98459b579ede968e2d4b2b31bbb27e6bab085cfa
7 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 Benjamin Welton
|
e8a5845661 |
Buffered Counter Collection API (#179)
* Added buffer counter collection API. Initial testing added into counter-collection sample. Added support for constant metrics in counter collection (#194) * Added support for constant metrics in counter collection Adds support and test cases for constant metrics (such as max wave size) and adds the metric kernel duration (though this is still not yet calculated). * Minor doc updates * Simple counter unit tests (#199) * Simple counter unit tests Unit tests and some minor fixes for simple and derived counter evaluation * Added unit tests for reduction operations (#200) * Added unit tests for reduction operations * added tests for combo (constant+regular) counters (#201) source formatting (clang-format v11) (#202) Co-authored-by: bwelton <bwelton@users.noreply.github.com> source formatting (clang-format v11) (#203) Co-authored-by: bwelton <bwelton@users.noreply.github.com> Local changes source formatting (clang-format v11) (#205) Co-authored-by: bwelton <bwelton@users.noreply.github.com> Minor doc fix Remove kernel_duration, migrate over set_dimensions to after HSA init source formatting (clang-format v11) (#207) Co-authored-by: bwelton <bwelton@users.noreply.github.com> Added output to ROCPROFILER_SAMPLE_OUTPUT_FILE: * Remove integer based counter in return struct This casues a lot of complications and seems to provide limit benefit of just treating all counters as doubles. For ease of use, drop the integer based counter. * source formatting (clang-format v11) (#217) Co-authored-by: bwelton <bwelton@users.noreply.github.com> * Add correlation id support to counters (#218) Adds correlation id support to counter collection. Requires tracing to be enabled to return any useful value currently (since we do not have HIP kernel tracing yet). * source formatting (clang-format v11) (#223) Co-authored-by: bwelton <bwelton@users.noreply.github.com> * Add sample that attempts to fetch all counters On whatever machine this test is run on, all counters available on the platform will attempted to be fetched from a kernel execution. Each counter will be fetched one time to check that the counter can be fetched on the platform and that the counter is returning the correct instance count (however due to the lack of transparency from AQL profiler this check is not functional for some counters). We do not do any implicit reduction on any counter, the result is that we see more counters than the number of events being requested. Below is the status of all counters on MI210. All counters appear functional with the changes in this PR. However, the instance count retruned will be greater than that returned by rocprofiler_query_counter_instance_count. Got 516 counters collected Counter ID: 0 (size) expected 1 instances and got 1 Counter ID: 1 (processor_id_low) expected 1 instances and got 1 Counter ID: 2 (capability) expected 1 instances and got 1 Counter ID: 3 (local_mem_size) expected 1 instances and got 1 Counter ID: 4 (min_latency) expected 1 instances and got 1 Counter ID: 5 (weight) expected 1 instances and got 1 Counter ID: 6 (node_from) expected 1 instances and got 1 Counter ID: 7 (version_major) expected 1 instances and got 1 Counter ID: 8 (version_minor) expected 1 instances and got 1 Counter ID: 9 (mem_clk_max) expected 1 instances and got 1 Counter ID: 10 (num_xcc) expected 1 instances and got 1 Counter ID: 11 (width) expected 1 instances and got 1 Counter ID: 12 (flags) expected 1 instances and got 1 Counter ID: 13 (size_in_bytes) expected 1 instances and got 1 Counter ID: 14 (array_count) expected 1 instances and got 1 Counter ID: 15 (num_gws) expected 1 instances and got 1 Counter ID: 16 (simd_id_base) expected 1 instances and got 1 Counter ID: 17 (max_waves_per_simd) expected 1 instances and got 1 Counter ID: 18 (sdma_fw_version) expected 1 instances and got 1 Counter ID: 19 (gfx_target_version) expected 1 instances and got 1 Counter ID: 20 (max_bandwidth) expected 1 instances and got 1 Counter ID: 21 (cpu_core_id_base) expected 1 instances and got 1 Counter ID: 22 (cache_line_size) expected 1 instances and got 1 Counter ID: 23 (level) expected 1 instances and got 1 Counter ID: 24 (min_bandwidth) expected 1 instances and got 1 Counter ID: 25 (location_id) expected 1 instances and got 1 Counter ID: 26 (wave_front_size) expected 1 instances and got 1 Counter ID: 27 (lds_size_in_kb) expected 1 instances and got 1 Counter ID: 28 (simd_count) expected 1 instances and got 1 Counter ID: 29 (fw_version) expected 1 instances and got 1 Counter ID: 30 (recommended_transfer_size) expected 1 instances and got 1 Counter ID: 31 (simd_per_cu) expected 1 instances and got 1 Counter ID: 32 (association) expected 1 instances and got 1 Counter ID: 33 (mem_banks_count) expected 1 instances and got 1 Counter ID: 34 (latency) expected 1 instances and got 1 Counter ID: 35 (max_latency) expected 1 instances and got 1 Counter ID: 36 (cpu_cores_count) expected 1 instances and got 1 Counter ID: 37 (io_links_count) expected 1 instances and got 1 Counter ID: 38 (domain) expected 1 instances and got 1 Counter ID: 39 (max_engine_clk_fcompute) expected 1 instances and got 1 Counter ID: 40 (caches_count) expected 1 instances and got 1 Counter ID: 41 (simd_arrays_per_engine) expected 1 instances and got 1 Counter ID: 42 (cache_lines_per_tag) expected 1 instances and got 1 Counter ID: 43 (gds_size_in_kb) expected 1 instances and got 1 Counter ID: 44 (cu_per_simd_array) expected 1 instances and got 1 Counter ID: 45 (type) expected 1 instances and got 1 Counter ID: 46 (max_slots_scratch_cu) expected 1 instances and got 1 Counter ID: 47 (vendor_id) expected 1 instances and got 1 Counter ID: 48 (device_id) expected 1 instances and got 1 Counter ID: 49 (heap_type) expected 1 instances and got 1 Counter ID: 50 (drm_render_minor) expected 1 instances and got 1 Counter ID: 51 (num_sdma_engines) expected 1 instances and got 1 Counter ID: 52 (node_to) expected 1 instances and got 1 Counter ID: 53 (num_sdma_xgmi_engines) expected 1 instances and got 1 Counter ID: 54 (num_sdma_queues_per_engine) expected 1 instances and got 1 Counter ID: 55 (hive_id) expected 1 instances and got 1 Counter ID: 56 (num_cp_queues) expected 1 instances and got 1 Counter ID: 57 (max_engine_clk_ccompute) expected 1 instances and got 1 Counter ID: 517 (MAX_WAVE_SIZE) expected 1 instances and got 1 Counter ID: 518 (SE_NUM) expected 1 instances and got 1 Counter ID: 519 (SIMD_NUM) expected 1 instances and got 1 Counter ID: 520 (CU_NUM) expected 1 instances and got 1 [ERROR]Counter ID: 521 (SQ_WAIT_INST_LDS) expected 1 instances and got 8 [ERROR]Counter ID: 522 (TCP_TCP_TA_DATA_STALL_CYCLES) expected 16 instances and got 128 Counter ID: 523 (GRBM_COUNT) expected 1 instances and got 1 Counter ID: 524 (GRBM_GUI_ACTIVE) expected 1 instances and got 1 Counter ID: 525 (GRBM_CP_BUSY) expected 1 instances and got 1 Counter ID: 526 (GRBM_SPI_BUSY) expected 1 instances and got 1 Counter ID: 527 (GRBM_TA_BUSY) expected 1 instances and got 1 Counter ID: 528 (GRBM_TC_BUSY) expected 1 instances and got 1 Counter ID: 529 (GRBM_CPC_BUSY) expected 1 instances and got 1 Counter ID: 530 (GRBM_CPF_BUSY) expected 1 instances and got 1 Counter ID: 531 (GRBM_UTCL2_BUSY) expected 1 instances and got 1 Counter ID: 532 (GRBM_EA_BUSY) expected 1 instances and got 1 Counter ID: 533 (CPC_ME1_BUSY_FOR_PACKET_DECODE) expected 1 instances and got 1 Counter ID: 534 (CPC_UTCL1_STALL_ON_TRANSLATION) expected 1 instances and got 1 Counter ID: 535 (CPC_CPC_STAT_BUSY) expected 1 instances and got 1 Counter ID: 536 (CPC_CPC_STAT_IDLE) expected 1 instances and got 1 Counter ID: 537 (CPC_CPC_STAT_STALL) expected 1 instances and got 1 Counter ID: 538 (CPC_CPC_TCIU_BUSY) expected 1 instances and got 1 Counter ID: 539 (CPC_CPC_TCIU_IDLE) expected 1 instances and got 1 Counter ID: 540 (CPC_CPC_UTCL2IU_BUSY) expected 1 instances and got 1 Counter ID: 541 (CPC_CPC_UTCL2IU_IDLE) expected 1 instances and got 1 Counter ID: 542 (CPC_CPC_UTCL2IU_STALL) expected 1 instances and got 1 Counter ID: 543 (CPC_ME1_DC0_SPI_BUSY) expected 1 instances and got 1 Counter ID: 544 (CPF_CMP_UTCL1_STALL_ON_TRANSLATION) expected 