREQ_64B[24] TCC_EA_RDREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_LEVEL[25] TCC_EA_WRREQ[25] TCC_EA_WRREQ_64B[25] TCC_EA_RDREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_LEVEL[26] TCC_EA_WRREQ[26] TCC_EA_WRREQ_64B[26] TCC_EA_RDREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_LEVEL[27] TCC_EA_WRREQ[27] TCC_EA_WRREQ_64B[27] TCC_EA_RDREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_LEVEL[28] TCC_EA_WRREQ[28] TCC_EA_WRREQ_64B[28] TCC_EA_RDREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_LEVEL[29] TCC_EA_WRREQ[29] TCC_EA_WRREQ_64B[29] TCC_EA_RDREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_LEVEL[30] TCC_EA_WRREQ[30] TCC_EA_WRREQ_64B[30] TCC_EA_RDREQ_IO_CREDIT_STALL[31] TCC_EA_RDREQ_LEVEL[31] TCC_EA_WRREQ[31] TCC_EA_WRREQ_64B[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_16.txt b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_16.txt new file mode 100644 index 0000000000..d0628bb948 --- /dev/null +++ b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_16.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_WRREQ_IO_CREDIT_STALL[0] TCC_EA_WRREQ_LEVEL[0] TCC_EA_WRREQ_DRAM_CREDIT_STALL[1] TCC_EA_WRREQ_GMI_CREDIT_STALL[1] TCC_EA_WRREQ_IO_CREDIT_STALL[1] TCC_EA_WRREQ_LEVEL[1] TCC_EA_WRREQ_DRAM_CREDIT_STALL[2] TCC_EA_WRREQ_GMI_CREDIT_STALL[2] TCC_EA_WRREQ_IO_CREDIT_STALL[2] TCC_EA_WRREQ_LEVEL[2] TCC_EA_WRREQ_DRAM_CREDIT_STALL[3] TCC_EA_WRREQ_GMI_CREDIT_STALL[3] TCC_EA_WRREQ_IO_CREDIT_STALL[3] TCC_EA_WRREQ_LEVEL[3] TCC_EA_WRREQ_DRAM_CREDIT_STALL[4] TCC_EA_WRREQ_GMI_CREDIT_STALL[4] TCC_EA_WRREQ_IO_CREDIT_STALL[4] TCC_EA_WRREQ_LEVEL[4] TCC_EA_WRREQ_DRAM_CREDIT_STALL[5] TCC_EA_WRREQ_GMI_CREDIT_STALL[5] TCC_EA_WRREQ_IO_CREDIT_STALL[5] TCC_EA_WRREQ_LEVEL[5] TCC_EA_WRREQ_DRAM_CREDIT_STALL[6] TCC_EA_WRREQ_GMI_CREDIT_STALL[6] TCC_EA_WRREQ_IO_CREDIT_STALL[6] TCC_EA_WRREQ_LEVEL[6] TCC_EA_WRREQ_DRAM_CREDIT_STALL[7] TCC_EA_WRREQ_GMI_CREDIT_STALL[7] TCC_EA_WRREQ_IO_CREDIT_STALL[7] TCC_EA_WRREQ_LEVEL[7] TCC_EA_WRREQ_DRAM_CREDIT_STALL[8] TCC_EA_WRREQ_GMI_CREDIT_STALL[8] TCC_EA_WRREQ_IO_CREDIT_STALL[8] TCC_EA_WRREQ_LEVEL[8] TCC_EA_WRREQ_DRAM_CREDIT_STALL[9] TCC_EA_WRREQ_GMI_CREDIT_STALL[9] TCC_EA_WRREQ_IO_CREDIT_STALL[9] TCC_EA_WRREQ_LEVEL[9] TCC_EA_WRREQ_DRAM_CREDIT_STALL[10] TCC_EA_WRREQ_GMI_CREDIT_STALL[10] TCC_EA_WRREQ_IO_CREDIT_STALL[10] TCC_EA_WRREQ_LEVEL[10] TCC_EA_WRREQ_DRAM_CREDIT_STALL[11] TCC_EA_WRREQ_GMI_CREDIT_STALL[11] TCC_EA_WRREQ_IO_CREDIT_STALL[11] TCC_EA_WRREQ_LEVEL[11] TCC_EA_WRREQ_DRAM_CREDIT_STALL[12] TCC_EA_WRREQ_GMI_CREDIT_STALL[12] TCC_EA_WRREQ_IO_CREDIT_STALL[12] TCC_EA_WRREQ_LEVEL[12] TCC_EA_WRREQ_DRAM_CREDIT_STALL[13] TCC_EA_WRREQ_GMI_CREDIT_STALL[13] TCC_EA_WRREQ_IO_CREDIT_STALL[13] TCC_EA_WRREQ_LEVEL[13] TCC_EA_WRREQ_DRAM_CREDIT_STALL[14] TCC_EA_WRREQ_GMI_CREDIT_STALL[14] TCC_EA_WRREQ_IO_CREDIT_STALL[14] TCC_EA_WRREQ_LEVEL[14] TCC_EA_WRREQ_DRAM_CREDIT_STALL[15] TCC_EA_WRREQ_GMI_CREDIT_STALL[15] TCC_EA_WRREQ_IO_CREDIT_STALL[15] TCC_EA_WRREQ_LEVEL[15] TCC_EA_WRREQ_DRAM_CREDIT_STALL[16] TCC_EA_WRREQ_GMI_CREDIT_STALL[16] TCC_EA_WRREQ_IO_CREDIT_STALL[16] TCC_EA_WRREQ_LEVEL[16] TCC_EA_WRREQ_DRAM_CREDIT_STALL[17] TCC_EA_WRREQ_GMI_CREDIT_STALL[17] TCC_EA_WRREQ_IO_CREDIT_STALL[17] TCC_EA_WRREQ_LEVEL[17] TCC_EA_WRREQ_DRAM_CREDIT_STALL[18] TCC_EA_WRREQ_GMI_CREDIT_STALL[18] TCC_EA_WRREQ_IO_CREDIT_STALL[18] TCC_EA_WRREQ_LEVEL[18] TCC_EA_WRREQ_DRAM_CREDIT_STALL[19] TCC_EA_WRREQ_GMI_CREDIT_STALL[19] TCC_EA_WRREQ_IO_CREDIT_STALL[19] TCC_EA_WRREQ_LEVEL[19] TCC_EA_WRREQ_DRAM_CREDIT_STALL[20] TCC_EA_WRREQ_GMI_CREDIT_STALL[20] TCC_EA_WRREQ_IO_CREDIT_STALL[20] TCC_EA_WRREQ_LEVEL[20] TCC_EA_WRREQ_DRAM_CREDIT_STALL[21] TCC_EA_WRREQ_GMI_CREDIT_STALL[21] TCC_EA_WRREQ_IO_CREDIT_STALL[21] TCC_EA_WRREQ_LEVEL[21] TCC_EA_WRREQ_DRAM_CREDIT_STALL[22] TCC_EA_WRREQ_GMI_CREDIT_STALL[22] TCC_EA_WRREQ_IO_CREDIT_STALL[22] TCC_EA_WRREQ_LEVEL[22] TCC_EA_WRREQ_DRAM_CREDIT_STALL[23] TCC_EA_WRREQ_GMI_CREDIT_STALL[23] TCC_EA_WRREQ_IO_CREDIT_STALL[23] TCC_EA_WRREQ_LEVEL[23] TCC_EA_WRREQ_DRAM_CREDIT_STALL[24] TCC_EA_WRREQ_GMI_CREDIT_STALL[24] TCC_EA_WRREQ_IO_CREDIT_STALL[24] TCC_EA_WRREQ_LEVEL[24] TCC_EA_WRREQ_DRAM_CREDIT_STALL[25] TCC_EA_WRREQ_GMI_CREDIT_STALL[25] TCC_EA_WRREQ_IO_CREDIT_STALL[25] TCC_EA_WRREQ_LEVEL[25] TCC_EA_WRREQ_DRAM_CREDIT_STALL[26] TCC_EA_WRREQ_GMI_CREDIT_STALL[26] TCC_EA_WRREQ_IO_CREDIT_STALL[26] TCC_EA_WRREQ_LEVEL[26] TCC_EA_WRREQ_DRAM_CREDIT_STALL[27] TCC_EA_WRREQ_GMI_CREDIT_STALL[27] TCC_EA_WRREQ_IO_CREDIT_STALL[27] TCC_EA_WRREQ_LEVEL[27] TCC_EA_WRREQ_DRAM_CREDIT_STALL[28] TCC_EA_WRREQ_GMI_CREDIT_STALL[28] TCC_EA_WRREQ_IO_CREDIT_STALL[28] TCC_EA_WRREQ_LEVEL[28] TCC_EA_WRREQ_DRAM_CREDIT_STALL[29] TCC_EA_WRREQ_GMI_CREDIT_STALL[29] TCC_EA_WRREQ_IO_CREDIT_STALL[29] TCC_EA_WRREQ_LEVEL[29] TCC_EA_WRREQ_DRAM_CREDIT_STALL[30] TCC_EA_WRREQ_GMI_CREDIT_STALL[30] TCC_EA_WRREQ_IO_CREDIT_STALL[30] TCC_EA_WRREQ_LEVEL[30] TCC_EA_WRREQ_DRAM_CREDIT_STALL[31] TCC_EA_WRREQ_GMI_CREDIT_STALL[31] TCC_EA_WRREQ_IO_CREDIT_STALL[31] TCC_EA_WRREQ_LEVEL[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_17.txt b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_17.txt new file mode 100644 index 0000000000..343869c5f1 --- /dev/null +++ b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_17.txt @@ -0,0 +1,5 @@ +pmc: TCC_HIT[0] TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_HIT[1] TCC_MISS[1] TCC_READ[1] TCC_REQ[1] TCC_HIT[2] TCC_MISS[2] TCC_READ[2] TCC_REQ[2] TCC_HIT[3] TCC_MISS[3] TCC_READ[3] TCC_REQ[3] TCC_HIT[4] TCC_MISS[4] TCC_READ[4] TCC_REQ[4] TCC_HIT[5] TCC_MISS[5] TCC_READ[5] TCC_REQ[5] TCC_HIT[6] TCC_MISS[6] TCC_READ[6] TCC_REQ[6] TCC_HIT[7] TCC_MISS[7] TCC_READ[7] TCC_REQ[7] TCC_HIT[8] TCC_MISS[8] TCC_READ[8] TCC_REQ[8] TCC_HIT[9] TCC_MISS[9] TCC_READ[9] TCC_REQ[9] TCC_HIT[10] TCC_MISS[10] TCC_READ[10] TCC_REQ[10] TCC_HIT[11] TCC_MISS[11] TCC_READ[11] TCC_REQ[11] TCC_HIT[12] TCC_MISS[12] TCC_READ[12] TCC_REQ[12] TCC_HIT[13] TCC_MISS[13] TCC_READ[13] TCC_REQ[13] TCC_HIT[14] TCC_MISS[14] TCC_READ[14] TCC_REQ[14] TCC_HIT[15] TCC_MISS[15] TCC_READ[15] TCC_REQ[15] TCC_HIT[16] TCC_MISS[16] TCC_READ[16] TCC_REQ[16] TCC_HIT[17] TCC_MISS[17] TCC_READ[17] TCC_REQ[17] TCC_HIT[18] TCC_MISS[18] TCC_READ[18] TCC_REQ[18] TCC_HIT[19] TCC_MISS[19] TCC_READ[19] TCC_REQ[19] TCC_HIT[20] TCC_MISS[20] TCC_READ[20] TCC_REQ[20] TCC_HIT[21] TCC_MISS[21] TCC_READ[21] TCC_REQ[21] TCC_HIT[22] TCC_MISS[22] TCC_READ[22] TCC_REQ[22] TCC_HIT[23] TCC_MISS[23] TCC_READ[23] TCC_REQ[23] TCC_HIT[24] TCC_MISS[24] TCC_READ[24] TCC_REQ[24] TCC_HIT[25] TCC_MISS[25] TCC_READ[25] TCC_REQ[25] TCC_HIT[26] TCC_MISS[26] TCC_READ[26] TCC_REQ[26] TCC_HIT[27] TCC_MISS[27] TCC_READ[27] TCC_REQ[27] TCC_HIT[28] TCC_MISS[28] TCC_READ[28] TCC_REQ[28] TCC_HIT[29] TCC_MISS[29] TCC_READ[29] TCC_REQ[29] TCC_HIT[30] TCC_MISS[30] TCC_READ[30] TCC_REQ[30] TCC_HIT[31] TCC_MISS[31] TCC_READ[31] TCC_REQ[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_18.txt b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_18.txt new file mode 100644 index 0000000000..a74cefd281 --- /dev/null +++ b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_18.txt @@ -0,0 +1,5 @@ +pmc: TCC_RW_REQ[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_RW_REQ[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_WRITE[1] TCC_RW_REQ[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_WRITE[2] TCC_RW_REQ[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_WRITE[3] TCC_RW_REQ[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_WRITE[4] TCC_RW_REQ[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_WRITE[5] TCC_RW_REQ[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_WRITE[6] TCC_RW_REQ[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_WRITE[7] TCC_RW_REQ[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_WRITE[8] TCC_RW_REQ[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_WRITE[9] TCC_RW_REQ[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_WRITE[10] TCC_RW_REQ[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_WRITE[11] TCC_RW_REQ[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_WRITE[12] TCC_RW_REQ[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_WRITE[13] TCC_RW_REQ[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_WRITE[14] TCC_RW_REQ[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_WRITE[15] TCC_RW_REQ[16] TCC_TOO_MANY_EA_WRREQS_STALL[16] TCC_WRITE[16] TCC_RW_REQ[17] TCC_TOO_MANY_EA_WRREQS_STALL[17] TCC_WRITE[17] TCC_RW_REQ[18] TCC_TOO_MANY_EA_WRREQS_STALL[18] TCC_WRITE[18] TCC_RW_REQ[19] TCC_TOO_MANY_EA_WRREQS_STALL[19] TCC_WRITE[19] TCC_RW_REQ[20] TCC_TOO_MANY_EA_WRREQS_STALL[20] TCC_WRITE[20] TCC_RW_REQ[21] TCC_TOO_MANY_EA_WRREQS_STALL[21] TCC_WRITE[21] TCC_RW_REQ[22] TCC_TOO_MANY_EA_WRREQS_STALL[22] TCC_WRITE[22] TCC_RW_REQ[23] TCC_TOO_MANY_EA_WRREQS_STALL[23] TCC_WRITE[23] TCC_RW_REQ[24] TCC_TOO_MANY_EA_WRREQS_STALL[24] TCC_WRITE[24] TCC_RW_REQ[25] TCC_TOO_MANY_EA_WRREQS_STALL[25] TCC_WRITE[25] TCC_RW_REQ[26] TCC_TOO_MANY_EA_WRREQS_STALL[26] TCC_WRITE[26] TCC_RW_REQ[27] TCC_TOO_MANY_EA_WRREQS_STALL[27] TCC_WRITE[27] TCC_RW_REQ[28] TCC_TOO_MANY_EA_WRREQS_STALL[28] TCC_WRITE[28] TCC_RW_REQ[29] TCC_TOO_MANY_EA_WRREQS_STALL[29] TCC_WRITE[29] TCC_RW_REQ[30] TCC_TOO_MANY_EA_WRREQS_STALL[30] TCC_WRITE[30] TCC_RW_REQ[31] TCC_TOO_MANY_EA_WRREQS_STALL[31] TCC_WRITE[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_2.txt b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_2.txt new file mode 100644 index 0000000000..70b69f8928 --- /dev/null +++ b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_2.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_MUL_F32 SQ_INSTS_VALU_FMA_F32 SQ_INSTS_VALU_TRANS_F32 SQ_INSTS_VALU_ADD_F64 SQ_INSTS_VALU_MUL_F64 SQ_INSTS_VALU_FMA_F64 SQ_INSTS_VALU_TRANS_F64 SQ_INSTS_VALU_INT32 TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum TA_BUFFER_ATOMIC_WAVEFRONTS_sum TA_BUFFER_TOTAL_CYCLES_sum TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_3.txt b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_3.txt new file mode 100644 index 0000000000..e47f8e33c9 --- /dev/null +++ b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_3.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_INT64 SQ_INSTS_SMEM SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum TD_COALESCABLE_WAVEFRONT_sum SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE CPF_CMP_UTCL1_STALL_ON_TRANSLATION TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_4.txt b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_4.txt new file mode 100644 index 0000000000..2d96f365a9 --- /dev/null +++ b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_4.txt @@ -0,0 +1,5 @@ +pmc: SQ_WAVE_CYCLES SQ_WAIT_ANY SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_BUSY_CU_CYCLES SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE TCC_EA_WRREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WR_UNCACHED_32B_sum TCC_EA_WRREQ_DRAM_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_5.txt b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_5.txt new file mode 100644 index 0000000000..e50beed390 --- /dev/null +++ b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_5.txt @@ -0,0 +1,5 @@ +pmc: SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU TCP_TCP_LATENCY_sum TCP_TCC_READ_REQ_LATENCY_sum TCP_TCC_WRITE_REQ_LATENCY_sum TCP_TCC_READ_REQ_sum TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN CPC_ME1_DC0_SPI_BUSY TCC_EA_WRREQ_STALL_sum TCC_EA_RDREQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RD_UNCACHED_32B_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_6.txt b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_6.txt new file mode 100644 index 0000000000..15a2277c1b --- /dev/null +++ b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_6.txt @@ -0,0 +1,5 @@ +pmc: SQ_THREAD_CYCLES_VALU SQ_IFETCH SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TCP_TCC_NC_READ_REQ_sum TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN TCC_EA_RDREQ_DRAM_sum TCC_TAG_STALL_sum TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_7.txt b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_7.txt new file mode 100644 index 0000000000..b42ce91618 --- /dev/null +++ b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_7.txt @@ -0,0 +1,5 @@ +pmc: SQ_WAVES_LT_32 SQ_WAVES_LT_16 SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TCP_TCC_UC_WRITE_REQ_sum TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR TCC_NORMAL_EVICT_sum TCC_ALL_TC_OP_INV_EVICT_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA_ATOMIC_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_8.txt b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_8.txt new file mode 100644 index 0000000000..21d4c7a998 --- /dev/null +++ b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_8.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM_NORM SQ_INSTS_MFMA SQ_INSTS_VALU_MFMA_I8 SQ_INSTS_VALU_MFMA_F16 SQ_INSTS_VALU_MFMA_BF16 SQ_INSTS_VALU_MFMA_F32 SQ_INSTS_VALU_MFMA_F64 SQ_VALU_MFMA_BUSY_CYCLES TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TCP_TCC_CC_ATOMIC_REQ_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN TCC_EA_RDREQ_LEVEL_sum TCC_EA_WRREQ_LEVEL_sum TCC_EA_ATOMIC_LEVEL_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_9.txt b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_9.txt new file mode 100644 index 0000000000..9ffe5778c3 --- /dev/null +++ b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_9.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_FLAT_LDS_ONLY SQ_INSTS_VALU_MFMA_MOPS_I8 SQ_INSTS_VALU_MFMA_MOPS_F16 SQ_INSTS_VALU_MFMA_MOPS_BF16 SQ_INSTS_VALU_MFMA_MOPS_F32 SQ_INSTS_VALU_MFMA_MOPS_F64 SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum TCP_PENDING_STALL_CYCLES_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_2/MI200/perfmon/timestamps.txt b/tests/workloads/kernel_verbose_2/MI200/perfmon/timestamps.txt new file mode 100644 index 0000000000..676cca1b80 --- /dev/null +++ b/tests/workloads/kernel_verbose_2/MI200/perfmon/timestamps.txt @@ -0,0 +1,5 @@ +pmc: + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_2/MI200/pmc_perf.csv b/tests/workloads/kernel_verbose_2/MI200/pmc_perf.csv new file mode 100644 index 0000000000..6721108893 --- /dev/null +++ b/tests/workloads/kernel_verbose_2/MI200/pmc_perf.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_1,obj_1,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_2,obj_2,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_3,obj_3,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_4,obj_4,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,wave_size_5,obj_5,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_6,obj_6,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_7,obj_7,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_8,obj_8,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,wave_size_9,obj_9,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_10,obj_10,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_11,obj_11,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,TD_COALESCABLE_WAVEFRONT_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_12,obj_12,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_13,obj_13,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_14,obj_14,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_DRAM_sum,TCC_TAG_STALL_sum,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,wave_size_15,obj_15,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_16,obj_16,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,TCC_EA_ATOMIC_LEVEL_sum,wave_size_17,obj_17,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_18,obj_18,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f7a5ea30ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,14028,19506,7920,547,0,27221,203514.0,0.0,72430.0,131084.0,64,0x7f1ae2278ec0,10859351,9857065,658222,344064,1639415,0,0,163840,832.0,515136.0,0.0,524288.0,284003.0,32768.0,485803,0,0,10923,131072.0,131072.0,0.0,131072.0,64,0x7f15a5de8ec0,0,0,0,956056,0,0,0,1011778,0,0,0,1136179,0,0,0,1189699,0,0,0,1104475,12,0,0,1152792,12,0,0,1145845,47,0,0,1300444,65,0,0,1238716,0,0,0,983608,0,0,0,937471,0,0,0,1144009,0,0,0,1161780,0,0,0,1121077,0,0,0,1023641,0,0,0,1136005,0,0,0,1124093,5,0,0,1216583,0,0,0,1002079,12,0,0,1140318,0,0,0,1029452,196,0,0,1321454,0,0,0,1139146,0,0,0,1115911,0,0,0,1124928,0,0,0,1095036,0,0,0,1014058,0,0,0,1103718,0,0,0,1027860,0,0,0,1051087,0,0,0,1148759,0,0,0,1015853,64,0x7f05f40a0ec0,32768,32768,0,64,0x7f47183d8ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65551.0,0.0,0.0,0.0,64,0x7fb8009f8ec0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,64,0x7f8d37784ec0,4096,0,0,0,4096,0,0,0,4096,0,22,0,4096,0,0,0,4096,0,0,0,4096,0,4,0,4101,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,34,0,4096,0,0,0,4097,0,0,0,4097,0,0,0,4099,0,0,0,4096,0,219,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,64,0x7fbc26c78ec0,0,0,0,224,0,65536,64181,56,64,0x7fed73b94ec0,114688,0,32768,32768,16384,16384,65536,49152,27830943.0,88351260.0,38720340.0,131072.0,0.0,206725.0,0,0,14875,138.0,131081.0,0.0,10.0,64,0x7f65b5028ec0,2231,4096,2231,6327,2284,4096,2284,6380,2283,4096,2283,6379,2286,4096,2286,6382,2264,4096,2264,6360,2269,4097,2270,6366,2294,4096,2294,6390,2290,4096,2290,6386,2290,4096,2290,6386,2232,4096,2232,6328,2286,4096,2286,6382,2284,4096,2284,6380,2286,4096,2286,6382,2324,4097,2325,6421,2272,4096,2272,6368,2293,4096,2293,6389,2280,4099,2283,6379,2289,4096,2289,6385,2243,4097,2244,6340,2258,4096,2258,6354,2281,4096,2281,6377,2325,4096,2325,6421,2269,4096,2269,6365,2449,4098,2451,6547,2285,4096,2285,6381,2284,4096,2284,6380,2295,4096,2295,6391,2243,4096,2243,6339,2256,4096,2256,6352,2281,4096,2281,6377,2327,4096,2327,6423,2271,4096,2271,6367,64,0x7f86b4438ec0,222024,129283,16384,0,16384,16384,32768,49152,27752,27752,1958260.0,1352086.0,3458.0,150388.0,1064219.0,0.0,1344454.0,1047013.0,220313,137414,27752,0,27752,0,888064.0,475768.0,0.0,0.0,64,0x7f0869250ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,10271,0,817,27847,0,72952.0,131072.0,0.0,65568.0,64,0x7f1c3083cec0,0,1240407,4096,4096,0,1293421,4096,4096,0,1290782,4096,4096,0,1155322,4096,4096,0,1145435,4096,4096,0,1087237,4096,4096,0,1643369,4096,4096,0,1264251,4096,4096,0,1137249,4096,4096,0,1259465,4096,4096,0,1230781,4096,4096,0,1245523,4096,4096,0,1128832,4096,4096,0,1138570,4096,4096,0,1280799,4096,4096,0,1238290,4096,4096,0,1057989,4096,4096,0,1137603,4096,4096,0,1119570,4096,4096,0,1501648,4096,4096,0,1216808,4096,4096,0,1288956,4096,4096,0,1162251,4096,4096,0,1182789,4096,4096,0,1222269,4096,4096,0,1023575,4096,4096,0,1059677,4096,4096,0,1416373,4096,4096,0,1365018,4096,4096,0,1187606,4096,4096,0,1057060,4096,4096,0,1306203,4096,4096,64,0x7f2d2947cec0,0,393216,163840,0,0,0,0,0,17744,0.0,0.0,0.0,32768.0,0.0,0.0,405.0,32768.0,4096,16384,352,28253,2231,0,56.0,5.0,0.0,203801.0,64,0x7f553b0b0ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131083.0,35839.0,46120.0,19416.0,64,0x7effc4ae8ec0,1257,113304,0,0,65536,63800,56,1680,64,0x7f123191cec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,41867435.0,34832387.0,0.0,64,0x7f637f758ec0,0,0,0,0,0,0,168,56,131072.0,131072.0,0.0,980229.0,64,0x7fb1db9c4ec0,6362,0,4096,6346,0,4096,6375,0,4096,6427,0,4096,6346,0,4096,6364,0,4096,6340,0,4096,6433,0,4096,6436,0,4096,6362,0,4096,6347,0,4096,6376,0,4096,6427,0,4096,6349,0,4096,6363,0,4096,6346,0,4096,6386,0,4096,6392,0,4096,6369,0,4096,6340,0,4096,6382,0,4096,6384,0,4096,6378,0,4096,6520,0,4096,6354,0,4096,6388,0,4096,6393,0,4096,6369,0,4096,6341,0,4096,6382,0,4096,6387,0,4096,6381,0,4096,200174259821413,200174259842053 +1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f7a5ea30ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,27922,28136,8427,550,0,35389,200522.0,0.0,69447.0,131075.0,64,0x7f1ae2278ec0,17699656,17126682,228910,344064,2581872,0,0,163840,0.0,524288.0,0.0,524288.0,456056.0,32768.0,784400,0,0,11580,91294.0,91294.0,0.0,91294.0,64,0x7f15a5de8ec0,0,0,0,1476958,0,0,0,1484506,0,0,0,2141999,380,0,0,2107744,0,0,0,1962154,80,0,0,1850892,71,0,0,1795681,0,0,0,1786698,0,0,0,1643811,0,0,0,1334453,46,0,0,1707745,0,0,0,1866452,0,0,0,1565908,0,0,0,1861219,390,0,0,2198669,0,0,0,1676566,0,0,0,1810149,0,0,0,1423959,0,0,0,1448796,0,0,0,1825655,0,0,0,1643794,156,0,0,1991800,367,0,0,1884672,13,0,0,1780589,70,0,0,1809295,0,0,0,1474915,0,0,0,1540670,0,0,0,1403032,0,0,0,1508568,0,0,0,1743565,30,0,0,1748857,0,0,0,1733371,64,0x7f05f40a0ec0,32768,32768,0,64,0x7f47183d8ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65550.0,0.0,0.0,0.0,64,0x7fb8009f8ec0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,64,0x7f8d37784ec0,4096,0,34,0,4096,0,2605,0,4096,0,11,0,4096,0,700,0,4096,0,907,0,4096,0,247,0,4101,0,30,0,4096,0,775,0,4096,0,106,0,4096,0,381,0,4096,0,550,0,4096,0,122,0,4098,0,309,0,4096,0,41,0,4097,0,18,0,4096,0,94,0,4096,0,289,0,4096,0,390,0,4097,0,274,0,4096,0,348,0,4096,0,503,0,4098,0,797,0,4097,0,55,0,4096,0,1123,0,4096,0,1662,0,4096,0,60,0,4096,0,64,0,4096,0,2765,0,4096,0,269,0,4096,0,94,0,4097,0,379,0,4096,0,1029,0,64,0x7fbc26c78ec0,0,0,0,56,0,65536,65536,0,64,0x7fed73b94ec0,114688,0,32768,32768,16384,16384,65536,49152,57504966.0,195097391.0,47200514.0,131072.0,0.0,543936.0,0,0,25010,5335.0,131083.0,0.0,20.0,64,0x7f65b5028ec0,2162,4096,2162,6258,2168,4096,2168,6264,2131,4097,2132,6228,2148,4096,2148,6244,2173,4096,2173,6269,2171,4097,2172,6268,2182,4096,2182,6278,2192,4096,2192,6288,2196,4096,2196,6292,2157,4096,2157,6253,2170,4096,2170,6266,2135,4096,2135,6231,2151,4096,2151,6247,2228,4097,2229,6325,2168,4096,2168,6264,2179,4096,2179,6275,2185,4098,2187,6283,2173,4096,2173,6269,2152,4098,2154,6250,2189,4096,2189,6285,2131,4096,2131,6227,2160,4099,2163,6259,2144,4096,2144,6240,2173,4096,2173,6269,2174,4096,2174,6270,2187,4096,2187,6283,2177,4096,2177,6273,2156,4096,2156,6252,2190,4096,2190,6286,2130,4096,2130,6226,2162,4096,2162,6258,2145,4096,2145,6241,64,0x7f86b4438ec0,303000,205571,16384,0,16384,16384,32768,49152,37874,37874,2949719.0,2367536.0,5033.0,364184.0,1639574.0,0.0,2353376.0,2042594.0,302992,214897,37874,0,37874,0,1211968.0,772115.0,0.0,0.0,64,0x7f0869250ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,19443,0,2653,38124,0,69188.0,131072.0,0.0,45562.0,64,0x7f1c3083cec0,0,3418781,2834,2834,0,3774926,2848,2848,0,4291359,2864,2864,0,4132082,2868,2868,0,3213153,2896,2896,0,3716569,2860,2860,0,3077725,2852,2852,0,3428377,2820,2820,0,3256268,2820,2820,0,3270489,2836,2836,0,3180611,2848,2848,0,4050351,2864,2864,0,3417258,2868,2868,0,3498552,2896,2896,0,4442452,2864,2864,0,3275478,2852,2852,0,3208451,2800,2800,0,4007546,2840,2840,0,3532965,2840,2840,0,3553152,2844,2844,0,3406685,2830,2830,0,3364811,2884,2884,0,5011486,2832,2832,0,4303897,2836,2836,0,3662817,2840,2840,0,4106975,2796,2796,0,3504339,2840,2840,0,3869973,2840,2840,0,4164728,2844,2844,0,4763343,2832,2832,0,3251083,2888,2888,0,4584202,2832,2832,64,0x7f2d2947cec0,0,393216,163840,0,0,0,0,0,27486,0.0,0.0,0.0,32768.0,0.0,0.0,252.0,32768.0,4096,16384,302,36563,2006,0,56.0,0.0,0.0,199961.0,64,0x7f553b0b0ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131086.0,81674.0,45365.0,0.0,64,0x7effc4ae8ec0,0,187688,0,0,65536,63800,56,1680,64,0x7f123191cec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,115073211.0,59212179.0,0.0,64,0x7f637f758ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2025340.0,64,0x7fb1db9c4ec0,6237,0,4096,6257,0,4096,6248,0,4096,6233,0,4096,6273,0,4096,6249,0,4096,6257,0,4096,6256,0,4096,6259,0,4096,6233,0,4096,6259,0,4096,6251,0,4096,6231,0,4096,6280,0,4096,6253,0,4096,6253,0,4096,6261,0,4096,6253,0,4096,6255,0,4096,6280,0,4096,6232,0,4096,6243,0,4096,6237,0,4096,6224,0,4096,6223,0,4096,6264,0,4096,6253,0,4096,6249,0,4096,6276,0,4096,6235,0,4096,6249,0,4096,6238,0,4096,200174259860293,200174259876453 +2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f7a5ea30ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,28576,24605,9466,3198,0,40300,200307.0,0.0,69220.0,131087.0,64,0x7f1ae2278ec0,18686016,17546663,795289,344064,2763127,0,0,163840,832.0,515136.0,0.0,524288.0,601143.0,32768.0,918208,0,0,12897,91150.0,91150.0,0.0,91150.0,64,0x7f15a5de8ec0,0,0,0,1560267,0,0,0,1528060,0,0,0,1949569,0,0,0,1855561,0,0,0,1587193,2,0,0,1924652,536,0,0,2205049,99,0,0,1973648,0,0,0,1771732,0,0,0,1531031,388,0,0,1965343,0,0,0,1927530,0,0,0,1794828,0,0,0,2021137,0,0,0,1772140,95,0,0,2222713,0,0,0,1814298,90,0,0,1946681,0,0,0,1475727,0,0,0,1772875,163,0,0,2171346,0,0,0,1901219,183,0,0,1862241,0,0,0,2132632,0,0,0,1880290,0,0,0,1655226,5,0,0,1614818,0,0,0,1605000,183,0,0,2053629,0,0,0,1704115,0,0,0,1545112,0,0,0,1681595,64,0x7f05f40a0ec0,32768,32768,0,64,0x7f47183d8ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65554.0,0.0,0.0,0.0,64,0x7fb8009f8ec0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,64,0x7f8d37784ec0,4096,0,98,0,4096,0,139,0,4096,0,1398,0,4096,0,1034,0,4096,0,2111,0,4096,0,969,0,4101,0,765,0,4096,0,812,0,4096,0,381,0,4096,0,330,0,4096,0,143,0,4096,0,245,0,4098,0,883,0,4096,0,1257,0,4097,0,422,0,4096,0,590,0,4096,0,1248,0,4096,0,1616,0,4097,0,353,0,4096,0,921,0,4096,0,214,0,4098,0,759,0,4097,0,1061,0,4096,0,1494,0,4096,0,1745,0,4096,0,871,0,4096,0,567,0,4096,0,786,0,4096,0,782,0,4096,0,421,0,4097,0,856,0,4096,0,1219,0,64,0x7fbc26c78ec0,0,0,0,56,0,65536,65536,0,64,0x7fed73b94ec0,114688,0,32768,32768,16384,16384,65536,49152,56434754.0,202460986.0,49754619.0,131072.0,0.0,558592.0,0,0,24814,26394.0,131085.0,0.0,24.0,64,0x7f65b5028ec0,2208,4096,2208,6304,2220,4096,2220,6316,2173,4097,2174,6270,2168,4096,2168,6264,2157,4096,2157,6253,2176,4097,2177,6273,2179,4096,2179,6275,2173,4096,2173,6269,2173,4096,2173,6269,2210,4096,2210,6306,2215,4096,2215,6311,2178,4096,2178,6274,2169,4096,2169,6265,2215,4097,2216,6312,2177,4096,2177,6273,2183,4096,2183,6279,2177,4099,2180,6276,2205,4096,2205,6301,2157,4098,2159,6255,2223,4096,2223,6319,2183,4096,2183,6279,2168,4099,2171,6267,2156,4096,2156,6252,2183,4096,2183,6279,2181,4096,2181,6277,2180,4096,2180,6276,2207,4096,2207,6303,2161,4096,2161,6257,2225,4096,2225,6321,2182,4096,2182,6278,2166,4096,2166,6262,2152,4096,2152,6248,64,0x7f86b4438ec0,326352,219998,16384,0,16384,16384,32768,49152,40793,40793,3136125.0,2454363.0,4502.0,347779.0,1753482.0,0.0,2443293.0,2133873.0,326344,229021,40793,0,40793,0,1305376.0,762190.0,0.0,0.0,64,0x7f0869250ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,20808,0,2647,39068,0,70062.0,131072.0,0.0,45782.0,64,0x7f1c3083cec0,0,4330318,2840,2840,0,3426749,2868,2868,0,3504767,2856,2856,0,3931420,2836,2836,0,3325380,2876,2876,0,4130117,2844,2844,0,3139565,2856,2856,0,4266411,2828,2828,0,3495466,2820,2820,0,4519191,2834,2834,0,3586841,2868,2868,0,3118187,2852,2852,0,3171777,2836,2836,0,4439257,2876,2876,0,4745545,2844,2844,0,3463541,2858,2858,0,3117032,2812,2812,0,3961551,2848,2848,0,4045052,2844,2844,0,3403891,2860,2860,0,3986132,2824,2824,0,3731800,2878,2878,0,4754579,2824,2824,0,4375906,2832,2832,0,4351714,2830,2830,0,2972415,2812,2812,0,3540266,2852,2852,0,3320714,2844,2844,0,4155841,2860,2860,0,3429068,2824,2824,0,3092763,2880,2880,0,3521856,2824,2824,64,0x7f2d2947cec0,0,393216,163840,0,0,0,0,0,29169,0.0,0.0,0.0,32768.0,0.0,0.0,239.0,32768.0,4096,16384,302,40080,1933,0,56.0,9.0,0.0,200220.0,64,0x7f553b0b0ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131083.0,101033.0,45525.0,0.0,64,0x7effc4ae8ec0,0,188262,0,0,65536,63800,56,1680,64,0x7f123191cec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,114564364.0,55936691.0,0.0,64,0x7f637f758ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2023601.0,64,0x7fb1db9c4ec0,6275,0,4096,6249,0,4096,6241,0,4096,6246,0,4096,6240,0,4096,6242,0,4096,6254,0,4096,6230,0,4096,6233,0,4096,6277,0,4096,6254,0,4096,6243,0,4096,6252,0,4096,6241,0,4096,6244,0,4096,6254,0,4096,6241,0,4096,6238,0,4096,6274,0,4096,6283,0,4096,6229,0,4096,6242,0,4096,6236,0,4096,6229,0,4096,6228,0,4096,6243,0,4096,6238,0,4096,6275,0,4096,6283,0,4096,6228,0,4096,6243,0,4096,6238,0,4096,200174259950853,200174259967493 diff --git a/tests/workloads/kernel_verbose_2/MI200/roofline.csv b/tests/workloads/kernel_verbose_2/MI200/roofline.csv new file mode 100644 index 0000000000..1b07b88444 --- /dev/null +++ b/tests/workloads/kernel_verbose_2/MI200/roofline.csv @@ -0,0 +1,5 @@ +device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh +0,1388.1689,1387.6534,1388.6844,5014.3301,5011.2061,5017.4541,9222.6172,9222.0459,9223.1885,18050.293,18049.406,18051.18,20931.176,20870.689,20991.662,20261.637,20261.008,20262.266,170400.38,170395.67,170405.08,164850.41,164845.45,164855.36,41415.574,41415.02,41416.129,41474.078,41473.312,41474.844,166318.97,165828.61,166809.33 +1,1389.2894,1388.6531,1389.9258,5029.8667,5027.9429,5031.7905,9235.4102,9234.6797,9236.1406,18095.471,18091.338,18099.604,20976.723,20909.848,21043.598,20295.529,20294.941,20296.117,170841.22,170836.52,170845.92,165117.64,165114.41,165120.88,41486.184,41485.363,41487.004,41540.363,41539.438,41541.289,166883.98,166881.17,166886.8 +2,1388.4487,1387.9197,1388.9778,5036.0479,5033.9048,5038.1909,9256.2939,9255.5273,9257.0605,18099.859,18098.83,18100.889,21040.043,21039.582,21040.504,20344.139,20343.57,20344.707,171080.62,171076.52,171084.73,165467.66,165463.81,165471.5,41571.277,41570.355,41572.199,41623.371,41622.438,41624.305,166884.66,166292.78,167476.53 +3,1389.0746,1388.5024,1389.6467,5030.7954,5029.2437,5032.3472,9240.874,9240.2598,9241.4883,18025.227,18021.703,18028.75,21033.723,21033.025,21034.42,20312.977,20312.451,20313.502,171026.72,171023.88,171029.56,165234.98,165230.12,165239.84,41442.422,41288.453,41596.391,41581.973,41581.297,41582.648,167019.41,167017.95,167020.86 diff --git a/tests/workloads/kernel_verbose_2/MI200/sysinfo.csv b/tests/workloads/kernel_verbose_2/MI200/sysinfo.csv new file mode 100644 index 0000000000..1dc99903e3 --- /dev/null +++ b/tests/workloads/kernel_verbose_2/MI200/sysinfo.csv @@ -0,0 +1,2 @@ +workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd +kernel_verbose_2,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 02:47:08 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/kernel_verbose_2/MI200/timestamps.csv b/tests/workloads/kernel_verbose_2/MI200/timestamps.csv new file mode 100644 index 0000000000..a3b3e59c59 --- /dev/null +++ b/tests/workloads/kernel_verbose_2/MI200/timestamps.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,373046,373046,1048576,256,0,0,8,0,16,64,0x0,0x7f7786f54ec0,200174259795652,200174259821413,200174259842053,200174259872358 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,373046,373046,1048576,256,0,0,8,0,16,64,0x0,0x7f7786f54ec0,200174259852831,200174259860293,200174259876453,200174259944224 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,373046,373046,1048576,256,0,0,8,0,16,64,0x0,0x7f7786f54ec0,200174259886715,200174259950853,200174259967493,200174259968429 diff --git a/tests/workloads/kernel_verbose_3/MI100/SQ_IFETCH_LEVEL.csv b/tests/workloads/kernel_verbose_3/MI100/SQ_IFETCH_LEVEL.csv index adde5a513a..22da007d7d 100644 --- a/tests/workloads/kernel_verbose_3/MI100/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/kernel_verbose_3/MI100/SQ_IFETCH_LEVEL.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2904152,2904152,1048576,256,0,0,8,8,16,64,0x0,0x7f425b4d8e80,48194,48194,16384,65536,14285,1852660,2187971638091705,2187972534891178,2187972534915658,2187971645570665 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2904152,2904152,1048576,256,0,0,8,8,16,64,0x0,0x7f425b4d8e80,43069,43069,16384,65536,8189,1048576,2187971645596162,2187972535018378,2187972535037578,2187971645902487 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2904152,2904152,1048576,256,0,0,8,8,16,64,0x0,0x7f425b4d8e80,42487,42487,16384,65536,8312,1048576,2187971645941430,2187972535059178,2187972535078218,2187971646129975 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,206689,206689,1048576,256,0,0,8,8,16,64,0x0,0x7f43269ece80,48693,48693,16384,65536,14469,1865604,194384658278855,194396826197502,194396826221982,194384666142164 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,206689,206689,1048576,256,0,0,8,8,16,64,0x0,0x7f43269ece80,43316,43316,16384,65536,8204,1048580,194384666163785,194396826332862,194396826352062,194384666499089 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,206689,206689,1048576,256,0,0,8,8,16,64,0x0,0x7f43269ece80,42593,42593,16384,65536,8350,1048580,194384666531571,194396826372542,194396826391422,194384666714708 diff --git a/tests/workloads/kernel_verbose_3/MI100/SQ_INST_LEVEL_LDS.csv b/tests/workloads/kernel_verbose_3/MI100/SQ_INST_LEVEL_LDS.csv index f172c7955d..d50fe3815b 100644 --- a/tests/workloads/kernel_verbose_3/MI100/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/kernel_verbose_3/MI100/SQ_INST_LEVEL_LDS.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2902498,2902498,1048576,256,0,0,8,8,16,64,0x0,0x7f3f26590e80,0,0,0,2187967105086841,2187972534891178,2187972534915658,2187967112866806 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2902498,2902498,1048576,256,0,0,8,8,16,64,0x0,0x7f3f26590e80,0,0,0,2187967112886433,2187972535018378,2187972535037578,2187967113226211 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2902498,2902498,1048576,256,0,0,8,8,16,64,0x0,0x7f3f26590e80,0,0,0,2187967113254975,2187972535059178,2187972535078218,2187967113428251 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,206876,206876,1048576,256,0,0,8,8,16,64,0x0,0x7f4d26388e80,0,0,0,194385153601799,194396826197502,194396826221982,194385161313521 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,206876,206876,1048576,256,0,0,8,8,16,64,0x0,0x7f4d26388e80,0,0,0,194385161331686,194396826332862,194396826352062,194385161649227 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,206876,206876,1048576,256,0,0,8,8,16,64,0x0,0x7f4d26388e80,0,0,0,194385161677080,194396826372542,194396826391422,194385161849085 diff --git a/tests/workloads/kernel_verbose_3/MI100/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/kernel_verbose_3/MI100/SQ_INST_LEVEL_SMEM.csv index 169afa3b0f..1dcdaa0866 100644 --- a/tests/workloads/kernel_verbose_3/MI100/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/kernel_verbose_3/MI100/SQ_INST_LEVEL_SMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2902316,2902316,1048576,256,0,0,8,8,16,64,0x0,0x7ff914be4e80,65536,186292,23841864,2187966659468399,2187972534891178,2187972534915658,2187966667025706 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2902316,2902316,1048576,256,0,0,8,8,16,64,0x0,0x7ff914be4e80,65536,166982,21426792,2187966667046906,2187972535018378,2187972535037578,2187966667353932 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2902316,2902316,1048576,256,0,0,8,8,16,64,0x0,0x7ff914be4e80,65536,167902,21431288,2187966667382566,2187972535059178,2187972535078218,2187966667556883 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,207059,207059,1048576,256,0,0,8,8,16,64,0x0,0x7f511354ae80,65536,213020,27276184,194385643338427,194396826197502,194396826221982,194385650922807 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,207059,207059,1048576,256,0,0,8,8,16,64,0x0,0x7f511354ae80,65536,210858,27017696,194385650943867,194396826332862,194396826352062,194385651292708 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,207059,207059,1048576,256,0,0,8,8,16,64,0x0,0x7f511354ae80,65536,226888,29109624,194385651321101,194396826372542,194396826391422,194385651501673 diff --git a/tests/workloads/kernel_verbose_3/MI100/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/kernel_verbose_3/MI100/SQ_INST_LEVEL_VMEM.csv index 0b29328368..5a4ea2e87e 100644 --- a/tests/workloads/kernel_verbose_3/MI100/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/kernel_verbose_3/MI100/SQ_INST_LEVEL_VMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2903408,2903408,1048576,256,0,0,8,8,16,64,0x0,0x7fcb25bece80,32768,650024,83216544,2187969596608363,2187972534891178,2187972534915658,2187969604283250 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2903408,2903408,1048576,256,0,0,8,8,16,64,0x0,0x7fcb25bece80,32768,675663,86476904,2187969604301304,2187972535018378,2187972535037578,2187969604617267 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2903408,2903408,1048576,256,0,0,8,8,16,64,0x0,0x7fcb25bece80,32768,667609,85437516,2187969604645480,2187972535059178,2187972535078218,2187969604817834 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,207248,207248,1048576,256,0,0,8,8,16,64,0x0,0x7f247b7bae80,32768,647852,82918112,194386133628101,194396826197502,194396826221982,194386141441194 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,207248,207248,1048576,256,0,0,8,8,16,64,0x0,0x7f247b7bae80,32768,686109,87810960,194386141462445,194396826332862,194396826352062,194386141756702 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,207248,207248,1048576,256,0,0,8,8,16,64,0x0,0x7f247b7bae80,32768,664689,85064412,194386141784915,194396826372542,194396826391422,194386141990585 diff --git a/tests/workloads/kernel_verbose_3/MI100/SQ_LEVEL_WAVES.csv b/tests/workloads/kernel_verbose_3/MI100/SQ_LEVEL_WAVES.csv index 450cd84d75..379e0427f9 100644 --- a/tests/workloads/kernel_verbose_3/MI100/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/kernel_verbose_3/MI100/SQ_LEVEL_WAVES.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2902680,2902680,1048576,256,0,0,8,8,16,64,0x0,0x7f548715ee80,48675,48675,16935,389408,16384,25332945,238585,0,101826432,2187967555826467,2187972534891178,2187972534915658,2187967563379597 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2902680,2902680,1048576,256,0,0,8,8,16,64,0x0,0x7f548715ee80,41997,41997,12499,335984,16384,23739645,232240,0,95445096,2187967563410094,2187972535018378,2187972535037578,2187967563720657 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2902680,2902680,1048576,256,0,0,8,8,16,64,0x0,0x7f548715ee80,42117,42117,12159,336944,16384,24844257,234142,0,99859328,2187967563759820,2187972535059178,2187972535078218,2187967563946040 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,207434,207434,1048576,256,0,0,8,8,16,64,0x0,0x7f839c740e80,48577,48577,18491,388624,16384,25209993,235570,0,101320804,194386624498284,194396826197502,194396826221982,194386632110978 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,207434,207434,1048576,256,0,0,8,8,16,64,0x0,0x7f839c740e80,43097,43097,14640,344784,16384,24236574,228131,0,97443576,194386632139723,194396826332862,194396826352062,194386632506297 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,207434,207434,1048576,256,0,0,8,8,16,64,0x0,0x7f839c740e80,42960,42960,14329,343688,16384,24452621,227388,0,98300612,194386632544118,194396826372542,194396826391422,194386632731563 diff --git a/tests/workloads/kernel_verbose_3/MI100/pmc_dispatch_info.csv b/tests/workloads/kernel_verbose_3/MI100/pmc_dispatch_info.csv new file mode 100644 index 0000000000..17300ae9af --- /dev/null +++ b/tests/workloads/kernel_verbose_3/MI100/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) ",2 +1,"vecCopy(double*, double*, double*, int, int) ",2 +2,"vecCopy(double*, double*, double*, int, int) ",2 diff --git a/tests/workloads/kernel_verbose_3/MI100/pmc_perf.csv b/tests/workloads/kernel_verbose_3/MI100/pmc_perf.csv index 7de7e467a8..46ed8fd8e0 100644 --- a/tests/workloads/kernel_verbose_3/MI100/pmc_perf.csv +++ b/tests/workloads/kernel_verbose_3/MI100/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_1,obj_1,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_2,obj_2,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_3,obj_3,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_4,obj_4,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_5,obj_5,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_6,obj_6,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_7,obj_7,TCC_EA_ATOMIC_LEVEL_sum,wave_size_8,obj_8,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_9,obj_9,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_10,obj_10,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_11,obj_11,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_12,obj_12,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_13,obj_13,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_14,obj_14,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_15,obj_15,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_16,obj_16,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f3970d90e80,8192,0,4096,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f869aa6ee80,4838,0,0,2039745,4442,0,0,1963650,2144,0,0,1712993,5136,0,0,2015775,3466,0,0,1990103,3647,0,0,1893680,1914,0,0,1696803,2795,0,0,1891489,2730,0,0,1913790,4645,0,0,2037640,1205,0,0,1574717,4099,0,0,1952712,4595,0,0,2019289,3764,0,0,1906068,1813,0,0,1758283,4800,0,0,2003942,2744,0,0,1856900,4127,0,0,2036913,2357,0,0,1757867,3358,0,0,1857619,2663,0,0,1836839,5145,0,0,2097476,1679,0,0,1710061,5215,0,0,2015286,3275,0,0,1895452,3599,0,0,1907947,3475,0,0,1972747,3934,0,0,1914830,4217,0,0,1942441,5079,0,0,2028400,1860,0,0,1673594,4706,0,0,2028212,64,0x7f5e4ca4ee80,32768,0,0,0,16384,16384,393216,22827237,960.0,513911.0,0.0,524288.0,889659.0,32768.0,0,0,0,16744,131072.0,131072.0,0.0,131072.0,64,0x7f9cba3dae80,2314354,360448,163840,0,0,180224,114688,0,68744211.0,204855511.0,79050065.0,131072.0,0.0,680988.0,0,0,26958,116308.0,0.0,0.0,116308.0,64,0x7f039dc3ce80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131342.0,0.0,532.0,131341.0,64,0x7fcecf5bae80,189673,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,14073,30457,9775,550,0,46647,262677.0,0.0,188.0,262489.0,64,0x7f9465f46e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86556.0,44516.0,131112.0,0.0,64,0x7fac0ee66e80,0.0,64,0x7f2e6b89ce80,0,0,192,0,65536,64483,48,1289,33249,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,539,49116,1660,0,48.0,384.0,0.0,262288.0,64,0x7fdfa8a86e80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8371,4275,8371,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,141,8195,4240,8336,0,8192,4096,8192,0,8192,4096,8192,64,0x7f55ae4d2e80,0,3669296,4096,4096,0,3311558,4096,4096,0,4404994,4096,4096,0,2822972,4096,4096,0,3791878,4096,4096,0,2895529,4096,4096,0,3602961,4096,4096,0,3187408,4096,4096,0,3201140,4096,4096,0,5197387,4096,4096,0,2768864,4096,4096,0,2726510,4096,4096,0,2949439,4096,4096,0,4653000,4096,4096,0,2973854,4096,4096,0,2322772,4096,4096,0,4019575,4096,4096,0,5372978,4096,4096,0,2836001,4096,4096,0,2734347,4096,4096,0,4741243,4096,4096,0,4979638,4096,4096,0,3604267,4096,4096,0,2552198,4096,4096,0,3102566,4096,4096,0,3269513,4096,4096,0,3065157,4096,4096,0,2803610,4096,4096,0,3117225,4096,4096,0,3843700,4096,4096,0,3038858,4096,4096,0,3846875,4096,4096,64,0x7fd4a2104e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,47352,0,131600.0,131072.0,0.0,131104.0,64,0x7fd628c42e80,4096,0,104,0,4096,0,1532,0,4096,0,1403,0,4099,0,287,0,4096,0,1511,0,4096,0,115,0,4096,0,708,0,4096,0,303,0,4096,0,1427,0,4097,0,203,0,4096,0,942,0,4096,0,1263,0,4096,0,713,0,4096,0,1158,0,4216,0,1513,0,4096,0,702,0,4096,0,380,0,4096,0,3497,0,4096,0,1660,0,4096,0,317,0,4214,0,5284,0,4096,0,316,0,4096,0,1590,0,4096,0,0,0,4144,0,0,0,4096,0,1609,0,4096,0,1073,0,4144,0,926,0,4096,0,1015,0,4096,0,383,0,4096,0,1692,0,4096,0,1221,0,64,0x7f15eafc6e80,131072.0,131072.0,0.0,2432037.0,0.0,0.0,111732510.0,61268276.0,64,0x7ffa89b16e80,0,49531,0,0,0,49531,0,0,0,49531,0,0,0,49531,0,0,0,49531,0,0,0,49531,0,0,0,49531,0,0,0,49531,0,0,0,49531,0,0,0,49531,0,0,0,49531,0,0,0,49531,0,0,0,49531,0,0,0,49531,0,0,0,49531,0,0,0,49531,0,0,0,49531,0,0,0,49531,0,0,0,49531,0,0,0,49531,0,0,0,49531,0,0,0,49531,0,0,0,49531,0,0,0,49531,0,0,0,49531,0,0,0,49531,0,0,0,49531,0,0,0,49531,0,0,0,49531,0,0,0,49531,0,0,0,49531,0,0,0,49531,0,0,64,0x7fba4a320e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,25863.0,106983.0,64,0x7fc20ddaae80,387144,236906,3462836,16384,25460814,144,48,0,48392,48392,3906142.0,3006675.0,5792.0,1052977.0,2049764.0,0.0,2997562.0,2686015.0,385887,246846,48392,0,48392,0,1548544.0,958433.0,0.0,0.0,2187972534891178,2187972534915658 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f3970d90e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f869aa6ee80,3072,0,0,1449795,3494,0,0,1521650,3253,0,0,1564300,3112,0,0,1619231,2431,0,0,1489591,2284,0,0,1428437,1273,0,0,1331752,2834,0,0,1584571,3346,0,0,1505031,3647,0,0,1596900,2077,0,0,1409125,2419,0,0,1553929,3746,0,0,1504584,2453,0,0,1403900,4045,0,0,1659582,3000,0,0,1518625,5407,0,0,1690475,3163,0,0,1531850,2997,0,0,1505856,2809,0,0,1438932,3598,0,0,1578928,2889,0,0,1439273,6089,0,0,1882981,2177,0,0,1456134,3563,0,0,1499920,3332,0,0,1534897,2775,0,0,1563634,3591,0,0,1623277,2805,0,0,1405808,3817,0,0,1585775,2666,0,0,1520136,5232,0,0,1757230,64,0x7f5e4ca4ee80,32768,0,0,0,16384,16384,393216,23082320,960.0,513986.0,0.0,524288.0,930151.0,32768.0,0,0,0,13868,86716.0,86716.0,0.0,86716.0,64,0x7f9cba3dae80,2229727,360448,163840,0,0,180224,114688,0,65248025.0,185092049.0,73965490.0,131072.0,0.0,765386.0,0,0,26657,89432.0,0.0,0.0,89432.0,64,0x7f039dc3ce80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131346.0,0.0,546.0,131345.0,64,0x7fcecf5bae80,186655,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,12306,28690,8594,3223,0,42477,262577.0,0.0,47.0,262530.0,64,0x7f9465f46e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86451.0,0.0,131110.0,0.0,64,0x7fac0ee66e80,0.0,64,0x7f2e6b89ce80,0,0,48,0,65536,65536,0,0,31412,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,457,42788,1740,0,48.0,389.0,0.0,262144.0,64,0x7fdfa8a86e80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8195,4099,8195,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8338,4242,8338,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f55ae4d2e80,0,3975935,2706,2706,0,5480144,2722,2722,0,3306016,2684,2684,0,3510906,2732,2732,0,2896726,2712,2712,0,3014119,2736,2736,0,4543990,2698,2698,0,4014239,2716,2716,0,4881393,2670,2670,0,4782876,2707,2707,0,2996595,2698,2698,0,5046679,2724,2724,0,3092001,2708,2708,0,4068091,2702,2702,0,4186170,2682,2682,0,4099972,2704,2704,0,4787227,2688,2688,0,3966896,2736,2736,0,3484297,2708,2708,0,4530195,2724,2724,0,2561164,2692,2692,0,4010698,2749,2749,0,2841819,2704,2704,0,3081570,2698,2698,0,2877530,2706,2706,0,4101094,2704,2704,0,4148971,2724,2724,0,2628533,2716,2716,0,3393589,2696,2696,0,4216577,2709,2709,0,2763493,2716,2716,0,3607699,2696,2696,64,0x7fd4a2104e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,38032,0,131120.0,131072.0,0.0,86487.0,64,0x7fd628c42e80,4098,0,3347,0,4096,0,2849,0,4097,0,2367,0,4096,0,3272,0,4096,0,1279,0,4096,0,1617,0,4096,0,1402,0,4096,0,2272,0,4096,0,1904,0,4097,0,1004,0,4096,0,308,0,4096,0,1520,0,4096,0,1548,0,4096,0,478,0,4219,0,4885,0,4096,0,627,0,4096,0,1600,0,4096,0,1754,0,4096,0,280,0,4096,0,998,0,4179,0,1213,0,4096,0,942,0,4096,0,2440,0,4096,0,292,0,4144,0,2161,0,4096,0,0,0,4096,0,5436,0,4144,0,1422,0,4096,0,1060,0,4096,0,1428,0,4096,0,170,0,4096,0,923,0,64,0x7f15eafc6e80,131072.0,131072.0,0.0,2738237.0,0.0,0.0,95212553.0,31412698.0,64,0x7ffa89b16e80,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,64,0x7fba4a320e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,30292.0,138535.0,64,0x7fc20ddaae80,370920,229187,3355349,16384,24454009,0,48,0,46364,46364,3727826.0,3026151.0,5270.0,1121547.0,2076178.0,0.0,3017353.0,2706323.0,370912,238971,46364,0,46364,1049,1483648.0,816960.0,0.0,0.0,2187972535018378,2187972535037578 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f3970d90e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f869aa6ee80,3221,0,0,1480222,3515,0,0,1506819,5779,0,0,1802317,4547,0,0,1757100,2661,0,0,1468617,2179,0,0,1456042,4157,0,0,1598716,3808,0,0,1608085,4008,0,0,1619786,3654,0,0,1595555,4842,0,0,1705460,2871,0,0,1522750,4049,0,0,1574638,2507,0,0,1484900,4471,0,0,1696150,3108,0,0,1567809,4910,0,0,1701508,1486,0,0,1398453,4205,0,0,1594245,3785,0,0,1576019,2746,0,0,1469990,3783,0,0,1567939,2963,0,0,1513741,4559,0,0,1601557,3358,0,0,1561727,3084,0,0,1468468,4566,0,0,1658082,3701,0,0,1548343,2969,0,0,1532931,4846,0,0,1674104,4391,0,0,1696699,3298,0,0,1505027,64,0x7f5e4ca4ee80,32768,0,0,0,16384,16384,393216,22603791,960.0,513890.0,0.0,524288.0,923748.0,32768.0,0,0,0,14420,86480.0,86480.0,0.0,86480.0,64,0x7f9cba3dae80,2749070,360448,163840,0,0,180224,114688,0,63738710.0,183168728.0,75516200.0,131072.0,0.0,848860.0,0,0,27014,78230.0,0.0,0.0,78230.0,64,0x7f039dc3ce80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131344.0,0.0,542.0,131343.0,64,0x7fcecf5bae80,189300,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,14365,30749,8601,3328,0,41136,262514.0,0.0,47.0,262467.0,64,0x7f9465f46e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86361.0,0.0,131112.0,0.0,64,0x7fac0ee66e80,0.0,64,0x7f2e6b89ce80,0,0,48,0,65536,65536,0,0,30780,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,457,42180,1759,0,48.0,390.0,0.0,262144.0,64,0x7fdfa8a86e80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8195,4099,8195,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8345,4249,8345,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f55ae4d2e80,0,4874597,2704,2704,0,4499623,2714,2714,0,3190499,2652,2652,0,3939651,2676,2676,0,4279204,2684,2684,0,3997782,2740,2740,0,3828912,2684,2684,0,4067294,2700,2700,0,4220204,2710,2710,0,4312896,2702,2702,0,4700883,2680,2680,0,4778105,2722,2722,0,4432673,2696,2696,0,4530712,2700,2700,0,3948090,2686,2686,0,4010100,2682,2682,0,4399850,2692,2692,0,4066929,2704,2704,0,3763701,2665,2665,0,4752081,2706,2706,0,4112967,2702,2702,0,4240228,2731,2731,0,3778141,2684,2684,0,3556517,2694,2694,0,3683407,2696,2696,0,4771654,2689,2689,0,3743750,2714,2714,0,3510278,2694,2694,0,4139346,2722,2722,0,4478234,2710,2710,0,4524585,2698,2698,0,3774795,2660,2660,64,0x7fd4a2104e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,4512,107309,158,131427.0,131072.0,0.0,87673.0,64,0x7fd628c42e80,4098,0,657,0,4096,0,1673,0,4097,0,0,0,4096,0,0,0,4096,0,68,0,4096,0,372,0,4096,0,915,0,4096,0,14,0,4096,0,325,0,4097,0,852,0,4096,0,961,0,4096,0,1710,0,4096,0,570,0,4096,0,300,0,4219,0,8747,0,4096,0,0,0,4096,0,29,0,4096,0,970,0,4096,0,9,0,4096,0,58,0,4158,0,0,0,4096,0,2648,0,4096,0,235,0,4096,0,0,0,4144,0,726,0,4096,0,1808,0,4096,0,968,0,4144,0,2131,0,4096,0,63,0,4096,0,4462,0,4096,0,0,0,4096,0,0,0,64,0x7f15eafc6e80,131072.0,131072.0,0.0,2506646.0,0.0,0.0,132611734.0,45877666.0,64,0x7ffa89b16e80,0,43160,0,0,0,43160,0,0,0,43160,0,0,0,43160,0,0,0,43160,0,0,0,43160,0,0,0,43160,0,0,0,43160,0,0,0,43160,0,0,0,43160,0,0,0,43160,0,0,0,43160,0,0,0,43160,0,0,0,43160,0,0,0,43160,0,0,0,43160,0,0,0,43160,0,0,0,43160,0,0,0,43160,0,0,0,43160,0,0,0,43160,0,0,0,43160,0,0,0,43160,0,0,0,43160,0,0,0,43160,0,0,0,43160,0,0,0,43160,0,0,0,43160,0,0,0,43160,0,0,0,43160,0,0,0,43160,0,0,0,43160,0,0,64,0x7fba4a320e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,15014.0,103182.0,64,0x7fc20ddaae80,340128,229118,3346971,16384,24433836,0,48,0,42515,42515,3726612.0,2992535.0,6227.0,981409.0,2042233.0,0.0,2983243.0,2671547.0,340120,238651,42515,0,42515,0,1360480.0,804096.0,0.0,0.0,2187972535059178,2187972535078218 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_1,obj_1,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_2,obj_2,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_3,obj_3,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_4,obj_4,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_5,obj_5,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_6,obj_6,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_7,obj_7,TCC_EA_ATOMIC_LEVEL_sum,wave_size_8,obj_8,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_9,obj_9,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_10,obj_10,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_11,obj_11,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_12,obj_12,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_13,obj_13,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_14,obj_14,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_15,obj_15,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_16,obj_16,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f5508d98e80,184843,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13902,30286,9861,550,0,46421,262634.0,0.0,188.0,262446.0,64,0x7fee2df36e80,0,0,192,0,65536,64388,48,1373,32476,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,538,48425,1718,0,48.0,289.0,0.0,262288.0,64,0x7f0995892e80,0,8192,4096,8192,0,8192,4096,8192,0,8342,4246,8342,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,141,8243,4288,8384,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f2ab255ae80,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,64,0x7f6a7b45ae80,382896,228889,3349219,16384,24380469,144,48,0,47861,47861,3786114.0,2947353.0,5519.0,1093149.0,2075525.0,0.0,2938717.0,2629100.0,381247,238828,47861,0,47861,0,1531552.0,958923.0,0.0,0.0,64,0x7fa8a50a8e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86606.0,44466.0,131111.0,0.0,64,0x7fa08cd16e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,47392,0,131550.0,131072.0,0.0,131104.0,64,0x7fdea13e8e80,0.0,64,0x7fcbfe282e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131472.0,0.0,792.0,131471.0,64,0x7ffa6be20e80,3859,0,0,1970765,3681,0,0,1984118,635,0,0,1611375,2014,0,0,1821378,398,0,0,1584425,3624,0,0,2005190,1299,0,0,1833567,4055,0,0,2060337,665,0,0,1582695,2478,0,0,1864662,807,0,0,1667599,3815,0,0,2094149,2489,0,0,1906402,1409,0,0,1772055,1089,0,0,1701191,4564,0,0,2065336,2791,0,0,1882729,2506,0,0,1870477,1977,0,0,1823086,2831,0,0,1904967,1631,0,0,1835109,3821,0,0,2117574,1454,0,0,1839408,2889,0,0,1950532,2083,0,0,1752582,2025,0,0,1811453,862,0,0,1728671,5806,0,0,2079569,2394,0,0,1902911,2217,0,0,1867275,2716,0,0,1936833,3107,0,0,1974779,64,0x7fe7a4682e80,32768,0,0,0,16384,16384,393216,23217465,960.0,513989.0,0.0,524288.0,893109.0,32768.0,0,0,0,16632,131072.0,131072.0,0.0,131072.0,64,0x7f3ce5ea6e80,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fdb47134e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,74795.0,141833.0,64,0x7f912f362e80,0,4913610,4096,4096,0,3440750,4096,4096,0,3451033,4096,4096,0,3012196,4096,4096,0,4179555,4096,4096,0,4184987,4096,4096,0,3449114,4096,4096,0,4180696,4096,4096,0,4473068,4096,4096,0,3697658,4096,4096,0,4624928,4096,4096,0,4341236,4096,4096,0,4524291,4096,4096,0,3774306,4096,4096,0,3834415,4096,4096,0,3054436,4096,4096,0,4849916,4096,4096,0,3854440,4096,4096,0,4273841,4096,4096,0,3044787,4096,4096,0,4315615,4096,4096,0,3094589,4096,4096,0,5124172,4096,4096,0,3359898,4096,4096,0,4669912,4096,4096,0,5241771,4096,4096,0,4064690,4096,4096,0,3095054,4096,4096,0,4829537,4096,4096,0,4142466,4096,4096,0,4488083,4096,4096,0,3337502,4096,4096,64,0x7f1809e16e80,4096,0,7400,0,4096,0,1410,0,4099,0,23,0,4096,0,0,0,4239,0,83,0,4096,0,6,0,4096,0,827,0,4096,0,46,0,4144,0,328,0,4096,0,3,0,4096,0,155,0,4144,0,22,0,4096,0,2165,0,4096,0,1222,0,4096,0,706,0,4096,0,0,0,4096,0,2845,0,4096,0,1753,0,4096,0,1452,0,4096,0,1725,0,4096,0,105,0,4097,0,4198,0,4096,0,112,0,4096,0,0,0,4096,0,16,0,4096,0,63,0,4096,0,923,0,4096,0,58,0,4096,0,248,0,4096,0,1470,0,4096,0,94,0,4096,0,282,0,64,0x7fb76b03ce80,2225524,360448,163840,0,0,180224,114688,0,70490386.0,198596091.0,76945764.0,131072.0,0.0,720519.0,0,0,26958,111489.0,0.0,0.0,111489.0,64,0x7fbc23f24e80,131072.0,131072.0,0.0,2573261.0,0.0,0.0,120200135.0,60407108.0,194396826197502,194396826221982 +1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f5508d98e80,183073,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13917,30301,8550,2895,0,41199,262499.0,0.0,47.0,262452.0,64,0x7fee2df36e80,0,0,48,0,65536,65536,0,0,31295,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,456,42618,1751,0,48.0,289.0,0.0,262144.0,64,0x7f0995892e80,0,8192,4096,8192,0,8192,4096,8192,0,8353,4257,8353,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8242,4146,8242,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f2ab255ae80,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,64,0x7f6a7b45ae80,398816,253525,3656449,16384,27608011,0,96,0,49851,49851,4093106.0,3142810.0,4779.0,1305387.0,2477227.0,0.0,3127820.0,2818002.0,398808,263315,49851,0,49851,1071,1595232.0,919010.0,1.0,0.0,64,0x7fa8a50a8e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86992.0,0.0,131112.0,0.0,64,0x7fa08cd16e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,240.0,524288.0,0.0,0.0,0,0,5672,44419,1069,131878.0,131072.0,0.0,100886.0,64,0x7fdea13e8e80,0.0,64,0x7fcbfe282e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131413.0,0.0,680.0,131412.0,64,0x7ffa6be20e80,2393,0,0,1505669,1806,0,0,1382894,1480,0,0,1315597,782,0,0,1244727,905,0,0,1407983,987,0,0,1401679,1650,0,0,1416579,1957,0,0,1476147,1009,0,0,1362920,377,0,0,1216413,561,0,0,1284898,842,0,0,1358815,3596,0,0,1644906,743,0,0,1285517,460,0,0,1359592,419,0,0,1245569,3764,0,0,1641410,1376,0,0,1384620,2651,0,0,1686642,392,0,0,1280907,4974,0,0,1786735,2025,0,0,1489720,2750,0,0,1600983,702,0,0,1252677,1987,0,0,1452574,1240,0,0,1387814,541,0,0,1328206,2416,0,0,1517465,1641,0,0,1328849,5124,0,0,1757667,1966,0,0,1508761,854,0,0,1398100,64,0x7fe7a4682e80,32768,0,0,0,16384,16384,393216,23214843,960.0,513820.0,0.0,524288.0,1000532.0,32768.0,0,0,0,15843,86661.0,86661.0,0.0,86661.0,64,0x7f3ce5ea6e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fdb47134e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,63379.0,129485.0,64,0x7f912f362e80,0,5406074,2746,2746,0,4542210,2692,2692,0,4168543,2694,2694,0,2979635,2700,2700,0,4522300,2700,2700,0,3781123,2690,2690,0,4354132,2729,2729,0,4131338,2698,2698,0,4771312,2716,2716,0,4308948,2648,2648,0,3778388,2722,2722,0,4860900,2716,2716,0,4453289,2717,2717,0,4258046,2652,2652,0,4826419,2721,2721,0,3514255,2672,2672,0,5138906,2701,2701,0,4451913,2691,2691,0,4874714,2724,2724,0,3103815,2698,2698,0,3478356,2708,2708,0,4425368,2716,2716,0,4300990,2706,2706,0,2892985,2694,2694,0,4234505,2712,2712,0,3932490,2672,2672,0,3494117,2758,2758,0,3322920,2699,2699,0,3706708,2732,2732,0,4753931,2666,2666,0,4796012,2732,2732,0,3421325,2684,2684,64,0x7f1809e16e80,4096,0,625,0,4096,0,1196,0,4096,0,472,0,4096,0,74,0,4356,0,1728,0,4096,0,1568,0,4096,0,664,0,4096,0,1448,0,4144,0,486,0,4096,0,134,0,4096,0,1845,0,4144,0,1242,0,4096,0,364,0,4097,0,3648,0,4096,0,5968,0,4096,0,815,0,4096,0,4108,0,4096,0,1970,0,4096,0,3011,0,4098,0,3166,0,4096,0,0,0,4097,0,2829,0,4096,0,4357,0,4096,0,131,0,4096,0,0,0,4096,0,2286,0,4096,0,552,0,4096,0,56,0,4096,0,457,0,4096,0,697,0,4096,0,1411,0,4097,0,6440,0,64,0x7fb76b03ce80,1295324,360448,163840,0,0,180224,114688,0,70428307.0,199281393.0,78745788.0,131072.0,0.0,770740.0,0,0,25457,111815.0,0.0,0.0,111815.0,64,0x7fbc23f24e80,131072.0,131072.0,0.0,2595896.0,0.0,0.0,124626523.0,46691436.0,194396826332862,194396826352062 +2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f5508d98e80,183878,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,12351,28735,8605,2881,0,41218,262475.0,0.0,47.0,262428.0,64,0x7fee2df36e80,0,0,48,0,65536,65536,0,0,31164,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,457,42753,1756,0,48.0,300.0,0.0,262144.0,64,0x7f0995892e80,0,8192,4096,8192,0,8192,4096,8192,0,8350,4254,8350,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8242,4146,8242,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f2ab255ae80,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,64,0x7f6a7b45ae80,344368,234389,3406775,16384,25110806,0,48,0,43045,43045,3805602.0,3051655.0,4688.0,1229012.0,2233630.0,0.0,3042247.0,2733003.0,344360,243917,43045,0,43045,0,1377440.0,836248.0,0.0,0.0,64,0x7fa8a50a8e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86562.0,0.0,131112.0,0.0,64,0x7fa08cd16e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,2728,39753,0,131401.0,131072.0,0.0,86539.0,64,0x7fdea13e8e80,0.0,64,0x7fcbfe282e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131403.0,0.0,660.0,131402.0,64,0x7ffa6be20e80,2698,0,0,1508527,2706,0,0,1594950,822,0,0,1253756,895,0,0,1383191,1011,0,0,1347161,1423,0,0,1436486,1020,0,0,1364229,1415,0,0,1465863,1106,0,0,1372123,3346,0,0,1630053,354,0,0,1304213,1716,0,0,1489722,757,0,0,1329802,1964,0,0,1560150,561,0,0,1310838,1843,0,0,1508879,1073,0,0,1355347,1662,0,0,1426961,1078,0,0,1409297,1997,0,0,1542878,1917,0,0,1497069,2521,0,0,1592084,1840,0,0,1479610,3168,0,0,1616809,1055,0,0,1348494,2948,0,0,1548195,955,0,0,1365520,6642,0,0,1835795,2289,0,0,1519329,4078,0,0,1764730,4556,0,0,1707012,1048,0,0,1385439,64,0x7fe7a4682e80,32768,0,0,0,16384,16384,393216,22648440,960.0,514059.0,0.0,524288.0,910739.0,32768.0,0,0,0,13564,86249.0,86249.0,0.0,86249.0,64,0x7f3ce5ea6e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fdb47134e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,64357.0,131446.0,64,0x7f912f362e80,0,4265051,2690,2690,0,3724900,2696,2696,0,4508775,2666,2666,0,3672269,2708,2708,0,3602539,2674,2674,0,4585509,2730,2730,0,3151448,2721,2721,0,4269878,2722,2722,0,3625060,2672,2672,0,4042630,2700,2700,0,3316608,2720,2720,0,4887594,2756,2756,0,3687904,2699,2699,0,4909789,2674,2674,0,5105095,2695,2695,0,4227334,2735,2735,0,3486620,2688,2688,0,4915692,2679,2679,0,3211476,2674,2674,0,4602044,2720,2720,0,3119021,2704,2704,0,3942482,2732,2732,0,3486389,2690,2690,0,2989916,2723,2723,0,2423470,2668,2668,0,4494094,2708,2708,0,3270528,2736,2736,0,3977918,2724,2724,0,3392450,2690,2690,0,4695773,2689,2689,0,2931919,2696,2696,0,4837499,2718,2718,64,0x7f1809e16e80,4096,0,0,0,4096,0,1036,0,4096,0,2049,0,4096,0,653,0,4336,0,1607,0,4096,0,1463,0,4096,0,0,0,4096,0,1536,0,4144,0,992,0,4096,0,1989,0,4096,0,26,0,4144,0,1530,0,4096,0,0,0,4097,0,965,0,4096,0,60,0,4096,0,111,0,4096,0,786,0,4096,0,7893,0,4096,0,910,0,4098,0,860,0,4096,0,355,0,4097,0,253,0,4096,0,0,0,4096,0,480,0,4096,0,196,0,4096,0,503,0,4096,0,805,0,4096,0,1575,0,4096,0,1282,0,4096,0,0,0,4096,0,5637,0,4097,0,979,0,64,0x7fb76b03ce80,1391842,360448,163840,0,0,180224,114688,0,70516697.0,203434105.0,79228043.0,131072.0,0.0,748918.0,0,0,25591,130010.0,0.0,0.0,130010.0,64,0x7fbc23f24e80,131072.0,131072.0,0.0,2574918.0,0.0,0.0,119544141.0,45104787.0,194396826372542,194396826391422 diff --git a/tests/workloads/kernel_verbose_3/MI100/sysinfo.csv b/tests/workloads/kernel_verbose_3/MI100/sysinfo.csv index 02e1b5e1df..15114cd207 100644 --- a/tests/workloads/kernel_verbose_3/MI100/sysinfo.csv +++ b/tests/workloads/kernel_verbose_3/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -kernel_verbose_3,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Fri Mar 1 16:47:54 2024 (CST),1,t006-003.