diff --git a/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx908/0400_roofline.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx908/0400_roofline.yaml index 9c80f75e80..c8ac74a94b 100644 --- a/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx908/0400_roofline.yaml +++ b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx908/0400_roofline.yaml @@ -202,7 +202,7 @@ Panel Config: 512) + (SQ_INSTS_VALU_MFMA_MOPS_F64 * 512) ) / SUM(TCP_TOTAL_CACHE_ACCESSES_sum * 64) ) unit: FLOPs/Byte - Performance GFLOPs: + Performance (GFLOPs): value: ( SUM( ($wave_size * ( (SQ_INSTS_VALU_ADD_F16 + SQ_INSTS_VALU_MUL_F16 + (2 * SQ_INSTS_VALU_FMA_F16) + SQ_INSTS_VALU_TRANS_F16) + (SQ_INSTS_VALU_ADD_F32 + SQ_INSTS_VALU_MUL_F32 + (2 * SQ_INSTS_VALU_FMA_F32) + SQ_INSTS_VALU_TRANS_F32) diff --git a/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx90a/0400_roofline.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx90a/0400_roofline.yaml index 64ed38e23e..daf66a87e9 100644 --- a/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx90a/0400_roofline.yaml +++ b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx90a/0400_roofline.yaml @@ -200,7 +200,7 @@ Panel Config: 512) + (SQ_INSTS_VALU_MFMA_MOPS_F64 * 512) ) / SUM(TCP_TOTAL_CACHE_ACCESSES_sum * 64) ) unit: FLOPs/Byte - Performance GFLOPs: + Performance (GFLOPs): value: ( SUM( ($wave_size * ( (SQ_INSTS_VALU_ADD_F16 + SQ_INSTS_VALU_MUL_F16 + (2 * SQ_INSTS_VALU_FMA_F16) + SQ_INSTS_VALU_TRANS_F16) + (SQ_INSTS_VALU_ADD_F32 + SQ_INSTS_VALU_MUL_F32 + (2 * SQ_INSTS_VALU_FMA_F32) + SQ_INSTS_VALU_TRANS_F32) diff --git a/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx940/0400_roofline.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx940/0400_roofline.yaml index b06371c850..3cca25864f 100644 --- a/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx940/0400_roofline.yaml +++ b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx940/0400_roofline.yaml @@ -208,7 +208,7 @@ Panel Config: 512) + (SQ_INSTS_VALU_MFMA_MOPS_F64 * 512) + ) / SUM(TCP_TOTAL_CACHE_ACCESSES_sum * 64) ) unit: FLOPs/Byte - Performance GFLOPs: + Performance (GFLOPs): value: ( SUM( ($wave_size * ( (SQ_INSTS_VALU_ADD_F16 + SQ_INSTS_VALU_MUL_F16 + (2 * SQ_INSTS_VALU_FMA_F16) + SQ_INSTS_VALU_TRANS_F16) + (SQ_INSTS_VALU_ADD_F32 + SQ_INSTS_VALU_MUL_F32 + (2 * SQ_INSTS_VALU_FMA_F32) + SQ_INSTS_VALU_TRANS_F32) diff --git a/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx941/0400_roofline.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx941/0400_roofline.yaml index c847403bb1..d95178b92b 100644 --- a/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx941/0400_roofline.yaml +++ b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx941/0400_roofline.yaml @@ -208,7 +208,7 @@ Panel Config: 512) + (SQ_INSTS_VALU_MFMA_MOPS_F64 * 512) + (SQ_INSTS_VALU_MFMA_MOPS_F8 * 512) ) / SUM(TCP_TOTAL_CACHE_ACCESSES_sum * 64) ) unit: FLOPs/Byte - Performance GFLOPs: + Performance (GFLOPs): value: ( SUM( ($wave_size * ( (SQ_INSTS_VALU_ADD_F16 + SQ_INSTS_VALU_MUL_F16 + (2 * SQ_INSTS_VALU_FMA_F16) + SQ_INSTS_VALU_TRANS_F16) + (SQ_INSTS_VALU_ADD_F32 + SQ_INSTS_VALU_MUL_F32 + (2 * SQ_INSTS_VALU_FMA_F32) + SQ_INSTS_VALU_TRANS_F32) diff --git a/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx950/0400_roofline.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx950/0400_roofline.yaml index 4064a4a84b..9829a8b37b 100644 --- a/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx950/0400_roofline.yaml +++ b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx950/0400_roofline.yaml @@ -215,7 +215,7 @@ Panel Config: * 512) + (SQ_INSTS_VALU_MFMA_MOPS_F6F4 * 512) ) / SUM(TCP_TOTAL_CACHE_ACCESSES_sum * 64) ) unit: FLOPs/Byte - Performance GFLOPs: + Performance (GFLOPs): value: ( SUM( ($wave_size * ( (SQ_INSTS_VALU_ADD_F16 + SQ_INSTS_VALU_MUL_F16 + (2 * SQ_INSTS_VALU_FMA_F16) + SQ_INSTS_VALU_TRANS_F16) + (SQ_INSTS_VALU_ADD_F32 + SQ_INSTS_VALU_MUL_F32 + (2 * SQ_INSTS_VALU_FMA_F32) + SQ_INSTS_VALU_TRANS_F32) diff --git a/projects/rocprofiler-compute/utils/autogen_hash.yaml b/projects/rocprofiler-compute/utils/autogen_hash.yaml index 7d4fc1150f..e91b1e2520 100644 --- a/projects/rocprofiler-compute/utils/autogen_hash.yaml +++ b/projects/rocprofiler-compute/utils/autogen_hash.yaml @@ -23,12 +23,12 @@ src/rocprof_compute_soc/analysis_configs/gfx940/0300_memory_chart.yaml: 249e9ae0 src/rocprof_compute_soc/analysis_configs/gfx941/0300_memory_chart.yaml: 249e9ae0445de0927827ec14d20f946a07d50d92fd56e1993bbe0c17eb65bd51 src/rocprof_compute_soc/analysis_configs/gfx942/0300_memory_chart.yaml: 249e9ae0445de0927827ec14d20f946a07d50d92fd56e1993bbe0c17eb65bd51 src/rocprof_compute_soc/analysis_configs/gfx950/0300_memory_chart.yaml: 643b31ffa43bc3613d6f90b0c23d95093d0d0aa5bc8e72d9a0fbc1b739a08b67 -src/rocprof_compute_soc/analysis_configs/gfx908/0400_roofline.yaml: f346786a63056303a0c6137f82bcea0baa3bb5bf63bfbef792df531725f64d1d -src/rocprof_compute_soc/analysis_configs/gfx90a/0400_roofline.yaml: 92aced41d421faf00ed542da38f47ad22c2fbf1f0383c550e255ed9bab95b0d8 -src/rocprof_compute_soc/analysis_configs/gfx940/0400_roofline.yaml: 867a31d84eeb5b5aa64606fcdb67732347acc43e88121fcc70af79169f44fd83 -src/rocprof_compute_soc/analysis_configs/gfx941/0400_roofline.yaml: 3f7bef2487df1ece7302de3f413a14032ba35d44fcf4e5ddee5186e2fc223797 +src/rocprof_compute_soc/analysis_configs/gfx908/0400_roofline.yaml: ba5b48696acc5c014e2332570855edfa3c0daebb1c2765e6877fa7db3e0cd587 +src/rocprof_compute_soc/analysis_configs/gfx90a/0400_roofline.yaml: a768b0cb265efcbef39a0e3174c2cb17abb8ff961236c441c9b17a92e547c580 +src/rocprof_compute_soc/analysis_configs/gfx940/0400_roofline.yaml: caa23f7cd9eaee6204c2f48e22d80b520ba5e0efd6e3697c0e2856024e7c0c8c +src/rocprof_compute_soc/analysis_configs/gfx941/0400_roofline.yaml: 7260566a8e13aca53975210aca25ba7fd1d7e1a6cabaeb7ae3d23e140bc62662 src/rocprof_compute_soc/analysis_configs/gfx942/0400_roofline.yaml: 58272f5d1136489255a7bf9c6ade720a0567b17ab58dc58ae796597ae4d73ce5 -src/rocprof_compute_soc/analysis_configs/gfx950/0400_roofline.yaml: 4362a8120d70cc0e62abd4367a09207897bbc3be44805092dabaefda41803391 +src/rocprof_compute_soc/analysis_configs/gfx950/0400_roofline.yaml: 290ff38832460c5f845b78ad0dea4ae8fab9a6affe53ea637eaceed074d31a57 src/rocprof_compute_soc/analysis_configs/gfx908/0500_command_processor_cpc_cpf.yaml: da1c2997d42d66da2aa069caa741cf9eade124357c56e4290333de2f3e0412bb src/rocprof_compute_soc/analysis_configs/gfx90a/0500_command_processor_cpc_cpf.yaml: da1c2997d42d66da2aa069caa741cf9eade124357c56e4290333de2f3e0412bb src/rocprof_compute_soc/analysis_configs/gfx940/0500_command_processor_cpc_cpf.yaml: da1c2997d42d66da2aa069caa741cf9eade124357c56e4290333de2f3e0412bb diff --git a/projects/rocprofiler-compute/utils/unified_config.yaml b/projects/rocprofiler-compute/utils/unified_config.yaml index 0b8e23f1ed..3293f3917d 100644 --- a/projects/rocprofiler-compute/utils/unified_config.yaml +++ b/projects/rocprofiler-compute/utils/unified_config.yaml @@ -3266,7 +3266,7 @@ panels: SUM(TCP_TOTAL_CACHE_ACCESSES_sum * 64) ) unit: FLOPs/Byte - Performance GFLOPs: + Performance (GFLOPs): value: ( SUM( ($wave_size * ( @@ -3340,7 +3340,7 @@ panels: SUM(TCP_TOTAL_CACHE_ACCESSES_sum * 64) ) unit: FLOPs/Byte - Performance GFLOPs: + Performance (GFLOPs): value: ( SUM( ($wave_size * ( @@ -3415,7 +3415,7 @@ panels: SUM(TCP_TOTAL_CACHE_ACCESSES_sum * 64) ) unit: FLOPs/Byte - Performance GFLOPs: + Performance (GFLOPs): value: ( SUM( ($wave_size * ( @@ -3493,7 +3493,7 @@ panels: SUM(TCP_TOTAL_CACHE_ACCESSES_sum * 64) ) unit: FLOPs/Byte - Performance GFLOPs: + Performance (GFLOPs): value: ( SUM( ($wave_size * ( @@ -3619,7 +3619,7 @@ panels: SUM(TCP_TOTAL_CACHE_ACCESSES_sum * 64) ) unit: FLOPs/Byte - Performance GFLOPs: + Performance (GFLOPs): value: ( SUM( ($wave_size * (