1 instances and got 1 Counter ID: 545 (CPF_CPF_STAT_BUSY) expected 1 instances and got 1 Counter ID: 546 (CPF_CPF_STAT_IDLE) expected 1 instances and got 1 Counter ID: 547 (CPF_CPF_STAT_STALL) expected 1 instances and got 1 Counter ID: 548 (CPF_CPF_TCIU_BUSY) expected 1 instances and got 1 Counter ID: 549 (CPF_CPF_TCIU_IDLE) expected 1 instances and got 1 Counter ID: 550 (CPF_CPF_TCIU_STALL) expected 1 instances and got 1 [ERROR]Counter ID: 551 (SPI_CSN_WINDOW_VALID) expected 1 instances and got 8 [ERROR]Counter ID: 552 (SPI_CSN_BUSY) expected 1 instances and got 8 [ERROR]Counter ID: 553 (SPI_CSN_NUM_THREADGROUPS) expected 1 instances and got 8 [ERROR]Counter ID: 554 (SPI_CSN_WAVE) expected 1 instances and got 8 [ERROR]Counter ID: 555 (SPI_RA_REQ_NO_ALLOC) expected 1 instances and got 8 [ERROR]Counter ID: 556 (SPI_RA_REQ_NO_ALLOC_CSN) expected 1 instances and got 8 [ERROR]Counter ID: 557 (SPI_RA_RES_STALL_CSN) expected 1 instances and got 8 [ERROR]Counter ID: 558 (SPI_RA_TMP_STALL_CSN) expected 1 instances and got 8 [ERROR]Counter ID: 559 (SPI_RA_WAVE_SIMD_FULL_CSN) expected 1 instances and got 8 [ERROR]Counter ID: 560 (SPI_RA_VGPR_SIMD_FULL_CSN) expected 1 instances and got 8 [ERROR]Counter ID: 561 (SPI_RA_SGPR_SIMD_FULL_CSN) expected 1 instances and got 8 [ERROR]Counter ID: 562 (SPI_RA_LDS_CU_FULL_CSN) expected 1 instances and got 8 [ERROR]Counter ID: 563 (SPI_RA_BAR_CU_FULL_CSN) expected 1 instances and got 8 [ERROR]Counter ID: 564 (SPI_RA_BULKY_CU_FULL_CSN) expected 1 instances and got 8 [ERROR]Counter ID: 565 (SPI_RA_TGLIM_CU_FULL_CSN) expected 1 instances and got 8 [ERROR]Counter ID: 566 (SPI_RA_WVLIM_STALL_CSN) expected 1 instances and got 8 [ERROR]Counter ID: 567 (SPI_SWC_CSC_WR) expected 1 instances and got 8 [ERROR]Counter ID: 568 (SPI_VWC_CSC_WR) expected 1 instances and got 8 [ERROR]Counter ID: 569 (SQ_ACCUM_PREV) expected 1 instances and got 8 [ERROR]Counter ID: 570 (SQ_CYCLES) expected 1 instances and got 8 [ERROR]Counter ID: 571 (SQ_BUSY_CYCLES) expected 1 instances and got 8 [ERROR]Counter ID: 572 (SQ_WAVES) expected 1 instances and got 8 [ERROR]Counter ID: 573 (SQ_LEVEL_WAVES) expected 1 instances and got 8 [ERROR]Counter ID: 574 (SQ_WAVES_EQ_64) expected 1 instances and got 8 [ERROR]Counter ID: 575 (SQ_WAVES_LT_64) expected 1 instances and got 8 [ERROR]Counter ID: 576 (SQ_WAVES_LT_48) expected 1 instances and got 8 [ERROR]Counter ID: 577 (SQ_WAVES_LT_32) expected 1 instances and got 8 [ERROR]Counter ID: 578 (SQ_WAVES_LT_16) expected 1 instances and got 8 [ERROR]Counter ID: 579 (SQ_BUSY_CU_CYCLES) expected 1 instances and got 8 [ERROR]Counter ID: 580 (SQ_ITEMS) expected 1 instances and got 8 [ERROR]Counter ID: 581 (SQ_INSTS) expected 1 instances and got 8 [ERROR]Counter ID: 582 (SQ_INSTS_VALU) expected 1 instances and got 8 [ERROR]Counter ID: 583 (SQ_INSTS_VALU_ADD_F16) expected 1 instances and got 8 [ERROR]Counter ID: 584 (SQ_INSTS_VALU_MUL_F16) expected 1 instances and got 8 [ERROR]Counter ID: 585 (SQ_INSTS_VALU_FMA_F16) expected 1 instances and got 8 [ERROR]Counter ID: 586 (SQ_INSTS_VALU_TRANS_F16) expected 1 instances and got 8 [ERROR]Counter ID: 587 (SQ_INSTS_VALU_ADD_F32) expected 1 instances and got 8 [ERROR]Counter ID: 588 (SQ_INSTS_VALU_MUL_F32) expected 1 instances and got 8 [ERROR]Counter ID: 589 (SQ_INSTS_VALU_FMA_F32) expected 1 instances and got 8 [ERROR]Counter ID: 590 (SQ_INSTS_VALU_TRANS_F32) expected 1 instances and got 8 [ERROR]Counter ID: 591 (SQ_INSTS_VALU_ADD_F64) expected 1 instances and got 8 [ERROR]Counter ID: 592 (SQ_INSTS_VALU_MUL_F64) expected 1 instances and got 8 [ERROR]Counter ID: 593 (SQ_INSTS_VALU_FMA_F64) expected 1 instances and got 8 [ERROR]Counter ID: 594 (SQ_INSTS_VALU_TRANS_F64) expected 1 instances and got 8 [ERROR]Counter ID: 595 (SQ_INSTS_VALU_INT32) expected 1 instances and got 8 [ERROR]Counter ID: 596 (SQ_INSTS_VALU_INT64) expected 1 instances and got 8 [ERROR]Counter ID: 597 (SQ_INSTS_VALU_CVT) expected 1 instances and got 8 [ERROR]Counter ID: 598 (SQ_INSTS_VALU_MFMA_I8) expected 1 instances and got 8 [ERROR]Counter ID: 599 (SQ_INSTS_VALU_MFMA_F16) expected 1 instances and got 8 [ERROR]Counter