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651240,,5.7.1-98,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +kernel_verbose_3,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 07 Mar 2024 01:10:49 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/kernel_verbose_3/MI100/timestamps.csv b/tests/workloads/kernel_verbose_3/MI100/timestamps.csv index 60e6337ebf..43443b4bff 100644 --- a/tests/workloads/kernel_verbose_3/MI100/timestamps.csv +++ b/tests/workloads/kernel_verbose_3/MI100/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,2904516,2904516,1048576,256,0,0,8,8,16,64,0x0,0x7fb62cbb2e80,2187972534864992,2187972534891178,2187972534915658,2187972534928922 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,2904516,2904516,1048576,256,0,0,8,8,16,64,0x0,0x7fb62cbb2e80,2187972534928402,2187972535018378,2187972535037578,2187972535038809 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,2904516,2904516,1048576,256,0,0,8,8,16,64,0x0,0x7fb62cbb2e80,2187972535050471,2187972535059178,2187972535078218,2187972535079265 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,210790,210790,1048576,256,0,0,8,8,16,64,0x0,0x7f8894d18e80,194396826171795,194396826197502,194396826221982,194396826235726 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,210790,210790,1048576,256,0,0,8,8,16,64,0x0,0x7f8894d18e80,194396826234664,194396826332862,194396826352062,194396826353259 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,210790,210790,1048576,256,0,0,8,8,16,64,0x0,0x7f8894d18e80,194396826363709,194396826372542,194396826391422,194396826392423 diff --git a/tests/workloads/kernel_verbose_3/MI200/SQ_IFETCH_LEVEL.csv b/tests/workloads/kernel_verbose_3/MI200/SQ_IFETCH_LEVEL.csv new file mode 100644 index 0000000000..fa09789595 --- /dev/null +++ b/tests/workloads/kernel_verbose_3/MI200/SQ_IFETCH_LEVEL.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,374560,374560,1048576,256,0,0,8,0,16,64,0x0,0x7f1c198c8ec0,27304,27304,16384,65536,13690,1541648,200364037453801,200376896683431,200376896703751,200364053586099 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,374560,374560,1048576,256,0,0,8,0,16,64,0x0,0x7f1c198c8ec0,40592,40592,16384,65536,9067,1048664,200364053606127,200376896785031,200376896801511,200364053915061 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,374560,374560,1048576,256,0,0,8,0,16,64,0x0,0x7f1c198c8ec0,40381,40381,16384,65536,9390,1048628,200364053944887,200376896822791,200376896838791,200364054105652 diff --git a/tests/workloads/kernel_verbose_3/MI200/SQ_INST_LEVEL_LDS.csv b/tests/workloads/kernel_verbose_3/MI200/SQ_INST_LEVEL_LDS.csv new file mode 100644 index 0000000000..cce6baf3d9 --- /dev/null +++ b/tests/workloads/kernel_verbose_3/MI200/SQ_INST_LEVEL_LDS.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,374762,374762,1048576,256,0,0,8,0,16,64,0x0,0x7f85d0858ec0,0,0,0,200364529244124,200376896683431,200376896703751,200364545052319 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,374762,374762,1048576,256,0,0,8,0,16,64,0x0,0x7f85d0858ec0,0,0,0,200364545078108,200376896785031,200376896801511,200364545315327 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,374762,374762,1048576,256,0,0,8,0,16,64,0x0,0x7f85d0858ec0,0,0,0,200364545342398,200376896822791,200376896838791,200364545475360 diff --git a/tests/workloads/kernel_verbose_3/MI200/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/kernel_verbose_3/MI200/SQ_INST_LEVEL_SMEM.csv new file mode 100644 index 0000000000..058adf7b52 --- /dev/null +++ b/tests/workloads/kernel_verbose_3/MI200/SQ_INST_LEVEL_SMEM.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,374963,374963,1048576,256,0,0,8,0,16,64,0x0,0x7f343fc74ec0,65536,173402,19359720,200365011775202,200376896683431,200376896703751,200365027932057 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,374963,374963,1048576,256,0,0,8,0,16,64,0x0,0x7f343fc74ec0,65536,233884,26199952,200365027949490,200376896785031,200376896801511,200365028257833 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,374963,374963,1048576,256,0,0,8,0,16,64,0x0,0x7f343fc74ec0,65536,226524,25416944,200365028281277,200376896822791,200376896838791,200365028549555 diff --git a/tests/workloads/kernel_verbose_3/MI200/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/kernel_verbose_3/MI200/SQ_INST_LEVEL_VMEM.csv new file mode 100644 index 0000000000..7e25b6a6ed --- /dev/null +++ b/tests/workloads/kernel_verbose_3/MI200/SQ_INST_LEVEL_VMEM.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,375161,375161,1048576,256,0,0,8,0,16,64,0x0,0x7f6600634ec0,32768,293599,32874012,200365501049676,200376896683431,200376896703751,200365517396009 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,375161,375161,1048576,256,0,0,8,0,16,64,0x0,0x7f6600634ec0,32768,575330,64446764,200365517417340,200376896785031,200376896801511,200365517640813 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,375161,375161,1048576,256,0,0,8,0,16,64,0x0,0x7f6600634ec0,32768,592307,66327576,200365517667002,200376896822791,200376896838791,200365517816915 diff --git a/tests/workloads/kernel_verbose_3/MI200/SQ_LEVEL_WAVES.csv b/tests/workloads/kernel_verbose_3/MI200/SQ_LEVEL_WAVES.csv new file mode 100644 index 0000000000..2d0dae3cd2 --- /dev/null +++ b/tests/workloads/kernel_verbose_3/MI200/SQ_LEVEL_WAVES.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,375347,375347,1048576,256,0,0,8,0,16,64,0x0,0x7f0457b50ec0,27804,27804,11190,222440,16384,10815372,129006,0,43764752,200365991059341,200376896683431,200376896703751,200366006804217 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,375347,375347,1048576,256,0,0,8,0,16,64,0x0,0x7f0457b50ec0,41475,41475,13865,331808,16384,19384380,223221,0,78032800,200366006832841,200376896785031,200376896801511,200366007074167 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,375347,375347,1048576,256,0,0,8,0,16,64,0x0,0x7f0457b50ec0,41252,41252,13554,330024,16384,19142382,223336,0,77058516,200366007109434,200376896822791,200376896838791,200366007260570 diff --git a/tests/workloads/kernel_verbose_3/MI200/perfmon/SQ_IFETCH_LEVEL.txt b/tests/workloads/kernel_verbose_3/MI200/perfmon/SQ_IFETCH_LEVEL.txt new file mode 100644 index 0000000000..293092f641 --- /dev/null +++ b/tests/workloads/kernel_verbose_3/MI200/perfmon/SQ_IFETCH_LEVEL.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_3/MI200/perfmon/SQ_INST_LEVEL_LDS.txt b/tests/workloads/kernel_verbose_3/MI200/perfmon/SQ_INST_LEVEL_LDS.txt new file mode 100644 index 0000000000..08439eedce --- /dev/null +++ b/tests/workloads/kernel_verbose_3/MI200/perfmon/SQ_INST_LEVEL_LDS.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_3/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt b/tests/workloads/kernel_verbose_3/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt new file mode 100644 index 0000000000..6cca322d4e --- /dev/null +++ b/tests/workloads/kernel_verbose_3/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_3/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt b/tests/workloads/kernel_verbose_3/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt new file mode 100644 index 0000000000..e527ad31ba --- /dev/null +++ b/tests/workloads/kernel_verbose_3/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_3/MI200/perfmon/SQ_LEVEL_WAVES.txt b/tests/workloads/kernel_verbose_3/MI200/perfmon/SQ_LEVEL_WAVES.txt new file mode 100644 index 0000000000..3f8e04adb3 --- /dev/null +++ b/tests/workloads/kernel_verbose_3/MI200/perfmon/SQ_LEVEL_WAVES.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_0.txt b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_0.txt new file mode 100644 index 0000000000..4ffdc32149 --- /dev/null +++ b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_0.txt @@ -0,0 +1,5 @@ +pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES SQ_INSTS_VALU_CVT SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU GRBM_COUNT GRBM_GUI_ACTIVE TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum TA_TA_BUSY_sum TA_BUFFER_WAVEFRONTS_sum TD_TD_BUSY_sum TD_TC_STALL_sum SPI_CSN_WINDOW_VALID SPI_CSN_BUSY CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_1.txt b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_1.txt new file mode 100644 index 0000000000..6c277f4a37 --- /dev/null +++ b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_1.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VSKIPPED SQ_INSTS SQ_INSTS_VALU SQ_INSTS_VALU_ADD_F16 SQ_INSTS_VALU_MUL_F16 SQ_INSTS_VALU_FMA_F16 SQ_INSTS_VALU_TRANS_F16 SQ_INSTS_VALU_ADD_F32 GRBM_SPI_BUSY TCP_READ_TAGCONFLICT_STALL_CYCLES_sum TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum TCP_TA_TCP_STATE_READ_sum TA_BUFFER_READ_WAVEFRONTS_sum TA_BUFFER_WRITE_WAVEFRONTS_sum TD_SPI_STALL_sum TD_LOAD_WAVEFRONT_sum SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_10.txt b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_10.txt new file mode 100644 index 0000000000..7053d4dce6 --- /dev/null +++ b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_10.txt @@ -0,0 +1,5 @@ +pmc: SQC_TC_DATA_WRITE_REQ SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_11.txt b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_11.txt new file mode 100644 index 0000000000..77ae8b461f --- /dev/null +++ b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_11.txt @@ -0,0 +1,5 @@ +pmc: SQC_ICACHE_MISSES_DUPLICATE SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_12.txt b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_12.txt new file mode 100644 index 0000000000..dfb2cf65e5 --- /dev/null +++ b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_12.txt @@ -0,0 +1,5 @@ +pmc: SQC_DCACHE_REQ_READ_1 SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_13.txt b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_13.txt new file mode 100644 index 0000000000..062fc9644a --- /dev/null +++ b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_13.txt @@ -0,0 +1,5 @@ +pmc: TCC_ATOMIC[0] TCC_CYCLE[0] TCC_EA_ATOMIC[0] TCC_EA_ATOMIC_LEVEL[0] TCC_ATOMIC[1] TCC_CYCLE[1] TCC_EA_ATOMIC[1] TCC_EA_ATOMIC_LEVEL[1] TCC_ATOMIC[2] TCC_CYCLE[2] TCC_EA_ATOMIC[2] TCC_EA_ATOMIC_LEVEL[2] TCC_ATOMIC[3] TCC_CYCLE[3] TCC_EA_ATOMIC[3] TCC_EA_ATOMIC_LEVEL[3] TCC_ATOMIC[4] TCC_CYCLE[4] TCC_EA_ATOMIC[4] TCC_EA_ATOMIC_LEVEL[4] TCC_ATOMIC[5] TCC_CYCLE[5] TCC_EA_ATOMIC[5] TCC_EA_ATOMIC_LEVEL[5] TCC_ATOMIC[6] TCC_CYCLE[6] TCC_EA_ATOMIC[6] TCC_EA_ATOMIC_LEVEL[6] TCC_ATOMIC[7] TCC_CYCLE[7] TCC_EA_ATOMIC[7] TCC_EA_ATOMIC_LEVEL[7] TCC_ATOMIC[8] TCC_CYCLE[8] TCC_EA_ATOMIC[8] TCC_EA_ATOMIC_LEVEL[8] TCC_ATOMIC[9] TCC_CYCLE[9] TCC_EA_ATOMIC[9] TCC_EA_ATOMIC_LEVEL[9] TCC_ATOMIC[10] TCC_CYCLE[10] TCC_EA_ATOMIC[10] TCC_EA_ATOMIC_LEVEL[10] TCC_ATOMIC[11] TCC_CYCLE[11] TCC_EA_ATOMIC[11] TCC_EA_ATOMIC_LEVEL[11] TCC_ATOMIC[12] TCC_CYCLE[12] TCC_EA_ATOMIC[12] TCC_EA_ATOMIC_LEVEL[12] TCC_ATOMIC[13] TCC_CYCLE[13] TCC_EA_ATOMIC[13] TCC_EA_ATOMIC_LEVEL[13] TCC_ATOMIC[14] TCC_CYCLE[14] TCC_EA_ATOMIC[14] TCC_EA_ATOMIC_LEVEL[14] TCC_ATOMIC[15] TCC_CYCLE[15] TCC_EA_ATOMIC[15] TCC_EA_ATOMIC_LEVEL[15] TCC_ATOMIC[16] TCC_CYCLE[16] TCC_EA_ATOMIC[16] TCC_EA_ATOMIC_LEVEL[16] TCC_ATOMIC[17] TCC_CYCLE[17] TCC_EA_ATOMIC[17] TCC_EA_ATOMIC_LEVEL[17] TCC_ATOMIC[18] TCC_CYCLE[18] TCC_EA_ATOMIC[18] TCC_EA_ATOMIC_LEVEL[18] TCC_ATOMIC[19] TCC_CYCLE[19] TCC_EA_ATOMIC[19] TCC_EA_ATOMIC_LEVEL[19] TCC_ATOMIC[20] TCC_CYCLE[20] TCC_EA_ATOMIC[20] TCC_EA_ATOMIC_LEVEL[20] TCC_ATOMIC[21] TCC_CYCLE[21] TCC_EA_ATOMIC[21] TCC_EA_ATOMIC_LEVEL[21] TCC_ATOMIC[22] TCC_CYCLE[22] TCC_EA_ATOMIC[22] TCC_EA_ATOMIC_LEVEL[22] TCC_ATOMIC[23] TCC_CYCLE[23] TCC_EA_ATOMIC[23] TCC_EA_ATOMIC_LEVEL[23] TCC_ATOMIC[24] TCC_CYCLE[24] TCC_EA_ATOMIC[24] TCC_EA_ATOMIC_LEVEL[24] TCC_ATOMIC[25] TCC_CYCLE[25] TCC_EA_ATOMIC[25] TCC_EA_ATOMIC_LEVEL[25] TCC_ATOMIC[26] TCC_CYCLE[26] TCC_EA_ATOMIC[26] TCC_EA_ATOMIC_LEVEL[26] TCC_ATOMIC[27] TCC_CYCLE[27] TCC_EA_ATOMIC[27] TCC_EA_ATOMIC_LEVEL[27] TCC_ATOMIC[28] TCC_CYCLE[28] TCC_EA_ATOMIC[28] TCC_EA_ATOMIC_LEVEL[28] TCC_ATOMIC[29] TCC_CYCLE[29] TCC_EA_ATOMIC[29] TCC_EA_ATOMIC_LEVEL[29] TCC_ATOMIC[30] TCC_CYCLE[30] TCC_EA_ATOMIC[30] TCC_EA_ATOMIC_LEVEL[30] TCC_ATOMIC[31] TCC_CYCLE[31] TCC_EA_ATOMIC[31] TCC_EA_ATOMIC_LEVEL[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_14.txt b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_14.txt new file mode 100644 index 0000000000..e0698dbf57 --- /dev/null +++ b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_14.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_EA_RDREQ_GMI_CREDIT_STALL[0] TCC_EA_RDREQ[1] TCC_EA_RDREQ_32B[1] TCC_EA_RDREQ_DRAM_CREDIT_STALL[1] TCC_EA_RDREQ_GMI_CREDIT_STALL[1] TCC_EA_RDREQ[2] TCC_EA_RDREQ_32B[2] TCC_EA_RDREQ_DRAM_CREDIT_STALL[2] TCC_EA_RDREQ_GMI_CREDIT_STALL[2] TCC_EA_RDREQ[3] TCC_EA_RDREQ_32B[3] TCC_EA_RDREQ_DRAM_CREDIT_STALL[3] TCC_EA_RDREQ_GMI_CREDIT_STALL[3] TCC_EA_RDREQ[4] TCC_EA_RDREQ_32B[4] TCC_EA_RDREQ_DRAM_CREDIT_STALL[4] TCC_EA_RDREQ_GMI_CREDIT_STALL[4] TCC_EA_RDREQ[5] TCC_EA_RDREQ_32B[5] TCC_EA_RDREQ_DRAM_CREDIT_STALL[5] TCC_EA_RDREQ_GMI_CREDIT_STALL[5] TCC_EA_RDREQ[6] TCC_EA_RDREQ_32B[6] TCC_EA_RDREQ_DRAM_CREDIT_STALL[6] TCC_EA_RDREQ_GMI_CREDIT_STALL[6] TCC_EA_RDREQ[7] TCC_EA_RDREQ_32B[7] TCC_EA_RDREQ_DRAM_CREDIT_STALL[7] TCC_EA_RDREQ_GMI_CREDIT_STALL[7] TCC_EA_RDREQ[8] TCC_EA_RDREQ_32B[8] TCC_EA_RDREQ_DRAM_CREDIT_STALL[8] TCC_EA_RDREQ_GMI_CREDIT_STALL[8] TCC_EA_RDREQ[9] TCC_EA_RDREQ_32B[9] TCC_EA_RDREQ_DRAM_CREDIT_STALL[9] TCC_EA_RDREQ_GMI_CREDIT_STALL[9] TCC_EA_RDREQ[10] TCC_EA_RDREQ_32B[10] TCC_EA_RDREQ_DRAM_CREDIT_STALL[10] TCC_EA_RDREQ_GMI_CREDIT_STALL[10] TCC_EA_RDREQ[11] TCC_EA_RDREQ_32B[11] TCC_EA_RDREQ_DRAM_CREDIT_STALL[11] TCC_EA_RDREQ_GMI_CREDIT_STALL[11] TCC_EA_RDREQ[12] TCC_EA_RDREQ_32B[12] TCC_EA_RDREQ_DRAM_CREDIT_STALL[12] TCC_EA_RDREQ_GMI_CREDIT_STALL[12] TCC_EA_RDREQ[13] TCC_EA_RDREQ_32B[13] TCC_EA_RDREQ_DRAM_CREDIT_STALL[13] TCC_EA_RDREQ_GMI_CREDIT_STALL[13] TCC_EA_RDREQ[14] TCC_EA_RDREQ_32B[14] TCC_EA_RDREQ_DRAM_CREDIT_STALL[14] TCC_EA_RDREQ_GMI_CREDIT_STALL[14] TCC_EA_RDREQ[15] TCC_EA_RDREQ_32B[15] TCC_EA_RDREQ_DRAM_CREDIT_STALL[15] TCC_EA_RDREQ_GMI_CREDIT_STALL[15] TCC_EA_RDREQ[16] TCC_EA_RDREQ_32B[16] TCC_EA_RDREQ_DRAM_CREDIT_STALL[16] TCC_EA_RDREQ_GMI_CREDIT_STALL[16] TCC_EA_RDREQ[17] TCC_EA_RDREQ_32B[17] TCC_EA_RDREQ_DRAM_CREDIT_STALL[17] TCC_EA_RDREQ_GMI_CREDIT_STALL[17] TCC_EA_RDREQ[18] TCC_EA_RDREQ_32B[18] TCC_EA_RDREQ_DRAM_CREDIT_STALL[18] TCC_EA_RDREQ_GMI_CREDIT_STALL[18] TCC_EA_RDREQ[19] TCC_EA_RDREQ_32B[19] TCC_EA_RDREQ_DRAM_CREDIT_STALL[19] TCC_EA_RDREQ_GMI_CREDIT_STALL[19] TCC_EA_RDREQ[20] TCC_EA_RDREQ_32B[20] TCC_EA_RDREQ_DRAM_CREDIT_STALL[20] TCC_EA_RDREQ_GMI_CREDIT_STALL[20] TCC_EA_RDREQ[21] TCC_EA_RDREQ_32B[21] TCC_EA_RDREQ_DRAM_CREDIT_STALL[21] TCC_EA_RDREQ_GMI_CREDIT_STALL[21] TCC_EA_RDREQ[22] TCC_EA_RDREQ_32B[22] TCC_EA_RDREQ_DRAM_CREDIT_STALL[22] TCC_EA_RDREQ_GMI_CREDIT_STALL[22] TCC_EA_RDREQ[23] TCC_EA_RDREQ_32B[23] TCC_EA_RDREQ_DRAM_CREDIT_STALL[23] TCC_EA_RDREQ_GMI_CREDIT_STALL[23] TCC_EA_RDREQ[24] TCC_EA_RDREQ_32B[24] TCC_EA_RDREQ_DRAM_CREDIT_STALL[24] TCC_EA_RDREQ_GMI_CREDIT_STALL[24] TCC_EA_RDREQ[25] TCC_EA_RDREQ_32B[25] TCC_EA_RDREQ_DRAM_CREDIT_STALL[25] TCC_EA_RDREQ_GMI_CREDIT_STALL[25] TCC_EA_RDREQ[26] TCC_EA_RDREQ_32B[26] TCC_EA_RDREQ_DRAM_CREDIT_STALL[26] TCC_EA_RDREQ_GMI_CREDIT_STALL[26] TCC_EA_RDREQ[27] TCC_EA_RDREQ_32B[27] TCC_EA_RDREQ_DRAM_CREDIT_STALL[27] TCC_EA_RDREQ_GMI_CREDIT_STALL[27] TCC_EA_RDREQ[28] TCC_EA_RDREQ_32B[28] TCC_EA_RDREQ_DRAM_CREDIT_STALL[28] TCC_EA_RDREQ_GMI_CREDIT_STALL[28] TCC_EA_RDREQ[29] TCC_EA_RDREQ_32B[29] TCC_EA_RDREQ_DRAM_CREDIT_STALL[29] TCC_EA_RDREQ_GMI_CREDIT_STALL[29] TCC_EA_RDREQ[30] TCC_EA_RDREQ_32B[30] TCC_EA_RDREQ_DRAM_CREDIT_STALL[30] TCC_EA_RDREQ_GMI_CREDIT_STALL[30] TCC_EA_RDREQ[31] TCC_EA_RDREQ_32B[31] TCC_EA_RDREQ_DRAM_CREDIT_STALL[31] TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_15.txt b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_15.txt new file mode 100644 index 0000000000..77ad088669 --- /dev/null +++ b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_15.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ[0] TCC_EA_WRREQ_64B[0] TCC_EA_RDREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_LEVEL[1] TCC_EA_WRREQ[1] TCC_EA_WRREQ_64B[1] TCC_EA_RDREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_LEVEL[2] TCC_EA_WRREQ[2] TCC_EA_WRREQ_64B[2] TCC_EA_RDREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_LEVEL[3] TCC_EA_WRREQ[3] TCC_EA_WRREQ_64B[3] TCC_EA_RDREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_LEVEL[4] TCC_EA_WRREQ[4] TCC_EA_WRREQ_64B[4] TCC_EA_RDREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_LEVEL[5] TCC_EA_WRREQ[5] TCC_EA_WRREQ_64B[5] TCC_EA_RDREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_LEVEL[6] TCC_EA_WRREQ[6] TCC_EA_WRREQ_64B[6] TCC_EA_RDREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_LEVEL[7] TCC_EA_WRREQ[7] TCC_EA_WRREQ_64B[7] TCC_EA_RDREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_LEVEL[8] TCC_EA_WRREQ[8] TCC_EA_WRREQ_64B[8] TCC_EA_RDREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_LEVEL[9] TCC_EA_WRREQ[9] TCC_EA_WRREQ_64B[9] TCC_EA_RDREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_LEVEL[10] TCC_EA_WRREQ[10] TCC_EA_WRREQ_64B[10] TCC_EA_RDREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_LEVEL[11] TCC_EA_WRREQ[11] TCC_EA_WRREQ_64B[11] TCC_EA_RDREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_LEVEL[12] TCC_EA_WRREQ[12] TCC_EA_WRREQ_64B[12] TCC_EA_RDREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_LEVEL[13] TCC_EA_WRREQ[13] TCC_EA_WRREQ_64B[13] TCC_EA_RDREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_LEVEL[14] TCC_EA_WRREQ[14] TCC_EA_WRREQ_64B[14] TCC_EA_RDREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_LEVEL[15] TCC_EA_WRREQ[15] TCC_EA_WRREQ_64B[15] TCC_EA_RDREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_LEVEL[16] TCC_EA_WRREQ[16] TCC_EA_WRREQ_64B[16] TCC_EA_RDREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_LEVEL[17] TCC_EA_WRREQ[17] TCC_EA_WRREQ_64B[17] TCC_EA_RDREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_LEVEL[18] TCC_EA_WRREQ[18] TCC_EA_WRREQ_64B[18] TCC_EA_RDREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_LEVEL[19] TCC_EA_WRREQ[19] TCC_EA_WRREQ_64B[19] TCC_EA_RDREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_LEVEL[20] TCC_EA_WRREQ[20] TCC_EA_WRREQ_64B[20] TCC_EA_RDREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_LEVEL[21] TCC_EA_WRREQ[21] TCC_EA_WRREQ_64B[21] TCC_EA_RDREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_LEVEL[22] TCC_EA_WRREQ[22] TCC_EA_WRREQ_64B[22] TCC_EA_RDREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_LEVEL[23] TCC_EA_WRREQ[23] TCC_EA_WRREQ_64B[23] TCC_EA_RDREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_LEVEL[24] TCC_EA_WRREQ[24] TCC_EA_WRREQ_64B[24] TCC_EA_RDREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_LEVEL[25] TCC_EA_WRREQ[25] TCC_EA_WRREQ_64B[25] TCC_EA_RDREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_LEVEL[26] TCC_EA_WRREQ[26] TCC_EA_WRREQ_64B[26] TCC_EA_RDREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_LEVEL[27] TCC_EA_WRREQ[27] TCC_EA_WRREQ_64B[27] TCC_EA_RDREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_LEVEL[28] TCC_EA_WRREQ[28] TCC_EA_WRREQ_64B[28] TCC_EA_RDREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_LEVEL[29] TCC_EA_WRREQ[29] TCC_EA_WRREQ_64B[29] TCC_EA_RDREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_LEVEL[30] TCC_EA_WRREQ[30] TCC_EA_WRREQ_64B[30] TCC_EA_RDREQ_IO_CREDIT_STALL[31] TCC_EA_RDREQ_LEVEL[31] TCC_EA_WRREQ[31] TCC_EA_WRREQ_64B[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_16.txt b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_16.txt new file mode 100644 index 0000000000..d0628bb948 --- /dev/null +++ b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_16.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_WRREQ_IO_CREDIT_STALL[0] TCC_EA_WRREQ_LEVEL[0] TCC_EA_WRREQ_DRAM_CREDIT_STALL[1] TCC_EA_WRREQ_GMI_CREDIT_STALL[1] TCC_EA_WRREQ_IO_CREDIT_STALL[1] TCC_EA_WRREQ_LEVEL[1] TCC_EA_WRREQ_DRAM_CREDIT_STALL[2] TCC_EA_WRREQ_GMI_CREDIT_STALL[2] TCC_EA_WRREQ_IO_CREDIT_STALL[2] TCC_EA_WRREQ_LEVEL[2] TCC_EA_WRREQ_DRAM_CREDIT_STALL[3] TCC_EA_WRREQ_GMI_CREDIT_STALL[3] TCC_EA_WRREQ_IO_CREDIT_STALL[3] TCC_EA_WRREQ_LEVEL[3] TCC_EA_WRREQ_DRAM_CREDIT_STALL[4] TCC_EA_WRREQ_GMI_CREDIT_STALL[4] TCC_EA_WRREQ_IO_CREDIT_STALL[4] TCC_EA_WRREQ_LEVEL[4] TCC_EA_WRREQ_DRAM_CREDIT_STALL[5] TCC_EA_WRREQ_GMI_CREDIT_STALL[5] TCC_EA_WRREQ_IO_CREDIT_STALL[5] TCC_EA_WRREQ_LEVEL[5] TCC_EA_WRREQ_DRAM_CREDIT_STALL[6] TCC_EA_WRREQ_GMI_CREDIT_STALL[6] TCC_EA_WRREQ_IO_CREDIT_STALL[6] TCC_EA_WRREQ_LEVEL[6] TCC_EA_WRREQ_DRAM_CREDIT_STALL[7] TCC_EA_WRREQ_GMI_CREDIT_STALL[7] TCC_EA_WRREQ_IO_CREDIT_STALL[7] TCC_EA_WRREQ_LEVEL[7] TCC_EA_WRREQ_DRAM_CREDIT_STALL[8] TCC_EA_WRREQ_GMI_CREDIT_STALL[8] TCC_EA_WRREQ_IO_CREDIT_STALL[8] TCC_EA_WRREQ_LEVEL[8] TCC_EA_WRREQ_DRAM_CREDIT_STALL[9] TCC_EA_WRREQ_GMI_CREDIT_STALL[9] TCC_EA_WRREQ_IO_CREDIT_STALL[9] TCC_EA_WRREQ_LEVEL[9] TCC_EA_WRREQ_DRAM_CREDIT_STALL[10] TCC_EA_WRREQ_GMI_CREDIT_STALL[10] TCC_EA_WRREQ_IO_CREDIT_STALL[10] TCC_EA_WRREQ_LEVEL[10] TCC_EA_WRREQ_DRAM_CREDIT_STALL[11] TCC_EA_WRREQ_GMI_CREDIT_STALL[11] TCC_EA_WRREQ_IO_CREDIT_STALL[11] TCC_EA_WRREQ_LEVEL[11] TCC_EA_WRREQ_DRAM_CREDIT_STALL[12] TCC_EA_WRREQ_GMI_CREDIT_STALL[12] TCC_EA_WRREQ_IO_CREDIT_STALL[12] TCC_EA_WRREQ_LEVEL[12] TCC_EA_WRREQ_DRAM_CREDIT_STALL[13] TCC_EA_WRREQ_GMI_CREDIT_STALL[13] TCC_EA_WRREQ_IO_CREDIT_STALL[13] TCC_EA_WRREQ_LEVEL[13] TCC_EA_WRREQ_DRAM_CREDIT_STALL[14] TCC_EA_WRREQ_GMI_CREDIT_STALL[14] TCC_EA_WRREQ_IO_CREDIT_STALL[14] TCC_EA_WRREQ_LEVEL[14] TCC_EA_WRREQ_DRAM_CREDIT_STALL[15] TCC_EA_WRREQ_GMI_CREDIT_STALL[15] TCC_EA_WRREQ_IO_CREDIT_STALL[15] TCC_EA_WRREQ_LEVEL[15] TCC_EA_WRREQ_DRAM_CREDIT_STALL[16] TCC_EA_WRREQ_GMI_CREDIT_STALL[16] TCC_EA_WRREQ_IO_CREDIT_STALL[16] TCC_EA_WRREQ_LEVEL[16] TCC_EA_WRREQ_DRAM_CREDIT_STALL[17] TCC_EA_WRREQ_GMI_CREDIT_STALL[17] TCC_EA_WRREQ_IO_CREDIT_STALL[17] TCC_EA_WRREQ_LEVEL[17] TCC_EA_WRREQ_DRAM_CREDIT_STALL[18] TCC_EA_WRREQ_GMI_CREDIT_STALL[18] TCC_EA_WRREQ_IO_CREDIT_STALL[18] TCC_EA_WRREQ_LEVEL[18] TCC_EA_WRREQ_DRAM_CREDIT_STALL[19] TCC_EA_WRREQ_GMI_CREDIT_STALL[19] TCC_EA_WRREQ_IO_CREDIT_STALL[19] TCC_EA_WRREQ_LEVEL[19] TCC_EA_WRREQ_DRAM_CREDIT_STALL[20] TCC_EA_WRREQ_GMI_CREDIT_STALL[20] TCC_EA_WRREQ_IO_CREDIT_STALL[20] TCC_EA_WRREQ_LEVEL[20] TCC_EA_WRREQ_DRAM_CREDIT_STALL[21] TCC_EA_WRREQ_GMI_CREDIT_STALL[21] TCC_EA_WRREQ_IO_CREDIT_STALL[21] TCC_EA_WRREQ_LEVEL[21] TCC_EA_WRREQ_DRAM_CREDIT_STALL[22] TCC_EA_WRREQ_GMI_CREDIT_STALL[22] TCC_EA_WRREQ_IO_CREDIT_STALL[22] TCC_EA_WRREQ_LEVEL[22] TCC_EA_WRREQ_DRAM_CREDIT_STALL[23] TCC_EA_WRREQ_GMI_CREDIT_STALL[23] TCC_EA_WRREQ_IO_CREDIT_STALL[23] TCC_EA_WRREQ_LEVEL[23] TCC_EA_WRREQ_DRAM_CREDIT_STALL[24] TCC_EA_WRREQ_GMI_CREDIT_STALL[24] TCC_EA_WRREQ_IO_CREDIT_STALL[24] TCC_EA_WRREQ_LEVEL[24] TCC_EA_WRREQ_DRAM_CREDIT_STALL[25] TCC_EA_WRREQ_GMI_CREDIT_STALL[25] TCC_EA_WRREQ_IO_CREDIT_STALL[25] TCC_EA_WRREQ_LEVEL[25] TCC_EA_WRREQ_DRAM_CREDIT_STALL[26] TCC_EA_WRREQ_GMI_CREDIT_STALL[26] TCC_EA_WRREQ_IO_CREDIT_STALL[26] TCC_EA_WRREQ_LEVEL[26] TCC_EA_WRREQ_DRAM_CREDIT_STALL[27] TCC_EA_WRREQ_GMI_CREDIT_STALL[27] TCC_EA_WRREQ_IO_CREDIT_STALL[27] TCC_EA_WRREQ_LEVEL[27] TCC_EA_WRREQ_DRAM_CREDIT_STALL[28] TCC_EA_WRREQ_GMI_CREDIT_STALL[28] TCC_EA_WRREQ_IO_CREDIT_STALL[28] TCC_EA_WRREQ_LEVEL[28] TCC_EA_WRREQ_DRAM_CREDIT_STALL[29] TCC_EA_WRREQ_GMI_CREDIT_STALL[29] TCC_EA_WRREQ_IO_CREDIT_STALL[29] TCC_EA_WRREQ_LEVEL[29] TCC_EA_WRREQ_DRAM_CREDIT_STALL[30] TCC_EA_WRREQ_GMI_CREDIT_STALL[30] TCC_EA_WRREQ_IO_CREDIT_STALL[30] TCC_EA_WRREQ_LEVEL[30] TCC_EA_WRREQ_DRAM_CREDIT_STALL[31] TCC_EA_WRREQ_GMI_CREDIT_STALL[31] TCC_EA_WRREQ_IO_CREDIT_STALL[31] TCC_EA_WRREQ_LEVEL[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_17.txt b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_17.txt new file mode 100644 index 0000000000..343869c5f1 --- /dev/null +++ b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_17.txt @@ -0,0 +1,5 @@ +pmc: TCC_HIT[0] TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_HIT[1] TCC_MISS[1] TCC_READ[1] TCC_REQ[1] TCC_HIT[2] TCC_MISS[2] TCC_READ[2] TCC_REQ[2] TCC_HIT[3] TCC_MISS[3] TCC_READ[3] TCC_REQ[3] TCC_HIT[4] TCC_MISS[4] TCC_READ[4] TCC_REQ[4] TCC_HIT[5] TCC_MISS[5] TCC_READ[5] TCC_REQ[5] TCC_HIT[6] TCC_MISS[6] TCC_READ[6] TCC_REQ[6] TCC_HIT[7] TCC_MISS[7] TCC_READ[7] TCC_REQ[7] TCC_HIT[8] TCC_MISS[8] TCC_READ[8] TCC_REQ[8] TCC_HIT[9] TCC_MISS[9] TCC_READ[9] TCC_REQ[9] TCC_HIT[10] TCC_MISS[10] TCC_READ[10] TCC_REQ[10] TCC_HIT[11] TCC_MISS[11] TCC_READ[11] TCC_REQ[11] TCC_HIT[12] TCC_MISS[12] TCC_READ[12] TCC_REQ[12] TCC_HIT[13] TCC_MISS[13] TCC_READ[13] TCC_REQ[13] TCC_HIT[14] TCC_MISS[14] TCC_READ[14] TCC_REQ[14] TCC_HIT[15] TCC_MISS[15] TCC_READ[15] TCC_REQ[15] TCC_HIT[16] TCC_MISS[16] TCC_READ[16] TCC_REQ[16] TCC_HIT[17] TCC_MISS[17] TCC_READ[17] TCC_REQ[17] TCC_HIT[18] TCC_MISS[18] TCC_READ[18] TCC_REQ[18] TCC_HIT[19] TCC_MISS[19] TCC_READ[19] TCC_REQ[19] TCC_HIT[20] TCC_MISS[20] TCC_READ[20] TCC_REQ[20] TCC_HIT[21] TCC_MISS[21] TCC_READ[21] TCC_REQ[21] TCC_HIT[22] TCC_MISS[22] TCC_READ[22] TCC_REQ[22] TCC_HIT[23] TCC_MISS[23] TCC_READ[23] TCC_REQ[23] TCC_HIT[24] TCC_MISS[24] TCC_READ[24] TCC_REQ[24] TCC_HIT[25] TCC_MISS[25] TCC_READ[25] TCC_REQ[25] TCC_HIT[26] TCC_MISS[26] TCC_READ[26] TCC_REQ[26] TCC_HIT[27] TCC_MISS[27] TCC_READ[27] TCC_REQ[27] TCC_HIT[28] TCC_MISS[28] TCC_READ[28] TCC_REQ[28] TCC_HIT[29] TCC_MISS[29] TCC_READ[29] TCC_REQ[29] TCC_HIT[30] TCC_MISS[30] TCC_READ[30] TCC_REQ[30] TCC_HIT[31] TCC_MISS[31] TCC_READ[31] TCC_REQ[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_18.txt b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_18.txt new file mode 100644 index 0000000000..a74cefd281 --- /dev/null +++ b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_18.txt @@ -0,0 +1,5 @@ +pmc: TCC_RW_REQ[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_RW_REQ[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_WRITE[1] TCC_RW_REQ[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_WRITE[2] TCC_RW_REQ[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_WRITE[3] TCC_RW_REQ[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_WRITE[4] TCC_RW_REQ[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_WRITE[5] TCC_RW_REQ[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_WRITE[6] TCC_RW_REQ[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_WRITE[7] TCC_RW_REQ[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_WRITE[8] TCC_RW_REQ[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_WRITE[9] TCC_RW_REQ[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_WRITE[10] TCC_RW_REQ[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_WRITE[11] TCC_RW_REQ[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_WRITE[12] TCC_RW_REQ[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_WRITE[13] TCC_RW_REQ[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_WRITE[14] TCC_RW_REQ[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_WRITE[15] TCC_RW_REQ[16] TCC_TOO_MANY_EA_WRREQS_STALL[16] TCC_WRITE[16] TCC_RW_REQ[17] TCC_TOO_MANY_EA_WRREQS_STALL[17] TCC_WRITE[17] TCC_RW_REQ[18] TCC_TOO_MANY_EA_WRREQS_STALL[18] TCC_WRITE[18] TCC_RW_REQ[19] TCC_TOO_MANY_EA_WRREQS_STALL[19] TCC_WRITE[19] TCC_RW_REQ[20] TCC_TOO_MANY_EA_WRREQS_STALL[20] TCC_WRITE[20] TCC_RW_REQ[21] TCC_TOO_MANY_EA_WRREQS_STALL[21] TCC_WRITE[21] TCC_RW_REQ[22] TCC_TOO_MANY_EA_WRREQS_STALL[22] TCC_WRITE[22] TCC_RW_REQ[23] TCC_TOO_MANY_EA_WRREQS_STALL[23] TCC_WRITE[23] TCC_RW_REQ[24] TCC_TOO_MANY_EA_WRREQS_STALL[24] TCC_WRITE[24] TCC_RW_REQ[25] TCC_TOO_MANY_EA_WRREQS_STALL[25] TCC_WRITE[25] TCC_RW_REQ[26] TCC_TOO_MANY_EA_WRREQS_STALL[26] TCC_WRITE[26] TCC_RW_REQ[27] TCC_TOO_MANY_EA_WRREQS_STALL[27] TCC_WRITE[27] TCC_RW_REQ[28] TCC_TOO_MANY_EA_WRREQS_STALL[28] TCC_WRITE[28] TCC_RW_REQ[29] TCC_TOO_MANY_EA_WRREQS_STALL[29] TCC_WRITE[29] TCC_RW_REQ[30] TCC_TOO_MANY_EA_WRREQS_STALL[30] TCC_WRITE[30] TCC_RW_REQ[31] TCC_TOO_MANY_EA_WRREQS_STALL[31] TCC_WRITE[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_2.txt b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_2.txt new file mode 100644 index 0000000000..70b69f8928 --- /dev/null +++ b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_2.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_MUL_F32 SQ_INSTS_VALU_FMA_F32 SQ_INSTS_VALU_TRANS_F32 SQ_INSTS_VALU_ADD_F64 SQ_INSTS_VALU_MUL_F64 SQ_INSTS_VALU_FMA_F64 SQ_INSTS_VALU_TRANS_F64 SQ_INSTS_VALU_INT32 TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum TA_BUFFER_ATOMIC_WAVEFRONTS_sum TA_BUFFER_TOTAL_CYCLES_sum TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_3.txt b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_3.txt new file mode 100644 index 0000000000..e47f8e33c9 --- /dev/null +++ b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_3.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_INT64 SQ_INSTS_SMEM SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum TD_COALESCABLE_WAVEFRONT_sum SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE CPF_CMP_UTCL1_STALL_ON_TRANSLATION TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_4.txt b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_4.txt new file mode 100644 index 0000000000..2d96f365a9 --- /dev/null +++ b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_4.txt @@ -0,0 +1,5 @@ +pmc: SQ_WAVE_CYCLES SQ_WAIT_ANY SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_BUSY_CU_CYCLES SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE TCC_EA_WRREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WR_UNCACHED_32B_sum TCC_EA_WRREQ_DRAM_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_5.txt b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_5.txt new file mode 100644 index 0000000000..e50beed390 --- /dev/null +++ b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_5.txt @@ -0,0 +1,5 @@ +pmc: SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU TCP_TCP_LATENCY_sum TCP_TCC_READ_REQ_LATENCY_sum TCP_TCC_WRITE_REQ_LATENCY_sum TCP_TCC_READ_REQ_sum TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN CPC_ME1_DC0_SPI_BUSY TCC_EA_WRREQ_STALL_sum TCC_EA_RDREQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RD_UNCACHED_32B_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_6.txt b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_6.txt new file mode 100644 index 0000000000..15a2277c1b --- /dev/null +++ b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_6.txt @@ -0,0 +1,5 @@ +pmc: SQ_THREAD_CYCLES_VALU SQ_IFETCH SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TCP_TCC_NC_READ_REQ_sum TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN TCC_EA_RDREQ_DRAM_sum TCC_TAG_STALL_sum TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_7.txt b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_7.txt new file mode 100644 index 0000000000..b42ce91618 --- /dev/null +++ b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_7.txt @@ -0,0 +1,5 @@ +pmc: SQ_WAVES_LT_32 SQ_WAVES_LT_16 SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TCP_TCC_UC_WRITE_REQ_sum TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR TCC_NORMAL_EVICT_sum TCC_ALL_TC_OP_INV_EVICT_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA_ATOMIC_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_8.txt b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_8.txt new file mode 100644 index 0000000000..21d4c7a998 --- /dev/null +++ b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_8.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM_NORM SQ_INSTS_MFMA SQ_INSTS_VALU_MFMA_I8 SQ_INSTS_VALU_MFMA_F16 SQ_INSTS_VALU_MFMA_BF16 SQ_INSTS_VALU_MFMA_F32 SQ_INSTS_VALU_MFMA_F64 SQ_VALU_MFMA_BUSY_CYCLES TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TCP_TCC_CC_ATOMIC_REQ_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN TCC_EA_RDREQ_LEVEL_sum TCC_EA_WRREQ_LEVEL_sum TCC_EA_ATOMIC_LEVEL_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_9.txt b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_9.txt new file mode 100644 index 0000000000..9ffe5778c3 --- /dev/null +++ b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_9.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_FLAT_LDS_ONLY SQ_INSTS_VALU_MFMA_MOPS_I8 SQ_INSTS_VALU_MFMA_MOPS_F16 SQ_INSTS_VALU_MFMA_MOPS_BF16 SQ_INSTS_VALU_MFMA_MOPS_F32 SQ_INSTS_VALU_MFMA_MOPS_F64 SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum TCP_PENDING_STALL_CYCLES_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_3/MI200/perfmon/timestamps.txt b/tests/workloads/kernel_verbose_3/MI200/perfmon/timestamps.txt new file mode 100644 index 0000000000..676cca1b80 --- /dev/null +++ b/tests/workloads/kernel_verbose_3/MI200/perfmon/timestamps.txt @@ -0,0 +1,5 @@ +pmc: + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_3/MI200/pmc_perf.csv b/tests/workloads/kernel_verbose_3/MI200/pmc_perf.csv new file mode 100644 index 0000000000..7c9af10527 --- /dev/null +++ b/tests/workloads/kernel_verbose_3/MI200/pmc_perf.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_1,obj_1,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_2,obj_2,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_3,obj_3,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_4,obj_4,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_5,obj_5,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,TCC_EA_ATOMIC_LEVEL_sum,wave_size_6,obj_6,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,wave_size_7,obj_7,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,TD_COALESCABLE_WAVEFRONT_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_8,obj_8,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_9,obj_9,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_10,obj_10,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_11,obj_11,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_12,obj_12,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_DRAM_sum,TCC_TAG_STALL_sum,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,wave_size_13,obj_13,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_14,obj_14,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,wave_size_15,obj_15,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_16,obj_16,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_17,obj_17,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_18,obj_18,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7fce36be8ec0,0,0,0,998532,11,0,0,1083440,0,0,0,980959,0,0,0,1030903,0,0,0,981390,0,0,0,1069686,0,0,0,1131769,0,0,0,1232356,0,0,0,1062747,0,0,0,1038058,0,0,0,1031835,0,0,0,1076817,0,0,0,1114690,0,0,0,1047006,0,0,0,1004792,0,0,0,1267535,0,0,0,1151763,0,0,0,1049694,0,0,0,992650,0,0,0,1084352,0,0,0,1062905,0,0,0,1080186,0,0,0,1067162,0,0,0,1109373,0,0,0,1033119,0,0,0,1094220,0,0,0,1044460,0,0,0,1100322,0,0,0,1071074,0,0,0,1056893,0,0,0,1127537,0,0,0,1109825,64,0x7fcb418e4ec0,0,0,0,0,0,0,168,56,131072.0,131072.0,0.0,929430.0,64,0x7ff515f48ec0,231824,128092,16384,0,16384,16384,32768,49152,28977,28977,1943011.0,1334488.0,3205.0,166634.0,1043391.0,0.0,1326526.0,1027716.0,230113,136232,28977,0,28977,0,927264.0,483272.0,0.0,0.0,64,0x7f9f4b678ec0,0,393216,163840,0,0,0,0,0,17627,0.0,0.0,0.0,32768.0,0.0,0.0,428.0,32768.0,4096,16384,352,27627,1918,0,56.0,5.0,0.0,204806.0,64,0x7f24b44c4ec0,0,1321973,4096,4096,0,1354767,4096,4096,0,1222472,4096,4096,0,1273722,4096,4096,0,1223330,4096,4096,0,1437590,4096,4096,0,1053340,4096,4096,0,1197753,4096,4096,0,1110670,4096,4096,0,1201277,4096,4096,0,1283526,4096,4096,0,1159739,4096,4096,0,1071589,4096,4096,0,1339830,4096,4096,0,1619403,4096,4096,0,1277254,4096,4096,0,1217212,4096,4096,0,1202885,4096,4096,0,1131247,4096,4096,0,1569896,4096,4096,0,1065897,4096,4096,0,1068306,4096,4096,0,1195134,4096,4096,0,1260756,4096,4096,0,1582680,4096,4096,0,1030715,4096,4096,0,1073841,4096,4096,0,1140133,4096,4096,0,1528379,4096,4096,0,1118522,4096,4096,0,1189188,4096,4096,0,1318239,4096,4096,64,0x7f93502f4ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,38788672.0,34533107.0,0.0,64,0x7fc9a0414ec0,114688,0,32768,32768,16384,16384,65536,49152,27474486.0,85701973.0,38726495.0,131072.0,0.0,193774.0,0,0,14978,504.0,131082.0,0.0,12.0,64,0x7f84c28d0ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,10365,0,816,27840,0,73095.0,131072.0,0.0,65568.0,64,0x7f78b2f18ec0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,64,0x7f61d8d50ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,12228,18953,8358,545,0,26802,204457.0,0.0,73375.0,131082.0,64,0x7fcb203c4ec0,0,0,0,224,0,65536,64151,56,64,0x7f8639bc4ec0,32768,32768,0,64,0x7f80789d4ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131081.0,34813.0,46193.0,19343.0,64,0x7fa505dc4ec0,6369,0,4096,6358,0,4096,6369,0,4096,6400,0,4096,6386,0,4096,6372,0,4096,6356,0,4096,6413,0,4096,6421,0,4096,6370,0,4096,6362,0,4096,6370,0,4096,6404,0,4096,6388,0,4096,6374,0,4096,6358,0,4096,6373,0,4096,6418,0,4096,6367,0,4096,6358,0,4096,6389,0,4096,6394,0,4096,6331,0,4096,6509,0,4096,6345,0,4096,6372,0,4096,6416,0,4096,6366,0,4096,6359,0,4096,6389,0,4096,6396,0,4096,6332,0,4096,64,0x7f4979c7cec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65551.0,0.0,0.0,0.0,64,0x7fd080e6cec0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,50,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4097,0,0,0,4096,0,155,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4099,0,0,0,4096,0,0,0,4096,0,0,0,4099,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,64,0x7f2f1f530ec0,11133304,9932039,857201,344064,1687571,0,0,163840,832.0,515140.0,0.0,524288.0,304714.0,32768.0,526086,0,0,11138,131072.0,131072.0,0.0,131072.0,64,0x7f40880acec0,1281,118966,0,0,65536,63800,56,1680,64,0x7fb6d0d44ec0,2298,4096,2298,6394,2295,4096,2295,6391,2333,4096,2333,6429,2304,4096,2304,6400,2292,4096,2292,6388,2362,4097,2363,6459,2288,4096,2288,6384,2309,4096,2309,6405,2307,4097,2308,6404,2300,4098,2302,6398,2298,4096,2298,6394,2338,4096,2338,6434,2308,4096,2308,6404,2292,4096,2292,6388,2310,4096,2310,6406,2290,4096,2290,6386,2288,4096,2288,6384,2308,4096,2308,6404,2292,4097,2293,6389,2300,4096,2300,6396,2306,4096,2306,6402,2354,4096,2354,6450,2274,4096,2274,6370,2463,4098,2465,6561,2299,4096,2299,6395,2288,4096,2288,6384,2308,4096,2308,6404,2295,4100,2299,6395,2306,4096,2306,6402,2310,4096,2310,6406,2358,4096,2358,6454,2276,4096,2276,6372,200376896683431,200376896703751 +1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7fce36be8ec0,1594,0,0,2720147,6,0,0,1869554,237,0,0,1993496,0,0,0,1923184,601,0,0,2130150,62,0,0,2018399,180,0,0,2134327,1167,0,0,2607349,2370,0,0,2542742,1381,0,0,1945373,1665,0,0,2542687,0,0,0,1535629,118,0,0,1941027,523,0,0,1974983,904,0,0,2531651,1115,0,0,2303815,2643,0,0,2702774,2608,0,0,2804743,157,0,0,1890348,0,0,0,1868577,0,0,0,1933870,221,0,0,2107803,0,0,0,1925904,0,0,0,2005264,0,0,0,1762695,2472,0,0,2491189,1386,0,0,2448452,0,0,0,1781075,0,0,0,1755621,62,0,0,1883518,56,0,0,1937660,670,0,0,2204976,64,0x7fcb418e4ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,1998111.0,64,0x7ff515f48ec0,329808,225588,16384,0,16384,16384,32768,49152,41225,41225,3209855.0,2470951.0,4763.0,361257.0,1643901.0,0.0,2459264.0,2150854.0,329800,234863,41225,0,41225,0,1319200.0,777557.0,0.0,0.0,64,0x7f9f4b678ec0,0,393216,163840,0,0,0,0,0,29613,0.0,0.0,0.0,32768.0,0.0,0.0,217.0,32768.0,4096,16384,302,40382,2073,0,56.0,9.0,0.0,200277.0,64,0x7f24b44c4ec0,0,3240352,2850,2850,0,3441033,2884,2884,0,3087288,2838,2838,0,3257695,2852,2852,0,4152851,2874,2874,0,4848014,2832,2832,0,3204429,2852,2852,0,3818273,2784,2784,0,3596741,2788,2788,0,4094721,2844,2844,0,2945150,2884,2884,0,3452935,2836,2836,0,3713736,2852,2852,0,4089463,2882,2882,0,4253109,2832,2832,0,3604687,2848,2848,0,4138665,2800,2800,0,4278658,2826,2826,0,3603473,2876,2876,0,3381891,2860,2860,0,3251591,2830,2830,0,3972817,2900,2900,0,4679674,2828,2828,0,4935258,2844,2844,0,4008260,2834,2834,0,3531928,2800,2800,0,3859378,2828,2828,0,4058627,2876,2876,0,3551846,2864,2864,0,3250186,2832,2832,0,3282636,2898,2898,0,4206694,2828,2828,64,0x7f93502f4ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,123589825.0,59871763.0,0.0,64,0x7fc9a0414ec0,114688,0,32768,32768,16384,16384,65536,49152,60639735.0,206253529.0,51932166.0,131072.0,0.0,519385.0,0,0,25870,3094.0,131083.0,0.0,20.0,64,0x7f84c28d0ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,15863,0,819,36741,0,69975.0,131072.0,0.0,45566.0,64,0x7f78b2f18ec0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,64,0x7f61d8d50ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,29844,27018,9579,2859,0,39240,200584.0,0.0,69498.0,131086.0,64,0x7fcb203c4ec0,0,0,0,56,0,65536,65536,0,64,0x7f8639bc4ec0,32768,32768,0,64,0x7f80789d4ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131082.0,126632.0,45557.0,0.0,64,0x7fa505dc4ec0,6270,0,4096,6263,0,4096,6266,0,4096,6267,0,4096,6241,0,4096,6241,0,4096,6285,0,4096,6293,0,4096,6292,0,4096,6271,0,4096,6260,0,4096,6265,0,4096,6259,0,4096,6240,0,4096,6243,0,4096,6286,0,4096,6255,0,4096,6294,0,4096,6272,0,4096,6273,0,4096,6235,0,4096,6237,0,4096,6227,0,4096,6242,0,4096,6244,0,4096,6259,0,4096,6297,0,4096,6279,0,4096,6276,0,4096,6231,0,4096,6241,0,4096,6231,0,4096,64,0x7f4979c7cec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65552.0,0.0,0.0,0.0,64,0x7fd080e6cec0,4097,0,83,0,4096,0,263,0,4096,0,0,0,4096,0,440,0,4096,0,623,0,4096,0,523,0,4096,0,691,0,4096,0,1236,0,4096,0,25,0,4096,0,2,0,4096,0,272,0,4096,0,3,0,4097,0,2,0,4096,0,94,0,4096,0,442,0,4097,0,113,0,4097,0,60,0,4096,0,174,0,4097,0,362,0,4096,0,118,0,4096,0,0,0,4096,0,496,0,4096,0,1319,0,4096,0,954,0,4096,0,72,0,4096,0,33,0,4099,0,229,0,4098,0,1484,0,4096,0,414,0,4096,0,105,0,4096,0,15,0,4096,0,199,0,64,0x7f2f1f530ec0,19169341,17753380,1071897,344064,2768728,0,0,163840,832.0,515136.0,0.0,524288.0,658206.0,32768.0,978464,0,0,13248,91430.0,91430.0,0.0,91430.0,64,0x7f40880acec0,0,183022,0,0,65536,63800,56,1680,64,0x7fb6d0d44ec0,2203,4096,2203,6299,2180,4096,2180,6276,2183,4096,2183,6279,2160,4096,2160,6256,2178,4096,2178,6274,2203,4097,2204,6300,2148,4096,2148,6244,2158,4096,2158,6254,2163,4097,2164,6260,2207,4097,2208,6304,2183,4096,2183,6279,2183,4096,2183,6279,2162,4096,2162,6258,2186,4096,2186,6282,2146,4096,2146,6242,2146,4097,2147,6243,2154,4096,2154,6250,2177,4096,2177,6273,2198,4097,2199,6295,2164,4096,2164,6260,2171,4096,2171,6267,2178,4096,2178,6274,2168,4096,2168,6264,2169,4096,2169,6265,2170,4096,2170,6266,2154,4096,2154,6250,2175,4096,2175,6271,2199,4100,2203,6299,2169,4100,2173,6269,2174,4096,2174,6270,2182,4096,2182,6278,2172,4096,2172,6268,200376896785031,200376896801511 +2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7fce36be8ec0,406,0,0,2297015,95,0,0,1670061,0,0,0,1301013,631,0,0,2222911,0,0,0,1707719,75,0,0,2098806,0,0,0,1563213,665,0,0,2343553,0,0,0,1796945,148,0,0,2086040,0,0,0,1588797,23,0,0,1650979,188,0,0,1802622,570,0,0,1982464,2294,0,0,2585035,0,0,0,1776048,0,0,0,1648207,69,0,0,1905642,0,0,0,1750580,652,0,0,2373172,156,0,0,1930432,151,0,0,1780438,0,0,0,1728190,185,0,0,1786324,0,0,0,1554550,0,0,0,1542435,0,0,0,1682837,109,0,0,2210172,936,0,0,2359037,0,0,0,1611581,147,0,0,1812175,0,0,0,1638739,64,0x7fcb418e4ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2136956.0,64,0x7ff515f48ec0,344104,228695,16384,0,16384,16384,32768,49152,43012,43012,3248159.0,2501995.0,4888.0,380369.0,1671249.0,0.0,2491439.0,2184921.0,344096,237615,43012,0,43012,0,1376384.0,790746.0,0.0,0.0,64,0x7f9f4b678ec0,0,393216,163840,0,0,0,0,0,29670,0.0,0.0,0.0,32768.0,0.0,0.0,201.0,32768.0,4096,16384,302,41194,2052,0,56.0,11.0,0.0,201187.0,64,0x7f24b44c4ec0,0,2742633,2856,2856,0,3972046,2888,2888,0,3535771,2840,2840,0,3286446,2836,2836,0,3821916,2852,2852,0,4493425,2820,2820,0,4766883,2868,2868,0,3348808,2804,2804,0,2888609,2804,2804,0,3156405,2854,2854,0,3263170,2888,2888,0,3213062,2844,2844,0,3120700,2832,2832,0,3015277,2850,2850,0,4277960,2824,2824,0,4497900,2860,2860,0,3320978,2812,2812,0,5182465,2844,2844,0,3174972,2858,2858,0,3891725,2888,2888,0,3917166,2820,2820,0,4111423,2860,2860,0,4032120,2796,2796,0,3940525,2808,2808,0,3999693,2810,2810,0,2612443,2812,2812,0,4054957,2852,2852,0,4818374,2866,2866,0,3208529,2888,2888,0,3146986,2824,2824,0,2777054,2864,2864,0,3700566,2796,2796,64,0x7f93502f4ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,123389948.0,62176176.0,0.0,64,0x7fc9a0414ec0,114688,0,32768,32768,16384,16384,65536,49152,58076389.0,202073232.0,49908871.0,131072.0,0.0,489706.0,0,0,26137,3855.0,131085.0,0.0,24.0,64,0x7f84c28d0ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,20354,0,3698,37941,0,69436.0,131072.0,0.0,45839.0,64,0x7f78b2f18ec0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,64,0x7f61d8d50ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,30337,27048,9628,2838,0,39591,201175.0,0.0,70088.0,131087.0,64,0x7fcb203c4ec0,0,0,0,56,0,65536,65536,0,64,0x7f8639bc4ec0,32768,32768,0,64,0x7f80789d4ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131083.0,94218.0,45624.0,0.0,64,0x7fa505dc4ec0,6281,0,4096,6255,0,4096,6273,0,4096,6314,0,4096,6242,0,4096,6289,0,4096,6299,0,4096,6308,0,4096,6312,0,4096,6284,0,4096,6261,0,4096,6271,0,4096,6319,0,4096,6243,0,4096,6290,0,4096,6303,0,4096,6285,0,4096,6315,0,4096,6252,0,4096,6246,0,4096,6231,0,4096,6271,0,4096,6275,0,4096,6292,0,4096,6293,0,4096,6288,0,4096,6319,0,4096,6254,0,4096,6250,0,4096,6230,0,4096,6273,0,4096,6281,0,4096,64,0x7f4979c7cec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65554.0,0.0,0.0,0.0,64,0x7fd080e6cec0,4097,0,3,0,4096,0,568,0,4096,0,0,0,4096,0,511,0,4096,0,93,0,4096,0,261,0,4096,0,0,0,4096,0,3012,0,4096,0,379,0,4096,0,167,0,4096,0,3046,0,4096,0,0,0,4097,0,124,0,4096,0,0,0,4096,0,0,0,4097,0,20,0,4097,0,0,0,4096,0,405,0,4097,0,1096,0,4096,0,381,0,4096,0,29,0,4096,0,386,0,4096,0,400,0,4096,0,370,0,4096,0,0,0,4096,0,183,0,4099,0,8,0,4098,0,28,0,4096,0,79,0,4096,0,1,0,4096,0,109,0,4096,0,0,0,64,0x7f2f1f530ec0,19307708,18022335,941309,344064,2770543,0,0,163840,832.0,515146.0,0.0,524288.0,598275.0,32768.0,949488,0,0,13517,91076.0,91076.0,0.0,91076.0,64,0x7f40880acec0,0,187732,0,0,65536,63800,56,1680,64,0x7fb6d0d44ec0,2146,4096,2146,6242,2188,4096,2188,6284,2186,4096,2186,6282,2194,4096,2194,6290,2182,4096,2182,6278,2275,4097,2276,6372,2161,4096,2161,6257,2163,4096,2163,6259,2166,4097,2167,6263,2154,4097,2155,6251,2190,4096,2190,6286,2189,4096,2189,6285,2202,4096,2202,6298,2181,4096,2181,6277,2218,4096,2218,6314,2165,4097,2166,6262,2145,4096,2145,6241,2162,4096,2162,6258,2170,4097,2171,6267,2166,4096,2166,6262,2179,4096,2179,6275,2147,4096,2147,6243,2188,4096,2188,6284,2199,4096,2199,6295,2201,4096,2201,6297,2145,4096,2145,6241,2160,4096,2160,6256,2171,4100,2175,6271,2165,4100,2169,6265,2183,4096,2183,6279,2141,4096,2141,6237,2188,4096,2188,6284,200376896822791,200376896838791 diff --git a/tests/workloads/kernel_verbose_3/MI200/roofline.csv b/tests/workloads/kernel_verbose_3/MI200/roofline.csv new file mode 100644 index 0000000000..d96ac5199a --- /dev/null +++ b/tests/workloads/kernel_verbose_3/MI200/roofline.csv @@ -0,0 +1,5 @@ +device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh +0,1389.2186,1388.6204,1389.8169,5014.8477,5012.125,5017.5703,9223.8896,9223.1982,9224.5811,18054.182,18053.324,18055.039,20932.783,20872.1,20993.467,20264.432,20263.896,20264.967,170434.23,170429.53,170438.94,164877.72,164872.09,164883.34,41421.809,41421.203,41422.414,41479.105,41478.355,41479.855,166340.17,165847.98,166832.36 +1,1388.9524,1388.3408,1389.564,5027.9482,5025.8726,5030.0239,9234.459,9233.7734,9235.1445,18096.832,18092.123,18101.541,20974.258,20907.176,21041.34,20296.25,20295.471,20297.029,170864.36,170860.03,170868.69,165130.7,165125.72,165135.69,41484.047,41483.246,41484.848,41542.871,41542.039,41543.703,166875.55,166871.89,166879.2 +2,1388.8219,1388.2272,1389.4166,5035.7168,5033.1938,5038.2397,9258.5625,9257.7793,9259.3457,18103.361,18102.363,18104.359,21047.307,21046.99,21047.623,20352.283,20351.742,20352.824,171108.28,171103.72,171112.84,165483.47,165479.25,165487.69,41580.016,41578.984,41581.047,41635.012,41633.902,41636.121,166941.19,166348.92,167533.45 +3,1388.7208,1388.1876,1389.254,5029.9995,5028.6465,5031.3525,9240.0186,9239.4795,9240.5576,18025.795,18021.91,18029.68,21037.256,21036.809,21037.703,20314.672,20313.996,20315.348,171029.14,171026.12,171032.16,165241.84,165237.61,165246.08,41442.031,41285.902,41598.16,41584.781,41584.109,41585.453,167033.36,167030.98,167035.73 diff --git a/tests/workloads/kernel_verbose_3/MI200/sysinfo.csv b/tests/workloads/kernel_verbose_3/MI200/sysinfo.csv new file mode 100644 index 0000000000..2928a953ab --- /dev/null +++ b/tests/workloads/kernel_verbose_3/MI200/sysinfo.csv @@ -0,0 +1,2 @@ +workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd +kernel_verbose_3,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 02:50:31 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/kernel_verbose_3/MI200/timestamps.csv b/tests/workloads/kernel_verbose_3/MI200/timestamps.csv new file mode 100644 index 0000000000..4dd7623cbd --- /dev/null +++ b/tests/workloads/kernel_verbose_3/MI200/timestamps.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,379175,379175,1048576,256,0,0,8,0,16,64,0x0,0x7fcd42dc8ec0,200376896658571,200376896683431,200376896703751,200376896714156 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,379175,379175,1048576,256,0,0,8,0,16,64,0x0,0x7fcd42dc8ec0,200376896714967,200376896785031,200376896801511,200376896803044 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,379175,379175,1048576,256,0,0,8,0,16,64,0x0,0x7fcd42dc8ec0,200376896812813,200376896822791,200376896838791,200376896840334 diff --git a/tests/workloads/kernel_verbose_4/MI100/SQ_IFETCH_LEVEL.csv b/tests/workloads/kernel_verbose_4/MI100/SQ_IFETCH_LEVEL.csv index a1bd10ff58..3ce8a7e3da 100644 --- a/tests/workloads/kernel_verbose_4/MI100/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/kernel_verbose_4/MI100/SQ_IFETCH_LEVEL.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2883379,2883379,1048576,256,0,0,8,8,16,64,0x0,0x7fe9f004ce80,48213,48213,16384,65536,13025,1662776,2187909095370806,2187903947758734,2187903947782414,2187909102831782 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2883379,2883379,1048576,256,0,0,8,8,16,64,0x0,0x7fe9f004ce80,43844,43844,16384,65536,8312,1048576,2187909102856338,2187903947881134,2187903947899854,2187909103178222 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2883379,2883379,1048576,256,0,0,8,8,16,64,0x0,0x7fe9f004ce80,43015,43015,16384,65536,8074,1048584,2187909103210202,2187903947920654,2187903947939374,2187909103395320 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,184787,184787,1048576,256,0,0,8,8,16,64,0x0,0x7f0b431aee80,48173,48173,16384,65536,14172,1840588,194313898560911,194326078140081,194326078163761,194313907696729 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,184787,184787,1048576,256,0,0,8,8,16,64,0x0,0x7f0b431aee80,42332,42332,16384,65536,8060,1048584,194313907719873,194326078246321,194326078266001,194313908055629 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,184787,184787,1048576,256,0,0,8,8,16,64,0x0,0x7f0b431aee80,42228,42228,16384,65536,8122,1048616,194313908088972,194326078286481,194326078305361,194313908306815 diff --git a/tests/workloads/kernel_verbose_4/MI100/SQ_INST_LEVEL_LDS.csv b/tests/workloads/kernel_verbose_4/MI100/SQ_INST_LEVEL_LDS.csv index 4a7b00be79..3e1fc6931e 100644 --- a/tests/workloads/kernel_verbose_4/MI100/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/kernel_verbose_4/MI100/SQ_INST_LEVEL_LDS.