ID: 600 (SQ_INSTS_VALU_MFMA_BF16) expected 1 instances and got 8 [ERROR]Counter ID: 601 (SQ_INSTS_VALU_MFMA_F32) expected 1 instances and got 8 [ERROR]Counter ID: 602 (SQ_INSTS_VALU_MFMA_F64) expected 1 instances and got 8 [ERROR]Counter ID: 603 (SQ_INSTS_VALU_MFMA_MOPS_I8) expected 1 instances and got 8 [ERROR]Counter ID: 604 (SQ_INSTS_VALU_MFMA_MOPS_F16) expected 1 instances and got 8 [ERROR]Counter ID: 605 (SQ_INSTS_VALU_MFMA_MOPS_BF16) expected 1 instances and got 8 [ERROR]Counter ID: 606 (SQ_INSTS_VALU_MFMA_MOPS_F32) expected 1 instances and got 8 [ERROR]Counter ID: 607 (SQ_INSTS_VALU_MFMA_MOPS_F64) expected 1 instances and got 8 [ERROR]Counter ID: 608 (SQ_INSTS_MFMA) expected 1 instances and got 8 [ERROR]Counter ID: 609 (SQ_INSTS_VMEM_WR) expected 1 instances and got 8 [ERROR]Counter ID: 610 (SQ_INSTS_VMEM_RD) expected 1 instances and got 8 [ERROR]Counter ID: 611 (SQ_INSTS_VMEM) expected 1 instances and got 8 [ERROR]Counter ID: 612 (SQ_INSTS_SALU) expected 1 instances and got 8 [ERROR]Counter ID: 613 (SQ_INSTS_SMEM) expected 1 instances and got 8 [ERROR]Counter ID: 614 (SQ_INSTS_FLAT) expected 1 instances and got 8 [ERROR]Counter ID: 615 (SQ_INSTS_FLAT_LDS_ONLY) expected 1 instances and got 8 [ERROR]Counter ID: 616 (SQ_INSTS_LDS) expected 1 instances and got 8 [ERROR]Counter ID: 617 (SQ_INSTS_GDS) expected 1 instances and got 8 [ERROR]Counter ID: 618 (SQ_INSTS_EXP_GDS) expected 1 instances and got 8 [ERROR]Counter ID: 619 (SQ_INSTS_BRANCH) expected 1 instances and got 8 [ERROR]Counter ID: 620 (SQ_INSTS_SENDMSG) expected 1 instances and got 8 [ERROR]Counter ID: 621 (SQ_INSTS_VSKIPPED) expected 1 instances and got 8 [ERROR]Counter ID: 622 (SQ_INST_LEVEL_VMEM) expected 1 instances and got 8 [ERROR]Counter ID: 623 (SQ_INST_LEVEL_SMEM) expected 1 instances and got 8 [ERROR]Counter ID: 624 (SQ_INST_LEVEL_LDS) expected 1 instances and got 8 [ERROR]Counter ID: 625 (SQ_VALU_MFMA_BUSY_CYCLES) expected 1 instances and got 8 [ERROR]Counter ID: 626 (SQ_WAVE_CYCLES) expected 1 instances and got 8 [ERROR]Counter ID: 627 (SQ_WAIT_ANY) expected 1 instances and got 8 [ERROR]Counter ID: 628 (SQ_WAIT_INST_ANY) expected 1 instances and got 8 [ERROR]Counter ID: 629 (SQ_ACTIVE_INST_ANY) expected 1 instances and got 8 [ERROR]Counter ID: 630 (SQ_ACTIVE_INST_VMEM) expected 1 instances and got 8 [ERROR]Counter ID: 631 (SQ_ACTIVE_INST_LDS) expected 1 instances and got 8 [ERROR]Counter ID: 632 (SQ_ACTIVE_INST_VALU) expected 1 instances and got 8 [ERROR]Counter ID: 633 (SQ_ACTIVE_INST_SCA) expected 1 instances and got 8 [ERROR]Counter ID: 634 (SQ_ACTIVE_INST_EXP_GDS) expected 1 instances and got 8 [ERROR]Counter ID: 635 (SQ_ACTIVE_INST_MISC) expected 1 instances and got 8 [ERROR]Counter ID: 636 (SQ_ACTIVE_INST_FLAT) expected 1 instances and got 8 [ERROR]Counter ID: 637 (SQ_INST_CYCLES_VMEM_WR) expected 1 instances and got 8 [ERROR]Counter ID: 638 (SQ_INST_CYCLES_VMEM_RD) expected 1 instances and got 8 [ERROR]Counter ID: 639 (SQ_INST_CYCLES_SMEM) expected 1 instances and got 8 [ERROR]Counter ID: 640 (SQ_INST_CYCLES_SALU) expected 1 instances and got 8 [ERROR]Counter ID: 641 (SQ_THREAD_CYCLES_VALU) expected 1 instances and got 8 [ERROR]Counter ID: 642 (SQ_IFETCH) expected 1 instances and got 8 [ERROR]Counter ID: 643 (SQ_IFETCH_LEVEL) expected 1 instances and got 8 [ERROR]Counter ID: 644 (SQ_LDS_BANK_CONFLICT) expected 1 instances and got 8 [ERROR]Counter ID: 645 (SQ_LDS_ADDR_CONFLICT) expected 1 instances and got 8 [ERROR]Counter ID: 646 (SQ_LDS_UNALIGNED_STALL) expected 1 instances and got 8 [ERROR]Counter ID: 647 (SQ_LDS_MEM_VIOLATIONS) expected 1 instances and got 8 [ERROR]Counter ID: 648 (SQ_LDS_ATOMIC_RETURN) expected 1 instances and got 8 [ERROR]Counter ID: 649 (SQ_LDS_IDX_ACTIVE) expected 1 instances and got 8 [ERROR]Counter ID: 650 (SQ_ACCUM_PREV_HIRES) expected 1 instances and got 8 [ERROR]Counter ID: 651 (SQ_WAVES_RESTORED) expected 1 instances and got 8 [ERROR]Counter ID: 652 (SQ_WAVES_SAVED) expected 1 instances and got 8 [ERROR]Counter ID: 653 (SQ_INSTS_SMEM_NORM) expected 1 instances and got 8 [ERROR]Counter ID: 654 (SQC_DCACHE_INPUT_VALID_READYB) expected 1 instances and got 