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2882468,2882468,1048576,256,0,0,8,8,16,64,0x0,0x7f59847ece80,0,0,0,2187906630784539,2187903947758734,2187903947782414,2187906638294306 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2882468,2882468,1048576,256,0,0,8,8,16,64,0x0,0x7f59847ece80,0,0,0,2187906638314063,2187903947881134,2187903947899854,2187906638615910 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2882468,2882468,1048576,256,0,0,8,8,16,64,0x0,0x7f59847ece80,0,0,0,2187906638645185,2187903947920654,2187903947939374,2187906638859026 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,184970,184970,1048576,256,0,0,8,8,16,64,0x0,0x7fde3b9bae80,0,0,0,194314397849244,194326078140081,194326078163761,194314405577707 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,184970,184970,1048576,256,0,0,8,8,16,64,0x0,0x7fde3b9bae80,0,0,0,194314405595651,194326078246321,194326078266001,194314405914695 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,184970,184970,1048576,256,0,0,8,8,16,64,0x0,0x7fde3b9bae80,0,0,0,194314405942998,194326078286481,194326078305361,194314406126466 diff --git a/tests/workloads/kernel_verbose_4/MI100/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/kernel_verbose_4/MI100/SQ_INST_LEVEL_SMEM.csv index 2fa2a6e8f5..75b8202d77 100644 --- a/tests/workloads/kernel_verbose_4/MI100/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/kernel_verbose_4/MI100/SQ_INST_LEVEL_SMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2881556,2881556,1048576,256,0,0,8,8,16,64,0x0,0x7fb3509dce80,65536,191298,24523040,2187904392047394,2187903947758734,2187903947782414,2187904399779759 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2881556,2881556,1048576,256,0,0,8,8,16,64,0x0,0x7fb3509dce80,65536,170726,21846392,2187904399800458,2187903947881134,2187903947899854,2187904400119407 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2881556,2881556,1048576,256,0,0,8,8,16,64,0x0,0x7fb3509dce80,65536,189884,24268936,2187904400148231,2187903947920654,2187903947939374,2187904400326776 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,185153,185153,1048576,256,0,0,8,8,16,64,0x0,0x7f8d97dd4e80,65536,219396,28112080,194314890482225,194326078140081,194326078163761,194314898156525 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,185153,185153,1048576,256,0,0,8,8,16,64,0x0,0x7f8d97dd4e80,65536,180206,23016480,194314898175772,194326078246321,194326078266001,194314898472644 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,185153,185153,1048576,256,0,0,8,8,16,64,0x0,0x7f8d97dd4e80,65536,189732,24288608,194314898500978,194326078286481,194326078305361,194314898675158 diff --git a/tests/workloads/kernel_verbose_4/MI100/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/kernel_verbose_4/MI100/SQ_INST_LEVEL_VMEM.csv index 136b3f3d8c..3e8714f73f 100644 --- a/tests/workloads/kernel_verbose_4/MI100/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/kernel_verbose_4/MI100/SQ_INST_LEVEL_VMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2879916,2879916,1048576,256,0,0,8,8,16,64,0x0,0x7fad343ece80,32768,649236,83101240,2187899881052709,2187903947758734,2187903947782414,2187899888771710 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2879916,2879916,1048576,256,0,0,8,8,16,64,0x0,0x7fad343ece80,32768,659176,84373492,2187899888791066,2187903947881134,2187903947899854,2187899889082173 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2879916,2879916,1048576,256,0,0,8,8,16,64,0x0,0x7fad343ece80,32768,661137,84622812,2187899889111618,2187903947920654,2187903947939374,2187899889270686 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,185338,185338,1048576,256,0,0,8,8,16,64,0x0,0x7f83005d4e80,32768,653995,83708432,194315383386910,194326078140081,194326078163761,194315391168805 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,185338,185338,1048576,256,0,0,8,8,16,64,0x0,0x7f83005d4e80,32768,665869,85235244,194315391190145,194326078246321,194326078266001,194315391477589 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,185338,185338,1048576,256,0,0,8,8,16,64,0x0,0x7f83005d4e80,32768,664826,85079520,194315391505763,194326078286481,194326078305361,194315391737011 diff --git a/tests/workloads/kernel_verbose_4/MI100/SQ_LEVEL_WAVES.csv b/tests/workloads/kernel_verbose_4/MI100/SQ_LEVEL_WAVES.csv index ca2a08c84d..b0b07c114f 100644 --- a/tests/workloads/kernel_verbose_4/MI100/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/kernel_verbose_4/MI100/SQ_LEVEL_WAVES.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,2880098,2880098,1048576,256,0,0,8,8,16,64,0x0,0x7fcca623ae80,47928,47928,17543,383432,16384,25204069,232534,0,101302588,2187900329987627,2187903947758734,2187903947782414,2187900337493257 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,2880098,2880098,1048576,256,0,0,8,8,16,64,0x0,0x7fcca623ae80,42184,42184,13430,337480,16384,24427777,227450,0,98206816,2187900337522031,2187903947881134,2187903947899854,2187900337944524 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,2880098,2880098,1048576,256,0,0,8,8,16,64,0x0,0x7fcca623ae80,42136,42136,13703,337096,16384,23965438,225125,0,96358012,2187900337975412,2187903947920654,2187903947939374,2187900338168996 +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,185524,185524,1048576,256,0,0,8,8,16,64,0x0,0x7fc1be638e80,48328,48328,17216,386632,16384,25447382,235315,0,102274300,194315877642313,194326078140081,194326078163761,194315886401849 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,185524,185524,1048576,256,0,0,8,8,16,64,0x0,0x7fc1be638e80,43255,43255,13566,346048,16384,25165439,234630,0,101170844,194315886432357,194326078246321,194326078266001,194315886856550 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,185524,185524,1048576,256,0,0,8,8,16,64,0x0,0x7fc1be638e80,42703,42703,13505,341632,16384,24776662,229753,0,99603288,194315886895834,194326078286481,194326078305361,194315887116442 diff --git a/tests/workloads/kernel_verbose_4/MI100/pmc_dispatch_info.csv b/tests/workloads/kernel_verbose_4/MI100/pmc_dispatch_info.csv new file mode 100644 index 0000000000..17300ae9af --- /dev/null +++ b/tests/workloads/kernel_verbose_4/MI100/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) ",2 +1,"vecCopy(double*, double*, double*, int, int) ",2 +2,"vecCopy(double*, double*, double*, int, int) ",2 diff --git a/tests/workloads/kernel_verbose_4/MI100/pmc_perf.csv b/tests/workloads/kernel_verbose_4/MI100/pmc_perf.csv index 21df8f8b94..bec4692c88 100644 --- a/tests/workloads/kernel_verbose_4/MI100/pmc_perf.csv +++ b/tests/workloads/kernel_verbose_4/MI100/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_1,obj_1,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_2,obj_2,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_3,obj_3,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_4,obj_4,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_5,obj_5,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_6,obj_6,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_7,obj_7,TCC_EA_ATOMIC_LEVEL_sum,wave_size_8,obj_8,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_9,obj_9,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_10,obj_10,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_11,obj_11,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_12,obj_12,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_13,obj_13,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_14,obj_14,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_15,obj_15,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_16,obj_16,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f7e1bfdce80,0,3346815,4096,4096,0,4046211,4096,4096,0,3770443,4096,4096,0,4726928,4096,4096,0,4211012,4096,4096,0,3715343,4096,4096,0,3255263,4096,4096,0,4486271,4096,4096,0,2790066,4096,4096,0,4318107,4096,4096,0,3539668,4096,4096,0,3944747,4096,4096,0,4053112,4096,4096,0,4799907,4096,4096,0,3172787,4096,4096,0,3237145,4096,4096,0,3683158,4096,4096,0,5380305,4096,4096,0,3167616,4096,4096,0,3472718,4096,4096,0,3258192,4096,4096,0,4039874,4096,4096,0,3715829,4096,4096,0,4576744,4096,4096,0,3914465,4096,4096,0,2541501,4096,4096,0,4960435,4096,4096,0,3373744,4096,4096,0,4550096,4096,4096,0,3478908,4096,4096,0,2957264,4096,4096,0,3011519,4096,4096,64,0x7f1c287dce80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86938.0,44134.0,131111.0,0.0,64,0x7f709d444e80,4096,0,1218,0,4203,0,556,0,4096,0,2118,0,4096,0,32,0,4096,0,991,0,4256,0,3336,0,4096,0,1921,0,4096,0,1816,0,4096,0,1849,0,4096,0,845,0,4096,0,2210,0,4097,0,2664,0,4096,0,1548,0,4096,0,798,0,4096,0,1933,0,4096,0,1581,0,4096,0,2249,0,4096,0,728,0,4096,0,2145,0,4096,0,1558,0,4096,0,268,0,4096,0,1705,0,4096,0,2678,0,4096,0,381,0,4096,0,852,0,4096,0,1063,0,4144,0,1971,0,4096,0,969,0,4096,0,2567,0,4099,0,359,0,4096,0,2604,0,4096,0,1052,0,64,0x7f36ce80ee80,131072.0,131072.0,0.0,2399518.0,0.0,0.0,112577034.0,63249102.0,64,0x7f38c0490e80,8192,0,4096,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f902770ee80,186503,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,12320,28704,9837,550,0,46781,262719.0,0.0,188.0,262531.0,64,0x7f6433564e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,48194,0,131648.0,131072.0,0.0,131104.0,64,0x7f559a218e80,0.0,64,0x7f6787342e80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,141,8195,4240,8336,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8474,4378,8474,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f2709d40e80,1847,0,0,1810375,3770,0,0,1952488,1557,0,0,1806737,2053,0,0,1819543,583,0,0,1542836,2131,0,0,1795618,1459,0,0,1857896,5016,0,0,2190181,2463,0,0,1846953,2684,0,0,1954341,1379,0,0,1739839,4711,0,0,2124282,2398,0,0,1838275,3499,0,0,1978489,1242,0,0,1736277,2677,0,0,1933483,1537,0,0,1781028,3141,0,0,1914544,831,0,0,1659861,2029,0,0,1777198,1244,0,0,1700652,3124,0,0,1948886,2420,0,0,1961305,1302,0,0,1756852,929,0,0,1652608,1777,0,0,1756023,1651,0,0,1782737,4071,0,0,2012829,1190,0,0,1711680,3877,0,0,1994159,1548,0,0,1864179,2857,0,0,1975347,64,0x7f2030e8ee80,2184591,360448,163840,0,0,180224,114688,0,68593419.0,200065750.0,79493648.0,131072.0,0.0,690925.0,0,0,26773,132645.0,0.0,0.0,132645.0,64,0x7f5ea15f6e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,73154.0,139500.0,64,0x7ff4569dce80,0,0,192,0,65536,64536,48,1277,31457,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,539,47356,1660,0,48.0,216.0,0.0,262288.0,64,0x7fd5deebae80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131438.0,0.0,724.0,131437.0,64,0x7fc4e450ee80,0,48724,0,0,0,48724,0,0,0,48724,0,0,0,48724,0,0,0,48724,0,0,0,48724,0,0,0,48724,0,0,0,48724,0,0,0,48724,0,0,0,48724,0,0,0,48724,0,0,0,48724,0,0,0,48724,0,0,0,48724,0,0,0,48724,0,0,0,48724,0,0,0,48724,0,0,0,48724,0,0,0,48724,0,0,0,48724,0,0,0,48724,0,0,0,48724,0,0,0,48724,0,0,0,48724,0,0,0,48724,0,0,0,48724,0,0,0,48724,0,0,0,48724,0,0,0,48724,0,0,0,48724,0,0,0,48724,0,0,0,48724,0,0,64,0x7f9a4e970e80,377608,229508,3362589,16384,24877783,144,48,0,47200,47200,3795461.0,2987016.0,5929.0,996231.0,2042045.0,0.0,2978195.0,2667220.0,375895,239438,47200,0,47200,0,1510400.0,949614.0,0.0,0.0,64,0x7f75c2a96e80,32768,0,0,0,16384,16384,393216,21590753,960.0,513877.0,0.0,524288.0,1136865.0,32768.0,0,0,0,16884,131072.0,131072.0,0.0,131072.0,2187903947758734,2187903947782414 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f7e1bfdce80,0,3984162,2677,2677,0,3770466,2700,2700,0,3905098,2664,2664,0,5486839,2702,2702,0,4422968,2683,2683,0,3009653,2716,2716,0,3611942,2716,2716,0,3784616,2700,2700,0,2980685,2695,2695,0,2743010,2696,2696,0,3423045,2716,2716,0,4355888,2726,2726,0,3925388,2676,2676,0,3256246,2688,2688,0,3899332,2696,2696,0,3451743,2696,2696,0,3631939,2676,2676,0,2862972,2692,2692,0,4161022,2701,2701,0,3512897,2720,2720,0,3300048,2691,2691,0,4122064,2769,2769,0,3129999,2692,2692,0,2407477,2676,2676,0,2966368,2672,2672,0,2798475,2684,2684,0,3358118,2732,2732,0,2855200,2703,2703,0,2664000,2700,2700,0,3568043,2693,2693,0,4873211,2692,2692,0,3688286,2694,2694,64,0x7f1c287dce80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,87274.0,0.0,131112.0,0.0,64,0x7f709d444e80,4098,0,133,0,4290,0,2301,0,4097,0,1299,0,4096,0,1524,0,4099,0,570,0,4205,0,225,0,4096,0,1207,0,4096,0,0,0,4096,0,123,0,4096,0,1814,0,4096,0,2240,0,4097,0,2569,0,4096,0,0,0,4096,0,924,0,4096,0,2228,0,4096,0,0,0,4096,0,1772,0,4096,0,3301,0,4096,0,147,0,4096,0,150,0,4096,0,162,0,4096,0,562,0,4096,0,1848,0,4096,0,0,0,4096,0,793,0,4096,0,1043,0,4144,0,6,0,4096,0,694,0,4096,0,146,0,4096,0,673,0,4096,0,0,0,4096,0,2055,0,64,0x7f36ce80ee80,131072.0,131072.0,0.0,2478476.0,0.0,0.0,111952108.0,47923028.0,64,0x7f38c0490e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f902770ee80,188832,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13472,29856,8637,6185,0,43762,262519.0,0.0,47.0,262472.0,64,0x7f6433564e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,3607,39708,0,131510.0,131072.0,0.0,86705.0,64,0x7f559a218e80,0.0,64,0x7f6787342e80,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8476,4380,8476,0,8192,4096,8192,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,64,0x7f2709d40e80,4355,0,0,1657743,1099,0,0,1249280,2396,0,0,1576032,5298,0,0,1789771,1499,0,0,1411990,130,0,0,1153158,811,0,0,1360268,2691,0,0,1543691,2082,0,0,1462466,1395,0,0,1383307,631,0,0,1282422,1061,0,0,1388753,3203,0,0,1622864,59,0,0,1135101,1233,0,0,1408790,1448,0,0,1432090,2179,0,0,1510609,3079,0,0,1589260,533,0,0,1291968,1008,0,0,1349779,979,0,0,1336278,1232,0,0,1411314,5780,0,0,1847886,1903,0,0,1497419,1100,0,0,1315789,1006,0,0,1300230,3796,0,0,1625896,3760,0,0,1610394,2069,0,0,1544074,1879,0,0,1416532,189,0,0,1170598,502,0,0,1296575,64,0x7f2030e8ee80,2065089,360448,163840,0,0,180224,114688,0,67142918.0,191047035.0,84268022.0,131072.0,0.0,992147.0,0,0,25266,83875.0,0.0,0.0,83875.0,64,0x7f5ea15f6e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,44473.0,110906.0,64,0x7ff4569dce80,0,0,48,0,65536,65536,0,0,30780,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,458,43484,1688,0,48.0,227.0,0.0,262144.0,64,0x7fd5deebae80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131462.0,0.0,778.0,131461.0,64,0x7fc4e450ee80,0,43236,0,0,0,43236,0,0,0,43236,0,0,0,43236,0,0,0,43236,0,0,0,43236,0,0,0,43236,0,0,0,43236,0,0,0,43236,0,0,0,43236,0,0,0,43236,0,0,0,43236,0,0,0,43236,0,0,0,43236,0,0,0,43236,0,0,0,43236,0,0,0,43236,0,0,0,43236,0,0,0,43236,0,0,0,43236,0,0,0,43236,0,0,0,43236,0,0,0,43236,0,0,0,43236,0,0,0,43236,0,0,0,43236,0,0,0,43236,0,0,0,43236,0,0,0,43236,0,0,0,43236,0,0,0,43236,0,0,0,43236,0,0,64,0x7f9a4e970e80,344144,226591,3311817,16384,24702164,0,48,0,43017,43017,3688452.0,3030027.0,6727.0,1110624.0,2084843.0,0.0,3021519.0,2710711.0,344136,236107,43017,0,43017,0,1376544.0,805334.0,0.0,0.0,64,0x7f75c2a96e80,32768,0,0,0,16384,16384,393216,22318104,960.0,513962.0,0.0,524288.0,1300404.0,32768.0,0,0,0,14476,86804.0,86804.0,0.0,86804.0,2187903947881134,2187903947899854 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f7e1bfdce80,0,3498143,2672,2672,0,3383358,2668,2668,0,3737626,2690,2690,0,5061641,2713,2713,0,3340325,2713,2713,0,3270492,2706,2706,0,3774120,2716,2716,0,3637105,2712,2712,0,3672884,2726,2726,0,3458195,2692,2692,0,3409981,2710,2710,0,3879056,2748,2748,0,3453969,2696,2696,0,3587937,2668,2668,0,4788441,2700,2700,0,4082533,2718,2718,0,4316836,2700,2700,0,4535629,2664,2664,0,3336440,2714,2714,0,4053390,2742,2742,0,3902888,2710,2710,0,3227731,2733,2733,0,3372762,2688,2688,0,3587198,2716,2716,0,3623389,2687,2687,0,3235968,2704,2704,0,3435629,2746,2746,0,3417621,2728,2728,0,3128351,2686,2686,0,3607841,2685,2685,0,3865909,2756,2756,0,3486442,2698,2698,64,0x7f1c287dce80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,87288.0,0.0,131112.0,0.0,64,0x7f709d444e80,4098,0,2597,0,4205,0,1062,0,4097,0,2174,0,4096,0,290,0,4099,0,1364,0,4260,0,1399,0,4096,0,1791,0,4096,0,661,0,4096,0,1864,0,4096,0,1298,0,4096,0,579,0,4097,0,2679,0,4096,0,1510,0,4096,0,2888,0,4096,0,1281,0,4096,0,0,0,4096,0,1073,0,4096,0,2615,0,4096,0,1129,0,4096,0,1616,0,4096,0,1216,0,4096,0,1074,0,4096,0,730,0,4096,0,0,0,4096,0,548,0,4096,0,2605,0,4144,0,406,0,4096,0,525,0,4096,0,2672,0,4096,0,2635,0,4096,0,1153,0,4096,0,687,0,64,0x7f36ce80ee80,131072.0,131072.0,0.0,2517987.0,0.0,0.0,103104384.0,48768154.0,64,0x7f38c0490e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f902770ee80,184306,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,12562,28946,8663,3447,0,41263,262582.0,0.0,47.0,262535.0,64,0x7f6433564e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,3605,38108,0,131503.0,131072.0,0.0,87164.0,64,0x7f559a218e80,0.0,64,0x7f6787342e80,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8480,4384,8480,0,8192,4096,8192,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,64,0x7f2709d40e80,3232,0,0,1619116,1062,0,0,1385959,1490,0,0,1381663,1682,0,0,1444388,850,0,0,1301284,603,0,0,1288600,3288,0,0,1664533,2826,0,0,1595365,451,0,0,1149558,1914,0,0,1491518,2301,0,0,1507542,3859,0,0,1608522,831,0,0,1281568,1078,0,0,1333723,2242,0,0,1503991,1777,0,0,1475569,2345,0,0,1548216,2077,0,0,1523033,2694,0,0,1521443,1390,0,0,1396395,4020,0,0,1688460,602,0,0,1341454,3015,0,0,1630446,3522,0,0,1681552,939,0,0,1267184,765,0,0,1283197,3053,0,0,1550602,2055,0,0,1475314,2308,0,0,1482373,2708,0,0,1498139,1842,0,0,1479364,2753,0,0,1582681,64,0x7f2030e8ee80,2087346,360448,163840,0,0,180224,114688,0,64879314.0,183601982.0,73886559.0,131072.0,0.0,723170.0,0,0,25273,119301.0,0.0,0.0,119301.0,64,0x7f5ea15f6e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,32597.0,102357.0,64,0x7ff4569dce80,0,0,48,0,65536,65536,0,0,30260,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,457,41538,1710,0,48.0,222.0,0.0,262144.0,64,0x7fd5deebae80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131459.0,0.0,772.0,131458.0,64,0x7fc4e450ee80,0,42231,0,0,0,42231,0,0,0,42231,0,0,0,42231,0,0,0,42231,0,0,0,42231,0,0,0,42231,0,0,0,42231,0,0,0,42231,0,0,0,42231,0,0,0,42231,0,0,0,42231,0,0,0,42231,0,0,0,42231,0,0,0,42231,0,0,0,42231,0,0,0,42231,0,0,0,42231,0,0,0,42231,0,0,0,42231,0,0,0,42231,0,0,0,42231,0,0,0,42231,0,0,0,42231,0,0,0,42231,0,0,0,42231,0,0,0,42231,0,0,0,42231,0,0,0,42231,0,0,0,42231,0,0,0,42231,0,0,0,42231,0,0,64,0x7f9a4e970e80,330984,223088,3256445,16384,23822698,0,48,0,41372,41372,3635827.0,2979087.0,6178.0,1174547.0,2072038.0,0.0,2969947.0,2659533.0,330976,232403,41372,0,41372,0,1323904.0,798493.0,0.0,0.0,64,0x7f75c2a96e80,32768,0,0,0,16384,16384,393216,21631526,960.0,513866.0,0.0,524288.0,1239823.0,32768.0,0,0,0,14251,87117.0,87117.0,0.0,87117.0,2187903947920654,2187903947939374 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_1,obj_1,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_2,obj_2,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_3,obj_3,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_4,obj_4,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_5,obj_5,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_6,obj_6,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_7,obj_7,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_8,obj_8,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_9,obj_9,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_10,obj_10,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_11,obj_11,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_12,obj_12,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_13,obj_13,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_14,obj_14,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_15,obj_15,TCC_EA_ATOMIC_LEVEL_sum,wave_size_16,obj_16,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f96e4ac4e80,0,0,192,0,65536,64457,48,1311,31841,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,538,47741,1668,0,48.0,264.0,0.0,262288.0,64,0x7f5ef0308e80,1778463,360448,163840,0,0,180224,114688,0,71426713.0,203167265.0,76086832.0,131072.0,0.0,598834.0,0,0,26004,74585.0,0.0,0.0,74585.0,64,0x7f6c34118e80,32768,0,0,0,16384,16384,393216,23021977,960.0,514019.0,0.0,524288.0,983449.0,32768.0,0,0,0,17750,131072.0,131072.0,0.0,131072.0,64,0x7ff8a140ce80,131072.0,131072.0,0.0,2568379.0,0.0,0.0,136601685.0,61311257.0,64,0x7f6c5942ee80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7faf7ef68e80,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,64,0x7fa507448e80,4096,0,1202,0,4096,0,534,0,4099,0,0,0,4096,0,0,0,4096,0,1099,0,4096,0,0,0,4096,0,0,0,4096,0,856,0,4096,0,0,0,4096,0,804,0,4144,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,73,0,4096,0,0,0,4096,0,0,0,4144,0,0,0,4096,0,1218,0,4096,0,0,0,4096,0,3103,0,4195,0,2223,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,618,0,4096,0,0,0,4096,0,0,0,4096,0,3006,0,4096,0,0,0,64,0x7f934f204e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86326.0,44746.0,131111.0,0.0,64,0x7fbef9ac2e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,65597.0,135103.0,64,0x7f2ec35b4e80,383120,234664,3438341,16384,25464910,144,48,0,47889,47889,3872412.0,3008555.0,7163.0,988071.0,2058186.0,0.0,2999602.0,2687187.0,381663,244594,47889,0,47889,0,1532448.0,961880.0,0.0,0.0,64,0x7f8f51342e80,0,2348987,4096,4096,0,3164882,4096,4096,0,3270810,4096,4096,0,2486750,4096,4096,0,2390329,4096,4096,0,2862526,4096,4096,0,4599216,4096,4096,0,4165857,4096,4096,0,2044135,4096,4096,0,2849050,4096,4096,0,2793085,4096,4096,0,4879108,4096,4096,0,3070453,4096,4096,0,2885449,4096,4096,0,2799819,4096,4096,0,2483512,4096,4096,0,2516048,4096,4096,0,3405966,4096,4096,0,5395461,4096,4096,0,4059517,4096,4096,0,5452563,4096,4096,0,3003469,4096,4096,0,2429593,4096,4096,0,2643223,4096,4096,0,2046159,4096,4096,0,2896839,4096,4096,0,2391960,4096,4096,0,2436407,4096,4096,0,2898051,4096,4096,0,3117014,4096,4096,0,3994901,4096,4096,0,2624006,4096,4096,64,0x7fe71665ee80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131294.0,0.0,436.0,131293.0,64,0x7f4436e58e80,0,8192,4096,8192,0,8192,4096,8192,141,8195,4240,8336,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8372,4276,8372,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7fb26bfcae80,4108,0,0,2059906,4983,0,0,2098059,920,0,0,1693058,5386,0,0,2179144,1053,0,0,1682983,1899,0,0,1788568,1252,0,0,1767342,4977,0,0,2156124,1744,0,0,1712961,5751,0,0,2234641,1677,0,0,1857668,3198,0,0,1961171,3003,0,0,1939991,1906,0,0,1873530,2116,0,0,1882706,3052,0,0,1989377,2052,0,0,1875555,1342,0,0,1734561,1455,0,0,1736999,1979,0,0,1838933,2284,0,0,1887073,3457,0,0,1998032,1571,0,0,1791744,3282,0,0,2013822,4209,0,0,2087168,884,0,0,1718885,4876,0,0,2181784,4006,0,0,2030795,1976,0,0,1866780,3802,0,0,2039070,1977,0,0,1866340,5068,0,0,2211134,64,0x7fca5ba54e80,190171,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,14631,31015,9883,550,0,46227,262599.0,0.0,188.0,262411.0,64,0x7faff5f12e80,0.0,64,0x7fbabfec0e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,47294,0,131481.0,131072.0,0.0,131104.0,194326078140081,194326078163761 +1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f96e4ac4e80,0,0,48,0,65536,65536,0,0,31028,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,457,42238,1676,0,48.0,268.0,0.0,262144.0,64,0x7f5ef0308e80,1169987,360448,163840,0,0,180224,114688,0,71601252.0,205731733.0,80519124.0,131072.0,0.0,638084.0,0,0,25583,64010.0,0.0,0.0,64010.0,64,0x7f6c34118e80,32768,0,0,0,16384,16384,393216,23310677,960.0,513970.0,0.0,524288.0,931546.0,32768.0,0,0,0,13891,86495.0,86495.0,0.0,86495.0,64,0x7ff8a140ce80,131072.0,131072.0,0.0,2608991.0,0.0,0.0,103623122.0,47412208.0,64,0x7f6c5942ee80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7faf7ef68e80,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,64,0x7fa507448e80,4096,0,2134,0,4096,0,2058,0,4096,0,2159,0,4098,0,0,0,4096,0,2834,0,4096,0,2140,0,4096,0,710,0,4096,0,13,0,4096,0,481,0,4097,0,2528,0,4144,0,1381,0,4096,0,1071,0,4096,0,2193,0,4096,0,1787,0,4096,0,1780,0,4096,0,1247,0,4144,0,2236,0,4096,0,2325,0,4096,0,1340,0,4097,0,231,0,4284,0,6187,0,4096,0,2144,0,4096,0,27,0,4096,0,0,0,4096,0,1199,0,4096,0,3037,0,4096,0,781,0,4097,0,0,0,4096,0,831,0,4096,0,40,0,4096,0,678,0,4096,0,250,0,64,0x7f934f204e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86478.0,0.0,131112.0,0.0,64,0x7fbef9ac2e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,51387.0,120030.0,64,0x7f2ec35b4e80,342504,229951,3375912,16384,24411432,0,48,0,42812,42812,3738776.0,3036494.0,6510.0,1064186.0,2018271.0,0.0,3027596.0,2715475.0,342496,239335,42812,0,42812,0,1369984.0,808395.0,0.0,0.0,64,0x7f8f51342e80,0,5237007,2734,2734,0,4405635,2688,2688,0,5446506,2676,2676,0,4914779,2700,2700,0,4127621,2718,2718,0,4901803,2716,2716,0,4043342,2740,2740,0,3315239,2702,2702,0,3917745,2728,2728,0,5060741,2652,2652,0,4277062,2698,2698,0,3797931,2738,2738,0,4902456,2712,2712,0,3338990,2674,2674,0,4861305,2668,2668,0,4187925,2688,2688,0,4084944,2721,2721,0,4099613,2679,2679,0,4846924,2700,2700,0,3225790,2696,2696,0,3139896,2736,2736,0,3188827,2737,2737,0,5523246,2702,2702,0,2812349,2696,2696,0,4541139,2713,2713,0,3468348,2701,2701,0,4200414,2742,2742,0,4445441,2722,2722,0,4659840,2734,2734,0,3942971,2701,2701,0,5054764,2730,2730,0,3640417,2696,2696,64,0x7fe71665ee80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131710.0,0.0,1270.0,131707.0,64,0x7f4436e58e80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,47,8193,4144,8240,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8336,4240,8336,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7fb26bfcae80,1157,0,0,1387560,3180,0,0,1594727,1717,0,0,1428057,2443,0,0,1534225,3130,0,0,1591318,1483,0,0,1469097,1386,0,0,1389458,1421,0,0,1328717,2187,0,0,1540140,1594,0,0,1408780,1140,0,0,1361729,2122,0,0,1556648,1649,0,0,1468613,477,0,0,1174541,1700,0,0,1513860,2905,0,0,1606934,1408,0,0,1435750,1772,0,0,1501579,1662,0,0,1426380,1010,0,0,1346971,684,0,0,1192991,1683,0,0,1480027,1394,0,0,1404646,4695,0,0,1784928,1782,0,0,1486329,2306,0,0,1599020,1301,0,0,1347891,5219,0,0,1804915,1381,0,0,1402904,6488,0,0,1862081,3967,0,0,1644655,1076,0,0,1373458,64,0x7fca5ba54e80,84961,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,15843,32227,8467,2381,0,41629,262458.0,0.0,47.0,262411.0,64,0x7faff5f12e80,0.0,64,0x7fbabfec0e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,2674,39939,0,131364.0,131072.0,0.0,86804.0,194326078246321,194326078266001 +2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f96e4ac4e80,0,0,48,0,65536,65536,0,0,30396,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,457,41606,1692,0,48.0,268.0,0.0,262144.0,64,0x7f5ef0308e80,1147318,360448,163840,0,0,180224,114688,0,71667473.0,208440349.0,80298221.0,131072.0,0.0,620144.0,0,0,24824,69265.0,0.0,0.0,69265.0,64,0x7f6c34118e80,32768,0,0,0,16384,16384,393216,22428819,960.0,513935.0,0.0,524288.0,996248.0,32768.0,0,0,0,13323,86623.0,86623.0,0.0,86623.0,64,0x7ff8a140ce80,131072.0,131072.0,0.0,2572338.0,0.0,0.0,108200627.0,48314364.0,64,0x7f6c5942ee80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7faf7ef68e80,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,64,0x7fa507448e80,4096,0,119,0,4096,0,1507,0,4096,0,1205,0,4098,0,0,0,4096,0,0,0,4096,0,937,0,4096,0,1226,0,4096,0,33,0,4096,0,147,0,4097,0,1908,0,4144,0,582,0,4096,0,796,0,4096,0,140,0,4096,0,712,0,4096,0,918,0,4096,0,363,0,4144,0,562,0,4096,0,1591,0,4096,0,2052,0,4097,0,1553,0,4207,0,3032,0,4096,0,786,0,4096,0,105,0,4096,0,0,0,4096,0,5,0,4096,0,1227,0,4096,0,335,0,4097,0,5670,0,4096,0,425,0,4096,0,507,0,4096,0,695,0,4096,0,204,0,64,0x7f934f204e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86400.0,0.0,131112.0,0.0,64,0x7fbef9ac2e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,36787.0,115469.0,64,0x7f2ec35b4e80,341320,230368,3357258,16384,24672672,0,48,0,42664,42664,3745496.0,3016362.0,7131.0,1046872.0,2020801.0,0.0,3007669.0,2696261.0,341312,240149,42664,0,42664,0,1365248.0,800407.0,0.0,0.0,64,0x7f8f51342e80,0,4037446,2724,2724,0,3392456,2733,2733,0,3585363,2700,2700,0,3376778,2709,2709,0,4031272,2672,2672,0,4211063,2735,2735,0,2953762,2712,2712,0,3058574,2689,2689,0,3553286,2704,2704,0,4858023,2694,2694,0,3152171,2702,2702,0,3322048,2704,2704,0,4658845,2706,2706,0,3536338,2708,2708,0,3494502,2694,2694,0,3199045,2674,2674,0,3568971,2690,2690,0,4968358,2728,2728,0,3464865,2702,2702,0,4939027,2684,2684,0,5209197,2700,2700,0,3665624,2727,2727,0,2971241,2712,2712,0,4012833,2660,2660,0,3598312,2694,2694,0,4249312,2704,2704,0,3670929,2724,2724,0,2768055,2688,2688,0,4895275,2726,2726,0,3815208,2704,2704,0,3163108,2724,2724,0,3163384,2648,2648,64,0x7fe71665ee80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131322.0,0.0,498.0,131321.0,64,0x7f4436e58e80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,47,8193,4144,8240,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8372,4276,8372,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7fb26bfcae80,1973,0,0,1439207,5139,0,0,1769560,69,0,0,1090685,2642,0,0,1463000,441,0,0,1263988,1527,0,0,1419006,573,0,0,1375541,3150,0,0,1544802,2233,0,0,1438569,2341,0,0,1507245,200,0,0,1227553,1930,0,0,1438432,2391,0,0,1483800,1264,0,0,1359495,195,0,0,1161586,3351,0,0,1555005,2051,0,0,1376124,2322,0,0,1540157,332,0,0,1175214,2945,0,0,1422837,1811,0,0,1452336,724,0,0,1332711,3666,0,0,1655244,2715,0,0,1502502,3414,0,0,1540029,670,0,0,1222591,522,0,0,1207168,3202,0,0,1498841,1357,0,0,1432612,657,0,0,1305841,221,0,0,1250267,2920,0,0,1509323,64,0x7fca5ba54e80,80179,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,14861,31245,8632,2373,0,42456,262441.0,0.0,47.0,262394.0,64,0x7faff5f12e80,0.0,64,0x7fbabfec0e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,2667,39182,0,131348.0,131072.0,0.0,86862.0,194326078286481,194326078305361 diff --git a/tests/workloads/kernel_verbose_4/MI100/sysinfo.csv b/tests/workloads/kernel_verbose_4/MI100/sysinfo.csv index 43f99e6662..c95cf342a3 100644 --- a/tests/workloads/kernel_verbose_4/MI100/sysinfo.csv +++ b/tests/workloads/kernel_verbose_4/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -kernel_verbose_4,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Fri Mar 1 16:46:50 2024 (CST),1,t006-003.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651240,,5.7.1-98,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +kernel_verbose_4,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 07 Mar 2024 01:09:38 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/kernel_verbose_4/MI100/timestamps.csv b/tests/workloads/kernel_verbose_4/MI100/timestamps.csv index f79bfc9ec0..fc4c2681f3 100644 --- a/tests/workloads/kernel_verbose_4/MI100/timestamps.csv +++ b/tests/workloads/kernel_verbose_4/MI100/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,2881374,2881374,1048576,256,0,0,8,8,16,64,0x0,0x7f7b5cfd8e80,2187903947733330,2187903947758734,2187903947782414,2187903947796258 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,2881374,2881374,1048576,256,0,0,8,8,16,64,0x0,0x7f7b5cfd8e80,2187903947795066,2187903947881134,2187903947899854,2187903947900985 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,2881374,2881374,1048576,256,0,0,8,8,16,64,0x0,0x7f7b5cfd8e80,2187903947911795,2187903947920654,2187903947939374,2187903947943625 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,188851,188851,1048576,256,0,0,8,8,16,64,0x0,0x7fcdc177ce80,194326078115281,194326078140081,194326078163761,194326078175646 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,188851,188851,1048576,256,0,0,8,8,16,64,0x0,0x7fcdc177ce80,194326078176337,194326078246321,194326078266001,194326078267189 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,188851,188851,1048576,256,0,0,8,8,16,64,0x0,0x7fcdc177ce80,194326078277839,194326078286481,194326078305361,194326078306553 diff --git a/tests/workloads/kernel_verbose_4/MI200/SQ_IFETCH_LEVEL.csv b/tests/workloads/kernel_verbose_4/MI200/SQ_IFETCH_LEVEL.csv new file mode 100644 index 0000000000..c8c3c11c3d --- /dev/null +++ b/tests/workloads/kernel_verbose_4/MI200/SQ_IFETCH_LEVEL.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,348065,348065,1048576,256,0,0,8,0,16,64,0x0,0x7f6ec65bcec0,27938,27938,16384,65536,19427,2170752,199736671989683,199749380764970,199749380785450,199736687821853 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,348065,348065,1048576,256,0,0,8,0,16,64,0x0,0x7f6ec65bcec0,40960,40960,16384,65536,9699,1048724,199736687842181,199749381010410,199749381026730,199736688142660 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,348065,348065,1048576,256,0,0,8,0,16,64,0x0,0x7f6ec65bcec0,41140,41140,16384,65536,9396,1048684,199736688172496,199749381056970,199749381072490,199736688346195 diff --git a/tests/workloads/kernel_verbose_4/MI200/SQ_INST_LEVEL_LDS.csv b/tests/workloads/kernel_verbose_4/MI200/SQ_INST_LEVEL_LDS.csv new file mode 100644 index 0000000000..2b9e01d65d --- /dev/null +++ b/tests/workloads/kernel_verbose_4/MI200/SQ_INST_LEVEL_LDS.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,348266,348266,1048576,256,0,0,8,0,16,64,0x0,0x7fecc9848ec0,0,0,0,199737153452827,199749380764970,199749380785450,199737169239551 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,348266,348266,1048576,256,0,0,8,0,16,64,0x0,0x7fecc9848ec0,0,0,0,199737169257485,199749381010410,199749381026730,199737169557161 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,348266,348266,1048576,256,0,0,8,0,16,64,0x0,0x7fecc9848ec0,0,0,0,199737169583481,199749381056970,199749381072490,199737169736681 diff --git a/tests/workloads/kernel_verbose_4/MI200/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/kernel_verbose_4/MI200/SQ_INST_LEVEL_SMEM.csv new file mode 100644 index 0000000000..f664a52ff6 --- /dev/null +++ b/tests/workloads/kernel_verbose_4/MI200/SQ_INST_LEVEL_SMEM.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,348467,348467,1048576,256,0,0,8,0,16,64,0x0,0x7ff2f8b2cec0,65536,185428,20819504,199737628417567,199749380764970,199749380785450,199737644116635 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,348467,348467,1048576,256,0,0,8,0,16,64,0x0,0x7ff2f8b2cec0,65536,255620,28684728,199737644142494,199749381010410,199749381026730,199737644446790 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,348467,348467,1048576,256,0,0,8,0,16,64,0x0,0x7ff2f8b2cec0,65536,250286,28090080,199737644472348,199749381056970,199749381072490,199737644628323 diff --git a/tests/workloads/kernel_verbose_4/MI200/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/kernel_verbose_4/MI200/SQ_INST_LEVEL_VMEM.csv new file mode 100644 index 0000000000..03410d100d --- /dev/null +++ b/tests/workloads/kernel_verbose_4/MI200/SQ_INST_LEVEL_VMEM.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,348668,348668,1048576,256,0,0,8,0,16,64,0x0,0x7ffb6b5bcec0,32768,297966,33373480,199738105805011,199749380764970,199749380785450,199738121666256 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,348668,348668,1048576,256,0,0,8,0,16,64,0x0,0x7ffb6b5bcec0,32768,597744,66947016,199738121684861,199749381010410,199749381026730,199738121958068 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,348668,348668,1048576,256,0,0,8,0,16,64,0x0,0x7ffb6b5bcec0,32768,580746,65045176,199738121983746,199749381056970,199749381072490,199738122145412 diff --git a/tests/workloads/kernel_verbose_4/MI200/SQ_LEVEL_WAVES.csv b/tests/workloads/kernel_verbose_4/MI200/SQ_LEVEL_WAVES.csv new file mode 100644 index 0000000000..5b7e010307 --- /dev/null +++ b/tests/workloads/kernel_verbose_4/MI200/SQ_LEVEL_WAVES.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,348853,348853,1048576,256,0,0,8,0,16,64,0x0,0x7fc8703e4ec0,27559,27559,11150,220480,16384,10713927,126978,0,43354456,199738586972194,199749380764970,199749380785450,199738602691601 +1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,348853,348853,1048576,256,0,0,8,0,16,64,0x0,0x7fc8703e4ec0,41116,41116,13388,328936,16384,19033337,220605,0,76630672,199738602721107,199749381010410,199749381026730,199738603154046 +2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,348853,348853,1048576,256,0,0,8,0,16,64,0x0,0x7fc8703e4ec0,41528,41528,13594,332232,16384,19388701,224822,0,78030200,199738603190014,199749381056970,199749381072490,199738603386556 diff --git a/tests/workloads/kernel_verbose_4/MI200/perfmon/SQ_IFETCH_LEVEL.txt b/tests/workloads/kernel_verbose_4/MI200/perfmon/SQ_IFETCH_LEVEL.txt new file mode 100644 index 0000000000..293092f641 --- /dev/null +++ b/tests/workloads/kernel_verbose_4/MI200/perfmon/SQ_IFETCH_LEVEL.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_4/MI200/perfmon/SQ_INST_LEVEL_LDS.txt b/tests/workloads/kernel_verbose_4/MI200/perfmon/SQ_INST_LEVEL_LDS.txt new file mode 100644 index 0000000000..08439eedce --- /dev/null +++ b/tests/workloads/kernel_verbose_4/MI200/perfmon/SQ_INST_LEVEL_LDS.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_4/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt b/tests/workloads/kernel_verbose_4/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt new file mode 100644 index 0000000000..6cca322d4e --- /dev/null +++ b/tests/workloads/kernel_verbose_4/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_4/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt b/tests/workloads/kernel_verbose_4/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt new file mode 100644 index 0000000000..e527ad31ba --- /dev/null +++ b/tests/workloads/kernel_verbose_4/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_4/MI200/perfmon/SQ_LEVEL_WAVES.txt b/tests/workloads/kernel_verbose_4/MI200/perfmon/SQ_LEVEL_WAVES.txt new file mode 100644 index 0000000000..3f8e04adb3 --- /dev/null +++ b/tests/workloads/kernel_verbose_4/MI200/perfmon/SQ_LEVEL_WAVES.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_0.txt b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_0.txt new file mode 100644 index 0000000000..4ffdc32149 --- /dev/null +++ b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_0.txt @@ -0,0 +1,5 @@ +pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES SQ_INSTS_VALU_CVT SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU GRBM_COUNT GRBM_GUI_ACTIVE TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum TA_TA_BUSY_sum TA_BUFFER_WAVEFRONTS_sum TD_TD_BUSY_sum TD_TC_STALL_sum SPI_CSN_WINDOW_VALID SPI_CSN_BUSY CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_1.txt b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_1.txt new file mode 100644 index 0000000000..6c277f4a37 --- /dev/null +++ b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_1.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VSKIPPED SQ_INSTS SQ_INSTS_VALU SQ_INSTS_VALU_ADD_F16 SQ_INSTS_VALU_MUL_F16 SQ_INSTS_VALU_FMA_F16 SQ_INSTS_VALU_TRANS_F16 SQ_INSTS_VALU_ADD_F32 GRBM_SPI_BUSY TCP_READ_TAGCONFLICT_STALL_CYCLES_sum TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum TCP_TA_TCP_STATE_READ_sum TA_BUFFER_READ_WAVEFRONTS_sum TA_BUFFER_WRITE_WAVEFRONTS_sum TD_SPI_STALL_sum TD_LOAD_WAVEFRONT_sum SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_10.txt b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_10.txt new file mode 100644 index 0000000000..7053d4dce6 --- /dev/null +++ b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_10.txt @@ -0,0 +1,5 @@ +pmc: SQC_TC_DATA_WRITE_REQ SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_11.txt b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_11.txt new file mode 100644 index 0000000000..77ae8b461f --- /dev/null +++ b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_11.txt @@ -0,0 +1,5 @@ +pmc: SQC_ICACHE_MISSES_DUPLICATE SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_12.txt b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_12.txt new file mode 100644 index 0000000000..dfb2cf65e5 --- /dev/null +++ b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_12.txt @@ -0,0 +1,5 @@ +pmc: SQC_DCACHE_REQ_READ_1 SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_13.txt b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_13.txt new file mode 100644 index 0000000000..062fc9644a --- /dev/null +++ b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_13.txt @@ -0,0 +1,5 @@ +pmc: TCC_ATOMIC[0] TCC_CYCLE[0] TCC_EA_ATOMIC[0] TCC_EA_ATOMIC_LEVEL[0] TCC_ATOMIC[1] TCC_CYCLE[1] TCC_EA_ATOMIC[1] TCC_EA_ATOMIC_LEVEL[1] TCC_ATOMIC[2] TCC_CYCLE[2] TCC_EA_ATOMIC[2] TCC_EA_ATOMIC_LEVEL[2] TCC_ATOMIC[3] TCC_CYCLE[3] TCC_EA_ATOMIC[3] TCC_EA_ATOMIC_LEVEL[3] TCC_ATOMIC[4] TCC_CYCLE[4] TCC_EA_ATOMIC[4] TCC_EA_ATOMIC_LEVEL[4] TCC_ATOMIC[5] TCC_CYCLE[5] TCC_EA_ATOMIC[5] TCC_EA_ATOMIC_LEVEL[5] TCC_ATOMIC[6] TCC_CYCLE[6] TCC_EA_ATOMIC[6] TCC_EA_ATOMIC_LEVEL[6] TCC_ATOMIC[7] TCC_CYCLE[7] TCC_EA_ATOMIC[7] TCC_EA_ATOMIC_LEVEL[7] TCC_ATOMIC[8] TCC_CYCLE[8] TCC_EA_ATOMIC[8] TCC_EA_ATOMIC_LEVEL[8] TCC_ATOMIC[9] TCC_CYCLE[9] TCC_EA_ATOMIC[9] TCC_EA_ATOMIC_LEVEL[9] TCC_ATOMIC[10] TCC_CYCLE[10] TCC_EA_ATOMIC[10] TCC_EA_ATOMIC_LEVEL[10] TCC_ATOMIC[11] TCC_CYCLE[11] TCC_EA_ATOMIC[11] TCC_EA_ATOMIC_LEVEL[11] TCC_ATOMIC[12] TCC_CYCLE[12] TCC_EA_ATOMIC[12] TCC_EA_ATOMIC_LEVEL[12] TCC_ATOMIC[13] TCC_CYCLE[13] TCC_EA_ATOMIC[13] TCC_EA_ATOMIC_LEVEL[13] TCC_ATOMIC[14] TCC_CYCLE[14] TCC_EA_ATOMIC[14] TCC_EA_ATOMIC_LEVEL[14] TCC_ATOMIC[15] TCC_CYCLE[15] TCC_EA_ATOMIC[15] TCC_EA_ATOMIC_LEVEL[15] TCC_ATOMIC[16] TCC_CYCLE[16] TCC_EA_ATOMIC[16] TCC_EA_ATOMIC_LEVEL[16] TCC_ATOMIC[17] TCC_CYCLE[17] TCC_EA_ATOMIC[17] TCC_EA_ATOMIC_LEVEL[17] TCC_ATOMIC[18] TCC_CYCLE[18] TCC_EA_ATOMIC[18] TCC_EA_ATOMIC_LEVEL[18] TCC_ATOMIC[19] TCC_CYCLE[19] TCC_EA_ATOMIC[19] TCC_EA_ATOMIC_LEVEL[19] TCC_ATOMIC[20] TCC_CYCLE[20] TCC_EA_ATOMIC[20] TCC_EA_ATOMIC_LEVEL[20] TCC_ATOMIC[21] TCC_CYCLE[21] TCC_EA_ATOMIC[21] TCC_EA_ATOMIC_LEVEL[21] TCC_ATOMIC[22] TCC_CYCLE[22] TCC_EA_ATOMIC[22] TCC_EA_ATOMIC_LEVEL[22] TCC_ATOMIC[23] TCC_CYCLE[23] TCC_EA_ATOMIC[23] TCC_EA_ATOMIC_LEVEL[23] TCC_ATOMIC[24] TCC_CYCLE[24] TCC_EA_ATOMIC[24] TCC_EA_ATOMIC_LEVEL[24] TCC_ATOMIC[25] TCC_CYCLE[25] TCC_EA_ATOMIC[25] TCC_EA_ATOMIC_LEVEL[25] TCC_ATOMIC[26] TCC_CYCLE[26] TCC_EA_ATOMIC[26] TCC_EA_ATOMIC_LEVEL[26] TCC_ATOMIC[27] TCC_CYCLE[27] TCC_EA_ATOMIC[27] TCC_EA_ATOMIC_LEVEL[27] TCC_ATOMIC[28] TCC_CYCLE[28] TCC_EA_ATOMIC[28] TCC_EA_ATOMIC_LEVEL[28] TCC_ATOMIC[29] TCC_CYCLE[29] TCC_EA_ATOMIC[29] TCC_EA_ATOMIC_LEVEL[29] TCC_ATOMIC[30] TCC_CYCLE[30] TCC_EA_ATOMIC[30] TCC_EA_ATOMIC_LEVEL[30] TCC_ATOMIC[31] TCC_CYCLE[31] TCC_EA_ATOMIC[31] TCC_EA_ATOMIC_LEVEL[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_14.txt b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_14.txt new file mode 100644 index 0000000000..e0698dbf57 --- /dev/null +++ b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_14.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_EA_RDREQ_GMI_CREDIT_STALL[0] TCC_EA_RDREQ[1] TCC_EA_RDREQ_32B[1] TCC_EA_RDREQ_DRAM_CREDIT_STALL[1] TCC_EA_RDREQ_GMI_CREDIT_STALL[1] TCC_EA_RDREQ[2] TCC_EA_RDREQ_32B[2] TCC_EA_RDREQ_DRAM_CREDIT_STALL[2] TCC_EA_RDREQ_GMI_CREDIT_STALL[2] TCC_EA_RDREQ[3] TCC_EA_RDREQ_32B[3] TCC_EA_RDREQ_DRAM_CREDIT_STALL[3] TCC_EA_RDREQ_GMI_CREDIT_STALL[3] TCC_EA_RDREQ[4] TCC_EA_RDREQ_32B[4] TCC_EA_RDREQ_DRAM_CREDIT_STALL[4] TCC_EA_RDREQ_GMI_CREDIT_STALL[4] TCC_EA_RDREQ[5] TCC_EA_RDREQ_32B[5] TCC_EA_RDREQ_DRAM_CREDIT_STALL[5] TCC_EA_RDREQ_GMI_CREDIT_STALL[5] TCC_EA_RDREQ[6] TCC_EA_RDREQ_32B[6] TCC_EA_RDREQ_DRAM_CREDIT_STALL[6] TCC_EA_RDREQ_GMI_CREDIT_STALL[6] TCC_EA_RDREQ[7] TCC_EA_RDREQ_32B[7] TCC_EA_RDREQ_DRAM_CREDIT_STALL[7] TCC_EA_RDREQ_GMI_CREDIT_STALL[7] TCC_EA_RDREQ[8] TCC_EA_RDREQ_32B[8] TCC_EA_RDREQ_DRAM_CREDIT_STALL[8] TCC_EA_RDREQ_GMI_CREDIT_STALL[8] TCC_EA_RDREQ[9] TCC_EA_RDREQ_32B[9] TCC_EA_RDREQ_DRAM_CREDIT_STALL[9] TCC_EA_RDREQ_GMI_CREDIT_STALL[9] TCC_EA_RDREQ[10] TCC_EA_RDREQ_32B[10] TCC_EA_RDREQ_DRAM_CREDIT_STALL[10] TCC_EA_RDREQ_GMI_CREDIT_STALL[10] TCC_EA_RDREQ[11] TCC_EA_RDREQ_32B[11] TCC_EA_RDREQ_DRAM_CREDIT_STALL[11] TCC_EA_RDREQ_GMI_CREDIT_STALL[11] TCC_EA_RDREQ[12] TCC_EA_RDREQ_32B[12] TCC_EA_RDREQ_DRAM_CREDIT_STALL[12] TCC_EA_RDREQ_GMI_CREDIT_STALL[12] TCC_EA_RDREQ[13] TCC_EA_RDREQ_32B[13] TCC_EA_RDREQ_DRAM_CREDIT_STALL[13] TCC_EA_RDREQ_GMI_CREDIT_STALL[13] TCC_EA_RDREQ[14] TCC_EA_RDREQ_32B[14] TCC_EA_RDREQ_DRAM_CREDIT_STALL[14] TCC_EA_RDREQ_GMI_CREDIT_STALL[14] TCC_EA_RDREQ[15] TCC_EA_RDREQ_32B[15] TCC_EA_RDREQ_DRAM_CREDIT_STALL[15] TCC_EA_RDREQ_GMI_CREDIT_STALL[15] TCC_EA_RDREQ[16] TCC_EA_RDREQ_32B[16] TCC_EA_RDREQ_DRAM_CREDIT_STALL[16] TCC_EA_RDREQ_GMI_CREDIT_STALL[16] TCC_EA_RDREQ[17] TCC_EA_RDREQ_32B[17] TCC_EA_RDREQ_DRAM_CREDIT_STALL[17] TCC_EA_RDREQ_GMI_CREDIT_STALL[17] TCC_EA_RDREQ[18] TCC_EA_RDREQ_32B[18] TCC_EA_RDREQ_DRAM_CREDIT_STALL[18] TCC_EA_RDREQ_GMI_CREDIT_STALL[18] TCC_EA_RDREQ[19] TCC_EA_RDREQ_32B[19] TCC_EA_RDREQ_DRAM_CREDIT_STALL[19] TCC_EA_RDREQ_GMI_CREDIT_STALL[19] TCC_EA_RDREQ[20] TCC_EA_RDREQ_32B[20] TCC_EA_RDREQ_DRAM_CREDIT_STALL[20] TCC_EA_RDREQ_GMI_CREDIT_STALL[20] TCC_EA_RDREQ[21] TCC_EA_RDREQ_32B[21] TCC_EA_RDREQ_DRAM_CREDIT_STALL[21] TCC_EA_RDREQ_GMI_CREDIT_STALL[21] TCC_EA_RDREQ[22] TCC_EA_RDREQ_32B[22] TCC_EA_RDREQ_DRAM_CREDIT_STALL[22] TCC_EA_RDREQ_GMI_CREDIT_STALL[22] TCC_EA_RDREQ[23] TCC_EA_RDREQ_32B[23] TCC_EA_RDREQ_DRAM_CREDIT_STALL[23] TCC_EA_RDREQ_GMI_CREDIT_STALL[23] TCC_EA_RDREQ[24] TCC_EA_RDREQ_32B[24] TCC_EA_RDREQ_DRAM_CREDIT_STALL[24] TCC_EA_RDREQ_GMI_CREDIT_STALL[24] TCC_EA_RDREQ[25] TCC_EA_RDREQ_32B[25] TCC_EA_RDREQ_DRAM_CREDIT_STALL[25] TCC_EA_RDREQ_GMI_CREDIT_STALL[25] TCC_EA_RDREQ[26] TCC_EA_RDREQ_32B[26] TCC_EA_RDREQ_DRAM_CREDIT_STALL[26] TCC_EA_RDREQ_GMI_CREDIT_STALL[26] TCC_EA_RDREQ[27] TCC_EA_RDREQ_32B[27] TCC_EA_RDREQ_DRAM_CREDIT_STALL[27] TCC_EA_RDREQ_GMI_CREDIT_STALL[27] TCC_EA_RDREQ[28] TCC_EA_RDREQ_32B[28] TCC_EA_RDREQ_DRAM_CREDIT_STALL[28] TCC_EA_RDREQ_GMI_CREDIT_STALL[28] TCC_EA_RDREQ[29] TCC_EA_RDREQ_32B[29] TCC_EA_RDREQ_DRAM_CREDIT_STALL[29] TCC_EA_RDREQ_GMI_CREDIT_STALL[29] TCC_EA_RDREQ[30] TCC_EA_RDREQ_32B[30] TCC_EA_RDREQ_DRAM_CREDIT_STALL[30] TCC_EA_RDREQ_GMI_CREDIT_STALL[30] TCC_EA_RDREQ[31] TCC_EA_RDREQ_32B[31] TCC_EA_RDREQ_DRAM_CREDIT_STALL[31] TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_15.txt b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_15.txt new file mode 100644 index 0000000000..77ad088669 --- /dev/null +++ b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_15.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ[0] TCC_EA_WRREQ_64B[0] TCC_EA_RDREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_LEVEL[1] TCC_EA_WRREQ[1] TCC_EA_WRREQ_64B[1] TCC_EA_RDREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_LEVEL[2] TCC_EA_WRREQ[2] TCC_EA_WRREQ_64B[2] TCC_EA_RDREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_LEVEL[3] TCC_EA_WRREQ[3] TCC_EA_WRREQ_64B[3] TCC_EA_RDREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_LEVEL[4] TCC_EA_WRREQ[4] TCC_EA_WRREQ_64B[4] TCC_EA_RDREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_LEVEL[5] TCC_EA_WRREQ[5] TCC_EA_WRREQ_64B[5] TCC_EA_RDREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_LEVEL[6] TCC_EA_WRREQ[6] TCC_EA_WRREQ_64B[6] TCC_EA_RDREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_LEVEL[7] TCC_EA_WRREQ[7] TCC_EA_WRREQ_64B[7] TCC_EA_RDREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_LEVEL[8] TCC_EA_WRREQ[8] TCC_EA_WRREQ_64B[8] TCC_EA_RDREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_LEVEL[9] TCC_EA_WRREQ[9] TCC_EA_WRREQ_64B[9] TCC_EA_RDREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_LEVEL[10] TCC_EA_WRREQ[10] TCC_EA_WRREQ_64B[10] TCC_EA_RDREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_LEVEL[11] TCC_EA_WRREQ[11] TCC_EA_WRREQ_64B[11] TCC_EA_RDREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_LEVEL[12] TCC_EA_WRREQ[12] TCC_EA_WRREQ_64B[12] TCC_EA_RDREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_LEVEL[13] TCC_EA_WRREQ[13] TCC_EA_WRREQ_64B[13] TCC_EA_RDREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_LEVEL[14] TCC_EA_WRREQ[14] TCC_EA_WRREQ_64B[14] TCC_EA_RDREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_LEVEL[15] TCC_EA_WRREQ[15] TCC_EA_WRREQ_64B[15] TCC_EA_RDREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_LEVEL[16] TCC_EA_WRREQ[16] TCC_EA_WRREQ_64B[16] TCC_EA_RDREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_LEVEL[17] TCC_EA_WRREQ[17] TCC_EA_WRREQ_64B[17] TCC_EA_RDREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_LEVEL[18] TCC_EA_WRREQ[18] TCC_EA_WRREQ_64B[18] TCC_EA_RDREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_LEVEL[19] TCC_EA_WRREQ[19] TCC_EA_WRREQ_64B[19] TCC_EA_RDREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_LEVEL[20] TCC_EA_WRREQ[20] TCC_EA_WRREQ_64B[20] TCC_EA_RDREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_LEVEL[21] TCC_EA_WRREQ[21] TCC_EA_WRREQ_64B[21] TCC_EA_RDREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_LEVEL[22] TCC_EA_WRREQ[22] TCC_EA_WRREQ_64B[22] TCC_EA_RDREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_LEVEL[23] TCC_EA_WRREQ[23] TCC_EA_WRREQ_64B[23] TCC_EA_RDREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_LEVEL[24] TCC_EA_WRREQ[24] TCC_EA_WRREQ_64B[24] TCC_EA_RDREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_LEVEL[25] TCC_EA_WRREQ[25] TCC_EA_WRREQ_64B[25] TCC_EA_RDREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_LEVEL[26] TCC_EA_WRREQ[26] TCC_EA_WRREQ_64B[26] TCC_EA_RDREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_LEVEL[27] TCC_EA_WRREQ[27] TCC_EA_WRREQ_64B[27] TCC_EA_RDREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_LEVEL[28] TCC_EA_WRREQ[28] TCC_EA_WRREQ_64B[28] TCC_EA_RDREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_LEVEL[29] TCC_EA_WRREQ[29] TCC_EA_WRREQ_64B[29] TCC_EA_RDREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_LEVEL[30] TCC_EA_WRREQ[30] TCC_EA_WRREQ_64B[30] TCC_EA_RDREQ_IO_CREDIT_STALL[31] TCC_EA_RDREQ_LEVEL[31] TCC_EA_WRREQ[31] TCC_EA_WRREQ_64B[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_16.txt b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_16.txt new file mode 100644 index 0000000000..d0628bb948 --- /dev/null +++ b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_16.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_WRREQ_IO_CREDIT_STALL[0] TCC_EA_WRREQ_LEVEL[0] TCC_EA_WRREQ_DRAM_CREDIT_STALL[1] TCC_EA_WRREQ_GMI_CREDIT_STALL[1] TCC_EA_WRREQ_IO_CREDIT_STALL[1] TCC_EA_WRREQ_LEVEL[1] TCC_EA_WRREQ_DRAM_CREDIT_STALL[2] TCC_EA_WRREQ_GMI_CREDIT_STALL[2] TCC_EA_WRREQ_IO_CREDIT_STALL[2] TCC_EA_WRREQ_LEVEL[2] TCC_EA_WRREQ_DRAM_CREDIT_STALL[3] TCC_EA_WRREQ_GMI_CREDIT_STALL[3] TCC_EA_WRREQ_IO_CREDIT_STALL[3] TCC_EA_WRREQ_LEVEL[3] TCC_EA_WRREQ_DRAM_CREDIT_STALL[4] TCC_EA_WRREQ_GMI_CREDIT_STALL[4] TCC_EA_WRREQ_IO_CREDIT_STALL[4] TCC_EA_WRREQ_LEVEL[4] TCC_EA_WRREQ_DRAM_CREDIT_STALL[5] TCC_EA_WRREQ_GMI_CREDIT_STALL[5] TCC_EA_WRREQ_IO_CREDIT_STALL[5] TCC_EA_WRREQ_LEVEL[5] TCC_EA_WRREQ_DRAM_CREDIT_STALL[6] TCC_EA_WRREQ_GMI_CREDIT_STALL[6] TCC_EA_WRREQ_IO_CREDIT_STALL[6] TCC_EA_WRREQ_LEVEL[6] TCC_EA_WRREQ_DRAM_CREDIT_STALL[7] TCC_EA_WRREQ_GMI_CREDIT_STALL[7] TCC_EA_WRREQ_IO_CREDIT_STALL[7] TCC_EA_WRREQ_LEVEL[7] TCC_EA_WRREQ_DRAM_CREDIT_STALL[8] TCC_EA_WRREQ_GMI_CREDIT_STALL[8] TCC_EA_WRREQ_IO_CREDIT_STALL[8] TCC_EA_WRREQ_LEVEL[8] TCC_EA_WRREQ_DRAM_CREDIT_STALL[9] TCC_EA_WRREQ_GMI_CREDIT_STALL[9] TCC_EA_WRREQ_IO_CREDIT_STALL[9] TCC_EA_WRREQ_LEVEL[9] TCC_EA_WRREQ_DRAM_CREDIT_STALL[10] TCC_EA_WRREQ_GMI_CREDIT_STALL[10] TCC_EA_WRREQ_IO_CREDIT_STALL[10] TCC_EA_WRREQ_LEVEL[10] TCC_EA_WRREQ_DRAM_CREDIT_STALL[11] TCC_EA_WRREQ_GMI_CREDIT_STALL[11] TCC_EA_WRREQ_IO_CREDIT_STALL[11] TCC_EA_WRREQ_LEVEL[11] TCC_EA_WRREQ_DRAM_CREDIT_STALL[12] TCC_EA_WRREQ_GMI_CREDIT_STALL[12] TCC_EA_WRREQ_IO_CREDIT_STALL[12] TCC_EA_WRREQ_LEVEL[12] TCC_EA_WRREQ_DRAM_CREDIT_STALL[13] TCC_EA_WRREQ_GMI_CREDIT_STALL[13] TCC_EA_WRREQ_IO_CREDIT_STALL[13] TCC_EA_WRREQ_LEVEL[13] TCC_EA_WRREQ_DRAM_CREDIT_STALL[14] TCC_EA_WRREQ_GMI_CREDIT_STALL[14] TCC_EA_WRREQ_IO_CREDIT_STALL[14] TCC_EA_WRREQ_LEVEL[14] TCC_EA_WRREQ_DRAM_CREDIT_STALL[15] TCC_EA_WRREQ_GMI_CREDIT_STALL[15] TCC_EA_WRREQ_IO_CREDIT_STALL[15] TCC_EA_WRREQ_LEVEL[15] TCC_EA_WRREQ_DRAM_CREDIT_STALL[16] TCC_EA_WRREQ_GMI_CREDIT_STALL[16] TCC_EA_WRREQ_IO_CREDIT_STALL[16] TCC_EA_WRREQ_LEVEL[16] TCC_EA_WRREQ_DRAM_CREDIT_STALL[17] TCC_EA_WRREQ_GMI_CREDIT_STALL[17] TCC_EA_WRREQ_IO_CREDIT_STALL[17] TCC_EA_WRREQ_LEVEL[17] TCC_EA_WRREQ_DRAM_CREDIT_STALL[18] TCC_EA_WRREQ_GMI_CREDIT_STALL[18] TCC_EA_WRREQ_IO_CREDIT_STALL[18] TCC_EA_WRREQ_LEVEL[18] TCC_EA_WRREQ_DRAM_CREDIT_STALL[19] TCC_EA_WRREQ_GMI_CREDIT_STALL[19] TCC_EA_WRREQ_IO_CREDIT_STALL[19] TCC_EA_WRREQ_LEVEL[19] TCC_EA_WRREQ_DRAM_CREDIT_STALL[20] TCC_EA_WRREQ_GMI_CREDIT_STALL[20] TCC_EA_WRREQ_IO_CREDIT_STALL[20] TCC_EA_WRREQ_LEVEL[20] TCC_EA_WRREQ_DRAM_CREDIT_STALL[21] TCC_EA_WRREQ_GMI_CREDIT_STALL[21] TCC_EA_WRREQ_IO_CREDIT_STALL[21] TCC_EA_WRREQ_LEVEL[21] TCC_EA_WRREQ_DRAM_CREDIT_STALL[22] TCC_EA_WRREQ_GMI_CREDIT_STALL[22] TCC_EA_WRREQ_IO_CREDIT_STALL[22] TCC_EA_WRREQ_LEVEL[22] TCC_EA_WRREQ_DRAM_CREDIT_STALL[23] TCC_EA_WRREQ_GMI_CREDIT_STALL[23] TCC_EA_WRREQ_IO_CREDIT_STALL[23] TCC_EA_WRREQ_LEVEL[23] TCC_EA_WRREQ_DRAM_CREDIT_STALL[24] TCC_EA_WRREQ_GMI_CREDIT_STALL[24] TCC_EA_WRREQ_IO_CREDIT_STALL[24] TCC_EA_WRREQ_LEVEL[24] TCC_EA_WRREQ_DRAM_CREDIT_STALL[25] TCC_EA_WRREQ_GMI_CREDIT_STALL[25] TCC_EA_WRREQ_IO_CREDIT_STALL[25] TCC_EA_WRREQ_LEVEL[25] TCC_EA_WRREQ_DRAM_CREDIT_STALL[26] TCC_EA_WRREQ_GMI_CREDIT_STALL[26] TCC_EA_WRREQ_IO_CREDIT_STALL[26] TCC_EA_WRREQ_LEVEL[26] TCC_EA_WRREQ_DRAM_CREDIT_STALL[27] TCC_EA_WRREQ_GMI_CREDIT_STALL[27] TCC_EA_WRREQ_IO_CREDIT_STALL[27] TCC_EA_WRREQ_LEVEL[27] TCC_EA_WRREQ_DRAM_CREDIT_STALL[28] TCC_EA_WRREQ_GMI_CREDIT_STALL[28] TCC_EA_WRREQ_IO_CREDIT_STALL[28] TCC_EA_WRREQ_LEVEL[28] TCC_EA_WRREQ_DRAM_CREDIT_STALL[29] TCC_EA_WRREQ_GMI_CREDIT_STALL[29] TCC_EA_WRREQ_IO_CREDIT_STALL[29] TCC_EA_WRREQ_LEVEL[29] TCC_EA_WRREQ_DRAM_CREDIT_STALL[30] TCC_EA_WRREQ_GMI_CREDIT_STALL[30] TCC_EA_WRREQ_IO_CREDIT_STALL[30] TCC_EA_WRREQ_LEVEL[30] TCC_EA_WRREQ_DRAM_CREDIT_STALL[31] TCC_EA_WRREQ_GMI_CREDIT_STALL[31] TCC_EA_WRREQ_IO_CREDIT_STALL[31] TCC_EA_WRREQ_LEVEL[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_17.txt b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_17.txt new file mode 100644 index 0000000000..343869c5f1 --- /dev/null +++ b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_17.txt @@ -0,0 +1,5 @@ +pmc: TCC_HIT[0] TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_HIT[1] TCC_MISS[1] TCC_READ[1] TCC_REQ[1] TCC_HIT[2] TCC_MISS[2] TCC_READ[2] TCC_REQ[2] TCC_HIT[3] TCC_MISS[3] TCC_READ[3] TCC_REQ[3] TCC_HIT[4] TCC_MISS[4] TCC_READ[4] TCC_REQ[4] TCC_HIT[5] TCC_MISS[5] TCC_READ[5] TCC_REQ[5] TCC_HIT[6] TCC_MISS[6] TCC_READ[6] TCC_REQ[6] TCC_HIT[7] TCC_MISS[7] TCC_READ[7] TCC_REQ[7] TCC_HIT[8] TCC_MISS[8] TCC_READ[8] TCC_REQ[8] TCC_HIT[9] TCC_MISS[9] TCC_READ[9] TCC_REQ[9] TCC_HIT[10] TCC_MISS[10] TCC_READ[10] TCC_REQ[10] TCC_HIT[11] TCC_MISS[11] TCC_READ[11] TCC_REQ[11] TCC_HIT[12] TCC_MISS[12] TCC_READ[12] TCC_REQ[12] TCC_HIT[13] TCC_MISS[13] TCC_READ[13] TCC_REQ[13] TCC_HIT[14] TCC_MISS[14] TCC_READ[14] TCC_REQ[14] TCC_HIT[15] TCC_MISS[15] TCC_READ[15] TCC_REQ[15] TCC_HIT[16] TCC_MISS[16] TCC_READ[16] TCC_REQ[16] TCC_HIT[17] TCC_MISS[17] TCC_READ[17] TCC_REQ[17] TCC_HIT[18] TCC_MISS[18] TCC_READ[18] TCC_REQ[18] TCC_HIT[19] TCC_MISS[19] TCC_READ[19] TCC_REQ[19] TCC_HIT[20] TCC_MISS[20] TCC_READ[20] TCC_REQ[20] TCC_HIT[21] TCC_MISS[21] TCC_READ[21] TCC_REQ[21] TCC_HIT[22] TCC_MISS[22] TCC_READ[22] TCC_REQ[22] TCC_HIT[23] TCC_MISS[23] TCC_READ[23] TCC_REQ[23] TCC_HIT[24] TCC_MISS[24] TCC_READ[24] TCC_REQ[24] TCC_HIT[25] TCC_MISS[25] TCC_READ[25] TCC_REQ[25] TCC_HIT[26] TCC_MISS[26] TCC_READ[26] TCC_REQ[26] TCC_HIT[27] TCC_MISS[27] TCC_READ[27] TCC_REQ[27] TCC_HIT[28] TCC_MISS[28] TCC_READ[28] TCC_REQ[28] TCC_HIT[29] TCC_MISS[29] TCC_READ[29] TCC_REQ[29] TCC_HIT[30] TCC_MISS[30] TCC_READ[30] TCC_REQ[30] TCC_HIT[31] TCC_MISS[31] TCC_READ[31] TCC_REQ[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_18.txt b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_18.txt new file mode 100644 index 0000000000..a74cefd281 --- /dev/null +++ b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_18.txt @@ -0,0 +1,5 @@ +pmc: TCC_RW_REQ[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_RW_REQ[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_WRITE[1] TCC_RW_REQ[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_WRITE[2] TCC_RW_REQ[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_WRITE[3] TCC_RW_REQ[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_WRITE[4] TCC_RW_REQ[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_WRITE[5] TCC_RW_REQ[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_WRITE[6] TCC_RW_REQ[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_WRITE[7] TCC_RW_REQ[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_WRITE[8] TCC_RW_REQ[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_WRITE[9] TCC_RW_REQ[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_WRITE[10] TCC_RW_REQ[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_WRITE[11] TCC_RW_REQ[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_WRITE[12] TCC_RW_REQ[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_WRITE[13] TCC_RW_REQ[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_WRITE[14] TCC_RW_REQ[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_WRITE[15] TCC_RW_REQ[16] TCC_TOO_MANY_EA_WRREQS_STALL[16] TCC_WRITE[16] TCC_RW_REQ[17] TCC_TOO_MANY_EA_WRREQS_STALL[17] TCC_WRITE[17] TCC_RW_REQ[18] TCC_TOO_MANY_EA_WRREQS_STALL[18] TCC_WRITE[18] TCC_RW_REQ[19] TCC_TOO_MANY_EA_WRREQS_STALL[19] TCC_WRITE[19] TCC_RW_REQ[20] TCC_TOO_MANY_EA_WRREQS_STALL[20] TCC_WRITE[20] TCC_RW_REQ[21] TCC_TOO_MANY_EA_WRREQS_STALL[21] TCC_WRITE[21] TCC_RW_REQ[22] TCC_TOO_MANY_EA_WRREQS_STALL[22] TCC_WRITE[22] TCC_RW_REQ[23] TCC_TOO_MANY_EA_WRREQS_STALL[23] TCC_WRITE[23] TCC_RW_REQ[24] TCC_TOO_MANY_EA_WRREQS_STALL[24] TCC_WRITE[24] TCC_RW_REQ[25] TCC_TOO_MANY_EA_WRREQS_STALL[25] TCC_WRITE[25] TCC_RW_REQ[26] TCC_TOO_MANY_EA_WRREQS_STALL[26] TCC_WRITE[26] TCC_RW_REQ[27] TCC_TOO_MANY_EA_WRREQS_STALL[27] TCC_WRITE[27] TCC_RW_REQ[28] TCC_TOO_MANY_EA_WRREQS_STALL[28] TCC_WRITE[28] TCC_RW_REQ[29] TCC_TOO_MANY_EA_WRREQS_STALL[29] TCC_WRITE[29] TCC_RW_REQ[30] TCC_TOO_MANY_EA_WRREQS_STALL[30] TCC_WRITE[30] TCC_RW_REQ[31] TCC_TOO_MANY_EA_WRREQS_STALL[31] TCC_WRITE[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_2.txt b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_2.txt new file mode 100644 index 0000000000..70b69f8928 --- /dev/null +++ b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_2.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_MUL_F32 SQ_INSTS_VALU_FMA_F32 SQ_INSTS_VALU_TRANS_F32 SQ_INSTS_VALU_ADD_F64 SQ_INSTS_VALU_MUL_F64 SQ_INSTS_VALU_FMA_F64 SQ_INSTS_VALU_TRANS_F64 SQ_INSTS_VALU_INT32 TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum TA_BUFFER_ATOMIC_WAVEFRONTS_sum TA_BUFFER_TOTAL_CYCLES_sum TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_3.txt b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_3.txt new file mode 100644 index 0000000000..e47f8e33c9 --- /dev/null +++ b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_3.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_INT64 SQ_INSTS_SMEM SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum TD_COALESCABLE_WAVEFRONT_sum SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE CPF_CMP_UTCL1_STALL_ON_TRANSLATION TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_4.txt b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_4.txt new file mode 100644 index 0000000000..2d96f365a9 --- /dev/null +++ b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_4.txt @@ -0,0 +1,5 @@ +pmc: SQ_WAVE_CYCLES SQ_WAIT_ANY SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_BUSY_CU_CYCLES SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE TCC_EA_WRREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WR_UNCACHED_32B_sum TCC_EA_WRREQ_DRAM_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_5.txt b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_5.txt new file mode 100644 index 0000000000..e50beed390 --- /dev/null +++ b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_5.txt @@ -0,0 +1,5 @@ +pmc: SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU TCP_TCP_LATENCY_sum TCP_TCC_READ_REQ_LATENCY_sum TCP_TCC_WRITE_REQ_LATENCY_sum TCP_TCC_READ_REQ_sum TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN CPC_ME1_DC0_SPI_BUSY TCC_EA_WRREQ_STALL_sum TCC_EA_RDREQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RD_UNCACHED_32B_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_6.txt b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_6.txt new file mode 100644 index 0000000000..15a2277c1b --- /dev/null +++ b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_6.txt @@ -0,0 +1,5 @@ +pmc: SQ_THREAD_CYCLES_VALU SQ_IFETCH SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TCP_TCC_NC_READ_REQ_sum TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN TCC_EA_RDREQ_DRAM_sum TCC_TAG_STALL_sum TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_7.txt b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_7.txt new file mode 100644 index 0000000000..b42ce91618 --- /dev/null +++ b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_7.txt @@ -0,0 +1,5 @@ +pmc: SQ_WAVES_LT_32 SQ_WAVES_LT_16 SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TCP_TCC_UC_WRITE_REQ_sum TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR TCC_NORMAL_EVICT_sum TCC_ALL_TC_OP_INV_EVICT_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA_ATOMIC_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_8.txt b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_8.txt new file mode 100644 index 0000000000..21d4c7a998 --- /dev/null +++ b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_8.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM_NORM SQ_INSTS_MFMA SQ_INSTS_VALU_MFMA_I8 SQ_INSTS_VALU_MFMA_F16 SQ_INSTS_VALU_MFMA_BF16 SQ_INSTS_VALU_MFMA_F32 SQ_INSTS_VALU_MFMA_F64 SQ_VALU_MFMA_BUSY_CYCLES TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TCP_TCC_CC_ATOMIC_REQ_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN TCC_EA_RDREQ_LEVEL_sum TCC_EA_WRREQ_LEVEL_sum TCC_EA_ATOMIC_LEVEL_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_9.txt b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_9.txt new file mode 100644 index 0000000000..9ffe5778c3 --- /dev/null +++ b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_9.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_FLAT_LDS_ONLY SQ_INSTS_VALU_MFMA_MOPS_I8 SQ_INSTS_VALU_MFMA_MOPS_F16 SQ_INSTS_VALU_MFMA_MOPS_BF16 SQ_INSTS_VALU_MFMA_MOPS_F32 SQ_INSTS_VALU_MFMA_MOPS_F64 SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum TCP_PENDING_STALL_CYCLES_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_4/MI200/perfmon/timestamps.txt b/tests/workloads/kernel_verbose_4/MI200/perfmon/timestamps.txt new file mode 100644 index 0000000000..676cca1b80 --- /dev/null +++ b/tests/workloads/kernel_verbose_4/MI200/perfmon/timestamps.txt @@ -0,0 +1,5 @@ +pmc: + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_4/MI200/pmc_perf.csv b/tests/workloads/kernel_verbose_4/MI200/pmc_perf.csv new file mode 100644 index 0000000000..8b0348920b --- /dev/null +++ b/tests/workloads/kernel_verbose_4/MI200/pmc_perf.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,wave_size_1,obj_1,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_2,obj_2,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_DRAM_sum,TCC_TAG_STALL_sum,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,wave_size_3,obj_3,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_4,obj_4,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,TD_COALESCABLE_WAVEFRONT_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_5,obj_5,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_6,obj_6,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_7,obj_7,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_8,obj_8,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,TCC_EA_ATOMIC_LEVEL_sum,wave_size_9,obj_9,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_10,obj_10,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_11,obj_11,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_12,obj_12,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_13,obj_13,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_14,obj_14,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,wave_size_15,obj_15,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_16,obj_16,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_17,obj_17,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_18,obj_18,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f2f6e5b4ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65551.0,0.0,0.0,0.0,64,0x7fd81e810ec0,227888,130668,16384,0,16384,16384,32768,49152,28485,28485,1976915.0,1346731.0,3502.0,162005.0,1058194.0,0.0,1338074.0,1038757.0,226177,138808,28485,0,28485,0,911520.0,492133.0,0.0,0.0,64,0x7f5244f38ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131081.0,35133.0,45994.0,19542.0,64,0x7fbd9d184ec0,6332,0,4096,6379,0,4096,6385,0,4096,6388,0,4096,6379,0,4096,6415,0,4096,6342,0,4096,6402,0,4096,6405,0,4096,6337,0,4096,6381,0,4096,6386,0,4096,6389,0,4096,6384,0,4096,6416,0,4096,6345,0,4096,6395,0,4096,6400,0,4096,6366,0,4096,6365,0,4096,6388,0,4096,6398,0,4096,6379,0,4096,6572,0,4096,6406,0,4096,6395,0,4096,6409,0,4096,6371,0,4096,6366,0,4096,6392,0,4096,6397,0,4096,6382,0,4096,64,0x7fe272f00ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,10615,0,815,28216,0,72438.0,131072.0,0.0,65568.0,64,0x7f536aeecec0,32768,32768,0,64,0x7f50437bcec0,10803107,9669253,789790,344064,1627540,0,0,163840,832.0,515140.0,0.0,524288.0,250900.0,32768.0,494328,0,0,11207,131072.0,131072.0,0.0,131072.0,64,0x7f641ab38ec0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,9,0,4096,0,0,0,4096,0,173,0,4096,0,69,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,24,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,14,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4099,0,0,0,4096,0,0,0,4096,0,40,0,4096,0,21,0,4096,0,0,0,4101,0,21,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,64,0x7f248ac6cec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,39939937.0,34902096.0,0.0,64,0x7fd0cb6bcec0,0,0,0,0,0,0,168,56,131072.0,131072.0,0.0,978039.0,64,0x7f5d6ba58ec0,0,1295420,4096,4096,0,1267420,4096,4096,0,1137361,4096,4096,0,1292375,4096,4096,0,1394049,4096,4096,0,1413718,4096,4096,0,1282078,4096,4096,0,1406440,4096,4096,0,1175897,4096,4096,0,1175191,4096,4096,0,1141265,4096,4096,0,1084551,4096,4096,0,1233535,4096,4096,0,1292197,4096,4096,0,1082658,4096,4096,0,1525718,4096,4096,0,1076275,4096,4096,0,1246682,4096,4096,0,1028374,4096,4096,0,1422522,4096,4096,0,1140737,4096,4096,0,1184374,4096,4096,0,1256059,4096,4096,0,1335820,4096,4096,0,1578280,4096,4096,0,961057,4096,4096,0,1286633,4096,4096,0,1199648,4096,4096,0,1284892,4096,4096,0,1057368,4096,4096,0,1091224,4096,4096,0,1293848,4096,4096,64,0x7f9ae5d50ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13652,19180,8940,545,0,28065,204169.0,0.0,73088.0,131081.0,64,0x7f909e244ec0,0,0,0,224,0,65536,64267,56,64,0x7f529fde8ec0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,64,0x7f1acd934ec0,114688,0,32768,32768,16384,16384,65536,49152,26699351.0,81413137.0,36824372.0,131072.0,0.0,225596.0,0,0,14858,766.0,131082.0,0.0,12.0,64,0x7f87d1384ec0,2298,4096,2298,6394,2303,4096,2303,6399,2252,4096,2252,6348,2286,4096,2286,6382,2315,4096,2315,6411,2298,4096,2298,6394,2287,4096,2287,6383,2259,4096,2259,6355,2261,4096,2261,6357,2303,4097,2304,6400,2307,4096,2307,6403,2312,4097,2313,6409,2285,4096,2285,6381,2313,4096,2313,6409,2300,4096,2300,6396,2287,4096,2287,6383,2264,4096,2264,6360,2249,4096,2249,6345,2303,4097,2304,6400,2332,4096,2332,6428,2291,4096,2291,6387,2270,4096,2270,6366,2272,4096,2272,6368,2485,4098,2487,6583,2321,4096,2321,6417,2260,4096,2260,6356,2253,4096,2253,6349,2302,4101,2307,6403,2333,4096,2333,6429,2297,4096,2297,6393,2277,4096,2277,6373,2272,4096,2272,6368,64,0x7fca9853cec0,0,393216,163840,0,0,0,0,0,18303,0.0,0.0,0.0,32768.0,0.0,0.0,415.0,32768.0,4096,16384,352,29242,2021,0,56.0,6.0,0.0,204400.0,64,0x7f2c3627cec0,0,0,0,1060710,44,0,0,1106360,0,0,0,1081222,0,0,0,1023260,3,0,0,1106282,0,0,0,1070725,0,0,0,1020710,0,0,0,1174527,0,0,0,1011182,0,0,0,1042669,87,0,0,1092404,0,0,0,1052883,0,0,0,1058866,0,0,0,1064453,0,0,0,1060598,0,0,0,1107483,0,0,0,1068967,0,0,0,1145100,0,0,0,985717,0,0,0,1077602,20,0,0,1070334,0,0,0,1086426,99,0,0,1149875,0,0,0,1046518,0,0,0,1006129,0,0,0,1105596,0,0,0,1178090,0,0,0,1109748,0,0,0,1010572,0,0,0,1055077,0,0,0,1091509,26,0,0,1148206,64,0x7f7fc6578ec0,1296,119602,0,0,65536,63800,56,1680,199749380764970,199749380785450 +1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f2f6e5b4ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65552.0,0.0,0.0,0.0,64,0x7fd81e810ec0,329112,222763,16384,0,16384,16384,32768,49152,41138,41138,3173212.0,2449003.0,5326.0,375837.0,1713794.0,0.0,2437206.0,2129038.0,329104,232059,41138,0,41138,0,1316416.0,773783.0,0.0,0.0,64,0x7f5244f38ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131080.0,93570.0,45609.0,0.0,64,0x7fbd9d184ec0,6276,0,4096,6262,0,4096,6274,0,4096,6234,0,4096,6248,0,4096,6292,0,4096,6255,0,4096,6259,0,4096,6260,0,4096,6281,0,4096,6265,0,4096,6268,0,4096,6236,0,4096,6249,0,4096,6293,0,4096,6255,0,4096,6259,0,4096,6272,0,4096,6264,0,4096,6243,0,4096,6266,0,4096,6289,0,4096,6261,0,4096,6238,0,4096,6239,0,4096,6263,0,4096,6275,0,4096,6262,0,4096,6247,0,4096,6266,0,4096,6292,0,4096,6264,0,4096,64,0x7fe272f00ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,16985,0,819,36469,0,69196.0,131072.0,0.0,45529.0,64,0x7f536aeecec0,32768,32768,0,64,0x7f50437bcec0,19630104,18288855,997185,344064,2813658,0,0,163840,832.0,515166.0,0.0,524288.0,568327.0,32768.0,1013168,0,0,13706,90994.0,90994.0,0.0,90994.0,64,0x7f641ab38ec0,4096,0,0,0,4096,0,3,0,4096,0,314,0,4096,0,163,0,4096,0,994,0,4096,0,566,0,4096,0,0,0,4096,0,423,0,4096,0,537,0,4096,0,217,0,4098,0,3,0,4096,0,1190,0,4096,0,189,0,4096,0,687,0,4096,0,256,0,4097,0,300,0,4097,0,0,0,4096,0,513,0,4097,0,290,0,4096,0,1145,0,4096,0,981,0,4096,0,578,0,4096,0,437,0,4096,0,474,0,4096,0,88,0,4096,0,21,0,4096,0,3,0,4096,0,211,0,4101,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,64,0x7f248ac6cec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,119451113.0,60267847.0,0.0,64,0x7fd0cb6bcec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,1976955.0,64,0x7f5d6ba58ec0,0,2939690,2820,2820,0,3426253,2868,2868,0,4013036,2860,2860,0,3841543,2868,2868,0,3112428,2890,2890,0,4302886,2852,2852,0,2904736,2888,2888,0,3725742,2824,2824,0,3264165,2824,2824,0,3233772,2824,2824,0,4304458,2868,2868,0,3540582,2860,2860,0,3720780,2868,2868,0,3554590,2892,2892,0,3827770,2852,2852,0,3146264,2888,2888,0,3211063,2842,2842,0,4188618,2876,2876,0,2949166,2836,2836,0,5277715,2832,2832,0,4832339,2836,2836,0,4745132,2884,2884,0,4603028,2840,2840,0,3605773,2840,2840,0,3654437,2844,2844,0,2909567,2838,2838,0,4004989,2876,2876,0,3367918,2836,2836,0,3277015,2828,2828,0,3135925,2840,2840,0,3735874,2896,2896,0,3432476,2830,2830,64,0x7f9ae5d50ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,30999,27117,9916,2983,0,39213,200295.0,0.0,69211.0,131084.0,64,0x7f909e244ec0,0,0,0,56,0,65536,65536,0,64,0x7f529fde8ec0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,64,0x7f1acd934ec0,114688,0,32768,32768,16384,16384,65536,49152,58198192.0,205684795.0,51659496.0,131072.0,0.0,571037.0,0,0,25370,2998.0,131083.0,0.0,20.0,64,0x7f87d1384ec0,2167,4096,2167,6263,2151,4096,2151,6247,2163,4096,2163,6259,2155,4096,2155,6251,2212,4096,2212,6308,2163,4096,2163,6259,2164,4096,2164,6260,2166,4096,2166,6262,2167,4096,2167,6263,2172,4097,2173,6269,2156,4097,2157,6253,2221,4097,2222,6318,2163,4096,2163,6259,2215,4096,2215,6311,2170,4096,2170,6266,2167,4096,2167,6263,2171,4097,2172,6268,2159,4096,2159,6255,2158,4097,2159,6255,2141,4096,2141,6237,2157,4096,2157,6253,2176,4096,2176,6272,2167,4096,2167,6263,2163,4096,2163,6259,2159,4096,2159,6255,2170,4096,2170,6266,2165,4096,2165,6261,2163,4099,2166,6262,2145,4098,2147,6243,2159,4096,2159,6255,2180,4096,2180,6276,2171,4096,2171,6267,64,0x7fca9853cec0,0,393216,163840,0,0,0,0,0,29627,0.0,0.0,0.0,32768.0,0.0,0.0,228.0,32768.0,4096,16384,302,41430,2065,0,56.0,10.0,0.0,200867.0,64,0x7f2c3627cec0,0,0,0,1660978,576,0,0,2205430,0,0,0,1691927,134,0,0,2178102,0,0,0,1866592,681,0,0,2193488,0,0,0,1450222,6,0,0,1973301,0,0,0,1503169,0,0,0,1730254,96,0,0,2004579,26,0,0,1890497,305,0,0,1860881,0,0,0,1804412,379,0,0,2093422,0,0,0,1697503,0,0,0,1693186,0,0,0,1919436,0,0,0,1443628,157,0,0,2134344,67,0,0,1804613,0,0,0,1678333,0,0,0,1758987,0,0,0,1759137,0,0,0,1736394,0,0,0,1312740,0,0,0,1483042,537,0,0,2437421,0,0,0,2065350,0,0,0,1873346,139,0,0,1655597,0,0,0,1748383,64,0x7f7fc6578ec0,0,186018,0,0,65536,63800,56,1680,199749381010410,199749381026730 +2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f2f6e5b4ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65552.0,0.0,0.0,0.0,64,0x7fd81e810ec0,330560,222288,16384,0,16384,16384,32768,49152,41319,41319,3167403.0,2420097.0,4960.0,320846.0,1624577.0,0.0,2408196.0,2100449.0,330552,232125,41319,0,41319,0,1322208.0,764152.0,0.0,0.0,64,0x7f5244f38ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131081.0,135279.0,45600.0,0.0,64,0x7fbd9d184ec0,6295,0,4096,6280,0,4096,6314,0,4096,6266,0,4096,6284,0,4096,6263,0,4096,6259,0,4096,6262,0,4096,6265,0,4096,6296,0,4096,6279,0,4096,6315,0,4096,6268,0,4096,6289,0,4096,6261,0,4096,6263,0,4096,6285,0,4096,6279,0,4096,6292,0,4096,6287,0,4096,6294,0,4096,6308,0,4096,6261,0,4096,6274,0,4096,6271,0,4096,6289,0,4096,6277,0,4096,6296,0,4096,6287,0,4096,6296,0,4096,6311,0,4096,6262,0,4096,64,0x7fe272f00ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,20942,0,3127,38145,0,69565.0,131072.0,0.0,45440.0,64,0x7f536aeecec0,32768,32768,0,64,0x7f50437bcec0,19619179,18010368,1264747,344064,2830893,0,0,163840,832.0,515153.0,0.0,524288.0,524080.0,32768.0,1000691,0,0,13989,91164.0,91164.0,0.0,91164.0,64,0x7f641ab38ec0,4096,0,1141,0,4096,0,539,0,4096,0,2224,0,4096,0,1394,0,4096,0,218,0,4096,0,407,0,4096,0,1222,0,4096,0,1121,0,4096,0,979,0,4096,0,33,0,4098,0,314,0,4096,0,852,0,4096,0,1812,0,4096,0,546,0,4096,0,161,0,4097,0,325,0,4097,0,447,0,4096,0,259,0,4097,0,431,0,4096,0,793,0,4096,0,1301,0,4096,0,1185,0,4096,0,11,0,4096,0,1400,0,4096,0,28,0,4096,0,454,0,4096,0,553,0,4096,0,336,0,4101,0,31,0,4096,0,1365,0,4096,0,522,0,4096,0,382,0,64,0x7f248ac6cec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,117603812.0,58363570.0,0.0,64,0x7fd0cb6bcec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2044775.0,64,0x7f5d6ba58ec0,0,3387149,2812,2812,0,3672773,2846,2846,0,5032810,2852,2852,0,4135074,2844,2844,0,3299394,2916,2916,0,3858099,2864,2864,0,2681232,2884,2884,0,3352298,2836,2836,0,3203452,2832,2832,0,3320733,2818,2818,0,2943999,2846,2846,0,4470664,2848,2848,0,4323946,2844,2844,0,3199954,2916,2916,0,3732372,2860,2860,0,2952493,2884,2884,0,3387769,2824,2824,0,3421718,2864,2864,0,3213328,2844,2844,0,3671925,2816,2816,0,3649922,2824,2824,0,4162166,2864,2864,0,3739001,2860,2860,0,3944805,2852,2852,0,4077494,2848,2848,0,3294647,2816,2816,0,3254687,2864,2864,0,3414766,2844,2844,0,4710619,2820,2820,0,4307580,2824,2824,0,3322530,2876,2876,0,3601901,2864,2864,64,0x7f9ae5d50ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,34917,28899,9771,3687,0,40769,201084.0,0.0,70000.0,131084.0,64,0x7f909e244ec0,0,0,0,56,0,65536,65536,0,64,0x7f529fde8ec0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,64,0x7f1acd934ec0,114688,0,32768,32768,16384,16384,65536,49152,56702455.0,195105281.0,42665129.0,131072.0,0.0,486307.0,0,0,24543,3941.0,131084.0,0.0,22.0,64,0x7f87d1384ec0,2160,4096,2160,6256,2148,4096,2148,6244,2152,4096,2152,6248,2121,4096,2121,6217,2159,4096,2159,6255,2169,4096,2169,6265,2158,4096,2158,6254,2146,4096,2146,6242,2146,4096,2146,6242,2165,4097,2166,6262,2157,4097,2158,6254,2210,4097,2211,6307,2123,4096,2123,6219,2160,4096,2160,6256,2170,4096,2170,6266,2165,4096,2165,6261,2206,4097,2207,6303,2206,4096,2206,6302,2160,4097,2161,6257,2161,4096,2161,6257,2144,4096,2144,6240,2128,4096,2128,6224,2152,4096,2152,6248,2158,4096,2158,6254,2164,4096,2164,6260,2203,4096,2203,6299,2208,4096,2208,6304,2159,4098,2161,6257,2166,4098,2168,6264,2152,4096,2152,6248,2132,4096,2132,6228,2156,4096,2156,6252,64,0x7fca9853cec0,0,393216,163840,0,0,0,0,0,29902,0.0,0.0,0.0,32768.0,0.0,0.0,242.0,32768.0,4096,16384,302,41638,2021,0,56.0,10.0,0.0,200309.0,64,0x7f2c3627cec0,25,0,0,1677051,460,0,0,2286718,1087,0,0,2304846,2273,0,0,2698650,169,0,0,2297086,581,0,0,2136583,16,0,0,1452752,439,0,0,2400393,1133,0,0,2316866,26,0,0,1703628,523,0,0,1862380,706,0,0,1963481,894,0,0,2059243,0,0,0,2044577,362,0,0,2229000,213,0,0,2271334,252,0,0,2187217,2348,0,0,2658178,0,0,0,1572261,666,0,0,2486274,1038,0,0,2113109,493,0,0,2198353,75,0,0,1981269,0,0,0,1728361,64,0,0,2162060,493,0,0,2011829,1571,0,0,2421765,0,0,0,1732236,318,0,0,2110194,1059,0,0,1795396,649,0,0,2356621,0,0,0,1658749,64,0x7f7fc6578ec0,0,186203,0,0,65536,63800,56,1680,199749381056970,199749381072490 diff --git a/tests/workloads/kernel_verbose_4/MI200/roofline.csv b/tests/workloads/kernel_verbose_4/MI200/roofline.csv new file mode 100644 index 0000000000..b13d4fb9f2 --- /dev/null +++ b/tests/workloads/kernel_verbose_4/MI200/roofline.csv @@ -0,0 +1,5 @@ +device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh +0,1388.7625,1388.2411,1389.2838,5016.5361,5013.605,5019.4673,9223.2041,9222.5723,9223.8359,18050.207,18049.324,18051.09,20932.619,20872.697,20992.541,20263.148,20262.469,20263.828,170389.42,170384.58,170394.27,164857.81,164852.52,164863.11,41419.113,41418.391,41419.836,41478.637,41477.973,41479.301,166324,165836.27,166811.73 +1,1389.254,1388.6711,1389.8369,5027.2559,5025.0059,5029.5059,9233.7461,9233.0928,9234.3994,18092.617,18089.189,18096.045,20975.557,20909.123,21041.99,20295.359,20294.771,20295.947,170836.59,170832.16,170841.03,165098.92,165095.12,165102.72,41481.727,41480.871,41482.582,41535.816,41534.801,41536.832,166838.17,166834.67,166841.67 +2,1389.1714,1388.6238,1389.719,5036.0137,5033.8647,5038.1626,9259.9805,9259.0732,9260.8877,18106.842,18105.809,18107.875,21048.09,21047.76,21048.42,20353.053,20352.539,20353.566,171123.58,171119.7,171127.45,165503.53,165499.88,165507.19,41580.453,41579.621,41581.285,41638.012,41637.074,41638.949,166947.05,166360.5,167533.59 +3,1388.7527,1388.2761,1389.2292,5031.7871,5030.4165,5033.1577,9241.7812,9241.1855,9242.377,18022.385,18018.469,18026.301,21035.93,21035.412,21036.447,20313.078,20312.459,20313.697,171051.62,171047.64,171055.61,165233.8,165228.7,165238.89,41440.371,41288.145,41592.598,41582.023,41581.367,41582.68,167017.52,167015.72,167019.31 diff --git a/tests/workloads/kernel_verbose_4/MI200/sysinfo.csv b/tests/workloads/kernel_verbose_4/MI200/sysinfo.csv new file mode 100644 index 0000000000..b1bdbe022e --- /dev/null +++ b/tests/workloads/kernel_verbose_4/MI200/sysinfo.csv @@ -0,0 +1,2 @@ +workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd +kernel_verbose_4,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 02:40:03 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/kernel_verbose_4/MI200/timestamps.csv b/tests/workloads/kernel_verbose_4/MI200/timestamps.csv new file mode 100644 index 0000000000..48347d8de1 --- /dev/null +++ b/tests/workloads/kernel_verbose_4/MI200/timestamps.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,352810,352810,1048576,256,0,0,8,0,16,64,0x0,0x7f9958dd8ec0,199749380736229,199749380764970,199749380785450,199749380797865 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,352810,352810,1048576,256,0,0,8,0,16,64,0x0,0x7f9958dd8ec0,199749380796593,199749381010410,199749381026730,199749381028502 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,352810,352810,1048576,256,0,0,8,0,16,64,0x0,0x7f9958dd8ec0,199749381037980,199749381056970,199749381072490,199749381073997 diff --git a/tests/workloads/kernel_verbose_5/MI100/SQ_IFETCH_LEVEL.csv b/tests/workloads/kernel_verbose_5/MI100/SQ_IFETCH_LEVEL.csv index 1248227d5d..19b9118e94 100644 --- a/tests/workloads/kernel_verbose_5/MI100/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/kernel_verbose_5/MI100/SQ_IFETCH_LEVEL.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,2887854,2887854,1048576,256,0,0,8,8,16,64,0x0,0x7f71bd1fae80,48330,48330,16384,65536,12717,1644360,2187922897764055,2187922015837329,2187922015861489,2187922905324719 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,2887854,2887854,1048576,256,0,0,8,8,16,64,0x0,0x7f71bd1fae80,43223,43223,16384,65536,8223,1048592,2187922905347101,2187922015985649,2187922016004529,2187922905672040 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,2887854,2887854,1048576,256,0,0,8,8,16,64,0x0,0x7f71bd1fae80,44791,44791,16384,65536,8428,1048576,2187922905705223,2187922016025809,2187922016044849,2187922905886102 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,189129,189129,1048576,256,0,0,8,8,16,64,0x0,0x7f1e88b78e80,47888,47888,16384,65536,14433,1862592,194327668479458,194339836161015,194339836185335,194327676337277 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,189129,189129,1048576,256,0,0,8,8,16,64,0x0,0x7f1e88b78e80,43039,43039,16384,65536,8098,1048584,194327676358677,194339836365335,194339836384535,194327676683011 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,189129,189129,1048576,256,0,0,8,8,16,64,0x0,0x7f1e88b78e80,42802,42802,16384,65536,8330,1048576,194327676715643,194339836406935,194339836425975,194327676893850 diff --git a/tests/workloads/kernel_verbose_5/MI100/SQ_INST_LEVEL_LDS.csv b/tests/workloads/kernel_verbose_5/MI100/SQ_INST_LEVEL_LDS.csv index e1cf082f10..7788abc5e0 100644 --- a/tests/workloads/kernel_verbose_5/MI100/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/kernel_verbose_5/MI100/SQ_INST_LEVEL_LDS.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,2884392,2884392,1048576,256,0,0,8,8,16,64,0x0,0x7fcf7498ce80,0,0,0,2187913007219260,2187922015837329,2187922015861489,2187913014707707 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,2884392,2884392,1048576,256,0,0,8,8,16,64,0x0,0x7fcf7498ce80,0,0,0,2187913014725911,2187922015985649,2187922016004529,2187913015043928 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,2884392,2884392,1048576,256,0,0,8,8,16,64,0x0,0x7fcf7498ce80,0,0,0,2187913015072262,2187922016025809,2187922016044849,2187913015249895 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,189312,189312,1048576,256,0,0,8,8,16,64,0x0,0x7fad7f8bae80,0,0,0,194328163709266,194339836161015,194339836185335,194328171429995 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,189312,189312,1048576,256,0,0,8,8,16,64,0x0,0x7fad7f8bae80,0,0,0,194328171450363,194339836365335,194339836384535,194328171753527 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,189312,189312,1048576,256,0,0,8,8,16,64,0x0,0x7fad7f8bae80,0,0,0,194328171783003,194339836406935,194339836425975,194328171979305 diff --git a/tests/workloads/kernel_verbose_5/MI100/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/kernel_verbose_5/MI100/SQ_INST_LEVEL_SMEM.csv index 18f671544f..aabdafc9b1 100644 --- a/tests/workloads/kernel_verbose_5/MI100/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/kernel_verbose_5/MI100/SQ_INST_LEVEL_SMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,2884938,2884938,1048576,256,0,0,8,8,16,64,0x0,0x7fe3e521ee80,65536,206022,26440464,2187914587782605,2187922015837329,2187922015861489,2187914595345833 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,2884938,2884938,1048576,256,0,0,8,8,16,64,0x0,0x7fe3e521ee80,65536,191302,24448192,2187914595365179,2187922015985649,2187922016004529,2187914595667957 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,2884938,2884938,1048576,256,0,0,8,8,16,64,0x0,0x7fe3e521ee80,65536,185914,23818016,2187914595696932,2187922016025809,2187922016044849,2187914595866861 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,189497,189497,1048576,256,0,0,8,8,16,64,0x0,0x7f84a049ae80,65536,212580,27329616,194328661888318,194339836161015,194339836185335,194328669468581 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,189497,189497,1048576,256,0,0,8,8,16,64,0x0,0x7f84a049ae80,65536,174110,22221416,194328669488829,194339836365335,194339836384535,194328669746277 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,189497,189497,1048576,256,0,0,8,8,16,64,0x0,0x7f84a049ae80,65536,175038,22381160,194328669774400,194339836406935,194339836425975,194328669923212 diff --git a/tests/workloads/kernel_verbose_5/MI100/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/kernel_verbose_5/MI100/SQ_INST_LEVEL_VMEM.csv index 200ce30e23..f1372153bd 100644 --- a/tests/workloads/kernel_verbose_5/MI100/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/kernel_verbose_5/MI100/SQ_INST_LEVEL_VMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,2886214,2886214,1048576,256,0,0,8,8,16,64,0x0,0x7f115046ce80,32768,655158,83860692,2187918626848987,2187922015837329,2187922015861489,2187918634311747 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,2886214,2886214,1048576,256,0,0,8,8,16,64,0x0,0x7f115046ce80,32768,681403,87235228,2187918634330652,2187922015985649,2187922016004529,2187918634742656 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,2886214,2886214,1048576,256,0,0,8,8,16,64,0x0,0x7f115046ce80,32768,662971,84848596,2187918634771299,2187922016025809,2187922016044849,2187918634944234 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,189683,189683,1048576,256,0,0,8,8,16,64,0x0,0x7f75c51c0e80,32768,655761,83926252,194329155359106,194339836161015,194339836185335,194329163428154 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,189683,189683,1048576,256,0,0,8,8,16,64,0x0,0x7f75c51c0e80,32768,661507,84658544,194329163446258,194339836365335,194339836384535,194329163755814 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,189683,189683,1048576,256,0,0,8,8,16,64,0x0,0x7f75c51c0e80,32768,665810,85240480,194329163783727,194339836406935,194339836425975,194329163954160 diff --git a/tests/workloads/kernel_verbose_5/MI100/SQ_LEVEL_WAVES.csv b/tests/workloads/kernel_verbose_5/MI100/SQ_LEVEL_WAVES.csv index 8db0a506ef..69ee17fcd3 100644 --- a/tests/workloads/kernel_verbose_5/MI100/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/kernel_verbose_5/MI100/SQ_LEVEL_WAVES.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,2885485,2885485,1048576,256,0,0,8,8,16,64,0x0,0x7f88c1c54e80,48651,48651,17511,389216,16384,25525138,237905,0,102598448,2187916174956229,2187922015837329,2187922015861489,2187916182460807 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,2885485,2885485,1048576,256,0,0,8,8,16,64,0x0,0x7f88c1c54e80,43349,43349,14232,346800,16384,24473253,233441,0,98383328,2187916182490753,2187922015985649,2187922016004529,2187916182803049 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,2885485,2885485,1048576,256,0,0,8,8,16,64,0x0,0x7f88c1c54e80,43525,43525,13895,348208,16384,25721040,238149,0,103376212,2187916182841271,2187922016025809,2187922016044849,2187916183037389 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,189868,189868,1048576,256,0,0,8,8,16,64,0x0,0x7f48053c0e80,47704,47704,17048,381640,16384,25028052,232701,0,100607848,194329650334392,194339836161015,194339836185335,194329658009754 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,189868,189868,1048576,256,0,0,8,8,16,64,0x0,0x7f48053c0e80,42903,42903,13930,343232,16384,24547026,230432,0,98677920,194329658036545,194339836365335,194339836384535,194329658400675 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,189868,189868,1048576,256,0,0,8,8,16,64,0x0,0x7f48053c0e80,42215,42215,13410,337728,16384,24070442,226068,0,96775756,194329658439689,194339836406935,194339836425975,194329658670235 diff --git a/tests/workloads/kernel_verbose_5/MI100/pmc_dispatch_info.csv b/tests/workloads/kernel_verbose_5/MI100/pmc_dispatch_info.csv new file mode 100644 index 0000000000..2166cd6fad --- /dev/null +++ b/tests/workloads/kernel_verbose_5/MI100/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/kernel_verbose_5/MI100/pmc_perf.csv b/tests/workloads/kernel_verbose_5/MI100/pmc_perf.csv index 5de17d9d9a..ee0800033b 100644 --- a/tests/workloads/kernel_verbose_5/MI100/pmc_perf.csv +++ b/tests/workloads/kernel_verbose_5/MI100/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_1,obj_1,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_2,obj_2,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_3,obj_3,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_4,obj_4,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_5,obj_5,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_6,obj_6,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_7,obj_7,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_8,obj_8,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_9,obj_9,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_10,obj_10,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_11,obj_11,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_12,obj_12,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_13,obj_13,TCC_EA_ATOMIC_LEVEL_sum,wave_size_14,obj_14,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_15,obj_15,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_16,obj_16,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f6498f94e80,4096,0,1643,0,4096,0,1733,0,4096,0,1615,0,4102,0,454,0,4096,0,6712,0,4096,0,933,0,4096,0,5673,0,4098,0,4037,0,4096,0,1492,0,4096,0,3378,0,4096,0,1082,0,4144,0,2476,0,4096,0,1876,0,4096,0,3718,0,4096,0,611,0,4096,0,0,0,4096,0,436,0,4096,0,5095,0,4096,0,1043,0,4096,0,4138,0,4096,0,1667,0,4096,0,605,0,4096,0,895,0,4096,0,541,0,4096,0,1367,0,4096,0,705,0,4096,0,2402,0,4144,0,260,0,4096,0,490,0,4096,0,44,0,4096,0,242,0,4096,0,417,0,64,0x7f59a5096e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131305.0,0.0,458.0,131304.0,64,0x7f5d2c2f6e80,4829,0,0,2129266,2363,0,0,1882798,2896,0,0,1736714,1879,0,0,1725295,2908,0,0,1975519,4533,0,0,2126419,3027,0,0,1856901,732,0,0,1708569,1018,0,0,1552172,1458,0,0,1725024,2060,0,0,1819178,444,0,0,1588564,2423,0,0,1954435,2019,0,0,1813218,2065,0,0,1795262,1636,0,0,1770592,2935,0,0,1912590,3223,0,0,2023705,3999,0,0,2071622,2245,0,0,1874014,2745,0,0,1795405,752,0,0,1585128,2873,0,0,1896431,8830,0,0,2375300,2088,0,0,1867078,1781,0,0,1799401,1697,0,0,1811871,1570,0,0,1771462,2656,0,0,1800735,1853,0,0,1770382,3548,0,0,1939050,937,0,0,1683685,64,0x7f832b1dce80,206730,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,14057,30441,9907,550,0,47557,262713.0,0.0,188.0,262525.0,64,0x7ffbc7a20e80,8192,0,4096,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f404524ee80,377648,228791,3325353,16384,24458783,144,48,0,47205,47205,3784508.0,2939974.0,4713.0,1101060.0,2167040.0,0.0,2931222.0,2623154.0,376255,238738,47205,0,47205,0,1510560.0,964914.0,0.0,0.0,64,0x7fdf4abc6e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,52554.0,123129.0,64,0x7f380e6e6e80,0,0,192,0,65536,64281,48,1888,32481,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,538,48845,1668,0,48.0,384.0,0.0,262288.0,64,0x7f442ec9ce80,2832273,360448,163840,0,0,180224,114688,0,63063880.0,182726621.0,73509932.0,131072.0,0.0,792646.0,0,0,27281,113156.0,0.0,0.0,113156.0,64,0x7f5b4839ae80,0,47503,0,0,0,47503,0,0,0,47503,0,0,0,47503,0,0,0,47503,0,0,0,47503,0,0,0,47503,0,0,0,47503,0,0,0,47503,0,0,0,47503,0,0,0,47503,0,0,0,47503,0,0,0,47503,0,0,0,47503,0,0,0,47503,0,0,0,47503,0,0,0,47503,0,0,0,47503,0,0,0,47503,0,0,0,47503,0,0,0,47503,0,0,0,47503,0,0,0,47503,0,0,0,47503,0,0,0,47503,0,0,0,47503,0,0,0,47503,0,0,0,47503,0,0,0,47503,0,0,0,47503,0,0,0,47503,0,0,0,47503,0,0,64,0x7ff6dfe38e80,0,3298003,4096,4096,0,3346739,4096,4096,0,3271742,4096,4096,0,2634514,4096,4096,0,3394041,4096,4096,0,3309019,4096,4096,0,3221938,4096,4096,0,3052326,4096,4096,0,3056966,4096,4096,0,2769168,4096,4096,0,3085722,4096,4096,0,2934436,4096,4096,0,3432961,4096,4096,0,2977450,4096,4096,0,3038836,4096,4096,0,2685183,4096,4096,0,3267212,4096,4096,0,3372497,4096,4096,0,3174395,4096,4096,0,2607771,4096,4096,0,3048516,4096,4096,0,3129195,4096,4096,0,3119664,4096,4096,0,2937515,4096,4096,0,3547398,4096,4096,0,3413272,4096,4096,0,2750570,4096,4096,0,2873569,4096,4096,0,3627247,4096,4096,0,2853614,4096,4096,0,2804514,4096,4096,0,4938266,4096,4096,64,0x7fe1d4338e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,87440.0,43632.0,131112.0,0.0,64,0x7f4f30368e80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,141,8196,4241,8337,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8334,4238,8334,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7fdbd5232e80,0.0,64,0x7ff44ef22e80,131072.0,131072.0,0.0,2309906.0,0.0,0.0,119690272.0,59894761.0,64,0x7fed6a790e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,47978,0,131722.0,131072.0,0.0,131104.0,64,0x7f4b6a732e80,32768,0,0,0,16384,16384,393216,21980888,960.0,513862.0,0.0,524288.0,1304330.0,32768.0,0,0,0,16862,131072.0,131072.0,0.0,131072.0,2187922015837329,2187922015861489 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f6498f94e80,4096,0,561,0,4096,0,1313,0,4096,0,2069,0,4154,0,1246,0,4096,0,0,0,4096,0,1702,0,4096,0,843,0,4110,0,5748,0,4098,0,1121,0,4096,0,2909,0,4096,0,1879,0,4144,0,1334,0,4096,0,782,0,4096,0,266,0,4096,0,1250,0,4096,0,149,0,4096,0,626,0,4096,0,2886,0,4096,0,4839,0,4096,0,3333,0,4096,0,0,0,4096,0,967,0,4096,0,629,0,4096,0,323,0,4098,0,384,0,4096,0,2694,0,4096,0,1778,0,4144,0,440,0,4096,0,250,0,4096,0,2727,0,4096,0,214,0,4096,0,484,0,64,0x7f59a5096e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131277.0,0.0,408.0,131276.0,64,0x7f5d2c2f6e80,3120,0,0,1536279,2418,0,0,1566523,1811,0,0,1354936,1372,0,0,1473912,463,0,0,1325309,472,0,0,1317226,2624,0,0,1512574,1150,0,0,1417408,579,0,0,1328205,1081,0,0,1316935,3163,0,0,1465593,273,0,0,1177449,2659,0,0,1478119,1081,0,0,1386202,1395,0,0,1370908,3758,0,0,1696953,2402,0,0,1587864,3141,0,0,1562100,2219,0,0,1479336,2425,0,0,1601556,5408,0,0,1769750,2178,0,0,1447503,4599,0,0,1672669,996,0,0,1319335,638,0,0,1287644,1420,0,0,1416439,3148,0,0,1465782,728,0,0,1280205,668,0,0,1325913,2226,0,0,1477686,2933,0,0,1480492,430,0,0,1327275,64,0x7f832b1dce80,203365,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13478,29862,9008,3827,0,42167,262554.0,0.0,47.0,262507.0,64,0x7ffbc7a20e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f404524ee80,331720,222098,3257691,16384,24182412,0,48,0,41464,41464,3620722.0,2964800.0,5718.0,1139817.0,2091296.0,0.0,2956307.0,2645681.0,331712,231405,41464,0,41464,0,1326848.0,808771.0,0.0,0.0,64,0x7fdf4abc6e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,71495.0,137932.0,64,0x7f380e6e6e80,0,0,48,0,65536,65536,0,0,32442,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,458,46674,1755,0,48.0,395.0,0.0,262144.0,64,0x7f442ec9ce80,2362326,360448,163840,0,0,180224,114688,0,69173861.0,207621779.0,72410478.0,131072.0,0.0,1024336.0,0,0,27024,86886.0,0.0,0.0,86886.0,64,0x7f5b4839ae80,0,43367,0,0,0,43367,0,0,0,43367,0,0,0,43367,0,0,0,43367,0,0,0,43367,0,0,0,43367,0,0,0,43367,0,0,0,43367,0,0,0,43367,0,0,0,43367,0,0,0,43367,0,0,0,43367,0,0,0,43367,0,0,0,43367,0,0,0,43367,0,0,0,43367,0,0,0,43367,0,0,0,43367,0,0,0,43367,0,0,0,43367,0,0,0,43367,0,0,0,43367,0,0,0,43367,0,0,0,43367,0,0,0,43367,0,0,0,43367,0,0,0,43367,0,0,0,43367,0,0,0,43367,0,0,0,43367,0,0,0,43367,0,0,64,0x7ff6dfe38e80,0,5533170,2740,2740,0,3974574,2746,2746,0,3014325,2725,2725,0,3601426,2698,2698,0,3460424,2720,2720,0,2691551,2726,2726,0,3100731,2740,2740,0,4103367,2714,2714,0,3954754,2703,2703,0,4957124,2712,2712,0,2731690,2716,2716,0,3800703,2718,2718,0,3388691,2734,2734,0,4207858,2704,2704,0,2724158,2718,2718,0,3219518,2676,2676,0,3436850,2708,2708,0,3870024,2722,2722,0,3102531,2702,2702,0,3234642,2704,2704,0,4303239,2700,2700,0,4617493,2751,2751,0,2858349,2682,2682,0,3575089,2676,2676,0,4003318,2705,2705,0,3429844,2740,2740,0,2659745,2736,2736,0,3196069,2700,2700,0,2827014,2711,2711,0,3529063,2734,2734,0,2857735,2728,2728,0,4686180,2692,2692,64,0x7fe1d4338e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86563.0,0.0,131113.0,0.0,64,0x7f4f30368e80,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8193,4097,8193,0,8193,4097,8193,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8399,4303,8399,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7fdbd5232e80,0.0,64,0x7ff44ef22e80,131072.0,131072.0,0.0,2471838.0,0.0,0.0,119900899.0,46029151.0,64,0x7fed6a790e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,3413,40724,0,131528.0,131072.0,0.0,86842.0,64,0x7f4b6a732e80,32768,0,0,0,16384,16384,393216,22340503,960.0,513958.0,0.0,524288.0,1147342.0,32768.0,0,0,0,21782,131072.0,131072.0,0.0,131072.0,2187922015985649,2187922016004529 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f6498f94e80,4096,0,2033,0,4096,0,872,0,4096,0,0,0,4100,0,1550,0,4096,0,168,0,4096,0,261,0,4096,0,1907,0,4162,0,4411,0,4098,0,455,0,4096,0,1213,0,4096,0,4379,0,4144,0,4080,0,4096,0,1604,0,4096,0,2345,0,4096,0,1601,0,4096,0,176,0,4096,0,5984,0,4096,0,3974,0,4096,0,3357,0,4096,0,709,0,4096,0,297,0,4096,0,888,0,4096,0,5281,0,4096,0,1001,0,4098,0,0,0,4096,0,2172,0,4096,0,303,0,4144,0,425,0,4096,0,385,0,4096,0,1429,0,4096,0,255,0,4096,0,1202,0,64,0x7f59a5096e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131253.0,0.0,360.0,131252.0,64,0x7f5d2c2f6e80,1189,0,0,1329827,2093,0,0,1395072,1165,0,0,1371343,1322,0,0,1342583,559,0,0,1193819,1156,0,0,1415496,1746,0,0,1461250,1509,0,0,1329244,581,0,0,1368232,1711,0,0,1375586,3636,0,0,1643794,197,0,0,1187022,678,0,0,1285971,1014,0,0,1281207,1631,0,0,1462272,1249,0,0,1298474,1338,0,0,1336199,914,0,0,1258225,2813,0,0,1574930,2674,0,0,1429853,6302,0,0,1856536,2953,0,0,1528400,2214,0,0,1506562,700,0,0,1244235,748,0,0,1284770,1132,0,0,1241223,2097,0,0,1499565,972,0,0,1299747,1261,0,0,1279841,1356,0,0,1285609,2321,0,0,1490219,1596,0,0,1442432,64,0x7f832b1dce80,203624,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,14980,31364,8897,3935,0,42359,262581.0,0.0,47.0,262534.0,64,0x7ffbc7a20e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f404524ee80,336520,226190,3286022,16384,23537813,0,48,0,42064,42064,3682766.0,3001178.0,5258.0,1015366.0,2170593.0,0.0,2992592.0,2683297.0,336512,235967,42064,0,42064,0,1346048.0,821984.0,0.0,0.0,64,0x7fdf4abc6e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,35724.0,106795.0,64,0x7f380e6e6e80,0,0,48,0,65536,65536,0,0,31932,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,458,43623,1745,0,48.0,390.0,0.0,262144.0,64,0x7f442ec9ce80,2979338,360448,163840,0,0,180224,114688,0,60352424.0,162813579.0,58777467.0,131072.0,0.0,840692.0,0,0,26760,62515.0,0.0,0.0,62515.0,64,0x7f5b4839ae80,0,43548,0,0,0,43548,0,0,0,43548,0,0,0,43548,0,0,0,43548,0,0,0,43548,0,0,0,43548,0,0,0,43548,0,0,0,43548,0,0,0,43548,0,0,0,43548,0,0,0,43548,0,0,0,43548,0,0,0,43548,0,0,0,43548,0,0,0,43548,0,0,0,43548,0,0,0,43548,0,0,0,43548,0,0,0,43548,0,0,0,43548,0,0,0,43548,0,0,0,43548,0,0,0,43548,0,0,0,43548,0,0,0,43548,0,0,0,43548,0,0,0,43548,0,0,0,43548,0,0,0,43548,0,0,0,43548,0,0,0,43548,0,0,64,0x7ff6dfe38e80,0,2937101,2760,2760,0,3401405,2714,2714,0,3402475,2743,2743,0,3218037,2778,2778,0,2917143,2729,2729,0,3183950,2788,2788,0,3470527,2718,2718,0,3372222,2778,2778,0,3331646,2764,2764,0,3065916,2752,2752,0,3131757,2742,2742,0,3656675,2784,2784,0,2817913,2748,2748,0,3341512,2750,2750,0,3375985,2723,2723,0,3048520,2766,2766,0,3590228,2728,2728,0,3782095,2800,2800,0,3325905,2718,2718,0,3916657,2748,2748,0,3811122,2722,2722,0,3238106,2781,2781,0,3152645,2728,2728,0,2524000,2746,2746,0,2902501,2734,2734,0,2998841,2738,2738,0,3665398,2764,2764,0,3005702,2798,2798,0,2926751,2726,2726,0,3545077,2721,2721,0,3168118,2786,2786,0,4542244,2806,2806,64,0x7fe1d4338e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86539.0,0.0,131113.0,0.0,64,0x7f4f30368e80,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8193,4097,8193,0,8193,4097,8193,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8346,4250,8346,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7fdbd5232e80,0.0,64,0x7ff44ef22e80,131072.0,131072.0,0.0,2554590.0,0.0,0.0,118062600.0,43753527.0,64,0x7fed6a790e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,3150,39907,0,131522.0,131072.0,0.0,86522.0,64,0x7f4b6a732e80,32768,0,0,0,16384,16384,393216,22705919,960.0,514058.0,0.0,524288.0,1118614.0,32768.0,0,0,0,14736,86337.0,86337.0,0.0,86337.0,2187922016025809,2187922016044849 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_1,obj_1,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_2,obj_2,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_3,obj_3,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_4,obj_4,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_5,obj_5,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_6,obj_6,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_7,obj_7,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_8,obj_8,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_9,obj_9,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_10,obj_10,TCC_EA_ATOMIC_LEVEL_sum,wave_size_11,obj_11,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_12,obj_12,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_13,obj_13,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_14,obj_14,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_15,obj_15,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_16,obj_16,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7ff152bdce80,1499613,360448,163840,0,0,180224,114688,0,69824868.0,192774399.0,72890617.0,131072.0,0.0,734883.0,0,0,26199,102634.0,0.0,0.0,102634.0,64,0x7f8735dece80,32768,0,0,0,16384,16384,393216,22517640,960.0,513930.0,0.0,524288.0,920924.0,32768.0,0,0,0,16834,131072.0,131072.0,0.0,131072.0,64,0x7f72d4350e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131333.0,0.0,514.0,131332.0,64,0x7f0845a66e80,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,64,0x7ff61a272e80,0,8192,4096,8192,0,8192,4096,8192,141,8195,4240,8336,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8471,4375,8471,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,64,0x7f4f9d2f6e80,0,3939748,4096,4096,0,4443055,4096,4096,0,3266882,4096,4096,0,2911959,4096,4096,0,4065717,4096,4096,0,3071282,4096,4096,0,4649556,4096,4096,0,3887334,4096,4096,0,4190930,4096,4096,0,3284101,4096,4096,0,5112928,4096,4096,0,3262087,4096,4096,0,4263841,4096,4096,0,3017669,4096,4096,0,5446783,4096,4096,0,4079591,4096,4096,0,4550102,4096,4096,0,4891926,4096,4096,0,3838648,4096,4096,0,3450667,4096,4096,0,4325669,4096,4096,0,2976756,4096,4096,0,4299053,4096,4096,0,2986696,4096,4096,0,4140733,4096,4096,0,3338287,4096,4096,0,3906922,4096,4096,0,4384229,4096,4096,0,3883644,4096,4096,0,2473675,4096,4096,0,4171046,4096,4096,0,3634635,4096,4096,64,0x7f9f2ec6ae80,188344,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13608,29992,10029,550,0,46442,262581.0,0.0,188.0,262393.0,64,0x7fa8312c6e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,46836,0,131572.0,131072.0,0.0,131104.0,64,0x7f70169a0e80,392424,235362,3419058,16384,24849883,144,48,0,49052,49052,3882896.0,2966072.0,6251.0,1351704.0,2110113.0,0.0,2956889.0,2646381.0,391103,245302,49052,0,49052,0,1569664.0,972093.0,0.0,0.0,64,0x7f120dac0e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86456.0,44616.0,131111.0,0.0,64,0x7f7d83402e80,0.0,64,0x7f96cc104e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,46104.0,109288.0,64,0x7f4b453eae80,3123,0,0,1931203,1585,0,0,1858254,2374,0,0,1796834,442,0,0,1569154,2735,0,0,2026502,957,0,0,1645619,1938,0,0,1798818,2306,0,0,1886738,2023,0,0,1802143,3424,0,0,1964058,1326,0,0,1735545,861,0,0,1690252,1890,0,0,1832679,671,0,0,1654111,2115,0,0,1802902,954,0,0,1752317,1445,0,0,1749518,834,0,0,1649391,2137,0,0,1776798,471,0,0,1580312,4684,0,0,2088290,1455,0,0,1723765,2832,0,0,1849038,1082,0,0,1760634,3534,0,0,2085132,907,0,0,1747966,1863,0,0,1799368,2226,0,0,1827243,2647,0,0,1874254,4737,0,0,2068035,3386,0,0,2018812,1467,0,0,1758289,64,0x7fd19fc96e80,4096,0,1138,0,4096,0,1270,0,4100,0,670,0,4096,0,287,0,4096,0,1017,0,4096,0,0,0,4144,0,0,0,4096,0,0,0,4096,0,6733,0,4096,0,894,0,4144,0,0,0,4216,0,5171,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4150,0,0,0,4096,0,9364,0,4096,0,1394,0,4096,0,181,0,4096,0,0,0,4096,0,0,0,4096,0,398,0,4096,0,152,0,4096,0,0,0,4096,0,66,0,4096,0,287,0,4096,0,0,0,4096,0,129,0,4216,0,980,0,4096,0,135,0,4096,0,0,0,4096,0,488,0,64,0x7faffe2a0e80,0,0,192,0,65536,64415,48,1529,32223,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,538,48145,1710,0,48.0,255.0,0.0,262288.0,64,0x7f4e3f6d6e80,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fcdfc71ce80,131072.0,131072.0,0.0,2553503.0,0.0,0.0,106102580.0,61371369.0,194339836161015,194339836185335 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7ff152bdce80,1347457,360448,163840,0,0,180224,114688,0,65721003.0,188322359.0,74301065.0,131072.0,0.0,817243.0,0,0,25001,99300.0,0.0,0.0,99300.0,64,0x7f8735dece80,32768,0,0,0,16384,16384,393216,22361836,960.0,513922.0,0.0,524288.0,946179.0,32768.0,0,0,0,13964,86911.0,86911.0,0.0,86911.0,64,0x7f72d4350e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131382.0,0.0,618.0,131381.0,64,0x7f0845a66e80,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,64,0x7ff61a272e80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8470,4374,8470,0,8192,4096,8192,0,8192,4096,8192,47,8194,4145,8241,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,64,0x7f4f9d2f6e80,0,3518684,2710,2710,0,4231549,2741,2741,0,4057507,2692,2692,0,4903784,2728,2728,0,3307219,2717,2717,0,2949122,2736,2736,0,3198882,2716,2716,0,3364134,2727,2727,0,5182322,2696,2696,0,3019700,2708,2708,0,3040906,2712,2712,0,5054873,2728,2728,0,3684522,2716,2716,0,4375277,2712,2712,0,4608066,2708,2708,0,3996044,2683,2683,0,5373070,2698,2698,0,3628970,2712,2712,0,3036938,2692,2692,0,4411604,2702,2702,0,4219579,2684,2684,0,3396626,2779,2779,0,3038731,2709,2709,0,2917673,2662,2662,0,2653865,2704,2704,0,3889594,2748,2748,0,3298029,2708,2708,0,3160945,2744,2744,0,4108399,2688,2688,0,3145392,2758,2758,0,3738007,2724,2724,0,4972697,2708,2708,64,0x7f9f2ec6ae80,183144,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,10524,26908,8578,2411,0,41597,262495.0,0.0,47.0,262448.0,64,0x7fa8312c6e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,2756,41301,0,131508.0,131072.0,0.0,86974.0,64,0x7f70169a0e80,342608,231992,3366611,16384,24103847,0,48,0,42825,42825,3769538.0,3020480.0,5081.0,1146243.0,2152781.0,0.0,3011816.0,2701946.0,342600,241453,42825,0,42825,0,1370400.0,827545.0,0.0,0.0,64,0x7f120dac0e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,49432.0,37197.0,31128.0,0.0,64,0x7f7d83402e80,0.0,64,0x7f96cc104e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,73418.0,138198.0,64,0x7f4b453eae80,1540,0,0,1444301,1386,0,0,1370255,1984,0,0,1460020,1823,0,0,1364651,571,0,0,1298101,1909,0,0,1536794,804,0,0,1402101,2211,0,0,1439847,1534,0,0,1378863,3516,0,0,1674602,1296,0,0,1287668,921,0,0,1386270,2090,0,0,1436246,571,0,0,1308261,1940,0,0,1397466,2692,0,0,1611344,1564,0,0,1394917,312,0,0,1304531,1135,0,0,1385174,1856,0,0,1399700,5155,0,0,1754415,352,0,0,1237235,1413,0,0,1383004,834,0,0,1195428,2955,0,0,1543371,2663,0,0,1563322,3129,0,0,1509995,4932,0,0,1669094,3640,0,0,1729842,2782,0,0,1500497,2802,0,0,1554076,1813,0,0,1412117,64,0x7fd19fc96e80,4096,0,8972,0,4096,0,0,0,4097,0,3048,0,4096,0,623,0,4096,0,1277,0,4097,0,683,0,4144,0,634,0,4098,0,602,0,4096,0,1000,0,4096,0,717,0,4144,0,625,0,4216,0,1863,0,4096,0,0,0,4096,0,1633,0,4096,0,1709,0,4139,0,12,0,4096,0,939,0,4096,0,1297,0,4096,0,1856,0,4096,0,667,0,4096,0,6453,0,4096,0,1536,0,4096,0,124,0,4097,0,0,0,4096,0,439,0,4096,0,319,0,4096,0,1372,0,4096,0,0,0,4216,0,1,0,4096,0,157,0,4096,0,995,0,4096,0,21,0,64,0x7faffe2a0e80,0,0,48,0,65536,65536,0,0,32188,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,458,43552,1767,0,48.0,364.0,0.0,262144.0,64,0x7f4e3f6d6e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fcdfc71ce80,131072.0,131072.0,0.0,2566412.0,0.0,0.0,137327742.0,48410073.0,194339836365335,194339836384535 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7ff152bdce80,1322927,360448,163840,0,0,180224,114688,0,67761045.0,195182409.0,74818673.0,131072.0,0.0,830136.0,0,0,24728,124626.0,0.0,0.0,124626.0,64,0x7f8735dece80,32768,0,0,0,16384,16384,393216,22532751,960.0,513891.0,0.0,524288.0,880969.0,32768.0,0,0,0,13611,86501.0,86501.0,0.0,86501.0,64,0x7f72d4350e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131442.0,0.0,738.0,131441.0,64,0x7f0845a66e80,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,64,0x7ff61a272e80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8476,4380,8476,0,8192,4096,8192,0,8192,4096,8192,47,8194,4145,8241,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,64,0x7f4f9d2f6e80,0,3086531,2683,2683,0,3317971,2746,2746,0,3352513,2684,2684,0,3146409,2736,2736,0,3151727,2676,2676,0,3192235,2744,2744,0,4376009,2702,2702,0,3202802,2720,2720,0,3259134,2686,2686,0,3800343,2708,2708,0,4164544,2712,2712,0,5007777,2716,2716,0,3543308,2696,2696,0,3046028,2728,2728,0,3951001,2712,2712,0,3081473,2690,2690,0,3430534,2676,2676,0,4548064,2724,2724,0,4307039,2700,2700,0,2770369,2724,2724,0,4926197,2676,2676,0,4759543,2780,2780,0,2904016,2672,2672,0,2674117,2682,2682,0,2712433,2660,2660,0,3723130,2730,2730,0,3027792,2746,2746,0,5357453,2738,2738,0,2946611,2688,2688,0,3470740,2738,2738,0,3642104,2724,2724,0,3791165,2694,2694,64,0x7f9f2ec6ae80,183111,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,10793,27177,8547,2427,0,41005,262465.0,0.0,47.0,262418.0,64,0x7fa8312c6e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,2753,40874,0,131486.0,131072.0,0.0,86902.0,64,0x7f70169a0e80,343176,228919,3326199,16384,24374477,0,48,0,42896,42896,3723476.0,2979824.0,4955.0,1145869.0,2122116.0,0.0,2971114.0,2662193.0,343168,238681,42896,0,42896,0,1372672.0,815676.0,0.0,0.0,64,0x7f120dac0e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86525.0,0.0,131112.0,0.0,64,0x7f7d83402e80,0.0,64,0x7f96cc104e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,74538.0,142626.0,64,0x7f4b453eae80,4663,0,0,1719035,4195,0,0,1705745,1860,0,0,1485385,4286,0,0,1670609,1887,0,0,1438755,1922,0,0,1492049,2334,0,0,1461240,4691,0,0,1707754,1212,0,0,1369671,1726,0,0,1412373,2977,0,0,1561380,120,0,0,1264876,2134,0,0,1387316,3406,0,0,1458464,3058,0,0,1645266,2781,0,0,1542979,1451,0,0,1413717,254,0,0,1161879,3414,0,0,1555880,1934,0,0,1454006,1569,0,0,1457370,2026,0,0,1440167,3540,0,0,1586729,2286,0,0,1475484,3771,0,0,1617066,695,0,0,1221590,2953,0,0,1623377,4190,0,0,1717194,3460,0,0,1512751,3341,0,0,1485875,5129,0,0,1712068,4177,0,0,1646353,64,0x7fd19fc96e80,4096,0,2325,0,4096,0,777,0,4097,0,1666,0,4096,0,1212,0,4096,0,4085,0,4097,0,2021,0,4144,0,1527,0,4098,0,1600,0,4096,0,1350,0,4096,0,2403,0,4144,0,1505,0,4216,0,1587,0,4096,0,1329,0,4096,0,547,0,4096,0,1710,0,4199,0,2801,0,4096,0,2783,0,4096,0,3770,0,4096,0,1964,0,4096,0,577,0,4096,0,2787,0,4096,0,1761,0,4096,0,1228,0,4097,0,177,0,4096,0,907,0,4096,0,2452,0,4096,0,1400,0,4096,0,334,0,4216,0,1781,0,4096,0,2604,0,4096,0,992,0,4096,0,931,0,64,0x7faffe2a0e80,0,0,48,0,65536,65536,0,0,30399,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,458,42067,1751,0,48.0,327.0,0.0,262144.0,64,0x7f4e3f6d6e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fcdfc71ce80,131072.0,131072.0,0.0,2580798.0,0.0,0.0,127933603.0,44561024.0,194339836406935,194339836425975 diff --git a/tests/workloads/kernel_verbose_5/MI100/sysinfo.csv b/tests/workloads/kernel_verbose_5/MI100/sysinfo.csv index b2108f7bc8..d47d561271 100644 --- a/tests/workloads/kernel_verbose_5/MI100/sysinfo.csv +++ b/tests/workloads/kernel_verbose_5/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -kernel_verbose_5,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Fri Mar 1 16:47:03 2024 (CST),1,t006-003.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651240,,5.7.1-98,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +kernel_verbose_5,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 07 Mar 2024 01:09:52 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/kernel_verbose_5/MI100/timestamps.csv b/tests/workloads/kernel_verbose_5/MI100/timestamps.csv index 9d33c3f7b3..55ab5c0c9b 100644 --- a/tests/workloads/kernel_verbose_5/MI100/timestamps.csv +++ b/tests/workloads/kernel_verbose_5/MI100/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,2887489,2887489,1048576,256,0,0,8,8,16,64,0x0,0x7f0b0e0a2e80,2187922015811459,2187922015837329,2187922015861489,2187922015872124 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,2887489,2887489,1048576,256,0,0,8,8,16,64,0x0,0x7f0b0e0a2e80,2187922015874338,2187922015985649,2187922016004529,2187922016005454 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,2887489,2887489,1048576,256,0,0,8,8,16,64,0x0,0x7f0b0e0a2e80,2187922016016244,2187922016025809,2187922016044849,2187922016045729 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,193214,193214,1048576,256,0,0,8,8,16,64,0x0,0x7f161346ce80,194339836137003,194339836161015,194339836185335,194339836198729 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,193214,193214,1048576,256,0,0,8,8,16,64,0x0,0x7f161346ce80,194339836198048,194339836365335,194339836384535,194339836385834 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,193214,193214,1048576,256,0,0,8,8,16,64,0x0,0x7f161346ce80,194339836397035,194339836406935,194339836425975,194339836426992 diff --git a/tests/workloads/kernel_verbose_5/MI200/SQ_IFETCH_LEVEL.csv b/tests/workloads/kernel_verbose_5/MI200/SQ_IFETCH_LEVEL.csv new file mode 100644 index 0000000000..04f0b9eff5 --- /dev/null +++ b/tests/workloads/kernel_verbose_5/MI200/SQ_IFETCH_LEVEL.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,353243,353243,1048576,256,0,0,8,0,16,64,0x0,0x7f22368d4ec0,27758,27758,16384,65536,13694,1543472,199842697294641,199855576360179,199855576380339,199842713192646 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,353243,353243,1048576,256,0,0,8,0,16,64,0x0,0x7f22368d4ec0,41938,41938,16384,65536,9427,1048652,199842713218094,199855576464819,199855576481459,199842713520406 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,353243,353243,1048576,256,0,0,8,0,16,64,0x0,0x7f22368d4ec0,41692,41692,16384,65536,9176,1048624,199842713550233,199855576502899,199855576518579,199842713708813 diff --git a/tests/workloads/kernel_verbose_5/MI200/SQ_INST_LEVEL_LDS.csv b/tests/workloads/kernel_verbose_5/MI200/SQ_INST_LEVEL_LDS.csv new file mode 100644 index 0000000000..e61b8446d9 --- /dev/null +++ b/tests/workloads/kernel_verbose_5/MI200/SQ_INST_LEVEL_LDS.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,353442,353442,1048576,256,0,0,8,0,16,64,0x0,0x7ff70b594ec0,0,0,0,199843177960026,199855576360179,199855576380339,199843194318883 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,353442,353442,1048576,256,0,0,8,0,16,64,0x0,0x7ff70b594ec0,0,0,0,199843194336376,199855576464819,199855576481459,199843194664897 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,353442,353442,1048576,256,0,0,8,0,16,64,0x0,0x7ff70b594ec0,0,0,0,199843194690786,199855576502899,199855576518579,199843194840179 diff --git a/tests/workloads/kernel_verbose_5/MI200/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/kernel_verbose_5/MI200/SQ_INST_LEVEL_SMEM.csv new file mode 100644 index 0000000000..b2282f88d2 --- /dev/null +++ b/tests/workloads/kernel_verbose_5/MI200/SQ_INST_LEVEL_SMEM.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,353643,353643,1048576,256,0,0,8,0,16,64,0x0,0x7fd986054ec0,65536,173084,19363944,199843663138849,199855576360179,199855576380339,199843678826435 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,353643,353643,1048576,256,0,0,8,0,16,64,0x0,0x7fd986054ec0,65536,261280,29317904,199843678836955,199855576464819,199855576481459,199843679089202 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,353643,353643,1048576,256,0,0,8,0,16,64,0x0,0x7fd986054ec0,65536,261428,29254416,199843679116284,199855576502899,199855576518579,199843679262340 diff --git a/tests/workloads/kernel_verbose_5/MI200/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/kernel_verbose_5/MI200/SQ_INST_LEVEL_VMEM.csv new file mode 100644 index 0000000000..b7945dfdb8 --- /dev/null +++ b/tests/workloads/kernel_verbose_5/MI200/SQ_INST_LEVEL_VMEM.