8 [ERROR]Counter ID: 655 (SQC_TC_REQ) expected 1 instances and got 8 [ERROR]Counter ID: 656 (SQC_TC_INST_REQ) expected 1 instances and got 8 [ERROR]Counter ID: 657 (SQC_TC_DATA_READ_REQ) expected 1 instances and got 8 [ERROR]Counter ID: 658 (SQC_TC_DATA_WRITE_REQ) expected 1 instances and got 8 [ERROR]Counter ID: 659 (SQC_TC_DATA_ATOMIC_REQ) expected 1 instances and got 8 [ERROR]Counter ID: 660 (SQC_TC_STALL) expected 1 instances and got 8 [ERROR]Counter ID: 661 (SQC_ICACHE_REQ) expected 1 instances and got 8 [ERROR]Counter ID: 662 (SQC_ICACHE_HITS) expected 1 instances and got 8 [ERROR]Counter ID: 663 (SQC_ICACHE_MISSES) expected 1 instances and got 8 [ERROR]Counter ID: 664 (SQC_ICACHE_MISSES_DUPLICATE) expected 1 instances and got 8 [ERROR]Counter ID: 665 (SQC_DCACHE_REQ) expected 1 instances and got 8 [ERROR]Counter ID: 666 (SQC_DCACHE_HITS) expected 1 instances and got 8 [ERROR]Counter ID: 667 (SQC_DCACHE_MISSES) expected 1 instances and got 8 [ERROR]Counter ID: 668 (SQC_DCACHE_MISSES_DUPLICATE) expected 1 instances and got 8 [ERROR]Counter ID: 669 (SQC_DCACHE_ATOMIC) expected 1 instances and got 8 [ERROR]Counter ID: 670 (SQC_DCACHE_REQ_READ_1) expected 1 instances and got 8 [ERROR]Counter ID: 671 (SQC_DCACHE_REQ_READ_2) expected 1 instances and got 8 [ERROR]Counter ID: 672 (SQC_DCACHE_REQ_READ_4) expected 1 instances and got 8 [ERROR]Counter ID: 673 (SQC_DCACHE_REQ_READ_8) expected 1 instances and got 8 [ERROR]Counter ID: 674 (SQC_DCACHE_REQ_READ_16) expected 1 instances and got 8 [ERROR]Counter ID: 675 (TA_TA_BUSY) expected 16 instances and got 128 [ERROR]Counter ID: 676 (TA_TOTAL_WAVEFRONTS) expected 16 instances and got 128 [ERROR]Counter ID: 677 (TA_BUFFER_WAVEFRONTS) expected 16 instances and got 128 [ERROR]Counter ID: 678 (TA_BUFFER_READ_WAVEFRONTS) expected 16 instances and got 128 [ERROR]Counter ID: 679 (TA_BUFFER_WRITE_WAVEFRONTS) expected 16 instances and got 128 [ERROR]Counter ID: 680 (TA_BUFFER_ATOMIC_WAVEFRONTS) expected 16 instances and got 128 [ERROR]Counter ID: 681 (TA_BUFFER_TOTAL_CYCLES) expected 16 instances and got 128 [ERROR]Counter ID: 682 (TA_BUFFER_COALESCED_READ_CYCLES) expected 16 instances and got 128 [ERROR]Counter ID: 683 (TA_BUFFER_COALESCED_WRITE_CYCLES) expected 16 instances and got 128 [ERROR]Counter ID: 684 (TA_ADDR_STALLED_BY_TC_CYCLES) expected 16 instances and got 128 [ERROR]Counter ID: 685 (TA_ADDR_STALLED_BY_TD_CYCLES) expected 16 instances and got 128 [ERROR]Counter ID: 686 (TA_DATA_STALLED_BY_TC_CYCLES) expected 16 instances and got 128 [ERROR]Counter ID: 687 (TA_FLAT_WAVEFRONTS) expected 16 instances and got 128 [ERROR]Counter ID: 688 (TA_FLAT_READ_WAVEFRONTS) expected 16 instances and got 128 [ERROR]Counter ID: 689 (TA_FLAT_WRITE_WAVEFRONTS) expected 16 instances and got 128 [ERROR]Counter ID: 690 (TA_FLAT_ATOMIC_WAVEFRONTS) expected 16 instances and got 128 [ERROR]Counter ID: 691 (TD_TD_BUSY) expected 16 instances and got 128 [ERROR]Counter ID: 692 (TD_TC_STALL) expected 16 instances and got 128 [ERROR]Counter ID: 693 (TD_SPI_STALL) expected 16 instances and got 128 [ERROR]Counter ID: 694 (TD_LOAD_WAVEFRONT) expected 16 instances and got 128 [ERROR]Counter ID: 695 (TD_ATOMIC_WAVEFRONT) expected 16 instances and got 128 [ERROR]Counter ID: 696 (TD_STORE_WAVEFRONT) expected 16 instances and got 128 [ERROR]Counter ID: 697 (TD_COALESCABLE_WAVEFRONT) expected 16 instances and got 128 [ERROR]Counter ID: 698 (TCP_GATE_EN1) expected 16 instances and got 128 [ERROR]Counter ID: 699 (TCP_GATE_EN2) expected 16 instances and got 128 [ERROR]Counter ID: 700 (TCP_TD_TCP_STALL_CYCLES) expected 16 instances and got 128 [ERROR]Counter ID: 701 (TCP_TCR_TCP_STALL_CYCLES) expected 16 instances and got 128 [ERROR]Counter ID: 702 (TCP_READ_TAGCONFLICT_STALL_CYCLES) expected 16 instances and got 128 [ERROR]Counter ID: 703 (TCP_WRITE_TAGCONFLICT_STALL_CYCLES) expected 16 instances and got 128 [ERROR]Counter ID: 704 (TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES) expected 16 instances and got 128 [ERROR]Counter ID: 705 (TCP_PENDING_STALL_CYCLES) expected 16 instances and got 128 [ERROR]Counter ID: 706 (TCP_TA_TCP_STATE_READ) expected 