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,353845,353845,1048576,256,0,0,8,0,16,64,0x0,0x7fd4b4cecec0,32768,297864,33349068,199844136266023,199855576360179,199855576380339,199844152348036 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,353845,353845,1048576,256,0,0,8,0,16,64,0x0,0x7fd4b4cecec0,32768,606519,67931848,199844152365519,199855576464819,199855576481459,199844152661319 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,353845,353845,1048576,256,0,0,8,0,16,64,0x0,0x7fd4b4cecec0,32768,573147,64198532,199844152687678,199855576502899,199855576518579,199844152842461 diff --git a/tests/workloads/kernel_verbose_5/MI200/SQ_LEVEL_WAVES.csv b/tests/workloads/kernel_verbose_5/MI200/SQ_LEVEL_WAVES.csv new file mode 100644 index 0000000000..8612883695 --- /dev/null +++ b/tests/workloads/kernel_verbose_5/MI200/SQ_LEVEL_WAVES.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,354046,354046,1048576,256,0,0,8,0,16,64,0x0,0x7f88dc418ec0,28307,28307,10953,226464,16384,11233584,133850,0,45441188,199844616863730,199855576360179,199855576380339,199844632629614 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,354046,354046,1048576,256,0,0,8,0,16,64,0x0,0x7f88dc418ec0,41933,41933,14003,335472,16384,19589760,227074,0,78847996,199844632658339,199855576464819,199855576481459,199844632941905 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,354046,354046,1048576,256,0,0,8,0,16,64,0x0,0x7f88dc418ec0,41231,41231,13891,329856,16384,19366564,222291,0,77959488,199844632977062,199855576502899,199855576518579,199844633142895 diff --git a/tests/workloads/kernel_verbose_5/MI200/perfmon/SQ_IFETCH_LEVEL.txt b/tests/workloads/kernel_verbose_5/MI200/perfmon/SQ_IFETCH_LEVEL.txt new file mode 100644 index 0000000000..293092f641 --- /dev/null +++ b/tests/workloads/kernel_verbose_5/MI200/perfmon/SQ_IFETCH_LEVEL.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_5/MI200/perfmon/SQ_INST_LEVEL_LDS.txt b/tests/workloads/kernel_verbose_5/MI200/perfmon/SQ_INST_LEVEL_LDS.txt new file mode 100644 index 0000000000..08439eedce --- /dev/null +++ b/tests/workloads/kernel_verbose_5/MI200/perfmon/SQ_INST_LEVEL_LDS.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_5/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt b/tests/workloads/kernel_verbose_5/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt new file mode 100644 index 0000000000..6cca322d4e --- /dev/null +++ b/tests/workloads/kernel_verbose_5/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_5/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt b/tests/workloads/kernel_verbose_5/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt new file mode 100644 index 0000000000..e527ad31ba --- /dev/null +++ b/tests/workloads/kernel_verbose_5/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_5/MI200/perfmon/SQ_LEVEL_WAVES.txt b/tests/workloads/kernel_verbose_5/MI200/perfmon/SQ_LEVEL_WAVES.txt new file mode 100644 index 0000000000..3f8e04adb3 --- /dev/null +++ b/tests/workloads/kernel_verbose_5/MI200/perfmon/SQ_LEVEL_WAVES.txt @@ -0,0 +1,5 @@ +pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_0.txt b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_0.txt new file mode 100644 index 0000000000..4ffdc32149 --- /dev/null +++ b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_0.txt @@ -0,0 +1,5 @@ +pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES SQ_INSTS_VALU_CVT SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU GRBM_COUNT GRBM_GUI_ACTIVE TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum TA_TA_BUSY_sum TA_BUFFER_WAVEFRONTS_sum TD_TD_BUSY_sum TD_TC_STALL_sum SPI_CSN_WINDOW_VALID SPI_CSN_BUSY CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_1.txt b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_1.txt new file mode 100644 index 0000000000..6c277f4a37 --- /dev/null +++ b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_1.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VSKIPPED SQ_INSTS SQ_INSTS_VALU SQ_INSTS_VALU_ADD_F16 SQ_INSTS_VALU_MUL_F16 SQ_INSTS_VALU_FMA_F16 SQ_INSTS_VALU_TRANS_F16 SQ_INSTS_VALU_ADD_F32 GRBM_SPI_BUSY TCP_READ_TAGCONFLICT_STALL_CYCLES_sum TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum TCP_TA_TCP_STATE_READ_sum TA_BUFFER_READ_WAVEFRONTS_sum TA_BUFFER_WRITE_WAVEFRONTS_sum TD_SPI_STALL_sum TD_LOAD_WAVEFRONT_sum SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_10.txt b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_10.txt new file mode 100644 index 0000000000..7053d4dce6 --- /dev/null +++ b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_10.txt @@ -0,0 +1,5 @@ +pmc: SQC_TC_DATA_WRITE_REQ SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_11.txt b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_11.txt new file mode 100644 index 0000000000..77ae8b461f --- /dev/null +++ b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_11.txt @@ -0,0 +1,5 @@ +pmc: SQC_ICACHE_MISSES_DUPLICATE SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_12.txt b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_12.txt new file mode 100644 index 0000000000..dfb2cf65e5 --- /dev/null +++ b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_12.txt @@ -0,0 +1,5 @@ +pmc: SQC_DCACHE_REQ_READ_1 SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_13.txt b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_13.txt new file mode 100644 index 0000000000..062fc9644a --- /dev/null +++ b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_13.txt @@ -0,0 +1,5 @@ +pmc: TCC_ATOMIC[0] TCC_CYCLE[0] TCC_EA_ATOMIC[0] TCC_EA_ATOMIC_LEVEL[0] TCC_ATOMIC[1] TCC_CYCLE[1] TCC_EA_ATOMIC[1] TCC_EA_ATOMIC_LEVEL[1] TCC_ATOMIC[2] TCC_CYCLE[2] TCC_EA_ATOMIC[2] TCC_EA_ATOMIC_LEVEL[2] TCC_ATOMIC[3] TCC_CYCLE[3] TCC_EA_ATOMIC[3] TCC_EA_ATOMIC_LEVEL[3] TCC_ATOMIC[4] TCC_CYCLE[4] TCC_EA_ATOMIC[4] TCC_EA_ATOMIC_LEVEL[4] TCC_ATOMIC[5] TCC_CYCLE[5] TCC_EA_ATOMIC[5] TCC_EA_ATOMIC_LEVEL[5] TCC_ATOMIC[6] TCC_CYCLE[6] TCC_EA_ATOMIC[6] TCC_EA_ATOMIC_LEVEL[6] TCC_ATOMIC[7] TCC_CYCLE[7] TCC_EA_ATOMIC[7] TCC_EA_ATOMIC_LEVEL[7] TCC_ATOMIC[8] TCC_CYCLE[8] TCC_EA_ATOMIC[8] TCC_EA_ATOMIC_LEVEL[8] TCC_ATOMIC[9] TCC_CYCLE[9] TCC_EA_ATOMIC[9] TCC_EA_ATOMIC_LEVEL[9] TCC_ATOMIC[10] TCC_CYCLE[10] TCC_EA_ATOMIC[10] TCC_EA_ATOMIC_LEVEL[10] TCC_ATOMIC[11] TCC_CYCLE[11] TCC_EA_ATOMIC[11] TCC_EA_ATOMIC_LEVEL[11] TCC_ATOMIC[12] TCC_CYCLE[12] TCC_EA_ATOMIC[12] TCC_EA_ATOMIC_LEVEL[12] TCC_ATOMIC[13] TCC_CYCLE[13] TCC_EA_ATOMIC[13] TCC_EA_ATOMIC_LEVEL[13] TCC_ATOMIC[14] TCC_CYCLE[14] TCC_EA_ATOMIC[14] TCC_EA_ATOMIC_LEVEL[14] TCC_ATOMIC[15] TCC_CYCLE[15] TCC_EA_ATOMIC[15] TCC_EA_ATOMIC_LEVEL[15] TCC_ATOMIC[16] TCC_CYCLE[16] TCC_EA_ATOMIC[16] TCC_EA_ATOMIC_LEVEL[16] TCC_ATOMIC[17] TCC_CYCLE[17] TCC_EA_ATOMIC[17] TCC_EA_ATOMIC_LEVEL[17] TCC_ATOMIC[18] TCC_CYCLE[18] TCC_EA_ATOMIC[18] TCC_EA_ATOMIC_LEVEL[18] TCC_ATOMIC[19] TCC_CYCLE[19] TCC_EA_ATOMIC[19] TCC_EA_ATOMIC_LEVEL[19] TCC_ATOMIC[20] TCC_CYCLE[20] TCC_EA_ATOMIC[20] TCC_EA_ATOMIC_LEVEL[20] TCC_ATOMIC[21] TCC_CYCLE[21] TCC_EA_ATOMIC[21] TCC_EA_ATOMIC_LEVEL[21] TCC_ATOMIC[22] TCC_CYCLE[22] TCC_EA_ATOMIC[22] TCC_EA_ATOMIC_LEVEL[22] TCC_ATOMIC[23] TCC_CYCLE[23] TCC_EA_ATOMIC[23] TCC_EA_ATOMIC_LEVEL[23] TCC_ATOMIC[24] TCC_CYCLE[24] TCC_EA_ATOMIC[24] TCC_EA_ATOMIC_LEVEL[24] TCC_ATOMIC[25] TCC_CYCLE[25] TCC_EA_ATOMIC[25] TCC_EA_ATOMIC_LEVEL[25] TCC_ATOMIC[26] TCC_CYCLE[26] TCC_EA_ATOMIC[26] TCC_EA_ATOMIC_LEVEL[26] TCC_ATOMIC[27] TCC_CYCLE[27] TCC_EA_ATOMIC[27] TCC_EA_ATOMIC_LEVEL[27] TCC_ATOMIC[28] TCC_CYCLE[28] TCC_EA_ATOMIC[28] TCC_EA_ATOMIC_LEVEL[28] TCC_ATOMIC[29] TCC_CYCLE[29] TCC_EA_ATOMIC[29] TCC_EA_ATOMIC_LEVEL[29] TCC_ATOMIC[30] TCC_CYCLE[30] TCC_EA_ATOMIC[30] TCC_EA_ATOMIC_LEVEL[30] TCC_ATOMIC[31] TCC_CYCLE[31] TCC_EA_ATOMIC[31] TCC_EA_ATOMIC_LEVEL[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_14.txt b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_14.txt new file mode 100644 index 0000000000..e0698dbf57 --- /dev/null +++ b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_14.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_EA_RDREQ_GMI_CREDIT_STALL[0] TCC_EA_RDREQ[1] TCC_EA_RDREQ_32B[1] TCC_EA_RDREQ_DRAM_CREDIT_STALL[1] TCC_EA_RDREQ_GMI_CREDIT_STALL[1] TCC_EA_RDREQ[2] TCC_EA_RDREQ_32B[2] TCC_EA_RDREQ_DRAM_CREDIT_STALL[2] TCC_EA_RDREQ_GMI_CREDIT_STALL[2] TCC_EA_RDREQ[3] TCC_EA_RDREQ_32B[3] TCC_EA_RDREQ_DRAM_CREDIT_STALL[3] TCC_EA_RDREQ_GMI_CREDIT_STALL[3] TCC_EA_RDREQ[4] TCC_EA_RDREQ_32B[4] TCC_EA_RDREQ_DRAM_CREDIT_STALL[4] TCC_EA_RDREQ_GMI_CREDIT_STALL[4] TCC_EA_RDREQ[5] TCC_EA_RDREQ_32B[5] TCC_EA_RDREQ_DRAM_CREDIT_STALL[5] TCC_EA_RDREQ_GMI_CREDIT_STALL[5] TCC_EA_RDREQ[6] TCC_EA_RDREQ_32B[6] TCC_EA_RDREQ_DRAM_CREDIT_STALL[6] TCC_EA_RDREQ_GMI_CREDIT_STALL[6] TCC_EA_RDREQ[7] TCC_EA_RDREQ_32B[7] TCC_EA_RDREQ_DRAM_CREDIT_STALL[7] TCC_EA_RDREQ_GMI_CREDIT_STALL[7] TCC_EA_RDREQ[8] TCC_EA_RDREQ_32B[8] TCC_EA_RDREQ_DRAM_CREDIT_STALL[8] TCC_EA_RDREQ_GMI_CREDIT_STALL[8] TCC_EA_RDREQ[9] TCC_EA_RDREQ_32B[9] TCC_EA_RDREQ_DRAM_CREDIT_STALL[9] TCC_EA_RDREQ_GMI_CREDIT_STALL[9] TCC_EA_RDREQ[10] TCC_EA_RDREQ_32B[10] TCC_EA_RDREQ_DRAM_CREDIT_STALL[10] TCC_EA_RDREQ_GMI_CREDIT_STALL[10] TCC_EA_RDREQ[11] TCC_EA_RDREQ_32B[11] TCC_EA_RDREQ_DRAM_CREDIT_STALL[11] TCC_EA_RDREQ_GMI_CREDIT_STALL[11] TCC_EA_RDREQ[12] TCC_EA_RDREQ_32B[12] TCC_EA_RDREQ_DRAM_CREDIT_STALL[12] TCC_EA_RDREQ_GMI_CREDIT_STALL[12] TCC_EA_RDREQ[13] TCC_EA_RDREQ_32B[13] TCC_EA_RDREQ_DRAM_CREDIT_STALL[13] TCC_EA_RDREQ_GMI_CREDIT_STALL[13] TCC_EA_RDREQ[14] TCC_EA_RDREQ_32B[14] TCC_EA_RDREQ_DRAM_CREDIT_STALL[14] TCC_EA_RDREQ_GMI_CREDIT_STALL[14] TCC_EA_RDREQ[15] TCC_EA_RDREQ_32B[15] TCC_EA_RDREQ_DRAM_CREDIT_STALL[15] TCC_EA_RDREQ_GMI_CREDIT_STALL[15] TCC_EA_RDREQ[16] TCC_EA_RDREQ_32B[16] TCC_EA_RDREQ_DRAM_CREDIT_STALL[16] TCC_EA_RDREQ_GMI_CREDIT_STALL[16] TCC_EA_RDREQ[17] TCC_EA_RDREQ_32B[17] TCC_EA_RDREQ_DRAM_CREDIT_STALL[17] TCC_EA_RDREQ_GMI_CREDIT_STALL[17] TCC_EA_RDREQ[18] TCC_EA_RDREQ_32B[18] TCC_EA_RDREQ_DRAM_CREDIT_STALL[18] TCC_EA_RDREQ_GMI_CREDIT_STALL[18] TCC_EA_RDREQ[19] TCC_EA_RDREQ_32B[19] TCC_EA_RDREQ_DRAM_CREDIT_STALL[19] TCC_EA_RDREQ_GMI_CREDIT_STALL[19] TCC_EA_RDREQ[20] TCC_EA_RDREQ_32B[20] TCC_EA_RDREQ_DRAM_CREDIT_STALL[20] TCC_EA_RDREQ_GMI_CREDIT_STALL[20] TCC_EA_RDREQ[21] TCC_EA_RDREQ_32B[21] TCC_EA_RDREQ_DRAM_CREDIT_STALL[21] TCC_EA_RDREQ_GMI_CREDIT_STALL[21] TCC_EA_RDREQ[22] TCC_EA_RDREQ_32B[22] TCC_EA_RDREQ_DRAM_CREDIT_STALL[22] TCC_EA_RDREQ_GMI_CREDIT_STALL[22] TCC_EA_RDREQ[23] TCC_EA_RDREQ_32B[23] TCC_EA_RDREQ_DRAM_CREDIT_STALL[23] TCC_EA_RDREQ_GMI_CREDIT_STALL[23] TCC_EA_RDREQ[24] TCC_EA_RDREQ_32B[24] TCC_EA_RDREQ_DRAM_CREDIT_STALL[24] TCC_EA_RDREQ_GMI_CREDIT_STALL[24] TCC_EA_RDREQ[25] TCC_EA_RDREQ_32B[25] TCC_EA_RDREQ_DRAM_CREDIT_STALL[25] TCC_EA_RDREQ_GMI_CREDIT_STALL[25] TCC_EA_RDREQ[26] TCC_EA_RDREQ_32B[26] TCC_EA_RDREQ_DRAM_CREDIT_STALL[26] TCC_EA_RDREQ_GMI_CREDIT_STALL[26] TCC_EA_RDREQ[27] TCC_EA_RDREQ_32B[27] TCC_EA_RDREQ_DRAM_CREDIT_STALL[27] TCC_EA_RDREQ_GMI_CREDIT_STALL[27] TCC_EA_RDREQ[28] TCC_EA_RDREQ_32B[28] TCC_EA_RDREQ_DRAM_CREDIT_STALL[28] TCC_EA_RDREQ_GMI_CREDIT_STALL[28] TCC_EA_RDREQ[29] TCC_EA_RDREQ_32B[29] TCC_EA_RDREQ_DRAM_CREDIT_STALL[29] TCC_EA_RDREQ_GMI_CREDIT_STALL[29] TCC_EA_RDREQ[30] TCC_EA_RDREQ_32B[30] TCC_EA_RDREQ_DRAM_CREDIT_STALL[30] TCC_EA_RDREQ_GMI_CREDIT_STALL[30] TCC_EA_RDREQ[31] TCC_EA_RDREQ_32B[31] TCC_EA_RDREQ_DRAM_CREDIT_STALL[31] TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_15.txt b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_15.txt new file mode 100644 index 0000000000..77ad088669 --- /dev/null +++ b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_15.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ[0] TCC_EA_WRREQ_64B[0] TCC_EA_RDREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_LEVEL[1] TCC_EA_WRREQ[1] TCC_EA_WRREQ_64B[1] TCC_EA_RDREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_LEVEL[2] TCC_EA_WRREQ[2] TCC_EA_WRREQ_64B[2] TCC_EA_RDREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_LEVEL[3] TCC_EA_WRREQ[3] TCC_EA_WRREQ_64B[3] TCC_EA_RDREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_LEVEL[4] TCC_EA_WRREQ[4] TCC_EA_WRREQ_64B[4] TCC_EA_RDREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_LEVEL[5] TCC_EA_WRREQ[5] TCC_EA_WRREQ_64B[5] TCC_EA_RDREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_LEVEL[6] TCC_EA_WRREQ[6] TCC_EA_WRREQ_64B[6] TCC_EA_RDREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_LEVEL[7] TCC_EA_WRREQ[7] TCC_EA_WRREQ_64B[7] TCC_EA_RDREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_LEVEL[8] TCC_EA_WRREQ[8] TCC_EA_WRREQ_64B[8] TCC_EA_RDREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_LEVEL[9] TCC_EA_WRREQ[9] TCC_EA_WRREQ_64B[9] TCC_EA_RDREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_LEVEL[10] TCC_EA_WRREQ[10] TCC_EA_WRREQ_64B[10] TCC_EA_RDREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_LEVEL[11] TCC_EA_WRREQ[11] TCC_EA_WRREQ_64B[11] TCC_EA_RDREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_LEVEL[12] TCC_EA_WRREQ[12] TCC_EA_WRREQ_64B[12] TCC_EA_RDREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_LEVEL[13] TCC_EA_WRREQ[13] TCC_EA_WRREQ_64B[13] TCC_EA_RDREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_LEVEL[14] TCC_EA_WRREQ[14] TCC_EA_WRREQ_64B[14] TCC_EA_RDREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_LEVEL[15] TCC_EA_WRREQ[15] TCC_EA_WRREQ_64B[15] TCC_EA_RDREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_LEVEL[16] TCC_EA_WRREQ[16] TCC_EA_WRREQ_64B[16] TCC_EA_RDREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_LEVEL[17] TCC_EA_WRREQ[17] TCC_EA_WRREQ_64B[17] TCC_EA_RDREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_LEVEL[18] TCC_EA_WRREQ[18] TCC_EA_WRREQ_64B[18] TCC_EA_RDREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_LEVEL[19] TCC_EA_WRREQ[19] TCC_EA_WRREQ_64B[19] TCC_EA_RDREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_LEVEL[20] TCC_EA_WRREQ[20] TCC_EA_WRREQ_64B[20] TCC_EA_RDREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_LEVEL[21] TCC_EA_WRREQ[21] TCC_EA_WRREQ_64B[21] TCC_EA_RDREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_LEVEL[22] TCC_EA_WRREQ[22] TCC_EA_WRREQ_64B[22] TCC_EA_RDREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_LEVEL[23] TCC_EA_WRREQ[23] TCC_EA_WRREQ_64B[23] TCC_EA_RDREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_LEVEL[24] TCC_EA_WRREQ[24] TCC_EA_WRREQ_64B[24] TCC_EA_RDREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_LEVEL[25] TCC_EA_WRREQ[25] TCC_EA_WRREQ_64B[25] TCC_EA_RDREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_LEVEL[26] TCC_EA_WRREQ[26] TCC_EA_WRREQ_64B[26] TCC_EA_RDREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_LEVEL[27] TCC_EA_WRREQ[27] TCC_EA_WRREQ_64B[27] TCC_EA_RDREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_LEVEL[28] TCC_EA_WRREQ[28] TCC_EA_WRREQ_64B[28] TCC_EA_RDREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_LEVEL[29] TCC_EA_WRREQ[29] TCC_EA_WRREQ_64B[29] TCC_EA_RDREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_LEVEL[30] TCC_EA_WRREQ[30] TCC_EA_WRREQ_64B[30] TCC_EA_RDREQ_IO_CREDIT_STALL[31] TCC_EA_RDREQ_LEVEL[31] TCC_EA_WRREQ[31] TCC_EA_WRREQ_64B[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_16.txt b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_16.txt new file mode 100644 index 0000000000..d0628bb948 --- /dev/null +++ b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_16.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_WRREQ_IO_CREDIT_STALL[0] TCC_EA_WRREQ_LEVEL[0] TCC_EA_WRREQ_DRAM_CREDIT_STALL[1] TCC_EA_WRREQ_GMI_CREDIT_STALL[1] TCC_EA_WRREQ_IO_CREDIT_STALL[1] TCC_EA_WRREQ_LEVEL[1] TCC_EA_WRREQ_DRAM_CREDIT_STALL[2] TCC_EA_WRREQ_GMI_CREDIT_STALL[2] TCC_EA_WRREQ_IO_CREDIT_STALL[2] TCC_EA_WRREQ_LEVEL[2] TCC_EA_WRREQ_DRAM_CREDIT_STALL[3] TCC_EA_WRREQ_GMI_CREDIT_STALL[3] TCC_EA_WRREQ_IO_CREDIT_STALL[3] TCC_EA_WRREQ_LEVEL[3] TCC_EA_WRREQ_DRAM_CREDIT_STALL[4] TCC_EA_WRREQ_GMI_CREDIT_STALL[4] TCC_EA_WRREQ_IO_CREDIT_STALL[4] TCC_EA_WRREQ_LEVEL[4] TCC_EA_WRREQ_DRAM_CREDIT_STALL[5] TCC_EA_WRREQ_GMI_CREDIT_STALL[5] TCC_EA_WRREQ_IO_CREDIT_STALL[5] TCC_EA_WRREQ_LEVEL[5] TCC_EA_WRREQ_DRAM_CREDIT_STALL[6] TCC_EA_WRREQ_GMI_CREDIT_STALL[6] TCC_EA_WRREQ_IO_CREDIT_STALL[6] TCC_EA_WRREQ_LEVEL[6] TCC_EA_WRREQ_DRAM_CREDIT_STALL[7] TCC_EA_WRREQ_GMI_CREDIT_STALL[7] TCC_EA_WRREQ_IO_CREDIT_STALL[7] TCC_EA_WRREQ_LEVEL[7] TCC_EA_WRREQ_DRAM_CREDIT_STALL[8] TCC_EA_WRREQ_GMI_CREDIT_STALL[8] TCC_EA_WRREQ_IO_CREDIT_STALL[8] TCC_EA_WRREQ_LEVEL[8] TCC_EA_WRREQ_DRAM_CREDIT_STALL[9] TCC_EA_WRREQ_GMI_CREDIT_STALL[9] TCC_EA_WRREQ_IO_CREDIT_STALL[9] TCC_EA_WRREQ_LEVEL[9] TCC_EA_WRREQ_DRAM_CREDIT_STALL[10] TCC_EA_WRREQ_GMI_CREDIT_STALL[10] TCC_EA_WRREQ_IO_CREDIT_STALL[10] TCC_EA_WRREQ_LEVEL[10] TCC_EA_WRREQ_DRAM_CREDIT_STALL[11] TCC_EA_WRREQ_GMI_CREDIT_STALL[11] TCC_EA_WRREQ_IO_CREDIT_STALL[11] TCC_EA_WRREQ_LEVEL[11] TCC_EA_WRREQ_DRAM_CREDIT_STALL[12] TCC_EA_WRREQ_GMI_CREDIT_STALL[12] TCC_EA_WRREQ_IO_CREDIT_STALL[12] TCC_EA_WRREQ_LEVEL[12] TCC_EA_WRREQ_DRAM_CREDIT_STALL[13] TCC_EA_WRREQ_GMI_CREDIT_STALL[13] TCC_EA_WRREQ_IO_CREDIT_STALL[13] TCC_EA_WRREQ_LEVEL[13] TCC_EA_WRREQ_DRAM_CREDIT_STALL[14] TCC_EA_WRREQ_GMI_CREDIT_STALL[14] TCC_EA_WRREQ_IO_CREDIT_STALL[14] TCC_EA_WRREQ_LEVEL[14] TCC_EA_WRREQ_DRAM_CREDIT_STALL[15] TCC_EA_WRREQ_GMI_CREDIT_STALL[15] TCC_EA_WRREQ_IO_CREDIT_STALL[15] TCC_EA_WRREQ_LEVEL[15] TCC_EA_WRREQ_DRAM_CREDIT_STALL[16] TCC_EA_WRREQ_GMI_CREDIT_STALL[16] TCC_EA_WRREQ_IO_CREDIT_STALL[16] TCC_EA_WRREQ_LEVEL[16] TCC_EA_WRREQ_DRAM_CREDIT_STALL[17] TCC_EA_WRREQ_GMI_CREDIT_STALL[17] TCC_EA_WRREQ_IO_CREDIT_STALL[17] TCC_EA_WRREQ_LEVEL[17] TCC_EA_WRREQ_DRAM_CREDIT_STALL[18] TCC_EA_WRREQ_GMI_CREDIT_STALL[18] TCC_EA_WRREQ_IO_CREDIT_STALL[18] TCC_EA_WRREQ_LEVEL[18] TCC_EA_WRREQ_DRAM_CREDIT_STALL[19] TCC_EA_WRREQ_GMI_CREDIT_STALL[19] TCC_EA_WRREQ_IO_CREDIT_STALL[19] TCC_EA_WRREQ_LEVEL[19] TCC_EA_WRREQ_DRAM_CREDIT_STALL[20] TCC_EA_WRREQ_GMI_CREDIT_STALL[20] TCC_EA_WRREQ_IO_CREDIT_STALL[20] TCC_EA_WRREQ_LEVEL[20] TCC_EA_WRREQ_DRAM_CREDIT_STALL[21] TCC_EA_WRREQ_GMI_CREDIT_STALL[21] TCC_EA_WRREQ_IO_CREDIT_STALL[21] TCC_EA_WRREQ_LEVEL[21] TCC_EA_WRREQ_DRAM_CREDIT_STALL[22] TCC_EA_WRREQ_GMI_CREDIT_STALL[22] TCC_EA_WRREQ_IO_CREDIT_STALL[22] TCC_EA_WRREQ_LEVEL[22] TCC_EA_WRREQ_DRAM_CREDIT_STALL[23] TCC_EA_WRREQ_GMI_CREDIT_STALL[23] TCC_EA_WRREQ_IO_CREDIT_STALL[23] TCC_EA_WRREQ_LEVEL[23] TCC_EA_WRREQ_DRAM_CREDIT_STALL[24] TCC_EA_WRREQ_GMI_CREDIT_STALL[24] TCC_EA_WRREQ_IO_CREDIT_STALL[24] TCC_EA_WRREQ_LEVEL[24] TCC_EA_WRREQ_DRAM_CREDIT_STALL[25] TCC_EA_WRREQ_GMI_CREDIT_STALL[25] TCC_EA_WRREQ_IO_CREDIT_STALL[25] TCC_EA_WRREQ_LEVEL[25] TCC_EA_WRREQ_DRAM_CREDIT_STALL[26] TCC_EA_WRREQ_GMI_CREDIT_STALL[26] TCC_EA_WRREQ_IO_CREDIT_STALL[26] TCC_EA_WRREQ_LEVEL[26] TCC_EA_WRREQ_DRAM_CREDIT_STALL[27] TCC_EA_WRREQ_GMI_CREDIT_STALL[27] TCC_EA_WRREQ_IO_CREDIT_STALL[27] TCC_EA_WRREQ_LEVEL[27] TCC_EA_WRREQ_DRAM_CREDIT_STALL[28] TCC_EA_WRREQ_GMI_CREDIT_STALL[28] TCC_EA_WRREQ_IO_CREDIT_STALL[28] TCC_EA_WRREQ_LEVEL[28] TCC_EA_WRREQ_DRAM_CREDIT_STALL[29] TCC_EA_WRREQ_GMI_CREDIT_STALL[29] TCC_EA_WRREQ_IO_CREDIT_STALL[29] TCC_EA_WRREQ_LEVEL[29] TCC_EA_WRREQ_DRAM_CREDIT_STALL[30] TCC_EA_WRREQ_GMI_CREDIT_STALL[30] TCC_EA_WRREQ_IO_CREDIT_STALL[30] TCC_EA_WRREQ_LEVEL[30] TCC_EA_WRREQ_DRAM_CREDIT_STALL[31] TCC_EA_WRREQ_GMI_CREDIT_STALL[31] TCC_EA_WRREQ_IO_CREDIT_STALL[31] TCC_EA_WRREQ_LEVEL[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_17.txt b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_17.txt new file mode 100644 index 0000000000..343869c5f1 --- /dev/null +++ b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_17.txt @@ -0,0 +1,5 @@ +pmc: TCC_HIT[0] TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_HIT[1] TCC_MISS[1] TCC_READ[1] TCC_REQ[1] TCC_HIT[2] TCC_MISS[2] TCC_READ[2] TCC_REQ[2] TCC_HIT[3] TCC_MISS[3] TCC_READ[3] TCC_REQ[3] TCC_HIT[4] TCC_MISS[4] TCC_READ[4] TCC_REQ[4] TCC_HIT[5] TCC_MISS[5] TCC_READ[5] TCC_REQ[5] TCC_HIT[6] TCC_MISS[6] TCC_READ[6] TCC_REQ[6] TCC_HIT[7] TCC_MISS[7] TCC_READ[7] TCC_REQ[7] TCC_HIT[8] TCC_MISS[8] TCC_READ[8] TCC_REQ[8] TCC_HIT[9] TCC_MISS[9] TCC_READ[9] TCC_REQ[9] TCC_HIT[10] TCC_MISS[10] TCC_READ[10] TCC_REQ[10] TCC_HIT[11] TCC_MISS[11] TCC_READ[11] TCC_REQ[11] TCC_HIT[12] TCC_MISS[12] TCC_READ[12] TCC_REQ[12] TCC_HIT[13] TCC_MISS[13] TCC_READ[13] TCC_REQ[13] TCC_HIT[14] TCC_MISS[14] TCC_READ[14] TCC_REQ[14] TCC_HIT[15] TCC_MISS[15] TCC_READ[15] TCC_REQ[15] TCC_HIT[16] TCC_MISS[16] TCC_READ[16] TCC_REQ[16] TCC_HIT[17] TCC_MISS[17] TCC_READ[17] TCC_REQ[17] TCC_HIT[18] TCC_MISS[18] TCC_READ[18] TCC_REQ[18] TCC_HIT[19] TCC_MISS[19] TCC_READ[19] TCC_REQ[19] TCC_HIT[20] TCC_MISS[20] TCC_READ[20] TCC_REQ[20] TCC_HIT[21] TCC_MISS[21] TCC_READ[21] TCC_REQ[21] TCC_HIT[22] TCC_MISS[22] TCC_READ[22] TCC_REQ[22] TCC_HIT[23] TCC_MISS[23] TCC_READ[23] TCC_REQ[23] TCC_HIT[24] TCC_MISS[24] TCC_READ[24] TCC_REQ[24] TCC_HIT[25] TCC_MISS[25] TCC_READ[25] TCC_REQ[25] TCC_HIT[26] TCC_MISS[26] TCC_READ[26] TCC_REQ[26] TCC_HIT[27] TCC_MISS[27] TCC_READ[27] TCC_REQ[27] TCC_HIT[28] TCC_MISS[28] TCC_READ[28] TCC_REQ[28] TCC_HIT[29] TCC_MISS[29] TCC_READ[29] TCC_REQ[29] TCC_HIT[30] TCC_MISS[30] TCC_READ[30] TCC_REQ[30] TCC_HIT[31] TCC_MISS[31] TCC_READ[31] TCC_REQ[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_18.txt b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_18.txt new file mode 100644 index 0000000000..a74cefd281 --- /dev/null +++ b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_18.txt @@ -0,0 +1,5 @@ +pmc: TCC_RW_REQ[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_RW_REQ[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_WRITE[1] TCC_RW_REQ[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_WRITE[2] TCC_RW_REQ[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_WRITE[3] TCC_RW_REQ[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_WRITE[4] TCC_RW_REQ[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_WRITE[5] TCC_RW_REQ[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_WRITE[6] TCC_RW_REQ[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_WRITE[7] TCC_RW_REQ[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_WRITE[8] TCC_RW_REQ[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_WRITE[9] TCC_RW_REQ[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_WRITE[10] TCC_RW_REQ[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_WRITE[11] TCC_RW_REQ[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_WRITE[12] TCC_RW_REQ[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_WRITE[13] TCC_RW_REQ[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_WRITE[14] TCC_RW_REQ[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_WRITE[15] TCC_RW_REQ[16] TCC_TOO_MANY_EA_WRREQS_STALL[16] TCC_WRITE[16] TCC_RW_REQ[17] TCC_TOO_MANY_EA_WRREQS_STALL[17] TCC_WRITE[17] TCC_RW_REQ[18] TCC_TOO_MANY_EA_WRREQS_STALL[18] TCC_WRITE[18] TCC_RW_REQ[19] TCC_TOO_MANY_EA_WRREQS_STALL[19] TCC_WRITE[19] TCC_RW_REQ[20] TCC_TOO_MANY_EA_WRREQS_STALL[20] TCC_WRITE[20] TCC_RW_REQ[21] TCC_TOO_MANY_EA_WRREQS_STALL[21] TCC_WRITE[21] TCC_RW_REQ[22] TCC_TOO_MANY_EA_WRREQS_STALL[22] TCC_WRITE[22] TCC_RW_REQ[23] TCC_TOO_MANY_EA_WRREQS_STALL[23] TCC_WRITE[23] TCC_RW_REQ[24] TCC_TOO_MANY_EA_WRREQS_STALL[24] TCC_WRITE[24] TCC_RW_REQ[25] TCC_TOO_MANY_EA_WRREQS_STALL[25] TCC_WRITE[25] TCC_RW_REQ[26] TCC_TOO_MANY_EA_WRREQS_STALL[26] TCC_WRITE[26] TCC_RW_REQ[27] TCC_TOO_MANY_EA_WRREQS_STALL[27] TCC_WRITE[27] TCC_RW_REQ[28] TCC_TOO_MANY_EA_WRREQS_STALL[28] TCC_WRITE[28] TCC_RW_REQ[29] TCC_TOO_MANY_EA_WRREQS_STALL[29] TCC_WRITE[29] TCC_RW_REQ[30] TCC_TOO_MANY_EA_WRREQS_STALL[30] TCC_WRITE[30] TCC_RW_REQ[31] TCC_TOO_MANY_EA_WRREQS_STALL[31] TCC_WRITE[31] + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_2.txt b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_2.txt new file mode 100644 index 0000000000..70b69f8928 --- /dev/null +++ b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_2.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_MUL_F32 SQ_INSTS_VALU_FMA_F32 SQ_INSTS_VALU_TRANS_F32 SQ_INSTS_VALU_ADD_F64 SQ_INSTS_VALU_MUL_F64 SQ_INSTS_VALU_FMA_F64 SQ_INSTS_VALU_TRANS_F64 SQ_INSTS_VALU_INT32 TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum TA_BUFFER_ATOMIC_WAVEFRONTS_sum TA_BUFFER_TOTAL_CYCLES_sum TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_3.txt b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_3.txt new file mode 100644 index 0000000000..e47f8e33c9 --- /dev/null +++ b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_3.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_INT64 SQ_INSTS_SMEM SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum TD_COALESCABLE_WAVEFRONT_sum SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE CPF_CMP_UTCL1_STALL_ON_TRANSLATION TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_4.txt b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_4.txt new file mode 100644 index 0000000000..2d96f365a9 --- /dev/null +++ b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_4.txt @@ -0,0 +1,5 @@ +pmc: SQ_WAVE_CYCLES SQ_WAIT_ANY SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_BUSY_CU_CYCLES SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE TCC_EA_WRREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WR_UNCACHED_32B_sum TCC_EA_WRREQ_DRAM_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_5.txt b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_5.txt new file mode 100644 index 0000000000..e50beed390 --- /dev/null +++ b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_5.txt @@ -0,0 +1,5 @@ +pmc: SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU TCP_TCP_LATENCY_sum TCP_TCC_READ_REQ_LATENCY_sum TCP_TCC_WRITE_REQ_LATENCY_sum TCP_TCC_READ_REQ_sum TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN CPC_ME1_DC0_SPI_BUSY TCC_EA_WRREQ_STALL_sum TCC_EA_RDREQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RD_UNCACHED_32B_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_6.txt b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_6.txt new file mode 100644 index 0000000000..15a2277c1b --- /dev/null +++ b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_6.txt @@ -0,0 +1,5 @@ +pmc: SQ_THREAD_CYCLES_VALU SQ_IFETCH SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TCP_TCC_NC_READ_REQ_sum TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN TCC_EA_RDREQ_DRAM_sum TCC_TAG_STALL_sum TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_7.txt b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_7.txt new file mode 100644 index 0000000000..b42ce91618 --- /dev/null +++ b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_7.txt @@ -0,0 +1,5 @@ +pmc: SQ_WAVES_LT_32 SQ_WAVES_LT_16 SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TCP_TCC_UC_WRITE_REQ_sum TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR TCC_NORMAL_EVICT_sum TCC_ALL_TC_OP_INV_EVICT_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA_ATOMIC_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_8.txt b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_8.txt new file mode 100644 index 0000000000..21d4c7a998 --- /dev/null +++ b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_8.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM_NORM SQ_INSTS_MFMA SQ_INSTS_VALU_MFMA_I8 SQ_INSTS_VALU_MFMA_F16 SQ_INSTS_VALU_MFMA_BF16 SQ_INSTS_VALU_MFMA_F32 SQ_INSTS_VALU_MFMA_F64 SQ_VALU_MFMA_BUSY_CYCLES TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TCP_TCC_CC_ATOMIC_REQ_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN TCC_EA_RDREQ_LEVEL_sum TCC_EA_WRREQ_LEVEL_sum TCC_EA_ATOMIC_LEVEL_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_9.txt b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_9.txt new file mode 100644 index 0000000000..9ffe5778c3 --- /dev/null +++ b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_9.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_FLAT_LDS_ONLY SQ_INSTS_VALU_MFMA_MOPS_I8 SQ_INSTS_VALU_MFMA_MOPS_F16 SQ_INSTS_VALU_MFMA_MOPS_BF16 SQ_INSTS_VALU_MFMA_MOPS_F32 SQ_INSTS_VALU_MFMA_MOPS_F64 SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum TCP_PENDING_STALL_CYCLES_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_5/MI200/perfmon/timestamps.txt b/tests/workloads/kernel_verbose_5/MI200/perfmon/timestamps.txt new file mode 100644 index 0000000000..676cca1b80 --- /dev/null +++ b/tests/workloads/kernel_verbose_5/MI200/perfmon/timestamps.txt @@ -0,0 +1,5 @@ +pmc: + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_verbose_5/MI200/pmc_perf.csv b/tests/workloads/kernel_verbose_5/MI200/pmc_perf.csv new file mode 100644 index 0000000000..68b236abe3 --- /dev/null +++ b/tests/workloads/kernel_verbose_5/MI200/pmc_perf.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_1,obj_1,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_2,obj_2,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_3,obj_3,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_4,obj_4,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_5,obj_5,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_6,obj_6,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_7,obj_7,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,wave_size_8,obj_8,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_9,obj_9,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,TD_COALESCABLE_WAVEFRONT_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_10,obj_10,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_11,obj_11,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_DRAM_sum,TCC_TAG_STALL_sum,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,wave_size_12,obj_12,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_13,obj_13,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_14,obj_14,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_15,obj_15,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,wave_size_16,obj_16,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_17,obj_17,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,TCC_EA_ATOMIC_LEVEL_sum,wave_size_18,obj_18,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7faf0bc30ec0,230680,131907,16384,0,16384,16384,32768,49152,28834,28834,1992463.0,1416205.0,3424.0,151322.0,1123559.0,0.0,1408683.0,1111503.0,228969,140030,28834,0,28834,0,922688.0,493585.0,0.0,0.0,64,0x7f3fa0d08ec0,10920182,9928588,647530,344064,1635530,0,0,163840,832.0,515136.0,0.0,524288.0,263908.0,32768.0,484575,0,0,10847,131072.0,131072.0,0.0,131072.0,64,0x7fee1fd78ec0,0,1294043,4096,4096,0,1179623,4096,4096,0,1343759,4096,4096,0,1307993,4096,4096,0,1140025,4096,4096,0,1612067,4096,4096,0,1186362,4096,4096,0,1315869,4096,4096,0,1131318,4096,4096,0,1133330,4096,4096,0,1108961,4096,4096,0,1305492,4096,4096,0,1187943,4096,4096,0,1145887,4096,4096,0,1313106,4096,4096,0,1324761,4096,4096,0,1198429,4096,4096,0,1207007,4096,4096,0,1131412,4096,4096,0,1383544,4096,4096,0,1029790,4096,4096,0,1819610,4096,4096,0,1462597,4096,4096,0,1176151,4096,4096,0,1129491,4096,4096,0,1106642,4096,4096,0,1224066,4096,4096,0,1140871,4096,4096,0,1248507,4096,4096,0,1062605,4096,4096,0,1166831,4096,4096,0,1345424,4096,4096,64,0x7fcdf8740ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,12268,18688,7820,545,0,26156,204286.0,0.0,73206.0,131080.0,64,0x7fe6bad74ec0,0,393216,163840,0,0,0,0,0,18307,0.0,0.0,0.0,32768.0,0.0,0.0,381.0,32768.0,4096,16384,352,28734,1982,0,56.0,7.0,0.0,204399.0,64,0x7f0732708ec0,6336,0,4096,6376,0,4096,6376,0,4096,6449,0,4096,6360,0,4096,6390,0,4096,6364,0,4096,6395,0,4096,6398,0,4096,6340,0,4096,6376,0,4096,6376,0,4096,6453,0,4096,6364,0,4096,6394,0,4096,6364,0,4096,6339,0,4096,6390,0,4096,6376,0,4096,6349,0,4096,6422,0,4096,6412,0,4096,6374,0,4096,6582,0,4096,6415,0,4096,6340,0,4096,6393,0,4096,6378,0,4096,6347,0,4096,6425,0,4096,6415,0,4096,6375,0,4096,64,0x7f779dc18ec0,2218,4099,2221,6317,2301,4096,2301,6397,2289,4096,2289,6385,2323,4096,2323,6419,2287,4096,2287,6383,2291,4096,2291,6387,2247,4096,2247,6343,2297,4096,2297,6393,2295,4096,2295,6391,2220,4096,2220,6316,2307,4096,2307,6403,2290,4096,2290,6386,2325,4096,2325,6421,2291,4096,2291,6387,2290,4096,2290,6386,2251,4096,2251,6347,2274,4096,2274,6370,2283,4096,2283,6379,2280,4098,2282,6378,2283,4096,2283,6379,2322,4096,2322,6418,2323,4096,2323,6419,2296,4096,2296,6392,2441,4098,2443,6539,2274,4096,2274,6370,2272,4096,2272,6368,2283,4096,2283,6379,2279,4096,2279,6375,2290,4096,2290,6386,2326,4096,2326,6422,2327,4096,2327,6423,2349,4097,2350,6446,64,0x7f2de1778ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65551.0,0.0,0.0,0.0,64,0x7f6e6cc84ec0,4096,0,14,0,4096,0,151,0,4096,0,0,0,4096,0,232,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,91,0,4096,0,76,0,4096,0,46,0,4096,0,68,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,65,0,4097,0,147,0,4097,0,6,0,4096,0,65,0,4096,0,17,0,4096,0,0,0,4096,0,0,0,4099,0,0,0,4096,0,77,0,4100,0,0,0,4096,0,82,0,4096,0,215,0,4096,0,26,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,64,0x7f0da5fd0ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,10375,0,814,26950,0,73182.0,131072.0,0.0,65568.0,64,0x7fafe65c4ec0,0,0,0,224,0,65536,64215,56,64,0x7fb469ab8ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131080.0,34503.0,46188.0,19348.0,64,0x7f01a6500ec0,0,0,0,1092005,0,0,0,1089074,0,0,0,1035974,0,0,0,1162858,21,0,0,1221153,97,0,0,1207141,0,0,0,1054401,0,0,0,1132993,0,0,0,1000441,0,0,0,1083011,0,0,0,1022785,0,0,0,1026577,0,0,0,958099,0,0,0,1079211,191,0,0,1244224,9,0,0,1233237,0,0,0,1043911,0,0,0,1074089,4,0,0,1073967,264,0,0,1390233,0,0,0,993520,0,0,0,1068643,0,0,0,1059660,0,0,0,1134638,0,0,0,1168395,0,0,0,988146,0,0,0,1043386,0,0,0,1223013,0,0,0,1170092,0,0,0,995145,0,0,0,1070150,0,0,0,1165258,64,0x7f14d1ef4ec0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,64,0x7fa9abb20ec0,0,0,0,0,0,0,168,56,131072.0,131072.0,0.0,987560.0,64,0x7f45db7a0ec0,114688,0,32768,32768,16384,16384,65536,49152,27583386.0,86084092.0,39380069.0,131072.0,0.0,197650.0,0,0,15345,808.0,131080.0,0.0,8.0,64,0x7f4ab1148ec0,32768,32768,0,64,0x7f919f270ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,39771619.0,35264159.0,0.0,64,0x7f2c30ad0ec0,1223,117633,0,0,65536,63800,56,1680,199855576360179,199855576380339 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7faf0bc30ec0,303864,210822,16384,0,16384,16384,32768,49152,37982,37982,3017252.0,2430599.0,5004.0,392631.0,1603801.0,0.0,2418147.0,2109628.0,303856,219933,37982,0,37982,0,1215424.0,782486.0,0.0,0.0,64,0x7f3fa0d08ec0,17457179,16858737,254378,344064,2526932,0,0,163840,0.0,524288.0,0.0,524288.0,534338.0,32768.0,737631,0,0,11538,90762.0,90762.0,0.0,90762.0,64,0x7fee1fd78ec0,0,3118224,2832,2832,0,3261055,2876,2876,0,3655187,2876,2876,0,3725380,2876,2876,0,3655126,2890,2890,0,4218172,2852,2852,0,3800127,2892,2892,0,3247809,2828,2828,0,3713563,2828,2828,0,2704879,2832,2832,0,3180484,2876,2876,0,3445378,2876,2876,0,3438040,2872,2872,0,3949512,2884,2884,0,3914862,2848,2848,0,3064322,2892,2892,0,3261739,2824,2824,0,4429124,2874,2874,0,3383179,2844,2844,0,3517378,2844,2844,0,3357375,2828,2828,0,3737385,2900,2900,0,4115302,2846,2846,0,3843878,2824,2824,0,3894509,2824,2824,0,3078837,2824,2824,0,3642306,2876,2876,0,3805127,2844,2844,0,3120755,2844,2844,0,3299928,2828,2828,0,3075429,2900,2900,0,3865800,2848,2848,64,0x7fcdf8740ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,31503,27653,9598,2884,0,39454,200900.0,0.0,69815.0,131085.0,64,0x7fe6bad74ec0,0,393216,163840,0,0,0,0,0,29913,0.0,0.0,0.0,32768.0,0.0,0.0,241.0,32768.0,4096,16384,302,41069,2026,0,56.0,10.0,0.0,201195.0,64,0x7f0732708ec0,6275,0,4096,6266,0,4096,6246,0,4096,6263,0,4096,6242,0,4096,6236,0,4096,6254,0,4096,6259,0,4096,6258,0,4096,6278,0,4096,6265,0,4096,6247,0,4096,6267,0,4096,6243,0,4096,6233,0,4096,6256,0,4096,6274,0,4096,6258,0,4096,6265,0,4096,6252,0,4096,6262,0,4096,6254,0,4096,6227,0,4096,6223,0,4096,6223,0,4096,6274,0,4096,6264,0,4096,6265,0,4096,6260,0,4096,6265,0,4096,6257,0,4096,6229,0,4096,64,0x7f779dc18ec0,2212,4100,2216,6312,2229,4098,2231,6327,2217,4097,2218,6314,2181,4096,2181,6277,2179,4096,2179,6275,2194,4096,2194,6290,2168,4096,2168,6264,2177,4096,2177,6273,2177,4096,2177,6273,2211,4096,2211,6307,2233,4096,2233,6329,2217,4096,2217,6313,2184,4096,2184,6280,2185,4096,2185,6281,2198,4096,2198,6294,2168,4096,2168,6264,2169,4096,2169,6265,2203,4096,2203,6299,2235,4098,2237,6333,2212,4096,2212,6308,2189,4096,2189,6285,2193,4096,2193,6289,2134,4096,2134,6230,2178,4096,2178,6274,2182,4096,2182,6278,2166,4096,2166,6262,2200,4096,2200,6296,2244,4097,2245,6341,2209,4096,2209,6305,2187,4096,2187,6283,2194,4096,2194,6290,2198,4097,2199,6295,64,0x7f2de1778ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65550.0,0.0,0.0,0.0,64,0x7f6e6cc84ec0,4096,0,298,0,4096,0,57,0,4098,0,121,0,4096,0,871,0,4097,0,927,0,4096,0,538,0,4096,0,1030,0,4096,0,1340,0,4096,0,557,0,4096,0,313,0,4096,0,554,0,4096,0,611,0,4097,0,292,0,4096,0,2357,0,4096,0,1070,0,4097,0,1090,0,4096,0,898,0,4097,0,1084,0,4097,0,752,0,4096,0,447,0,4096,0,1710,0,4096,0,610,0,4096,0,625,0,4096,0,1619,0,4096,0,1520,0,4100,0,125,0,4096,0,426,0,4096,0,683,0,4097,0,1464,0,4096,0,530,0,4096,0,1195,0,4096,0,738,0,64,0x7f0da5fd0ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,21337,0,2714,38454,0,69733.0,131072.0,0.0,45609.0,64,0x7fafe65c4ec0,0,0,0,56,0,65536,65536,0,64,0x7fb469ab8ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131082.0,105091.0,45612.0,0.0,64,0x7f01a6500ec0,0,0,0,1547715,0,0,0,1895436,0,0,0,1639521,0,0,0,1912827,64,0,0,1748731,1139,0,0,2134241,0,0,0,1581029,266,0,0,2089147,0,0,0,1839559,0,0,0,1511723,0,0,0,1853730,0,0,0,1998002,0,0,0,1471157,26,0,0,1845058,0,0,0,2011350,0,0,0,1667585,0,0,0,1849370,0,0,0,1901748,81,0,0,1879494,171,0,0,2133104,0,0,0,1516145,280,0,0,1881994,32,0,0,1987480,0,0,0,2122447,0,0,0,1580493,0,0,0,1972374,0,0,0,1673834,0,0,0,1760131,0,0,0,1667013,0,0,0,1445299,26,0,0,1763949,138,0,0,2052419,64,0x7f14d1ef4ec0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,64,0x7fa9abb20ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2003653.0,64,0x7f45db7a0ec0,114688,0,32768,32768,16384,16384,65536,49152,57785445.0,195794080.0,46777541.0,131072.0,0.0,506614.0,0,0,23278,3912.0,131073.0,0.0,0.0,64,0x7f4ab1148ec0,32768,32768,0,64,0x7f919f270ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,118741265.0,58141396.0,0.0,64,0x7f2c30ad0ec0,0,204845,0,0,65536,63800,56,1680,199855576464819,199855576481459 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7faf0bc30ec0,328312,221517,16384,0,16384,16384,32768,49152,41038,41038,3156901.0,2474907.0,4814.0,365446.0,1623645.0,0.0,2461722.0,2154515.0,328304,231043,41038,0,41038,0,1313216.0,767227.0,0.0,0.0,64,0x7f3fa0d08ec0,19141904,18041249,756591,344064,2767961,0,0,163840,832.0,515146.0,0.0,524288.0,579320.0,32768.0,961827,0,0,13250,91256.0,91256.0,0.0,91256.0,64,0x7fee1fd78ec0,0,3317020,2824,2824,0,3917642,2872,2872,0,3669871,2860,2860,0,4815879,2868,2868,0,3724570,2870,2870,0,4117769,2848,2848,0,3483454,2868,2868,0,4210386,2828,2828,0,3168618,2828,2828,0,3609674,2826,2826,0,3412411,2872,2872,0,2953535,2860,2860,0,3780585,2868,2868,0,3806005,2874,2874,0,3795130,2848,2848,0,3911999,2856,2856,0,4582343,2832,2832,0,4440612,2836,2836,0,3488933,2854,2854,0,3351485,2836,2836,0,4894774,2832,2832,0,4223851,2876,2876,0,4446861,2820,2820,0,4601305,2832,2832,0,3916128,2832,2832,0,3862893,2826,2826,0,4301803,2828,2828,0,4111966,2858,2858,0,3511557,2836,2836,0,3643517,2840,2840,0,3233508,2876,2876,0,3690737,2820,2820,64,0x7fcdf8740ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,29653,27002,9610,3157,0,38993,200335.0,0.0,69252.0,131083.0,64,0x7fe6bad74ec0,0,393216,163840,0,0,0,0,0,29946,0.0,0.0,0.0,32768.0,0.0,0.0,232.0,32768.0,4096,16384,302,40895,2005,0,56.0,10.0,0.0,200454.0,64,0x7f0732708ec0,6269,0,4096,6274,0,4096,6245,0,4096,6259,0,4096,6262,0,4096,6271,0,4096,6272,0,4096,6254,0,4096,6253,0,4096,6266,0,4096,6274,0,4096,6245,0,4096,6265,0,4096,6268,0,4096,6276,0,4096,6270,0,4096,6272,0,4096,6271,0,4096,6262,0,4096,6254,0,4096,6251,0,4096,6250,0,4096,6239,0,4096,6282,0,4096,6284,0,4096,6270,0,4096,6276,0,4096,6267,0,4096,6257,0,4096,6250,0,4096,6252,0,4096,6243,0,4096,64,0x7f779dc18ec0,2188,4100,2192,6288,2185,4098,2187,6283,2167,4097,2168,6264,2178,4096,2178,6274,2151,4096,2151,6247,2173,4096,2173,6269,2187,4096,2187,6283,2168,4096,2168,6264,2165,4096,2165,6261,2192,4096,2192,6288,2183,4096,2183,6279,2173,4096,2173,6269,2179,4096,2179,6275,2151,4096,2151,6247,2177,4096,2177,6273,2190,4096,2190,6286,2141,4096,2141,6237,2139,4096,2139,6235,2193,4098,2195,6291,2179,4096,2179,6275,2146,4096,2146,6242,2178,4096,2178,6274,2174,4096,2174,6270,2178,4096,2178,6274,2185,4096,2185,6281,2141,4096,2141,6237,2141,4096,2141,6237,2192,4097,2193,6289,2180,4096,2180,6276,2143,4096,2143,6239,2182,4096,2182,6278,2231,4097,2232,6328,64,0x7f2de1778ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65551.0,0.0,0.0,0.0,64,0x7f6e6cc84ec0,4096,0,726,0,4096,0,1142,0,4098,0,686,0,4096,0,863,0,4097,0,963,0,4096,0,5,0,4096,0,398,0,4096,0,830,0,4096,0,644,0,4096,0,1569,0,4096,0,735,0,4096,0,0,0,4097,0,0,0,4096,0,778,0,4096,0,110,0,4097,0,490,0,4096,0,617,0,4097,0,312,0,4097,0,986,0,4096,0,400,0,4096,0,688,0,4096,0,697,0,4096,0,1169,0,4096,0,1587,0,4096,0,335,0,4100,0,364,0,4096,0,115,0,4096,0,962,0,4097,0,192,0,4096,0,419,0,4096,0,262,0,4096,0,936,0,64,0x7f0da5fd0ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,22740,0,2720,39449,0,69871.0,131072.0,0.0,45668.0,64,0x7fafe65c4ec0,0,0,0,56,0,65536,65536,0,64,0x7fb469ab8ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131085.0,86862.0,45515.0,0.0,64,0x7f01a6500ec0,7,0,0,1718556,601,0,0,2173730,9,0,0,2184674,0,0,0,1566960,186,0,0,1769966,0,0,0,1335502,115,0,0,1566006,69,0,0,2027798,148,0,0,2088893,245,0,0,1747696,0,0,0,1601415,0,0,0,1539228,0,0,0,1741793,57,0,0,1604001,0,0,0,1361187,167,0,0,1811428,178,0,0,2212179,0,0,0,1716561,0,0,0,1415555,110,0,0,1827595,0,0,0,1559563,45,0,0,2042839,0,0,0,1596467,0,0,0,1817249,0,0,0,1879937,0,0,0,1754566,0,0,0,1932763,0,0,0,1541753,186,0,0,1946934,0,0,0,1451277,0,0,0,1397953,0,0,0,1691843,64,0x7f14d1ef4ec0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,64,0x7fa9abb20ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2095169.0,64,0x7f45db7a0ec0,114688,0,32768,32768,16384,16384,65536,49152,59553355.0,201014624.0,50577064.0,131072.0,0.0,536773.0,0,0,25345,4083.0,131082.0,0.0,18.0,64,0x7f4ab1148ec0,32768,32768,0,64,0x7f919f270ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,122091435.0,60575096.0,0.0,64,0x7f2c30ad0ec0,0,195561,0,0,65536,63800,56,1680,199855576502899,199855576518579 diff --git a/tests/workloads/kernel_verbose_5/MI200/roofline.csv b/tests/workloads/kernel_verbose_5/MI200/roofline.csv new file mode 100644 index 0000000000..71240f3964 --- /dev/null +++ b/tests/workloads/kernel_verbose_5/MI200/roofline.csv @@ -0,0 +1,5 @@ +device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh +0,1388.8767,1388.2836,1389.4698,5016.0059,5012.9766,5019.0352,9224.0928,9223.3945,9224.791,18051.355,18049.885,18052.826,20936.43,20876.176,20996.684,20265.637,20265.018,20266.256,170439.45,170435.92,170442.98,164875.23,164870.25,164880.22,41421.074,41420.531,41421.617,41476.754,41476.145,41477.363,166335.31,165844.97,166825.66 +1,1389.168,1388.6588,1389.6771,5028.2383,5026.2607,5030.2158,9235.3203,9234.7559,9235.8848,18094.438,18090.258,18098.617,20975.785,20908.943,21042.627,20295.773,20295.225,20296.322,170850.08,170846.11,170854.05,165119.91,165115.77,165124.05,41485.68,41484.938,41486.422,41544.367,41543.547,41545.188,166856.59,166852.83,166860.36 +2,1388.4858,1387.9718,1388.9999,5036.541,5034.3604,5038.7217,9263.6934,9262.9854,9264.4014,18109.801,18108.615,18110.986,21050.965,21050.545,21051.385,20356.039,20355.549,20356.529,171162.62,171158.59,171166.66,165532.17,165528.11,165536.23,41583.977,41583.031,41584.922,41639.477,41638.352,41640.602,166952.73,166361.81,167543.66 +3,1389.3755,1388.6982,1390.0527,5032.1636,5030.7754,5033.5518,9243.207,9242.6523,9243.7617,18028.232,18025.232,18031.232,21036.127,21035.678,21036.576,20314.527,20313.791,20315.264,171022.38,171017.88,171026.88,165242.08,165237.72,165246.44,41443.5,41289.41,41597.59,41584.898,41584.383,41585.414,167024.86,167022.92,167026.8 diff --git a/tests/workloads/kernel_verbose_5/MI200/sysinfo.csv b/tests/workloads/kernel_verbose_5/MI200/sysinfo.csv new file mode 100644 index 0000000000..bf0083881d --- /dev/null +++ b/tests/workloads/kernel_verbose_5/MI200/sysinfo.csv @@ -0,0 +1,2 @@ +workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd +kernel_verbose_5,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 02:41:49 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/kernel_verbose_5/MI200/timestamps.csv b/tests/workloads/kernel_verbose_5/MI200/timestamps.csv new file mode 100644 index 0000000000..b02f2351fd --- /dev/null +++ b/tests/workloads/kernel_verbose_5/MI200/timestamps.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,357956,357956,1048576,256,0,0,8,0,16,64,0x0,0x7f847a4d0ec0,199855576335457,199855576360179,199855576380339,199855576391773 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,357956,357956,1048576,256,0,0,8,0,16,64,0x0,0x7f847a4d0ec0,199855576391062,199855576464819,199855576481459,199855576482615 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,357956,357956,1048576,256,0,0,8,0,16,64,0x0,0x7f847a4d0ec0,199855576492554,199855576502899,199855576518579,199855576519625 diff --git a/tests/workloads/mem_levels_HBM/MI200/empirRoof_gpu-0_fp32.pdf b/tests/workloads/mem_levels_HBM/MI200/empirRoof_gpu-0_fp32.pdf new file mode 100644 index 0000000000000000000000000000000000000000..e4bd70888bf7441d1b7b23354a57dc982ac469e1 GIT binary patch literal 12635 zcmb801ys~)*XR{NLJ3Lf0R#zw38oN1Lb|)VYv_^?DG?B9>6AvgJETMDE(Ph9jys%l z-uJxmt?%ADi#0R=;A8?|72yQ~ z!8||+5Do@Hp*&CyAn+;r53MJIGXCFH`1$cnY>jV^0QvhUMg{;79=DJTfLj*jU}IqY zw-V3aO2UG-N`Iv<1Kpm{$; zV!ML~ncr7fy;wZ}%g*~1c^eu(nCIi8yXIYcMaZTJYiaFU-^^*}UWgZ1p_1h0YL7#K zaYCDX&h@srjnyC{+9GvYb%yTOmD9Lu34n0ft&9HoKp+y>G%-Wrr zL_?#Jig$vXBz2#`qbkxjqgxU2Ukz^`D#-XWb${WNGDg`XHd&3E^|_12yKfii$t938QRIyZ7NH*V5v!TfJ+o3&-6C5IU8Uu9=5=Yk(yFRr^aed*$rN8gk{>lX zH+B;~J|B4CGIbmw@`kvCw>11C`m%ekEU$RkQ)9AqLqdFFZO4l}viiqssCYYH_Rlb8 z%*anEG%*ODVfC~Up?%gw3e9NR`KVtM>+G@L3dgOSF>T2`rPzm~vkd*H*f^cBK?D>;t_F(`S^#jksTv+?4aa z@L87*1H1Ta#+opZ`$;nu<-0b<(*4Y^_~5iZq$`>Nnb7A zehscqME%?v{#n?Q${Wx7=1Ur}A8SqKXFT$3$TqUJr`RQ@KxxPlr`#cwRyqVn?B z%NGNd&sz;k9?=F^cMGxI442cM@IbxUvStBz`d%GdewGm}dfUmK_Xnain|VJt-4}~W zaCIP!$ZDmbwMA?+lqb;KOgC9t`dd9O%maCBe-rE`Pq*mO`{gxG`fTEON^wtn#z3ZZ z6y^IhYq|RJ)$WNPG+?6AYmC%(!kGfIbvSFf{sdc4-Z$s`dXWUTqxPq~dgSo7^%0`~ z`4Z#lm#9~(i|Tm&BOME&DoNy^#ZLeFpQGu=BNk&&llKh@wB&qB~dNoMs<8ber7)>EfhD2;iT0kGd##BGn zcRDVKP}f18&CF@&BX9Qu#gD-&1t`Lx^K)=EafNtl43{_^0knzI(WKKjo`^X)D2Agw z!QVi5rUcJM9b%|n?W&$>s?Kabsqd+NI9Rg$Rq*QhacWp{u}UXQ@dJBM4ljq5)w}Y> zFr=7YQ0H;B6tpB(Eie8zVHlxirWuoEpJ_4S#&M-ofl!t57bfjW)Al2klyT&oLu-Ef zxb}08tLm^{9$i4uPerePOD{eN-Cniq0*>p~>nFZ`V2Kjk=FGiH_0yECI@D=(6qJ#q zjZ_SpE630Z+kJcRi?gH=tE#%?IF-v8LYjjZIxD6DcrU zF#N~kqoXfz-`_8+cB^*m^xk0rElP*1F zm^Vl?8~Zw{Ltw62K?a-C6vi)GGp&mD;NG?;@6+U#6)s~M%9o|%cn@BPpp-Ibj1A>W zX6MO*VI+)ZmOJlBxpAxt<#M{TsT4-jGXrXtsi^YQs^#-pQK>#5nUt*Z;LV}toY$aq zlj9#t^u}sWW^TvWU%mLRfd>A&k1M;|nE<%u4b0H(ThYW3<@<9_AlB&OtaJ95!W#UOy&k*SEsEye@5or|~c zpn%({cKZ$vxSdIg=+Vh7in4XOT_Fks!2XooN@YxpEewQEZU8MHS_lP0xjCdi5pX+=(DszjbJWO5-oW7xA$r*U`4)iuYm>ixzP9RXUmp;6TNd#raKOIp*Q+sr;(yCXe@Iey6F?wXWPHl0X87;iaL_WWfDbQyr{#?_v?-Jd%Gx zL=FNQxDycp0W3I-qA)TdCh*5QVAe+>#@ctxXeg9lYBRR?x0?tly64#P;(Qo7yShI2 z^47^~TBxgzb(BpmvZZ=_r)Ev+Zq0Vp?DKKkUcEal)=m>XVhgi(hs<0O#kO7UXzo4_ z`fSF(ci0zlM>=Zl>>aMsVMsK)9?FtFo1cTFKZWv5PwCv_;U=<1|&A8n7IX<{3lp4cTeC~0X6?}%Zzw3R$R%yY%1`f8JOocY$e{`U) zjAD^VKHDq3_vk_1i`3QBv&9PBvjHoaT?L;EIs(}NpBiy@twe%vJ9w4%2v_8iKLJ-) zQFj#^M{k_IS1iX5(6^hvIo9j@^$Nm5{+s8@Pd|b3WelH$MN5tj#^KF2d+ORA(i0!~ zt?z!e+zN?o1*<#H@x#aT!NoTfRa03+bObm1?KC{QTQ{?E2Miazn^4a=8u%=|m(J@> z?oY1wYBXhQCMwgnqwiN@8^6IPZzFblNEh@pjd;9WbP}^(Uw|fna1nA!?rofeROhkk z18bmQ@51zdXfPzU(HTM}=_ic}BW(=pC%s*wy;}H<7Ru<6zX<3CW)7t16A71@PTh37 zbM}HxA6{c$KQ8{6c*@n3O22{>QF}C|qFj(Se9gGcEviIo`K{Y#Q^t=8djomjJ7F)4 zX#S;JNs6Cf+iMw=2*GzB*v>AKrx?xz5gk=qrT^~3r7M3&q0>7{^+KnBrF!90Xj{9` zDbdm_xi!7?CIKqFmEV8w9Z{3t-U|l4=soclLCvqihH@i6WX!jPzfQ1l{>gf!a*yH> z9c|kP?gDii#JurBbKH@FgpQ;Qf*X#%q~YHcuxH)o&cGLB=ZzyE?dFLy#LUOwPtTxD z)W+=pG;lA||ADX@-O`2dDWU(<06Vs&9tOVDy=Wp`eQ&mdyE8@ib;VBwwR}U`wZu4Vki0{0sI9fjQ4ld!WF?v^AfM_7KT_B(ruKU0b3rYdnv*+ZaPNgnd!qp55AuLc`^Qha;+g55rhXFU z4>9#Tgqs##gi(giA~LUw$0>1j1em6)A46m_zl()^@58Zyi3&{eCS=`dX2X(gXh$6k z`Y;QB%oLWhji%}T&d_x4Ah>t^IUtqD(rZ|bUtx`o;hbgkT;$8-hw!xB^#k1Wh1YF8 z&02z@P4mhK%sfD70H6GkPlUB})$b~N{i^LsT8sj(5-(P_ZL6&qqV<$jT^#R(R?&*z ze(U3yTA`fduc)o^l4Cl#bXyO)SSX7G7--Yl-DM(*Q@xp2ylJ zJ#1TgFQYN_zpRq!R?YLoB=_AL_pCyW3VwK*uO@^D*6cTDS`(cyJ$lVOx?s{>^10Vu z(IHQ{Ncp+q0KxC{$vdQd41tz8|Fvd{0R3?n}_>7ED0r=P6`Zg_R9C^^{()364bW)Tm} zSzP;yND&l0|1i#)b(Z~ovUXsAA$eVV^oV&Qi0E^B9y)fwVAVv13!c=AD~BH`m&ZXS z!uUyP2fWrn_}0{wc=-6w@2Yshp9N|-{la5ki+xI?2Prx>j#2Y!C{ z>6EC;``no!@>WVWJTm?}urf%;1n%i0asw`I=CPjT0FfI|!se4OJ;JYeD}vJ4ts`r6 z3UXFq@Ft_uOpi|1xb$e%!2nLpuvIAYFuS7R%;Y20;v!#mM8L_C)8!{lRpJnP(qxjA)ppcBV|H-i7wa*aS)yhh;z?QcR&o%r+F5cX5eu;UxIr`Uito2^ zh&`nOdunH!#0Y>nxpU-UwtHZcOuO|bpnMF)XZ^OU7Naj+#IN~Q6DBi_LMV9dJ>7iS9_w8Y%93ouCfD9)mk?0? zeDXP8cj{7D*`kQ&NoU4Gg)0Bv)G^H8vXzspWC=mNFQ%uhR+vUwd^n8qv_aSdeR-Gq z>ry5uCIu!1bOk4)@HL;xY%1oV)e3wI&f~;~^*@cQfD3i6lgcLuiBKJ#)D9=9{MIzf zk4?@njqQFg7_G>&vd0KHKiEgTT}zXx#hX?!Rh8<&%9%+1(u}K}vne-W=3h%P+k?B~ zFN8%E0?OWho6CdrzW())GiLk?`OQz}1njME(6!N&x0M9-xZg4bKke9gfopi5xf*k> z4FuJPQE6}U05R*scvCfYcjlAH%?pS0sZQKqJPNjPcQKPw(=9Vz%J`}hLnilSj889k zo`U;*3PqEVn1Ddv#)d^BXT>~^QR8Xa$dd^OsKg^02>IsG_~jCeQdh0%`n8hX!IiQ# z==nfKLqVg`?K|Uu61PY4mG;r;4#w-lkhkIiadxl$r= zZ7H5qMJ#xp1)8O#H=Cu@_C8zADNy?=*PpTaE^3)J|Ea~&v+;Nnm0-hCk?3HlJ8 z@RFFwO>WkT4=lFk7jK)q)j#jCJNx41KU;Mh2qzjU{4$bGYw8fRxv41<>HaF82qYf5 zZJ(jEWK_peGq&~f8N5fOM9`2n@f1cqT4PeL$d_jNvORvA=k6J?36cF)P*`hp?%Lzf zqk0vr+5G$?#}~i6hjmwUisYs5#tp{rgxjT)Z(7o5Z}-t^)26)MU9?2)G>YI#HZsZZ zdroez(`Bsk+7~R8TQ>L6eor=kU`n7Sn#&{|&KjOuZq%D0O=_PJZSL^mIv%K%NTx#r z8Ii+o%MJMcz=-@@?+u0FtdYJn7!)ywRd;MUl{~{z^<8?ZQA0I*`OuODpS8bn9^v2d zDaNPkP^vT8<1}J~so8Y?`b0FCW2PFF+OB%?sm^6Fsn@%@!BJ^-0ySG*$*SrpHj7HT z;$qpE5mYE4Ic+;)jy+}eEn!b>>@5>LRKps7@?~806qXZs(SD~<;kxQ>9DU1^Y! zM@%~J3V34YFl_Y+FAC?M&6DVbzko5H6y*hd7_*(LtTz0yniEKypy25_s@8vuVCkAD zIzLM7=@GN-Eqr!U{NBd#{d=j%=^b3m`Gu=Bg1iZ=iassz9E8TUqRUH*w=pEF8Y=d zS)dS&Gm!4rz?Sq`P%Ac2XHwoJXIu6HhqrjhFnrO_G^ePd1hd~E>TW&B9PU&u?x08& z!g1AYL>*eYPm^NZ?;)sM+Q3vHOl=W__wGRbF}1XEhRhE0m&rBusOsLz{=ou$U#|cQ zDQ*AM^)>9d&tGe)rhZ>6*A3FwWmSG7uifC1xED(Yh6# z%}mJW4c+?I64_y~e^M&O62^boB86(c8rB(F$v3MCd730^zdqyhjvm981a7i5S7Lxt z)H)FB3qD^76p+Yj_#Lb7kcFSGSdm}zK_z9(ohHofFXTp!TtukaS={ z>6dFsoyK%{QJrx`T@-QUchC7f^0vt55u8sY7^JZ$HTI=)Op{99Ta%@I zl`msU9Fa2KK0@j=6&63LyPiaKJvq?wT2)&P`iR7A-^`eQ$4}!p>4P{9tEqDvaTyXE zg45BocRE3hcX1to4mnfF3><)Db{jk^lMv&*uOIRK7I;^-N-tW6zN)OAM>05usC5J| zP^<5L9^$W$w)B)y)G{?od2|B$<*HX|*FMM3u@m;g>ICJn)8hLJwjDRV6p8xzaP!+z zn7*E!lDr}rmlwcsGuJOMs&b9RAvB@E!ambBmayAfnrzrZIV2uz79XymoP6o1DB%t z>nB5{b3-iqK~vV(tb_8apXgw5rJp^Uw%M8pIAY$BA4W#tlK>;=N#oqgSZiDAeM%}U zW``m9nQVBj(5zC$(lV@LbSaal?Qhy>yvHXVXw-XPi0yGkV_s|GWu4NMTx2Irsat4 z;S}x0a|wf$-migY;i}eTam6sNfpEB&W|ikxLtR!6xkON-`OK19tj)oFS-#)n3*FS> z9wfoK53=sR&v2P3^>Cw&rqj*n+#Y~EdD<2R%+gwb1V z5O6w{Lq)GgE$AEiSDfBIL~*S{Tf0G_Ng-IvQ6ILx$+oMNKP8p@EZXg3*%c0%D<$U#0GCp%vX5VoK()pDp9>Vm2p=N#`cD)R?{0zRp;BjMU3TbGjSO)P@UO zm91k9`_4THR@PjQp|q=suP;hdMX0Ll`*v+j)JJ$6|Gvyf0k;HoL|P9$y-Sk%j!@%u>=Wl&D2sUs z_os{+6`5CXF&SObv%!#xNI?PR$vyzBK<-aJ%`0!O)thWbq-mbxkGnHJwtKfX%#(sb zJ|3u%z&XeVx*GU2gH>mgc1B}!*z+vQ$bqi+csciUCAljLV0X^TuRYVi@{KywSWFc{ z{2K9v{21kIH2o^8`Q;U7ro4F;d09TBn9oSDPt&q9b0)>MQ1m>sN<-RV@=XjzCIi12 zRrlW~8y^k|w1sqpFXuB=i`I9u4yiV%-LSjF#`UeK3q5MiR1_)&Q4$POGR#vM*tdi{ z(kyDHRVQv<&`VVRq5H_d4=1!jtAE^$=k-N3^NQOqCoj|Nh?cC0<$=9RZ=CgAq zM?S1fFeWZ0ex{ERAHQeINdjSyDMAVFzr}5ZAxn|=$bF=5l7A8m$@YpZ#Heq%cexM4 z1UF=+P%=-lHi>wGx58O|^G!od!)e1yT_FW+1y6-ERs-+Z%hNO8Gu()16>X_xTT`96 z;3;sexzv=RYTIv0SA>9*%dfW)o|D4^zS!b@n&SPq1@Nz zavLABv1T3|>Ma~i8_2C6$R=0iWbsI9Y(Leo`QBjM?!87H+NPN}qDZ~2wNx0aL5)Q> zv>gE(pz+cwhZD&x7kBAsvk2IG__eVb9=DX=2 z8S0xpatl|JocCQ_b(PdzSJ3Jkk<)H)d&}Nj5746_6;MKc(%ZvOXxH~RL^g=OevIYy z7F6QTsX`;QCG}ggT9H~Xk;3L+(%?sC@0urJyq#na0aF!el~5i_ z%1O<<%?${chp9K<$Jg|spA8;IYX!)mhmA&?pIFL1e~_kblIWR_k9FDk+2d$oF%uQ} zjsg3ygf94C03lHjoqHhkFu6IhrR$kgzm&>Ch;&h9>Ai@`6sj3KpV06`FVn~UF9xr@ zf1K)=C4rbDeua&U#l(7oE9I;etW~yNm&O^5@qY{Yz2xQTWjIQZ?c`YZ*^eJTyVSxn z0i_vg((lwG{x)Kfnh#Ux%cwEXOi_~Bbw+k4(ZTxC|AdZ6tpgN0eaZ|O+bfcqnBYB~ z{2uhdd8eVk3wu0lowOPCD0RGOuG}i~hVC`bEOea}R+e zpPuDU?Nku#OA=;F5t_!_b+M~#Zy8Sfoo}_JqV@~)P%O}4f|=J|B8U8F zSzR>pZvM{nlp68!{83I#Xk)=X(jY_ql>Aahvt#o~bZx~K&%+pUC-b0awMBqhyoT>g z|Cdf((N2dZh5LkY%;r6%KQ-Pz%a5Rb(#y2G2|ZFc_@Zhtj{pk_; zcE2}0v@um<ft|QjYFB6D(JyPc9;ju#cA?ZbMFecF+NHE9 zjqx1f=yvbIDGrevLQT?Mvkif2`BnpowLuQvVOs0T-w2eVT`Ut~P4T8#3{q?;xm08G zI4T`RJhZK*KMWP1e*sP4=ehEa+kd)JM*PB*SNu5Zb!=YiwPwnt&Is3a%SyIUWkR(* z`1yp>XN#wD*5}cuSFgNnj$1XkYHN=Po|(G_43{$gF3YdP3B$~Gzfqx&jA4u2D!>mV zs2byo6@O}8%92|24E6>J!p_uYv3ovX%GqV(vU z0zPA6dz!~;p`u6@Bfy+2V<}tq(e!cMV!f__w*skNNJiGNK*QdOa3#bv233#@GFz#d zp5`BOq@VKbqf5SOk5jZsnE{LiqGpedQep5IHuw4+`Wy32TM8m@lWFW)YgbVi0p;VJ_blTFGYt?=}fKKm5uMztp%W*Kf zFLBYRvL#n#^v36LVy(Q!QH70X&M|dTd@2fYnX?nG0Phj-2Ciq`4!=IUhdy`xQrpkB zJiOxbt{DPPX>_|h{aU=hdpvM|KQ@=#A4W}!2#x4Y36=njxaoT=`=I0-;CD~*;;qgzh z#G{fnCazSQi%4qs3C0PkQesm)2gzA)M;BT+Jd|C&@%LLuOk}PCqeo-m6Q8PL`dX`t9SfI$ABdU17 za}|f6KsDrz5EuI}M-Toih~s+lT$}$W;Co+em`|D9+<59W?|HXhfY>3$mrpfJH9zu( zZnSH}*2@cY>St#cTQJ2gocmx~GSYm}$uBm(v?6;3v)%_#yLL)&<`}WwOrLnT~&D5(mzhcVg9aa**;=FHhUo`IXtNzqKyL>-qr)uMl zY|sp@Z2gQWw!8hLbAhd+R*{E5{n#=_fo5PavJhK`pkAih9LF?gxuWi8qQwhWyUHoI zGxGP=^Hvc>Uj`AJ{$OV&!pktesha!+G2>o%NE}ptAOUN8$-{rnM6SYY27AMGLwGxr zGxIl_N4!^)SJ+(Uy+;NrHmX5ml&zk#pKC^O=B$2CXV88hBo$}m#AUq;jTyA=@rZ=> z#2TV@&37Nx)CUbhnS&OhXLNlp&h0ksW>~ve%|6tBBs-8eH|{bvOR4X;Ecs#Z z3+&ckHd!}W)!)=#+Fv`UXi!vAI|=c8hMaMFn+*ZLkMwj zYcgGn3jgA6CvL0ycFo;C%)}^M+G8`~_r2Jk?84NkB0sQ+Lp`sQA3azk67ZU|i!&N+ zzM^msbr?RSx9@AtioLnMi38E)=h@a?(+OZ>@$48iB@T){k{A8`AU{SKF3*`(S6a!v zw4zLLIZw5rZI^fW)8a5Lyo~OHm4b8W-r=VFp5(B)S?Kq#X+SksBNJ&y~AZzSC#d}1U z01{q7a)tTu>5)ZW>Q2lrVRZp1WUbm%NXnh3{H9dR_Mh(Lbv~q2F2f1Sp*w)HMXkGo z#wdBz_@$Y9?*Tuq#=o?}O5^4eXTIaAmsl`qE|XP|Wdrk~ke9o<(I4ZQP#yRjV>+U# z^ss3MzSf-sx^d;0@4mv^NJRC+zCVsY*^#DcWc_@fJLHz&3jY1z+o?r`N7KGE{JKvj zb+wtQ+3T`e4nLLNx{1A{HRMLJGZnI*BYFAVR{*Dhaj!XQKb7E8j9FK- zD(2LSc^tmziho+vg7R3LxZ2BTDF*Miof&KdNbSY)FqT1_ox)fUcg)wBh zY^HlzK`ij-v=sXWMkv7h#)s^b!TH9HE(PgT?_o-p(nKrgMU0mJ8H?8l}<-KibKCZnr!)lMwa8#gCatjm20?}z*OFPERlf92E6PR?QZZ8+T z;p1Eqs#aLzThG(Rab~MsL+f_$>?9U%T^W_txk{H%p4^WSVEIAkTdcZl>syRdNPb$@ zqJwoBdCzr6T-B9)@xwNqvl!U+WHChKCAD;@RO!SW1AoTz>fAYFB(K;v%m37WM#hkV2guIC&Z5emE+C zlLRNE=WL18PSuPI4aZ61*fYQ$EM2muHN#Dsdh-<@k$E=52fk97vs*k}BuzO#h z%4_mimK zJ$#<6RjMQwGTjqE%Q?wFGBW+NzyfQMe=M^~u2Y$?N=ia?=J(fVW9vj~l^I^p)O!gG z609nFLyZ0S#nzX1JK_2?r9^6PN?nekFt0F-sDO3!q6$os`o?!fKV~sv29Bidu^!NHBs63#2)62ip;g`*J?2$+ip3_>8#1kCL+ zG)!Uw2K+&r+>$hZK`x+wK~?{xTyAy$T=BQdXlu8W3z|JOa5TA9_;=5hoDH4+pn`-Y zL~cL5H3UXGBq5@V5|a>-F|b2}KgQ^oSU9==Ay#sCM0+n`Yl^yMc@#~|EYP@-JAhRX zP0yO3QCm3&V-p7pTQdObKbE0|O3rq6)+RQ$p#|PTKWewMj}{CF-ih^j^2gtb| zbQJq+{eVObhh+TOLGR*vgoVWMEuIi~2x+Goo}@+_iEMXB;C|honsD>`o7b z7^TlBoYGenOHsWVu{5z*E3RU(&z34^1QO>Lbz$u{@38+k8`PF<7uQKooR?B!xRi6{ z4Rs+dFdIuSs3Vw~9sQTO`wxqW5qlir4SIOATKG^?d{)+)iQQOxdGbj@WOhyK`XPwF=ZH-FZnTC`2hlDNHFLPCRdn<3LC(S$o(0En&LJ zpmAt|k+w+2(PIlE5eed1+4;8vGxvj^L=*Q8Wbn;`fx)~h58g5?tiGX3-!KkQeI-@! zEwT3I@Odp^b(7}iYHxTjHg9;@n3E4G8(wa8eSN2atbF>vd*E%3{~N>hXIJ=Vq2E?G zx*h$`?ckLy8t%TW-hUQ7r}#g5ps@kE6QNrK8l3y1^(dl~Lm8!FYjMkiqd9Q&zW>sl z+#F0y@qhpj6c6~%2LJ|zLZARsz&~XmG$(lb0NDOR20|dwb@1;pbdIB~|ECOHk^dd*!K`;=^4}<^(z(6RJAIb#;vSa=*dWsHa|GSE)D3Q6n8FmVgzoue}0)UA4BoqOB zN)FC;DBHi3`2SKuier`jRDFsB0EzgX%K!1Ljg>1t1@IH`sfz>9&aUSFvoGlXlP~Ze zzA)eat1p574`2VcdBOkkC2eJk#;iV{v@K?xCCyD8%rLP$HMh4!KL>#LVFIF}02ego zz1b0Yq;Khcd$|N7@jcOA`}m?ZLH5@z3S7aU4BvU!6EWkNx%X=nYsc3C3Hyrjww4JK z{7(dWJvOHvxO&JQnCJ`1o@JBxdmCN^Kba9cx){Bj>lL>&{gT7&`MH>{)wR_p|7y|n zlcg#{i|rnuc=`7jKGfFdY_|FLjb8_1x>`W#dwkq0>L>B7+KO4Gk@D;^o!26GDO+aW z!IiN@BG-F;Q&zv!7kEACZ`;`f1U)btCoU%wzns2odK?*ElDT@~BY#+GLf zUf6Xd<(lb@m{X^G(4EOF`H|Se6nFHJn<@roOem7gs`|%PusTUX(`}Go?mcejga|yBMZ|PUR@@V(Ptz3qj(yc6giQ-}y;Ymj>1A~k zgVl?1F=l#PXHSJlk}QdRRPscoKe9B1Ay2k@tNniMMtJto%oh<2Ead*qoa~AExq{Lm zpG?S`QUX#@Aoeo731X!+>VR-gl&kC^LB@uukS z>(wl6;vyp60Pjn796!C!=%Sngc)7tQs6@fNvs=8__G$B`LEHOyFk1t_oaAF7rQrOB z4P(*hM6Yvy1a-#`u4rkGuJV~&`Af?;=ffWh3?ePXoD2CI#y~ui_2aoxXw9E6wGSUm zPUuoc(&Y4S+I)s?(=-&l(HCD_ylE#tR4P6bqCPQO`s2mRq+&8E1$ZOymsd08%XcEi zyUSd35`(-+Me`1;P%UOe)IH@->9`uuJA*gk-9(+5Zxz273Mgufm44Ur>js{$T7jMY z=u+{Z+ibf5F{fs@juaID!B_1_&9x|!A+BEc#DSD8^QL;ON=!*e&w6TLz#W_Bb`w)R zHyeG;=Gjs^&EvpQwVFwv7!pgC(7LU%A~LDvq{7`x(SjoJ zmfFf9yx(6}iyj_oz0vw&p!Tz-#l;I%EP*-P zQucBto)lz#`->2%VY#o!B6m~$RY*J)#do>}aI$RNkxFSbIgJG48*!nhhK}mXYI*gH z1M#Z9D&>Q;p36Q0+jlk6b;jug zklmqi;>t%>WD0S19TE0D>p!|5dkouyPb(&c0K_VRI!pJIfc;dj57RKM4qenESF zgMycll-`v)j#nj{J|!x331G!(#$ny(`V#3!rQ<0S+gx+S>X8AtO(vRuANr#eVy;B^x>cRO{Mz$!UYGTVk|jYw*KlaOI_s zSV-mlZ@5_(4CCA4TMXkZ3-3Zd(a)!8Z)mD4_0fNHWKj??emdH|$mlZqVl*k0W9@X6=ZJRJr{HwjU!`TJx7NYrnZkW7mT6hR z(6}ckoUP!JUh-tp_m2iusYlai>&c7u9pwD|d;)oYPC5D0eYgZCF@zlqAdhk~${#B3 zKjkktSN-kCZ)M5ZaF#5aD6_lx_OO1yf}y{&Sn;y5_tsMUTIw0?mBU*~k9mSmqU0GP zK4+=rUIUJu?u_X#@4fn|^5U8LR`UMptsAT*bP)XjU1rZqCsl5v9@IaiVPRGu*y1Gw=VH@B-s`x)zA^5KjpyBCg4&YNkSz-#m znz@UEtFx)O3jouuF|FBD-5d?j|D!AOX_$MU0eo_H7)6PHT#^5{${7;zNqL}U)X~^x zjWLyh0I4O*qGa+T>#iVhViG4>A>k#~}ZR z8TtKl;#}czte;Wq$ zZzrBV8z~3?!k%6*!TvAJ77hkO|Gn8xczOD0NY(jkW_UZef1ekc)0Jgk=T;=Rd7r$U zw?>uPEeHpPKkf-ZTJjT}JJd-s5;`Q|gjElxHJ(KGJh>IG8UgrL9{_ntoQ>ne&$NVe zl2G%^w|6I_^B>x|JoeEQcsnLI(|!W+q+7dKNnVB0;q@&wQY!;^~N zVEmT2QB%-YA+q;}zK&*UebH}?bd|#GAJ@fZ@4Zi4~CL!ZMl6yN3)KWCj2zxyTokmd4)pHgd< z7^s`Ogx+RYO~(k99AiPQ%aAt2U|Bu=%9gU&Olaz+TVjS8jV#sn-3}4dgw8xOj*3tg zebU0in1LEy0Ty&zYSsczI6nTaRwr_tWcQJ1i8mLz;Jn)HnqU!i(;&#hT< z(e}jt`uRDtT%S=;%U7`jH~cg1E_Y`v&aSP&j_S47u|%itO=0}K(;Jyl9uhZ(k?HiG z4(|QL*}c_Ce%s^GqTJ03oWLdN9~@^w-(-(8@31dihTT5d z5f^5A!6=?i^GP>c26q>SPDqb7DiC(9x`sLbJX%HO+0l&13lAc+Qedx+9?5f559aJkG;8>L7|z+xavUxHpy6eYtY=XZVR8JG z(J67SDQV89f*WhB-7KSQ*Pqy#%l&!P79SB)vb&ECHl!Rn!?H@>=-sC8B>1%NdgC)H z#@ZE7q$OZ=`Rn#&X)4L3R5W=)2ldM)@=+QE0d5$#$Sqd7e&1Admq9X{F%1PZgrXnF zEvLgk(P<(#f*v#KOs3<0RYAZ9q#@qsr3shn{AQ&SYMc^)dlXG@&Fj-nw;21H`1XqG zvTcTRwan5;P_aAm*JykKs{R*_!K1sD{h#BB_4RM-jna6}h8>bh&9DLJUpWoZz{QTA zH(z*9&I#@6Gp0&g_vkjwvv~JvHQ?KLrou8H>D1e0?X4JAaSMOwrmy^qqf*q{cCdb}AY z)9+nz82mxiQt1_k8j>$w!kOagW}ynZ2tc=o6@J&dm(oD0XPujqy;1hw=wi-UPBLX> z*zOSLnXvTXAV+ESvhbXenB=dQqbtiyo)1`HaklwX@#WRa>{WDNT~LwS<9_71@`Axn zrwa=;4%84*vt5^I9{J0uG-Adb2c5)cJ?W|z&1IQjC?B&p-nIBx!o+)xaHhZ(pt+3n zps;9TM~6^wHFMlyS@9!$0^|JrQ6LH=&tMqd6jdxcFtn;LjpjQGODs(bcWLE;w?pq% zhQ(zItA&}jm>@H~#wb-n6C=M8I6o86k#FCF2iaHVS)Rp7=P^HSPhSPBlf2HMvm8Cu zZ0HwT=qVkg>Ty9B_WLpYT(~*@L3sUPUn-n%6}cR)6whj$h~A$nN^w`QuXX689u_jq z7IHt=oG=~pERvJ1^~}o8tA(0IQ}D)?Ce2O!n9x?3pW?exjxj=S^Rt*n=QreD-wx3I zZ7KHRMEa#ThqVXo&WZmM8}cZv{%04oiH2J#{1erEb&u;NAAehZmT}3TtV}%} zy{S8E=)9a~nbJ7`Zwz%vcTj0pLX-F7Xuh1!D!E3;v6<_056wQ^R*^>F?!#>1-;I;~ zefizCL#geCFZ^Yss6NC?{gm z`F$b#z6S20o#}Uwy_%I&8LAvXV8(4+61}`9>gaC9s5ytB7PJnvia2JfzNHK|#iorO)y-zqa4^f#7@3`&-Bf2--4WLuN$ zibF?4sK!&L9HxP9{<4tOdV^M^o3yabI{DNq+D_K0=43O1m|uWRJ>+Bh%ebjy?$Y9H zA+E=|bv{y>=3Nk4%Fo(OI}^oCC$AmWds~g(AH~$q^BV9O>GSnjPDC7`6RGLd;xd1D z`PyHA9aO98k41nw&Xzjr9CBI2YPE+M+x^o+v)#Nr%39X3}Mg zkZ<=(wl%-cny@wIl6oT{=)K{{NA9K-BK;Nx$t>mFjT;N^ckWfCj{xsKUhq1J%jsU; zE-af;7QKjbspKkM-vnd^yg(l#7=V^Ys(O{<3U-o+QO&Q07a^k zMVvK-oVK3IG~1J|uv+3Ul@EqV;f6`M=x+zdmIInYNB6raOw?&K=N`dSm~01;MTRNJ zq96z(joQ|L4-V(eEcb$5hbEN!A&H7hSpCY*^V)9~ch@6o&eWvkvR6hL*mKyIJr{CO zg3)l4nh;uK8)23S{$PkYr4wMdYEP=wf6y{;$>a%|&6KKY>XFnF7;WZL+?WxCNsr_n z}$J0@KiBC@*+sLW9eH1e;83~sJj<@H8-j?k^U6$URyWhVGO(wZ)41~x7 z=frW+QQOB1X|(C8c&y?CkKolY{z2VhL^lSRB-QJ>Luv2C)RmV_*AV9>JoOEo?MW}7 zQ?{>>ta{GkipX6{KHjs6?~xT)ejJ~7)@HaV-g+c-=6$iTm!D_Z0y#J>oSDNX)wcb9 zw%M~(O{^Sy8JU`S%R%F^Vc2iiOL_K{n(mbmrS~co#e=R|vE{ucf5#EgtjUk{{f#R5 z)OrVMMmW%*lpD!ogw(E@;E-HAYqbdd5e2rvH`MW<>h5GYpj(!*uW6*=rcFnPXbfjh zR9)q$)$Ht;iGt8WIhm(L-6ll*jCZ#hj8kQ2#w6FI!^ZFx@21KuP5bcr-qKQm*yjdF zBa7(oOflHRD%}o&^o^Z%Mdj;v_s_5PJGLN>q@GDtEB_$1`%K>_)yLf9VN^1%WXV@4 zRZ~2QD7H1X(2`0@om_L13au|BvVT95D60=?b}_PbKSichJeXzDzl5SbwFf$Rdo=sI z2Om@tr;xvSHCxMLA|M)6kyNB)DhM5c`vv%mU3HE-IShE54Wzu05q`^QG~55SPVcPN z;i}jF&|_%+m5;~9*AAyG)tMDp-`rK@#U5%SgE)x+RyH-t5{-{R?%#@@nu9jxY?|_@ zgM_%jJ$FV_7oMSk1(J7CqpY6WpGx`qC=HyfdAczSDOj#l6Ycu~6U;}rA7mv&0rL4F|d{fV^M34*k|1GiqWIxI{+$GgMWfa}FL zw|7x#I=ln#d+@ch_NUnH4&%_`cmLm%*U~O3VP+s19*aCwAz zp{zQ|brvj@ASWxsM%-H0PnX8UlUwu6_H&tYJ||U2IY$QyK9{5U?)zy14*O}1cx6T{ zwjH77{gc%n1l}as&#S35c-H*buX9R!Mww@}&bs)xS#3NK#~odLEj5Q58}D z1i&2w!ct$NX!1DGkM*DYtds)krDBk|y?S2KuAQ zDl!>MY*Q-s-`iRd2HjSSs7dDQY8H;k%({n|Bp1rm-9G6GjVGE=S<)^STy6@vYvg(>G~O@#jKW-QpZu5k1|lW z+5fyylsVe%$9&Q@)8d1=XGtNVGI5!rcjG&(aD%ni=!d`Et$)nDab&|p!79o(J zB%0q6*vuWDTNG&9FG51$DRB0IRZ3k5rxzbG5a>yAeXOxy6@LlYJb+m0nZ*50D&_vb z8J}UjE_dNFc1I6yVuipnBx0TA-VfV$hx66pVn2cIG-VO?^Q3Az>U;R zj2Wy1hnUIBhjZ-ixFY$OINOUOc1MyoAuJnUw1RO2%UOhr6tk|sRptwq=QM;vS&|EM zZ2Rm++7%mzf)@Et`TSncXxx67V=b%gN^fs`a zLStPu$!>mWRBuPH?X@f`z~o1J!X>3%T> zQF{HNzS6~9eG|jbwxdXe2W5bxI{Z%>((;msFL!*lRtIf7@176wh=1qtlUB0!JXs%2 z$UiZ-TCV2Pf5uW%8!scP)WUc)axSxfpY>_gM0W225k>WrUeAqkAAiq}J+_g+2d>>? zALW~JNFh@krr~W8&xlm5dEAuc##P-gSz_0E~kub2~R35r(rdAD&Jmg_G}i|D!ZY@&BQeV@&R6Q%LxUn znXDsO?$UeSR_@-mskj{;-qBu#Bkrp~ZJVdLmkI|06JN&+qmTFtTbU7p~emn-j)IVy&o! zv@5WQsb%vqrFMc}ky)!9ZsAFW+bMp`()9@npJFd(WgL2Ga9@{_P&QxsYH0X1#keqaI>u4js3##T2&~g<}xDU z&G6gS^yGR0UQ(JW75ptquFR45HIea;*$F?7iPJf$A|w2AH@zbIYT3NFYrd+Q>MfDF zgPIkTLxEwnt@=WAUv1a{;yGfTjSIu`_s^v$BsHX(sGLM3wq?#o{7T*y8`aOsy~$Aq zqty=NLJyvSjWzo!xPp`fQwB4T=Y;#KGf%axy<>rucY<I zss_&Ua#anLae$}3RrR8q2X6f8kq%-~mm5(Rp)o#W=b1SxQZ_~E*C%ZEkg?t?v(*cQ zi<=aQCU;fiAXLRtS1LKrC16I+y8D*%4{3FBn^aq0A%KjU$@d^%Ny+$J5*ou|9BbPZCQt_7IN#Xq2x3q^p<-1wKYkP zJXOFkC9?Z$hKm$g@S5YE;G07J_S?_}R}_rCQvb+{wWI8VMLlu^)MdSwN5lN`I66!D zZ78kY3#!N;#PTou!@0usskB2T-!AfY)ppaUK==(E=L#8HIU@VZIS4Pm>m2v(%}l%W zpNtP>wz?_X*|q)(QQi!yk~;9aP%9Wb&<~lZ*b=I{u(DJrO!PJG>y)x<%!s1HiMMyR zv72+Su|uYPW$1Hj-Y{wXsz2%fMc+WDp!7Rru*+2{6G(j!tcPC+od_3hL($(P)xI_o z$=&ZdCgx(2lCLb&F|y^*ii(lSGjXZRozk=As-r>_wU>oW?}*CG9|4PZQ!al$hHZXt zT@ZBLwVAx`ZOwP9M;{%o7aO&@{9@EU6Kab053?^|_o8LrT6jZ3B2Bb~6I&X2&wZ32 zH|ZfVLrL>cQtZkegy&4-r z!N5F=smudZh7Q+=QC$$+SE-+WKPF^)?oOs*_}uo1b4^f;*p~~ATQS*#k9oeM8nVY) zMp)#UfW0a96L#pdhIh0(W}9Ze?AA(;VaG5Ukxt~24t{M=rKw5+q;~>Tk2DJ_z)_Y! z8~8-%nQ((%C(|#QlbS{rQMch(RJ@?HCBxeS(9Nm^KN984GHMSFUJPa>+_+zKzl=TD z#00VN22PbLBBN%q<6|5z*>$ghwvSZnuD_Fk?sTW+`NU4k*`yOYL%&c;we8@tZ;S8n z)#b2fSdJgQAi8JZ@J?hMdRC+E$kBFlucoGwIn>Of)QPgcZYP#P@1+dOaZnR|Eu9Nq zRLO^S1rO1(u{TB1iItLvurR6TA0JSwUEoW!8k*?9Pb0sJMLqvPvdv?H{LO!lauY4e zv&a=n(Qq7sjA<~sB*vAhhO@Ktx0aN@5#pDfHAw)guMn~ zrQW8N3G|zy1(P4Q#Y92srgV0yJ?x=vC&!!ijR&R~gC?*-Jlyd4$GS1Fy;+SxI zpt%(7l;`0hqaaiKc|Id&gg=R!wO?f1zS};JVKp-;^Q+l!-%c6d0esP3_TLn5hw_yL z4z;h18O&(Rj;0~K1cHGvfh3$rhSKQKn6F~C9y;{qbmk9jXlw>6evSykG&3wxEC%bS z)~R$J==AqI?jTwsQcw9fpk^^=RshsWhUvrf-D%uYj&+Z9i??=W_@?!@Ua6j$5g&;a zY|2Q*$(qxKid8@FFhxStvpsjn(ZclpCclJ~Z5ebDIPW<4;W3QOvu{}J6G(7htjZ`d zbDLgoU0NiepLzSQ`x{oBpM3X~peXFF+8FZQ1ow71y{!oHkSBeVtJCsHEyA2D$$W zR(9ilGEACvidECfA~p9 zndOX(%l1@zV?5rw*03k=X@YFtqLscd?l+dJO9|&n;|t0i2UoLnk2F3SNAg#_KW^l) zB%|*b?^%?q-{_z}$rY-2DiHyBLAiJ9mGBd`SL-Zc(QGcgvKPMT6ik^YRc?T1SrMSl6&ash~)mifWBXUW;ko^K`Z*U%*F$xHFy^A5j`NeG>B+tX{ANC2G)6=W<-fhTt{g(&OL*YYo~_U zC{CWHz8{GXGQD!=njgGm*-XnGgz3`8XFDyo=>{(oRSZj}yFWZW_;KoEAR=R zYIRwBEaq{2T!>Qe@n8vKW54Jp7R&!MD1X{}OU${xZK1V!HwgDimvFLq_p<2s@(#kF zIC$rARwZGJU7!Q}BAd!5gH#*g^ZJ(dL+L*4$5}UpV9~+-Mr^%r(th-_oCbD$M;OQl z3}@`>vikHbkmFz2fqZ;OuKE_3H?Kxa>OB_j?ss)LF5KN+z+c!8qZ1_vJ3%ykUN9u} zUv+G`Ka>%ZIP3(cCA3ug!5{XDYja;tpoyO3h)&7TBdQ~fZvMwEJLzXc(@@sS4iKr# zmWux3Ya7Hk9fEDr5$+6E5OpSb$sJF6J;KE}v|rnfdV46tN4L1E$4a-n`#8*+wA>LM zN6e>hd@WkuBt~_-<=XSRsbcab-=h&eXj>HBvmX^<9rpN}ixnLS^6AmrjwL#Vs8AZZyl-PG>&&Q! zVTDmBBCUP+)77|s)cvpsI%h9&H}Yr!@dsft@aQF=TlC{tyFk!mVLCcCvGiNni0Jm$ zGP%e+VrjKBVK4=Qb9;E3_&xzCjkHHx$1V!y2@gZTsQXX^btDTwk2pmJI-DS;fqeii z34aG8oTMQ5>h1PLdxn3wZkP1?RIl{Q zHPLuP4)(N1y#$7W zw9CA(HQN_ToN-elTE=R23c1mgQJ`GT9gpBg^}pfX(X ztZ%mmeEl*@X=Al`eV1|nI`zf(OUaA7B*V?y|BZBD2#LRO3Rt#6(%i+=*~$@vUH-{h zD52~yw1=d*HA>4>9c7QfA28&fr3)5i6n8Pj02BZO7|sg@gJCctjM|?f9xw#T3x^=! zSg;UnZl?v{$2?;mA#e;nfpU~Jx3YYW20);2UaS&EOAbRwSec63TiTjqiAn5CB>vzz zctAifkQWLRfP(-${4g-a4G;zafCLZ_UVf+mhLnJSdHKO0I2;3dV9hYhggF@S2ULLt zM*hKafc}l;{1fKD>i%i*SI8J|SeOF?XQEupu?qhgxw@+f`VaU8DJO~j73&C$2}n*- z!$C$)QW52d;akiwYhs1={6nnn>4J$~&fdZSi>#=bTUueL8czU+I0i2@$FQi%&SvJ$ zR`!+vj(?hAgzB!2j<)7@*rf$x*%oaq)S?dq0(pT50T>o~0RkW(0baNO2#7GmMv7%! z5I|lK1SWuq90t&bz<_@)|6hs#2n5E90PzE17!w2lEC7IE1Yih|UjP8Xn84utyg)b@ z2m!$0FkT=8it&RT2}9FhF&YFE0s;sK@be;oU00Ss~j zM}Pou%&QVWfDu@5M*xnI0uc~600xBc0>J{9lRW?vi9QsF9RLRUrz#A>&np0fV%{&5 zAHfR;^24yK3=9OtOcawln1liI0K(eL-O3}P90$UO}mf-O?>BTQ$^1p8y z^Kq(yk{;n-wOG7iQR4}KE@kYMxp%x5ew~-5bGm@1+15ET^c;W5(UnN&_M0Ib1K?bt zmDH)WuU*iWsAA9bcYKOMIJ(_Br|Zg}dk1X~O2Y6m19#`F95X&v47#g&8W@&dhA<3t zz6T7agnkuj{(4-x9T39tEotVh`&iRas!ZpkZ2)0sdX;KW=*U+h13O+avv?y!|B&Cx zP3p@XgM=ch3FR%I;PHqm%X=U3i*Sy4=7d|S&eDk#;cobchV<}O8qsa`*zk5--93VP zVq~5YYO)f9_6g)4L*oqcBr`eroa1p5K)F=vxCvE>`+53xiNY(HvQ3E&HudFrR*_mGj?zOYfJOU{SR5LIL1V`Kx7y?3Y;HjW1c0DKz<+%JFenrP1y}(7B?Dn#H|z&s|4$ia(_wbc zf66eajq(0>8D_uzT?U5z-4+CbW2?vCY%%-lzhwNF0`WIJFc|n>V_*QZ|MG_|D1WmB z0b$r$@*m@ZfN<#F#|43~_55FYXlE3rk~?Gn4?x|@3$v~bobB*2uOD~(y4Tpgrsz*(%p>+|M0%= zIqx~=`>yl<|6E+m-uJAvp0%F6V$WRnW_Tqg!2#mr#$XuR*;>K?0e}D-eRB+celAga zBRzzTJ%Cx%)ZWI*%+ZPkgX@*OjiIA~5fW6fFw^5g>H@5Ic#t3bA#7%2EvAPs0x*m5 zfq`IdAOr{p@j`ikKsF$d3HgVVleaPa?;?VN7)I8H_bx#GcEvys0K(uBkq2-o*w|a? zS^h1={kM>)@V(HVqH>}DAO@G5%pd>N?{RrK05=AgiZB3S?`ZVD+k*Z-*#iGz3;F-Q z+JgUo*!sWu#q+l<2{TIsa`(9;ERp*xW@KPvh>S(f$l3&93IK7#cm)Lk4hZCRv%+vm z-P4@2UWH-3zfj+-_pXnY+J5vLHThlT&>Y$(dQPL(bNLU}cht;g?v^YD?oNy{=%!2r z->Bwjad6Cnt5B#;4h>2?+?ZSR4Q&_s1)RMc-9{Uqe+XOoX>@X?a?$U+uE-l;Plz*? zAds{g>gjp?t}Crnx51fu*yGAQlJGN>T{OpIU$Ae3mN3#D94SzF^X$3W+(@~&os_@N zOK8$Lp0-c5 zVrwV?U_O0yap5O!qe_x(?d*5Oj7LiL)S(kUrB4&nES_UCY)nkk_)#3uZ(HpMTg1lr7_0p(d4|tiD%V-TbT|0P?Mg;P)1`+sJyU3F9S~levgXxn~ROd_`!zav;=5UpG`tk8H|F|M|-1uDere0R<{)EMN z|GTKo7{*L20xvkss$hJ&e4dJR`<2^H>b_u+CsjHGkg~@_RGBubQ!}7z;Uw4-dH$&5 zOPUGy_Qotrv&;^w={E(6n2N_q@+G7mft!pS&Yix?-inI%+jz|q=ntcngD4A53; zwwU@Q8TZpY=VKEBqFiyyw}DOmWxg{Flqt`9IpbM!j7Akq(?-fO`k(8e{aP>72dwD$ zbI+aHR;Yx8HY~?apRX9a^!1&2#8avz0Zk&2f@7zgx-a zqM&JZozZ20nr%sG^40u^o@VthsdBCDbdt5K?L5y=v`o0|{*jv$UL?1HFB%NW&h-0v za;*5|I@ZTk&W)lwCx7Uo%7VJZ0*p0gVc6Uy-#u1E9bfMuq+@bWG&RspQ`SNfn&RW|0-g3BgndBbH!YiOCdX6 zki=n8!p0|g?!99|j|Zl)&)X*L{fVji<9`i9@ZU2))z#Jr!1YSc1ljtPjT~$o?G20^ z0LX!j9L@$RMhJk`A9I;Y)yM?_;F7jN3X1&oF8bHIv^EBpxC=s31#v&Fk*bmq!2P&Y z#^93V2Helo`y(jeej?r0?5%(GrFaYdN>>iajGBnc@v2g)t0g)gS z4CMrY0TB588*(X8q>hm_!U1qU$&mI`kTci-@k-DB4-h%1|2zcn{el_UzEJZ#-3=t zcz@?6bTCuW+-h+ELRC=^;P@)MD38;BYKdXGtm&_;e>qn=yQ7z`^Tq!PNtSmf@Tn2$$os z2qze=flsb5DkL3^UtQW#PTG0$tppXW*smloaCMz$Ufz6-ozKU}S?S{zi5}EjI5FIh zJsQd0|BbyPKYc6LHr`Ikkr5T;S9SM_pDR(Y2=77E}&s*Y7&l^ogJQ&C`FcVCZ%g7nq8apM`l!lLLBd7&Lgz_@R4mP<$K@d!nBlfs6 zLlg}ddH?Z@;W>TEV7l>8nM_U8p8l_Cy!apl;k!3Mxn!7M2tPTA@Wi*VhJCM7fB>sn z1y#Or(Nf`l-NC~dH}Szaq8ez-^gV4Yy11bA1bSQG;b8yd>%>7l6zoiT*hGC4`9RS7 za_NC5`O)wL!9bq=2zeB{MLkb4IbU28^h4i3>Zd>30t0p+Gru&hDEb{&B@Z^bVQQ7E z2)|nnLSg_F>DMt_A+oPyb}ijECo>p$5g0#710~T9xezUzTem2}4)~wcqdqmJB z$d1bPzMS9R$nBi~-KxVR%{42bB&{cp_rfvGWac$oEj9Fl`ssWt`qAM7&*yfpA4G`o zvwL^H`(atlg)w_-k~!Cqv}xfK0}FhOYwm`LH=>5dO)XblJGAb^@kokb>e|9VLHIU=`^#)@YuxQ9eLJDBv*F+*n%nUM0QvTg<{H_R*Cn z3ve~{r!%&CPcYvR-bx%NQL+G;A7}=F zf~xw24*S0!#012;^iX_jqeP?`V>Bm?Ey0g#GV}#KgTs+|Xqn5mjlA3Jsg!#-o?h8@Nj0hA&j@ioaX#6Pqbw|vtT|?7 zN`vvW`db(Wnbwqa*2=P6ks=j1Eg!jg0B7;vS0APN?5%S(s9!@kW z`I(*X5`3y2Z|vCpKCcrtYjeu?HPe4FGxnllfX7hWXkuABSKx?DEnlkjkvOBU4gZ#-aJkoI;;w@9dY7%(`icb zG|slgUCLfmW`o;g*Cb!jf%A1PgYU#oou^Xn8NPli*ghXoK46`L-vIPp2CTZpjqf~T zDQF=pzVT(I(>EmxGn(BSXtholy0r+_$ghYGQRa2SMtMq8-U7(&Qz!~8-t8B47vO>eL-%UD#r3oKB-t*kO(GhdLgMrAFWpez@5;vh#1h|aml#2odYA2iAHP@`YWZ0`CtVX~9DNZr zC}8H+eK}1c9x%rno&p!9@>r#Q|ltxpK!!2qq8T8+Q#6c<#ZwZ&Ww zCsqdIZ0k77exW|S$uuZ5OKE&7GRt6@U^F{2N})#$U;e_kaoSg>7q*F1-5`>DvA&AAW`@P@KgJyd7LVTqv6 zeqXL!*Y(;w46AgMr>I0$z9g6($T4LZj$x-HP#3sZB=#m{Gi^t|xr18sWA#t`H#?;m zC`3e|{T(~Mi|JA$(PKC_vUTDc^>UD@m)kfd_EIa}%0r9PI4 z_i%dQHK@O&-ujE_Zf1qoPO&fjZ0Dl$TXt1{)V0h+MrYJgOC8{2qD)v0t45(cs!jQ8 z(uA%OdyWe-1H_lI0sygCBVE(xyH`P+g`DfkW4UwND-Q2kBo)h5Y-RXpGG0Xqk!3xx&^zIw$A02;O;0&>8AUjb^S*nwmJI(J_G+aY&N-qWo)(YVL>2XnzH^RqR6DdU?OF@Q4yFZxIAe-{Ql1ua*U5MD zMOuc^XbXP|5&0s*2-?ZAS7nnA~$LQ*C}V}a=qaM21b3X>MdbKORVN79p4XML4z^UJ9Q4M)V z%nIUJKE?Q$k@V+vyvehBl-84;RXNR{$T={{pUaUgs}XeMdj3dNhQ{-P0gN8#ui@ma zYow!tNOJt`B7Ks`fc&2CK(cEtm-Wr#;r0foDi&?^ZAha5&bEmqN#XDg>n^70$6LqR zflo%lde%va+HLlU#lGQnyUN^OOw0-V?eQeXU(EtyD=lQg7|>il)tKIqEj(J>d_l;a z{3Wj$-h4XB=;_V)`AxO?GdOTd#-O(;nB!)4VBKcAeEr0zKc36@s%c|F-@c3 zn$3*L4cC0~`PR1#LT!-E{wn|1$3grt8-2ZSld)H`A8N8`w5~LD+B4SUHZlCF^zED| zrB7$#FoM+H-JUnR&LczYN9#OUmuvP?{@!fPj+Xk`aW1Qq$~S5NmA$h5y3V%ecMaT` zsHLcEEsLFBjDBnT1ee$6^-HmjlefWE36LR%q<*_hV@QS`92Ct>uye6*cjMf>Rw6S7~HCtW;oQpu(t;6d0<{y==6jeZ)ldPnY!6JU%n`9sUma~u)*li()5lScDWoNj2Mmmw3 z$+;;(FD}L&MaG?TiC{^VlYbg36`jFj!X159n+M|YPqtbn2`29bMz>z_`N(Ha0LhIs z?H=Zh?F>_HI+D6QL*a;oSD{t8bGyAMt;(?VKVx7`zemeUyw2%de z={tm`x67C33=UwFq8?g?Qpq#xc;okG6!6{bncAC10~4BYHu(h=`b#x=0nv8e zMY*MUUK!VZ-q|q0ZwZHVHv&2m8$G@*9IfA5*Q=|jpXK9K{V={|{sG_zFNBVeuhjnN z$|WocLyxjsAFQ`VrN53{fxB&(DCQ zNi$!w=9M%l$2ODZDC08WV)YD641?+v79wnx%BXKvw2ibD8D(s2B~7K|#1iY98NcI= zb-8_^VsLtDkhUFCV&4A#ETMRku6Dfr2BrNgYFxXIg4sBgv%dYZXb=hd#9L`Uz6)yl zmEJ1owd`*U#qgQq$=%Nmt=Hs2L#1-JH(ZdsI-Y=Jz(y+r0ld4xqR=wJ8f==vDO5RwAlt8|Lv+c=MqvGhI&Y7rKzV*p<- zPMXd|ULRO;sIXaDv45yJ^gi|G$6xQD{i>bhZ^n?eoP$lo`LW;1P7-$rKUZv~*riJQ z$^M5oIE4Z8Z?+__hXqSo$8|klk_uPEdBCKT>4z99flr2_)_Wjv_#r3q~<)SE^AixBMnNR_?lKahnoe7nG%WRs~k|-Ufd`O`CQF`1B%9d0^O=YgPT&m zUmjsrNH>#`KVzynLw-fbET>XBk>4;k^859d+)+;m6G7IgR^K1vX_36Fv9SH+!OQtX@-W zHonaX;lkPuCDPU|aH!9P>06PM&rv^tvd$j1M70~`=%{D+GDPW8*C$snF%{7lv0_9H zPB!67=Wd^O8XHMjJhDa^`*~bEByds0JTTnCs3=<-~Fy-Kx~QIl)js)^{<+0j9l9C#uHZ|9+tgg}%E#|PD}5=^ zOWDV5znlTubAJ@*+M3ai*1v+bnjJr2q#jL10 zOlqX)a^U3@Hr~BsDRo+G3Qlu$B()jv*myEGe?u~Nctf~0-@0E^U&h#5 zzh()yk@k)_<4LD_uax!r(kN`;AP(hM4%X-I53nPv`NZ?0vvM^@r+z91PF#Qm$T+LJ z__xBFBk1QV)fRq*MkVTyf5+FzO3fKCzOwYGi5!S0uE;&EoSi69)+t`-+^ri^PJDQw zZv_xGr(Ytpgr?J;u@gKWud4k+~H5u#b&y1%`D$quUA6+Gv zTz>R_q(X6L{-j5SAn2S>RN{J>u#t0IBvvYHOoM3a!)zdm-s@-OZ>lsI#`3BS8$?Dx z--_zx2#g`yjlEO?oZ9L!l9^9hKE>93uk)#kvr}`qVb~XWE1QZ96`ercNV~SvQcCp{ zm)>qh-lEVz_}@()G?o!UEm$WN!_h=+qvO#3n9R)K6B4Y;wkMBMt_H`X~N{# zr5WWr%OU!8fA=J%cCKYwM^8LQie>V-MTq0KYkkqE@@Z8|&YI_1Ay(q&MP(LxHH|-n z7S8aSYzGD@35%Wg-@Xr)qkI8;5B$-;!%HaD+E7)ymqa~E1 zG#okkJ9X_h>|gKu?@RawxR_E{WZM{+lE>~!In_L~CYb0-+msFsmt~$vAd?BpWo*1; z0vZJCfV}bK-l1V?&|tOGJbJ5~!%4$iuD+bux!f7u85g7$G=(n;a!o#;i&YQ${l0JR zsS$cVnhkk9Vrv@Oyj?qg`KzZxah1APyUybV`$zaj>!ro5b>Y+(m{moE$M5U`D_xBS zPese!w$oEQQ8Z&W4m(0j_^#>?{N?kM-}E*wIl5EZ*ey5?$;wAiX2H!5jo9%%PgoOa zenIme|2p^hF2wkB$ma5QWguGk&wW~0XMRY*yX;CcJYD{>!@b%eYj(C6_@Q%uN^v~4 z&c$&zdw%NqbI6bWO39KJxNSD>MNbqRIggcE*$uvCeOnqvWR&DQ%yI zfTW1m`jP!VttywiCoI9+ju^O~#VbfkmhU*OOFm3!p2gV%DtN8MYp&fK6Q1{sPw*e& z92=go-r+{GE+*)z1eT~F-eF7zB$ni9s5BI|-qQSjHzu_p_1o}$QekJ+tl<;^eLH~s znXxZ}A77GMMIVh@K${*GJU|Oyio!fd^0+6cPW^0q1%>?Q5%yOQ|M9Y^;WHodBBu}dii^!4cJBnjXe7*V)?VREHy0OnroWtn7azA z>lFaMKuRkuVV1Cc;6a({oM4%DS@m>R_HnQA_8qz;SJC>R<=Ic@$!j4HGaE;;vyhzR z*hm0Vi;%N+>nOXK?HHMh$nSA6$VW+h{dMGT#}xWhM~yag64LqO2UItA#@go@tw|5y zg+G zD$I9vD=i50cxh(4$7QsF9)RXv7jV*Qv?VwO>)TFD4(^c)n6h+PHkBzTASW7|{u#^A z*K5_|OYQgkwQdU$Ll`|2ySzbiF9nSYbPq!5g0`Qqxa81~g>ZD%s>d9<(!_7^yyi^u ziFKFqqA;NtT%);&VmdsG46q4PE12wBQ5%L~4!KS%-+2Ko^0g|Bm*gsKzx1-|5~%Xo zmk-@7ggQG2Vb84>WrwM|uNG0b+CHbLe`EQ3|9g8GkNbkG3TdR*!w}lQ`S( z4il%#ZjVcZ&`nwg)AUWumF@X=l;fEz+x3S$zwP`yk~_Nb4)FqTcs;%@l~O3Ewf7Pz z9ZO>~W&LzvrC6~wESDEt_POxMOz+UcKCpKQ=%B&&TC$Don4`e9ogUK5c(yImY)=_5 z+x%-y6WjeFH2PvcpqXJbUC4b+AlrkZteffg3}z#5liE`##p3F#fu(2IjmJM7A-nTS zan9>);d@T50mLjFNJ$j)tYLkex==FeBG;*)SR=PpmET`cDg2w_A@ZGwhR%jwXKQKKnj# zoy2}U?1235z_}-tr@)wwPzh#BzpXIfXFLoZxwS+30H&-ZJM0)M(&N=kU{FWr74RY3 z6-Adr&k8WSLj${h0g#U;L9X{aK$16f6{ugQLpAcG&AA-~G&CZ0C z``Xo%nSa-t2E}KUh64QT5I3L=M{})>f~u+=fQ@q0`w|=FT5Ij0@UYM*{Y9;a5CQ+! zOdE#NLcc|deUrVlU*t3fLi2E34+=NCP1jQG{Vi{Ica2r|z2WRe>HQ^(@|Vs8h?U_u z(S$+ldRaQezG2*p7oSubg!c_UB2W;aKHLO3iw2P@yz>U$v4*~>`aXsz2-DJ-7aEz( z*t5AJ%37tVvFKI=d-hsf^s|}rKI+yE)buViix!b996zBiDFQUGK}3NPg4ugNdr_R} z#Aq;;Tyf1F5z7pJqshW+hXAnH^e9A50FN06+i6H%pay)1@%0tOMSlS+b10)Jt-&fA zM3<#X zHhp6=9lgU5I=)NxzPk*$(d~SDjru=1PDskoe-L->$wp#E4hHsSwn!%OpX4J2Ju4*r zNzBMx@3o_fo;8vWge1e7INY;)g&ho#j3NLpn1>S#2E$+&NU=X54lo4D$phi#x#!v< zjI3S*xRK|`QwR@|Po!rnWn^YziU2^MJe>DJNGWL~Wys7x*xJO>=$=G;?}^AC1Sbv< z5Desm0^vL$00%b=j5Gs;K>#2)FNBjD3I~9|5HKe<7{tSaWIo-iAxT6=V89?R~%S!w{J{njl@`1I^xhB{8IZJ? zs*R+yn7p1XlJI4S+!Hf|>mRU+s{=B6X=`Jfdk&Yfk%<|SX66cD7Dh6zjga(gMSDXd zdoybj0P{c8kf4gAt*xbz)&15Y8BZ8o>h~-!Ef^5U3FL*t?pa_!00ac* zQNgDsp~!w?>sz9yp9bq|<9VC*c(PqQ1+Xq>#{2onU4@M$?)9o071Ji$*fZgD2$ARY zn4LXjj=wnbV?Myc86y=&Tyw=~5wTNT-8$@>r1AVYs>-ly?o?L`RG8;PzysW; zADDY_bDz?-Jx#;QWyo51SX|=PqF8*>F@WcaH*!T4v+_i#2~AN|3sSw@oP==BPP zUN2glKF*ef>bY`WkoFflcs5<;*?#F4tN!q-veH+(BK`oUuC1Evf40W^)c-e1LBfxyU4^B))xh%B=IfpH@{%fIUa!GF}+zu7}#P-Ip92L?e_=f7hh zWViayH9*KZ{7+v%VDNq0`G-A(y&iG|*xx@>qhjWU+*K%&xNBpBq_EzXFS5D+(U0$o a`F^V%5PJ5AKQbGYBXh(xEgCFmw(>mjY7K-7O(XNQjaG(jnd5AkrlQ zckutd-~WwoefQp3teNN8v-dt{pJ$)F&w?N9Dw5KCAbuzz`{3sKJRt}G1lSo_5(*0o zNMO(?tQ`ixC1H-Sv$1fp;U*MN!PuEN8KZGRbt?;$0L~U*gFxWE_@iuLXDf-qq5)iz zLSP^m3WNX!K}Z+^2;>0*IdMNYJw-c{|64^=ln`xeay13W-%~M00YHQT;)(zPB|D4_ z%KC35=-)~bVpmFksVYbSfP?}H@_*i+U&$2}08l~!buj=IJep$^H*i58CVeZ=_YG;+nR60GKZBB?iyL{5860JB9P0y)7jJ1)8 z;tOtum?0qa$(?GQB?gNk1q(cQ&svW%7;AilK3gafhj=v4EF5e(9#7sqpRJa04RPFW z=7fUlYJE<>M=;fUZOwRPUTijKKl}d0j6QPj?OD)q`4<(?Hv{&r(90RT^{u6eEMq2* z)!o1txZ`Mklg-{ke1p-ZFrCt$Ob(dvUkzUjsii>WdsV>&=Be56f>6@^w+US=;16Tq zR4mUIXrx=rTbmBTDr#*7%uFOY=UK7>s|AM^+P{LT2`alN`5||GNL*<^I+$AUI;G-$ z5-)O-S4KpjbnGL%aj9YX_X*x42xd$Ez@NDf2(;Zf}2bob+HbN1k^-f+x!HntJ3-utF1A z>mvIt3k4PTZ(xmUWhc*6FfCt=SJUBI3kV7GHiEAr(U4w+I_lVNYkrhfS${@_Z%-^hzMR%k8E~HKp=9idlGCw;8F(WnU^U4e{-`if*j-Y7`b@)BG*^ zfw|af^LXO|{ zh>|qRl>DhC0h|sdjjU>wa=Ed>oB1x$8b65g#_gCasVA#XhBYl%Rjf4tTalZoV7FZk z(Q)gxw_A?PZwbjXDqck&4iNdelKng-PW}k>b^`7aC%&t&HQ`&0RicM}(AvC1m122d zHTmw{Zi!8iWmu+W_z|H}I+tzYM(yW3yg)16BAwFes>)8h2xo7~Y+1wdIFE*~LLJ2C zs>+bp2{=Q&YKvtpF_d&#`L6)uG>BFuAy(h-K}M+1I|;b=Iq(TOo7?9c5k2?9r{mF& zw&3kw)?T*eWMR5B6sh8;DidupVdw{UVD7xKn4T!2grw}JBW=D10)$yc34p`R#rV!M5(9} zl2v=?eWZ}^y}@ibvH*Pc`h~D%3nN5;^Et`NBl9gq@kgJ#10IkpYv+IXM4J4LtLlkZ zU|}VUMyu-Nppa*qX@bI+bl^CRG17BG-qWM|HEoP3fbi~JB9{R6JI(TT%`6otxnPv` zEGjq|71e@zy^HD)YWAfhDBC{yZ7_abCq6FUIkjv*WtL@g$DzdTZSVUXm30FVH7M^g z<@Ap;riXMx^4oD-ut{C7d*uStIusvAmcdO@HqSH+mn@P7VdT8D)*Tf&!oUSgJd2-HL$+dDR73Tvnei+uCw4-D5{e5dF{R#WFL-wKRr059 zO!AdZ-sDIdNC0u#3QvDmMKFZFdFx z4;*%}Ni?#Kv+N6A82UWSoR#$_BmeO1w#+Z71_Fj%ky}MZ*bdeTB=L#6RwpAli&8Od z{5au@Fmz747RmjrM*}~f=)uG23aQIYj7&Q>KX3t|tB1e6-FP~ei0e&{jE|XA`VtXW zef1yB;U66q{C8u~aI;4P1XNIFxPGFBcC>TC7^58lxKjYG;~T4^u>jpa&0atQ?TQ5m z$l2f&#sBds@sCeAeL?{#SFDUW_Ua6PGnIh=u6no{p@0k&aMh@?UzzrpVvq9Tp9RXME z5$8`G*Vv7*Dk#h!A+G!XbqPTJV~~Hue0BSe1J2(uJ6^eS!p#A9P2ti}+a_rthDfAD;a-EjRTUo!HzH?sK=b zg81JTw?1Jf+iSe3Eir1>p)Y$IhAQ${^U}U)Ah%V2ZFB36>Mvo0F!FFW!_ZJ6$QCTh zghc7szN#3F^E+f6Gh6mYmJ6H6o7@#AmMHDrC*n{{=|}f!h=*!%)^IFSQQc!OXgPt5 zD8{5GCivt{_MmQ;F^X|0clW%x=n|wZ3*V0_jw$r|?PfZsW4>Z&NBuF~`_UJdj(CGaW|iLZ zt@ol23>VzKb_e6tVJ{^UH57w*UGEP7sB7Hiy&b8QHTICF$tKY=9N9Ho>7`O!h$TZ& z<%)<#7w?G;EaqAS;Br@j53!wkIiR&9l1~6MGmfsNI%Zb=(k%_4h0brnQdu3+-$}#i?SB(GE*OqvF7jy;4_P} zCYo#}Ej8vPUw_!>>(OpMJ4WDt?Wcgh@q@hnb_F`Dp9I0XBwBB>-OOt-=5XIQqga<*NXJXP884{q)(&w?1pbbK z-Ztpc{YboJ{JJpF?%1{TFju{6ePXHPjgDli_&e%BZ3H{QE#x;&ELz;I>-oDHUF(xc zWojh4r%X6!c2Ajf&ZtHGM)j@Tp=$;OK70ob>W@hT#DDu2K7RVO^QIPKGZ<2uLAHlC zDPb8Gz)JR*zOjGLrD}eIj#jDlNan`YF@TY>F@mL+aL&4g^@b~bI74BWlvv6o7j_bu za&KRBfU*Cfc#jTcUxLqNii4HXr&R zW2@iwy-fBW=`bzL{w^L_b^GBcDbclUc@_h=b$CI~y4ZrKYg}w0_i8ko58XcR4Lxjt zEcVx!X#j$DtMA&Z2x@IMOj5F5)D^VQ zOw_IwEx~qZ$VHcC;b+0xpK_E!N}l6Z>PF*`JetfSSK#%m?M|ZuN&B!$f6LH zXRiKnopCTH&pKud@=$xtl7)5IVvk5GY;ShHge?OZc_ZgWW&#a)RA}@g(WKM!{mA=w zlkyRtV{E@G<|H`Ywy7JUT?0s8i>JFz9|3ze{Hj1_I`{Al@O?I~J&BvvT9YrTsrmN%0XEL0IUEb1iZ}cdT;gp3IzDqpIh=dj!eL-NH<7X|uxz>76F=uSe(X3mCcrk^Eb7Zm zEC{KbP7q82NLh1R+N3xQ<_+L|7Wyuxbua2-5i$CJzTp*xd?JBroPE5%jjTv9%-}5C zUun;6>x)u|!!obhhoOf``t-#tY*lHDZ^Jru)TDZwjDa^r-#*PnSOh{}#-6cXL*~-2 z&H!4uPO*%8{KYJwM=3nZ-_w?u)WU6rd(YG7ZjVm2F-nK;bujZfQqt`Wz2Sd_mMwIp zmFr!@m+L?hSo|k2`KUfQN zPY}?T&?e{nN*`SNR^8+d4LgHK73~T`;`2oh^Vrq%eo&gw#k-BNbzvA=d8=@r`s741 zQa&V7X0-h$?aqc3o81)kvQvFUIX(Z=KKf?K2@{S#m~{Z%FH6vZ zDELlCZwih&4hRkiVpt5CReAb49=~~d=lRH@li2D=@#_J5HZ}eE@wuiFK~CrL}S|+XA2MW8hUsYb#lO;pImcQIb|=yTw!ID{Vaz zyg4M)LAPyrU%U@p+Lz}xESA1-Vw*CHwk2Dp8t(eG<{Puw2b+tK$yC?L4xY%O3&+9QIo`iY}4p=M&&`t4w=wt*VNm$K{usW%B4n$Oxw;}MtFG#j|eWf4_D7%ZR*T3G&x5GRgJK+V(z}1hxNN%wPF@uNfTn$7rqD$ z)RbDLe$4)8*|G2~Bq!>){s6gsx<&bGX1M4;KNS{XVD!xzB;Qn@VQq4sJ$kFjLh%~6 z7^pZ=n5rN1ny;8DYF+*Jghch)8I^XoInA9o`#KLxu!d-Jp>_h6+{1?G!nh0Sg;IW}apf3W(1scRO5=OH9ou(ll{}XJ zaimKP=}yXehuNVX@U~Ozoq`oTj|7RW6-Bi^SyuH0Ntq#uAg#@)nmKRzB)vr;X-yb= z?){pumTw_;RYr?X1?Fd;3QT9?d+(3%dB@N$DR>8Dv|{k7m2&jWbtnav-qwav4`^Z; zy^@RX>-oIOaw5j~O|CkkpTxDiTY4>|hW;+YV+-gXGJixphI;5+T{a^SJwzw|I#SHU zI)n24{jQ%>#tDOU7S6Fe`Fx8i-8iCxfSHi0i-ZTinC^;7IYjgPJG1 zw^7w~zpU$HEXrfNzE^Kqj}@iB43ASCW-z+RJ}@F&-5Lk0=0I%re}(nFmx;Q6&pj~N zb17)LpY=%(!$N#R4$L-1B$r@dM=(-29sRRCzl++SwJ= z!YjylyP4{>K#11TjF_|JSh-vkb&~A1{FlS5b^VEN-yVKB5QXw-Vvv++;=t~@LE&59 z65}5o#0@x@Ww`&EDkv!|zsy1XZtYEbv^oG2$^XEF_yk_O7(CAPKL2SvNyu{gsr_7f zYFm7%UW9wciK7@$Ido5d7$^RknZVTV@E&8L?#;{ z^DVQ=UAylmGS@S;{mnZ^#_V&l`j3WTDb86MY6X3f)Nyoan;mbWWZ_}i{P`5*ll;sg zgb&t3^w|5ckE`E^tkszET)y-XIXW47f1J-CYVgUX?;=D|H-pLB)pS0%-%xe1d@iim z&})~VRtoOH^e0a$Rg{m?)M?Q(2^ld znb*~Ygtplev0S>4I!8lmmlKJUQmQEy-E$bKvB}rL!?n)G#ectyD2Y5FW~!3UNRVG# z>#1g&Dnp97@Z+`yCJ*dhB5Op0^WKux-MUovjM?R2 zDih1HUT;^F7dp5MJtM`t-*Tu?zSsEd_i6l{LYL8K^>cT{GJF>;jYvA9Y}VSf7b?ND zQ0l?&Q#)^dounpi_d|XVr$#AtyBMIj>WWk7{r z-@C7`^gJz7X^x~0ti_#Nt+p2pRgw%Zqd)CfL1Uze-N@V-#`gBU`U%(}8&`%~KP^7q z*=Fikne{oNyp(oSSzNE;n$L31ge$g+sJ7oSEU-3fY~;^sh;(@T1V2PczkfVgdDM!G z1nu@xhHsAW8dNxMWq-38^PubOgx6~6RH1Us z>^f4IJaHeyVU{Z24S_ z-8mq>XydyaPj>$c0!;zNOuo&B{_I`&BBr}6g3$Jdts%eemEEbM>xET~e^`mMn?0DV zvF+O%zh&4R}zaQ#+FH|%mFCB%wz4esTq`0XzA9AL-Jq(%|7&_4n@%_N zfhb`e|1!rCks9bTF27+pU@UYUnMzznkDI0C%K+uKy*^9s6EDJK{E$pE= z^6wjNQpy=?XXN(yP}Y94vhC#4I((;f>T?nZ%eVFE@NGiXo&?llIvKWE9VPcXMSkVE z_2Q^qrDu;)g&wbN8Rkycs#jiLs%q(ZJ6%^5LL@)k=W@IHv22MRdFH3`KB|Il4tqrKocTS1C@g2LSZY0JL>1q< zx8hV!D}Iuu(V#$^}xAT4dGq$ zJ}XRn5hodS-o48P?VqEt2gpOpAFyCv4N4Q;pSGFpH60}sg~){ zH0wlSKG$kLYx#lT=^c%wNR&wq*>7*zgjncGOn;A&4cYn05(>{dA?E&~pnoS;HaY|G zoH+V$bj1M?7@ssxFAwcSvH0vcU9V9pF?Q}eSitYjr2WoN5J0Ti_T=u8QytkBW0=7+ z%1=WwQcXQZf&S>*VnHVidv8vyq)YCeEY{&sp>|lsXlh;+@~;fx6>e!gN|PB?IxNt~ zu5VDlGbqeuoP8W}IkxSdb~; ztG++ChOe@>)~YIBL9YMgjYa;k>n^u}oh<@8=)9`!!n}Du!CTY-qJ5{XY4Y$_ONoyl2);A&H19XW>=>C4y2k$@+bug+6 z?&F{NE1LKJ3#Rl0+Hv`u05b{88^OrjML; z`FLlUiKkS!->=1fJeJ|);1o@~J$_Lu?%%pLE2kG@p_?0vPm#{}X{+b+WX8o_$#0eh zp~JK2?AD|bhKG|X2g`D_dyBCRUBlZ>n>t{#rk1tRT;(I5JvaG1f^#OVU)?eLITDW; z#+}}0F-$01u|~wEdJ0Zt9Y!o^$|sr>$vpRqe(OpYnfmFX)g>X}O?TC8_93~4P3G(D zfjhUzZHPfy?M2M;Y2SWwhl$P=zbUFLAqGX=yA7i|Xf^--=taikX`6o%>9`AlY(EV*Wc_(oe9^|7+RZ}m};0}^Ee?K5I7_Y zfRZ!O*3iZ#<@1`#{n+q-=f8PJ)kb0xzmlXqxHGtScd3O!l2Ve|mC#5&TR!`#FgqyA z#nj<=!1kybOB7PWutIAAa!Duf9iM+%L#^bKRa{lIo%OaxxpFG|N8BOutek_9aesDH zTgSWqq)GXRozz0R8uIu!jn9tBfudw>%FRq%ygYLFdaP#Uf@BRQ=4U;y0HRIelvNxz zG7)r$YMDQgD3I$9e0-042zeN=vQ8_Rj{Tw2d68NWUGR?Ui4Y9)J6Dabr=?tAAo=CG zC#{~_^5<0pvbW3Q>2?%p93MX9znNLne%=oWYHQC}9Uxi9+wfAMSCTP8{yQie6PKo%L{gP~B5y zd`MtrgD%nW;lv%Sd+W+Gb|>Y>E%i}&QJPUqk_Hj6XVLW)0-Ku~bj&V8?3*zp48!Xt zLTSBuHF+{LAI)w{8$lNbTz76wr6?IIaZ(Cy!_wTWHgnt?tWIhv{ZqGGlxBOo0|;D^Fce7H36$)-6_XsdP&6( z6YMEvP1uI_h&7g=SuHHcaV3c#LPGEp$J@<^$EWBtyo~4 z#Ok2;N>$!=82T^#n(ywvUSN^ok&?6*egWT81j+jTI5&1;4X2# z_#HCso42uxHs zyzlnJ&g$m}G#N=xQ`RK0s6-xfo63vGN>>I>($ejr1)0vznr{)8VmCakTTV3&q=MaR z-nR?YWVcW3%682|4!}1Nk|T5!N%A4-8yz>LeLm);m3RokD^88q!)x{KqbBl}mlxUc zHvF`2JdKSxVAU2)$rUhhT$Zv<`u*OUuPAnO^AngL{RV|;i=()QY~)0joP2bzSu!y) z4_zv$!%?Ev=|uOU&X%*5WqY(P|4hq;ytr9${R>69h~Moa^JFoiQG$)clDAG@1; zZJQKk`xNem*{VsmcCmZw?w>{& ze|dedF&~`pLKZhvkChyb95NkHQBzrN9xIeP=tnV;H2p5<728m#WOh7#-&$GJ%RY~(S@Tst_Nnu{hxt+qYGX(CQdz zuJR#T(sd0f<%7G37BanZzJr8SB_e{)0uXb@$jIPXze|?Ldo&axrHif4H#XcEweAm% zlbq2XsR!yFWh3@D+rho3_s=u zvK~;S%{-WFsLR}#($~I^pUfnc=`fYXUdb-UCYHDa{j>r9qL|hn<^pww9)b_lJRW!? zg)%N=?Y^&@m>FZ{8c+JMac@fWofkHn6T~5!rNIY_PnPc?-R%=@rO*WV-sygEoo5U{ z+{AoiN-dX}8ChnxP~Ec765TQ!tQkB?E&<9)-`&J21fSUmjZmTqcmlR)%B{ywoV+$a zP5+)u%u!xq>e8>kEbz}3uRgwXybvwiPCwcz|LA$sn3usotIEMgZ)*PFp#LsO?}5%D z50%Zthq|q=Im~BbGyXc^NI$6&-FZ!;{J;bBJ2EscSzQl`Os5zxV5m`U^s?#R`TnN& zC2#gCNOeLG$<~0BM(N<^iXedpdM8JdtDj=yI#Nz*miaWh0&K>9lXY?Dd$n{P??utP zatw+q-kB~Lg!rXtY1XK+w^)|x1`k^cCIwe(cfV7GjfY9YnysN@L8|!y&hO{LO_S_sM7)Gst0zexYmEC$q23F1mw}OG4968_2NwWA&W2`Yj8&Dy| z`FMM)8^JPsyRwW(vOZM<*bI%GJkX^STk8H}T2@HWj9V>aN`K4phvkOtPt-a}v20ex zbEwU8F2?ht^6t9lFJcLw!@Dc5;$J<>5P2gk$z;R|Q16VDdB}=oJ&d4XRF$ETNtD)= z)`e`HLNgSfIsTCPmCviJoe;Ggz~0K9hh9O)qerNTDO(8#@w@P?D$6D+x;}R4 z7+=0QkFFaQC5uz8Qn`GyQLk|;7+U2#_T|(ngC;tTs@a3#t?~L;PRy*2d-KZyUJI># zAy@IUuvfOU5o|3@cHUD5k>~@vi{>=GwEhd9txK2j5TDBiyC4pj*1K(M;{-Xz@Uz%0 zc1coZv{rqiS}>Y5UYIwfG}d_h)$-%_FCDvC;cl-Gm-F1h{XPlsNOE~vZVfh!ugHqs z;Dnj++3=HD=3Et_vo6TET<680j*BS{_>>_RfpljOp;}#4Z(2U0x*l-#5F)v%oZ#%akOW z7p(`5?&fITy

(6prd{sX5{M7Skf3CTA8M5Nr0rOUUhaF(`d9=VzN4o(W@ksyGKT zQ+dU#p#mUyf|%R&Ei-L|NXs@lZ*E_l7vfN?2PWY@j(mmayQSA9@sm|~ZkhS+Yacna3+&QD;$;ox_KNq7qn=^Yl!CDKVZ`1X zuQ%uKlV5#E`b{co(E$a9Z8%ga}7%A2zlv*?Qz^)7kO51$ZFE+gICf=Ps`Rbpqw-aVLefs8g*gc=$2~*s$A@^*aXA+s;B(Cn9FVd(U0P5AN z-60t(Lm~7oz}odww+uO&sp&;m?YSvM9h<(%S2xb96a4nN?uof~(K>JZ<6`#)!sqAR zy;D5Zr4h|3ais~(bo7>p+Fq10W3B0{>6+TTpTc96gUs7|O-cl{A(9Ofw;myC zn^2DeZAc4NN}b+F%_I}*^6p?5HBbrf`Cn_u{m z7^uvm%9q~MnCWCkdXr8IaNO9{XYtP;jI$~fm6GB+!&N)vOQ{b64=jjDUJL2{+2|iO` zJ^in#&B!yv{LIX=Qv-s7pXhjxGo26LyNE@Q2Xo)+Qq+IW+?xI}v1F^XmTVhaGXa>s zt)C6(Auc?oS=JyureS6u=gLoH9>1OT=)qDie9h!#cwywwS02t~u|Ubdsjo!Aq~;lO zag(zIcMQx|VVzs==V0Q(fe6yFXF+13#`JR?erp^-;#AptfB|CL*vu3ONpgR)Cp6ER z5dJG-x8)!DO8`j;NpDgUa0UWMNq@}Ey^t~3dhkN`+K6zeJut-=4Iv;ug5&u``B~n) zNg(1p==dEe)^YO=lYGH-{>Eo>jitRp*DJ5jKe4iyiPnU!Uk2Vi^-*kWIG4P*>jhE^ z_-}j$N2B})6LQ6|NTMB$F&6eXa`rE-MG0ktBWonlmZ)b=>L^6)qgWV=*_v6Sub|hfnTY>kXZS!sFpwVx6hwdkd{8(T=LQIe06>CB2tO1i zh@(;${2emR+Z8y2<7-il z=qrVPk6hi!2>S;#l8}?U`u55Z7#EP7q=uc0oTMVk9>)@y;1<9F>-I;i?&gS#Ue4Ck z?g|f5Lz`LP2qrfGml%!^M&oc|WsC_LV_|Cs;QFT-PN?o=Z*PsZxmriy6-V^^3Lw&j z1A+WNq#*nXFaiP~AVGeFAP9)mzl!vVD?$SKK@hkgE^;_P7Xkk+M0t5wdqv9awtJQ;Dp-Z?+ z5Kao^M*_hRC_oSf;=d9>0AM6ecJ&zk%nt?=#9>YdBnW`OJu*Qg7PXzcAlSc3k+>j0VBB9AMjr78IPyJU9uO%a%}!Xk_;{28h0|n#|g%CaHE$h^6zPWC}w%X837z%J1eL#!aJ#)Vge(plpB4!V|Nn;t#ZC zxvFyj{b;4Htl6;|CQ`V+2gskxVz`&XK3O9zI{EPAg!;Iu8-h`ho}JW|NxAzXPD=QY zFYm&t4X!!WPMz$5e=cfJuQsvmp3dD)m_Nk-DbOA6jN+SRx;0vQ`QO#=D!cy;i2JJ^ z{LdD@+S|B7^uHGZDO()6ezkA^XS?&s{&GFWgJg&80a+?}Ao-EGhWNO0HS1cFNl1b2dafB?ZgxVy_6 z&N=s7Hn+7A(MK8sm_&HM zKrj>t0dj+ZFw}t+2xLV4q4Z>JjsABPett}28>71^K>nVJp*{eF$tffY;FPmN(x0j_!T=y9r;OAe?`n5)Ss4HnlT%p`fOK#&{-15Z{-11t|FDI6|6gr! z|9{x}zs(E&w=FSqDnvhyXlsOuMaJ016ln$kLAW9O`~XKJ>b_ZHx~6Pv zPTBnC!t)qY+pBqBO>gQ?{F!O+VY0{U=qmxhwv8h6QSG(Y=YWq4QI+&#L6wg+I~D1r z7yA++BYO&=&L4Xsz-LFb7gB=dP8;Xhmu0=gpTYz~N*5`ebv@TTFT}1tSo+pwLDM1z zy9%z(7ktQY8sF{AdH{~kiw#&wG9Qu`zT4nmJY*r}$;m@H(4K7~jBHI;O*;8mPR`o< z$A2Ez*vHq03yx;a(_n%&9`TweeRmPyNFu=Bp5e&JFqXaiT>2t3ch)APYo|Rf*61Xo z_g*61kHk`T!{&S|8KzzCP(;j;PNfWi?71ttVUWhI0aNru*jK%49it#(c5_BUHdU;I zh_@tkn3qn)YZb&^9`Ri(Z`_de{k->jj)!a1*^1Q$3lurBo@FXybb<>^pl?{#C%Vx@ z!Oz4=s3Zt2svps>{=~AT;<6F~e2F3|=KDCdHM)ZKl@cAx_C9ghR9TGUBQH2|H^1rfOW=$~UY;{~HMIJZIQ@3O8)?%EkHaw2Qk5G<6uf#!%RMpq>~O zdaz|AD>uY!3}m`Rqwn}Ymz8sIvkMk^+Sxos)*QuzAUF>EkrwGkGObL5d2Wo;|8|`B zs&Fu}iT3BQ6aPO10 z`@cnf=#*1gq%3!t>T#f1EX~@y7vW6<_6*a0mi{b<{B5b2{rF?mK3r23;gy|N`0ig?D;yUtj!syZFjW1BJMP{P6Sry9DSc&3 zIaVAm$M)^1Q*7{}X1t~$#B@+&R-)ZpSCDvwf25)9CFS!P(vL>?A&vbbFi1tDhjbz& z+Nw_=m!#pRtp}X5Q$o1L+Z(3nU`_rDWT?}ULLDV2r_90~Jsh-u)(4*4&nlrg1o)%B zb{rYEk7;CGaTpsyce-6sw3ojSBRKF>$alR6{TAVv>6BBsYOdx;2=tnCv8im5eL_vB z(Qy@=#u0o7$Px~*=H2l2ml|37*m+UJ?1wRpnM=_lDRhs940Mh_^5~tlrwD3bM}?Mg z<(rnDaHVVWv#UPDK5Vc`aS4@h>T7-Uu8Oh}0BDDUV@foGVY%D4~JyN(4sbcJk1aL}PqZEbyItu@Fl+?!L6m><4DwmQ9E0Mlj&0dyqA zd+NzwL~AlJEwU4~OZ)rBtKo5`lP2VdnW$QbttcvhrHA_Xa+P@FH`LuWg;v%pdIi<% z2PPp2&OD#yc8gCB`wf2F6g7-3yQLmakD6dG_>S*M(=MgHEe)`pPW}E7&!VMnXW_aG zy&-ba5md=bka5)DqT;X-nx?BE7ih!6KadE8e3zIcsVAQjFOmO|b?*4mNYjW@=&9TI zil3;mN&gO)7Y~h?Rm_a?K}bj-4i+frTvnM%Q~m6qO@Nc8Ep*$?X=CZidriROnwg&` zWS~yIoqWX-xF1)+p(9-IA#PtBt50=!a6A-DmL@wo`+s~A4Q4i$ptMU9OJdHj2EJ6P5 z9gPD{wS5tWv?xwVqHZAmOzz?nEq`y}*(FDjON@7$xecg;$P3x1(Dqj&$}>mUPG2y$iNr;LON063QUSk=AQNJhF%3(2 z2swUwFGk%MYUWHLGCAHsmC1OVbOe%?J!^Qq6^Y{!T9ok%$vY#B`}6ma@P*3->^cf$ zqQ6l1K-$=20xz!hMX3KHEiMW_LoK$(H3rgTjU2%^S;{lwJW59 zk|mm#*_f^A!K7Q|>8J>rwD53Wmo){Pz2EsdsJ}5VdF>MzfNn>*h=2c0#M$gUeqT82 zdt5py(kAS{U99;r{0Pi>y1=sQalU6`l-s$@d{6D=?%|5R^ST%Dicjo^!LHu#UG-u* zfr2#ZOSYMd!IBM2G7cd=j`yZ?o`CnO^X|A8V`ap2{n+z0ft~1kd~JkiuKbJj_jKOF z1>RE&@`2tH)22RailF7dm?vn9dEkn_*m6%N)K%)9fWNE7y?EMGq9$oPdEEKzi+Ewv zgq_hna2syo<8RNbrhSeD3mwreNol+c$n!_d-~{^~_bJ%DEXlJQ3l@y(y}agcC<8km z?mY-BdjKciU%Qw3-q5kUgvsoX+Si7BCB1k;o`+UbI`14N(xyN;_zpNWv*oyFlJ?;H zhU1w@nlSg}h^2?g+?J!rrgET%&e#Q?zXzGkCSCH}$OYhbrK+4?UOz39Ow(zqfxFzk z_rY(HL_o*-qf|iZ+5>(p(|4ELCRSHrq!BaxnHK{mr1&#DbO|nIkp7mRofSWy2c`~- z35@WQWxw)N#(e6=_`RF=GWKZ@38kw;-BKV4<@^*~YS+{6FBhL=oG>OX2Kk=iEpVew z4cf!m(7&68Fa~<=J`ujPp{E5Ox3>i1Vny!LM@Vc4D01-(n+y|Wa8m*)X~Yf{4lx#? zwm`KQg-fqaQwid>&LlM)lPL z3}rjqivbjtEc=~&H0!BJ{TE*nSgAMZ3tM<)I)dxu9_v51cO@H5S2xuYy{2o~#nJ_F z1Ls;^dEg<6ey$w=qW5_5*LVF6aYbtV>97&iv-Bx%$@(GjY*v<7W(vexzo^|vLy>bK zj&iTuU;Lhg*iml%a$XRKopM>9^DyJdr_23TFXG9Mug&X6j&K}pss3d{x#+sXw3{JCJ`0E{o_`{;SAW}Qe5VBQ2Ardn*wJ9ld@*mnBM_C_H95@AENyG_r zv5GoL8Tv`wK1tbxhR?|aGxUY!Nx`LC-b%bIf+=2x`*Iv0zP_Q$u6E#>NFQOA)21k* zrLT;k%9QPSJUs*11N8YvtYb3Exhs;1uv`KT@8tC=IBSV+2@@aR&cF>k7URYD{0v4)xVN~(QW!aU=!;$Dh%|ju1Z7r=)5@sPPE!H~A<}byu_4aAEbpdHE z>wHkl(A-L=rkM{K=u0zUr($7(Oq#CbySUX_Z(k67jcqvNh8K@Q%nM9otzW;{eO=kz z;J2PRHcaTxMSCT*WgBOoS9Ws%b@NNfZbrgABF@KEN70na51O|hRUl12*K>C2ljg;m z9~hsPMrZX^Yv_!M-bhQfAB4~5r@dd!YW6eE(x-{@%2Tb7n8~aRHrO($*E=XDE-Tb{ zL9RQNyV#WRWHgjoqMV4+ws+O*BF{L%xKQv+WC^ZU82aqMB41(l!_}rl^#J`0pa;7k zUiv3HBX_EGt~2wQ$7d(oI`$eF`6@%Fgok!F%oUdtOf zafvtRakD>u`ow-@*J{kjsom%f3;qq>eY=dg>$pztepPl@Uh-sY>ci%bq0x{N4JU(_ zlni14&$1Y+bvll9SFok9oU2o0h{tB4X2Z6dn7)TXhZF*^b4-udJC@rF)xMVq(}y7Y82^?-IXy5 ziu+%9v2Kj3CyD(|@KoCzs9SQpO<_LCuiy4o2}*615RypYl*qS_BpY_`Oj7WfB70<` zCc;$YrM)%QzA0Pzg&7(*VI5ws5-`(2pcFJCwrJ4Kt<_+>sd_b4d;A!-mu53PFQDj? z(k_2^`YpA?Z`h1GNwqb^jg)h>9m%dOL7i>+Xe`aJnlfN|{^a~kq5@qBnOlDN2+7gU zU~&m4Y_k8cb3!nsjRopE%yF#(jS(K{lv)Ypa-Q)x<`X5- zEL1AodFRs{Dfc{rpbrtwG1iT~-}W#toTiL}#*H<4%3oS~4ZZpOCZZ$~Ke;Dw1E=Hz zfw?8A=4KC-CV9$r)1ap5$peWe7!AU*{O%(=YtKKg5ZU+64QW>Wpc=w5KgZPn0^g~(*NFuuGP zI-d*JRkKLAQnBajl5*9o@?*&5La5-lzJm*kw{b9N2u}}JVwIBv_m%F zUwzy|Hs%=AyaPb%2fCm~{J`!v^ND8i#Y>s#|1S8O`q6t6{0wHT;r319WUKh%$#QQc z$#i~UK^0GAV=h39wgwtpo1!FR72tcsWR%705Gyi#J+S~)YkkC`8F0*1ZBnO*B}O7q-3rmCZ>s6F^z;LO3q!V$FlZSMEE-dx6v zP%)NWyvt`fQ29!BqlCp{$bFzG0dT{@2vZt+B#WRbBVHzn6GUrh5(bLV+p-cfR4&lo z+H5Z)mCf%8sVo_ioSu#`kmeo09RuN^LSw1bK%j;LuH8Ed*8{76ig3m;s&=#k=b=n0~F5o-|EJqpD zbIM_kP4rqtEx>q8!@jokS#&8KlFfwY;c>rimQ_h6Ft$vu+6mbv@-ibF_0}@7tY>+u zt`4-pwLRJmx8rxFaa?qWo~jhx>d3_#)f{${Sv4UW7&zGNpibu5SqqJy^Eh3O8ZhZy zb>3$zRP{XG^xC85OI3Esq8Kk-e)SIhqcek&?$`4eS8xY0brzmuV$jG#R@lz`sx>Sp zc>H(=rlVZgOiA>7$v3m63`HiFT!ELISix2KXh1$y^PF#@Et%(skjg<^u|SET zUNpmtD?r7U&jh@}A&O3G6wmF4_0V5)Qhml=FYtZT{rIKH04*b=i{)ai15Y1FN<6?- zF%`0cVXJdAS1C^Wp|fM>FoEgEv9V@;tcH_nLu@F`p(MVB@Kc@wQ%sU9J+cmmHIg{v zB%$0=@wIoA7%LK3$cVMxb*aj>qi0hOe<=mdwTU2oNCFM9uUHNbqNNMR0$8;e3;7te zG+Xs-9SPW%r9mdCB6EYjDVzHbS7}_%7h5D^E%F@LvR`lX{&dbvedH(F+qQ@k*E+3@ z-L@TRU?-rg1)Rpv&8@k7fsgYxd#kL27I%c|_grRjQwSLoU&YGdqQTl@_fto$D*jG# zv!R&HF@f$dncAUxBgJ2bSCe6*oD*d91FD=USC4VfHlhgQ6? zGCyL4aI_5Qw5u?+hcvQv6iIBqVD!V#dJ3(T?mWA{lF-RHwzvI`N?W#5K+vfySX1@z z%as^Pke0Gik%XcWRn3webF2K{Pu>ACgL{At4UzV>*xZJOJ2^GyD4~pnb}oD z-x4Y7%AK){rfDPMvGQz!(X`vmA^R${aOrV2&F@{>&L5KWfaZ00giJku%nSYv|5*_w z-(7sUM&@=?iJ!*naZLo083yp4ou#_10d_(=9Cq6##7DD~R*~5~rw4U%#fHv3M~i5E zpUDQzRD^R13_qhE1kVPJe#oKu60EiHg?7P&Ml@ZZMN9-7_mI;MvHVMVLX6jO7LeD+OQp{KcL1t_uK}-df(~^^Z968zLy;Jo^&p53=4pgiy ztgg@_YW*ZoKOY?73aQ<=ONXm3176=yfclai>vL%3bxg7&G88^Q*?DF5zWAJAKS|qD z#Y}rA#B6)%dy*5e7kdTwN{%1)I{@l*a_;xmhvQ@{K)rD$o2logeCINF2XQkQ#iZK! zi+-_j2OgdH4Y82tgV~(MRbHmDE&&|{csG{^fSM;=F(pQDyiG4x zNX=#Y`8!BTQsi1#-1?R75C3v10pVMz+Y|lGC+E{)cSL2X0T! zqpZT#-0g^&S6ZVFJ9N)dd!+E2rGP9hQBpupH^~Pp2R}RTeEjO4WsGQTrIxM^fcZAH>~lGSl| zzxc~N6fWP_=hd(A$?M1{swg6(a+ypdN21plQW-$$RVxseA*z#VWYj&R#O~-z_Lb2- zcmgHjyXktN?6H&6HJR!T;+MNmDKXayWmoDuqiHW)Lvud{!jRiq0ekh$A#J~NTN|(I zyiBCiSWz7Tfu?UEPI{p;lU%tz_xd`Pk9*871?mk=!>=LZBw`fdAJSilQhUm00Y8mw zCaE>JHYj4eSbn855}lXC^onPy439q6;t6poTGZ%68LQ#>AuM^meeb-l5vQINOD~5; zPjtG!G;D5a9OSdA$>|%PK3_U~d;^K|zw#!IB9k(y(tgic9iX3;#_9d>XKZwKU%k@T zD(PdIYPSWRfW)T`I2ctG^ELeQ`e(;qDyfSwGsC}$vIVIVD-zO#YDzzRFmh~XuJKWT z(3h32(xk!p>daC@OZ=%9f7NsAe5}`Ew(&!!^bFc?j|(BCp`tTaqb?!Ja+eg>FJVJ0 zq6I1RXakb_ZKBx57qO+A3@l^GYYT(!;-AdJcw5?!I9`(WP>kNU*-n_w`}F8h)D85c zR$x_ni&*2C2I0BqQiVhf^}6_FiD!`~zJsZDDgVTv#wSsepBh$ima4uqE|q%pV$y9e zD!%(_1;Yu$lG*H+GP$^N0wDXLOURj%r}vA>cY;n%Tj#OKo9tFs)pU%tPE%9)kZsA= zp(QT+^5on*b9J(3VMZ!GX^Ja?Muh|HQ+blN(L%l5Vj)AHO97NWNsSsNEGSlSIFN8q^H&_v7w0v+6dpLYnzI;=e51W=Re8RX(gKeFNi=G0>JUqW^V(qp}1|Z`)d( zlx#Hz-+peabl%+zc2pi6k&I>U-V$7dE)%aN*znu1d&8%@RDWeA~6}JjQvd+Gk{f_eo~E%banGH{As#shRDX7oC68m z5mBh`1hUQM*JdnR-E7h_j%eqz-1Z})(2dEdxX{p$u?l)ACT~tA27cB?CQt2m*m2y8 z1D#dv?P=-eRVp2jLuVmnE)K++uk*SJ~9-${HJWw_C(rgxfRD1>Vt& ztW2;AS&vt4%YWa0V_EaD%B81Gbh}RbJ;lSQohnP~R$I&McIU4%X{#48A=jF=+P8wX z_WJ3So&!+avFA18czx{~lv%SXj1HgxCwlms2cE}`{lsIOg}xt|vTKz*^3zq=VQ~pk zKeFSLEc3sP=q%#rFGET&O_ctKVi-QoU6PN*m?2P|0Y3j6;r=6ZuR|(OL&DIdAd> z$wi(=sE3Rg?*5?bsN%NS*0YaWGR{tzJ0!nAJU?Sd2-6gD;z)aCj7QlyOdbAp`Tp=r*SySkM@OFvu|WbtDIU8w<_CH<+SS(yYC~mww>V<6OGNFIJsn& zN{YY`-sn_*=cPfmVpyZaMCD6Gq2B$xuEzMP^f<$Qy{KbV*PwB8pT;+^j8KM*Dg>KQ zZ$(q&h5*UsHbHAkquSMthR6d`J8FD#o~)2Oy<9A_C%T~Wv*WP=YfjGis{JY!ElUO-BE6T0qzL`|0nIb&DFeAUB_hbOQPorsPnf zOqg$Nf^2CwO~LRQ)K9DB>l1paiZ(j8B@w6PnAw-THeN7*Ejs&CykY_RJdiG@>J$&O{baqaJv)xna8yZm1Lmb?UCZ4MDMuQxtDDbQu9)`=vG(!i`VUK6P~O^ z$xb!uXNOmqcGI0!)Tv=Y5{S`(5>>+)?}~eyT!pdQ*Z7>*4X`D@wild4xj%IIhfExl zBnfXLMm+5u4-=udySn>TvHDr+JdT%e>&A#~e$eW!;|ovZ;Aob1aU{WnB#xxt^5*^x$#p`X)LS9jvpvxhKp_?hZqvmlr+A@Hg`hM}KIl#rDE)r{k zK1hb)#kR-%i~X4A-R<7{EI09A>3+9y0_Y#u7+{hTG<|#+V{@PFrgsAIej)C1h+X|f zdK+m|@R=z`O|s03VM+dOn!_%pdj3$QAI)za_gFl&_kjD6DnqeZG|P$OsiG#+Tpf;% zBid($foyG2!(Gpo42w=ed?o1>lW87FlVt>r3ty!gk@0hO@Sv~uFhZgna7jZCWm+ou zvIN{PLIS2;9E%LT!bpp~E6>lg-@p8I8}Pbr?hTAwEh)lMcI+%E<7ZTa;mxgT{ijRG zacryUS-QQh4Wf=)%mmmoENYE9SKd^!k+%acTEc(I9`i;;yAfq78;Zl58hJ9i8j~e z+eNqTKX*Q_CZEOe7sKg<*S9ao;)o;an-?$w#t=|Dc;7-K~;0l2r9K~IqW*p7TYYM4 zZOV8&58@SI|!yNnwRSgLIxqGla zKV^8m;`iM7j1#9feqwove3UM|`rB$!)8QQwo{w?pGRH?Q@5HZ#Ax5!pH zB6U6QbC$l}z$((}t_!cuKu@Z^$Wx?LKf z7|xSuafdE&O9O@2)2ePd_|vLpAdc{Uw*rpv5zGh-cT<7=ZBY2rV^8|uIkz#AGFZS_&PFVf1lNc*XS8aWd5YE?yIV<|QU z^Rse>@XnH-2s%<`uZQwd*qfNgHOv8>)in%nfF@kH@VP5ZFczn^?>_t~jjuU#|g$ZJ9P zrs~PrjQrB=J*>8)-v8!OP?*Pmz!rCah={SHp@X>{ithXq7?IPrMj~B0l`2H7?2wd0f)fE3WbAfta0DR;Vm zj`%xdl(jn|1;v2sI~w09{CnieP6o(72p(Zck-Jat453gH)Rl^@xTJ`zz8wnEF+#10 zInwP9v9g;ZDtbv96WcrPM#||$W zWo&)7w7@$+N9~Tx(c%IEIe-Xmt~+uE2!MdNIpEwNAVT{t(mP-W0ptKdxVTY~a{;s< zT);n<|8GSA1j5CE06~FVs38ad7!Ke<3BV8_lp6p+4dH@AIe>655CY(Wb8!G6FqEA; zPbehljs-%%ARquYHcF^Bybv4#0>DwXh#LV$+)+o|aFi5? zfS`NA4sI?O>W0Ih z2o5+9%5_Hoae-i{nWHunY6pQiP#7`y-7L5u5DxCU-2nh|qgDrU7t7u35vVzUP+tF* zB2aOFz^Ix1%NQ;YhyxDdg5D8DKmZhV1%iN4dk%)$eFy{>N*97a`MTT0+Ndp$nkoW> z3X}`A?@$|0MD34z^^eW=FX-|A#vwsqs2lt@m8-2ZW#a>U>aogtF#b~IAx47)Mt=5} zwpI?Z8T7$6qy(J^jmP{hv6Wf2sQ21<=Sj(@Z%p#pHk4Qb)|{+%h2|Bdz#|vd584Z( z8-UeEa|)~Lblq<5D{+t>3Od{ZsE84KBU2?lNtzAIw)elGW`7ohf9CjIa-%BI|6B<~ZBTsmUE=;T-`OSp zQT~kdQAG$<9Z-DRA5}*QwLesBU)z}9A=v=XABf)Hg~`>y*aQ;@0KqVU|9k^R8sth47JTs*8g1(2tp<0f6BmIsPz0dJrD?iKqb+?$$&sq zj{TPmimD#}p@&MP|Fj1LgSb$&^xy4)QHuW|Lyi0|d#J=jrR%?s1%Y7P|KbDbppPo^ z4tM{Hplt4rT2&YdsI;|3p@nzZiz?uM)ZDvVzUu*wNPP$79}A7jdI$uQfk9MW?Ee6x CQ;z8X literal 0 HcmV?d00001 diff --git a/tests/workloads/mem_levels_L2/MI200/empirRoof_gpu-0_int8_fp16.pdf b/tests/workloads/mem_levels_L2/MI200/empirRoof_gpu-0_int8_fp16.pdf new file mode 100644 index 0000000000000000000000000000000000000000..997f21265a680e54e7464a7d4e1643cc8f3572ee GIT binary patch literal 12295 zcmb7~1z42Z_V87tmF^rGq^4kID3xxc8yr#)7`h}BkWjiykOrkwX=$X9?ha`rrM}^u zd+#~--v9IezHc6$dEa-d0|N!n7j7Vs1O12AQ$m^j?}N2xt*o+3jhcTg@}m(oSf17W{c;Z zx}!I3HzP>oJ+8g+^)*#=>mnv6-iUPSdL{l5#xSdtD&>pcH%|thafi&rRT`yq+zV@n z&xvbWOoFs7KCm+9T1_`vhU71CV`_Drq%+j{3VFOxdhqU5>)g`Oj??Kh;nlpmwEKIf zU#oawiu~!uVn@sEH6^okgd@IJupT_U(@+exMrXzY4=u_^xf7qwk`Bh}01Y2z^@UE# z+!&hRRuC6&z8UrslLcGenS9KxYhsS|{F~1gE}CQzZd6L}yACdE|L+^XSF+hZ9%oS^B2(O(0f*1`;-U9IKVU@h5tIS!_E>)=WHlvjj;h zg+R~g$h9hIuNSPLRRdin_(-xa6R<730w=#V4j9AAW6UKhIVn=x5KUTdBwioN5migS z@?M%`i%WW%Tc(4lRA$Gq^l@EMM(LBX0O|+CcYcK4Wv$OFjDPth+x6U9;m1q`t>xX# zsV0 zPoM2httC$H(Y)AL4 znVeRifW@d?qF?Rt6w-VY4>9B`Op~=wbrfF>_c(EN6cVVUA^6pz<0O;`wON+1qP+lU zEDW0NDybJlvwIfn-oqJ&t+(SW`Mgp!9UFQXM>Ej3E;LLv_Ow2n$EjIE1wLZYAEF+P ziKE2Y<)Ns!_#~NFGG1C((Xfodo>!gITVwfdU5f_$G6OaqA~m{9T2$OQDeGg;0O z{T)p&{lRBrQ=gn4ki1h1Zk}C^&!HkA!%?lEs40JRe_0iJgtaKOD{u6Atc!3^*{%X9 zE#Wb4wN>PwD|_BnBDzccK2&3R>8HB3nDG>uAH}9q9)7fnVF;?jAm3r+f#l*Ua<#jZ z9XYXKtMgW{kPB3}C0wWqDU62O0L2P*Ep^J404MbG>2V*@$-ir<16tRa{mmlnq05a~Et5Lt*e1-XnvW+GBaO=+*EkCjit!AnM|SN2 zFDyLkBRAV`}_Lc=M9{-<23CH?_1# zv=3bS>w&=<2gefoM4%Z1K(9#^O{e6{-_E2 zFdQ)#(fP8ea`oas)LYw@)3l8x|FFl?L7|r$mMChS(y23-wD=Aann;;F!;J5dFJ_ zW!vQuaiqkxEISlS< z{L&~p=UWSDL4e?&vRkQ=xtSGG9OVws2cm@nU;#c57yyCYUeH5Hpl!_UoSgu-{R-_* z9o=b7ou45c{}7_v@t?N<#6Jf4N6fd6|MEm6{_WDJ8UEGy zLAO)*H#-TWGtvfSc{`3Jda3?n7|`Fo+5FisK>!d4Apk}P`@b|*I7krj_oh1P>0zKb zI(4JBHQ9=|=nZnBTDcRn7#xiE2A;Jz?!>6|m&jJq*c_2O zPT6vVWY@>1Ni2dkJ-XsJ0?UR2!NOqd#|gtPL1V(inMX~Q&T8NN$Bp!)gN5kRBR+t+ z^PWsC#Ft$QRqKkHUmNfz5f7yhE!!9Vs`s<1uy9L%979Ap*1c}d_0)EsqW;MHFtA@U%2d^-RWG9^pN&WAey%*>{Ln@IE}(k_j3?SPekoX zoU1$f=y(W_O|u-YbQPw`;AOkTO$M~Nb=ICPrs}F^RoLB7Y$Z)xJ3sYVoEaPFx-U*5 z6ta%#luL1>c@qLe0-4GeBOeS8D30*AkyevoCWLtp5M2?S ztz|VR=V9+t9ij-W+a1<#E?oTxhqMe(3n?96R<8q6emeQI7g92fa}%A`4OPXAu%0q? zw<*R)tCdHKD5n85%}6KZtD_oLh!DzR%)Tu1(dk@ST2pUav$-lC)5~`bcS9rkvk8A7 zjzG21T0^$Z{GyT(KO#2fH)@V7I}+nup402%Z4CsLm)U@OOd*r4HUzIii_A1_Xs3G! z%9eRBHXk*YQz-Dp6XM)8Fy44=o~_IRL8%43B^UxbUqY8M?$%Qu0C_Pkg9-Cdfdu2l zo2P`#48+YY!7^C(qD!ytoe?dC-VqCR*SN#@)C+Z|>7Bdt9Y(3t$w1y#`#F#;R40&y zfwq~2Xr8i}g*f5|ctTj`oHm}jD`Ko8g2mX7Qpo6)R3~OI$Nhbqwo~kVy41Zl)#r3? zgDdX2^DTwk6(KyxzLORK7k*6%=*L}0670^N|rQ= z<_M-VhUWHQ%lr1YOG$U@+xAU1{MYK7>&Xrz*52??bNiQyyf#;UF50>}u#;73O)mpz zguTvM+1tsgN^nUHINigaX?l3@%$AS^a6qcIGC|=Zt zZKQ8cif2k*Y2TKRo<~o^_>oV~y(_9D*5B0k(^%7}?up^ccx|~!+njwMj+hn7JW;p^ z4z^<;<`MWEd_HmUWv-5H$hF~AVy8hBZ^bRAInwR0uD)WvD>8WQ4M&Z9c<|ia#)hSk z-u-dzG=Q~lG+&x*OIF@{j^L^EU~1vAvNK_Qk*7y8DpbGSNQt9L9;bz#9oz>;nUTs} zV47zo!;)a6{^zgHIYGLCy3!;G<_$UT0)!6f6+*COfGoC~X4PC%bavrDnWUKBnxs9L zWm0>xYPbA2NvNUYr+VVgQMTG=_}!+;+0EH^s8~BBS+iDhSy)id`P7!!@X0CNhLnEt zc=DwTj#U)B!OFyb{*|QJK_|!Gi8Zr4dLi524A^4=gR?_&30W%J#muZw~J`o|74wMqnw=r$1!r5h3feW|WhPZYI1c z`bM5kxGy3x0Ny@ zqGc$V_m+4_vMMmu1ZSnLnan@OIBeJ4mw~VQxbi#3%7j1H{WuYo*XWFhWyx8xx{t^q zh>I?L9R87S?3kBvxJyw|Dsg?A#W3TY#)7O+lf25g<@Q(I-y|NzA74%ktdPyT^-SO} z6xSuC{6-f-r$MfJPg;($q#^!1aAoYbOxUkRh*<5*gn5ky*HL{1ur)7!gG*5n^>Vho zhgZ>d0cLuJ)?vHP`Hkn9`8Z!IxWnV6KGqyLmCN%JLwD2>JRmc$=HR-y?#R+)SZ^}O zSEBr7gL>{O?J4b!6J4wHsl1mdlu)9;vAearS96HFF4a3;$@P-TKb{NuHFjRw;J*yC za`)MvR;OXw!Aafg0l5F6( zKOIj+IK|#it&6|udPl}l7MbRga!5A$yej{GDjx1|;mJVID3*EnXAZrst%eT5&sCd= zXRpE@rw?yz%+hkauv5&%bE->aDx=rcbF);@(x`QwJpB3TI|q!jzr^F_J*CGy{`}Cg z?_&j88iz)jRDR=h{_iODcCSZl?0IBn0Jw1zcT+fREX}raT_VkNYtq<<(S^u3&C#9& zUiH+l`uWMGUt;ryA5n(&vh!`KPMf+~z3~~Wbl6=M?5fO@k9}1rpEy3N6c$Q&TVwFN z$6C_t_XFP(622)0)*h;dEEy#IZnSdNin~ca!>_iNBM_9Ihm-qH78`M7wVU2MH_zVN zx^sVc5@Hq-@QpT_##yZd%AWQ6lk52_)sD_V4Vs<@b$Z1+(F2!Yg+g`REkwaR(V&ok zNFCouwH?;cHJAR;4Cx475|Q2gXQ?;ubV`0{)9fTfTRm`^_)x&59Q2_*k0|IvTSu^Q zwe_!f-m@C>9vABs?God4?E=;Qg}k#@I?9V}1(m`|MQd;CV-pULuAmr6ppQ?vh9;o&0!1o@?@!mUc=q+EFT>2pk-`Q}ag2L{~J6 z-Z7bf^o`@HGv~Z)UZX;g;P`el9`^V{JE01E>?g*|52eCI%|1UCE0ll-c+!N@h*aLfEjkSGSNt$sQ!+EkC5Qa$apD_LBe1_>pfE0>@Ox7W!j zZM?oJFGXEtWKr3D>0oIZ?g&lBIEJ|OpoF&tR1PiK1RI_rPTgMSMnNt6Um0eI0(o~z zpp@b+e%NuJh@f!-&(bc`WdIBejKexhZ$8^Bd)8>B)OW??%&_ z91YD&nbm$w%(qew^rx>H74g3#RWYofBuvx13jt^@ysb9v@oWhQ(_@HIOX$t}SK>TYmZY1Z-J|Y`0Tc_; zMh|mCvRRY@7@S!fI=v#yd3MLwhh&h5ss%L~D`>XR;A{G_@D1oQc$P?5I>IT_JahY{ z7S)W~j@?8mRe|cvkH_&>@z|AKy zAIh~?M`Xg7dD$_Ca+v3Hl-=boD8f`{iWda+3hHRX!jOagvW41TvNmF$YgH^IS!zAc z=vY)C^j$aApZ6y8ku&!>=bmffA9_F|c4@Wo>cw`(5l|t94=QfZMcv( zI$!YDmOt?@4cGSi-3Lq8qRT@#CGdTCk2&7WH`l#+k`V>FawEbHWYaZi!B-2yqHzFL zQYuM}=Le@qW52*UxWg-3M0UbL`!G@XeP}P|%Z&_L@qn*K!oIa-vwF@j_hpl_Mo|J> z5iyJOaYd{6$FtJ5y}45l1i|6G9GGSTpid*sWI*|E(9p1)Wt~6|nh*U98NVi(6Ipnl zF@j=;$P3#p$)<5M)nrrNgiK%!5%q-cEA)20=PR9KEP9btxfE(+i|gN@6jGVU|E)^o zOBMaPbTkM}-0WR#RA$fK4zq?1c3>s>C?w3Ika z+3h6Egy|K>UPU{AaD;faS`qe||MyyZXztdg;dG77WPik98^?IjtLT(O=duDb)l~wY zbI%^wwqy^b`DZPDOOJZr>(oh1VPoH~UMW4V4h!6_Nw3~~gi&k?MBi^xFNoD)>o}u) z2-Y0BE1L}1arXZx7cp>Q!=5b*vsE=wX%2|L7eAzSQ4E~=R;TCrE?9rUQ<>s7-BZtt z21$avI3gn}d$FyFt>VgJNMX2H+wulqPGDft_QrFXlmQs5GUpB)_c8AXVlpU=XDUN> z2aDq^j=}>CPub41yKAYPO~q@|XCk%ll)d~uon!WWK4ZHUeVEygo&H#2e8+~1K{U`V zyJDl&d3oWfZ&GaEP4D9s#)HQfQ}Dd4W1hU}r-vk2UB#?^k%ni2nU?oFEhMkv%_jLR zyCxmqUWOK$VdgL|?=g2Og|Gs?CBefLy?iS8#D2aJlT-^>C+2GeO`;UFAR{E4QLK+@ zv$mD%d#;B?a61Ppu;?U0T0p%k0={nc`B-rXPDn65Fv~(RYbbOx`Fr!76*hm|A`B&o zF|vpeV~G}C@pt0B0b#)tB!{1)Hgb_T*)J~e3R`$O{D8PDKW2J!u&n5HWkx@{j@0Y9 z2`Hs}qbOr`$`E@7fi>xSDa6J5REQ>L%9KRisbz%Y0zADflza4~v>i1C{@3^i>AxuO(tVY=P*&BmvG^&9jmBcrsN+#7($hQ&6>fOiJ9U5YK|-}fEAMcc*sS(`egikw*iFAoH7kGpDLU=+R9mGop&Cyw*@y?t zg|2s^9QwuTCo_TD7)k08%4a1#JOU*z92fI0NCRtlCgT!*byRB`yHS+<9JAH-@~Vg& zWs21dTN1xIj5N9i=EJ5#k27{ht84ckBHK3Wg+~ghgdV&j>PdE#syX|`{E49{)(aq9 z&RQ-+5~=(lRZy)U4R7K4zExOfEH^oy$Y~qtK*;c+dwRnAIhLZLJ@ST`yv8)P5B2T` ztQ4*&JA%h8C5s-c9H$=Hfzgvi>kG`qNGj?DLXI5gw`ROmg@Zro)x2@|jIc+onEVYf zgeOuQI;jVJd{(2c@)X1uTXq)N7GJi0ZhhOb$tC}~HqDNy?Me7ON*TLu_tmolZE$rc zT^Y;gx4wQS`Jt2SIXiNSB5prNzP7a)IyiJi#tB)a>m1mT=V*p%e3gY;>^rn6h2;d2 zmtSB$8c*3=9Q3sO;8Ddf)Azs*gSsQN`VE6O#`woQwfj-FxMOkE54e#}B%eyUv|$q` zu&mrQyF=fM^#wbi$8dyIBD(B-yvm`KSdZI!5N(A8zI5g>nd? z`qcB26)r}Ru9E#4EAe028bzkUS~j0*%0o!Q8)q9X=K2j^@PEpikdlpxuAKQZfmGDDp|pb>S~D#B02|;Va2y$iK;+Zh>NfFt zjN_Lg^9;q=Ddljv0Pec9cBSY<3ml6Bo~O#tP;(EPEjAR;#!|VL zn%ttLu$;6_;lqj~o9b~&o<#Lmx_E`vLz*1%+55C3hWn{rPrMbbBpdJ&7C$-b{)`kz z!8v*HNtIAP=x5SiU3|m#w;o>9ICt?H^^rkOT)Zex^(y|#srGq09V>0(!dizuSyMZM zEIHmvPx&xAlq_-ScMb@^EpTs#J5X`oO(V7A8LcX_M$K2A7JQdQnU?KG4igWs*jkaL z=I-J{p!S~!xzsG-*9;$xn|^5@-Qg$u#u!VNK&(wvBUnr`Fuv5^QPn}M3UM~HpD$!= zdi1VNNtFbvvGFJ;>)2^cbGtCT;(1^H@85T;@EK!seFR#BHZVeu$)Mui#36 zRPx=TJ)J&uk)~FwE;tij_NB1;Zoe*NR?8;)+#YCRTBc?52u!K}uBg4*8 z9EOZ+qu*r6X813Rseu;dlRx(AS&C#@zk5T4g=h~{s^L9K$eSl6aP*ZPggg~zw`I80 zeiP60(#p9o-0a$tJlTeM=#tr!@W)mn`3xLy>p3(2|(R#SZkxEPRe39Pkty2Rnic z8LA>r6$#|ZfM>8GZN*($Rs)_X@>t%`tY;p%iOO&H@smgAPpq9hnf&%CYCwgPKmBs$ zbs)X=jnLwRgh!`Sd~sUsbkjva(+vXE1bvRmQ%*{{W*Qpnr|p3;28W3z#|!$5ls-u3 zEq2@-6O9t@aiDGWiLJ?uH|>8O_fXLN?rEva1M_5Da~@*fa4Y6V@Qr(VZ3%?jUdN-5>F?iHiZ1)!#s55vN=Z8pHrF1!Hd&iK z*9mQ&Y?IbL-_v;5y8#gFLk{DV>Cy|DRKR;FnEABcTMYLS#KV5iX?f%9ga*%NK(X-HUUwgKOOZ3}4InkH)Ke5^8OA z1wD9C58n~MJMNeCeJh7txKn*jMO8)L)`r~h3mS#^=v5;j8g|o4!qq$DW7^>`jH)_bi9!h*9~pLPDVZ`*B$IiUX&mUMPOEpvMI|T~ zw01CdQ2juLq0jV374;Z(wT(>FBJmbWwPX44mzl~L13Rvo_-R2JZl$<2r7@*y8uc)b z8kd@)v4h6t!mLpcd7Mi1aCJfmMm`Qnfz4GH2W64(3wH}^=-#VPbt=}@h!gHyR+<|-X)yT;D`D1+@& z>S>u^I`QwNULiSnJr+D)b*fE>Z&+Bw{4NJO4OBB`wH@N%i z(`u;;+E(1L;(7f$ zRNSX6)Terrjc7 zni9e+jn1V8ggg0s9V5F@w0LclMz#q3*7?de{om-{F>6WF$s^xRIAJ9Pdi9PrMX501 z{>JHc&t*;yBnZ*H?f-vYSgL^UUlD)Ov7|d3%N)ua*F~YEj(co*ryWIo#M2(spNXT37jws3ZoHeM@qy= z%{6CyzZW-AP>z>ofQn1szQ0wpFG*Uc|4PTG6KN|IUw;BD9)E&h0{cWaVjlqh)41#B6KbV{%5!s0K3*Kw%*TSCo<9;$mNhRRW16{h^b>N%UGlyi6 zM%)f7dt>`VFJrvWRUnonLkvNZ9hK6~;l{Hs2}QwSA|mmSHKz2gG)Lr`wibZ_1!(c z>5Ivg=?{Y?B~rWVsH&&N_(zL_DH0`Vd|$OmkG7EsuWCQaB+Kn0gP^3&5dj+b*)tZ= z>hKv0zZKS)RGT-fq|RH`v2~LfpNVU;pO{#trzYZmAWe0&WMqYBsMo9PI%Bt8e9RhP zb*p?caNmK>1kpADpg9k9^@CAnCId)xgL~iN;JZKbV<1>m8f2nxDJAJ(f>Me*3epi-oR3R5AdN|WCB|GdXW z$?Cd*tdaCeD9A zED~~(x1ZiRLem!LCk>R0oTL)c9?hwkq1VL9+2aqfx`z`wdO14_)Gd0VW^QSPreiz+ zoKMj>s5zP)RdF;kceJvz1aSV-3@uc5vA4G|x4m6j;4Pz~eG8}P3j%?BKm<(i7G41Y zARrhY90md+3~wX7WmXVCJ`h9@hK^hipbrrQ{<-{rDFPr6K|TZs3KT?}AOK((KoBhe zLx4~i0D?9VghTm&a4--85QGcz0U-itKer>HshC?F1|a|e0bnpF9|8!5+=4b>1p5AV z+5glLfT58YI06KKqqhi#03&X}8yFld1tK7DfFKaU2L!_)P(uJZ0(}ACtz$vZKUD=G zP(GNT0D4~qpa?!V5Gr`fx(I><&=W-G3_4N3d}!S?8n>Uz=;E0FK&6;qVRl*`ufNAPS%JjfL$lE$mU_MK+wrh4-d^(&~Ft z#&wR)CK_)%5vIWO=qH03Z59dcxnT3OmAe#p)w?WDjf+6|vhGr_tgT3&;9;pNlvXu9 zjg<0PhQ9+tcFXa%c63j@4CBq86NEHzkHBXq)t?9cUuXFC@S-ct|9sM=?9d?c?ZN!ldFGY!#_Ix#d*ns!#V>@u2JMvwcq!sG5}Zh;2`fCTV>|9Sxg1q2`h01Lps zWFR!LcKZU@{Zj@)K+w+rU53tYwDvm+8+#vN~=eRV5O s^r{M=nL!i^P0!sPTXcc`qo)3|#ydG99i9JJXf*!@g5$BVNvTNxANNh~IRF3v literal 0 HcmV?d00001 diff --git a/tests/workloads/mem_levels_L2/MI200/perfmon/pmc_perf_0.txt b/tests/workloads/mem_levels_L2/MI200/perfmon/pmc_perf_0.txt new file mode 100644 index 0000000000..dfc38b8643 --- /dev/null +++ b/tests/workloads/mem_levels_L2/MI200/perfmon/pmc_perf_0.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_ADD_F16 SQ_INSTS_VALU_MUL_F16 SQ_INSTS_VALU_FMA_F16 SQ_INSTS_VALU_TRANS_F16 SQ_INSTS_VALU_ADD_F32 SQ_INSTS_VALU_MUL_F32 SQ_INSTS_VALU_FMA_F32 SQ_INSTS_VALU_TRANS_F32 TCP_TCC_READ_REQ_sum TCP_TOTAL_CACHE_ACCESSES_sum TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RDREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WRREQ_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/mem_levels_L2/MI200/perfmon/pmc_perf_1.txt b/tests/workloads/mem_levels_L2/MI200/perfmon/pmc_perf_1.txt new file mode 100644 index 0000000000..cd7a1d5f55 --- /dev/null +++ b/tests/workloads/mem_levels_L2/MI200/perfmon/pmc_perf_1.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_ADD_F64 SQ_INSTS_VALU_MUL_F64 SQ_INSTS_VALU_FMA_F64 SQ_INSTS_VALU_TRANS_F64 SQ_INSTS_VALU_MFMA_MOPS_F16 SQ_INSTS_VALU_MFMA_MOPS_BF16 SQ_INSTS_VALU_MFMA_MOPS_F32 SQ_INSTS_VALU_MFMA_MOPS_F64 TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/mem_levels_L2/MI200/perfmon/pmc_perf_2.txt b/tests/workloads/mem_levels_L2/MI200/perfmon/pmc_perf_2.txt new file mode 100644 index 0000000000..952da7fef3 --- /dev/null +++ b/tests/workloads/mem_levels_L2/MI200/perfmon/pmc_perf_2.txt @@ -0,0 +1,5 @@ +pmc: SQ_LDS_IDX_ACTIVE SQ_LDS_BANK_CONFLICT + +gpu: +range: +kernel: diff --git a/tests/workloads/mem_levels_L2/MI200/perfmon/timestamps.txt b/tests/workloads/mem_levels_L2/MI200/perfmon/timestamps.txt new file mode 100644 index 0000000000..676cca1b80 --- /dev/null +++ b/tests/workloads/mem_levels_L2/MI200/perfmon/timestamps.txt @@ -0,0 +1,5 @@ +pmc: + +gpu: +range: +kernel: diff --git a/tests/workloads/mem_levels_L2/MI200/pmc_perf.csv b/tests/workloads/mem_levels_L2/MI200/pmc_perf.csv new file mode 100644 index 0000000000..047fffd111 --- /dev/null +++ b/tests/workloads/mem_levels_L2/MI200/pmc_perf.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,wave_size_1,obj_1,SQ_LDS_IDX_ACTIVE,SQ_LDS_BANK_CONFLICT,wave_size_2,obj_2,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,TCP_TCC_READ_REQ_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RDREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WRREQ_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f764ae94ec0,0,0,0,0,0,0,0,0,0.0,64,0x7f3ee4578ec0,0,0,64,0x7f5f9f2b8ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131079.0,131072.0,131072.0,200269062125200,200269062145520 +1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f764ae94ec0,0,0,0,0,0,0,0,0,0.0,64,0x7f3ee4578ec0,0,0,64,0x7f5f9f2b8ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131080.0,90825.0,90825.0,200269062165520,200269062181200 +2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f764ae94ec0,0,0,0,0,0,0,0,0,0.0,64,0x7f3ee4578ec0,0,0,64,0x7f5f9f2b8ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131080.0,91006.0,91006.0,200269062256560,200269062273200 diff --git a/tests/workloads/mem_levels_L2/MI200/roofline.csv b/tests/workloads/mem_levels_L2/MI200/roofline.csv new file mode 100644 index 0000000000..92ba4e75ad --- /dev/null +++ b/tests/workloads/mem_levels_L2/MI200/roofline.csv @@ -0,0 +1,5 @@ +device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh +0,1388.4659,1387.9966,1388.9353,5014.292,5011.3125,5017.2715,9222.2314,9221.6152,9222.8477,18047.654,18046.666,18048.643,20934.172,20874.197,20994.146,20264.623,20263.846,20265.4,170416.62,170413.19,170420.06,164843.52,164838.78,164848.25,41416.324,41415.676,41416.973,41470.824,41470.078,41471.57,166316.98,165829.77,166804.2 +1,1389.0763,1388.5209,1389.6317,5027.7285,5025.7261,5029.731,9236.2383,9235.5508,9236.9258,18094.5,18091.361,18097.639,20977.633,20911.295,21043.971,20297.01,20296.498,20297.521,170866.23,170862.42,170870.05,165155.59,165152.28,165158.91,41491.578,41490.852,41492.305,41550.871,41550.168,41551.574,166913.05,166909.62,166916.47 +2,1389.0742,1388.4591,1389.6893,5036.0171,5033.8262,5038.208,9262.3984,9261.6523,9263.1445,18107.012,18106.16,18107.863,21049.77,21049.328,21050.211,20350.424,20349.812,20351.035,171118.78,171113.83,171123.73,165490.17,165486.91,165493.44,41582.547,41581.484,41583.609,41642.512,41641.527,41643.496,166939.88,166355.44,167524.31 +3,1389.3132,1388.7598,1389.8667,5031.4556,5030.2266,5032.6846,9240.3389,9239.6533,9241.0244,18023.418,18019.99,18026.846,21029.805,21029.383,21030.227,20311.688,20311.004,20312.371,171010.95,171007.27,171014.64,165229.59,165226.11,165233.08,41444.262,41292.633,41595.891,41581.301,41580.785,41581.816,167019.86,167018.14,167021.58 diff --git a/tests/workloads/mem_levels_L2/MI200/sysinfo.csv b/tests/workloads/mem_levels_L2/MI200/sysinfo.csv new file mode 100644 index 0000000000..4319443e9e --- /dev/null +++ b/tests/workloads/mem_levels_L2/MI200/sysinfo.csv @@ -0,0 +1,2 @@ +workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd +mem_levels_L2,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 02:48:54 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/mem_levels_L2/MI200/timestamps.csv b/tests/workloads/mem_levels_L2/MI200/timestamps.csv new file mode 100644 index 0000000000..ac6d613e93 --- /dev/null +++ b/tests/workloads/mem_levels_L2/MI200/timestamps.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,374061,374061,1048576,256,0,0,8,0,16,64,0x0,0x7f5e2ba9cec0,200269062098147,200269062125200,200269062145520,200269062176465 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,374061,374061,1048576,256,0,0,8,0,16,64,0x0,0x7f5e2ba9cec0,200269062157580,200269062165520,200269062181200,200269062252319 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,374061,374061,1048576,256,0,0,8,0,16,64,0x0,0x7f5e2ba9cec0,200269062191985,200269062256560,200269062273200,200269062274741 diff --git a/tests/workloads/mem_levels_L2_vL1d_LDS/MI200/empirRoof_gpu-0_fp32.pdf b/tests/workloads/mem_levels_L2_vL1d_LDS/MI200/empirRoof_gpu-0_fp32.pdf new file mode 100644 index 0000000000000000000000000000000000000000..f10d0a494fcc1acfd49bdf1d97a5a2feec8d9a33 GIT binary patch literal 13043 zcmb8W1ymf{(y*N%f#8r}!6t&+Fav`G31P6{?(Q<^-~>W&4-h;+2*KT5fI_}00Fj!mRS7! z>>>^(25?&k0E39RgDuR$3C4)UF7IG#>||tu5Gq+&7_cM80$@Bmh#&q?wy?E<8o*5e z3{XB05X1=t1Gzy!E>0jfGZ09R_(SN)*c$)uDuRMoCN{>%C4m24ije_;1B?Bw41itM z)&XW<{kIb5-%29FNTokjr9}WhEOzO4e|)PUjfRi|hZ&7U&OK zi0}W^7We;yt^dDu@%(K|%)%Ouh(5cRH6qSX6C+z=gfG%2HfC^h00$>GL{Jdm2uIvE z7?$goUCkMr6$sAzbG3`w50!PF>K=&t$dpX2!%$C9hxbTCmA=m0W4JRcd=J~*G5(DA z%akqxHuVA@pEjgITqFJ{d*T8wkH^U;w)D2m=vt;J+` zKc{kZ;T8v>yt(#nO5YYrS`xx&#d!C(ZfCd8+nHdjwRi&V)|Rn_X!3&JBv%UrAs*^?V?e zK=7G9oQoq#rMDm<2=i4-QAb~p@i)dGt6-uD4rb}GLOhjGCm2b zUT$-6v?e6fbaal0k>U~1RHSA1f*fU^Vaoy;;84p4WnZU1K9inax>;E5Bz%ft`ws1i z6n}VZV&TlkT)$nma=%2mrv>MqT<)bJBk-Q`xd_I7*l{edw;mz8?+y6a>c9|wqGP09 zI2t}pKi$eX*2*`=_HB1|rKVSpB9V{majB%LBU;6j;zO%7b&r*GCVU%oMn<}r=t`|m zc)yiv;mka;qEECdO8p!$GX~nUeq$zppYmU012TfpYqhdeTR!@lX=9X;6&YBN>%g&KHkY(RyRP3P*u14c_qo zbd>8&R$C8>{Gq%$R7s^8r&g%?oSoOy;jl$#u)ZK?tZ28SY`ngzIZm^5ZWc=cx_=oW zNQs(fIbh|Hm!na<&9EG!Am`BIn;rQmC#-sPq>G*?NGTPs;CR!kjO)C7TASZIErJ+F z=qb@EL#c}rQ&E>TC_A(XKFaIwNig??hLK0mm8W!aqw*chcOoL3gtz=S&^c8hKFx}r z=rB~R*!F~$YRXkxKMkhxCTh6q!E{M)_%;p`0hI%BN_Tx>Kyw0GhUm^rqmvQYDq_oJV`NDq&kD7%2x~kzHAqE1K74LD4*F7n z)txGTc`BAZDx5EQD?%U1Ky)PurZ9zn_K?)FeH@p^5JO{ZRhQ{mYr zCkv(S)Lxih^7u|dQ_lz_+k zp5b_)R-ySLkq@%sfvMUd(PO0lNljab;xSW{|(YyaO4Ov2mtb@3@Mc{ zF}5&xYwHTo0wRQ5ATBlz5CF`LJRqhLL5wl6fja__4Gm#W3DJs;;PM6ze+Uu%`p;7U z?_ZPr^nLkw`MKb6H*XjQ4`vXL zFhDkunz5fT1F9&6E~@wwYTy0q&3odm(Wflnm)X+&-3?flx>Cc^jn#_v)ml2tTom06 zjd41D9s3%|z80s>3k!P9gZnJwQwx>n&r;Vl1}pF=$R6-)N z&W*gTUy!oUS(mTJ{V;w!|D4ex^5$mC^Ff=ddn(vjQ8#@n94LPcJaseM3A6A@Aeh5# zsR)|>_VwVmq!M3$0;YaCWXF}KIEMg7xn(+ddOVOOMdjebQqO}Dg_-Pdn)rB{>j_)I zOmWJKI<(b$jl8+$eX8dUCV)y`c*` z)}@m10c=oy=3agNyS@F({fmHUwcPu})*jK3B*6f}2fGVVgV@;-%nfq~>>qcVQRHdm z6rUYfn0as7799nX3;GrVu-(;v9OQbou175fk({z@&;;AwRa8t}0I0F<58HM)_rvaI z<&K_T_ip2Qj!;(5(%36`Y_TV}pw~2gw2Pz=nPE7!bdf-3?(_98K}-FZosKg8H1P3RTNIFs3Tb!vgPqWVmdfV z8DpE%VVke5<=}3Og-S@=^$kHWJ^!yS{tsI{aBcnZLH7j<3*r~4fFe46o**mC1&a3T z$7bk<4_nXC4~1LLF%BvG0?`hiw@&p>LOzXCO-uX22!4M7GzA`@3iBr%03Au_=a%ok zzvByDGxgGr!Od?COxByQfBu_LnBV`vSC~I`+#|3$L z4t~6jez@${g?7l&YUF$Ixb;$4TiR8dV31CmpxqHuh_YRdh?=II){h>|p7D3EF#p8G zyNj3O^>F^kgN$)O{@7>la|NMJmUcoJqjF!)6PcYTWiIXj5h~4&cpS}H%TMd>-yGb* z`~uMref`RPU0?l97v@juT-z{`{8c3+IR}xU*DJ@ECeXy|JL7u}R6*mSfsJur?bHvM z?H6BB)(n~5hYNDKr!jJ0Q4U`}l~3b75tLI*^Q}HnfZ1-n5AvSTa!)hM88o0`tzDf@ zJGDRdUFHdkTMi?NjFSr!P7?(;-M$8o-wlL`+oTNL?8lKmp5uQx4cP|EW(|p-4uw93 z4T}p+gOa{KXl6#2ZD`v+8t|qS`IO-+XA?`=JtW+8dlcNeIm4btVCfdkn8pB)BzXVC z((Q$sb(`acM~LU!jmT8HqkWQ3QN{Gccn_H{GXSJdkDDbSkGA=?-GQ3tn)p5)kY5lo z{;IJmEKC;}=YCY0etp_$kU5;EQV0t>;?hU<<#Tq#yq&Yxa>dgPB`k5ZX1 zF9zI(<a zFJhmjU^f@+s4)4cO{bU9fHR73?S>AWPpR2zBQ4vw)_D+*K;+D4Qr!;dz^RXW!n zD`P0W_hZ_m?REvc@2*(%EdO}=JQ^B1kev1@swpP8*oO072Wsp6jWu+mJDsa*_~wau zkp(b6moZ0&D(HNEw4D8v5_*E4UMv1YXE`W9++1L53V!FUWHZ+zbX9_r6YxZN-fy=g z6_%;$Qa>Eg?>(0mq(vtN{R z34u;vb1VkmSb^T#ca;v3yy!ZgU#xzP&VO18pUqjz(aLphtCqxw6k$;=ca%rFKD3hV z^6k|Lp&IzjIEzPWL7b~aua9mWVEC=0jZWk-``YW`3~>5yt5$->XWRDaBd`_$V~I&Iu5~G_EgjHY&u6&V zIH;eWK9d8Jt!=pTkc0JKq#O1|Ig4Nvd?4nG87LkXy$u#CQWK<4RV!J&q37{;i4r7X zh?g8+eArv8pC+tCyn-`*oua~D>g}bn*ko|$642#jexIMUU~!-(tQrf8Yp%;>v`Qe# z#4A>OuaaP1ph&bVbe~4;HJ^UlQebeG*D2_NZnhiaK{`hP3j1n31gl$EXS+?*u6QT& zz4@+I<*s!3R_cq?Qa!tU#5S7_nw$7byE4*EA-Q8lc2db>=L5R%Q~Hu^EwI>gs#0 zyvH^8{iw0S)UB^<&OwL7D(TcwOIoUQTbJk}XDeiwripBKCuKF88?iFKm{YG0T+28h+Z zz7Zi5vba+d9u5Jhg*C|(eSvT@EOB2`N#>!r6DCt0Q^VhO(p8cBrx0xGm zo6$A5OVv9YX6x!Os>15T@#KPHQVKh=757JvNUDhp(KL&@#`M;3CGnj+1ZD{qrc#E2 zZL=7EGBc6(r4`q1Ln9s2g7+45jcxVn+ULJ%98dA;wywv#()KVAP$Od)kdxg)k-!Z; z?p!_2=?wL}GbJAr%qrFa7%#jBrj=u2s+l*=05aJsrRuovmPfMvKh+O^?r|AO#7Y-w zL5+eBFGgV|^yq!4#X|Rz&K;9%)Qo?(Wo4JQ(8Je2EM;~$Thn;BzPmN$Ef;;QJPy~@ z5Ke7FF(9D99AcW2x6oPDC9yf;HT<<6j+K2{+L?#dHcYJYuz6W(P;GEYg zqig5o8T0AE3rkhpRT-ZuwOFk6?O;28BiXekQ(x_;RwqunU2I{JJM)D;e%JU?M$mI| zb&urx8l8RqLMc<)2=REhIrev46^BvEwkN$$w!(7CFi}OnVA4iwN7_E?`;{e5A}Vt{ zWB@YMU1`X1Yl4-q_Hq%4(Gfi%Pf3@OiyO*y@?`G+G!&DW&8Qn``s+jMY%;E|MA)X= zc|(QW$!1p?4|s=pZSz>)ucq$(^;x2|%DJS~^REkI zjV-FbPsAcF2Rmm6+ex6ZJ1jP9EU9?7na?Y>s;{1rca#)mBlw{5?DhMNU@nUuMa=Xm z)|+Jbo#X>!5`((3F`XLs^nuG&lWbiHrd$^N-pHQN{^Rv7MqqRYuvk3UYK)KZWdPZx zw05NtdH*8GS;<76%#y(2SdP(?@`XhBhI)UTj>k`KYj@M`^jy)dK<}OcIRiuM-Cj9w z32A-@EzORQd!_}x@{$~$^i%5Q``fv47m3D!Y@K;&zK))x^+(?labX|Kf1*{8F{uPN z%Jf-2N;6e1sADfBFoL9T60%=)GId!vM*d`lS@~3bhT~?B zn$xj76k)K!DAahp)Ay*{qwsv%VWU7OMZgC;A-rn1eF-=x`e-M_rNiVa9nTZ;rJbqe z@Ql&+fMeIZ=kJqqjBCZs10lcgR-dd60htJjq0h9jQ--2qAIW7pmWHdfYR`b$))Ig; z;0*jeS=P>}7Mpp}b(yPZY8eR`y)_m{#vF)Q(CA!y{O*W)H z<)wb@9tRi*+83uH7g{=aS=?~F$9&$HP?$Q$mg>yYzG{0%>veK1Hyc;ya(mVIxG?w% z_Uil)+W5!_^><$AOY!)(ahXJ`IWJzGXOn-yrMGg@OFE*!pw%EhdxReTK*sa|s{QiT zu#;>X}3UB#)}6HmM+m%I+n5j8o=W+Je;v1vXXU#$vF zTc?*!Hkob$>HRO>?MSF5eo7@_>Q_+Pxlnyfp28Pc0SAyDWinS=Yt%Yyla!jwGnrql z^OjofjU=~MT1~W9_TQ@Zr&YV3HeBXk%xw4ejtf+mSnEW1yKHXnH=et1+IZ(@FbiI7 zd#BMxWCHr_qt$&vicx4LK-zfF`XaA% z>~UdYc&#I~VT5h7aeCddw=h3h+r-|&#gY#yyUi^7?kJm5(> z53^-uldRwNM&w%UQiX#DW~FZ*TS4IDMjUv{m%{dm^dU>34Ko;_&&1jJ@~0_Y+Nr&N zt@>gu+KZZAD);3;_~JM4Sc=aDCIfeJ@0_DX?PaWbd`Gv)3qzHX>$hW=dg4zmX5Ufn znrWh<3vAk-epRB6E!Wzz5occVsa;As-*_YuR<9wvJZb4Xk+q(-@CvWY*-Eug^CgRR zt+F0py=Q2RL*pT{SHs~*S>{iY1C$}hqfthGE&S#x*NiUjr9_uI;cJnTJQZR0*N+VReP$qqnkH$#U5hd$1GYDwt#=fGw|><8OqQ(|L$38c)}%!Ju$JdJXbRh! zJD*@#G_G4osc6vncfm`m!Pcsf%5Td2j7;6c5*8gJTXYh5HI)wj@k&|8Aqpms9DGAG zu-2qu$KO6@?l`NPYs~%VdFD+i&Pj4q(3$6wxxH20SQ^^*IwWZze^>-6QvHEultDE@ zVO8urv`A;(;hJf=j0{gujh1OA@A*&pkj#+Q6}#xU zLzl~iXJR9i?t4&2^HR=0;ycO>KQ`Z?7M(DPRrJ~(>lZOx$)Ns65n_I7;Ur};AnCD! z%g?E%FJ|d787kE@bHYjtniFzt5<2xMCw0u@#S(po0Wz~YtJESvwOqEa0}9RL+cnt$ zoMSY>WKs&#M5#;uHvZ#x)OkScfD(o(-z8QyAhsc=m^d-%kadi`ar5k zBsFihGUGF)3jkv&o;4n`0o6PSEj?7S(7ozMkkCZ6k`culpQ}O1>&zlgxKgV2Uck{B zKW}SP1fi~3&A_ybTbZ&CTtGzDQWfKtB1Vuf97pKVk7MZM@%8{UX=uB`VHJZ>`Ka(W zP3@<8A(rEjqGb%@w&kw!)}M4^V5UYn))rMFCbc$!&wmLJ$U+!ohITnAHmybDCV$e( z42|qCC5aZU_dE=3quAbErP_TzmcIpYYZI3r&a8OJTQX*NS?BaqRPAiQNpivIuqbKx zVj}w|iD2XDO;?)NP)#`eO)42A`c?E|&l~*Y*cn!SI!LGa(j#zWcz6$|mZ2drJL-OD zD%bB-woJS%*X5ga~oVOc-XPfp1m~O zzAqKJoz>)ksKGzuQS~fe<7VO$^^0aUz%I1qJG*xsEG9%G%7GPM#idO=j6_uZ z8VEiPS0s&~skzH@IHyfItrY6exARWlhAvSuE}k%F%jx~d#KjMmYY!}7mHNb40hPi% zLyvwMpO-7a7)Qq*!e1D}1?qBdTA*Lh@c!cKVS@Xad%_VHFXOl} z{Ws#sNy(;xLweW53xzM0D-Mz#zRIlkmp6g(e8QqBmq9q$i~R$gIPpviBX6v?hTLi4uv{ z8hfbLFG~|eli}F!332JHzM79#I#)W^t{j)KjIfNbZ~g5vIWkK#?}lsadaG?-#k!QR z6| zL#Zpm;f~d$D~+{>;ca`-nN+WBdMX~Qz$)CBKL)wN$rV$2i=Y?Iyije3dZBwbUn<> zPVwXD+*N`)H%hZ42gdvly-VGlu>LZAas$+`jVn2jt>ai5Ti9Rt9M?POW|86nmhAD zGwdFiE%0c#8N`sx_scnY^E4&uNy|@Z?C?rDdqUx%Mo#L3*F#DH_Gdy5}MU z1qF6<$GkBJGovz{J(;V1_g4Xsp?mCJn$+`(2u~at6fvFpF<1p2e zs3GaWYKf?kOrqno{Lc9{#rA716_xt=U;Kln;WYK%o}(}5aa^?EeG83v@UBT#jec0_ z$=4JM6KAzbr^3WxEHW0>>SF3%c;(LXNK-a$(ZIP{U4h~-7p{C-ANVZ`Mc#_qV5&}2 zc^2LA>8369YBB}Q5{2%how=h?;+n-QknP^Xg3vZv-gKz$XrjmYVZF128!nzhEIILp z6&&&_SkGY!;F~q_6ljv@AmdM`G8nwH%5m3kdBspW!OS%{L9k*Z&~HYk_u2Zh*VLlr zS?`Z>=`4lSAPj>-Nu|VZf;RY`sg zm|5R%^cw>s!nE9h<NHjxpSIOx1bZ&x?J|WRr*<2&t4!@TXv7zkXo1aClXn%(0rXxoHK9TdnTP7(YZeJD z1Khf>*`8$zAzCl*D82mmC2>+VHaD{5CA_{C=IQRDV@dvEC?ov$McBQ)1Ttr1SYl|J zRyImCs1@eE6PhHuU0XT6gtDkLlwuiit02BI&)+KvOQ+gdK4s*$@m16UY}#Wn;<=bU zpGN%({965DAIB=+eX(OpXZ!(8O5gr?ZhCtms?g9M5i{I-=i~9PomPzzEPQ?$za*hdwx_sYh};fwQnbGZh#)|?bqW%O^<`~%Conj z<9j`)cVj=j3#;evzgAb2D9@Me)e+o6phG7HY1)FHR0ZFN#Y`xfN*Q?5?b%6X4LuhDURi@A@L zP46=PBDMBlHgma){r%}cY4Jp;3pC{-Vpg8}2tqwxsR82ozyKGvY{}3tr)O0+Erw8W zCUCtZyRKUuWUhlnHS;?v@^uSnd?u1i zzidM!{zF|QbBs>uhDR))_D7~Z9p9^jAiPUj!pxd7^+T2uHoSOy+S03d>61H#j5+<2 zimeebMW?km>CY(rk)U5Sw*62oA_a+PI^G_$GY!x2h?UM6t!XV=?m3&LIfweOB@7{{ zMOYt<1ty}%&p2O|4l|r?r@M|>CW>yzCW=-eM(P*1Kv(TeD~?HmU|#`%;I|_(|TJ!|wje z2!2gFPTTo1``0M1Q!jVe(LFxv)=yXT4B(wamRG-bKD=r?JPZVZ0v5P|%tKM~g0^h~ zWVx$w=$cRtg~U%rvyyxWA}jJ}1Lzo9 z&uT{WSLjH2`q)CrTMS%yTMQgEU;uXKkD{z?+&gi;vi1Fz5DQGP zz@-wNRd4*hDb)P1EBx<2y4Pw6r!1{bl@x(W6UQwJJu#>GS32rRH>c+zkMb12>8zua zrjFA~F!HLqHIIH@*h}e`eNXyLsuX7|lV@4)c59sxqAP>O=*SRaIwIc+L6P#w9qZdEfJN`cqg_3Uy#}J9Ct|Me_vu52;%| z5Xqxzwh#bKldcl>t4^!WUC^|r>}cvE@jF;(rTT{go;if!Cr|_ND{(6Es_|WnYq8WH z(%7czr!96n5mV4q3+<`nNJ(R}U>AhKLU%){29tVOSI3>soFe+;`p2oxs3Mpq^mNv> zWs2;-d*-EZ-D@v|Zu0W$3Apy}j78%0%0@n^rZLEv%z3%I;AW`P>_64J7{Ha&{GhFS zLXK$YfwTQ?+tu|>oA>ekT~sgQ?fpgnJw*GeYyW{hi?YI;=dpkn^^wJFmnU~hcuhPw4IQ6Svy!#S8IWlu)n{_`LKC9Pb{I&4oVJ2SI!TISq^o>)S z*Sw6FUR`r3IfZPCmz!QKChIWT>x8hwtJh4`MUDh}zg!GnnTot7!$(x`NwZZe znUMIvVU?yX{SSmktmGZgqqI6NY{TkeQi)qxp7B1UrW4HC zw9N|hH+~__R zvPc$QxEvk1X;!a14p%9+$Rw{Aho%$pO;n zyq0^}cAA}wVyuSfpau5LLNE3M2XrqrAE(m`n1I*IgYCTw6*|Nlc#~(k4M1q4x({j2 zvj20}yU?eno&sJ`AJedJq!(*BZ?Z9j3R~pRymmUh`+h{?EiRyYNz4g-@iiNqElf@E zHQVbPp@HURqk9qf?_+z)E$X4)i7w`1@w>ec6JR`m;xr`(bfHu0EGkA`9qh^%5W7Mb zwNMtGx~eaxp;HrG1hn{~;A772wd7s%kFGQQ?A^s@I z&i2iv(u+O93wQKAl8dAkCZA%g+1SY9N&EE(sFRuC-sGOD%c~`4?j~tyvv%YRTGK1L z{1#T5Sr)qyvHChjT<+<^4$p$`Y_Y@_A6sw-wHW7rAFFELYx~s+(xhpvE2o9FILUgB zhYezCYZ)j_U=@@Y@ZvHRw{Yd}ZY4o#rX%Dgmh)mUMpaPMipX+{_&+d9#S+WW<}r&c zg?u0Nxw<+1jb zr_ZrAkD7jN3z3gc7X5mkLfTUvGrWO;t|jYY%`ZW6m|tiQ>|YO5Ea8AZ{Hp-FTH5bUfh^-*PtEcFs2jF{=6U@GZJLEM>28ReN(qZ#AsX$WD=+$0^N z0&IjLhN#r(n<#9z1&U3F8AdwU>to+;_J!j1l1wX-qy4S4pxDeWaiWvQVR>EM(qUi4 z{8|n?ab8OLKgP)vPAA+T-XJ7<@k@qk7DcB$pZQ6OATVv?9`!8t zlktCpLJ02WKj;@Eu>&=6G;*-8Lr}ec5ENy-X4 z8X>S8056D#4Fm!~AXo^sKSit{Fc%vSn3o61t-?)UssK*JHR2M?gMe}j>?BMq%*^2c zFc%LSQVF3YiQsN5jD&5>tWA(WE^;Mr|Dc3eIe;J_8yAq9hXcUM2>~I@03l!i2RAR6 zjgyNT!QX&EY@8qt9v%cfgdBz-aZEsfKTsVchV&O9#PJVQ_)kO#sr%=MzgskO zR7wj11hN5nxgkiD3J3smaI^7na{zgDke(t5DqbKP2N=SQ@Eiir0z-g*hW~Fx02mBm zF2wCb=zuxcc)?&UUc~%=twaZa@K%cph%^l0_?NlA2XS%o zvhe^pAxKIK!oh`b29aNgqyn)4k@DV+@3YgN=s+!il85fB;U!6$coENJB0}Lh|xL5V~Mq#9YX{)b1Z~D zB+!a7JtB8l+_!QDM1`Q4cY?2v>fG#E;9#utHu#owMh=Az`LnuYg;#8FSj95NH_Oo) zz+GO|4%I}`;0RDrYopF_SQ+ztBo!|sv3;azi|u5mWK|jBQ2HHhJM9|Naq%>d{2E3ib~yy z;r*WPz0RQ>uX+19U@Tq5LwC^xj721-h_d?TwU|L40~UGDgN=5EkDw|00opp6q8{o> zD)n_?YU`;TkFXoo?w8#H5)5r<=#mmIMpu1jef)$w0dfb=EBb~WTH+0rK{uZd2Lus` zZpaq>SknuGI@Cw__K3QvgMq;jE7%{O>v^_>$vgQG(*FQ4^_e#1x@GKHeYNSF#9gdh z&QD`+9D*4g`((M@dpdWQww_ij4)5(?{_6hc-$U~Dc?1pt?#ouiGR z_1{X|e=CWJ+$sI3DlY~AVROmL{_(1LCs&XMaAR|+i2#s}&WQin7wrGZ7vv9LsMr71 z7w`Xvum4+Ie1H3rw6I2^R-a4K8nw>i2xB`F)Li5dwq{6k0GI~^5)=eDAyJ>34Yph6 zuFiMcIUaoPDb3AVKeG7tCA4SQ(~_ARmFO4uEfU@pKIXpmeQSo)b<`Y{tgj?B->K5j zk)_Ipi{Zi<*yM_Ctzd##y*{e15!RPmwdVzK8Iv7vzruDn6%Bmte6Dk^DNiw#91O1Q zgJnM?4Gq!GE-i1Ttj}XuHeY@3!`7*Ze5fkOOZ%&~5bLR$^~;L>vlF1S6$>IX#M?Tn zOGt56ULgm&rsorxoBm^7^VT}=Z#{6!TT35p;?Dlw?`-ehIlTG#7Q!ztG1W&8shWml zB01~0W3^QkBN{j@TC3@!WCkfmi=!H|VJ74h*4kpplQMAZ!HL-9;hy*t<_Ua~lG3hb zrDBldcI(z?5=E|nrGoD(c z>r$3TAI;60x~CT|;6GN$`>fsH_~Tn*L58hOFxRtS17F0b> zpuQwOQc03p!h&+&6h~Q`@8iyVf83+4qSHekoWm*7JT-|=BQHyTgS*6J+64tyPs(Ff zW_9tlZPEi~xktXR>|l;oKMS2Gb0kyr`MQSDHsgVTvTip;RC4#qkfJ~wqNKhnq5$6V7V#~o4PKsk;rQt1g zPgA2jT=wVeahv-G4+xDtfYBw!Y^A6rPc+=7-uJh8;neI$?mBk~R&n+lB_=sAqs*xI zfKGP>+oKhN^(u6tpu}EF+^X`AVlP-t+auo`7LQHpVko>M?gKD?5q?7^`hDl8TEY*Z z@t#N2c|%b&v0j#rUeI;1DvaAV6F2#T03E^O)^gA`aXYjIDgoP@kGn}zE`0Gs#htAbk zRs+7^&d}DS(Gj{AbqISc{;cEaH+x=IE56zDZ0SUO>I$h4THKPYP_NoN z8vr^6tcdGL?b??mE6IHkTAP;I6IT-N68NP5JJQ7jV~7RZ*Rv zOVZ93d1oQX1K{~nb|+Opm{=H!+PMLAK`0>%0t12}04VR>1vQiy$_8PJbOPKpQEw;)99#2UC;i zfOunx- zd;uSsARMw-xb;}{98-`owAv%&MJ)VaEpacRd?6b@f2jR^yeiG@Ruv+sQ0x z_0TEOXqJwE<6&ntmW_3Zo287QgAvWMhHZ80GHXpG0z!kRx7B2*E`aWASUem}a7y-D&B^EHXo)_!KyrK&~ClZq%0=g3hoQ>vKRA+LV(vW(hV zNT5xz3@7i?y*_@9ulqX>MekJ+iI(F`S(vPI{)}A|(Fuvpk$OHIQ$tVl4&jIQi|%-L zF?UwU97k$r~SNGET5(12MRwQj4`A08Aml8kC>{` zjnqKC?=c(nH2Ymg_(}&W=V4A)ZughmvLX?7bnOOS zX7#zkSuXO?3vx@RC1uFo>ypFyj4oumSFn;FmIFF9>(L_jL$iq#5%*Gkp`*d@a~ve08SMk>-;bIh#kfmQ z!Zdz}PH$9vU?r$!x%V6HRWOum@Eh(?Fcc@?ZFwyC1tt4%+S4Uy_tQJORnYnLcO0kP zmUpag-*=Ckjj|yJ>XN#GUDu1Rh#QAUdHfZe2TJ%#I6gVS(56dv=;Up05LTbT%ZB^@sL%h4nx>Aemn|C^?=oPJ_qF6W#35p`*!)rfKi`4cG0R^58vQIp-=) z)!IAcNySL&xVS@gcc=z~&i(;Q{7|N}zs!A*bfiq4!p)76q|fd1ybd`MHsIbn-Es2Y zj<~s;q`Fts9he7Q*8axjlE?h`3ZFBMeGJYo1)RyNN$?$8;{7^<@`;j(Ib1mO%U*M^ zh-lFa=d-WV=jAka7>fun@3UA>ZIlTk}fJR zHXBFJ^Fe7sjMHGpugAJNR~O@0wchtGpS1Xh#Tkuok+P<}`7}s!tpmJ0-Cpp%Jf%&S zwCuKMSfKap)~I`IbzaAu&78DzPg`-_uutGOHzy*i%!ag9WYBPk(2?RqItZ7!Xj-GxaUtk_FN`X?#4vJCkYTj|JTWWu_%Sw58ou0k-iV{*e|IXpMg<6XvZ zM%ZuqG_mNGsaR}hRiPePV4L=|Sm`pGXpCY4L{$Pij)XKz=8YB|WjN=4j~SS9I^a-1 zVQ|#uHtwk9y||cV}btLvvVZfA+S^wET9Wm8-B5B#VVB*=G4s2*9OC@i0f7nENZV1E@x0` z+;n^5iyjmMs ziV%wbGK_Z&GN_BLUnFY4TO!Tk$L%3oDY4!AF(hPlo9Q#nV~HcG(r#+K z|3k@_nWQ9n<-kr^vC4H+eV^^}V`}!Nodi#8SHJ9GVKSXJ2Tw+aynJ(Wvkhc6C#MTrcaedIP4C6~A9_dQ?&t|i z1ns!(xbJ89&_73g<2TNll%OnX%=NZA+?smeByf~h-3L*wQQ&F%P-D27j#a%N6f6BA zWFcYY$3>w