16 instances and got 128 [ERROR]Counter ID: 707 (TCP_VOLATILE) expected 16 instances and got 128 [ERROR]Counter ID: 708 (TCP_TOTAL_ACCESSES) expected 16 instances and got 128 [ERROR]Counter ID: 709 (TCP_TOTAL_READ) expected 16 instances and got 128 [ERROR]Counter ID: 710 (TCP_TOTAL_WRITE) expected 16 instances and got 128 [ERROR]Counter ID: 711 (TCP_TOTAL_ATOMIC_WITH_RET) expected 16 instances and got 128 [ERROR]Counter ID: 712 (TCP_TOTAL_ATOMIC_WITHOUT_RET) expected 16 instances and got 128 [ERROR]Counter ID: 713 (TCP_TOTAL_WRITEBACK_INVALIDATES) expected 16 instances and got 128 [ERROR]Counter ID: 714 (TCP_UTCL1_REQUEST) expected 16 instances and got 128 [ERROR]Counter ID: 715 (TCP_UTCL1_TRANSLATION_MISS) expected 16 instances and got 128 [ERROR]Counter ID: 716 (TCP_UTCL1_TRANSLATION_HIT) expected 16 instances and got 128 [ERROR]Counter ID: 717 (TCP_UTCL1_PERMISSION_MISS) expected 16 instances and got 128 [ERROR]Counter ID: 718 (TCP_TOTAL_CACHE_ACCESSES) expected 16 instances and got 128 [ERROR]Counter ID: 719 (TCP_TCP_LATENCY) expected 16 instances and got 128 [ERROR]Counter ID: 720 (TCP_TCC_READ_REQ_LATENCY) expected 16 instances and got 128 [ERROR]Counter ID: 721 (TCP_TCC_WRITE_REQ_LATENCY) expected 16 instances and got 128 [ERROR]Counter ID: 722 (TCP_TCC_READ_REQ) expected 16 instances and got 128 [ERROR]Counter ID: 723 (TCP_TCC_WRITE_REQ) expected 16 instances and got 128 [ERROR]Counter ID: 724 (TCP_TCC_ATOMIC_WITH_RET_REQ) expected 16 instances and got 128 [ERROR]Counter ID: 725 (TCP_TCC_ATOMIC_WITHOUT_RET_REQ) expected 16 instances and got 128 [ERROR]Counter ID: 726 (TCP_TCC_NC_READ_REQ) expected 16 instances and got 128 [ERROR]Counter ID: 727 (TCP_TCC_NC_WRITE_REQ) expected 16 instances and got 128 [ERROR]Counter ID: 728 (TCP_TCC_NC_ATOMIC_REQ) expected 16 instances and got 128 [ERROR]Counter ID: 729 (TCP_TCC_UC_READ_REQ) expected 16 instances and got 128 [ERROR]Counter ID: 730 (TCP_TCC_UC_WRITE_REQ) expected 16 instances and got 128 [ERROR]Counter ID: 731 (TCP_TCC_UC_ATOMIC_REQ) expected 16 instances and got 128 [ERROR]Counter ID: 732 (TCP_TCC_CC_READ_REQ) expected 16 instances and got 128 [ERROR]Counter ID: 733 (TCP_TCC_CC_WRITE_REQ) expected 16 instances and got 128 [ERROR]Counter ID: 734 (TCP_TCC_CC_ATOMIC_REQ) expected 16 instances and got 128 [ERROR]Counter ID: 735 (TCP_TCC_RW_READ_REQ) expected 16 instances and got 128 [ERROR]Counter ID: 736 (TCP_TCC_RW_WRITE_REQ) expected 16 instances and got 128 [ERROR]Counter ID: 737 (TCP_TCC_RW_ATOMIC_REQ) expected 16 instances and got 128 Counter ID: 738 (TCA_CYCLE) expected 32 instances and got 32 Counter ID: 739 (TCA_BUSY) expected 32 instances and got 32 Counter ID: 740 (TCC_CYCLE) expected 32 instances and got 32 Counter ID: 741 (TCC_BUSY) expected 32 instances and got 32 Counter ID: 742 (TCC_REQ) expected 32 instances and got 32 Counter ID: 743 (TCC_STREAMING_REQ) expected 32 instances and got 32 Counter ID: 744 (TCC_NC_REQ) expected 32 instances and got 32 Counter ID: 745 (TCC_UC_REQ) expected 32 instances and got 32 Counter ID: 746 (TCC_CC_REQ) expected 32 instances and got 32 Counter ID: 747 (TCC_RW_REQ) expected 32 instances and got 32 Counter ID: 748 (TCC_PROBE) expected 32 instances and got 32 Counter ID: 749 (TCC_PROBE_ALL) expected 32 instances and got 32 Counter ID: 750 (TCC_READ) expected 32 instances and got 32 Counter ID: 751 (TCC_WRITE) expected 32 instances and got 32 Counter ID: 752 (TCC_ATOMIC) expected 32 instances and got 32 Counter ID: 753 (TCC_HIT) expected 32 instances and got 32 Counter ID: 754 (TCC_MISS) expected 32 instances and got 32 Counter ID: 755 (TCC_WRITEBACK) expected 32 instances and got 32 Counter ID: 756 (TCC_EA_WRREQ) expected 32 instances and got 32 Counter ID: 757 (TCC_EA_WRREQ_64B) expected 32 instances and got 32 Counter ID: 758 (TCC_EA_WR_UNCACHED_32B) expected 32 instances and got 32 Counter ID: 759 (TCC_EA_WRREQ_STALL) expected 32 instances and got 32 Counter ID: 760 (TCC_EA_WRREQ_IO_CREDIT_STALL) expected 32 instances and got 32 Counter ID: 761 (TCC_EA_WRREQ_GMI_CREDIT_STALL) expected 32 instances and got 32 Counter ID: 762 (TCC_EA_WRREQ_DRAM_CREDIT_STALL) expected 