y#sHTnR+5hXjrd4p(g%BNW0q@aubQJZ&jAJA(t^_^9(&qFT5uD#mN zLssueB{Bee36i+tKEUxOkx80`lQ}nnx-u&R>DLdg61Rdcc<;noW<-a7zMN)feG*Oc!ruQwh{;D#O&>Y&SaiO#gNt!6doob> zm9|QgL&EY^{AsOA)M?!X=ZjzG5;{NpwqGuJK#z~gT!dUe9)eL4%f;2BJp;;Nvp#$j6G6R(DZ z6ZYI}k?Y^q);|u9C0s3fP-wRne}A5cL4qJ*o0z$ z%Eip`&6uItFV+r27VyY&M#;iO+vBs-w#PL^aX;$3Gk(02ga_uVnU!UB2CG?+rt9=< z96W6Z8p^fW620KoXa9QhK5TElZE`Ynxg1{b0-k;$w`NlvNns9jc6J(7=3^;sRw zkRHS!jg+6ox)cL1nodqEC4}>Mhq=C;YKBn&H%)q5w(dCBLVvbXoZV7~Ha(rbR{zaM zd>kh`*b@oxhjm;}_s$?Er5D~l{hH$wwv+q zbz`K!5MBj{kfcB>!d17HiezAWLOl3PX@wM+X-&h`1=A1tqEJ-t&NSeTacV zqxkL8C{KB!yp4uNr>Kr?H=jg9CRuB;@Fjr=%}4)Ga~Gzz1@X?1s@;@pppYS{PLQYB z=VloP?`noR z&;9B$c;WnWf`H4km-OVo%!bG3I-~g)ZNtLYDHH8%-LbN@K%xt|szL5|Z4UC4h$qTn zh~PAJbhf1ImaG$5CyU=6L+N}@l_Nxi1dINK-DP~-&&Lbd>$dbQ>WrF!K#{jY!S47k z`Ucyyw<^7KM4Ir#%dFEC-aoBjFH6$+xhHS@j=T~~xboDLB8jm3qlWE|Cc?)sTyLMv z%MI&B+~+rFN#{{=4QU1iU4;b&+XI_7b4JM~9bKAPg(gP#-6mBcl*|@6!HjU2fxVu!Ongm_kT zu~bscYJuv}w1zg+VXz0{x@*&dSLH~Gc2CNa_4-AAG)nPcC7nOE>^F>3kY z!X^=d*7ta#3&CQ(HUG8}w~RPty_<2NCv8;2uBRU#h^&{8s40b?dpImGmv>Yh+5N_x zn_n0jhOwD5?zog?^8P;5B@TlE@nl8RJ65@PL35C|@|=GDe4&=S$x4maze|$#Af0vK zB>#J1)QoyYtK_%X^E|&|I>{u8)CZERu_0v~{2_?cg5jbaR{k8$fSJ(;$E;#l`aN$3 zhRO$&>Cmd`xCm6}u#L2+n+KQOmR?S-v?mP^X}pRp8K5g`2FH>7Vk*pG8BwK(b$aNq zII|^UAdks96}dLZRH^3)8#RQK`Nc}7X}$1w3@i8&=a#8Tyk{m$6v7utUw4k_>i03t ztA!-$xw4e{HqHEf2NhR#bK-g7%f{brkGX#Fr+;<0zKELZ$g_&-jOcYeq^!wkHe$&T zV%Kgoh4*cEn+|5bEZaWY&KJ;I7#nK5C7q+q(=0t1`#!V5ye649Zu{CLs+%sEco{6K z_yQ_iZ^48cbt$aqrstFSFmn%i4CBIC}?9_m$Wl;)o&oE@29P9 zVrl}YwAK&7t(ilJ>%N%1Zri3gU{TBQ7>_{FkqsBS!Oq;BYLz4h2P zkb&7V&VuroMDyS&fF z_5<9Bw-5{jy2C@$@ksNEbg;e}IhkLBDJa+GondeKa@>Wv^j8UK74y$!%5l7puC3qI z8B$z1EDHO-Btwv32696N2J|fbCZns=8Z89|J~^w5Ra#gRu&a|=c3KzJsq1z1&X4+|mUDT2EZXGR-GGL^$t&@=nD$7<9>B~o$7r45Q zSiDl_GBAg1;jA250rP%a#4rU(iO| zy~MbtTozgzAQrq%R9!e^-Id8%WC40b_9T^c0=^$iz=J9f=aNPQio$>aD%)>_wje z&TSs|E~(e(tW58yHqo10`jV>}1iWvn-|q7WF|ojImuBLh4(-)l^_ZokyS~Q_J8H#E z6o2miZR)#`sRmI*SR{xn?PGa&cNlVjn1HpG)uDNFmP~Iiwzuco*W+l|E(5okNviC- zcG2RjaePgr=Vih1vvPK_7^E+qBSqp|%+xN+USaUDK+p{(TksQVsgvC9puC_^B9O+` zc_gM(oVu(1sfnpfC8wy|!;Q?evZE-p`s}9PEH~uMJlB`YZ6PzCCzGsM8<20%uR*(9 zjuZ9sbtFSM+;9lvuN5&`-|WoaBDeS1bKD(OOzaC*JeBk;LQlpoS0jA5&YX61=Snmgp-DiOzh0K89XAj})rp+;pmY>+oEuaa5vSksm#mp*Iw2ww`1;7g7?u2QsgwEPLP z6qD3x)M@Y~y;q#zXRcn-EP`x;ID)jLfw11N!7#2c1DaQaDumk0oZ&h&jld?zjii_O z_u*<0n}?3{j`U6qa1}HHv^cbdfWqal43`bmqq9D&6Ew7fP&r%1RmR6o@w!uWnXHQpP;rSki z&V21r_SqRT-6w`;pV&HsUDoL4z3G&#s>!Va=dG+^h8dz^W9Q0c+Tb8uOwym3j%ue! zO>rNWWsk$$%&_IKUQA*B?}vnpNk6wZvnApt-JVP4wN0etc%L9t(tXE{j@zJl`D^k^ z+b^uFv`4qBrWB108IBy?sc*49*UdG|OFv=yq62J)&9&o?PLWD#3@61q2P5(|wqq>= z?TBg`UywvVu%6k+ujK})kRodc`kccbig(n>Bpk&PfG09h)g-SNqNm)FldkG|z z#P%xhP>5p3VMm;@tCzyY-nUi_QXEkzrDl-Np+kb;HrFpaq)Vri@&dXi#o7lZIY7B~ zZX#}oGmItPwzZ}_uHC+iy33Fr>Ip`%`11EW3H^D{8Tr$Gknsset8}8R9zWizW=}Qe zb@igcEx+@frLBF1%-^jmSIoXK%-s6#ET4R@b(AYfilTMhX$0z@xNb_5N+lBeO_FkwZ{$8igedolMUXI_`5h17`;kBJXM!{74e z&3-g?2;0{GF<#%aP((TS^tZ>!wi|Az*LCbr)>0|*v8KOxh}sKMVF|^jvi&|Ev$-Rg ze+f-$Xzu%}IoJ%Q@)s4eV%=!*Ty4I}dpxGbs#Ngl@z4A?za%y$4XG&igb=zI9MWU~ zVb?EpIwvGu=%GX}ru?aDvX46WbS4NzKKgjzBpzClaI*c-)Xlj0)=;BZ_Hn&yx_b9} z^h;REv(j~&grg=>l3yg)2)a`Cg#@OH;$HBUvuc-#Wo-Aoz(%a0>3}}wrQu!49B_N8 zF$bvEqam6AW246MfMIQ}R9(-2NQhR~LGX#UNVr`-1Eq9kX5z~9lCJ8EW zMR{a}{y3m2X7!8OCfD{P9$$|6Bmp^k`R~Vb?g1U#Vt@!UEXQ|r5o=#qL*Ul_4T(v; z&0y=-PY;>f<@&?Z>e}Q}`)WeniW)Nu89xdhsds}@+8m42Uwuj}(tVv!hw&;IuW0`x zZBfl4`dqxNbneWTu-7pkD30yD^O8Hgzc=K(@OgjUsM9&Y9ren#X{I5jliN4s>V~6v zv)zPT-tHLI$>mzai5aL5BSy<6*pKG`Qymv5L?ympBTz|)e6_7gThtW!}1 zE&VWkCftnHwE5{^K*O>liNYU9H_6cSOCV8JAZ5r|N3E4*wkl*Qay?-J+-u%|7^9J#8dJjb>${7<66~j{#L@y z!7#VFB-?_fl>P91Ybxyozf4K3xAjAy3mI zI3ykYlRW^%pY6+IVo?dsp;3D0yo~x3%=zKJ*);;oC%J3Ql_6>x>hUNp`48BNJL^ zpIGjJ`6hGs<}gNGz-8LLs?+B-Ffu+e*EcP?rMw zo-4hscVl+z_s@A@PF2|$H@)sM&3!-6^21I`c!}vLi5avWpnk-kCp4D%f-_1p8KV1* zyvt&&icqc`5!hKoz}Uu^p`ek#8CI93U(qL$-nR+~)e*D##Yj@s!S25H=($v3nx)(babGFAR9nGlQq&uf`cBz=V^(l)&&#zfN}6 z=Su($*><=Ia|b5nO((zes*g8m1ziGTd{IYnGwmFQk1Rv2HejLicI+iY@d_daS!QNV zX!Vho0cZiSo5GV61`*Pf(g%khRF7_RPdI+JgC5zQe;qzjj6q`V_=SZHeAz;mN>+Sw?Y8_XPZKnM2eOZQ6`}P~gd>yTg^d-V06N z4_mhcT}pj9$3N6=`U*mxUh3F7nIl_;Ru&70zrMULq_c#9%L~6^z`d~zZhqMk#dqd2 z@$m4Js#LSZ_37|1<`14WUaF=&EQ9=Z7_PyGmI?OvtDm0QqY1nsM@!*i>PewoQYG|i zU2?)DRa^WFJS%=6xONaubW=fw`t!B#`T>E5%U5S;0YIp|HsoU?LZNOl$1 zjzM+PvUEx{sL_%(MsP@uTfnfWj-9z`Z&WKLxa9BpFgLqhfNEj=fFyK<%BO3IER+{M z?!ec(6!y?kv!kbq$`Y40$%>CkFp-m15IZy?U#vMQ0S|Ghvly#%VM9f=dLW5LwRpfE zYKi;VVLAunvyS191wMBJnw|NT#M5uBG%O7P;?1L&_3(y%L(ggTL#hUQX*EGE!Vq2pEb z1wMSO{8fU+B-Ee8Ev(%Sd(+_lHQ)1Y{vJFY(F+x~*O+H~zt@I0dEhcu;hu+Bw6cZw zZCf-JTgnFc?^ius61Fm5IIQCS<=Y;5r9^ZdVHF|KBJKiY)mLzT=Kb5l1)~ zJ6hPInAtxW6-7fE6eS~$ur$Z6J;0|M~!qDBS7VRx$syTg!Bw_uc%8wdwMpm%^1 z1dh7DTYl6%N(aV^LY4U7U;rQLqvC}_;CH|iFCR(@fd)L3^JtdGifRH$$;YIZ!Rq(fz$xaJ=p)IT!qUuf?CjeCN^p#O?J>8tkH27>S# zj-CouhlZulg$KnFj!IKqC|d~mEiy^4eS@sVHh-R>3s+|phGuKWxbBj!<&MuYUf~IF zKUH|QTUo)4OZq*QZ=`nY6&cn9Y%JjH`|qk>US_4GE8^Zo-&^}2bXQ6>{E8=R*)EoR zBVRU}btS6D%zpjWSI5;PHTEfDc@f^y=agIMob<}-NaK{ztGYyXZL)r=&M`Z5dD~K2 zJW?#r0$t*L5oJY{U_uJoUXO$eQfV(v<91T*tD?=3nyyBdBK0Gc*r8`S(0Ibad$W)? zYLYVj(vrebl30n`ocp!vuKKz>o+jVF0R5iNmcenzg0Z?EN;6{RMy3c85td_k4yQ}idfYTZydHMz~5n5&b`S;YAsf#$<=3Cga zAUs6V^V4u%Qmgs0^N?SO8|NrY-~fv|W=m1OHwA?$Z0;=(ax#!aw);-R4GB zqW`%PNZ6vN^}CJx&;8CR{g3izVu&h2sOo@1>i(!Ys;CrEw|i-8aR<5sz<*GIe-|b< zM}#Rh2mpp*gZ}vi;DN!QFn}rGpE59tAiVnm*#1KX0l`tZ`tLGSrlY+7rwp|j|5FCx zL2b)_(?gX}?*I0O+GhWu2Lf@Us>i?EqAJ1NhWh^>>v2Q>Yg{mh=Re~EgCTI# zp8hv~U@-iyApJvzbTmYjdB?l|@KCexK&>ha#cpwHM4==W>OTB-~@5;;4lqsuFvCu06>7Pp#_eB z0Jo?E(g0=a0ALk0bFj5Gcd}-~;Z}68HFh#WqJ=7!<_6qoTYxn$FZzo=l+A5z#0*eK z0IL`u7zpM8LV$2EkOv5aJOct*&_8HBIa}lZt|BOigS0WeodV?VsTdgmKsekYasY05 zTL)_ctG|_a{#FtdzE%2DRaO)L#Nn2G`NzA)tz1qPz=OlBA`Cz|I3fRcU(o+2U*JD{ zq2K?jFZln5um9V;c>ne#VQz&&uRgbg6?&b;kVdw~=vZWtHl`>u00_zh78C?HqR`jP z8pkzxTYEBM5r*q^qH$XLriw^<`c207zSpLyU!JDX0;i`l)=1WlZ+vOSBRCNeLyRx+ zDr3XiLadd7vQV;M<(4v^D#~4Xr2e=LGSAD+`r2wx9NhG5l5!I}$Tl@8wbAnCJG4!& zdRNd#gk>n_B$9S=zWGZ@Z(Zb+_f=v1a+M7yWtOM8;Jnwb$LuXX3#3LC8i`XS`1#-j zTXN6veX2>V@kMDLnOc7!Xs#u8???;!wfzjAe(HMWvXY&{oCqW5GaW}lUWT(%6vg&a z4w8)*ke&=4jq=2@0oJF_KFZxs$x)h#tMslJZ3EBO(1p)ona0vuNJ08oRTL5tJu{Sp zl>}W$ik&vv^##lK<+PPJjX`|kM476DD@>ecuPv}2^(@Ae0D5#XvtsV+GOAe$`{t+> zJ(vqqSHsYv-Q<+9%nyBnQ!rv&I+6b}V@zwAol_h~*H({MT0#FC&hl%KJ!m&e2!jBP zibfCX2O7J33dah3ltRh)&SZKjQ_XaW@3O5hgynw@VhKvJcqqbr=`rZAtpuJ)3?tt} zhP5y9J#fFO*vgt1np+rNBS9)_KKLdk5NKJ$7VeF5h^V9al;om-Ur^nz|GGx-C(ky~ z(1GQ_^9aA=H*IDHycRs}k#Rc=MMW3sUe`rud-dV2Fml&WUmR|L?6LHlNcp}M@EmOQ zh0IHx1lI4b?&V9wG^|wIeCySea&u@iWtFHKA25kDvngFP{t|pVJc&Ck251tVIpF5x z1LJmirWimow$;aZcGKjKIg{Mpxy9)?lzfEi*uMa3|BS5IwF`r5?+s>|M7yXeS3}Hw zj}$EI&(kdZEZZ`z5MI%Z!}mx(kPZX07O^zQ zI=8SDV$z?+R^C~cIi7Wjgt@!$TvI0sBsK6S+F{B?V7h zN9-%5_v1-NZ5e$tsCe?gW0Shid8#3sVr_Tk5;m5aVF~pdRq$?7WKn~8G3&eSUPo~) zYyAue7m_1lpR#?WKLN7_SNa;V5{+9{Mle)UaxYo_W;G(Kx3{NJSNtpKvS$yw#9_cn z)ruzj^yK+R) zxY;x`p9I4IFJ6EhLxPM8Zl3fMiH-=3`25JZ%grkI%I1Z{R4+V75{l;v6y?MJMVu8o z5&Fn6cc^-znB|qhQ^oEgf;R^v>v(&?5@rgf-4ZkVrC%LUlZhv;HKWuj5Pbh<5rTIR zG-1&%xCq%#(~9Ibqu-yjfiM6`@u-oO;|C2XA#3sSI!2s)IUeG%48Fx3sxd;;eH7pX z-S=MZ=KGtDsj@#gyeLr;`-4lT%sn3|GfjY`HaqIYC`+QR#FK1BpPKcb`yMNEax8CMorne5OfAOjfELey z-p-Et7raxsw4n{aQaaX{){E*XT!?OXXc!)ko($0t^T*1_Zo$6H^^CmFs59^Ya4)M0 zW)-`BllraOXzDwz&x1jnzTxzY27U#0j1YWc(d2SuU`ruu5A3B9-Fm~F!tqLBv*5gs zAZp8xc%yX^m_saI4&NdY>ZklLBy||%Me4piF#p_LGgzLQ*m$?CX)gV?m;Tid{_3jW zznh7wn;jCst!QA1?jg!ZM_VTcBcvk$-TBd7-be+B0_gnF;JH@d|_4Wu3xNVHe=>E+uVQYiB zwUB@TV1LSPrE*APa|01uSAY%>Erf!hTp%z20>Ax04<(AWLE4}k0k&Q_Vlltn!jUqymjYAZBcZma5i*c(Y_SJ&rW-g;hj-@a^cttNX^>*xg#iCCR7 z5IWpkX^D>7^y$37hR&;<{PZZttdE&65**=woN?%7=jyPrDAf2Z`0+Gjed=>>i&yDW z3`+tdk*|{)7ESvPV>+XsKLqu(@Nu&y^E$bYj;mmU3{$oe6Esw%P_B<-$v1OC6nZ!l z_OGI}MS3({Qj>V-xMvSmZH3x(^cSyeV)y*cn5MA;7-2@wZ3c%wDqJx!_b5n7S}B+c zf~-AXg(0NFMj!6dCMKS!rXTu(Q=+nBl~6@#$O!ytw?Z@yvO~qL&ZJ&R2@BjDLDu3 z7!g@xIyQ#>nAMJhtkBO4NgXETLDYcuj`pS9C7pd@XRlSpVy!Se-ahXx7&EC3 zdiuIulX*}r7|9ez$w5nWFE8bB1TsN_0a7%ChyOIs#KQIYg7Dq?yT4yUi7$gs)@L3* z&A9%oHyi0{c4w51hV1)MFfH!f{b0!bQ@}#dz0=1FLHAENTbl2m0vA5RtZ2dxBFr+I z1TgHK?+}PzO5Gt46;SRq-Zfg@)huQZvY-+=Hvg)Yo;eJM>IS=_?kGrJn%(LDenw-N z)c-1gm*tHqJq_{qipP<7bK}8|_g(Q9>hE~t{I0q4>7A?R9iebup*Qac6|m>rf*;*; z6E_D!!YcK7={%jiH*>@bJ zT{JJ%LV#5&c|8Nu^%8CFbiIoHepL535_e9L(DZ>F{sQ4$0kR7dOE0CLD?-@QupSZp zig?tENr1N=I_;Ox9;txnWLH zf6WZH^478Rzf77Pn5cha9bvXM&R=|`wE2bgXJm9)M(V4%vV{o2xeB`$7a!A>x3d(# z*HRb?ZY*dC2eujf+zMd}JX>C}n++rbWJM>$+YL%MOD@^pqg?ju>MQg+qk?CA`CVQ{ z1kc?4Cf>3JfLtDh@&`}s8VB~rI@RwR$rf}^5&RtxdoVzd(Mwf8Ygq{Ar z1Ae!I zVY4l7muciOGKA<(9=yCqR;joDBCY@X3&P(n*m3EaF=Ya**zGZ)NY^wJgY|C(sfM7O zMr-k&=pdx$>xhS%iuXJ2aL_X=w1J;=FKQ~1hXmjKVcUZn28S!si0*(QVqKSH>2a=^ z>A5L*SMEzKDrTAT_B|(CW%~}wHMprQD!S{n5jHgwl#D0FMbqNUP^w3x41Q>uLN`(M z>axE*W%Ibv$BZwZfo0D%X^W9+&G|E_S)!|-YK3-rLeGz9lIst@zISS~oa}@;Q0m0R z5|^sbqaI5)7Y2BS!t7E^q8oT66gIM+JB5m684SK!H^`U&N}obMolU>~{{1u30iH1q z)9%T#!vGhh*$85S{LEEpLd2cf7nIa7JFy%~0?B?UOW;2G!!?Y2fQ~e1a3O0*>ftjJ zg2fLfODYL?pGD770J&?-?v(lbFUX@SmL5cn-6;?GB>qi4Dz$^Y!;mS@(ERhAbsvIu zzQC)|X!?f-Oa(-JF?*ECk&fX*-VEs#p6dL?(L~9JcUEc}B)ME~KXss0`E#WxDW zJ4gZs$p=f1;}D^EZX0ss&B|G-Q{jxcDE}--GrKN_j3Hi>vozoY~$ufy~_r|cxZSiW&S=teMsXT1t z23p)qUF=QlMPrNOaW5WSpO~MtWI@Xb8t*$=)-STSrB*$sn%vZy40!e9X&TEg@!L3h zPw}2znoK3r$%vyRCx^F~L+OW%2NmI;DVTrQbTWOo+%Su)*wYMe*9paoES`uiN>-QO z6mepxS`6C>6V%i{PBLonZkXq4_H4d*d-6;5h(Z8Ak9_!1+dx}xSZbnf&b{q1GaAEJ z6W*GihOJ`5^F8Ji+~V7`FD|77v~e34+8cjMA3W}6ZAQ@h0UkYh#_*v2C41Bt`Wrr? z9k?_+#36QLnF#f(6VH@#m%bVjZc3@*w>99bU-|s&3;JI1#{-@pHP$(VZXDmn1UruI z`IH;B3io8y%@)+Z7}4(GyN4f$kxw>R+XNNXV%Q9saL;PbYl5od5&J|c#Vb>7KlfO` z=nZF6HQ>r+V1#|jc5ydNju-L+CRw%3r#oYiCcH6zN}XfyeP>xOzG0$eo4B92xAOrIro2Wft3#{a^N6< z))XntIg1A@T#mN7>wTRut4kCyN|;`el5rZd=Aip9X3YqbxGYCf!E9P~+rr`bzOyxM zv9oEIh}hHxma^m@Awy;wiR!)YTq(F$#ZeDZWKwgUVT|e zTg-e_VW(7tr>$?vQ{V9l;lV~Y$I4v?lF~FS1NnLpx z_+`FC=9VC6a+`)OwK~%pZ$-aJWMg*4x63#(wMt5ZGLi2>h_bC@cdFJA zU+HgypT+8I+V9AFFDkGH-WUBIJdz2oE-9X< zyq_H-a`pByPe9=lTu7T9!4vv5Ss5kkDdJ879>lACnXzs?hku+lTfliKdVQ2|l4IN; zbhPJjG=Ex~H;=qk z`EBEWZhGo27v-to7PWXB@yEUU(EOI7HKy1VnXrxoEu$XBC;UUX z>7ZX+BS(WD1;g_@-c^?l+Urg&8cOq1N=wRCOBg8gV8JiHzD^WdFegG~Hm~{TVD*mI zl%$HMzHJ>2lQB;lh%%A9U)?^DIV3zEwvX~Y-ufK}Dla*sPqvVsY$`P0QPNG9s}VVq za$}@ejQsG!=@_hI>{`{QWvydj^2^xQt=7g;H8`nYj=4ZCq#QalIoj%+Bvkp(vWcl2 zs!NK=!SN(M2wqtfVJGNJ=eXby!yhO9xo!3Fi1M_#aV|4ud;cD78+8iLdBU3x77wxlOwl_^ahwchfAIfc;-+I~qX5Gfg`u6gG#ojneh)arY1x%ceuU;_S zG->rKCmU2a)$Nt@#Gjvoy#sIH6E-d16V(iv#CNsBp6ldCzxhG4nYm+Zyi6%k3alM2 z)+F8O2p$Q0g#V;jb}<(Z?5!|AL)okOhzu3~@ewBOhDwY_P+TpcrK_QlnW{)1X{7h| zJ==K=bLQ|To0kk2!3xY&v@~ZxlUxw^Eeuv*zH2P}!bsM`ptvKqin6XGs#&E%$Ux(G7 zJILxunEPPiaR~RRoJHLW--$D-%l#<4O4}Fl0(nfsvQNh&l{Q`U2VQd~H?+`(8(L06 zrCn*0T)_oyv>)mh8-vC`Yu!Y|ptlohiXkcKaAl__t|ayYud&p)ZPI)O)o^whsSax( zglEOV>Y!_A0Cww!8o`Q;vB4fsnayXq1 zhCh{_t9%DM7y`!0NtVkFiSdOz7dNeN1BxbQdc4$^k1tgodbA~;7b7w;72iP(pfnt( z^Zsz=`WrcNu*k$|6rcQolhdFymn|f2??GN_`+zcKwBz%#MVjBQe5{`2tKxl#cu=YA z)oTRb&{9m0WF~VdrC!-F1lR@1y!&%K- zWvGfFkA=XKo41?(hh5OS?scbnS%YuhPaO8-5FvV!Uru3mrXydN!L3`;?MGKI%>y1( zc90jP5VPrdrR1m(+{C2LQ5-U9%M_k6e(F3}T1s*>W8D_vABfua$uP2cElwnET=~G)uH(LQ zHH!ROLEcdYhkzL4`uYhG!cSd9EPLj6xmRT2VEM~Nfl$IP4TbN?C`~F2_ROrl4Nv_v zdCB`wh=E!xlps^JQZITUC7*=8-YRWSj<4$k)Xs6O2A%CO9YCUb4piYqrEV0BU5&ZI z!@o}>Dp0?U<6`C+*50Amy<)!c&RsW#^)CA?(Eg4*OZBu)9{Qz?If)c83p*bG1S;&TZON>kxPu^LYs)n{JU7&@Ly<2xwyCjga;9j%60yc>79BSxl91 zz7EuCD>Z=Jc$uymleZR8&VPOPLgqk|TC^M69=FxsD4~P)O0TJSXfq)N+`xMml84Eo z^(!iUVr=U?J|jK&nPdO3AFGR52PJaA}y4Xs~hLKCSvEeHfT3K$tRN z!%$u?in4#f>6KpnhFaam;IB?Anr9=uYBJ*@(;`kxkK*zO{md|02IZsDc3-c(ym(RV z{ocUOJJg`sn`>heCogNWDPJ6)N3910^h|qiX3Ccu_p@(zKZdwIOIUF7b5LqhjIjbF zT52dh?@B~Nuz~ZU1Qpd)y(QF>h-tv3lh-z3J>ID3%fq>=V5Wk#O-|JJn+#{QPpM0% zf8f<2+qVGP#oc`eJ`I{5o2STY(vr;kX1w8P_pA3M&zR?->*`^pPmCtF6t&aG4IZyA z6Npohb;iBSwrAL~OxcX@@9Xty zeAfBmcapX{OL929MBCBH>Er#ae(P+TT>izgWJ6LO?`|Sb!Ga=8t61Q>#@IpWm`0}mm&1jZr&^g@;Tdt+LVeY zhplS(s+G_A5B<~C%dYpdFW*s_);s5U>irHRFzbknyF?)ghVn`;BV3SXM)&Q1Ed4w= zIn_+5c=5&X%rcrGhvyy&(d5rR5`854ups?AM=ZDHP-ai^JoA#Kag=sDvNNnFtn1L& z9g+z#0u$p9lS#%&e(>mOSRQz1q|U6$qAL?@u{$x7-ymwETFf$z3XGewA zv?VyEWCrh8!!;?Cp3)_cb85U9c5*SVwVa&6EXJKoI9n+*vNf@xhM{!iA5AEm7KDv) zWbewq{OYedaWV;YN$)3aoXR_r=L6oKQw#M2 zrljLPE5K07xzXk*%A}PTj5A)MZw8zCSq}ioU-ZLLWZdh6z*JtzU_ayUt%Ro>F7Cdpb zBOeUZxx=QPS@>)t+xJZ%`!bnFig{6}`2z}OjuUUr_vRMkl2*N2_+j`}wOpJfVO3x9 znf!RHgJ?LGM|+brYU{oUF7|5K(i-XL&=@7Xnn1Z)%G54cjq}jmU>OkFW-6{M)GvIr zjG4`#j++4lCCDBT)#}???hGZc*I1DW51H&yf$?hJiuiwC7AsqrZ<%yDjdrkAf7WL! z^(GRJ_fzOMRweGs^1hjs5BEJj;x_c$!H=%O6wist$aQyUEaNo)^(p1hyndMGAZzlN zCC08FX6*x3H!KiLU@8?uNT>GVjEQ*>CNXdu%Pg-R7HWN{S8ohN*uk@a3_J0BFZ_mu z<&|Sl-b0KXP|m>CL1ni<<#Zh^ODFz$Qn%C{y=j)ORCahaQlnXW$?IaJEK?OyA^5|P zSr<-^vBgpCnL>@^-q`ilxJ}MFEvxR;j$Q8kcjF2p;HKW9+!F5!&ZxI!U8Ba?a%QZ+ z*0YkfH=j|_X8IuGN}*TwPeh8uLWXN)m!n_hz2hY@86vDxE71UNyIbb)lRQ=V9M{cb z1j~Fbv^BIk=)~zp5;{llGNe1~S(pxmMtD2zVqbez8-*f-N6&7$n6{BMv`|io=z>=3 z^nCuDqJq78v_GN3(8J5CF|k%**Dw3P$U&PLW_v?q`(kIvc^)HKM2;Tov^y zO-_ote$}~@e3N*3xl!e_N1OMwPaolZ*)_V`c+!h`Eoi$mn@P11GSepQQ7MgyNf+oG zv*5xmp)1YsUS|V02vv~5a(?l2;diKs&Kh@rG6}weEpv{T2(vZKCAn|FcR>Gld8$|W zCA&_q?G?%4TTWvN)HeCz_9S8P$Yg8Ew#XB^Y77Uas1SSt#*AhkX)#bS$A@HOadtX= z@#%(lrx}8gwh0I1!^hUfrS~9lwXoOs zAe!HCVA%e4!FRrpm`h2?Z^iS%${5Rd?2(2}3so(OvY&Ep_?FcSeUkQ_MaP@U4frLv z_4sV$8sA#Ouldf`h#$1?lX0b%b~kPYa$l>KYHWPT6%G2#ar50wrkyEbk^tNbjiD1QKJ*qNbCeCoWAMl0$zSMoME$E}aEv#!X-@gw%AMmH38YE; zD@)kKMxJ2;u?p!-k`N=wHZ*yHdH9e>SeSZl-tvm_fklNVlT?5bjDl0b659!sWE?B1 znmb^Q^CdusSc=*rL}R}zq(s!5{(7i2(Cils34@9LD&NQ{v*T`l9*} zS2ves_*MV$!Lj-UhN|GW$mDgvnq(FAry`nalbH>cx5nAx2Q!lEPxw~WvQAQ8!P7Wo zC`alsKmDA649G1<2WXy#D0-Fi&~UgHC$2FN$r=- zntmp8k)X?>?vB?iD7E??6Nw~_!{OjB}lvgfJ5n`w^?D6UU=vtOjrNpmK*E)9cMm4QLR4hvZ zoZ^+$a3Ergh4}6sI`(c9{>5PWp~DN^c&^yvlhmL0jh=_d`fD0AHzuw=uGP^Ar0$@X zHYNg@_rKOBDM3nek%gK5ws{*7MrL~^g{j*@0%m=~_K;cczUHOnEZdv;>dirGP3H6# zitnMW2;V75<|sDCNaI*7W8P1xV)-VERTQpdyFCKZ^^6}-bmmfSm?OE-?YnD>4Zk*D z)oVzt81{D>)9-^+Jo-%pq=zM>ni%i~c&+GWJ|>2pyesYbUbf$%nl&YZxxl+<&&6FE zB;XqqFW_nUnZ5{ix8JXN{4^<&^Vf~PR^4_dcLV6jTXBr*DEURFRzN=2p+_| zzThc>)JC;Qf$TK8*$Mw<+uuifj#kaC7fVRMBl7ZoP@&qM7by>{$wh9DGsxDxX_Ue) zuvsJD?rhNR%z;$*$J_X~&8?3*_gk53qHy&cPW_tCR8Q-O1xx%KsRbRs&#pA*V$GLO z3pTB!_5@X!(nR(51wjbDuSYU04N(h5you!X?3nMTzHXUUB~2C}WJ+DKqsI}H3S6X) z;H>U$pW3ql^4Rfq%|FGrb>#gqA4!ex==!di4j&6aT`KDJQK5KM@ykt`Zo9$FH)^*V z;W2&o?F)Z}nfOK9Kriog0>QEF`Cj(Co+ScGgM0dbk~cY}LDp7@K1u*Im+ zM-EA^!yY>D3UnFp1Sv77xv3I|sm@2w0negUJ63@AOlhL;YH>Z0x8C1VbRBz0fQJ)9 zyAWj_fQ7)NvWN|`e`4WJM~%6d(nO7kSJ~Y&duHQmlWyZuJ6q1S=dr;yY=DV;p%6SX_arR#ZOng={- zYWm^yV7LREDvK)Jk|gUR-4R!2a@RZ;Llz^|G6{r{DqY6Zf2tKT1@9*tX$;@_QkLgh z!devnIbh)KQzB1?AP+zj)^EW~YTE~?gbTba4#8z2Jo^;ecWeb+69G6{!CgU8kQyaF z8+<~!$Di&RXg*wgoJc^&n*SKT3H{ewTwUs9YCm4yQeS`nr*2iIZ>$A151M{7S>eR> zQp=7_kl;$-7vSMiACAfP3$J1@(K6PvrDN9IDY=LB)@g(y4-XqlTk?RsBu)B8$g|_d z^4|3}%f8Q@nBiH9|4A;PL7@M@ac&VJF{GoBgSj0VRQ?kwk~gqMLrr2x3j=j06$2YI z<%4ErO&xFHUtvchG$#Z=fO)yVU@#1ZgI4=f#0iE#xp*N6-dhwGg|t=&@SxAprx0E= zC1hYHg)}!cLjfRAUanguw3aj)1Tr@gwlTFr-ZI9wGZFa%TjB%(!9Xr35Y7t%aPq*w zXg5F@1OS2~AY439H~<8OfVp_UAYNWH&va{sMuU)Gz#r_;Ef@6{vIP1U`uR_0=~nko zi@!rgd%IIXGDQ8sc!^4j-F|!P2n{2l&s1$CrN!h7?9dpOF?vnR zQEq>TRoooW(M#Ky*xr&^%1BdlG(6@8U=>CK*+?|Kt>9pcbTGFu1+f0Z3@ub~va_>7 zTHh`$@D}0HxMjC=U_c-j5CMnXvRyy`1O(^eg@b?yz1v7{kuC&~3j~3|(UHRdIuID} z&*lGH5deX}xDX&7APjAS0DyS`Fth*+0rJ2B5VQ%5mxl|;3kE^}FkToJ5CTQ}0RrG~ z^r#>N^mg^2x6~N=5QLWUa3O$T$SscsMxc*xmmhtM)`7y&WEn341mHzqDmVg+xaHH} zyl5#90YQ%mgm3}D@INep=o#>E!C_GJ2DuIIHV_1QIw0u3 zN)hOgKw$JF|HTFd0&($zU_7@N8W6yPJ_A9(=rn|)6B2=dp>-h$^jNoft%u$P=&2$= z=$K*XR7B^Zn8qKM?;rVhyH_AJ-p{3RVXN$J2!bL=g>2 zQJ*WC3%yBT5@&A%FGV$$jMIgv%DnD%b#|$@Y-A}UOq7>A^^EHC_DBA{$yE|Y{XnLJ@ywG(5+8pxf`OP%UnBR*`VOD(E z&Iz;-odT`xe6SH(4CX+5*?DWKn=u-txi8l_j85VWvqAte?jTB9T?nwd{JuASQ1 zeea7y^wa6C=YzeC2P8_l>Q}>Yzsgjwgh`elp(9~g80>GV!xr8v5kX=Ie?}|aTXye; z#%~o{%9I6tdA@nCBNGoR=x(MR9YG$aFOep;u#ND}iyS~?n4xj>gPtF+!X~9_!r*{t zCTTlDHyM~M8%}5M_KGZ5*HzKISRl846z?0(Enu!mje{-3rW5YKIq_%~Y+2nPR8TXgxq zE%pDX0ehllbLzvop0Wmzr6unEfn*yL>;tPQOG zQsVeaNkr&D=}%Qz5daW{O;-AkXN?EBoGgF?g-t~W0C#YL{m;HQ|DSw;|L}!){$G7@ z{eSrSzs1Gx$iY~ogkJd47NY>g3nk%ifq!p#664iJc+AK(Z_+&60!*VH}j z1)FsUn%9NKW&Qi=82TL~yl2VpDn}Nc|3tQG)WMVcU~^CL^9!Gm4DMWPQa;h=6j?kE zt580^Z2JC>6`zhr@{f{KkK&M+jCvFlI==fYR?$B1$}+IEzr0>J9B^5CTPNZA(edI8 zEp3oKBZEKeq;H0;qY;zC`-*M=MLRO=IYUNJ=Bv{6_lgON=GKG0wUwr0QZe*hW)d5{+{T0Xdc&C` ztS0o#ip&NU0I}Zh&!dWh`02LPnT)DZt%*}O8==h~EvQ~UPr@^8$wHHwa#9_xH2sh1>= zkOkh;7QGlZB}9!ODdI!78K8TEVh#E>{(^uFVG#l}y+DO#c8y z&HozK_}CEUWeA>p3dfi<5Ak9tQvGr)J}21cKIR*yl{x2c$Uzs0>uOlleOovGFR z88S_~nKCWg$Qu5#_B3j(vugQrU3KZ#Gif?oXr6G%R&DCW@`2yi={L2`>eV(4)s0`B zG)mj>74vUW<6NH4Kr`Y(>lPXYFO4UqSn5w`hacg`M{K0j;l9iVIez$o;k4#l?)1y7 zTB$Vr`-D({q$>ZX{c=pRd^#x$nKv`B^~QrvThW;^@wGyyj{0V}2Ssy)ydXuD?`ql| z^2sMWy))4;9Pa5}j9s)XYRFb*as+j+J!=h?XmVPlWgb~BtLB=1KVHAvl-nXCvEO(x z%V6vW`LKHG2dT|%oRsckTvV12jQ5N!#b)$6;pS^mOn5n1A3Qo~WI)tJSeYg)1~9c3 z-C0=V=oMkQoaVRw%gfZKu>)3#V@l~x^X|Lv3O=q9s}>VTqCc8n{WYPu{PqUVSA9El z9KSE`OK0sn)=nhM-JDoR;A<&Jn_dUoS}CG$3oVphN9+kt7lS+%MDX_ z6*(2*W#&VH+j8misW$bWx69%!O-t`v%4w>y%cDLW-0ZK@m|OX@2;`RIEIcc?WhrQ; zsjkgFN2lYIkUG;x%8;^fG1D9`^OiC!Jk(PhYNe^E?L3d4ZQ1CI&vf4#*k;lfSsal6 zQIYR`1lh`wvDlnxwQuMf2>O`u+iMs?H*;4zTTNa6ks4R43kxTlHKyV!V*?}l5l`Zl zc|-@_P+utT7e=3i?GXxy;0Cc{9XaNf_ujz8iQ{$2JbhQb60?rBL6M8}R-=?w#~AB{ zXy&ia{TLkIOXp9$pht{)_ld?YT&WvP?lxN&6rTMI7Y$A_t8PD>DxD94u6UrRcm0f! zV6@Y>Crhk2lI`qM`;gT9Xj;=ba%&0~dotRY$$pO0CRcxP)lkT-SpZ$a(OZhI<{}TX zqitr;oAmA(h8uJL!yx-dH~z;+1OL^@Ro(1h05(MfQ$zz-hB?|gIT*nl0f@1S7_mkw zFgQTxkLk*$3Uh@6*rcoxio*YR75T@jlpYG3m@8aD1^zH}5vCICfQO-}jKU_t0eF~< z4_BOkhq?A}#RYhnO3H}g$tG@V1Anj(hX5dd${wV0Fk^EAVOv*#4iF*a1aq>2zyNlx zhZn?BA_yCp4crm%Fpm)aR1lNY2(D=0@P`mFZvVUlK>xAGKlc3a_8;FU{@SzSgF7cg z42a1rV{YsS(0NFWvff{V9rO^wzuAcxzzwWyO&``VMWpIKmI3|ko6DaA5d;8%*&*DB z&HgV#lbeGb`uCwZRacZ`z{8RLA!uBDeLpPX3Pd;B6EmiLo;L>FKJ??0t@5&h+ADEWa#wf_nDX1 z!OG&6*ZIj+>WDKr>lc44CT}T!G}1(V&xwel9DhZs>4rdoDE^;0+2k^1q%y&|2OU{B zG3l4v)f@h1c?LI$ee9JEFpqDsn*0%781m@?Gjh2>=hUJCgadqZE<1yBdRrra&iAki z7YlWL)-gj$ajy7ql?>faM%=9ozF4^Netvm!ef=2sCo_cQ+axtEDS`O8d-D_iou_RM zr&URgge_{sK$3wZ?)ybLQ@LS_q3PkyyR@=q8S(LqQU;-+wEz5A)t%+`QxweS6g8caXf6etqN;w{`2Q zg(+;4K)LT|YF0E!eL)%0DH$J4S@DriCY@>{+t-SUx7XXjKb4vyrZu*-FY=QTJ9;je z8P1+e&?pFwGxUZ1rwSayE3hPU1CG3;5IGuqDst^|&G|bTWMa}*^hCzcYYqz%C}#+@ zdhYRY$Y7*QttfTx-OU`fb4<=kivy^%LpS`&OZZU^t}iH3@uD{jfBwq{zc>#3*7vT# zn6^TEs!~tbRz>D(p9C=o6r2TNV_vL~bW(ZN5gc{!dp@;K#-tGA8xPvW5?Jl9r6k|z z=)uaXHJDJ;b%8IC%XVNz9<8hdQ=F|}2lp_VqroD7ld<gtO*BEmNov_&<1y7DZz($n?zsuX|Iiz8zSZxZ_& z%q^<))s9f?t;<84P8F|9;?4=rx<^NF3RY3Rj-Z4ceRR+E*|%K-SOVsx-*C!-SSM?V zTbIM^qIZKl$_1+S^s5q{+`4zuJkoA@T`x87^GomeJB_?9L7m(DsUKXcFcmt>jV8-` z%_b=Pt#-G*6hkEqv5RRYPoGm}vRz2=CtB>ELOt_FzPvqyy625V^LklK@mC(4LUYgi z+W2k1dZoAVJ6)Vc%h?uqMR`vwSY&LKkJ#fEH{|U{?$m9x*oVpDt-+BL@K|^vIQ^Cdz5 zt=-TNY&Kc|t|V>rr;KPWZKD8t)G=aA;z(>i^L+EC_KApLFZJ0v-kR8c1x+=5~F^wP8D+n8pi1#xg@e7HrcWy_s&T#z;KQwm^@ z0p#6&Sp6##rcLq|Qs1k`agBzo!q+zrXeN_J$5FPo@7@x$xDsuyB;o=En1jEi`n!E% zb5Yr-WeIhw1S*^l@jhdhenjlAb-BKs7-Z;;#NJPd%`Z5Mj;->-r=d52LSpA_w<&VA zEG5ZpM2D06kK5n&k$(09=5^mzV_A@Ho0>mq+UuO`kLzptq;LX; zcUQl#i`+E$gT@4(9Uq`UC2Gea?OY^&Iyijb!^C+dS~G?!IYWF*rG>Fw^hk_3Y2(M; z_pbWkl}nTuI)f%r{B|wA>6Lx^VyPV$dU!lr{`PZ*Z*db+ak=7aqv9)!zDAAPFX!{; z1R47z4!H*d6}C|rq}{bhM5PzFA0=huZIxgdaX{hNL+ms{Qv zivE`5#*qLqXg0u81dWHpIL=7v- zOWV`N>C3rXNs!iyT_c&Z=2*@}u9KchKnJ5ss7gcp-Z6_|SaMc84U3VtvE)2K8!kDI zAl>!0)fL^6Z)I#K)^_2PDul2&%v9CnhQ|r7+fP*#lJGTH^x>X$wOZb0I_7;bH(Huv zd2)SYLKZbgu`3=fMlY=ye)i z#lJZCc8G%RUPs86+3AV4NR0%lw2Pc~r8z3@rPUKwYVMOXH-imwC~D^AEHo5@aa zmIh~^-KI>UPTcS$*f8c|o_=)fRRB79vN26xE%Yb@%hD&1s; zZBwM?2v@qT>}jRgEFX4FFlh+KmXPELzJ3Yk{poK~Inolnp;pr?5?)aBzJBPYTScGM zI8K>maE4)xH>7Hw&C7~KNjvg_h^uNo({ObURPwrDY`T(;b#yUNl5=po3|Z9a9fRK9 zl9u;a#Re1OzyQQ%e71Gft5koZxztlc!P`4znrqcvt!|mwsoAbnjA?p8*|1E;o5y$e zto~}C$-D2)InU2Lt6@&1p@K2BqNvHC>v)62gX+L>+i`g}h3Pb{P-A<6+Y-{;i8AZ3 z?!SjM*G?@>y=!W!_MG}!jGL-LOL73erb*hhOyS5`~#z#F_sM9=`7`$3o-T(a~A8QQl z1byzp#PJ0ARr?5g7Zkr%KVEvwfk^UE$nmu~<6ic7-Es@9;z5P~hXG=o;N98ZxGT3WI=fcQ!b@BQm-?F$m>z z^~@b;M%Kid61T>x;n-fuCHSg7A6Q-al>K_PoN|S8IvF=|w3Q2H0xWd}+Y8#q-=khfJ-_~ku%sT4t>r=^{_*# zq8Z1^o)xQcGxGHn0gS?8X$)gw3{%&c)>#GP<@&-I!bK=qADO<5^+M5`kIKGWq1+ciM z0vL$oA}v{yN|Ojv3BfY~ggu{OZ3Dvb_4>4IL9<}VK;#g~ZSjVS90omJQ89}u1}}4m zn02^W6^XCSe(|P3Z})o93LC!Mt=Y=NR*!yG#N)_kM=2iXzqABrE|Tlb4}Fg(kw=yj z;Cp*LE*pWzwo%tCuFGzcUd(-G&adSKawIAA*Ut;#$&6>OI7*~10`t$3Ifv8i?^p$p zA^;l5wNuX`?3!uifo%fKY2MA!0^mnel!Ev*-GM3S;nSrhI#d3-QrY@m&YJ43@w~jk zl*AliJY>qE#zBdnfYjNql<^f*=D)pJ7ivA@y}G%b_jfVPZsj_eZLDrQr(j&DIk{5m z*<4Q}xxnY-M@>Jxb|P%OaFt(7P}RSF3u`1?-`tRJ;r{9DWB2Yz|MkqAYrh)33R<;W z0oSMGZ=#Q63!b9QODDA}zu{!;%o&pspNc1n0>(-wDq%UdD0msg$fa6#T=9oXNrt+Y zjWh5qs;o-#l1NIR)pQ#uRy|_7)%GD#;2CxODK0S@6poqF{iE5N+>1nA5tlqCU0kpN z9egmAl*^{ojnUCd zCV3c(X=v4@;*+P%3fqx%RUZ>76(s{L*_&^4i(KYJ3P%a}C@p_GefcKrcjW5owXpqS z%?Ou|P9C{_OS98l*Z*^Tzq}DI=a`vyx)0Y%XVp(S3KLKjklP>W37!-FfANRz{ZmaC6G#U%MsaE-*^3k@o@Lbb1%Kpvmb-It=th8%GQ zX-s>&9n+n^WYIXpUEt6xJ%Ts$vK*=L!BL`?j$Ug+*Wz)h&ge=qZ39%ImJysCEjcJi)pW^caQW@%r~bEe`f`|Kd$@;YZ^Z@t!LX|?w2^WwKH zRvm$`ftgAd#*d*)`t*z?L~Hztm)$o9txB%n$lNMUV=ZU+8Qw@$ZnEk?2-(wP)tVYr z&O~0@dQbo$aG8oufBbC7Gdx41e727Sa#`Z4JJz3niaxQ3s*(K}Su|tti&?g|xSxrVxpzQPyn$MZ_^Vqj6xN3SJ@53y~L*UxJpT$D<7nu(6P=b9<3`?Cs?ABP+cPJy?u0Yi#chuR_M$8>4%cq~!&%fiVFFO9Bk&aZ>C{rUN zUv7dx_zSfXh}6wxhvP=(L^M?-T+0qaj(gaE+UL~yS&Did4AKu@eJor0QwfIe^)(ar z`N?te@cV|4j|@yC36mOa;VDlE15Q!U@zYs;5aO%ht8AfSVXh|!C`Ua066K!Dog}iG z2Y*LaWn+!pRSciXrJtBHj4##8#;btM!}@tP*_57Kj$s97rUAqW3lF4kz7Z{P|HfNF z`|Y_z`DvzFQT**AWX7*=pMGU@7y8(b&cWdVaehAl0Q z`886`+unXUm##dRv+^`S#&fNh*S+TGs#1+i{P>hnMdG<2>($TRB7>$)0qv$4O8q(l zS5HQeRUkZCgciId_zYw`_h=OKUQs0?tOSMq|RC zywy=EkH7eQutadvIHWM}lEufnr0!?^Qi4G9C2U}T{t2b>_YbMTuSZ;O62k_q-WjYI z@VuE|Wai^zRs;D5$jD2lvhhHk$IoShE5<69YiJ>|ApamUDPzf~`btPIHnHXJB68^T zdvf(^LUm57#=AAA-9BDJgFAvR2OoqDggT<_>G@b+@2_z8nw`|Odj;H!OC|^|G$(P; zAN=anvt^$BeVX92LU=Vr{2hOjYuK&2q>l1_V1naE(6&!(;qvx!vEAJ|!-~*R2I=+s zNvHn>GMetyph{@R6JCn%9u;4n>?l}LVaAbqQtW)$z+A_dPBbo-aD1PdLqs7HvEZ|D zBP}B~m=H<2!@Q9taT3K7w%39F*qz;tMo`7FrarVivd$vQ!pagUjQSChoO{}9Qh3B; zvcqq~h;P%<%6f2NuZ|%TyzJPoBQsnJ(4t#o(8g6!ZM~UV?37&0 zTzoTWuatMn z^ZL4AzQCyV1lWYXs&51wl?!BIdvmcULs`qWuzPk}nO%Kmb+_AWVX4)gRH!lX&Lq;< z^oZvUH@BhaSAsp)r$L)$G>s!PKS=@G7Yvz9G>*~cIm(u?7EcZjeXE^uiPwp+tgO2| zS`>D#hIXeZN>Ig6%LDNOi%<*Dus=FW$lALsrTK=m^kS7n%qE|A_r=;~Ta$r2HN;Wx ziT0vQPB9o@Z#{1}9Jg3|dJaM&#C-=RGb%V}75KeM5S%n?j4TZLM#T?cFist2}ExKpX_OI(k6 z7iCnw4PKN=`7AT)qHGea1t&<^NX5?_No08uq8KNW)3(QMs~yK(tUBuX&2|4U%!N+Q z`~IbOY^%&#a%=WHNsT2;tT;)I$miEmiQa|FFHsN0XTO*IZVi9u`rXvNZ2k1!@DTTS zF*59=!I+72M}KV8u%fT1KqWCF-t4Sm*cgQ7_#!XwMV={^yscTaR@Z9sSYAuLf>*Pi zTI%yE_vu|%mG;^5sF|eAA~=f5hZM9N3+DH}sm%U~zg6G3am)Rnm{iv|@KITtO@&xH zm^&hQD)OxU)L)#zuBx2dX=%vR-FcZBH|9Xr z3;zmI_*5*%j7?p5@ydsx(d1~g!mGNvz;@7Mm%7lxE!BFVWlvL0ro4Ns!dm*=MVM+? zIG4HIsq0mtYpIr_tb5udC~1cptY~W8t@HVFg%%OKaJf)n!gR;+tYW7$t8;3JuoDiAtxuKn%e&$T!R-WgL&*oE`x?AZr`%$HL<;ay*B@?RF9R#=1#WlornTk*&w zGhv~teA+Qh8JqZO`}X?OysqFmL>Q~dJ7mm!tbS}alL_=2bgc}xtRkloiF>xSbbJ*0 znS0?Wjm@_sSSeXy8ha_+WiR!arOV9pd7=L4sXo0H-+d5Uz-&{USTOoR&02uKz7<0} z_(CDAs_u7HWi*n&_?~`2@r`wXwOPWvU(&Du?_BA|^cAl|C@N~Xb*1cyogOv?dfR3G zw7f+)CnbM{j=1j<^oPd5L6g#N-(#tkTtS`BOrwPK&jLM-J`{Y@eaBEnFnhcgC&cAz zb+KG_;5L*{YyW+@0{!OPx=v{C_B!0>_#hvhRqu_{&QA5k^6wskJ969g@0r9qA=BML z9#!_w1AkyxKV>^5d6J&}_~Q`gHBWKo81|B2V;yZ_L%{j*t(E}*Gxy5+0+-Lc@<%I> z`ca@i=6=;i&iuT-g!-kEeVb6@-e7tBlirBbzKXEIA>sQY))E4dlIzTDr51qsB%2V< zbsSEg(mL}?Jnt@*6PZt^lEK48Q&39e&X0O&t#s1D5+{Ck9OoWc+2??e&KGg1+seAn z6UtGOkK_a8yO*z*rENuQv)beqIg+~=%L604Uq(DNmAIcRn?2-q(G`WuMk^cBg9(y4 z?}-?UNW_dDQ6+vuBPbKbdMfgwE?dz{R#>;SF2w$seSrP$D&v|>=QBgWH#ajYiL^U! zJIZZ(c{SgxZXD6j#6r#szdP-gt|{;(If5cZ6`;sD-Zw@@6BEsTRD)z( z306=%d?#ia*kbP&b8;E@T!r;byZ@)Pvv4mqTM>qy#5U$#=0lY7F&@2gLqT#GQPb*_ zfKP=HulrnHS$o6^M}zb!xh?TP08L)P$1VKb(MldLTjL6?c*i}FNk0z=ST7%e5aNvxq_7{pIV zij(+M-7qS2MXvJ8umyw|zxjFaFr^ln`jNPn6oq!N%G=~CzLd2H)51~>DpyO9m^zI@ z`yaN836puZ)`BsvRIVZ-#%bc1v_3T7j5)=Ulx6+mg5t1qkFJmU(Q;;0&F0@#Fg@im zhzfsR*@h#SHpr;8@uvDQEuIJ`TzNHq(SdY1i%+`h^*oW$j@iDM{X#=5UUEB5 zj%a<*_|WLkY{%rp;zW#@$9va;1h+OOH&|(R;n|Mz*^^H}vVKE;Ec!Y;#8MI!V^Op@ zeMTHv)kg5h9SSw^SK_aFl6thpt)Lu1aw@qgc{*V0tA>EhfOwn=>DKnLc1=S@P=Y38 zcK{96jp7)P)2|3yv|P3Rjoisk3w9O;q zGwx4++=*q6217-q298WOs(gX>pUrknj}?UnZ>M|YsD{?=HUz#Ak3-LV8m;f8wSQ;a zv!ShIlQ>Q-IsF3nb=zlDJn`>+oK18>m^c8kZA%Szdu4L;igoOcm+4)GSSKSJHkV*i zP*3%n925uXSmrx{f;+}7RgbskE?#MU|=FAUy9Q;0qxdI5H*>eaUh+#pAT@ zeTD}Hq;6A7xq76~Ti*AhZrqOi! z#A_|=J3>|iG@*9ua4`OMV&R><0XRg(RI>9^m>JGFRx30qV$Usc>xZtEG41}M-19ZQ zSbG*OxA%M@eRAaW>>BCX$-WBZwO5yE;cw#ZgVY+Av^dE$k|QmL6t|PV?o*-m+};3s;B0z)B!;i_Y2mTe6_tjYDfF2c(Tl?vOLc z=hWA-z%H&sL&`44;FD(#DM^`82YuZw%-6I2WsB^4Hg3=16=j^;rN@K=E9@8<^DDM8 zKVq{EH83cQE+P}Y1)N~^5ypSJ3i^?SDY72P?MZ}0Vdt9BkpaC8>8N+$_MnyJA6Stk zN|pCjA(byF>!Z^L9$twgjj(r(6(I}CB8`~+T+>T6H48Kl=R0TPml#hsr_sQdTFx3cm2pFwpZu- zqw)2UbqKq}n;j*Xa5+cT6WC{v@HF(^uIr}bfEBW2;hOA?E zj9qE=btee}y)UZQMG~w-@0CkWi;$-sG%FiIn*uv_Sj$lQbk81rD&pv+!O#p5B2vdQ z6~T7++WUmb>hLXTJX>Yo0F=41O&KGA6ouPWCqt`3)H|>vhNg`B)$v4{Lkn{HW?68D zFgr7_-SgR|ed5AXH#uP5OA{_3)*vm?^wmS-r+jS&fh=n2Ae3Ck#G0qMhOdJ<@G#~` zX&n zk;6z==_1#oOx_1U!-#C+BYNhtqtg8iWaZguAV?`qOG3q67 z;Rhyhjl7?AJ__xd1mHb^qx%`-QZJcC#UlPF^1kz_U#gk!(uWNW`1BrrSYUPHR6diWoK$bbF-^^!6F010vg(PKmt1Pk&|{rWK+cu4y~1gE{? z_2g65_0ORqlDJRvgs}*Gxu2SdJaS-s?w4S4lszD8-cGpm?20I7#Q#eD)NBA{DV*d{f#vJ z6H$54{nO&FEhD@=ASwuS)W8w;pz!ZIS8+0g|AF*~NQpjt`rrtR*pQT{s;z{SsGNZv zg4!`g%-%@MJCDH{{p2M|XYW@?ULh1>x2LJ0U3h9G4X9E@QO<~F7P`hS`s zgep#Uc2+R!htvWeh#idwR7VE_1hN95T#yHp2MAyXaj|l9fq+oGhn+qUJWwDjh#kU( z*f|8C!wv!dnf|{N0qpD$Rw#%A2tk-Y0bniw1R(&k139<=>3$ZE)%K4Bz&Id>caS1|5Iar}UF#7|31coB6AJUJwM(A*IAwVK-CHmWjsjP*;%g+dUz>`=s74;8G3sCPuDP!M8w z5Jb@-s!mknj~n&RO8XnG{J&92hz$Q7O45rN`sfG5>N(&Si&zpFGn*t3HQOWL`-N?)ujThw^F+FQpDhWRddlhW4Xe(fG@2&FMpxbs(bJm ze~nuczD&@w=KKCkV*)6wv6FjI5eB*+NW;iVo8A0;&D7+27o_%1$IB??Ak#s2Df}t` zu5H->nDLID0ARFxuU<^K&RPx1>kffyMq3T*s+E;2* z4n3(pRbfy=?R}G-$tSq#0Zz}a0eqA~qFY;a02m2(vpWfDi3%A?>5Dd_C^K}DaM`}x zz-z3Q;^;Q!E9o1ROj3 z14Ii#^acd(_D9cAMihvut(uMb1ILZvw-M|9tu47az)Vnp01zh%@LvxAgp-q<6JP@P zmkflU`yL(un}5ncP#~gK|6PWtbABiz6N{zsw_$DSL4LPH~_ApU;dsCmKK!ml$4NAK#}f}1{IL*?rxC&hjY&R zo%g)ocYXi=&&4&*Gm8~_?`Q3`_FUXBsYpn1fw*~bn1;4C7H~iSAi&<(3P(VIN8HH_ z>0<8$U=@GqWN&NfYRiVhqvB+5>S|(!5~^EUB6(1@09!a5^@~50E$!_jkS=BbR*7d| zAea{j0m48CJ~$A<0R*z3eo%Uf_NM>4ijWYFnVsp~5FmdK#RLfe;qZtl0(g|{ootad ze=G6+tt2jbr}U?)f;a$(!=oVg$Gg^@Tu}kQi^HQX3UG09HT$1^@%=yf0{`I)_5Q#5 zg8hH^`oE0}{hnn1pw?N!%*5UlH5UalI}4YW01zJ>EF=VQc0oNiTO9ZI zJ9<-5Q&2*mF|GYtzsCd??&x9nCnTZ$miWi$RkC5(dRZH{=;^Vhp$Sa2RU0@j8>uC$ z7zz4m;&M_*r1TVKqQO^Fo7)_ipIQpXs#p7^>~up!`7!$RgnTZiuddQB{P*aDSL#-W zSnM9iz4pDzzj!p)1l<$LzPQk`;CP%vLu<1le-!FlyeZa2`c7#SaWkbJGpqDf@d=j7 z@_Dqn>HPRffg`U{@VJrQfxoBldsTaHda)C)qoHij0VA=xPMdZ>Zv263%p2?s$}ra~ zG_%`+=Pb90}E!eUFKb$$S0_br5cdR&}X+$b;htCnw=}!Sw-en!gDeB zTCLl+604KT->b=}8xDe>_}Ofiqw{-fD-&8MGHJCxE*cCFdH+~S+@Q?esT6(XLBh%z zEsH-IpVLR2h<;)grZ`%TzBYKczO&c%`>O-8LQyqU+fZkfrmjb_dn^>6^iMW^HFzCt z7e4bwF4is64ATrP6rE@E_j}iD0AEJ<^ap!acfxP|pIwc5!)j9zBIK!zwS*h^+JlgNc@vV-;}Er z#g%h)Uu=pJfbC%A8HZI}jL$sVoM3y4pD6X75 zE=y2t{(XfA{jp7U%DXQk=8s-Fk+TkBzb}t5ceUq}d9QrFTm#k#a3OfEBVvThPL>R3 z9rx?;+z>a^9opKyMsVt&y>x5J=yW#dckB&yb# zTF14LWvcd>0UL7+XZ)qzm#qliT1+Q5UPo%h4Rzd*(rf{Eoqh8_>a7bMt?)@j-4k*IBfQN`7qfx zUcn9ea?|{aWNN033dKBm%IHsh#)H&DQoOM0#qehMXUU8=XVHoYP0k|S=ktD@K$AKX zmlqt{?g6<=66_ztOGUX|^B%ui9H_J6<*NvS1XHi=cvBv14hx0!J;q|+{!x;kz!UEJ zJ*nT~kZI8+rpc>?W~Ji7emy>EcABQP&nwhNYT1={Kz7lE^pf>ZlvvW!mGJWHk#2g3 zWr~KVe2(cuf#N8!0RUyE;(eZ&FFY)SJ3A?2iua>=yK5g8?g17U1;fZ&PXlT(>KA1jXlx>=@4*+8ay0;Gi=3{ zZ{B-4aqlId7Du+x$@)>~RF7Go5e+QCqDR|4)MrHX?VBTSe9rylvWZV)%+11;J$Q$uX@Dl2leV778y8Y8=O`fWPdbZEHywj7*M6ZLXzrH z&fT03OdJ@l+8|fP&G`2qN6=vSgtYQF zN){)Gm7&Xby4CQ7S>kd}9%N`I_-K}0_6sUEriiJJe!P0~pxfQF=!E}sUGrEb&a}P6 z@%clw?9EUUC?c!y6j@kjm1_dz>(jN{mv6IHxktXx8czwT!po*;*7bkI?`K6-V zh$k=oGxpGFEHxxgBqLjQwi3DyZZbVpKZ2?5M(W=6+`k&fU)>k{chk}Ea4-Y#s30v+ zy++N<+1}O3#LO9hIw7D=119QbE&#nh4gx$HX6`Nk9$8zIqS#+o@xQLJ1~@#D?k>{m zE_dexl&LfXaM$0}aCoG70e4OO?v4*|*MjfvV1T;@s)p+GJW}>{E_W7EPyqB#*_~9; z%+wMoX73Kr1EPd{U_NdT7yyCYT~MLKQ8s3FF3y0v)`{|`j%xZQE-FZ;KZK~0!JoGP z#9u-Fn)BVqzYaft&)NCTohxb#s6&LjrKvMO?`~<-4E{cYfbNFy4?A(B3)05k;x3K_ zYN`Gs4CvnuS%3C!5C8;*LQ&)T-}*Zo3WxoBe;@Jm@Yay5^3_bQcbS{zpV8r$wO|Oi z7mAIfm}LFVEQL+e2OHfcZ$l=;!~AvZv9udyV)TnN&G@zc zlemr8>xZDIb}$cT>NDq8#pjTRAY{sRYO0aGgoZ-Rt#>_8VxpOC%}(F0@^L3SU#*3mp8 zUW?p{Hh&NXb$;P|?~1gvA*Ake8fSdoZC(;QPILNLuf=NIyejy~i!N>QLCpXU{MBba z_lWM-G!aI5Bq%XJ>{X-#2!_gBuJ9HY&>Dyi9&+J&hnyAI2Sg3O9^E=)XoC1r6Gr3A zOSQXU?4z~opm`G>%%FKcJP<^?qFNk4^M34DMXM(@-(YgZt1U&}hds|vG)Mg{hcJ4i zYfa3jPI+hqpwc6G(0%)U!~(D!>u-HqCI;5%~Ps7b9`^q%9SSccgDS_#OCtoQNsa8 zoY6Vz{ATQf@q0~=9ADjAqkl^Bjil5*YL)`S_B`j8?UH~Pr!wLH_HJ9-5^UMxl=fPCrgfF{exRQ0P8>Udb~mr!H}OdyV;qC5%7FueX(G?kbWf?X^jJ4lFAF`m?iy#8~vh#G;Fk z@{%)9qZ?B;m**Z9zgG@vx4qmOy1iwXhedN79Z@5?n_U78>f-Iy@g!xTSZi8z*n>rV zI<|y>=!Sl?fx&$HyVJf~RgM4p*)FhRkC|Rz4xkY68;F)7au||(jcb;Z3QL9&`+H=b z13@}c+EPSGX6boB0nf}4iG+`$UPw)Xdu-Gr5Un(pQP5Ax_TV{-KE80ioVa&i>A-3k z+`^F^thZ!0ayTg@Y(Tbqn4zGB9@g63cujcjJ+_0mz_9T8bxc=g!8GZYT`5r_=mY3L zBZ7H%PSr*{iJ>3njWb?vPG1=W-EdxD_b?%$$lW)!Mp?aFbrO=kc=*6MqL(nvn0gcP z*Vjrv*^>8&+l`eNUJJA2PHBy)`;wcim}ErgXa}$*JLdJM{A@i_>Jqqrgr2Or7E*H3 zD)bXSq8b>pC(WJNYR%~c*hq~H;I*LlX^TnZeD6lzry8=<+uDT7|Lp#=A#_CDlc@*^ zxvm#!-nlQR`k>Mk8}Q4^jZVJvokzU@{9MYREmM{WnQD^)m9Y|YwI7>3VDKaBs6lhx z9?usuube{Pw0xSY&_Ut zAd_dw6(~sl*k+E9o{g%dZ3y*rc`p%<=@~>CkG{{B+eWtm?UC#IhCMFZx5OzXoGME; zAtx6@PLVDtr-NOOWj!0GoRu`^2exKrS!ebnF5nkQiW^#Hiy2ob3(b&fO6^fLWiu^T z(@1xD9&+3qXp;WzhFYdHz>#p|A?kn?JiMeIe>^9%PM0}4#H1Dmv4}5{^Iue3av-NG z-8p8pRUM7hbt2vkp4bN&Fn7rE=YGij&V$y?pb0<49FS(q#f^1~m1|$Od6OXR7FV1n z;7S~I{c--`+VqcI(I}iAx}UhD{D-`L-2QU88q<-CEW-Icr=&IPA zh?88b;TU!r*)^>VhT8x^m|P}9zorY{W$1gqDV05(yl__QMf%4KvDbz4^50lDb}Pq9 z1CSW5P4!)#b5ALTaxRO*4C^1qggqIvo~$`$0)A}Kt_(9wUp+^*#_&^2ou zakfC{1_R%=Zk@92P4#igMGCTM0Y3+0=>C$b!V_Kkk82fU3aTFuJ{ovlv^I=ht@Q;w z)!&wfepry$k5VMDMfYVKsIzaNd)0i1oRZmsFR@6#VdUdqB1jLZ3RGspu0AtPTO@uZ zUSa3!&U^V*Jyof4T4MW?u2N+#Cc>Bo8x)l+7Ft0jE-~d{n4{}^gN%v`a2`9L)ec=` zBp>XuP|u*>Dk6X9r%orDI&#w!QkS(|8Y!^_A9R}zd6pIxTD(`|Y{?b%`r6@bRiZ{A zu=)oj@mQeQvC}D%X+=Jf`*TsjYp2G=tGGvX4sRa8Z@C0dCnzU}-yYd^oSSbPNnY9% zCM)N)FDJakd$30BexBs$Kj@!sN1?vt$q(@?ErOf6D(;l!$&*>&(z>rgW^bpCj(c$_ z)~VrEXo78W6KV+oCbSdXjB<>ZEPI>xW$?osyGTnyPLFIho-d>bb!G|%gjZems7bZS z~3{GA<|0L({UgZe#3pST65IuA!Z* zX`+Xi)^>*5sSboOU`a+)s@3XB2m=Wi2qSqk`yUBBY+dD^JX zJ4y#EUL|#Srq@p!Hz&)Pq_piSC_6vf<^)B;w;8#gUzNS1&h#N~?iccUM|J-0v(`D8 zRYLi1>>KV?61d~D9myeU4-n59Swr&IkGLBQE|v2a&MrkuvDErPnfxSHOwT!Zp34>u z5Ei-nNvOwPYrF_7&|XMnZk8G3#w8QOj4f@1mdJ8eD@Ta;$;h~6=_8)>Wqwqj{m?d5 zwVMzY48^k*Y$U-F(WA$gjuJGD=K*mF+!qrh(4i;LNd)io^Ji2H*Nw`ptA`kvXdDHM zi-uNIN9H?QMCar7HQ7s~b6g7LJ_wloz)Xu+bU4LTaZayU*?XDZwfk@*xZ-@UQwHG_ zbrEtLA|RYiuOJys!W@{haqyGr=$*$x2a&U&I{;6QxQWp?)B_a+ueY|f@pD@n7YRQnVHe74mnbxJg9s^%l z66DxVC~>n7bB-D@K*T+Hs>3^R#>VxG<`Q%ajj^9iQx~vcC0PDrb_;t4#mo(S43|48 z!E;vARTf4kAGwqxg#ak}5c?s29(P_QaeK$ga)@-3?3#pzTtF`NF(hM1E_q*IL# z$E^}>dF~E>OXOXaG}7LHbMHEq=FTYOQe$c@0SR^eusryZnd7;6DLsc&kGYQw5@`gA z`*WhdfvsBdcn2TLxXoj}YDXA@MHV6s@m^mXADm)4iB0Li2NIk7#|9g6YQ)kU0&!vv zWxy>IEP>_avRPY5P$~ja|p`O=uGv5)loGY?@|&btkF~t| z%>G2>y=CQbo2y0G?Xs|EV=pXkcdEwG$eSYJ6`7h*&Q!cRc$9)Rmr%YoWf+sAGGpHM zRM**TTerXPf%BIE5^}QTH_7WE4|sw35^F9b&R=(?c{Z1vkqy$yB_s}FR*7k3%k@HG zD}(w}pKAPPVYtB(- z8gCqGGX*pC(xuPo8ht^UUlBjKDm~@=Tsu)P;KIHJ?~tooquj5 z#wrI>Er{Gy-O{J7WOtOe%11P%bv@ZDr5y0g!LII*$eo-@)#Zj&uD{)x{_I&mYd5$R zkn)SfR?*v2w*&~jcoi8Q*}p!*pI?qrCo(W7n`4>3!?_EYULAu zc0^E>KSmUaM2WdZhN|bZy+mMt9;uS8%mu^iMw_7Snr}A`P+u2g$F-v+wH`Az53%_4 z_-+p;&3`O`wMI+O9MFV%GZeDv&TI%QUrl1?gM3_OUSaB}YRO3P#O;p7jdNGTb0xH_ zF~Fik1UHOs=Pj<-D}6=ZJp0XYb=4i|q9T%%tty`%_{@3tQtRSwvXk*0}}i?xd=gE`H{OuwOz2BdyPRq|h@I zBpR#}_>O%Q>BLGgGx$daEyG<{oOg_We^sA(@RUMtk54^y>qmtub$J2QKQe;pNR~)P zGJ>5Ch!LR%#5X~>aQ*-*=M9awxd?fYuFBvJ2ji2uAUGhx9T`DXZ0+_<63h2Mgk1y& z;hb-h-dkJ?Y0nBdo?A{#KE?FXjkjboin#Egag)P!vI7tZP|R+I<1&n-mQL0tKey(Q z-t zZGcSsub0iFVhv<#-0SygB%;fYYvM0B3(A!H;*OTt&k;I3_;S*nbD~jt@v{a`br4X0D9#zJFLvU$5B|#$|-Q$4AMAZe17e4oV zBhHuqQ#3_X-;a`y!H%joxu5_KPs9+K?BF&(8pGGYfIk@H5FV5Li?&ocV2$A1EPh?D zjj*KsMDlqlmy?JMHp9^L&pb>^18s_t&#wj=bb0v1)B2v8F>Q(!MR2Jmy|mUYkx(R* zU;sqD3YHMpGU0hf=!CZvp^gWMIKsz`4BxQI|Jd&*Up-T!^Xo?rnl#(MQx_txJi*!J zyxxWiS)mzozf8UOm31h6>}dah&_jds^}65nld^@^2X4t+PgRnjZB7VSUW-|$>c zU)RFArXUtx*dY}<4^W#uz}``&UHx$mx?wKP!d;1Nc$2wibcp#ZA!z8~GZ&8LXnW#U z;dYX=!G;8EL|ZkwbG4$m%{&Rur(`P~ONYKv?*C*C*1_Zt>0+(DN*m#^61+K0vDtlj z_To(9?1!C>&DgPZJ*hu}jdDd~>|lf%`eoH;V@eCdN9&y5N$%1pBcIjR_;Mmz_&VDM zYg0r}jvjl>ZJrG<{*8v2UQ17lvd8#SOU{YpNkhkZxMvuE1(3*lts+ zBtLl$i5Nt`UuZw;d>kp*dxa;rARz3I3)&m(iBEcAHg$bPaznQxwG_zhHfbBUea0k5 zpc9Lh-bl|K=e`@PD=W(^b8JQ*0f`+@a+zFBthkk3E5j38V)(%XSd8#4Pv}ono;Mnw7dc4Z%nU1H6~3whZoja1dhcE zVhdCY1`1|}lZVG!LYria5_l%pPC9-Ym(!PLmt~hX=zw%ebwVXWf6#MevuATOkb!;} zk1>ui8_Gp&Zck1Wl#3f`7`kM@cs{ZgvetF$k*bqxk{hgYg=04gJ#R=kb!;~axtE12 z#k&C-%Y62BVgXW5(eGJT`T@EBVWmE8s#xu`^`gONLY*M`wpgCCvBXsEK-w!_s)}b; zC;9ebbu0=luXVaz3jviXc5mMMZuNPwRdAcm#|QcAWfdj0_{?V;e4?$kkRcE0d>v50 z+*7tHrAf1y!VHpu@zU^u%fsyN*;YCCHntX z{HW6pr=kHmzM%QVz|Ts!l$%t{UONFn#`{U zB+j9Aa(UW-re3)Dvp~&KukpP7hSFX!^=cOV3hW!sT~vI9wfz)2E5tVYxLaN z7)?LTqq-Q^JO8A(b+$XfxGjZK*wW8>1OWG~#qJE-xT}63Gi}sFPen*zI7(*gm zuyH?P}pNLx3QugA6_1Y^&u)sPQ%?dNu_$%`kcnc1}|U0uBl)%BGv6w~xa67TP6MLw&+-DrKG!TxJwGtkqL@kO3o;K;xW z!{QHKOgZg+jRvrdI$Z+N;0M7Z=@vd2dXE|xXdg|QOvQ@K2>eMah#|)M}>T`VR6H#tiO;Z(U2}USplE8cIJhB8%gDS znIimA{eZ)bNHy>|p2quxnD`k`;Xm8Gr!=n|!Ol)QOBob~~>)P~KG5sf;d|tgIl& zxJtyZm3^fPe@i>EVYVa?0piw5#%4JC8pG=PF8-bAh(!jb$Eut*v*!2D@7P_@zi7F& z;vNc}D4vL);OM{Q7-V7-aDx(UV;^yf`J+d2E=-*YZoiS=vFBs|TD5U(bGdRl!};}E zeff;yyknPTD`kFl(pe<46+J=Vgyv!iC7xVj+lwEE0oll~AspDa6#;j`{kwP@QWnhUVID&5c(WM|x>{`rYUrFjwQmXgZEj)ut!qX|Ks)vR5|c zp53P1(-$;Z_&|JMT0^`1l8#o<=K?*IFpiEHt{Q8Nv2{j!H3e_u+UIucuq3_ri#+0; zq>7+7l$TIuc!sO5q{OqLFV?YV=wWx0H^m9j~3Vj%a_>+sC*(ah)Uj$^{) z@*frtWb6~3e4(i{@itq@Wx;~k)*n_MNYio(BsQClBp5UqDEpkQwKfjU3mVj$TU-Wp zXx9rG)H)jJPcKA7IJ!l5%awF!@k~_c`F;$LmOS-uz^yeP$rc0pk&2(+ByWeH?;1zr=krhA<Q<2`921w-A2`)ZR{n%Lkbyze<9B2hYL{(>`cwf9KrdREh); zF;Cc(rP|O9_io1-5De%uCn2V(?Bp2_@|g^KI9L`^xJ1KY9cd(7Ghb$G45ew~L?POR z3G8Pho@t(Gm%0}^mlJAFstIXNK(xOZGq=^f3;Sa%X|iXKl;%&&j}T=&GskvN%(7fg zgfwN&>f>F$+0T)nNKkZnRJj=f$C57XqhhsE^$J1`?~xvDm1Z1Sr`bodRXO>*%E8l$ z(n$^5*%vb}rmQBdX3b{IK09A^ICc&!B)|R6qE~S1`1?g+*S^h6J`1hE*?jl*@nfNR z)^rgTn)K6C2I`sTM(!>pAwh!qY zC$Cl*Yyn;GTn>ziZ&n8@y#@uoG|%&JFvym=9Cp6GaHoy;1g-8lGaJsXzZ@v0kO|$U z$I2DE79^vujG5T>xqgC6&)(Nq1xF^Iti4eV*YahA;dXv@R~BJf>PTaZBccGk!+Z2X?yYR`J@Q+C+oKmX zUk&RBelRA~+}9@ZO^BcBCI$O1$J2nLBRaRlSx0ETr1@(d^mU52%MZ#Z$3-Pr7<-U= z%m)e0S~uEtcuAVloxWH4NKfm0awfnW&*&4Np|BCcjKn=K>~m=_itr$adZ%nozhVf+ z>q?1m_UPeS7F95G>aQ#fI~gQxz?ocKvPY{LzM(bW@v$AXd2cDy$0xpKU8p22bb5Z9 zb|AIOVlw6JQ^DpL?VZlR6GhLc6=2J}P%~7TPI1}aI&pO3m3pHr{QB9=$L8B}`%KK| zt6MeSKa619%K2pu&CB6mnFi7#^jG(du=oARZgkL-i03cKs=Mc$YqZhlMnvQ}yr*#H z9Ddgcd%we`fP1H4uJuPI_K$r-*tpyAzQ3lI6q>>@%Kf%RBedkejDNH6R@r)$A2G2Kx=&Th@xdf-L3l*MN0wy{4y5Np)3Kd#J5YD*`<970^e1KY|L5PsJOY6 zUo;qdxh;+aU5SWglc(;G$Ek3dm3_?MF$B%RJ_|uGqM>tvFxa1l0G?GUAZoY#tK>Fo z`Wy1LN#EmEbliw}=hEbD1JBqP+NJj(Ey)X>U@hycj5ZFMO?bmkq%vBAY2Zvf@$w8t ziS;M-*?0H&)A#9#uZ=mj=lAai@6c2skQ~8WX+?*LyyG^3Yq(kDX~U!6oN1tf)>6J$ z{i(<$2=cJ=zPq`8mAdC@jo@nT6C%NG%-*7W^%KNOwva1%`k zgUHA*RHEY8mHo^JexnEH$Ia$4|RJdV+GeK>I?=V|TwcJn4@DCcFx3KwBb(4l%l5 zHX0nb!YVLS{Izelbs)BR_lg5;@BvL{XkO@-SCl_(y zkf6g=#UQjqdnEU(jV_z46+(xHi=+|51w3FPYo&Y4j}iPP%|Be65Q_!s;N$=(j#4P$ zxvz(&jnMwtQWoe>sh8&8(k@!=AM1~nMhVa7R>2WzO(VAQqb?zb13Al|itLEMe_`sD z*zhUdH1E^hPCdBVWjSm{1C80b{dYhI#k>3mb#h0_NSHaBI9WQNxZOX=86~7GirtYg zvqC<1RY%&PU=|cQYTQ3#|?)d;CE!Ii<#|n z059q@>LUb>f?<#jGG>+*FI@l-J~;QC5=u)J#k*LVh}v1$nB5__cOwz|gU;as0l`3S zJ|GMZ0&wv{!6-LCC zvJ#3&2NbPjidqv(7mq*0>K@Lh*~{9Q+us35YGxLeC`QTyz$%L3lg&^tv$B(^nUkfR z1%UNmW+fd~jH77)S>1j8V_1^_-(Fc<{HjetP-5U5~(g*5=6rl!XSyo(40{mTaw z!pjYV@}V9$A1{I%4&;U2p-@l|A8O>NWI|;Sm>YPP9CuO(gd2939RM&4wK|Zyx!jE& zff@q{74>f^0yPg17&Wqgvw?y@+;9+-_YSQB0(eoMKoBr0=lD?Bhd@A4x)1~^)?E@C zpi&++RMZzP7y^pQJ5=IHX#Mf5{*`S129^JBKo*4eA3T_k)hK>wJc7G%h;-N>}3+*yhAn5H@WOXT(P-vX2*mc zBx%KbOmS0Fda?QfkE-!x)D8{<+gax>M0TAbn3)xlc|Myx_t^aH+>$n+7T%^ zWqc@gFybAnM_Aq5+}kfM^Z4(z?=H9h0o?sr4gPC`-|cKv8Ty~gfTSG?o4?z&|Fzk< zWd2qAOp&Mxgenav%I}YoqlQWj4SP*H%RAB@0Qv(|{JSc-JDHi|08!vQ4)DKT04N_H zgb!d2_%9g<1vTEi0CxY9fq|%v{vR?_j-$N)Qx6D2?a2R>fuX3q`42r1_>X<{4;c`M z+F<{o2L$q>O2}as(dJ{)ZQKiSl(@2RQ3L&;NETIy9VIwf^>5EW1&%qBoOs)Dom2f GQvU}&XCLbT literal 0 HcmV?d00001 diff --git a/tests/workloads/mem_levels_vL1D/MI200/empirRoof_gpu-0_int8_fp16.pdf b/tests/workloads/mem_levels_vL1D/MI200/empirRoof_gpu-0_int8_fp16.pdf new file mode 100644 index 0000000000000000000000000000000000000000..a9951bcaf6b5aa8861b923fc0843b85af6f39ee2 GIT binary patch literal 12513 zcmb80by$>Z*XTt-l#)=S8M5`O^lI}*jQ(8c}TN>mH zd++z%Z+zEx&Y6pA=6TkvweEG_&x-lu2ZN%R1P6$d2a92Bdvg&B1ONhT4Buc02yh|n zObn1Vb^vCCxt)!bg@Y9f7MG%(jj@A~2}-D9X<@*HvISW2@}j=@L)pT{TFd}x0$>*7 z0|UW4KyDxm1c&efx!Hg~Ce$BFPu|A(e^(I_!ZNWoz6*i-?@){k03a+bQF#E@OB*{Y zgSUSx@%*iX5V=$OQ&kQD0Ag{;$^7xIaVM9T1MpyRsfYlOb`B>0voFa1lP~ZezEJP~ zt1sC9hp+!zT)cn#lCXG-M4djD#9P!kit?$iYZVBH;n_w8Z#v!uYw}g7n@@W8HrVyg07u!0+BQIyxyghbO z;=Sy^r@&u%wsKU4KOH!J(=Q2i$MC*8QW35sX z_$PHFsfZ~D$!G|N1)5uIXVyBdg*mNQ4zW3nJjbwvDi-lnwG#L;OUTq6+rXPb|E*Xv z6M8gR=}-dTlSHzT-R|{$A|D$QdA4$CpSjg;Rf@HX4H1Qml!qqm2@J&ns~OP}X2Aq* zw#F%bOXk{mLrfn@vDlu{zqWrQMf{L0A_hn9k{p+0uwXQ?%EcJgX+=5nW(5=Ztv67_ zdTW^J>&MQL+w_H-k;a9> zw&cfz0gT?X)ZW>l%)QZ_KA$lp=J`NFli;UakSt0BeNkkx14D+O(o4J!R@p|6D1=m* zDn8@c0YmgNV{6G6MGml2^Xcd(Kj{oM5=h;-Bu?FVAJ32sWwjMwGVF4e@ss~8ml+WW zc-i?$aZUbQ!FMlYp_?tJew_C*Qg(Au(n)!;t|yyQUa(-NB(ly|t$uxVz{P%8{oBmV zv=wPxFIY=Nre*MpUk$ni(aYGpDjx*C)#t!czw*bKgLYbrkAC)Gyv}5!kQrc%W0kdD zgAh|>I*g>ehhyi;R3@PrzDP@8=eW;@xy5T{gWd;!eV>;E4FmeT`jECLEc({cAR8;T z`n@-yE2X&66~)N~PGYU|`A~Yh6|>3V2ZK{8vg%YkD!vR0s>dk=SLcc|n0lvBuu)YK(M<9)>W$j04Lm;R z`cazmvRZ3aCTy6`E_qAJ$o%<|ys-`@9%(~}9j`+_Xf@}-V^=B_k#~T$r5O7h+%KHD zOo(RGbY3XI%!L>GT`x!+;Zesv1yrx!?zeE-+wFRV*2mFnL>ki} zaA=hFY0-%5ub7d*a9N6gcR^#%9c9#-CbEb2t4&Wx>utiX7CiU*hL-Ku@@86NNgsSo zvPv&Lv+b&XJZ#s#nJV+WQD=^PecgrUSevs>e=A%*4n16AqJQDs=_U`bEJ1ttDe$53 zR^n8|J`JFKBPt&FQ^0mNp^o8YdyiV!r$WHj(ml)YSfWTA$DBXtbZxD>k@i<#{%g2_|L*CkF198BE=2<~R4Z3DvA1!s zGcvIUpaw8%*cz#rAOTu`%vml~6K5oVOWF#hDEikY;;&C>9V{+!XQZSG@^1X1OeMJi zcjHqTi%XIRa5p3Gt{{NB33qn|1KiCgWz-nulCZHx-dRXM0nk5XcT#y1V+#XO8)twP z5G90wA)FvEfE#xAfm#ZIvN5qn+5_$;6Uv_oYNi??6%FkE5TXX}pO*mmUyJ;;=eyg# zep~##XZt&M4yYJVGg{Wd*dCyDcQnd6e~)<3T?qeXhcG}IytOgATgMD_RR6II=wE)r z{5cvy01z0=iyE{4+xX<=0dfE9_#Ah2(~cRRxSe+s9OC94`Vl}{^Z*A&phSbezbR%h z-zKJvjUnD(^4a+#&UX!bu5^}!FB0=$2;DI=vkQ9<_#|0oH+g>RRgi`F+GZuY-$4Co zoBqt^yz*%fg#}e3?h3iveQYE#8}Lu(y4>a*rSeg>L5_o4&d- zTeXk+C?6|b3i7bhSac2*b25m*p3QPI4)hPk3k<$~B^2gCESCuDLVWpfO4~k6)F%M* z>g|6$wQ`X%XSeVOJdIKcL5H|T^Jt)GqD5EjKl>1V?6(n*oD1KDGnL`bMdV$tVVB>9{|_;Bo)2}-O?;@^9)PsLz*F&>*m^=owbup-lsvcPSPF1If3(CyEfnmW z^<_W6E|dNZUDKr-e)!>{Btg!V zE#uONkN{ejskxET@S5=BIcPsayL$vutRhkIcsnpKeKhAnzo>R@{a{xpz;kSUV^>Jh z`Ydn!vcGO_Jz;|B`Bg*ui3{1)_qlONXmj3)$nOCg3y;(`p)N?pQc<0-<#OC*CkQMO zI)*JEQnBFy#Wr)lax(pTn?kDaLooAF_9`@RFPWg9zk>AG_LsC3k~Cv?W}|CXGV^Ko zzKl1`{)&@}S#u-}L8b?XlWbVvh)|PYhPdhZCILs_jFz%^h@V5?0g;kh$g5JizLufa z85kqfmB5O930eU?VYyIe5E`jMSzy+0pR$op&`(gJ#?6RL5>R45q9lHfOG<4N`pof; zY#_NAkj5&{I1beM)DR2uA&F4#EP)DQlGvWA)FV2HPs*YY2QvhH-6j7mVfX0)3y}4m zYY-@?qHp0$rjIhhH^#YJw4)~l8Ewtj7$a`J-J!0B3Azu|J6SYmS1QC28}DT-)N3qm zR*N>!B3|}eSpt%SoW6zrPMQKP1Zk)09eUjT+i z+f&TQsKuHsbZwgFW_@ju*jid1nxhylB!PndG*(0rVLdf#ILXv*6}p$1$TPg_`H(LW zWOig@Nybm6<(v#yG{(M+Wd&0L`nt8h!bKFuz!MnTj*;6d6sPPAIR@ck8~9P7m45D_ zuI|2HqJ4QKxwf(zk-=hF1fwFG26+;7v?&aNS@$=;#xOh^HlAWM>#hf$`BW>Jy^OR~ zMsP*lw?l98H_nZwieO)%P5vOb0xqImK_e>mobV zc7&_8WyUEfmd*;cX5GtR+f`&4B2Ou~j#*n=>g{tu5%O4vtl(tdE`4Hm(RgX4QELl) z7MtjM#*uc(ZqX!}E2AH}>!m&zIzsh&Gu*l-mE){w2XCr=KAIHhrjiJ=lcrp|2*!2U zLd1)ZDzj=LdS1`rv!Hb?N8mn^-ku}O35M+cMD0}QPq zAy+}kA21ac?6NJHEtlv?oqM# z4`2&I3JWcavhZErR_+w}lXz469zYM?e zSHeHh3gy`~Il6wj*{WBXjj9e|%?9Vrv%QUWbFwIRc5OY-4m_s1sJEcldaLD{+8{Hi z;>DMoYM@*70n+w#im5g$VISx#%@<0?z`j>) zIbyuvHU6)mD@QUc8uQ-Q+fpTy^mDYm9QpAf!#^0mr`a?FObxbgM z!&IXHbuEZogJ2hw9x~&0(u$EtPL$WG{ZjIUDrVg1z=-d&IQG|dU-QchZyt6WKHGO% z#oD*O&~iOG4ykA&n4Iq6?oAab8j}%97&JdJ`5oJ&`t-+lkx>zFheMAM7Zq_)_-38T0;V z$2R>pXKwv(F95NPFNkF~a%s|a=}sh!X!DB)8NHZ}rlb<(G7~%%`i9(Au$%jzUa8Kw zO0!D#8PKEA_ipE?!lhy@3XRl0f3w1UP|ZeT{=Z? zSRI)wb=aeBJzs{gpjGuFon;8Qjk4q&qeEPglV-=8&Lb*w3ElBbu3`C-xcc29}0 zy<&))rfcQQX{Vo6DoVy%B;Q;)+lW}Bbj$J)f%qnJ?tFVZ94Cc{FoI2QeZW8M$*e_vVd z+6~hcdb5XLeN9>DIJ<+^7y-2zHD^H#4hymfvJ7Ff;EtwuJ&y7j`Bk$X;nMr#r%wdj zy5SmwBG3#z`OSSsuj8>@nsSkTt+nFGz2}5x zw-CAFR!+oEywqMQPA-KM`obyd#S#PD_;KHtC3+c+<&(hj&q}GZ{e)!j8 zvllS)>&$xxuh7kVC#GyO(??FnAxUwHtU=!`yC3)A4V|utNzq69E5)k>2kzh}5&DNB zC5x6UWXNkm1UH%;`MuKgC~pUU{c22EVg_Jr@EkA` zZf{SnVahAJ7G`xE7~*0M-LoBDzWCXq;`Tvz{U_)CixflW#OH2^JkoyjmSmZh+=3_; zcBo>s%#UDQutimSVCW}Er<_mevBx%f^p2q(`QVwAoTzTa$Jm#PYpH}I=TYxYgcF~Skg;obvbWQ5?Jwz95(71{56RGa90giVncc*&n3I)KTe-A( z$HBT`7ES18NzqQntcecyoy^(x6!Da)WIEk4v-DFM+lk4vv+dQVd;7lzvqOtVcOPNf zsyzE4R>@*eW$L=#G__X}0DY%v8}jyKvK@_>iKIGUvU)cRDC9_EzhoCxUnRcNX@>t@ zdE7;Aosn!{=y<;?ErDr3DB(*v_Ybg7 zBV1W8Z#vo>+)2KhgKr-cq)nn%OS(6f!#j>Lm9Ijdt>M;?GslTkUcyqe_SRu#$`8f4FUKBq)7hXW-Eq<_Ed zI(n}AD(n-Pzo78Woc)9lrm4G#iRX>%d~5Lt4;gsJWy9WhHbgSKsb=?))+?ep@7tDU zFZyV&+g*)o@_`rfS^RB&A7(zz@H{&cqls?tE=xgsQ15pt+Ie%2l$p#y+{{u)rPw9V z&kIy<=-b)gT{IjLy%~si);*uO{;JprCld?3uW?1>=xHwFcraci2Fzb#Byi5QVYSab zrkcL*IXIEH?{Mj~gmAT9IojswJlft_Cwd0bC^o-@Q!T90pun)2>0x39f341lbpcu- zEYa3dOe&+Ww&_s9Ba?CJv^+o7b&;kKkpR*enGj=Qy1=H(q@2v{-iWcDyP4ttY+4d) z>A0s|ZaVq0$-YN(^fEleeRs*M`Zx(@bCksYuu!MYc&?5?cCxG*78_^n+LVP<@n3&& zxV_(e>w1W$u+noBUaWglb4@>xT5jA!(Vq(niOf`9VOAVVVAgTQ=b#Z$+j^N79CHz% zF+Fiv96VAxN8o8d4<5Cec>1u%=1f}ekb3r{qgiO9@aHm3*IXB30juE2p@Z}FYvM`|Y44c}%j=_(fr>PR z_*Ny^+)sR9s>}(S=8WHo{BGXDWS!6o%cv3|=pj<2T!_`B&yBh?b1a^L(H*C<;4>jV z!ZK@X_>ehcR3B4~i)>hElhw~53fHyaQ=s!CpkU*6>w%x)i52g{lywLXll_(KtxkR2 zV*%*V`z|qyFR*c$!v6g7twLj*Pm)JHtcJr%f+{V5i!nf)NLLBZ*i*h(j?c$aDnPBo zVy(|y*?q4|H{n$Ttl96O#|*TXf$y2syNXLmbe%t)T-v(y`K>-TmX*cdu?fx*cL!~) zvk0(!?5<6nI+Sp3hOq{!=K5oG8EU3C5n98xKItje$gx{{!Mo?iU;Myhxqrr;N2*hM zK$pm7^|W`I?eIN>(B<=KV3lAUt|9H7>hPnwFrgBUzPR0nu+Cz=dPhMRcvD8@P~{o_ z#fcV&#&llXkc>u=W~ZG?bHjA`krSm?;oGD!`^#FVTcRhKpJ7;=kOGtF>9Vr#qo&`BgZ9NA3`ghxcC&l^)%G7$IOCbeE)GYuepNk69Wz`O|G7$Q2!`h z-6xRV@pG4VVnjy63Sv{w z^5&AI(OL&Du;#LfuJP^rSM}5mt=u_vq`QP=9b7I3*e)QyDNi!PNb9+VE9*6bB|d&3 z-;}#VpW`+Exxi?A*nIHhJm8uOWR*PTpouem0(6O0GS(pEoM#lk99d%L*vrzj&)A6_ zTVb!&_7qVE-$X?oo<%HwabAl4iA9NIQpjZb+3cJ;N>*P#=_)T07G5SA~9SrCCtEzRqc(S6_NT7g8 zh5K6VhqCaq$1rRbtQ!I|G3UMadQXBJd437Wx&szy!^9s3(i!OIhrk^?-(XINtdBS- z3ci8q1oM3q?7(us9yhEKs}|E~yJmQUE=+b`se-$Gi=V7+q$whu+A`s5nsq{sp7|>| z4FrY4I z!TISGfV~(0J92unSpzGgN@6d!kLnsV1=}lg48|qL|j)R z-i?$8e1Ju>K^P-LW$nhLKluRjaCD+%#TnuJa!~tldrA9&n1Z30q4Di2n_O5w`QC{$ zT|=Zrx`lzoqD5*&U`2Pu)b*4}dbUCKVs`3iph={qVS!6>g6=gJm9PA04Z@(N4ke!`b5^iEO`4tO-DB3AuG~(Ynlhy+pkpqe z3?@41lXrFX{XAg|`Tnp@{k5ei6rCVo`P+-=j3-nitW}Urf5#G@atgdV{9dwnhL z`E`$(Asg-T8)tcD?Ldw!USoMFwLnE)j(fk9Cfl-I&Z{2b7llqmonH1t7w1@!g51qa zv2Py@WrAIkV#>ILeveL<$1g3PiAmBSh_^mBX11%miBTs|UZtmT77k|Qe8W7#6|cjk zQad3Q{&0ftja~taC3v=$lgqBVc+7!svGr^!I_TcrAdV3Qq6<$NsaVgL zZY;be7RH6e_P)vvGm-EWxX_2Ml?rI+2GZEa>C=m1w?L=_nv9CZ62_#(2QcN#o+x;k zEoGgV9gtsBl1*MSjE|S3^ufk8r_SGX&2LUvdF2dNFsY6FUKkQCSg^IdRX0c@QpEL? z_;eLns$2awlkuhxi-UojT_&aX8b|`^b}b+0?Pm#XW({ptBDqZ;C&mrg7F)PnYdSf> z+x^M&bF*5fjhsLtETEx?MfOu~(}park|PwMaL8v9;|ch+)A ze0dFUG$Cf{cSx?$58hERnIq%4C!;S~L}Qgh8apdQ#K#mQ0;BmAxnYT#r_a#7&UyRa zyoi&<#?IKWdJ_bAUEg&s3x_BOs+AU3K~GL2x+Iy1#> z%KECM7JO{Ev~0vZn3KT~JT_}0J~91Fe1h|lW_x^oJn0L{X?;awRu$R-)$-eq@9qLJ05Chw&=Em#{ z#o{(pohC5M4zp_@EIv;BA{v*66DMtQ^d?)o`Z09lv_$l`|VSC zpnfwZ0KDQaJMPJC6KwZKtiS z;^3t>Dls)^UGWXBUmZ_>9O+b+uNTj&Y0WmfE=Ieh@8r1%d$N3A>lhHVnwqd0x^;1r z&5Nn@>TS=NapK2>AJEP1Pt4RUOwRZ_778Y;UKWJhsN3k=O4z(JNUySrv*0XZTk@kJ zVfxM|RhTEy{upmt%C_d=^%^_{mhYuV!=f6D6u+cJL~0td^E~?$!Y)2Rs}^i z*zI{He_7P!g0X$JTllKlW}$BT`?q49Tc+F8nZ>18m7F4NkF%6w*s+rf-7VgLB3A|U zLeNLDW#gChE=KbWjsu_C2+_@pfEvFyX4t!{7u>BcsN{~_zA1EP4fx!$ zM%*JI6skF1i+^M3M*VtiavT?v@^q|A6Yn#x9a9guC@$dlGNm?0oc7@Qp2URs_Po*q8aHPvPO3;)SS zQ_AtM&X=B#2hlZ{Zo>>H+m;315sZ{Fya_68S2c7DOe-f*QSErd2=vAHs_zSUViNuN0+j+OMbE zPj0rI=C7}6h{D%X`*q9S9O>@QuM6GE?uq2x{tlxY8*B8XV^4v`SqVLT=D^NiveTVz z0h-tdX3#pb7~(%5Yx9h#&WJPW*N;3=cP8C0akx|-4+O^r&aag`;+UjBD9>gW?rLXf z@gBTM@*tjX*<6r3_s3&tWt-Y`*X)kR<#1m9h&?MKyIOc%codgkMv$a?9$^wY=4rU< z=JL?>C%a)bTjSaGuYP?d^>J&}$EBJ(>V}Y6c~jaZcGL0P#2tyu#5Yi~x9!aFt>nZ; zDFcSkyoVTp^Q^BwLJwD7$x~|nH3aI(!SP0L^;;L`c{j_NqI41$K;7J}`|1!?<_sutXwNnj)JBp794PxXaLPp45==3vA zuiP8AKqmTde4BVh_)&8yQoxR4p2_gLxlskn#E+iQo~_a|01M9t2ALo`h06NU`n;Ul z`0RMdh$r=-GS{(>#!;_sN5S!y3hsmNm;=5XzJEp4CYgBA*DQnS`P$!8ajsMi!ZxRRImOy+cZLR1j>#1w2 zX{(qlo7A+rEx5^O92X*uRj3-SlB~SRvnA|#I~RDOQ0V6V%GC~i-`*!IXIVkc(!W5e5%01=a3+(>b1enp_w}xl-@U^)F4MW{)Ny~2RAbDMSYtiPWEcum~D0a_) z@4rRt>*W(ePBdnEdx6S;lzO)xw<`>h6B4^uSS&FqD}gZuH+nu&AB~BxUR)KXb>rFj zoe<7H->$ASn6t1G`z{+VedQ%M{Ll!Vx*`(8+tK_wC+tVTt|((xv@`hG{_N80af!p{ zPkTD954EoS3+a~Ig~{k2SR2xkF15v+M_UWAd(Q3bwAo5FA~EBn0q-tLXg%8*o<#H* z^Yt*28gr6pMqlCy7iOI2#Z!}&LX=&F5PX_>#V~v z(T7^Y&?mz7B{`S3rEkt=3%)GN9NQLdlIf}N@RhymzkSOCXh~NF2@~KA ziO?20{Sb$)TPu z^&gHY_lI-hLsH7AA)|Hfk>`aQcT2{^;(9tCK~2lea>4SH88zkg( zP7O~CjXonnmG<;MkkE>v&xHbQ zhmBx@m?=at6cHs#qPVtb6ZbLwO(rmMaUWr7BJAS|zZ~8^*In^SdN1t$;Wvys=6A<` z<0vS)<3AXSJ1#`b#NNox!WIRA{>h2FG_XREDq<#Y4AdP|46IS;28u&8v%do?MeL1G z@CN`6=H&!~!B8j`O6^Y(2bdee$;%DD<1bW@CRXYI9@IVRmYWxaei+zFnOK;aBLUnH zUd}rul$JD#?yxWtu{L{aa>sApMI!nKi^2f{f`Ob6AdD9T;NXFRQEq@xZU6`d=jP;r zz)+M2H<%MeLGtpVAeB2a6z^dI2K)hp+`%q?aVVgFAxr-RQSNmAwD^0=C~tQl3JMi9 zus69=`1hTwI2a=T0Cy15Vt3!(IRc|LBrT?DBPlH=Z(xgJbBs}EVu5t|L#*OrkJ`Po zwW-Y=Zli2sW`QDtTmZ}>DA?5mMaC-F8JpNySepTu|6zs_syNu%zBRGBJ6hl!m!ok9 zX9fc6!I@z=50~ZYT`3b0|QI8w&jM`2SV}aC1XB z;UFF$6lDSjfO!E>lmN^PaEP=#{yaKfMv)N_UKz&Uw=JkUG72MU6q0z~BuDpA0kz`Go{lX7!& z!tRm)0EVFsf%`7xyCC7Hr9hB>mBLZsg21Q%{>26g0&((!pgecH5D>tFx&v{8QK4nNKF^xYS$v<-HUqIyljWXiqhW{&Mq@&zt z?F+G^RN$TjsELS$oKip!m@oeY=IZkb;CmQILkAZsig5E z_rvi6R6lO<{Hjv^$!h-~4yzfQntIbqLUO~!DeX`=uCNN^Kb;m8qfJtbp^I`81B=Ea z6EHlT-5YUoeAL!);PRW`7(H8(|7pN|CEjQzK6yf!jp2xH!AMM6m{=-7#|o`Iy%8(d z7d(13meq`;DqNS|xl!V%$B|tfIMVqlP0D@7jd104RsFJT?7%hb&tWvN~b^nbX`?J{pS-*FMi|R7}bCru*qY&%6 zqWotqb4dN8wHX_r8VsuPQOMdK9Yqk2sZ>^3iziCgd+6rUI6QV$UyMB_Vw>FRBofZ|ECO9aQ`U-Ls6yoZ+ajw5cuDE zsKWXWJs^+=)fxWX76=AG{wqE(s;K@;4-7$7=fAHDg#8aPIQ&2Tfk3Dt``Z?2XMk$q zc6a}dpkm>QI#mdYk+iWv(Smm+i)zk)^i!0E;{G zIrpA>@BjbY@B8NAnc44}wbtHizk9E}hUfP(Du{}6fPqjf#?h^f1uQTC1h6x-#Ny}Y z6mc{$K-xJ1SVYVn?QATZZCJ556&&r1osCRTLS-up15T7Jzy^Upees8~g`KUa0n!A( zBFf7J;(~%8AZ{)YjGGJm90X!U{h{<^?Tr7sil88tiLLS75FmdK#mE2v#^Mx~1#rsQ zIocRl|E&c5TS?^QozkDGG9myF7N^XsKi<{vE#kO90Z*+2nus1^a*U#r20T z)cb$+#r^-`>;E<`#NWQeEv%8K+2<6uM$NORiIJT#Di#?NTQj6N01Ssh1O)+3NYs6^ z!E#I6(VmW)hClTlS6^>@LmCHZzAxstO_#b>hkbhSr8SV>n98Doju!=k+4ykN~3;B-Ugn0%Q z>gan5iZG7$t#wE5*dH8AAMVoE>)-6!JSx`?dGI_lRsKxpXJ9yM1DodB{q1bQ_EX(A1xSDhA8?wScF)-%E)J2uG|0& zk!oD1NXIK>#<2)#@eP$QI1X~*JC63)#i|~K1aUWq6{V`Y&NCx;k>wYpN(0R&SlN4x zcxZ0?qGg!{3DK!?b~udCazZM$G}%EX2q23!PHpyI`9SB_n*+HZa2pr6^TNU?P|i3rq<2GI38Bk~1hCfJ6d zagNB&bpj`1i$MDTA_XbBFK}EkKPq`S=AgGFaWqO14XQH1u}{PYz5U&g)fg)e6FRZ+ z9s{0K$1|MOS2F?1W1W`udMM=^1z_LwBGEL+q=ep?ET?}A3CTOoee2|Nu|L!7d0=1f zee-1TB5*VgAZ}D}j8Z#2|~M8_^tjvTFGN>UbQw*!9(JP0A>Cn2os|lcm;<4AS*{Pdn)s z8ZU=Gc`#M`NWkGw-%MJ==7lne&yZYFO~)m3f`%*q;=qF+waZ{!GGhL1f!mQBIzQo@ z=OJl$Q#1w3P?2b$X~!xWJF{~oEjJ-AfVB6?5|IGq{HxXc=gXaR4RN*UvG0E}Cu|?L zsry-V(c2y08iIAORg|J+UyW7xO+BpBP#Aw8%9iqCxQp^TQ_PBCGjUuNzrzb+Edag; ze3+g1@TYim8{YtV7njB3HTJw9It3g8F1gH@itlWBPF0B`U+b%s{ICq#&|i&7KgaB! zEZx55fxd@2IDzoiz6^|X4Oa7Kw8u%)zZ1tZN@O6}7p&>igQg{I_6=@0tbJeJ92gw7 zHhnDZytZool?NKYi*%xNpy)0F&Qgl=q8X_boi<#QVx*g0@$;3Fz*n@n zRtMORbUfGhk{?{lo{N5N5z(b3*rnRQignntR}W3_#AuOOp5a@6Mz=AiSou`*G|Dqb zQk%1rB5}CeAX><}z1MiIMP!bJaF1#m>%IHlYxSNVm*{*;CJtLR6%pl+*G5ksqv-^* z&I>vi2h4)5+!C7Qti+sDOD_kqHy?g&RuRmTv8a=0d1*!PP7%*vqtgA{i$R}m4#UFt zEZ{-!!t!VTN#)AW4*9sEHcDPhgIosk512E=OO;vddED46FjhVUu=}O((TmM0wan)> zPb#sGj{6%8jm7M|&okFb3YYLZbNJI$l>%~UgICrYB&4E4Jchu~(eEE~i0ERL1~b_^ zV}1#TPFc`Cc^>+jzwM1;@Jfl)4z{Idyn;NCUf!vQWvHe>BdSe3k9mZTdOQM_oDS#n zv^cnQN+0-c?QMw^KNwj)V;Xo*k!zNPh3ER*^%D$xHf-#Zs`+dR;q0f@S#sDcTiER5 zuBQ6A4K%(V1flW)XoxUw$&aEP5#XnboBA4W*i*VDz=GDBNVD^ttX=NDN> z4@bIF>&;`iPu@FYC9%q~74$mCtASgk{N+v_CD>|w*5y_qdbc|rYD4S^`9+qTRG(=R zY*u$PS^9@{W56?L(*jkqXw$d6RXijrJ3^l6kFD`oG_HBCZQ9CTxV7c%QP1qQ?NHC$ z9JcLD-BKWJ%9iNHq;iRba}w!UQ&*{yb2Jg$fdVAKRm>@wWxp=>2ym}I?nq~VmyQt` zmyH#klo_LVohKms(5F(A!rHrd6uV3&k#Ai-F%z52CvRIJqn)fieII-W^p)Xy$j>z% zoNjczH!AP?xOrDqbdd? zq=JFtA3{`F@n;jj^H(Q-#e8@9SLO6~%uaXioKa&yRUpz9#!dk3yQxvq{kwnx-wom4 z>_iNZ2G(|Fcm0^5rs_Ys0sl*d_UFM527vDhEmW}or8q$Fz!Cpi9Q^cf_aahlxNSLA zQFT?{OW!R^N1AN}J_Uejw}mOhCL;;xviu$jYY;sS6nm0OpOWegT>Ja zUZ6APU=9?$fkYu#-hLD{Ud=|(HoC8=@nUYKo?qWwc>CyjH+}xF30zC_Y|z#XBoMYf zqsMo=z19>NxBaI50u#2Ndive72E93M%1CgG?`h7Fx4oO==8{nB=g_CK49%GWK9+jf zGxW>+W6`fuTb9g*j^cV_1s;P3I(Ru*(h$xbeXj}e!R>`w z5USVR8cZXqp(c!p}G z>X2R_g87XZ9W~*X+NaStza~SS(A;nroA3Ex{r-3_R%@Gz<*Zsy=R-XiV2Zr8D2j+>rFKlvqrZ}!L@cM<cuF*U$yofuD)g+!SiIl z*VE}sZY^o>hj-}x-Amz%&~0y-trntT;__3%ofbu`W!L;KF|G$q&9(ZyF`;vQe6Fve zLg(&(7VB6CK(3C%`9i1mj6?Yd^h5$%QO!^?zAEdhbl@)F!qt`Z!j&FBwvv-N;_UZ5 zuHaF0w8-f6 zjM;U>`BU+cAuzjqO&bkI6c4k*+Ha{!yq@=|YH4bni$2B_AC#=&*;B_aaiN`|`4HlW z`HtWfYT29|A==YNuO1NB=^nhu8v61A|F6$hsK*)#Xg&AX>6qlZxJdh#G!#g}LhpaI8+a1I&8pgSK(BDPeY$CE3qo9eGf%)dTr|&ML~p~OSnd;DI^AqO-9|#f^Jl}*33jvo z>FT3ESH<}#LcHSKH7R_ad-E^IDdTqI*_Zj#{L`1YzR?}6KP(1lOMyog^F}2fKR3l& zdUv|4oQzW@a-I$-TxaqiFXnqe5?j0cC}!ebO<0E5XStZn9=aYw#v((DvU?l8c-_1~ z*Wb4d4vQW0HX}Sys7jnBk9W&tm@pj-9GB}flj+7 zc=QsFmY*i_gyXnx%96Az<*Cd>G87^M@{G5m>DO1SF1T?G@Fh(UUqg2Mjy>SVmPdgEF)w3YTL{B?rPIKv36f0vRgYGC%R%PwmeNuZcEsi zzJ4iUH$qTD|0LC@#iwNf*zVPS8GQOv<(P~gw}|8icGqxMVMJz%PQinn33F;gy(u4! zj33tVk;R_BEe{nJV#D-4ZO&KE)_Ecr0y{1O5-c%_;pL9(c(9M< zioaaM0vE5wJ3Vwi&6zi)2pc8Ou1ZQfPuQ^2zMHUNfQw(%m{7oNJNCLFxr_bgKf1@y zXQA`NXD%{Vr+p0@HCInj8+_|V#z&igL7Rn1&(SdB*iYd`J58a}tT%i#=_5P}cJhQnwj-NOOqa0U|Pkm$M&fef! z&V5p5BUj+g+Srz(yyqPT#pH2`m%RzB+Q-Cno;C@aFwyL*YO&Tgs&J`@0~I_??JL^E zt@b0Zu%gyk>Lb@7OgmoxMQ%2hEBP3+MMPH6v150gENd0+&_6#){$Y@MgwW!!Fe;{I z#d>yhWb|M=^Z-O9o(5v2)Q$FJdS5<(#TlNw(G_Vl@pV54AA6RsCkoROxA!+K;l`}w z>1Sw*m6vryj`W`Ns1jq6@-XYe_L=EH5rqf~cM*M73eSt;!l8((6y8fA@~+CgnMNmE z-Je#QQ+`e*T)P79>YL+x{0-%xINy*NyD!H;;a$EMVPBF(ET#S@8C-S>_5C_F8s#5L zTS|@8S^IUh2?AzcK1?&%b*mi2k&AvQMI?;*&2nu%>v!~n7qytf3FW^>j-?|TDl4Yy z(DLJiuY<3O_~kRWg|z5+py8j=l#nuB!X89iBRGw(ayD#!;htp8mvCH(+#DyL78th( z9q)S{PoHd;&eW|0Ergg6QPCVfg9%^=%D49o-EJIGwLGscS!`wdFvQBv7WH<1>)1zy z&o1fvmY2>-d6Dvya(6$WxRf@Tdjn(-BR*Na|M~z8R@_m(&KSQc9nq7lX*9q<$~Rh= z4gLunJ05v27+Ku&wxMdoL1$*kP>PRSNX95tOhnZJ>Kb(DpdE_s*SM* zrt=J)ot-o(guAXh%3jcg)@ji(jxSNHtZVJ*n9{6;aUm0V_s~8~7iBv1qGzend%w*J zuO*E!bGA40gVy;^yW2M3BMlu1WcRfR{){#;Fo;#)p`q2Im!W(V~m_Fbq}#&Pc(&=uSdt`>Z5(7Oni18 z*e$4AFh!EqPV%8X@IU?Tq9P$%!1eW1j>n@#*<>*Iq>tD-<@mU*IgS)nHB2!*Z+o+Zvi_*8q zCVvL5TP=<#1q8(p55V9|z!s|yStsa4WY&{?Hq&YqGoK^vv_FQ|-CXnQ*Z(@_xax|e zxau0aUrNlO)8es^qq;royt1-2mh`T&|70xj^Z7!EUE-LBQIx9J#qoHi8fC6Kganut z_6TNr-%%xsGRTsgu=Fr+n2SKI+%~?XcjUEvy^ZR=W9GM=DBN&5Fxa-X03_+-DRU8i zJ5j;ehGVc7NE3!w6eKv8QwfmxFzV3rI}%O7=#$l_9n6}nikPDchH_bH!$k`|ZI%Ge z5Npy1kCD=oFwQes%cd88Q|A;{2QfHxb}y3nix_{%P)$ZFZn^3Yzvf75>7a=;w3>!V zxzVJ$ah15!ylY-+4VeJ1_Y)9;gQrv#!qT(3m7Gc4h#ZDrW2kc4X8De&V(l?d9DRh~ zpI5w81K+>`F*`S%He`&NI7j>k%HwY?U7QKsRAkD>MJ=L)+Fz9ql+)JC5=qJRe5Eg!RHZbEy)9N0Cpfd_4)}+NMIPan!)hT%o z8gXxGDkMuV5xZ7VuI?HFY(t15x86@hWb1U`b0omAR<_?OSw+62E)w`;6KQ*2|7Zt` zTvmPbvcY=hV-QV_l$Bb!R(qt(rx6w2N=J%Tm)aF8m*$nj1CxG|+6Qy4QxO|M)6vb< z$l6iQ#h}yM;H`k8KG=ParZe5Vkv9obM*{@}JOgR3X3%@HO7xYbezM^FUqj7aZ14BuO=*-Kli)FJGykF=2a_yIR1y0(gb31(>jBFbL-DPX1<%g zLOd3trxXpx%T=k)H)5|7p^rsg3w26>=x}vcs6vjPP4v7$DpgYvgL>Qv`aLAZdoY?KpQI}O2*44o=I>sSWi?*R0V&b z3EXKXIc&1|DqAJ4Xg#Wi@8kpB7Q}r>5js@! zXH51c>AGKY1$T~3jzM3^V&X-KmvzRhu?Pe)d{ZKOY-Zm7Wxy6?SICPAtOrH-FeMA{Udj_j>)+<%rBu{YB2dY*p}sa_q^QD`V`C5PbVhjJ5Vnu}^zw zSnr7Sb0E#q-hm^pI`!ABGn1QVmAPo0R`#U9(~T88 zF$$uB^{Qfz8E_8cNiDWAvY{~?u4pycI&bdmu5+zpq+8i!Jji5sjw!>K&yawoJE&f! z{lWhi^#p3dTQ5~Xzn!HHs%m#7=JNR1U3P{K8 z2JSU$-;1yMXKPn|2{f^=(gnS75@AAJ zL%-$CCCHi0&7%{sCimoHwrl9n3N*qIQj5jxTJ(%$fZ_2l%rH^$+X-rX3gugF?fxIw z+7uF5^!xw;Ky>hV6{h`Ko{>jy*2kjwAn651iGisl&71_5OQOop7;WBcTlB}VP0!IJ zeWx;U643kbSaKyBl)f-Y$FCIjT0co}%5OYi&sVv9pjpb0Gi%@meH~~VpcR!~kU7%o zJ#&!Zbz&NNgu}}^HPu7U$UGnU`P&7?0owunB>DH1oD-#)1*vbTzAH`7*+l0QBD5wn z*}BTwBybmYe;7RhYxI=TzG~^*dK*qXs8d1L|_P*5POr{cS^=zvn+1lE?pwg>gP}hZt0gA0j^+MA|HEq3VCND(j$)>ED zhX&S(5Q~?l!w__VndsZ9Sg1G?0n&FGY2seha|F(I z#f&|iDamhJQP1$bd8Vk9v2`r|TWVy=qvkA9@A#PgyyM+-=BlcY!^1P$8whpC!GS9P zmLOx-f~jtg(=I9G`;awPnnC)#dzhA8(x!<0@2}3d5VBv}G`3cs6Q*`G&yPzRXezPH zhz;JdL~4*JQqiVOa;U%g;p}SBXf-{DUh!l)`Fyq7$j;Q35{}fC!=6$yD~Xt3&)<`K z^~r7XM`vDMx`RVcOc1YmrN-}hoL8j}iyh-IXU@CvNni;ZNj(+n#X5F57$RF#&IK#G zm?Wc3N5&v0jmxI`y26*9pJ+p^r;~N<`s)ZU#fZh#Bz#ESIh1xKE{1)|GE4OXXQYzK zV!6&^{f-sd+ zL6>T}!C1E?D3Z+ktffNt6uB+xsqoC{t>^g~j@9YzB*PV|7;GD2IRtR^?Iqg$$n#ar zUNJ5g3YFev1RC1=J z%)i?xae3?-Au6uKF)u78NBC;Mr-Do7B7M7C|)`Q!)5xDh@K#t0Y`VYm7{!p6` zYW9`!!Bq9erq6;)gPL|UM%vocMyYyJNH;6##zpH%DD5qV0lr zgnwpHwFdFnbLWBRcawNu`2Tn*rxb_u z8D;2!aRhaaD7gnIWou(tIrA+%bI;t>on`(+VUJ@gIi9zlwjo-@JX0$fhWi6D@5^@d0yG| zrVJTtt`9b@6Vh`a6)qPI`_U+~602AA7C~e>ir=JKsm`_IVO79KM5SDo*bg;==L!gI zkFJe4bGQ?Q|H69})*taaLYquIvYTe2-)5;QFDyv9vNuzmov2a0F z%hoVHlw51*>FwQ`(kQ>@pMPk2>-Mr}u%9Aus!BF>{MJEQx-p^2Z1JP}PHB2H<-=H8 zSIeF3`SB^~9jzwr@nbWR%lf%bHvw~t9l|!#{G;q?>dRRHAdGU?7!T$2o|jZ(Azv0Y zZ%diK-%R)zbmnQW4!>KMe!^%ORz0C&2&_)fkhW$#F_dtgs0Ur94~6c!Dd^Ujo>uhz zY;vvqEKYT`S?{|~Q$+PmpU3B_Z+x%ybP)YU&~AA?mtr$)u1m_ZP6{2JHpnGz(UnbH zM~Xf{d-F*MvLuK3;*x6dcettcI_FRt5w4>hQ-P>3lMVG1iC^Fsz|a>t3ccdWJ?GaB z3MAay&J*&Kw#8x&L=j0QX*T3t(Wmwe4;>j}!f^2za@u{RM8Os8@6t>v^0VnG&Nh8| zMQNhGYa>0(WNvZ&OCYYsIi%)3M1EZkW=vBVp>Yol;*@7grq|)lFS+M>CwhNOf7jlz z*|y>G2utd!#drDYt0^_I4=KXU5VbQz>IlErGG&Lnd*9i*oB$S6jd=Y4qVWX_ zju~JddhY{~g`}k1b`kFfnvqtnW~e$tbwxT~RgkO+9cCnQW^u;1lQ6<+YV< z4YuLF;k{TVeAInF49u+RZ`}&wyiuuA-~3Q05>m!~`^8+knjQ(Bmm+) z_OUN0)x}Ew!2a#P4Xd3nM|WBq-B$TNTlJ{Oh2zgquEfx})hbMm@dqN7ue;|@K&01) zTQ)bEqG)FJcK8&FqhcymqdaxVoYXo;W7=liNlE>wXME2%eoBXwdu|vdYQMY;f4{dn zN$Tem_6~SBUpfj2NY_wpQe^C~tkw?uY0dpU452wtq6nLe6o<82LnlHNfgvB*yF}n` zC-caO03M~ru&EATI?J(NB?A@VWE|pFn9kr-<9HF3!eI-n z4}sc*l9ZNV>IZ#cAJvbG9l8+8{*Af$xj(J;5GT9=cq!}Zt3%}6gw@scsL(6z2l*bkn1hep1UVO9R7Cca*C98F5CC_yTbEUqc8 z3E6p6_eNHUS({1QX{Ym|kX>FgDb5V%ZRA_oMWKQGF%q12U9U!Y`+2w2mefXp{Xnb8 z>!Fjw6Sd2SDuR>3(>Ho2zUQHVMLh2(2$<*y!7^oKi))5PiMjfbYE3xQ zhr-4fJYPJ*C*F>8e=wMR?D#?_2^fEJn)w~gNFYomK*ONDHD&E-qqcSsWe=T{F#*_O z=(RpkrHK@fIKu3=ZE#csvE8{Ox=sfX7t0&g$4t6t8dp~HtZx!JBQi2Yi%pm6$=rzd2Kc3#8QvjjEhOF1#|mS+_tuwMes1YCt4ppL z4)q$-9e|ZRhfMjUeuzu9(c=swtZC=or$n5-ts3}JebA$lHzSR{h*)v}ayEwW`-LR& zds&symBa53`8Q0SrABl7ybaK7noWUWo25iL$qt{T6b;9Qc;D=qHpgH7o`B0!*!Yjp z%P;l3&Bg3}W|-=L*fq9Z>%1AYKjGiWC~494%N%R9+*`d_RqlRuUCzw|3;iiLZ5Bt zGC+PVX~{0g+h+q$aH4-Y#ehwC=y@s|);<#fGmk6UvNtr*al;a=;w`%Ia5O-V2JB$@oN;S3Rp67U9`;>|o zc`|ik(VqEi@X(a~s`An#apws!(fy@qd^qX(dV?Uh`Nv~v(4%(jm2-vQIJUz!L%u7L z5HakX13FynovJq?tRV!rH)Ce2LrIwnAYZ|O{*XoXB%SSmLY{$@{e(xW$*&u*Y7qn0 z{y9v^!w*MOvtrtzxblu}bmY`)pw0|hc{1F19+?z8!fK^21`k5KaF=)@mSV=S9aCRN zJa$Cz_ZdJ#6zNsnRR|+g7Gi&a&SO=2RzVNUsAKPI0!ig;4)zt?CLZJAV8zia##jVm z@I0Zgj1O@jwG5!8L|;m8qeRE4>kaUK{W?#R+C1RCsoR_OYt`?qSi4L1oLlVk(+|lo z7Bbp?t$mLcnQx+U)MuWV?Pi?olTGBBH}Fv|1Q?K(=$wPS7m{fTbDQ7a|GysOWEti!b{$ z#vS=LzM}gv`*(wTFx}49%?B=pXM@KEMce9wRHl!Nky#I3%gelDZZ0>bbRgaI?dF z;CnCb$2{5pB$rSi(0|}KcLA zg6JGKi1fPlGy2yQTlNB1t$JEV&T1O!9i+^ERm0Br~y^yl>d ztq6cX;6NTQ6a+_^@Bp|F060p(1pz_10T7f4903J_5L_S#0FHnIK@b?q4+y}`jp`N5 z1G}3&*c~;7YJyQxD3Axl1-awVxOh|dok zsF1*1s6qaV4IB&xB2cLL9fk%1Kv7p<2p4J@!cYs6hX;<*h47&Ix?9(}s9k^>Di0VH zGaR)PQEO3D{g2!CkM;L2^!|T?*B~(1zp`t(O8vG0pr_4;&jcGnLX&920%Hh9Bq=Wx zEQH=9Gm5cwaV^KRR!-7}sYt&bbaQcSwrXX;%im>M@SS+63Jq%*jm&rWs3Eo}x+dpo zz>p#*i@n&oX|;3?{P-z~@HpQVgR?(yUubp%F5V)O%8}oS+%g>9g*gJz) zlRQS^F`M~GaO#1hRyK2+8G%Cvr8N#~vq;^>__JCW<0a8DBz!C)?;+cphKR)kMFL11{`XkL2P+=^u%zt@ zE9vTx4+2{cdUA0vLhk3<)8Z9z_z`GezO;S0`=S649bsr3`)J^+Uc|K2#|UmfETfb? zzPmKsjuoqSaA#Ep*mqt2ARff2AM@mRL}2Rv_~TEFQHd2!HuOL9 z0Egs1(xR~eDmkID28xXQBO5897Kw_Ts;$M{qYVJ?A8_a23CqpV#1snz0K>3A|9k=9 zFc<^|Fa`Wm21bFPcQ1hLKV)2B2x^W0y9~9~QQrSkhT5e6DdU2pw(Gy?p*AyWPyM?L z1VU}J{~?2-vdVwxaY4BM(;w*m6^24_?d(uc>fIJbCH6mZ@!f{LI~$yk29C%-CK`-NR1hpi JMlpHu{{vm8=|=zn literal 0 HcmV?d00001 diff --git a/tests/workloads/mem_levels_vL1d_LDS/MI200/empirRoof_gpu-0_int8_fp16.pdf b/tests/workloads/mem_levels_vL1d_LDS/MI200/empirRoof_gpu-0_int8_fp16.pdf new file mode 100644 index 0000000000000000000000000000000000000000..41c26532644276c9cf60d12ff1c71e9b4a05a335 GIT binary patch literal 12907 zcmb80byQnx)99Gg}-H5k4sw zO9Tq(0$`W2c0oGWxH)j(@Ts{VE!@m4(Lzl-8w4NP7T^Gfqrdn=*#_w-jX+rf*rkQQ zKrlZL0u%rPp#oqK7ZAvX{zL02BQ5@S6)`a!OGk^_5FmetVvYcSaQGyZ0emV*7YBs> z-%9*{D@jS*D*dVYR0;sZ;d`q1$Gh&WT=^-0ABRs<0)TRHv;3cZLI0n8f&cJ@e*a&6 z3H*Qf`oF~m|J#?WjXesTeLh)xbe^Rx&5;)9y*#yav_e?}Kv1B7m>9qnh5p?fa6CWk z7)(1Z!-)JQbT{f>)G-IQ;i^5demNk9q|Ts^bgyMkzBhaQ>xl;&MM2Yg&iXMAT;|LghZ3vKEr1>4-{-o@!+4EHgQuSfDjDs2_?ONfsC2^9DJ*7$m znK4!OyB~3+_IxghIWtk_Zd&SthFGLqQl#n}k2{+2i#K9WygP<4w1fri)0I?$Jvz&A4weM9+EFf(;E#NSAp*_o4nrVR^|C5h&coxUIF9MYoR zNE7p(6Y_|hJ>J_z)~g>2BeFPHjBQsMA_JsZ6H(G*LhTl(YOPn3m4W61~5hq^}UMng|}k7X8iGz5%L$DNd?z0{0Y}aeH9%bh*iF6Z%5;l9OG3 zaiLzS?8-o837%fF{0e9m4Jnn@I!fpNO}i=QpR+AaT>2yUsj7Hgm`;qm-(|I&`8^Nm zbyuv(#||P%nwL|wJ}OR3A?!mpZO#;U=a?Vw=rdLhrf%mudVK%t3~wP5ErT!J35uyc zM1gMdy9{lv;Ny;8+rfjfJA9pb$yiC<^|tR)Qxdcaq?lYWnM{V10PDZ)OI|=VH;-qG zased(mX1N@O-8Or_eCw6r(Ez?uk|vl&9SX0WK-`|w-U#)QHWgN1glkrw2gN;|sQWJNP3G zJIfT$dsqJL!0glyl``$^?g~e%8k^}(2uyphn)oa*iwpC{hT7&sbEM=(H+W)TGc*kT z;av+TJu~S6N0%Ef#@pxX%Oln)1y{3iRrT22ty9lExn?X5qecWRtalez4#b>H@Zu(q zO9rjk4IQ+T88fmTF*=>(S3Z(@d6&U<9IRK2^VQRWwn^e=tU=5<+oxmJ%v7x^#L6)9 ziI78+Te+6ZuZJ2BaC0zd`^c?SjlKMAG_eeF=wo^1(;7(T@46y7Ehs};2ikh$5X!CP znGSldVa1f7;%VVxbx3hE+#V=a>}93*YYA{oyZ7X=Po2(VLxm)50zNnL@pvM_W1Y2r z48pjbF&>#V4U^2ZjDUP!HEKU#)~BBfza?gx-EFkH<9pp+6^+{`HusJS*_O;9lY-@p#&_<0+!J)xDGdg#7#5%PB*(i})aex4LW=Rv6X7H1gl| z0<@oT{Ys6>{`|0}_RBH(Wb@*ePMXrW@WyAZGHD!h1Az`VcQ5K~J_$%9>8fTIImGrR zmj%H5Yb?LsU{WK>%DoOorc(&JCn)QWa>tc8T*zctE8j9OZy7UNzAmgMe1W&-+`9%; z`B7QTDZM%mj=R|Gsh=_bcn(j!$mLN*R%|qGVGA?fF;d}u)$HFcW}@6n6>;pO%-oyp z;pH5-N8xbZY$VNY9PkwUKm@F5aou?{?eTCUTzUgEZ2MX*$6Ts8_?h-QUawcsU;9keH$d%j0``=3YC``X7X5M0_#~=__?+`n?qYwEwBsmDzoo0Wazn(|`&D6<+i6 zWAhU}_XVor+d=tPxBqKog8!ZrT3$|;06sN@6?#BuSh^zJT+A(90qC)g9^vMimMDPX zAJdyp%hD4C;8SowD@y+LDfQQ@=Vo(6h2^T{F|QMVSdFaYdN*{xLB(!vHIiSz^*0?|S!7|II*10VvoALyl| z&^DHiC|AJkyhHobL{DmSlp4b24v*d2Guxop#L%kAKCTp?V`#L7q{X>o>3iEmhL+=Y8IksGp zqduiRtYPK01S%P zp`JJ@F+`ysnS8$AdU>Mw=7~fIWgqc-m6Yg|^|Qm;bi}B>{hlB`SHGd#9?8fVpJ{WEg7IUaF8UZI@Le_Y7#_HzvXs0|2P zy`H?W|61Hy?~oq(>lLax^!TNqCeHchbzr$2n4xk(K|aWLeAMuOPjxsedZ=fDIp|1$ zc-AWGHIK|!2IPTYmfwTsvr+YrqxU@V&dTU*zk03TocO;a9M%;&l#?Sui~%!A6Jz-jfduz-?eA&GmFs^ zOZiHNaGhMXXDKq9p7eK5q_v`y*S)(|ooEMaQN_w|mxQlHQHA$^QV`%qg(PP#S`iWA zFARhP7f>$9`O2TjZaDp>D7n^dXS!EM{;T^=sgy7B4!!IL;xBSU?{OBq+fN?u+l9zs z?yI*a?M#Z`P0)_21bM-iito?`o?hRf3-v5c{yO)ybsl6YTftz4rRMm+VUlcRv&TTDjwo z=WKF^f+3CMOBm5Q=Du0G=KWLW_R)KFkAEHA;gt|!dXcbUis#pjN_dmN=s(FHvZ!zF zVeU_K_~DDcY9yoR(tQpf=N<1*P$;VV z$$n2aeQa>7XOCn@Pbw`j3y66JB%sZ=;cCp`4l5`t`2)jh?xst5;JX}oF1imL& zNlPBAu>v7^*LniI@}6}Xvju^0pNP;N0{aOOvR6#4ySRp+gijaWUI$(RT#QPFH)NO> zJ?@R9N4U-fp~A(fWS6~ToOd_jLq?V5B|I4tvym;0kqHd)Crt)rMmc6wrEs|;+s6I* zk&?!vJu&|9@6j=dCTu?4&l_-+&XUJdna6(K(N|eR45S<}^H|N6J5tn34n7+KyO12q zzan5M&{OK}%HPwqVHFHlFI`$GUW!1_-T}&6oiz$6<&|naL94y6qG9uMtdN3 z?;|rEQvq}uN<%S{E{~f7wek~oqq$c^KD-fKVJu}ttuYq>gyo4xmU61(L0o1hh=J(? zo1@DVH5axXn}*kE5?chLmMb(~ILxp_`^@#ovX~XCN<6SWs8Ex$PwsravtDKSR5?ej zbuy&zRh4wH)RuFJ!juOyDrU%L6NjTS4$?!AtK+<7=1j&=VSJ=Kl~dd`D|(->)&BGq zZ-QCw?8q~XVcxsl3}o;VR*-B@9&VIJ)Z6x-_JOfdCy~e;npx%#7d&5yOT8jzgK1V{ zy!&w`8dDUcd;^yMlJ7UMIz|qMk(eqOR~?ojsjF2ImAkho(X#-qgt>ZO`ZM(>^r7A)G2I<&jj zY}#wOM2b%BhSkWeE9K-8F&gk5aHg&%(66&&*SX{0M3He2n6Wlp>a2294x5b=JFzp% zS5J!3>X60?)UCOj{f3jH( zI`O*a@}$y!X(Wks^k>8FqJDsjd2iF6OP?`QDmVut{CkmdPkysd%4JjcvY9n!xaGNM zNz2cup)1#qlX;ajxEc=)2$--LDy{*!Qxb*B+cZT|_>Oju>Wqmq>#nscOv80k>=R;a z@T#V13OEQF!#nbb8pGQ=Ly$GLhgCyM^HoD8c^LjX=WhPtR4aJ?$?2`WR1_+?qSm%h zzLnh1?LK+U=d>#o95kjX1G29d1(mL8& zQz-OmXG(Sh!0z90bV4mp-q!TlG;0a>#*JoP+6b*03w^TeqAPH6+F4k0^>MoQiDg7> zWm383bh)jS3Gm$^fyFGrl4JJxgI`enR6T(o0~0JxeT>%ZKFi2BxVSS;u$UEo7>Ixl z_G3np5P1hD`~FOv9cB|BP+p2}$%8tkh~^NEtf^8mS@!5RbmerdoDo|hgpS|{4R|u$ zi4oW|iNfSDXd*nJy*zhOi7CFpBW9NP*gkqkigm<0+T^~q!F!bo&|6-IJIcyYMk+FS zL@3v?T0A+>$F&I0X4F!W9KEpcvE3HUk@(}52CJd8hbZIuB$8y0lQ9G!oVCJ;k}44ds&OfqE)7NsRHjRwJ60N{>t58|M|fJE&s0V-h>PsTcNg zaCGvGT})1|vM+(H*)lBIO^+RAn&OkLCvZQ4&R#q;q^P_4+g;q{%1gN}ES+ zg1H-sD!**hyX93^IHNvR2N_NV1#Z_Io}5jP&ZR}24fbavCw686@?H9l^JM8$H9gH{ zbiW@xI2FOSdvYkx+uR%!i)!6AwqFM?zU8RfVGG>>4IMy!JTtIs)mb4AjM8P~jK2i+nlO z^FdLue^5{B97+`)7LquwHhMA2Q_$!I9q=Ocu*Th0qtl>MU_CX@bxLjePEKi3;;J*< zJ5Zd=4JsSo3BhsJB%6`0=1{L8_daZ%bgT@9IU6{I+2bd4+$CpwTpKL#X)gjO=FZ@{ z3`>e*iW4we5sM)q}^`^zOb87F4l&M;h=~;B`K_7pREM5S{Iqlr>Occ|Q zgK$6jc&FRalLPwQp|vNzCuBD|5Ve?%L3Tu@dp1nDO;o+xA|T)1>dP12%%(`^C*l}y zWsQe_7^pz4=@>Un`%5P?D#|jsj+QNivf4x|Pqst{_a67<-&=H{_bL}5vy~6el5+SO zo>{@~EkI*;b%3{8QgBdTyvE{^RcBc&c~&~ILLGJzBz)DZ7VG#~gLbTBs)E zE_1QLEQfZ?!86rr2jhL)^ue77g13wykYm+HpuB&u>iOH7@0omG@e#;Z^kMKdG4eB6 ztsuGDF7>_B&b#@bCjMFX2l{Hd@&<&_Q>84RRBKE__8`7DNV+%PBPU*Vrxogofal&VD+a;z|q$TNbB?e6&RuAu1t@ZOxy8T=|a8TLn$(uW)-X$F2ns~6W zv+EJ1cwfVI6q2I20(8Z3re+Q%zq?p(!$v@O68HfSUjBmoEUVh;Uha0;2>;fi>3)nz zs$(vuHCcKm#Iy7R%I_|I?yQY2Rb?1*h2_%O2!c`kBYfyf6fQU$SkES*TcEz3fw zW!?fwpcVBLMaSg!i?NVC+vkQWlcd1r>KB%u#y@l69W02JG`%X}v~L99;u0&IpEgNH zWW*7v7kG$R&F>X{DjqG1Fl%?%W5|8;hSFg}B-wzK|sUo<{y#qeW2vxR25$ z!iWJG7xyzm%i_{_rA{#F0W~u_FIDd+kMVfKLM5t{GJ9pW9(RY60$aR zceXjp0Gp%`S8HO1!Awsl0@AaX7R*UEZ`vx&j}(N@FvecU=|FRegfP4Te4F8(uwT!5 z3zyT2D%2 zcEa`QOU9eG6C+>wKgfRjDtvn1H>^Avh3Tz#RI#(JW{{oQ1{j&3e`}>iBNMDVwj55Z zx+LBRe>>=|Im~OzbACcy!u#GX!!B!^C80RAhZ=TIN`ZrTRea(QngT0XY}yo_c<48A z*65xZ-T2<_#(oJCNMIEMtltOz<*VWYk>vK>gyK3y*7Zm5AXV!?ed90j^ z`jYoxJ;SFFUhQc7X1C+9)NHM6Hc2@%##ZiG6k;%Outt?y%`AN5J--iP^yO0D6Vn>n zmQ3>aJz@;H{6{+cG(UnxuobXRSTo8-mM9k^L|RCJY{LYEJovmKQ0H|nTzApqRnt?e z%aM2Vif@zGKI@s*6m0Z)*mSFo-mva@7U>Q}pT*>Pwvs#%JNmWWqp(NV;M1}Ep8MdH zyKv2kr#YL*69;7x4VMEyPlA#FWmCWB4i16Hw7CoykL;CC_W_xO%?D{M%8@?(g$S!tgR}s;59GRxaaAPgX(oa#Z|vDXW0ueWKQgC_;qXU0boN1V6L#`J4S5JTGg41XP&8*zHZm@PD!Ov4-YxqFFS~o{2 zNJvlGI~b(Mw=(?9J8p>73_9fFVx$*J_#^7_GqqYI-J8T$g-At74A%3ZCGK){iF3JZ zZHa9{-6i!a7&~h`A@(i&Mh@@qkz&Y_OY6ur(|fUK(8*(r1lniVJ$p5yosgpnMrm6` z>7&R~R+GsP-Dy0JL&pgcI)enB&7r7Vg$n9cUu+%~LFUr<&#r<`wXb2y)@RXMwm$~R zQntA5TTio*CmR(lO1e`ig&QZkE9p>sk-C7eeImsC6fd4?u1I(( zU48<_J@Ud>{h!qz!#Nv7z#1QB8ljM)0?PnrhjQU>F0|dwHXzmFCSxAr9NXHiXB=hj z!&$w4Zf=`p{XSRl>EUz0bfsJ0Fl~wD+bXxd*w6Isp`Ns_D~Tq^_U@Bjk+0?-feWm_ zV@fNIO(hTaCSUfEBfdFcv@o zm#cEHl)ciOXLRW&s;U3ZR*!5Dqo%^JrfB{2B%PYg$@#T%IPI}s1BZM3tCSj>ibLtp zg7atOLnJHGe&l^tn!jJ$2Y!x?>r>sBsN(d>_7`@2mQxC3>O4qgFxlc};|vvQv7uT? z>_yaT@s_D`qEen^I}(cU(T_CcUdVgkmwth6zI~J?nu2v~T`1u?5xkwa*EoLlGn1?=wr~0TjFjSL~H#X<+dvD%T z8`u67<7rUzGI$ARX}nY0{9JS9tgZ%r-}cQ%+|rca%epeo)m)0L8Rkl+LIwg>CLN^> zg1F;93yY}rs`e|I)S9iYRZVfKy&S95sB0{zApui!2CS<;(}ir*yByaUFeP%&=C?|=TQ+!jxxd%Uf(P2%WPJG_EoTd17C^?{o^~T>9}-Mt%zvi+ z-9>=M#VDg#QL1NZ&#n^|F7wgMwIX-Yz@DpyLa?x{^wkffUx0I;()U*Ui({SA`C8-^ z+15fr*=5j;_>R-{NGNGSv;X=I5_ag}NqR#!pho`*rZUxN3Dd=N?kj;$HL3Bu$hBZ{_Q|j1mb+)*bRo-N090)P^EUQ_{ZZ7l=#k5|zg9E=id3{%(XuyG%$cSf2_JGx57ZWQeXCn!6;5O} zc!ZiD&(*9X#(o%PF{AjOV9PDnK^3>KqUArsqam|}(;F~1Imq1Dl?1Kdr#t zp$VN8gSJ-Y2^q{*(M3v5>-mFe50H{5Bi{l8TW)AvGVM}&$UBZgvj?P!U+?LZOFVuh z^`I_SUdmUa^~<(-eY&+6I(o*JEX5yk3wTp=)7iEijs}Y zF1Akv=m(#qHKKmUHeENV`dyn`OV})252ivOS5jF##%a9szU;7LYlEpe^)|5YcwKL< z;js-eY5%;_Kejd_-n{==)NdWnz)72?=BLoCcPv@8g4~jQ(5^_5y6~EoeCdlzjYdE6 zxi6G6s;6&MY+AV{H}4s=ClGS^?o_)@_x7&vT!z0L-#Um&sqyc2;oP`Waj+wTE9yj0 zF`|7f?B@NvoV3VRpzxI*k2_aI@(wG6m@rHqTFBZsoc}Q;9D^FvYq_7?p@*zWR4$ab zn^mi*ldb%@OcxS7wo$DceRpW>^WqOGs!v#R{90ByvjB~Xn>LJCt zc+UuQr21j5#exGO(oMRwHgw3xWrJ#c{VZ$0p9d>OVrAQd4c?6tZJEJ(ScCIbvPT~| zV%K)Yz`v7}t;CV;)2(VQzjOZR=}MtQQ8Y0ZmNU#B&&|@;G?vzx_Hk}aEM9Ef;)1qa z^{SuHzlZOFtYxrFRRB+84@6jjS8=|RWbuf$qf`7%EQ1w?IZFTh0{^7Q{GIvJW$xu- z%46T;p^pWlJfkIo$Bb9m@p2`r7P*Le=lX&fBS(%}F^7D9on)9kOyA?NN8+);v4P#s zfSUB$+8=ot2R-Cd*DrkmWGaktCG_=(;q%~NtBTw*RBOuUoR|IR!pKt_i#`lb zy^DgEj;!yQ+gr>0zKisNcTKNr(|A(HuaR@t$Oi43vw+F z*=78M+k6kt3D{nbB$-ZIuyI@r&CHxf$s5KTf0lmh^b^5hdclJmmE3KA9C$p9%P8E9 z7?(RWDV`sXaAWI1sPh>!)3&rp;J#ax2IHD_P+kuR{a$f*pr~YsVUD(G&uOCfHMkU! zcd2;h`*t3GqucYB9cj;tl*FfRFn}yybL8%X-LQM$KdUP+X~6Ddj)mXXBff#Nc|>to zVDzx)ThLL456P(&>gx$$rY|MXyeHyQV3<|l)JTh1)nCap?DRywYapG*>6WAsOnoXN zwr1OMo%odG6J<0gmofR3Xgkv5qqz^mnjl=4Hz_pMr-$f+6}WVj#UnBpU9y?Z&agus;2rpKJAxkJd~s(1_3Q zut=l3$4RdaRl595XrAEe4vkG|?L4_TwYexdrXCJB`(8;BFzrS#pmLf==&ulHr@deG z(0|D(uI=V@K@Rsa8>jSiAvn&X`-xMX(ZhLN2~CLa1m3*M=|?`_RDuM!Z`?f!YPmj& zq6}hTSi~D#Q`R1euKO273G#{-zW1=7JqnId-*?3Mu;AodZ!EU^ruJoK zU|R~!+`_(4usO|j`yzYr1pK=zymhghc1zLEg*JFf_kDLYjfrS1PmA{h6P_r7t6}sr z<8kd*hL$5adYYAeMKYR&eQ+=p0iW|^IwqgNvw4&B&wPZ(yUyJ{e&tP9OZ(+~z2Px^;F#_vfAu09;5JY(o zhHBCNqu_Au=Uz;~oDi+0j9$*k@;OH22HrN$z6GS%&_~*&3*jJB^Z6L7m?w%eZNG=? zhuUI7+WuE6f+AhF1YK9XFzuh`9_?AhUtCNVe;dN{6Fge{)|jBVJB!!kJ+)$@vXS&W)@KSZ zfF+s*7{lYJrCfbPP)o@m*u&12!q9^?+eo>x3)^`9qLd?YvV)CnO(Nkz@Jt6LHo*qX zUX1Yk-CtrGE0EsQ;suB#O|TvTNGC*AESq*=;JzwEngLhci^v8;K=IoELl$N0C<7iY zf=2QX@PLJ^mEkew!{ETMpcpA4OiXttr*fvUV^ld0h8>+AJW=^;Wl|8fPs+=$-4fM- zfkAYQn}Qo3GFAd#g_GF6z%3_-1G%dl#T~@q-wcv#eesnqZx*GlO-c9ZpG4i@&ZNFH z|8GVIjlBE^cybHNNL#v^yVy9PdD}nX85M*B8sCw&v_#2DK?pBD zQ~-^>K)}5GU=SRRCU*ga&bih7)8g+fqrKhIIcO>u z;c9uS@b5dY>j;eAkb<-pQcgiy8R3KmmMqW-ut9nKA=dPAMekn0 z@j3FALDI0avO!}~UI2CpG*@hihLBZVEG%7Y9IXKC|1d)fHQk(?>@6K`^N1#PaQJj@ zDJ4S~5XcJ@6oB1QOh5nxB)|(7009M!Z+ChNF9`y9K@gY#dgm~JAp{2eGyQ)n0w53= zuONsY2t%6)0>E$p3@rddfcydg2-*Y&=jR2&!9WNA28ZziAyBj*AV5F>y(&l$dYe7y zEgyxx1fiw;yn;Y5p%t23>91u1c0M|Dgi;T;4O(I07pxKf)MnY zKnO1oEbxaV5FG(OuK)}RgBSzQ`!a+AZ(YDZ|1kXL*8nKLATJ!q54%O7U?3K~PMo0Y$K zuKx|lg7CxtmB%uU9&!u<;&twc$V5zMGKy!EyoxkvP^3AQGxxcZoJe5viv8PtWJ~)S z9V(KHd5Y;X8aD1C&D_S&*Yxg@(5J;apDKX_0$hQ{3sakbw@F(opNRY|=Mw>_p5G!W z-*g*jUy4|9U!sbZEv$}FYHbhGg7#-Q%Tt>x^Y$v;jppB-y{0>A_f&iIRAQU63AR?U z8TdM}rXbdE@1xhU3mvg()m?HXxfNLg9NAI%^6+NKNY|4`+)oqRIt-Z^LKL$^HKG}Ev77^&uf-e$Jd0MN-J92v#~K*;0vAVi*^>>C68(S)!bk80~2kmMJgRfm{7F zw~EP41w&J)&fzo79k-uD^YbwmPOAe30=l1{!quMisWFp4opMbsqVDbUq6Ny8oaX0~+)Dqv2?vt3wN^ z?Pzn$#{)orkcxlzBu^L1=Quz#E{_BJ=L-OXLLpGVbHG1kAT-r@`vN%rLk1GOJyriM zLl-&P`+v&N=kPyeVAy}!qC2SIf2{#TpRoV3 z!TvvV{om~3{acr$nI!@leJ)8$WSqr~3~UUMzQ`L{n;=X9AP9^{NC@D7K;AbiOqY~B z&3WrpD4yqx`euW7J*B-rNe1)i<7Cf8=nG-Mp0yGWYUAzu3=>3UuSV3WMiZLme58@e z%HbfHeQ#$kZ~8BFi=%z{qX{X{+Fbs|`hg@DpX`{l908@Gu9t<^RoN}pjKF?W>-7zG zY{AsUOX|7hf%uW3CfwHBo0m3hn)8@A8dsAZUB46*5@J*=stDUneiW2Gj~&7en6&>w ztr(Y=7ZKJ(DIZ+5kBX}kXq9fKf4-MKG!l|0-u3u%NTImpjZi^vcj2bJ*5ZVYWu##f zi8gVs=r-AW6_IvvUDu9lXIw~`R9yha%Da;M)RH%q#?&frzU}HWH<(r}1eI;3&IT3# z=+t>GY6%7H`Gy2t09RS|CJC9NF^>Ho6v1aA)-qlNdZrJj%C-DF^VLxuZ{An2FV(}< zmsgDY)#au7O$^^}MZlQNMj-FmBl?%UbY#|FLeyZt7+s~$<`}mO^(du8Rq#n_hq60d zp$+bqi-M1NXN0^S$=sgGSoy6THC$1dbmQB8U#|Z=?PjqM!Fx(&QtC@R*CU*C5wQa_ zF$R~QVCs11sxtRycO;QvN`g)89-^cm?AwUBQKBN_d^;mfa|TQ+6VA2h=0v>LW;+G19%CD{gEyFP_6hBH7o@0zY5`EjKf0xkyj1JxK z6_wPeUpD$H(R88adV!pps&|b3U<%%zS$ZCm=e;7VY+moR%mqRsNeje*VER=+QsbC* zJD!FEt{^|@<=|N6%l!O3rI&%y0ua_(l%aw+17{$Q%}EIDieoox3ZN}SS& zo3EAe3LC$$uK3maRP_y*)cMCTn0J%|d{PC}DtL0gmwKyb8F5L^J~7y~v&I-_Op(3Z zMeRuzA7hG_aJoQ6kh zBo9*`smXmweSwj<$zkBw=YO3Vb-GO?9bg z#f(J9UByWK?q>S2>saa3@M#e|U4GTrj8>-{Op(@^Ny?|)&gW)y%K6!91-~qMiszo! zJ2iJN_}xlQ{g~A(xV(j?xW=!{DHS=v%P1HyzZ{DeS?;D0zEaAvzqs*3jr)#^hS8~M z?fH;T4G}k(YuLQYw(0RH-H6N1*~eZ5Tg*wr;9_9&RrgNHZF<38vDir1%*6Kk@mjw5 zpy$kEIWM75H_L?{ZYTTUGyIjVw|tdt<5G*qcJ5m1mgTg*^Q~F7U)j(ho1Mm|!{5x| zGcV6)-}23-pHJXUuuSGFWH}t)Ef#2NtowqjXP2yllB^@Uto@FxS@;%2pYews*xt3zcGh;x_V-U3 zUQ`Wr%oD7%FZHMPEteg)H0Bm)%&{fGYnIeN1*t;3N^VYpZuxq;jWwo*rF}-eA&VvT zt-TZAdcN#x-!Wm5kV zjka0V9B=JuChNIcP-&O5zjPZzotAzRL*1Q+zWa_rv&|6Vtr4HBzH;d7=agnUOvK#8 zLsVL^@n~Lp!G%<{p~bstL(=ZMn;k)(xcnpcgq{9NU+Dxgbi;Zm`pLoF&G4Bm`DsQy@?B6!?!9Butc7 zC`Uo0C!#H41PaCn3=Xwo<5CYxf`p);lH3+4hs9(0x76fR1v3@4tjy)qgD*1tcx}z& zsRv0fj6{cad)9Rs-^l6T&)UBR#$Qtx{P(a?b+t7DaJ|wqLCzRuBL^Etdjlf}0CH!5 z+yxk@7$E>!e{2A_RE=B^04^CTB%|nGpJIP~%4lP9Nw^@SR1o+30;H%EH{gD*D`Rp= z@c{0J_x%|Ja6fwQ&tQQ2!KsX#?_82L)`)uvNhkpNC+(i9U}R{fCu-vY&;lZf5HN%j z1O{-!?mv)Ai6Lc-tPu`?`;m#%r-B^z28dUB_J0tOJAyw?0r0;T`OD|~%fB`~fBWok zug(!^19I~qXJ+UC(7F$evi9G5574~{|0XA<}8*MtFd;W96d669;Fi<-+sM zP55B8q@~T`03t9_on~eQ&Gf}%OQRRPJ|A+k-Ru62>iddr(NWMv_jQ}PO4DGE8--|0 z8ZNeiqUX&Fj2J&FF>s{1N1>17)8Z4Q3a=;gs$t2HPBBIaCkF9&AICIZpk9AXcr_!T z{ujPk5Y6WbZ_`77B&gM{gV5nvxZaXXG!SDaQkyY+WXR$D;ex9N0xjJ+DG(;lWf4v| zUI&|AWmHT&n!LKSeLijH#kU$%xN5%|&%o7vo_TrmCFXlRX3lCqk7(4e-olCDe$3HW z_Wmu-j>5O!^6iryWE|;{k-jx|uLQUfgjzG2*3+NN>(Yr63t*UiI!P5^Xln{)ayv%7 z@;8j4lFWj0rB(Pb^R6if$xWtzasI8jgV29~OLuoBHN?ALa<`~>NHZ6_!{O0G>byYh zD&=`?HQ0z}UrlKjp`|@99cB-U5)Cz^VPP2gWYXu56IDV-(JNUMvP&n`+q33y{QSxf zY@WBwla@E0hIlZPXJ96jDxaP+u{Ci@rYQp(*G5naiVEkYPaJG=g@U-TOpe%N&kRvC zpcDhgvxevN$-`;JBNeiBk$d{TzTw9OA&B0+3CbnMDkI8p66K9+XAK*ySL6oPv;XRuASF|5h(#0?{rB4kar0FOUxexUC}5mAI{H4d%{}On(>YZyM@?M z**q%+{Egh+3DT`OOw(Mm5=qf|@p>;D<4$K@!_-njFQ_rTx1k>$KJa>G_xeGEr~tcn z&$}hdS}x4FQ7nvr)X&4Ydmu|Ec`JwG#+aC+Rt;lEmOuLHgmgeQ^rfBP)GA* zv(Iyss`G0G$)Bg7FAb7WoNFT$4hpP3y`N|@Pu{2;q9GD=m}zM%xFtrt27x6{Colyh z1;)@kh{G=zsY5mH(CMgJ-NkR)G^NB58-efUO2T=G+^Ln^xg=_2_HM;3Y+@c=iLn6J zQg3Juc41)pEaxA63sH1g&fYc=F0|YN?p=i9r7yu8R& zL+s8PKnp(W^1-L3dLbE2NxOCDS2adDLpDQLY8P z0oJ@3@IxNTxwDhD1rZH+7Kux|7j;9IeMDTNJuWryYC2d+|%pWj5o--N}T^5i~t&tYK8* z1Zjkkzn@Z83y;SJ@ffaptlI9%@D4u(=jSqHi0nnSE%puoa@?82;b>cA5e~xPC+~{m zLhknJ-D7_*MC3(l+CPeL?sck4v;L~tTI9$iO;k)1(kI{SkdT%k_r|^XbL?BX{7NG- z_``VyQS?td&2qi@1qU-`#Is=rh+LdGwQN9>Pwv8ar*bJmf=_}^&TpKBMT#}YtU_rx z?z8?D=0T?Qb2@8fIj&ElRk*EwJiLIjxWTnYDIfRNz{9kN^~Wqs$ujukD;X*>AU1v6 z)zs``me8A>SN2T3ER7%1B)8AUB-YqnspzL8EHg|Z%L&&=s-9G7fQnSe2c)heRy6V} z?)a3M^{mCue5>i3114AB8caFR*Tjz$^+1$ExlJO6WJ^~@yH?mm^|iM2<}ymUrv$Mh z+IcQRIpg$mt(1k8_v0U|eX^%?Pus zb4>ZLMG8L3%z|aB=B514*Yfh39PUTu?-grJzKf4=Pn+mB2^u_KQb-VT6Xeh{rR(78 zx>*JhI8MKBmR*)74OX^|C~|l8|s~ zx0-n*y4E<_-&>nT#I5@5`gVmfB4#j}@?4RP_`C z1nHq^xz07t#uB+$BphW$B^uSQE8h>f>ojyU>Hbcmx>|WuYV+j^y6T}ab@g2+L~<}c zv+G^_$C}3*J9f9{^&)2NPWe7&`uwvK{8dA|h7v|oD-t2k+))nfma!K1ehr+qu&Hl0 z@tRY$dzD|^-zSgYpEO&ZQ!3d1+4v%Hn#T3(XlTFBw^T3uK0^4VUK z_Xgk;8&! zZatUZNF|~dqw{iQ6$7%Ap7=L7C!uAMPS{g>)FKAA^4HVIeq%eHy7GkTF1338vTQ7x zkEy*iQ8)hn{y1&YX3^79PK5rBszEnmM?3KQXByO2oG!8)uBiq&K@l}Ym00WAm7?R4 zaP3@nXKUG~PN?{{z6~pauSs~n^D!trq2Vo#eV^JdjQL=QR$Q&lUv7pAqS4lBu7(>U zi+Q$noMpezkk)J(6q=JWS>+~$DpM>2}lVDne`T8E7 zTWUaYGnr#>CWPxyLYXk(i8qUnw}=XZibh7Zq@W#(W?#WI0SeeynT#8=d-$}#M!Gi0 zu?3MQCB}N3#aV)QN^+5)FS0^f-0%-Swv<8WrgNvdMTu zMM9D-iz5&DxTWcrIt?uZA9IRQ+VDu4;Ix3|IaJ$MMZs*|g=h#K%2xAGof(%Uf$7rtm&rD>K3`wxjAuDxSl(nUP+-B>TO(*-0ox<#uzn+M`Q-EF0(H z#Q%O+e_6fl7t`JBD%|d6f7;p3Mc3Etnt{k`*{Srd$mQ00fM0@aSPrX3p*^ZiB3vvTQSw#VWM7)WvdGp)fN`R!GQcdb${D^+Y|`DoH#eL6^Dh6aac zfr2OSck^TU_(#8yqLqerx%u)3D`Fcb$2Z>`6R@koHouA-q}L(JU2o)APb_qgjJ;xw z#{)&UL@zukbZ6V{V#9uYOPQ;8`Av9t6sdI6bI`WFRET5FzCgerFbSQ^3#w zwR%eWjsBDbT!!BJVyuvj++w274I)Z^H@p{&O8y(_FG`J*M??OWPHTgc&f|PJlogND zIrdi{VMdZF8~G&hTT*hl?9c6)>*b0niz$rhL)LErOhMY+;FtrjT5Dy!di~M{w!{`A zvzpRg@osTe9FwIi2Bf>z5x)AC__>=6VmWRz@R@~*XXn{9np#C^UD0%7R^%d$ybby( z#Lld+y`!&Sot%O&ez8*Jl?BS=(>lwaaU5*w)(ah<+22ZN3blPv=WwwmY_nTMYpZNn zDw4obFW0FzC33gXely!hA~!H?JQ+vDQoC!`x-^&2h$AjmeAn?*$B#;(N0ZN&^?V6Yn4?ErZly`W9Lc85ine z7px*TYC+c-XX;A5(Rc<%{in5CA}=kUwnXaqe2~J2IYLJ*zM`DIOu}4FHB2RTW~5!3 z>T?Tye?}u(>GqayVstxX65z0tb(^WS@R$l;Wfi2%*B`H!No+i(Q9}$)8KgxugpZjO z#Ia;Ve>5W<$m@KQXZI+zH!Z9Bn?M5R(6m4JKuqH*IYj9tH;Cb4Ny%C+S=QYCIj4U6HC&<(H+)ZEK|SVj-Q7z zj70RT6BD%C?GuW9!s~aHdCE-83H|Nyr6ym^0b;5xWWyNHTr=uS@5mP(EpGA?@g$Yy zwZK|V#~Ho68B5>Pnq$L&Te1dy&A}Wub3^Mk-zwKnj0WPkjIWwECbuRq>!{ouwj={K zx=s%6P-f7#VvA8uoetqLemE?(=80-A*MKUlc3bpKNe?p@E`!8Y%la^sF|bS{VVW(B z%8l223i;N*8HC%pHwS9`UmphvL~r!>!AvGz&3&lLrqR06)agiHkKM%dt%XlmLxsd@loNbya_ z$D#ciqQp9vCtW(MiixiSeYHjZeBC|4lku)G*k+A;3(R*7FG|!LtqIlrDLe`=fA2B> zrqSHO;b>Iv6qV0UNJe*a=EBCn{!;f!>c-%=dU?7-1HZjBV9x``3e{bk7V8wVioDOsJy=z33qNPlFzNA0!rbh*_%n&~i0Y9DYMXG8{p6YI=5BhYng+I`2nF@xS-XIi zHEc%zXz^oxB2Z)jSx%CYN;-?gd0(P^_*>34b~b$kB~g!sJZ31JLbsja${E>IZYJlZ zB)x<~kK7*FVW>g*2F=2N>0M$@ftqdkRQlq-pms zZ(?Wk`KBY88#W5ZCs++yjXRIqoAUacG&lP1^sl8g{PBEyWkju$+sserUW6910I_^V z(DZis@|?i|jMCI2D-bG$=EdxT0-2eY`X?HZ#^J5L9Fy#m<%aD9kQaDi-Wqc_1T|KO z=VrLQ)8V6GGm6tg23sdBsY3}TsYbW+tzDqsIl|$YnF_EGcN%Izzd;c6swx48Z)g0?U_11CPy00Wk_t`zrLMHZhe^Rb`bg~qmdkx&ZOJZfn zq}()b)n8~NYR2-s%gZ=m6y{`ty+3^WX3If~%ggC^@w!z3ihe{bK11Y-wDU6{S>o)M ztnW&i&nGq$=by)B!o(XGm>7oDDJ?|VER|8;tZEx+Ei%g5*h-m7%Zn#8v@j0hPjtJL zQ874S7^H58l$dvTp2ZhW(|w-oxIyXof*RZLQPFIY%30rjMJ$LEed?`@FW&_<{c2wg zPij{F{j^vm7Nsc2tls+Y_Us?_LKb& zZ*U6(zQ5U$x*ioOX`9sbdO;>q73%?&NunQNs0Kb6iCpjHjwRSTF)WP=bPC8+4;YKb zHWji@@{+wfvO7__+8x5%(n2WL=?fhU z?MIlnfwQ>{z=W6t#8Pn*u?+(PMq?ocuNhSt-pU1<@6F8>)`}^rhV%DC6KdnB{op)& zCLS*yTQ4WTFqY|Te0MQET=xwTIsVlkJc-zILkOJkyt%@meUfC`+`|32M%9V8-(*p#yaZ!iNn(D(NZZZ^Hm z3E_IW9ZIaNUEt7=3)QzGt(>QR0%4syY>n(N%F$8J?qi75rEW;7Vqz+yFJi^~G(6o* zAd|a&-eqhgZSlw&W#Y$i@rd9>5%bW9lY8|hy_p&O&8hL{M!qljc=W<4L1+& zh$2uLT<1TL%jVU-^<}H~*UO3L`WQ3L5Y;eQBd%)_y)9~c)B$lK+}hYAw6v3nVMWj8~c*wba zOG*pvnp2XYRaIH47i*$yepTUcA%3IM#ACX#A`}(Z!^fh5l17SjM6fB+mwTxmh~0Wz z>W!HzrKE4CL{pPh9CFiBiL;xL=n+o4^~F~FbAH<(n}+oCa@{8P8MI|sloGa=L?U`5 zzEHenuH>EtCI_9xQ2#?gtPYM8#pxt=e-WJJ_R|g@GI4!S#axO0@{rpk?5v>tbFn|2 zGU?8gYSZ?l$FRIftV+EBJvgeUfs)le>6QMu#aTVN8ThWCtkG>|K6uq{Fle)3ItJUzX1HlY~NLnM zZX@FzamJfQ<*AhQ`qC(D=pYv5SI*PY!3Q{>YWXDcqOx)|$7g=L44k?E3zBozb_;BU zw?xo?uU1?56&jhKLorC8k(H7&WPD}$vF_7Q97$E~arN9(iLy@dLf3BngmS{e3wlz(%xZFv(!o2I^hs@JsK>>Liw`5OuT~Wd$n}X z`4s5jVyNlc>P%9^G)s7%%&Gp#*?KB_-Ic(xyOtNoy-$;|zTwPx#-s{ueDu*(Qpu&C z|05O3JM$;KvV=kBL}HTHD@0A4lcF)wVG|m}TOZ~EQS@G8SH7vyWSGdSHEa|e1AQ%O zkS8?e-frrn66DlYkCw`O(wY%dKUn{>jqz z-V;~@1R@%>EO2isr*+Jy<`&??xGB4z-F9xc+(HPkYR}yB5_!veMbO{jXqqrNc56oZ z%yEc)+21`${yg9MO-D~6N1A2&nMH`>*K2*T$jWc3mYj9Zv_h;T&WkE6^y-?Hgcr^T znr(-MpA!{3@4xj7o4cB_xLXrerg&R#zxyrLW>NTh&+WI6%@5%WitXUVZjq)-1{9P} zq7*Vm@MkDxIS=~>Ya3C>Te2ADTAhxzC2KiO<4qJX(Hr;)RcL7l+tAxMKH-u6*k7`~ zEp~KVIOo9G{_%0aX+Fqj2*MnGV^2I?wN@kK>bnT=I9GrzEdaKU^}D2HD*Un zY$Cg_TJHRWp1h(K)27cso^wx%hQG%K>1SNMc})ImA<@)=R+hk5M$v9d8!f&PrSZtg z->G}QasPVXe_zrkz{Ql(BHPBmlp3mtqW($pjK5?9=F*;R=OIEUN0?o z+fPsN#n6o1IP8e9V7sbI1S{vsxAZnIIC@gr*)2E@$t%ZD=D;lvjo9%^r>u!J%h3EM zzsx_r3o$+&vAMjh4nzz8u}=%_$`2`cmtAd!uPab-xc7O)nw>2gcIZ5iTpWj^b8+0m zo}Y65jC*OI8uVxb4@-N!NjKYwkD_wZ3QdrPxOzyGoiTY#yz8swIK`=Ca(l)IkPPu! z|I@$^tLkO%DNFFSBPL#{L=|bt${ojb$%iS;vsimT72H~)?%K^U{#ozjl)xeGvEdo( z9bOdcV!WRd< zL$&3#hqO6Z>V5@ATqodqM7=y`5ej>moVk$Xj_obC;qevRW6AH9M<-C;ArxS)2 z)MJ8K)W)R7lzLQpeKkKPJfKR#eFA+^25jR(Mqd3@F#_3ImKv6C%{9$+%w0v)^$LJx z+~w7lP)q1O@Ss9R<=GF&$!lQ{GaE;ev#`9>#8?1R ztFW_n+c>+K?F6}t=;)_J!2(+cT=4#sT_=S{ZfBqg&rxob-HI#1Xj0Eq>t#c?0Ugr7^r&#q-KC+Vhp$Fs~B0$a&DOaij6;=R|JrN|+)G@z^XcVJDP; zi=tv6W|cHSqIBr?uLY8>4eh9C)KxW)i%c52uQQ@iI3ysyr%&F=ew68XK&<f3r!U3TK_2jd9V#@ZTmG< zMW8#NfD?vu8BgM+;71XA7((W?ZkyV9=d#SieN#YS&){Gt@r^!dNp%O7n@d{foNRP+oLDXfYlVsgL&+PfxS5&{Q^qc3_^(U9 zbCs`DRC&ZS+Y6VlNA{DNL5;_S3 zdN=|3gTVPG)u+Jd&QM8aOW&<9U@1N(ul&zL`T(Y^WjmZ`E3)IYOkhxF*A?&~+ZAQE zL+>guyi)_GVF8ejFG->IEId%ck;LXnTH21Zu zDYL+?Hx0_iH5y7V_90$CJFe!>c1o(64ge0yQQr$3lxwY@4@E|W$LTLViwYA8e95$7 zI4$&Dq}(^z`}vE4#z6Qx49|no&2H1RTzh}Z+udDb&3$h)yGdq$*`o4=Ga+JiG*&Er z7^gvw4zX_-%g>*o(kQZT=!ZZ-gnr~9%vm(}qyqnL;2mS=lcN985Cvgc9?h?j*@82d zE2^wjo)Uv@MYw0L#YI1tsqj(V+JTzhg=W#>(<;Xg$P3B<4IB`0prlat-j6;MXF72j zEG1VwvqvPdqhD#V@H@BxPucV+MNa^a8HhS)Ncm9%K1BQYh~c60Ln|CAXv*uJRt%%d zQ6<0=Lffl?eDJj>eA>T=*q}Z~=YUSwkMh3gL&2byEqJK-rRmEDz0_KCbJUIx)8oxw z*-XdpaD|WWlDzLOLvD1t-d>~rH^vDG8Tt?4&OO*j+{nSe-pm#WdHxf8q^M_wgg=QJ znd`lFRME3W;(?H;TN8(S7_o?h0TNLJfP;BC!C){Hiiu?Vlf(h$hH&z7!+GyPy$B<# z*8m>mHS&_17l|j*vz0b7GciQ~xFNip_e@AG86;%L%s|B2#M0;wcVqekicj?2cvt2fA?I)Q6KRK8ca+^{Qlc}MPQ^uGUBQ> zQZnKSdbUWwmmxAHW(e0m$SST5NbhB=jcx8RT*^i!W=NQsD}Y%93GFsQ;=o_p8yeZ0 zS(^Zu{~?AXsyN!(S{hm1hZc!=!sJrFM|o*Mfj~|m90t8dfdK*BAQ&ev3 z7YyVEKzX5@KyC<94-f!@Ay);#A@|XP+~doTrywMihZ7D2bMpXT5D@1*i5mchBWd@y z;Sc*D5Ev4R#tR1lc#*dZ1_#6M5p6JDBozqfMy?Iy<^+OaNDcSiK)HE1VNeM2wjz1B zks7(VA#kJ}e_5mrKzgkO0sg@X`iHu|g&;g|PF^4n^d4vi1woKbA@dBGTu30rect@B z05>P>K5+nG7&36&_io-h1V@?!g8VBLj&uzKMjDAU>K`&t{1>SH{|0wM#{XZ@ zZraKN);>VI<`W{JynrV_e|iE@b7?xeO|jhD2Nm&?%AhzJ^xv(<@$||ZA0Rukvqxo} zReWlaFWGNweMou;H6LQs%$LruGieCm^Rrautn0iiM_5T z?CiPc1&TBM@&O*sm?=<_x+_kLh@Ilvwo#u%jc3nLRYqNNXS!PPa7lXDPBNacFA#34bafw^&%i^2PA$(W-u`8Vgd#QlI}MrV{{szK zp#RASh9XP#-(-=6{NHN;kwx|&d_W)%va|fVEV4@gkrnuF`jE8yQvVMcvabGv1_D9; zOBMuz@%*R1$Pobl7kvnOJ>&?mzkhf~#mo&ERR|KeYh#0iu-=z1vbq1!kME25em*!L V^z0FT1R4Z}Lx7kJ3=%IT{||p0;^Y7T literal 0 HcmV?d00001 diff --git a/tests/workloads/sort_dispatches/MI200/empirRoof_gpu-0_int8_fp16.pdf b/tests/workloads/sort_dispatches/MI200/empirRoof_gpu-0_int8_fp16.pdf new file mode 100644 index 0000000000000000000000000000000000000000..5dd56ac8bf2f8797ecfdfe037894b8b211a39bb1 GIT binary patch literal 13153 zcmb8W1yoht*6?o;A}I(;d1w@Y(?KcSor1)nI}g$&NH<7_(w$OLA}!rWN=TW}-)2z|5#t1LK?zt!HrE#jKmZ`XM&F!(kB?i} z-UyAcu?MgVo7&r0nK@cLA>dZ9w=r}yFv1FzEzHo|*tP&GBoh1JkFuGKwFnwx1Yj58 z0RzEMAOwg21F=UW2N1}H{ln_X+8F-tDgpuoM%IScLxB7}6azE>M8GX13*eTsvA057 z{;dT4TS-{(TInxU8DRjBfLliD&r$taE-M3o5^yUE0xUJt;6Jvo$N$w9 z;{Uv&3L$pIgilJI^9U1~!IRUu2A|O)#ba5F7;&5CAw}u_0yoDj2HZJe*F~Jg~`(j#!g?l&2dpHvf+A4tYbyROD>|kF(V&WxtW9n=&&+8A> z;lKAKlRs=aERd!Wq{S7Nr9Q~oWJ)h;KOfjweW@stMN2{UAXHUDj3e{XcGL4^U=D?* ze+Cy$ym4QOVz|g$5|pG$f+_YO7>cjCuJk1okHw%d6gu0gCK4Ael_{t!q&X_~t^%Bp z$DR?w;^#uh(uN%U8cU5f^nJ?G!_&D;#TQHJPcdD1E8{by(SQNX8Xa8gfeC_|u6H~^ zy|gqSeqoBkEuNYcb>}hRO>?6mjc};oH2gee)>4&05hqgk>C@#}6AczjQYp*m&#sk( zDnrxh!fl~wj0JPvld?Hmo3zJLH71DMyc0~`TqCl&RKQ(7WeRAsA(Plzex5cEN7C6z z{&+ysVwBo*S$OVdardRdqPB@R!!Zb z^eo0>-t*xHE(pAUa?6;Df_XH`mz9ZqaI=d;gA8z@3`Azg0~HhLiRsDx&s*nE0x1*L z37kvIsQN@7rsahfk#>Tj%~a1Csk>9qgfd&J{iz53N4A_!0Ku)(XN^(cqx5Zy5?V`I zm@pPy_RatYlaC$5zED9?(tZBqww;Gj3l`31iVJTei9d4?$2px=t#ounGR)nf6ZK{w zBz&xPHgT5bMRz%Wir`Ueukj)a-8?-xT)Fi-dfm)~N`wAOGeUHe9RAvMVCbg=yoo`R z&5|}3S%n8CVOh3VJidE_iN?zj2!_ALeC@c+e3@4l5>}&TS&<>d;6TH4XDa8$_cPN_KPzN@i{rYal9UaS(HDllbBNMh`zDib&HyJ24wcFo-`BUgNA z;U~lPZ2im*c472u)Jk%x@sJyrjw5ztaU$F|Rc?O! zkYmez9a3gQgD_muvRcN-JxH^YhEKt0CPp^;)Li78dUA&Esri^#%oLo!RjO;I%s_LE zIZc*quX~95CmaDUGYPA1(43ZiNz>lHfk(PL!}3nXA*tw|a;8yMNxq|v7(4EYk9dS1 zrJsp_cSL;1qbfEPfe9;*i<&7t3s~NyIOy#V9;v4~8Ss=nd*;1lkL|4=jdm$(6AiZ2 z_7i)q@3eTy>r!V}h1-aJXcxBl7)h&=M%bzm7v-bvy_Ywtq|)WB?hD2omXAorOgtU4 z8AX9IYeIb%h~o#YQ&> z9s|aFOF2%|NG?E5B_~22&KOpklrj@3yGSAoe#@@-&a4duj#dn9hShrP3>8IYbFIQs zs*GC>U#6^pwC!7pT3238yIh{UEjGCwM&|N>o<3*5)Y5}xYD6Pv+CTd%O@3q46ivQI zYt~9=bA4V-)F?9dV~Ryolm8_6626>h({?Ooi9K+VCp)=ObQ#|6QjV74-tnAD5^-y2 zKCde$jr&$%bTDi@&FHaxOT&8l_Pqq3EqbFe@_GIe=SN|eHgU~hKkFwRbLYP^t#P`I z0f{f3IzKM2zWD%Oqg6u>8Tbi@>dd-@Mb{c%W!vOsV4Y`SRD;3!uMf?ym9;jU%-3@* zrSBggVmLH+H{IoxPM}YL6ngHg_l-)Ufh_#;jq9tJyLp%^gABoO@kRF#-4mxX&Vfr@ z5qii?s6+ISlLxum8>c0~w|bdN?+sBOmv1XqJ2NPK{Px+h@pE3(*2uVwqR>Ci!v8o+Y7=ma zI%C9@G1uh?wy8J-a9vI)5pat`0oOId^%V?oz2jeBApqC=wGy_h;1;v7#$2}$g9G4y z$*!fcMuui+Asc6a77#0hfni)AFaUzMK4H5O#w0RGwEr%7K-WX~k9NXn4BFDh z{R_%H=uv3>HaDeKmZUJ0Y_q;{a?xnBm#=~_i|#))x}*!wAxEG)y>9fevWtc zCGUFwupcP^#IPkqbMspp`^}p~%%op3BmhOYGTsafw{ZRLh_-dH-qIJrC4V6j#y%Z- z54q$Z$Py?m(h-oskl&zO!;2q2aCUih?%}De?a{1S6Xzh8%CkDUEzQo*=KuUYgDvYP?!HjoU5i<#xj6pQx{qlglQ=uRVUMS33F$+rfUKn_&)8&AK_)G3yW%rGKYEZ?DR?GwUqeRQ z8~wMVT=|oByel~)Qo#1 zUyv{OqLZZRd+ouM18+-!DM!h~K9RwU%JUunpIh_5P06k*sWy*Nr)_pvPov~hP*iqS zD4!HPQ$&n;MU*A0R+o-_BrVf!%s^MovdP!Hw_?M@(6Hl7;dN7zMhaTsTF5|9xA6Ax0jQeDlds?#7^s!dlf~WGg8CQx=W)>w`q20a-z792F z(0-dRp;yv=!NuUcc`qtK+!P8P5t}XBV=#~NPZ#2Y1|k^fbBui+@86uIS!f;8{dlfU zI{&E6F;M)D9sgqen^VAI5kSE2bO#_1dYT6Ce6ZgI5O{;+_3mr6om0F?-P=kQLA=OI zHc!*WL>i%3ImxSWN_g;KS)6FkAU$7;MnKKuW$W9(PMrN`Z6`SUmMObepWTlc+fagh zc>AY-v=C<@(gEQVnzjS7Rh<1>ZREbr42zP27r?~}0GAjaDv*kS3xBaaF!#B=wA0C9;)>_yPFb(L7_P~h%e{fLW3 ztE}^Af90~PIlW8Hz|K4S9)Xp@~yE4tUi%;XYXNcwx zRW7%tX~zaL5o3)xM_QCyon3c^_!7COgJ`Mn@#MkGvOz|<&Oqb@`vQLU!F_cbO7Lp;k@7mvGP4)LAX~C;I1&S=u{}!*|W{&B?}I$-k*A1 z!a4ck@J6rt8{|!C6^`4ARTYvJC)Q<+vN32th^LUfWI|ZN5LJv$3%thc{)5ZAk4Sri z66|)P8CnFsl+FjCa1ONJX!M#Th~qjq$;#h;8Tu~3Maj0PJHalyTd()aiCilm;lb?$ z#nr&Fqb~xz3^$wWfC;{t1LIjxi~9~*8va68{ST0`zf^0BEg!_vUZj}h$or* z$FTM?%@cJ5S*NG8t)Ih=$q7IlXBoJ17EI)_AsjD^qx5t~EN0}>2PJ~zPBKgg%p>{k zBSW4H{ZNPFC@uxrr*_O?y4e92kmDI<4gJ@z`*77r?j=$E&K0!lE*k%d0BtDc#RCyQzM+ z|9*WC!j&3e6t+KJO-xHl>!`PLqlgBD`+*$|8z-TCKT94n{#D?DxV!jBE@{JK^w`vW zSKKPb&FQX&AV0d6_r6eeOwmn& zcI|woD?e}kD>|&yt$A;%e_sv)u_NlL<7<*#*%_^V$qa*C3U+54z(K5M=}YDs>n zvp9<=(y$|itS{6&m5(H%tPJ-SW?(32KkhD@irfMniCFPYIc$|_7WxM@uTFM+WOXam zK?+JMKUGcWS;r6A{S5wuaxGh|$nJ@oP*E?Qe~)ZhyyVhZ_TX|CkMQseheH?Kr)`@O zr`+kARoPZX6!kF@46bhujv9YX*D|bsAdZh&U##Z^e=4^^8mc<>{WR*K5GUVt+i{rt zRe$fWID~4Q25Bz9-zhZ-j`h2|@vV(nig}tX7kV?xzwML$!Aq4*oNCMDJ(*wb!)hNmpRH=Q!nZTAckK!PGYTr zAzP5?NJ{x>L1{m$7x&LeWRl!cqNn;Mcl~l@b3f^(%G_(60+AjxGn#qsamFZ8BFwDV zK()5TD(q$r$5YzXX2$WteW{pjrKe#AualYh`_MJzZBYH1s8i&AkD9gXx!Hxl63)OSLkoXSw1<+WmXk(~2c2#6RSR zyV=$T^QxJZj6L` zO|hGOp^>=DJyQPyQOk8|$5;xCQo(!v@}Tj^w?THvt2oXGuJGb5t#* zTT@jQ0@~AV9sUdlg%F$Pj?z;THZ#qQz$CAL8JjOhTtYj%(L!G8iv)^2glS+KiLjnm z1{%4w77d$=6Hg0YX~hW5GTcca+acCTrb(gqjb`>EO`7d*7F>Fa<2}tNqgh?h2`1;+ zI&qz!t}(3{+;o5S!zxdi(COg57Zm23cq0LF_n{*U{FVjRTq#IvNSd`T?qL+DvLitf z_&Uc%SUE|%$YLq6N!F|@q`GX_?$ykaz9jD>NjAcg4t)UhG0D$Q3Q00NgNAEz;)C@v zPKn}6E*@MS595>}T-iPyLZ9dmW&CsW$u|j1VomlcO(JT-<2^W67ckQ2ayr5e^KB2N zLOEh1V#QNy)tHm zeUJ*{#ncyfsF2l+H-0qQ+F2*><<`1t%_nZXEj=!CJ zrczmnZ(c6GxZjtd*qZ)E0I!D6ZEdhpi@4&g<6XMbh>HL>hf|VykM`ycCr-U?#EoykAP*;rrd_FNFseQ6xA`+amqwV0TO43N)AfX-oiD4OJqX$nr+w? zziaprZwIj8Mb?Zo{WEzVO{Ky$1ua{&DPP#^U2(1E3-6!fn6s_56&Cvnq+*fCS;^=! zO~mS(>B}bDSnCWW@{#P0a=5YT;`peovJhJhM~fBg{gD{Cby%2GRTUJfZDu-rXSzwf zN{M?W3xPi}@xV$}$W=2B2%dT!79riWHqM{bc+(tLtIqh>G0ft%XJn~ zU(-9?M%Q<`vvB9_itNpCPVMTr#;WoL_a$YcA2i}_C-0grcIvs~cMdw}3NO|+OP?3; zi5;vw)8@g0nD^da&Z9*UOh8$6R)gLfF=vR)a*ag>E69ggS*<-y@81q53SzLcv#!hm zN_f`Gp9lXQE#dw^L}nvGAI7sGKz%7D<11d%V>h`Uc3Z)~)%4Rge);>7$WUu${`V|) zbf&yo?7rOoHq`#E!*27w=?500$1FJJtK9qdS`kB@g4#dd$0aw@mcgsx4ejH!fihG+OdTYKyQqszA6iGf>KxPNlKd=U7sm zr6|U7aH(6QtseKK=drZ0sQ)1)bnzfoe&V7}$e)K1D4OS2|xpQe-&z3d#e$ruIBw>Z7= zfwTb1#cycOpfl%vobk=e2gT%SDepLo$;xU_iE(=@dFh>Yxlo2xSN%?hh3%_Te5Gva z0$OR)cjs?9tw$>(@groO?I@tW%#OX7A$~$R0V&4OuG?cu;;_2^^&5v{I*i!m{qf{y zYHhrxNty@HxRT7<)!25YMYr*SNqz0&%Pkj z3CnpQ!9j0=h-7XS&X3l3&|$;9W>g@&#FZ}uG@-r~qrX)(VBTg1tK_u5uzNV6*;S!w zA&>9N=d5l)f-Vf6>hJj?Bod?J$sLtx`anc=oo-<2ji=#sQhj!ETlIsg(Vl+Gv zIdL6v{-4#pNS;1I1C%`0vh}xvN3CVDfoLP&w>!hh7dISwf9Q_wak_J9OLjh&bA;T} zQu`@=;YKY)N3z8yJ+WiT`3My(AZaofuomNscWEHR^_#{kqIux=$~{}I6T$wltjhWP zQhja-!=M7dw7vXo(K*?h*%BkM^nx2r&norkg?ZgR?PYXb-97#mL|$yy<*~^cH=oiw zXT2?Y%V5M&6Ek!4;3p$_t0bdy`Q3DhkN8RjQ^N{~L)K_UzBqiMB&AD#745hZ3MrN+FH$%tyU)dY?$8Q{!0iazeGL-2 zEUv8eCe|H$VzH@Hmb)-mYa^F&!MI#V-vnPUFoAii zX1mnN)nl-8i{oP;(R1oHV+3%lJ>?T=)$Psq2OB(jI#tPB!l@mU<@&QiRk567oT?LL z3PIEieqw@r+k`>q;r`YixkJYzU^3(Kh~5$Iw#G8*f;HvuqYd|yZpQL`VvW7OEkreP zf9eOPj(v1Iw97>6a8KHyV#|!-zS-3+r?|n^2y5g^6_kYPcSAC?Yyf^d=PQG4|CqN5 zrI>A*sD}!$ZL0gv7m6ta&is_-j_+>EQtdssc<2=pKl1jctxhNRUa2!3oeYy11zkhf zd?(^wh)m6g6S3cPlS{+qRuKV_b62)A^ZLoWmId_knYBH?rrY68xKJ*D`L^K#LQ|Vw z-D~2`LD`HK690T9@K>Lbr9y=Dt3J13r;@wpCHv&|Qk(OSxw+lkJI^AXUsgD> zZFnOMtOO;Qqs1>g`dE!Y6%XY@=RRYe9ysfRRSiPL?G+bY$Lj$ zWU@(#FJ>@4)5ehX*M?WiQ!D6)t!+ZJ3`cJ5NI%!DpsO#TjN2u{<<6r}gG!xns46o$Lcv*<%rAFUhjL=)L*uf@)z(CH^OB>e7$z8RkM% zB#&}BaypLW55<2OT+la9Jl>4x3GNT>{%Pn^sb9HRasM89ym)+PtlQVdALTtumoFg1a%zU@k5387tTCTYpYR`d zK;+nY?X3r*6XnMz#*Ush=nr&{Tg39$Fr2(NUS?Xl`URHeW>3>N9J`~^gHeP9Vr=0vI?HSim4o=oo=0^yw{!44&&>OK_^ zotlz+&^%h-l$M>+;JnXl{94|V{&}xg3kJ#U#ik_OT~vKwOEv*~b9f>i1^y&d5u2!< zcl0`6fRKt?X%!gL((e;h9oO;kSbL!KRmCMn(()s_mWtVEQeF~!`A|vW6QzmP>~>3^ z1bVJ;XP(U;2Aw+nuC8sV(+-+v0j2@5idtEr{N3HF^63KUDGeM9Hy>3f;BC`!UxmCd zdk0XJyZ@GL?#^O{Klqa1+Y#TpP1!>Q=f=$bk6-D2=)1h1>uW6s5?#3n?VX*^JxJM!lvS4GW*Ua>PT<1^$z7&VjVL=0>4deS4Ku0)oHL1Xav z4qt@n9ERF~CqK(5ef^MQWIheKK8tty;0i8leips4F?sxeW|PzMqL#_VX|uXU*<>mP zn@?<3)8Uqr%}$kj(ogbmo8R{ecWE?hRV&6^xx9^wA)@?I_El)l86A0KTxeITjO15E z@@Lw*wwiNNQ{uHX5pjCZP}5FzknN1UzB^FsOo{yNWK?JV>Wc~>YDgsnq7XIm_I{t6=dzfP=e_`8|`^gc+{wd$Xky*tf`1=kbKC8g}ul_%1Z7a-#_Dx)rBK6?;ax=tE3$ zi%l1JnVNv8Vx@Gc{lmo(&xJ(YggM13g1M`cl~!Ikd9C%CARBe;m}?BhcLWp0Rf ztD&!8RDRZ4ei|Vd_YG`2QE)z|Y?9YAvC9c8`)_|1-wP%yry8?Z-tXO}m;W6?j}VP1>bMt(>8QVs-3)lBeVH zQSt3qF|0d0&JXs%>8ELVDq~qw#C*vuLh@ z--)|@;M%bDlNH}mYt-qk*ergzV+)npPfE8ElrQ8*Y);qg2UAYsi|z$vu^O^auog+? zwH#`Gsq?G8bKBfM=UxfT(Go(`4u^up?E6qQH+_COe~rEP<Nx2-w_KT5qfJw1U4r=Qo|WVDR|dsamJ?H#btTR9leCjgWs%uly=PZ9W8A1mmi)Y$GJg2E!ziBme&R<_RzWuFo2kf{f9sj%C>-}q_)Bfpx zh;H-2F(Ubtw;{+Y!Z?pglZI{kQ6wRuD8V-K*se-wZL}DB&FCZIO%+l3Ltom(@;B8r zgF0y_7Q*GLqDT`VKbc#U7YHA}7KMSx{^Yd6(p?W*7YTL5meZs>z1eKQB6|XJ4{}=O z@UhL3Wze!dP>T8yVYJv4CG!W}{Kyoel3?2fb$7>RQOOgLbxxi}h_#-$;8~h2`*GN z?Mw(yW42MU6w*)BG=2tomq@orBGo~m3VL(5SMMgrB;Xb!1Hp{aM+Oi}zSpo{R&>^I z7EBT*86Wcn^giwAm#s|D?-Sc1-mk=J;ghJ64E@FPE28PrD~Fk65=z=0txx7Zt$**Z z3H;V-@y!1{7fx4Mc`2;VnVMEKi2(>)Nr-h!)(04!72Q>pM(hry=`9RJUb5SWadsxO zFm4v_@s*FXp4*QFg5v_`R?6@>CuoH=_p)f5@q>@g+Pys}=RQB05ub-CzKgK0<4M6}H0dtsKh%aj^;fjcObj>+r1J3+v&teNemM44R1F_!iT8&DqEs5l7=M#&eP`%*fny90^> zu$BZpDX3EgrowfbUjnyJFJGx(MtR$M%X-6X$7tP1wrXDNVszl*d;CR(?*8V*xlHSe zBjN+n9@4`3G})aTr%J_07NhRWcZ#2e&fSPk3Nk}8WehkCieDbz()^rLF!F4qsP0(* z@>b6+3mlixvYFZ$6?93NibgtAiBuqBNigZ8jv@CpEFK-w~#_-YoUKw?wpF`F@)1n@#pr;?5OCId|KIEryI!2Pb zTOE2?#_!ML|K%Y)g`bd(CGFW|I?oD_oxlOSI z?yEKxFf{PVU6$E58W&o#sK5n(*LB=yF}90@`l1(4QZ>3!kANcl@lV}EHKXXctv^5in{?BN)k_gqTcdSdQgK!eBgYxWiFQCQA zW~K3x%zAcl;>yJ!0*{mgv0Z@(<^3~vg5AHX0$GL6byAjmJqVeRR8UUNiWv^ zwA@+csv3g5kz@I7?GdkEqvc9o(=g&bxzjPc=B$=6^V4s)p4-)aS!njy%fz`-C5rdh zYt5|ber{WwZOt&`RywUkUIwds(V4$@@hdJ>9#_Awxy4Bz;oa8jJ>!SaFY3* zpLo~)lsBN+4yjF)E7#GLi%bdiAvd#4X)XWp`YeHFj^HgWv5md6Z|f#)xV>{&D;aUA zJ+gO!G{Egn!)&UswCi(y@lvh>!Tv9gF( zX;Dd8p#o@Z@pYlxa+Quy+{TS?Mhs(lQU;LxWUF{y@O1 zs@i()Na^Asu3_TSnT*~}68@=4Z1L1#85W=?o3C<~AYan!Bh`GEK%(ZLQB_gc5ZwB; zWRJb#Y|Toc{0qA}5{=`pr=gfeV#J;ge*CPaRTue8%RD~bPQyHag;oj`Yr9v&U*TMS zfgjKwf>souFsWbGf6Uj5W(dHcOt5+5^0fB{F!xb#68bfy*W6!-7=q$!TWHa6_HMb6HwvPksXgk6cf0XwD#ooFJGcCJ~ z=s^P%kq3D)U9Vdt%wxp;TlwW`-An`B5dqJbX4=thsc@G&0lZeglvZE^B(!yq0q$ao zPZ$L65w-+Q5<1yFR3W-uh`tdp{gUeJ*tm=DP7TrR=K)u==d&A;zfcR~O=@Rqc!%2t zalg)|iv~Lh8&QXggOvfwJKqTTKTR*w%dMrMW9z2@t@yM0fLTJbnukB2#5E5YVD0R= zNeu1y+Vu~YOW=#tHQa=0W;lrlEiBXYcafYxIqGI-yvV=ioQdHZUs0K z+o=VL3K-CR@57Uav;ppc&Pc6r5mJMF3&!gq;&*GnMKkMn`R7BwZ_6mfsQyp52g}O*7qN0p*@zf97}%TH zViDuNs2e%76_)!EF)~N1IVz*Au^yZfkA$vGMKroOC21Fo108S_zj5Py}2A+XF01k42mgOErp@^jq`OV1dA z0e|qCYjo%zR1fIixaGgFo@?E|TKw%Y*4j1Jg9VY%4o24s|LM81qdw*j1|=*ha{ct$ z5E$!_q=<@*xTJ_I+7?SX8Di(e4CC@gtnA`|^8d+UWE%2IhQoqKVwBSG>7Z8PjU*k_e00e~KLLxvw zl=ii!*VGdV$OVGH5m?XR04)d{_}BFRtq6cX;9MvW6bQ#QK>@%>030g-Lx4~O0D^4- zM?$%PNH7orfFt2tKnM(L2M9nQu)Ts%uzJU-fAQ*wQaP18o0_8%$VQ`2x z0PCL?4ERR~`e(y`JqEy_C@v%r3cqHl;2;=w_}GZTh7p(xcpV{sOhLF1*C7G`Bd}8h zxpwG!=qPN*AlSc4QCKHHVC-0-&}8GR?6aAP1emViB#p!vEk-arFbvsevzLbmIUNns>Wrp z^-=gBN$G@bGujxc^JD%w&Pw@>|C#)*gZn>dy}#1IzgGD5(#GbY|8pJ?wZ3^{MQcv zhru8)fHB}-G7y%Cy#4{K|0%;RG;Cb|rwkk4SnK~S!!E)9mVx2e#rPk3An>1<{|_1V z6A|eD>;sC;9sk)D`$-A-zwKdVNNgtkPkUe(1iPyKLk7a8tp6S}2m}ZI_n1N0{pH{K zz}Ta)N#6eYa~NeaSM039uuQ6r4VKQlUbfiu{U_sIFXHPRzyX7{$NZUSEMJL$6R@y| H%8UJf+_b=- literal 0 HcmV?d00001 diff --git a/tests/workloads/sort_dispatches/MI200/perfmon/pmc_perf_0.txt b/tests/workloads/sort_dispatches/MI200/perfmon/pmc_perf_0.txt new file mode 100644 index 0000000000..dfc38b8643 --- /dev/null +++ b/tests/workloads/sort_dispatches/MI200/perfmon/pmc_perf_0.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_ADD_F16 SQ_INSTS_VALU_MUL_F16 SQ_INSTS_VALU_FMA_F16 SQ_INSTS_VALU_TRANS_F16 SQ_INSTS_VALU_ADD_F32 SQ_INSTS_VALU_MUL_F32 SQ_INSTS_VALU_FMA_F32 SQ_INSTS_VALU_TRANS_F32 TCP_TCC_READ_REQ_sum TCP_TOTAL_CACHE_ACCESSES_sum TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RDREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WRREQ_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/sort_dispatches/MI200/perfmon/pmc_perf_1.txt b/tests/workloads/sort_dispatches/MI200/perfmon/pmc_perf_1.txt new file mode 100644 index 0000000000..cd7a1d5f55 --- /dev/null +++ b/tests/workloads/sort_dispatches/MI200/perfmon/pmc_perf_1.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_ADD_F64 SQ_INSTS_VALU_MUL_F64 SQ_INSTS_VALU_FMA_F64 SQ_INSTS_VALU_TRANS_F64 SQ_INSTS_VALU_MFMA_MOPS_F16 SQ_INSTS_VALU_MFMA_MOPS_BF16 SQ_INSTS_VALU_MFMA_MOPS_F32 SQ_INSTS_VALU_MFMA_MOPS_F64 TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum + +gpu: +range: +kernel: diff --git a/tests/workloads/sort_dispatches/MI200/perfmon/pmc_perf_2.txt b/tests/workloads/sort_dispatches/MI200/perfmon/pmc_perf_2.txt new file mode 100644 index 0000000000..952da7fef3 --- /dev/null +++ b/tests/workloads/sort_dispatches/MI200/perfmon/pmc_perf_2.txt @@ -0,0 +1,5 @@ +pmc: SQ_LDS_IDX_ACTIVE SQ_LDS_BANK_CONFLICT + +gpu: +range: +kernel: diff --git a/tests/workloads/sort_dispatches/MI200/perfmon/timestamps.txt b/tests/workloads/sort_dispatches/MI200/perfmon/timestamps.txt new file mode 100644 index 0000000000..676cca1b80 --- /dev/null +++ b/tests/workloads/sort_dispatches/MI200/perfmon/timestamps.txt @@ -0,0 +1,5 @@ +pmc: + +gpu: +range: +kernel: diff --git a/tests/workloads/sort_dispatches/MI200/pmc_perf.csv b/tests/workloads/sort_dispatches/MI200/pmc_perf.csv new file mode 100644 index 0000000000..a4aaf64899 --- /dev/null +++ b/tests/workloads/sort_dispatches/MI200/pmc_perf.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_LDS_IDX_ACTIVE,SQ_LDS_BANK_CONFLICT,wave_size_1,obj_1,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,TCP_TCC_READ_REQ_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RDREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WRREQ_sum,wave_size_2,obj_2,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f0b0ff2cec0,0,0,64,0x7fe14e710ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131080.0,131072.0,131072.0,64,0x7fb733968ec0,0,0,0,0,0,0,0,0,0.0,195833840619598,195833840639758 +1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f0b0ff2cec0,0,0,64,0x7fe14e710ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131073.0,90884.0,90884.0,64,0x7fb733968ec0,0,0,0,0,0,0,0,0,0.0,195833840727598,195833840744078 +2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f0b0ff2cec0,0,0,64,0x7fe14e710ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131083.0,91096.0,91096.0,64,0x7fb733968ec0,0,0,0,0,0,0,0,0,0.0,195833840764718,195833840780238 diff --git a/tests/workloads/sort_dispatches/MI200/roofline.csv b/tests/workloads/sort_dispatches/MI200/roofline.csv new file mode 100644 index 0000000000..d1ae54a28e --- /dev/null +++ b/tests/workloads/sort_dispatches/MI200/roofline.csv @@ -0,0 +1,5 @@ +device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh +0,1389.1193,1388.5117,1389.7268,5015.0068,5011.9907,5018.0229,9221.998,9221.3828,9222.6133,17639.686,17638.672,17640.699,20928.205,20867.84,20988.57,20262.287,20261.715,20262.859,170396.5,170391.77,170401.23,164866.34,164862.11,164870.58,41419.062,41418.352,41419.773,41476.004,41475.344,41476.664,166322.31,165832.64,166811.98 +1,1388.9008,1388.3511,1389.4504,5027.5708,5025.5728,5029.5688,9229.8926,9229.2207,9230.5645,18065.086,18063.896,18066.275,20967.1,20900.262,21033.938,20287.465,20286.975,20287.955,170787.73,170783.19,170792.28,165052.28,165047.59,165056.97,41463.211,41462.293,41464.129,41526.121,41525.238,41527.004,166812.8,166807.95,166817.64 +2,1389.2667,1388.7651,1389.7683,5035.5039,5033.2363,5037.7715,9258.3965,9257.6201,9259.1729,18263.133,18262.299,18263.967,21044.596,21044.225,21044.967,20349.471,20348.801,20350.141,171117.73,171113.25,171122.22,165495.05,165491.34,165498.75,41580.641,41579.605,41581.676,41633.578,41632.25,41634.906,166904.03,166310.52,167497.55 +3,1389.0205,1388.4252,1389.6158,5032.0649,5030.7285,5033.4014,9240.1006,9239.5449,9240.6562,18325.539,18323.268,18327.811,21029.975,21029.445,21030.504,20310.877,20310.246,20311.508,171008.78,171004.34,171013.22,165225.19,165221.83,165228.55,41441.34,41286.738,41595.941,41586.016,41585.27,41586.762,167043.02,167041.42,167044.61 diff --git a/tests/workloads/sort_dispatches/MI200/sysinfo.csv b/tests/workloads/sort_dispatches/MI200/sysinfo.csv new file mode 100644 index 0000000000..1feeb577c2 --- /dev/null +++ b/tests/workloads/sort_dispatches/MI200/sysinfo.csv @@ -0,0 +1,2 @@ +workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd +sort_dispatches,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 02:03:05 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/sort_dispatches/MI200/timestamps.csv b/tests/workloads/sort_dispatches/MI200/timestamps.csv new file mode 100644 index 0000000000..06ff364328 --- /dev/null +++ b/tests/workloads/sort_dispatches/MI200/timestamps.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,182586,182586,1048576,256,0,0,8,0,16,64,0x0,0x7f60edf4cec0,195833840595837,195833840619598,195833840639758,195833840652003 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,182586,182586,1048576,256,0,0,8,0,16,64,0x0,0x7f60edf4cec0,195833840650831,195833840727598,195833840744078,195833840745339 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,182586,182586,1048576,256,0,0,8,0,16,64,0x0,0x7f60edf4cec0,195833840755068,195833840764718,195833840780238,195833840781368 diff --git a/tests/workloads/sort_kernels/MI200/empirRoof_gpu-0_fp32.pdf b/tests/workloads/sort_kernels/MI200/empirRoof_gpu-0_fp32.pdf new file mode 100644 index 0000000000000000000000000000000000000000..87c5bdb502336a84cd68a9120955bdf648bbbf3f GIT binary patch literal 13105 zcmb801yq|`v#_gZi&LaXa1RNAgrLRUt%c%FkpjUBv_Ns!;%>#YxNC8DE$&i^7XEO~ z`R@77ckjCY|7Wq1_npklp4so-Gn>T&oua5X8yLumK{vL$y@CM-fB-fI78rbd>>_r? z`Uo340HcVRosE^bgB247yP}!vbl}5s6N6Nz$nVY z0pj2UK|nAL5CqH#X90m2kUvO0IUA$@T}40u!`RyBJ_N|$p&04|z!>bpasYOD8#^m~ z%fFR4|5g$ax>x#BRaOK5!eEz`{^MQaUM?pK;KX285dt9W9E|^GUtIrBzBvByg?#^C zeZl@eeEr|z;{My0xVa?)Is5G5mdJS)H8!*{LgpfCY;B4#1Aw_;5CH*zJp%dMtT3FD z_BH21e?XtPpKEN@eyoa=+<8Rsl*c>SebMowM@wbB*a*|`{@r6bHr=caNBRKA$CXmz zh7#4i?IMAAPv4=MUof^W=@1E0g;&crHaL1Z*^SH)b27;+9;;5 zB^`^X_nzlsGpByIoNv5-uyZQtU8omKZOyu_avsr4ls^m>%Z{R1y`%6pfI$ao5Sc=4_7Mr@aoB#>G|nbM(WW;E?h!33p4NU2_Oe;cFdM)gFa=B zqAiZ#eu?LdN&8Zm@&TNW;0KcSpF}vSB26N=c?@aHeS>4u$3!)$$J-KYs95XL3|T0j zyq~SK`-EB|B>%F9ItpRdDX2MYKwF7}0^Lz>u`G`Zd4Rj=d%Ryo#!W%n%S(jXJ7?bH zELqOqu|?3GBPPE;vK)R8#)Ha8t4MZ4hC=F`QT7a-)ie%ZpC~swmXqzR-f#aguZknc z%&)b)x`jw=UulzLfRE4VFoka}H$@Pv(B5F7_H^U2>N+K?XTaXAXW%3FK*HKC4B~r( zy>l6M@cR_n|C!A38HnH(#Huf%NZ~NK_PXTF?^mIxdA*B~NhJM}@@ptGQV4Rmuf|j9 zC{c`d77sN*iOIUZC=E3;d*FNle#E5y-lLhg>HOwhSU>q0;V}Y7B)(az zW2{YgQs9KBs|Q17r#7(JzAxeHiJ6gwjqxZ+j@5=oxoXR7?{|Jb4MJHKNh$o3w?F1d zv$VO@2*)w7w#*)j63KAagLW{!5{9ihmoflV)P%4#l#qf zRmHY7B=8l|@&jkZ4}{mY1H3*xcS?4Aqei|oYpCYn{?1Qr!ll4vw$F=7X#RN0JT)f! zwn$suig13`ctTyIp6W%0|I!I@(-Nwh^_%%wt%=xft43pfLpYG!vWRQd*%HT*Y~eou!G*|UhO6gqyerv z)26W2N^9@xuzvk5FK#4M*PT{4MWdFUE5ZmbWk)-BUQyWv7*6#ZcJc^7Rqw_WOg^Xv zA+iRt12@0I4@S;o+2SkAWt3pR2gMmy96F)3i)%BjI9D}%mH2u#i|+6^25KD*kFzz9 z;&IP_tsBo9yHgG^Khimm6XM|(JucLZninJC!bbCf^<*94(;snaC&SCO5NMN+F-sF< zbPuYe8WH6$lP=)f^fDdT-y6-6oO)tUNZ;P9)(-LX#ZM5LvTM7zyX4?hN~XpDC3WiX zmV#?RhLynqtBKb!EWZ1O8W(v>agHRztoH?MZ;+$0{Rh9s8| zcBw1V$NWwoY@5YfwX`uFGmS)chstp3fyetiYYhS>)C8IDlO(I z++xiN{VQgL-6ZQ;y$Sty#REEb?mwP}GKILjEH0)6N*dO4bw+nFTbdT09!Tw{j3eLf zlE%I6P{f>L#%ll)K-Jy`rm~oeLB`R;fc=!|gMfX()M=pm*!ifepIS~u1mYRhr#7@% z^kH)aKPJF;sW4%A*K%GKuInSM$aKmj)Nr@GY07TrM29D>9DhM3eO6#HZHJHLYA<@`=9bu`-tEPU%TR ziG?W@H5Y>q`YsY?!WNo?$CUl=TkT){;;*L5@prFLb$M?LU{};PMYb4aV|yD1J40i8 z0P zq$V?Cq$Yh}+_UH7G-eiN7_sq@88HdCE(Fnhv03>pb$Q7=+J)nL!W(eGKCHIY^TGi= z&1Cz<^OEz^L4$$Y;>M|Umz1;lNfR_WpXnnRYNO?r{*{;28?5v`2}i|l7v%BYI+EM9 zXmjM~N>>XIW~TLYU7a`5{?^O_LkWB|47#CMGhX}c)24@OF7^#Znnvux&+JPFPERP4 zzy)&++djl)a*q68RKgVyul;+2tj4^t*?Y!xS+3)8Ak{Pi2|RQRQ>O<`sVkW_M=t02 z&g~6iPF~@m&3e4nJHhZUk0Y5aR3F+J+gmvHP*RfN0QQ;w-QY!ohxlOTbJ#G z3_FsupSSazm)oCdHkgbG-!=BXUL>AXvWRqxGBTi+kwka#;*(0DCN!d%k*$v8UwZ(T z767D19rg@GD`7s*B{##^m+%{A{1U)v_6BV*A$6^6#5l2KlaeoTdT|Y_a5+m=Lj$UP*~&l>^!7V0xiu^n0peJ zG^D>$3C4*iO-Nrc#l=Qnmh<=fO0q1`pm1)o1v(?zzxC*7e_Zq8*#AMX$OnZ7l&_L- zTTpSso-Mm}oTD7=`b#`LqUwmZn&u;zB3}^qb|GFZd_WO;(e!}glXGxF>ta{e=Iat_ zL5r7yzvAnv(hVo3IFrJh-#!=;{^0pwsOyZvOlwHzqw|LcLqdF1A2+E}h+9r^Oi_J+>dOx(?`*fPJ!= z>?(X4_?%tnrquj_Ojp;dLTtTc^64S8OO-jvD&_VF|HJ2cVK?4Z(N|x6qmFLfKV5&L zqQGxCrx|>nV}lz7LAm;({H59o~Ij#vl}lu%Lo27cV|uKgvR`Wtq& zcP*Fd4Z9+%8OfF3h3tx_ifE?t?VZ+5Zrbjtc*;=D-1ttSUc#F5&s<2a$tH*Kzs+9< zL9Na8$Y}68xf@&XJMrCHOjm+!ezyic_XPcj&@xrMn-HMMNHl$79|Qd%OXjZnvhmRf z)aqyZex?$}8g_O|xYLPWL&Z{0xc|r}hHuiL{v!{Y#5%SZAveDQ8T@Bcvw|4#7DarP zkeB|1yydJnDRe1-D+LAOD<>M}W5mVI@-=f%(aoNZD`k2e1%W0DorW=VB@jVuznhIr<2p36}YFaQzLapcp$DBf-Hg=ek;iNlljMW3(?o;)$AZn2%t z(0u9twMtI2+2+x2@`Pt|%xG{uxfY9#*{APF)nBRyKYwBf4`^}qqt^x#Q8_)e;8U+O z{$5MyJu>V`cfc%L?okNFREq!Z+Da0{_Qq>+ z@}q!*P~bs}$K!|~x6&oEy*Te^*-kanAdjNWJGWYgrQ6?rIT4z6czrL87-mGB^jH+e zI-;^7C&G=5fQxWpg;Byn%*8pO;_$KQis&StWW00{N#;emHN(nJ1)NcPop4trhW%_6 zTI!JSU()B&Rikv<1lv@ElDS!y`5$xI)ZsFVpQ?x&K3_Q|IZLwfOJMXoym+CUu2Uyd z9&Z00!!a_bCU7`2Dl1quLO82a$~2N%z2~5lw|h}^3``{cIcmr|d6F7edRO#_^<^Si6)&6gsE#RLjs zShCPG25Hr#i&n=wSDA$kc(-t8^9pHV);RedR4n7y$p*&gM59EML(yMBnc8b%fnaG0 z?T-yX%8Vwar`eWuQ6E^0cj;H=ZO}vC4>a!StTBd-8zz@bhvy0)ND5y`caBNgNy9{? z+m5-tts`U74Y}70tL8lju_%-`A-sZh^mFF7q;hbS+J>phw?A@44fs}Za%cpPERa}O_1XN)~ zu?rK+V;V9|)9iN(?d>U=goevo>fz|G4f z?fqoFiEE$zfayhr>71W04j%BQr+_L6R#*&fOM^v{tyqR4HF`)$W&OsSzNGSZCy0Gw zIyxv4Bc)f~QOLvV0*S-*D&RyC5OGLch%F*=H$|86q|w z`I|NMupnY}Z{b=}EmZ}Vf^X7S0VbpEHfkyKFIi2aZ**OGG!W9Ost?Sip{;%_v%9g?iXjurs;&M;sma58^&;WC9uaU} zd%@3t)d`;kI2W~@nON+)+^8qNR*(o7p?bQFUOaWaQ*w%ujl%m@J|}4ZKytV1>-+B~ zf!~c~;+R9l7tiO38qUv&wzcAbBQV>^x2~atW!a4A*8=4MQqhvt3QHqT!pR8s0|$+9 z*@$LFnQ>bMT1)tSf|{;-mBrg7^L%y}#3MG_#LzkQe5@Us0V6$x%Ofq|+wj@=#ljXt;aJqV+6} z*sGfgR^#rW!J{f&sH}tBX(){nwvUe$Gxufn{PL$)x_qG#S#JrMeV$Ppx)tfgOkYrp zIKl_wEF@~}czgs!a+A_T5(*rppL$!MawRVW;HR-i_yW4E%V#JlUr;z=6ObN;$cRxAJ1SIM3{DII%^*IUCPB(~VZQ zB`A3z8!var-g^=^*V%6lULvdxNnWB1l}I+9CeJB1xtxC5zl^wXTl2s_aC&IB6tQ+) zkEao?X>b(n?9HsbA>Gc?slBaDRImPKeKrY{M4-vY3^>0e{bo!F$cjSFPLjG)xF%XQV8SWtY5yEF3I1PI&vYM{P0U5^{~f^ ziO|@Sc?m4ooCYdx*C{#wo$$HdM`v>tsF5xYuH5Lnm9#*CJOt(9gLasWF@m0tXW@Oz zh?7lV2U8oGgn*;;_GFiQy9ny1r!Y;gpg92c*)HjBTl=sewtXYoWY7$0kkrTrzN1|) zbL#C^`02dlLWkf5!@)ND-*2yoSu;)Mr5}g*s`8SS@=sDEqhOdu=N?y>hJBL_cOTeX zQMKO*YKSzUY$cx!=8X=DmWV{Zea-aNl)X&MS7RqBrkc=1UFt=m#`f0?;d#}kFeNML z=%V<=2KMU2n{>I?nAQK7i`EoV`n1FX_?Ds)K9@q%C zhwmNtO3%2hAEoPMM?jo}Kq^z}LT_rh=H>d~ZL8;rtHNSzgUwiuyDj-JWs&HPhQ%%I z3;S8#-%X16`N0~@nRTi>lj22zOR;1YfxBytowY?MKY?2Yg(JAV)f>KD1;n+Dcr_9v9C<`26r#Nvgo#L3 zeV0|}QF^!N$(;Mf)J^V3_=We&w#8?HWVX}p+$RHhC}GyQnTy9okGsZ>`8j8Jy;unr z%r#+=JB0Ftu+P;MpE)kPDd)}QRR4L2vJ*-+eRb37J!HcVC~T)+oHw6LkA(ep!r?`sdt=ass$7r3 zTn4Fpq2?E=gbRD_sCc&ea5k*??dvehVZ#m96R>w-hNm?eZrA8}TYQ(J)=1KFNYJg{ zFGkv<=`W-u0i(ya2$m|2g2AufBEd!!y$l8ZLK0`P54{Ow+h4yRZ|9K39?joV;t6B( znHl}Cka?wCmqeJDVlwpVGr_2d4t2Q@XGgiKNBpJpirD0?_c|MXTxtv(n|^67Q^bqo z&b-v_5q3`MO;>|%NPqI}G)TFa^gDTwdF@qsxAk~M8YoPb^*|5azcBG?9*c?e9Fk2U z5^`jpP+&vweTJpBi`1J>(G4+2vGAa2E0K^hp*YjY%I%=msv(8G82QZkVI14aD#vXn z`#0auVr{06V~3!sXUlfUnwfp&^Pbq-vHB;@NK@Kb11p~>?e_XP9^5NdM6`DCxWPTF zV7^?vnK=;mTVrB0DXB?iy8S!Lrs4Tv6X_Z>K^ijAa_mO4O6>@PIbzue;kVl6Zpagp z&!J&x?ai)qQ_N5{%eGH$p0$a`skBG@-7D|BAL&FxqgA|`f#M-KL&GFLaj*K*K6xg7 z8Myntv`Kl?d^O7*cMaGSADuZIkE@8ID}SvPZdIH6iTW@Hnk_jJO(A3_=lcc}mhZ=} z=Imm0_vHGfBOsP|t;ra_&q~^;Thle7x^|m~&26_XwV|y85s6j|U8x9&T`?n}JWGr+ zZch5t>k;1|rrxo~%`!L@P5eb7A@sDTV-sesC9*J_D2XvjZ&EY-We-NX%Yo=rWRIs#BNl(c}2}z?sxa;JamQSncCy?V~7480fOl96uES{2L?;W-J z?a^^_ODdLeHpQSByaham=a{j1xL#&YIz|U^N)FAo#IJ>8Jqq;$J?ivRJRZ)rSuo}f zdEqC&Qsk_A7|kap63j1OKP*=1@8}Xll)NVP{A9+2|7J9r(JdiBG@(hf56|`DST5eC z);s!}ag+X}Dw_R_FxRB@_Ya?4vn}8@9}>TsFX7xV*`yzB=SH7QDwx|`G3pM6oqTg< z(gtAvsJfxPOPCrJ;!F}B7E-(MXnNypq$$RrKeK4^W7J}x%UjaMlX3PN$lgzG;)gkU zQA4x#m)Z)sAG4xG#!ViX6YI8TPI8FG)krS4<`qv+NF<&T7J^*2(e{VMVpNm6_OMfO zYIv09qWjm%wS4kT!OOjZSRy6V4iY^UY3dZdgTr@Fa8QJpOU6%>9F_QP{Fq|WOuon< zys6W{v-EYx{G`J3qN zvCG|+)s)))>O0GRiP_8}B;t|q%c*v!h+-jVQ!Zr{UFODlsauzpp%JFHe9}$%W($4a z&UtDClicU`cp3_A+Wfxr0oo*_KB8wmRt=?mI^C&&e}wh${f$K|brD9Mh;+*w{g``7 zT6r3q5J0wo?WxcY8)Z=u;g}|2T%`_xMVf^~XL*b2Qc=(2k+|EqRa(hjI#tJ}6IDY4UNO{Y)oD?n z2I(;^=L>cJj1;m}V!(`RTbKV*=BS6R?6s%TaFz08$gHqrT;m}98TI3>2hi7~tV>0~ zbZ?|766xilC}~bXXzbxHdhBBi_*24So>cNaYeWfdvXtx_8T)B?b&jnW+G|?kC%Kdn zl~EMJr)+n!u(ez0NzYCt7+Lgi0dB$GITo_kaErU7txj(jDLmc=RHiba6;KXifP{fN z^r+ZBGdjGe|JGsOqD`drPM6StnhM7Px)nk(%!`V6mFc`GYbYHU3#I3JTQeKn<*M38 zv)?E>cqVCQWT#rrFq24@Og1LCNVy$$;&!9sSt&?Q!$HH`9;ti?V z4%1nzID60=d|eVxI)Sh5X4h%I9?mGuq*&TGB0N-^7?u(#waL`>n0~#G@G}59(daiO z|0?ay35YI!ypfkb0!y{`nn|~>CmQ;YQ(Rr``TJynL91BhSDWvid%Ox($aN|UD_6;T z<<@RDeBUb8#rU|>uE{BE-avK7{W^$1(;MWUjlO@Cw#_)Si%Pi#n7DP`Z>f!#=?xbliZ#C~b<13!IQ)${5i_HgoV>Cs_&azUU zgV_1b#xXOh`DU&s+MFcc?ecyu`BhwCD8<08%@Yu_keJxMd&&NK$KFm?)Pga7!j%HJ zLg5>6dyA$l948ZtcWPHP2%Px5yzzOL%!H!{4w#?(K$X2vaZ(UxC8+&kkhSfF5?L92 z28S?r#mnLc`MWElCkAYFsO{OfL&gn`KeyhI422LkxqrZ%RVMlxyvUrrFE7jIxify* z(UELx+Y|no$L#R+u_tDJg>^6qL$qJb=SMigike8HTtUA zmtLFd<9CtsOcu?h$S0dCd^K3KW4J5SZ(rn3{JbP7%yse9m_oGcYN0$N;U_y&Wwd1} z;~6vNC~mUQWMWa5zWhq7>Pl-cbs4dy)kx`)iTlfhYbYl-XFD!a@IFV1{b!ZadXBd- zz?IO59?7rkc6mMd!T~ev6H$I+w6`AG4reJ-gqsi&6^1x2hSqCi8mt51x+7<*bqj=p zNFygssbcoHK?#?YBDe@Z)u&5bkMS;7_~oYH~HEvQIlG7LO!=u*?Pb2 z^LqX6&ZutUb(fO*#L0uX2IJH8ud&LVGvzMQ2Vrg0i?7mITO2yCyF{DC;Ixg>JMpq- zcqDn>xXvdysxSwr&1Ro@i1<>?h1-NzB{8a#^)KahhDEzKD%*OD@iHdCtc7CyocC0J`SCSgPlvAOat9%qI z#j-Xb9dAuzIlS*fwB}y-4MDk6+)7wOuN~3WJw)xrzmg&*jYtcGmXE0ni| zDr9bI6<6<>l(D5!H8+1}HxZm^c>;qi@?8y7zamXw*NupQrl+?MY&MfVE*}-kaPJJa zy~PS_$FZQ3&Kfjk4*4l;CF=e~PGV2JQKz?bw}|9G5g}Wq2^xa*#Wr^&2fYh{q?wr2E!Vvf^iU(vNX(#p#@(H1Q#yN(A6s5?x@oSqM+j%zqhNCKu541r zY-+Y~rr1e)@0;uH6}xK?CT5k@sjR)Nc7!)pD_P~B(2i^sHLAmF39ojpWtffb@3P4nv}ec94jQ&U*VQee#y)j$XxH)k zy_OzJN+7Xl^rmaV#NdY8x1cjh=94T!6@W{A_KrHx*7)-pt8Eb)p>3ze^*ef38=u9D zFe74-%2Z}}{B$AeviIRd@{7LzuXj*lOR7l=Pet4jY?3axX^e9}fmhwj%olZ{g}c_G>HY7HR^ebM1k>F-&I zAEA6nPMoH_UzzG}>Qio4OI+NtZ{2tt`}==lhgKt8O*(Vj%gX#lN4rAF5>_g@V%TRI zc%{wY6wNb&>jQb~Um&lI8VPl%9W_hX)j}8z1GcQNf`;wbKv_=~=_?!2#O`jS6Fpyy zw2;h8bogSKQ!`I*f6(lSd(P(k`>aAsMrM8BW}rOwJ0T6!`tqZ3+=z$4`kc!P@nuVc zY?j|nJ3ssN7}O`MRnf~d_tXuz=HyJMfiEg7ROK8qmE>SApF<6zWmX)5$`(z)iK^a@ zL~UXU#SB=tHg|SmdSQHQzHhWI!Lr%=B0u%A zmHpDVd3EaYY}@zY&ca4(Y^!=Re^hW5&5T)3IL8{RaV1d3Gj&D4q0+X}ywJFit35^H zbXwIR!8n0yPAAWE{3OresY_dFe@%a7TSHrU+f{J-{A=r3vl+7@4)u7)H;!)#_77)= zX0-NI6fcc1t=t|irCPxGv|t9m+Z?d5`(#5l+(U=a5p5CqHiFf*ic&e887};Mg}=Lm zVcrsW1}jqnmZat+*Y$UcVR7>2cX2k?u;uS}H-hd*;TDBzuqDGyDPZWe&%|;sqffNK zZ@hO;C*@w-mswjM207DBcHWskcX?RW8`MFPh(njY&um589iyt8Cb`D#mbRbb=m}hG zCfMQ)CXmeabf@Q)%6I(jGwu(+gP5*L&=rNup5ZZdl%Zzv?Vm$LEodvIuV)YW{r3Q< zui0_kj&CQSg}hQ&{@0^oqqlREKU=2dX(3eV(?>Rw`3&FQ)q^NFq^RSiWoNG!Ogj`J zX^Akq3NEz0LWA*}-$y*F3FtMFe4v6STlci|BFtg)fp6l03`{@X2ha2Y%PQsR8j$0& zECZZ2sGlzL=n9SL72oH6q9FLjKBU`zLjNbOi900Hlk0ae|`qk2^ za+cMGq1es#Ww}?Lr55Ke3rtp}Pu~}9lj>qyAl8<@+|?7>tb1_$8W=H2%n0cj;XYYq z6}G#aHpLs{eSYm?dn5anU&1ZNqM5ZtVOL`IP}%c5-?;O3a+fS2>4=^3Ci2k~^Rg-C zO~(qe-`#PmAlp$GM$M`>WonJcZAAMz#zp!g(!}L!`is!^Z;dO7h?Br8d4{h^cT$NO>0L_{p^{JYVidMJ}SUJtbS}}_X@*qlOPl5IG_Z2RhS;c z4gtL&PVL*+)N5m80{$P*;SJp@+E||J@4r4;gp<%Ux33rxBuReyK^6+E=#yADQU`Iq z=Wbh(!?JnL-M_+4hGpxVEW+>SO@=j{UfjVjWt+F)saU*T>bd0Xawjyc%esGEp|A*B zT*A1%8BKLBjcb2LsMx-uhBZN^vr@`Hq*L8;pe^9y1l*h54tKiL%YCdPoS|#sMFekX z(MR>$$I4qRwJH!>jD4iVcJu+LY7qAwW4cZM)Sf=r@hAx$%Kwty=KE(;*zB5VyI$t= z6r~k&te4FFCn#8iCXC%e>x88q$znQ7xRY;|^XXsLZ=^NEwkMPypCovf=DcQh8)b+K z@#ARznT4%x|GKKYpdqmRd-2he^2-kLQiED0ofV(;FJ3Dlqi-37q+%}g;>mA2^tbWq z8=~9scv&|T`_uiso6nBLg4Vj>teQ_S?bAVHbVOInU@S~-K8sJ6^j~t@-eTD&q@|&o zz*-CGdp1E)?KET*p}v0Hvfpz1#w1!fu~dj!y{CJAfIf=={d&phZF{z#&&YvVpZtK& z59yQnl^LqKSmFmOtu!rzE}IB?Rzaj16veglRU+mDRdgYC%rUqBjObbEE?ar zHC!^^IXz;(^a~?KKPqpllW+hrnRzVgoL)G|!3L=G5sGSyHrauZ_8M;@;5T3%OmIVX zWxwTAFLJQyGk2}IK1V+ME$q#~u1%FNCFJMEaFEClg?z0k{?9GzC^znOw*;jFYi~{( zM39#%Bx~LzT7`Sw#Al5*Gs)7ImIkqJ5MDo<7W9xO_mu%dYSI_XWIQrE21;7)G{Xjk z183BZ>oo5nMyFD*Av9Yu19-=4D$>hf$B!@~J~^DvtfK3}StRp}LNGsndNc(;kfo0; z+Q4U=XjL>nJu(6^6d;y7mJk`)bZcvCXv6GSYc*P7t=@_r^l6_77X6+T1_}-81PTh4 z>t4=gn!Q&fCZ0gF;^Vg;ojyHohweTaNAY=FlwI4WKGtzZDX@0O_3-W(|FU_dEKKdc z13*Zg=0B*GdlE;~*xu02{5=u}{*%m+*SA8lL88VM`sxlU`qoHT21%rv+TSC#LiUD8 z+y(&W;0AJVa6q9LNVPvjY#b0SAU6cgeGj}MjIGoGoXC6RErc5h+vvZSG&VOiLjWLL z+`xM!q?Qztr!hAavNp9ez9)I_BN6_C{$T@yI6y!y5R4lPVB>^xAl-nV5C9kkhX6Ub zU`Vb8!U5#u0CRIAv7mc1Bw=IB0r&&KxyOtCB7eaD#u)#J{@m;SY4LZ;NN@M(4-y*I zw>Q35_-E!S4hD!nP$>~9(fe=j9U++>BduU(WNc?{Z3f$FfK6gUIYPfz>%{1$M8pdTwE|DsKpHj1Gtfo3FW{ksMb zUY**Q*F{O4>(K{>;^H5o+U5z1eH>Ib3Qj!oznImB>I6rkHk-BNs<}+du7J#b1%03! zWeF3!PjQ>VDnF8Rc2|lHBrjOC;%1Y-jXCUdVs}kB0C2%rN+CO3AtFURlN+)+FKS|f z_O{dyB1Y~8@$=+EuJYL`47;(s7<)_!tcaz08Rbdnz%(Qe$w}y*W)6f_uzKi!sPI&+ zFx7eBT4`)c48r(^MuGDL@&tkciAx0%@d=EK|t(fkX}es7uPoWuj`MW^H~?`2)az(2{?bE@wMq6ATa%`o{qM*9!pU z;(~AiOaT8S10%`G`xn6aUowvSI{6H98WkI=V6{4vpB4j2bF1|6N4 Hg82UdNwBlV literal 0 HcmV?d00001 diff --git a/tests/workloads/sort_kernels/MI200/empirRoof_gpu-0_int8_fp16.pdf b/tests/workloads/sort_kernels/MI200/empirRoof_gpu-0_int8_fp16.pdf new file mode 100644 index 0000000000000000000000000000000000000000..4f3255ff4b0ae3a8a60bd8c28fd15ebbf2c9a7a8 GIT binary patch literal 13142 zcmb801yqz<_wdD_Bo%3JXpov@W=IL?Zb4$`p;KB!kZur=RJv12K%_xZT2fNFyZnZG z@B7|2{_FpJ-z?TV&+OTIpR>=i&pw;Ae#4?HA;}Hmf#S0aZ>-JZg8)E)oslKJpdhcf zqbbVS&Jn;aZsBNWgLbjuz~@zVv@>xrHpK|ltk5W4j4i+hfxvw6hcepERs!X03SgJu z2Lr)SAOr{p10f(Nk`oAI!~9|N6zoj?cNJk_d{bMKn<+s4o{BLF0K(@LQvmQP+Bw>w ztp8Sm{;eb~dZYBGs=PP=h|eo8`^UT1ja)$<0LAB369qUsx|sgYzF_}PzQBL@!o2^l zzTp2KzW#6XLj3JZ5^e2_S$$qfYs@-Jm>S!eU}BLswKaFP0D$-qU}0f^lQZVI+2FgS zZ0XuWPVo_3ZyU@H+$oaH%A+u(927V_ubaZUz|xySO%Q6I{PvBmppy&UY7161-q2e| zlyk4oi-*KfYG8F7j$6KRd2$hw7Uz4sD0kq>1aH1ung?5Ytz;kqYq}o1Za;}i&lvGK zZwr^_EKQ%Qxe6>bNP_Q_U+pW!ELYhE6UXn@oqa7W{H)9np!p22;A-A@_|nm4ed6sH z|8*yuO-G5+TXE+nZaQNv$2w8A2B#+6)joVpy&;T@%O67W42xR$^TLi7v!_fMl60)8 zLOzr0B}F4+vx>X-2Sd2TkfmL3KD?7ulS$h95Ei8=o@h42Zp4k|AB%cer2-Bqe2vdq zpi?2}L3ICJt!thJOFDptY}66Bky5ZsDy_1n)ACi$t#m#&T75+8)IZ3N%qk@&wmr`N zmRL+fierUjj63kI#k*(5$iBNaYU{|l#1BzVv6j3-@R4g&0se}_=|5_aQ#|M-k1B8B z7~60Y=)EzT?Y;wrwd19QxPAJxWVlkqkyW|~M2Vv_x%$?@<cFTzLi;Pk66<>zpc zzRDQQXg8cYJzw6DStw6_o8HLw#l>&2<)V!ucp-R9n{~&|ndny)P2e}wQpyXiM68`S z*Q+k9PNqjEMrL9$gvo);YF<0AnzB~q7x<5*NiL$|4Z5_u(Qar&n4Xx->aVCHc2Sw! zu?dH-W<_nj(KUX*mtM7={NyNafiTd$&ei1FIjf1MVNwfld*nif)gcdj^_;M|pSZl^ z`)}^MQk}|P9#X&(;^s~Y3NauR)rIGG#{?2DjTT}2F2$WS?vt=?E#}R|L~FEEdY!BG z7iQnb4)#Iab19LGtOEQI-446&CoTpRK<-vEIqb#isx^=YlEe7z{6dzThJBR6V+49} z7M7w5M+M82-|#H3hn}Ql^s3z_Dlinp#zm%RP?`qkkrNF#QEkxG-40Z)49R8(X&g|u zwmu3YJigoe{OPmQ0&0NjPez7;^_5$xcQnWwp7=6m3R-R$S-q2SnYSu&-^QyM!oD!~TtXJ__yy35O* zIvkT6^oyjeA=&-9g?XmiHWfwWpKF>!bSxXom;HiXfD^rIh@O;oZ`%}RBciq zoEki>$P>%35U^h~`txf=&XcV5f<-HA0vwz!VQ=gG3$v2ZH54U_|JFnKsjm4ws58SUbTvAz)2$SX|C}O)DC~Q) zUMbk;^x5RibHBd#)ivik_v;5bfRalZwVp}Bc*Yx$?+js&Civtv^!+BSlsyS8=Ny!s zI_6%ynV}qUQ$V{HKRb{4s`+!Otlx{!y3}_IR^~n6+gC4yZ&HD?#GotBYx{cgbI`H$ z+-DNa)e6(!LuNCK-W#{I^QY+UC;D#Eo0c(6&6K)PgW1uJ=hLL)!et+DtU0VJh^(kR&F&F-NC>9yJ_v5Q_CDhnxWbk= zet#>;IOh9D#<^6SM{mL-Vq=y^RQYo@cf_(R?sv*-8jeZxp^rA)B({mFQiJ4j%7u=M z$Z5dedTb1>Eo7Urst%^U2F(AIH4}mUzP*iR7rQyv|2mxhI^n^8A8hLG_ND+{Wt2JQ zJX1AwvU71XHgy7Ex)4mqVXS8A4AA|f+2B<-b#n&r%Gh8O#s0dA|8eG<}9V= zeA9zqOr;=zn;t?HpH~VBxM>t_?qGnMWB%q24!Aj_RWZE;ucV!=^NochAAs*q*^N}e z)C7$ZvvULJ0x?1u7{&tv10e953uY*BjE$+SvlHOvc*gis!!#Dg&dMmqKZKa>f^QPy_mH{+ON zmg+x-0sTuO_h)|q0)W79J_IJ%|D}gOz@hMe?IA`z+`ZJFRr_e9dfK_p%?ivs7g*~b z@+Sd+7&gUduzs|$V_^|8leA<=1B$TaUo$Y=#`eGatgVanwvhz(!>1DA>{DU)5sOZu zEJ1P-9f27P`3-6{0=N+aXIIzf-mmoZyqh#?;++&z`G1XU$+0uE1&BOg@WVEpt3%1n zJ`l^pvzl?8jTbtt`;-=1J{?VxJ*UT{Hbj5A+-~Z>nzL~AJ=SdLk?h5bhvi;mQ$$U+#URoilasiH46%$>iLfTaAJFCIxA)fW7wM50A=i6H zy4}yxntU!e;vEEsyq{<$rhiWbWG!-VvB{@`%$q%Tq^5nBdl1(tIOdAqLPy#g1Gb_) z9Ni>m--xaGgF~Yf&$N$)M!%P|U-X@M4 zmb72;FudNlADt*=0R<0B&XnykSjGpWiwQ!5;0*LRX13Roxt2>YLI1BAm)(*Um??R5c!-yj5D_qE#3s$fy~wvt8?EeMd#(X=s< zM5UfLo39Qlt5C`FRZc4Bqsy%Ki2f z?dV`8e6%s=NSA!Gv+M46CEne;4pNUlJx46)`T&huABUZ;^f47QRYwM`c91qVD9|{t z9t-Cjl|22Vv2kVSX%~0I_lzPdqv*`+E&T!rB?~7r|aE-Dnt!08-9)$=5P41Y4 z2s{{LXfcr3a%~Hv`(bgJ%CZeOuM{BIs*lDU7$<(n^h*9|N9+s6{H6?R=bZ2y1qnNT zLw>Qa71Ro88(QDIgmwP-{c(0%I8$O&wLG|o(kcY}ELkvzY?wReLLSLlZl+!_2$PWf zHoVMMPWiC5MMN6Q32;yH-cw!>s~{B%+^Yf~dxeQbze3r;k!>a~S#;pngUOdA+!Id^ zZ}n=uL14+LbKX&@s*tfdu`O#W=Bq(JcyxtFMbaCb=&%#R z&@9|iIv0$*ccAx1yBD1(h3(|3pmgVX*t0hmA9RcX1Xn&~rLZWz7JXebA?S7Tli+ych?oUm=;UB(-q<%d@ zEG3HxGRyEuKcDU=w7~CQYb&s`MdChy%Mx?WcsEZ)@b*_#-y9U14B?bid~BWe0jrP< zr#3~=lqgRuahWL+iC51o78v7P#InRRvc(Ba-s}WpZ-DV!-XZ$j+SbG4; z?>?+&Ro>3}Z9}^OJ)V;eVGi@llSRmN@MqEgO3J&E6sI^Visy-akb+FMR$C{_<)Jqx zeJ~|Dm!qbmM!C#iEN%sUy6%7j0| zD9q_NnnzjTi34-EL3ZFJ?7#}<*_yypd@4ID%tbfk}~F{ z#qnnWOXKG|^o!o+*47FAO`IM!{C3>k1u)*jv8pQ5@aT-C@~Vn@a<6lpZi?USzh54N z@}vfuhVPA46VZ~;x)^TXDxyJRe`H6&#)xS@%sh-8`zCxz)Lnd}n6&Oaa%|zXBV`lo z>58W6v3dz>vTi$BMa9C3)g)Pv!*m{rV9`b7P&rHI4S1 zLp4^*HD3M@bX18vv(SZsDrFAEVG}jB;iQ!XAGC00bT3g@y_8alYMi=>teXtw(aB|? zG-r7c6JF}sv^!aXH}*w@G;)Q;E@YZgp{&qziceYG~Ynl2H#GA(shXOTtP z4kVDZ`I;w6QH11`5wFD=7z)~tyUQk{HbF-cHUg7Qn`JtM0l`hbCOST`dY0-VMCH_; zXe9Qm;fC&f1%F0*lr2^nMk=2c7qtvj6ga(u=-H zgKcG4#mHHj!Q;)rQRDtpEyLPJqJ-GBg?a(-=W-i_iH1wxzG)Ac)WaRmZKv6b`um5) zp%iO02uoq1PT2`?od4CWA8pLC%u{T+P^_$gw$DZf&($~XRa+D2~?Y*D5o zS+yqxrTwfvy!#V~B*n$|ue3IJ>z68<`bjp_XJ6_UNc5nXQOvWCGe!{7;pk#xjoN0L zaI6~6C$zts7{?0tWMj8fpM)E~OlA`5L)DbGL5*snPZ4`PnzkP2=u6?NLzv}Htx~;3 zt$fk`h1@fa-du+T=gIJ#@m)s!jvjYXJq3!Pz%|R}BZ^g>P6l|b*DEd75$PgH{R}1; zcB7QTojv8uEqVL5`P%b20k5TpN^l>EVMmu=X_m=y2zQWP8yZ4l`9O{T3Q9V(tfP706cl7F#kaQi& zeB8G>#vrWt-SjYX4IR^yze@JTcKaxPp1tF+K_HzodAIpZ;6T_}55V6neiHW`B~Tnf@lx#mDzvPch1?Rp)eYhAUK;^8EPZ zuPT%MO8k|48rwkfW6o$=YH>Y94!#m`BS`}A5M7;Y4i%RDL(f5*i}ZD!Bgx|k|MBOh}4Wx=*o4c7fG$J!T984arJNR$D-%&`+! zOVTT{T73US0o@f^T{h(KVtUa?Mu19&ji98%2mpOdy#HA_NuGbuWK~gWuwLHvz0{(+ zH;*@Eyc&cj+qXmPGabB4XqG-13*S7>e7Dj(vL+(IoBP+iv)s9&zPQs|+oQ=a&bY`p zso1@1Hx5;E-pXfEW2-5!YJ5l`gIsT+^ORA`wE8``ij8bo@!Q#2o@$!Sj|!XQFBo-O zS;~Fei8_|&34KRNJ34tx6kjMh4p#(?o{}-@Sn)@$P0K$#rMhlCh37^HoPWK~rr2PA zQu$;5hu)<_;X8x#V}nb!(vv0bd>lR-{-{B$Y`x$SEvsW@->^M4fA+Q)W{j|pvf%>G z^~D|Pq%~uW-^@cGwM<50(zq|Bym&?{F z7yCHd4AqCj*&XG4W*Q4)Blc=yY&D$CHn0yzk`Hae!)2?gpin)u#n9cUFIrWqywh25 z+~M&@HVR@MI(b0w-%gM))@We!mKRlU-A z$nTL7-j9T&b`tdA{OiKhSCaC6QZ+pe6MNxzl#M+sK5yZce<+Cxvt<_gz~Vq>A)w3d z#~WZr9pEwKIp>#tU^Q~ga?kP?@811Z`1e<$dix*Zl_4%+U($7&EPO?84yej zmdLc6PqaN$>O0R{BK&RB7NKYmpSTMeDS0EiNl+YJAl{i7BGX_c(HaYQ6OzW+SiVIjg{h{RK5KAQO5H z=E5LRsUvwTKQdXS2@C!J)Au=p`PNveo#f5d=r6XuUs6g8vvb%cVwJhy-s?>Wq6LsI z{6M`5K6BfUNouIBgz$`@!jw4kL2^a6IvqS`X*T z1kEF8d`ae=YRo~T`6`jM)S&*Q5FET_vC=rTL?6 z#JOradG5*5!<|ct65=7waqP9Nb=T-8cT_EhA<42!xK7j#G|YkISo2@-NCJ~R4QzuX zwUtA?$|qsLLoQkt*hjm(r!r|W=^rmFVCml~-O^GVZG;JP_0ZwiCFztywRB!k0dnK=msWFJ{NFV9Tgf;I!x8etj&{3((p&-#COC8 zeAR4`Ii*4YRJ~WTjkZEYY~{0oC{w?;+e68hx14&H4Mumly?FFwIz<#+Aoq1O_vJ1< zsm17sHwER!w=KA-kRie{=7WK&v3@vL#$r6bX?!A^27a&Hx92$#?GMkYoXamY;*~ZD zE&xn9D&2WDtALd)Jsd|by8eZ$(vV(U!1MENM%Ojo@sHq##SUHG8?5njDZR6{ThDGA z54-3%Pai$nXMETy!{}CymoEJYS2Z**e=g<8#WELCt0XQx`VojfB4iQ9hSM3Hvxori zoheKXDZ>w0V;BYFaS4-DuL9Kd;!DV6Sva1iaFTbQOZD8P6%XZeAZYh9PVBO}wly4I zbLmxlum9pTmHM5eJEKwg>y)d$4SDc|FP#d!g(14@xs3B>iMHa;Az^XKVTCG&`hk4r?%cu)h)qajNJV?Td6a35?_h3tmV)()2GPk~C zOaipaT=#HS&Z%M(&F}zyecLsDur<;a@mw7#t?|=@6r~V|o520Tcq<_Gt#YaJmV7j& zGHi?DfyjI@nedsv>g+MzmIB4@qf1Jk(1hW)`}X>syt}1tbae7eXfnEn@VQR-{ZRRu zk0+A9=_VG3ENvnKqh_z|r{|241*{9`l`?C4E~eV~T(O}%0Lv|tdAN=qy_V1T-SJSK z=Tkf5Tf_nRs^D+FC5we{+ZTPFL#`!w=Oud&9c4G>9`o{gdUc*fidWte(jxE47fp z$ff5@+Fu({twgPC6u!Cv)ioKuy)7qVP(fE;LLR?Eip`rxrU{ir;t0xc$hfk6d^}>r zGQTe9LlTxd_;QDrkcS_Jy68D@6}(&)InBLXID9M{nrzl&U+ZPOm%wH*p)`CgH+!rZ zxt)E$s&Fj9?Bo11b3jdPmJVUj&P2?;@9&EIe4%ZOGc97HAgJTGFH}oh?87pk*21iN zCy6?at35V+so_}ZOKyegX^&ByGDSXRV|FBMhuZs2O0%-4U#)Q-p)?Ki-J!3F!~%-ZyctG^$*vcyRw=f>c6hoaeX3_Ru*7@rxhtP2cM3G&<(RLu_ zz0%nD=#fZ+(Lnc@Rh&=_!^zX*C8ove3$Pq7dz$v)_v@_rV!4-(mKwh-k7h>1ywj`S zmX)_At>6!;n9M;q7}Uuq`P>~zE($oeAAe${HxhumU_VW2t9lsim+_WASMNKQUS`l$ zgr2NW6pb3S+QU22=AONNS*qO59S4F#NkLL^&b7PKi;*I1jvK~}22X^aO-?F4Y8t8k zl9rv);I_wX_EPB;y-2T5vonI%hfP(yyQuoWo^%}e=I}%+8vI$TBJRCb-qFi^VFC(X z)nCBa=6>Jk>iCXN$9e;$FDkB_WvoB3>#CzilJb(+%fFWta;T2CX181WCergnxbbf+ z8+YpWdw8^^PC4nE1zH5gspw{f33Ye>Qc4$2Pif#}z@n;9#@V9dy$*efeh1J{eDIcS z_U=MP0Qd_3$C2Q>4TVExx5mu=Pv7X4jXV<42#kp~p4O~v(|l5E1c2=Ubq|7ovFB10 zlH(FhG~P&^ZKd!PMYpSbDg2^mTtXHD~%_s*=zYe`h5UGG^agGc!iI{e@kv(D5` z{P|g?>1&6a!*gkfwHch#N7sA`mS-{R>l4S1Xg0X5FKe0XTsNv~)XXPiG4;gmS2~~d zM3Zaft{g`mcGHJm@hgixlvN2?__ zH91b(7ea1t8fx0f4$|$>mv{rUZsdrcuBLUCFIvBdx8t zwNi?c*?#>7ylmTGk9&(KbsJ0EtYMeRO6Wqdsx?Yrui0>WSFvZ5KcjR`Zno>)d zjh9=x`@Q0H`pNMWB`L_}>@Sg@nNq~Oaha1JWmWKcS@ms$PX36EKjCM+-4w56SCjDHD6Pat+eR_|J%)jjDoK)cO)O^t^Md;>yKPcA1{3m%jrW8Flw?uJ* z|Ksaj_;@=1d0(|*kUG0T{JYnK%7!5a<2fISoWIvLEp#D#aN1G0H4j*Heu3Xfd4A+s zxA#|&+SF{+@2=P=e!guFmETKBw-Hq;6oPL|)$E0kPvAb=4a{OSVIgBJlF4g6)M=^n zufBW7G9c%E3C+*im~2JJ9OqPFlnH;)N7htWmavRt7I9E{~Wuur5}9)%7K+ZI(60l_o;E#}c3^|0C)N%oo%DxwYbXG({DvqF=3@Txx5+QzzW&Y115y3SX@#Xb-uCX&TJTNR2_<^;OyB~0B6AO7O8)S%-J*5y zk`Yjrnu;Js@|v9aqd|UDifKuR{k)c!OVcx%6Nxo${zizcp_J(8`{WE}XQ&9C)M71C z){;0zI%6URGF>pW%IES7GW%oV$4KX()Ryt4G1wzGfwe5cQpz|tip)HuP|cz=)H~^7v$Z0x&>m{4l)hU8@ygaEY1nQZAJ$CY1K~*AeMZeA^)tHtf4HJ3``~= zwgvPd?dZZ@KKS>EeUZR7BF%^iWJ!k6!ud7fROz+TbTTnHZIA9}%YED5+ib$Wb(>%1 z|DKJYtE{{dH{woBE1GZy2wzJ}c1+XkpOepPav zkSsFzwB0=aW39YlAlX@v?)S=wEB!2@mP?oVdj&oH$ZYap-_P&<+NYz$$vf3yS2aFc zPFcf~KKs5+x3sR$exLnhs7kDv(eCVz_1ZiEO-TjON`3?R_|{P$u=buM!i`JX8Xg|V z_R3vb6S*^#cZas05i8Bh_!fSOrqvpfiDrym+`N98swqOT!HYdb#P)0mr)efOHS2Pq zuI`K}x|(&%Bbv;3&QI0%Sdkz)sf+74?N}Hmnr;cO!Q#a`W`}1uBjcz%B1a*8aUp2o zTb?3sCe|>~+LZhYSf`=;mbQzv+vEudJwTsMR!SwqLmr~Fr}!o!?4ez;H1>-&bucuD z1CM3qjrOJP3^Hgwz+(-YE7pF2!06c}hZ1&Fw+VkYQ)c%I@Pks~XvVhKZtI4S6LES* z{TRv5G0s_n4|^cpci=~R`a3QHvz*NL%YQ+^_s$YC8`Z$U%xI=8BUvdZscw+#>zw&3 z#@ly6i-KSnzEWlEl+>k7ICO;nQ!vm&AfN5L73pZ+nQO^En;7* zPB^C}t_JZMCzx|Q&4GKR;!z;I-eFTvOMRm#_()2_7vXFKwi$c*WL5t*4Oh!2+tLwvrQv}6OPyJtGG+7z?00MLPR@`rviaZ z4hTKMT*Z#ATtrHk??beGN^AM@%dlQl0d(g zdAtYRN3`quNak?|x8p2^MImkgtB0s8rJHE8BFKNUZ6kT~$%o5YqasWS70-Y}H1& zyoFs0fw~u9sI8JlY|5Swe#}+VYJlL}RY~Qs-HvKY<#WFqC}0CjX$3Yw!deFz_}ndU34-~0#I1o7 z1g`d!>V$U+QMUr8o>QD1n{^4^ts%T45_nB}KC>Qmft(-vqIsr?bGT(3e{nulG}uYd zh&)^vtPE7!{y`x0d1{GXaWxGUS3d=4#hoz%%n+b!D3_r`HIxjncJ|yPhIU-Nddj5| zzEz{w{phIaZZ@`G;~SM5~Fbu>!N$!NRLQA>ZhVenP}<2f7hCXa+qKHm3X8 zhob~(1KbClk=S6vWe58h3aA(%47cx-(zYBh5U@PzU?3BCEBQLqFIF5E2ZztzzKp5# zSiX!K+e%m)k*M&o;=Lc9Zn9W&muQu*uOEH#8gez|!;+sroMq$|g(0`Sp|+Xc>&e&l zA6%e5XO>Bqzgq(@n^=D;iG2TkM_x5nWVrUV^A6Z5{%#hgTZ`!_!zZ6MciNrj0XWhB5uf8 zXHy$Z02K2X^AUo#2)62b$8!78+7O| zst5Ehu=1Z+&yDV%7Jr9~@pgmtVCZ9%lj)7Zzeld-V&wb>1|=>dar5nsBQPc)83}be zDH#a`ls$%YGQq3~+S&aNv6{ORCVClLGrJpjN!8RGjp3`@0qmj}e%cfRTPr!5m^z|u z%>nHHFvAGdTJ(L7I;HBY2DyWx_m$&4-g6GyTPA;00;=qgMfp8NWGg#Z>T3E zkOu_egJUA+1L#8dfPXIk---YTgpUUaf&%$4CP)An0pP<3zz`r54uD`x_z+MYAOb^! z1NabpJU|Ex;|BMrh#&wk5+l2L41dfI z27_ZDECdn+Kwusj90^9=pj>bSMhZkiFk=HDJU}oUB4}2 z2tofa{O8vI7!=8a07Ch0SSmgc3^RR9Mq$zj%mcj1kUv~Oc;GiF0szA?O9Z(I=w|9j z%)lVnzevKQiuL$oKz^=)#2XuRxccYLBfSkfh;)(@UP1lvn%# z9s?{Z8gck>=+&(Wxe)a*(=Okp(nh%l`O>e=8X##${OpBl*%%)5@yj?^Z^K4a1u$HT z)3?Tc4Hjxt;(;v1ZF00AxSvw1pF&n#Q)bFQM!{7IEKG_^rz1#N2weailc?*2b zbj#iwwnBkD2qAv1Vt+5y$-|~s7jlbOxw<$`cjuSs1~f9HwEb2jsZ^X~1U~DqbXoY9 zTRq|@WP&2~xrQG`n~vhtZPV7WfO z%2+k~E$!6yIqKV@P)H_;%BL8%NnH|I4l#)(U+Dres%Ucwyt<&67S#s-bJ94~pydAF z;C(Vr#%_MOV8PkmsH~KQw>qpFo6@OjU*jSyDN1pk(p@|}fiDUxx>t=UVEUtoLE_SJ z`zDkbRDXF+2+iBRMZ+;2@0R2HZ{#};b98JyefdCK;ANbD~fDZFS&48rX6|Bzww8{_@o^)P!Elgs}h1M^`v