32 instances and got 32 Counter ID: 763 (TCC_TOO_MANY_EA_WRREQS_STALL) expected 32 instances and got 32 Counter ID: 764 (TCC_EA_WRREQ_LEVEL) expected 32 instances and got 32 Counter ID: 765 (TCC_EA_ATOMIC) expected 32 instances and got 32 Counter ID: 766 (TCC_EA_ATOMIC_LEVEL) expected 32 instances and got 32 Counter ID: 767 (TCC_EA_RDREQ) expected 32 instances and got 32 Counter ID: 768 (TCC_EA_RDREQ_32B) expected 32 instances and got 32 Counter ID: 769 (TCC_EA_RD_UNCACHED_32B) expected 32 instances and got 32 Counter ID: 770 (TCC_EA_RDREQ_IO_CREDIT_STALL) expected 32 instances and got 32 Counter ID: 771 (TCC_EA_RDREQ_GMI_CREDIT_STALL) expected 32 instances and got 32 Counter ID: 772 (TCC_EA_RDREQ_DRAM_CREDIT_STALL) expected 32 instances and got 32 Counter ID: 773 (TCC_EA_RDREQ_LEVEL) expected 32 instances and got 32 Counter ID: 774 (TCC_TAG_STALL) expected 32 instances and got 32 Counter ID: 775 (TCC_NORMAL_WRITEBACK) expected 32 instances and got 32 Counter ID: 776 (TCC_ALL_TC_OP_WB_WRITEBACK) expected 32 instances and got 32 Counter ID: 777 (TCC_NORMAL_EVICT) expected 32 instances and got 32 Counter ID: 778 (TCC_ALL_TC_OP_INV_EVICT) expected 32 instances and got 32 Counter ID: 779 (TCC_EA_RDREQ_DRAM) expected 32 instances and got 32 Counter ID: 780 (TCC_EA_WRREQ_DRAM) expected 32 instances and got 32 [ERROR]Counter ID: 1893 (MeanOccupancyPerCU) expected 1 instances and got 8 [ERROR]Counter ID: 1894 (MeanOccupancyPerActiveCU) expected 1 instances and got 8 [ERROR]Counter ID: 1895 (TA_BUSY_avr) expected 16 instances and got 1 [ERROR]Counter ID: 1896 (TA_BUSY_max) expected 16 instances and got 1 [ERROR]Counter ID: 1897 (TA_BUSY_min) expected 16 instances and got 1 [ERROR]Counter ID: 1898 (TA_TA_BUSY_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1899 (TA_TOTAL_WAVEFRONTS_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1900 (TA_ADDR_STALLED_BY_TC_CYCLES_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1901 (TA_ADDR_STALLED_BY_TD_CYCLES_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1902 (TA_DATA_STALLED_BY_TC_CYCLES_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1903 (TA_FLAT_WAVEFRONTS_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1904 (TA_FLAT_READ_WAVEFRONTS_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1905 (TA_FLAT_WRITE_WAVEFRONTS_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1906 (TA_FLAT_ATOMIC_WAVEFRONTS_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1907 (TA_BUFFER_WAVEFRONTS_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1908 (TA_BUFFER_READ_WAVEFRONTS_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1909 (TA_BUFFER_WRITE_WAVEFRONTS_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1910 (TA_BUFFER_ATOMIC_WAVEFRONTS_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1911 (TA_BUFFER_TOTAL_CYCLES_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1912 (TA_BUFFER_COALESCED_READ_CYCLES_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1913 (TA_BUFFER_COALESCED_WRITE_CYCLES_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1914 (TD_TD_BUSY_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1915 (TD_TC_STALL_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1916 (TD_LOAD_WAVEFRONT_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1917 (TD_ATOMIC_WAVEFRONT_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1918 (TD_STORE_WAVEFRONT_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1919 (TD_COALESCABLE_WAVEFRONT_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1920 (TD_SPI_STALL_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1921 (TCP_GATE_EN1_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1922 (TCP_GATE_EN2_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1923 (TCP_TD_TCP_STALL_CYCLES_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1924 (TCP_TCR_TCP_STALL_CYCLES_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1925 (TCP_READ_TAGCONFLICT_STALL_CYCLES_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1926 (TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1927 (TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1928 (TCP_VOLATILE_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1929 (TCP_TOTAL_ACCESSES_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1930 (TCP_TOTAL_READ_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1931 (TCP_TOTAL_WRITE_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1932 (TCP_TOTAL_ATOMIC_WITH_RET_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1933 (TCP_TOTAL_ATOMIC_WITHOUT_RET_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1934 (TCP_TOTAL_WRITEBACK_INVALIDATES_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1935 (TCP_UTCL1_REQUEST_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1936 (TCP_UTCL1_TRANSLATION_MISS_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1937 (TCP_UTCL1_TRANSLATION_HIT_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1938 (TCP_UTCL1_PERMISSION_MISS_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1939 (TCP_TOTAL_CACHE_ACCESSES_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1940 (TCP_TCP_LATENCY_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1941 (TCP_TA_TCP_STATE_READ_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1942 (TCP_TCC_READ_REQ_LATENCY_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1943 (TCP_TCC_WRITE_REQ_LATENCY_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1944 (TCP_TCC_READ_REQ_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1945 (TCP_TCC_WRITE_REQ_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1946 (TCP_TCC_ATOMIC_WITH_RET_REQ_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1947 (TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1948 (TCP_TCC_NC_READ_REQ_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1949 (TCP_TCC_NC_WRITE_REQ_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1950 (TCP_TCC_NC_ATOMIC_REQ_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1951 (TCP_TCC_UC_READ_REQ_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1952 (TCP_TCC_UC_WRITE_REQ_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1953 (TCP_TCC_UC_ATOMIC_REQ_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1954 (TCP_TCC_CC_READ_REQ_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1955 (TCP_TCC_CC_WRITE_REQ_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1956 (TCP_TCC_CC_ATOMIC_REQ_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1957 (TCP_TCC_RW_READ_REQ_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1958 (TCP_TCC_RW_WRITE_REQ_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1959 (TCP_TCC_RW_ATOMIC_REQ_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1960 (TCP_PENDING_STALL_CYCLES_sum) expected 16 instances and got 1 [ERROR]Counter ID: 1961 (TCA_CYCLE_sum) expected 32 instances and got 1 [ERROR]Counter ID: 1962 (TCA_BUSY_sum) expected 32 instances and got 1 [ERROR]Counter ID: 1963 (TCC_BUSY_avr) expected 32 instances and got 1 [ERROR]Counter ID: 1964 (TCC_WRREQ_STALL_max) expected 32 instances and got 1 [ERROR]Counter ID: 1965 (TCC_CYCLE_sum) expected 32 instances and got 1 [ERROR]Counter ID: 1966 (TCC_BUSY_sum) expected 32 instances and got 1 [ERROR]Counter ID: 1967 (TCC_REQ_sum) expected 32 instances and got 1 [ERROR]Counter ID: 1968 (TCC_STREAMING_REQ_sum) expected 32 instances and got 1 [ERROR]Counter ID: 1969 (TCC_NC_REQ_sum) expected 32 instances and got 1 [ERROR]Counter ID: 1970 (TCC_UC_REQ_sum) expected 32 instances and got 1 [ERROR]Counter ID: 1971 (TCC_CC_REQ_sum) expected 32 instances and got 1 [ERROR]Counter ID: 1972 (TCC_RW_REQ_sum) expected 32 instances and got 1 [ERROR]Counter ID: 1973 (TCC_PROBE_sum) expected 32 instances and got 1 [ERROR]Counter ID: 1974 (TCC_PROBE_ALL_sum) expected 32 instances and got 1 [ERROR]Counter ID: 1975 (TCC_READ_sum) expected 32 instances and got 1 [ERROR]Counter ID: 1976 (TCC_WRITE_sum) expected 32 instances and got 1 [ERROR]Counter ID: 1977 (TCC_ATOMIC_sum) expected 32 instances and got 1 [ERROR]Counter ID: 1978 (TCC_HIT_sum) expected 32 instances and got 1 [ERROR]Counter ID: 1979 (TCC_MISS_sum) expected 32 instances and got 1 [ERROR]Counter ID: 1980 (TCC_WRITEBACK_sum) expected 32 instances and got 1 [ERROR]Counter ID: 1981 (TCC_EA_WRREQ_sum) expected 32 instances and got 1 [ERROR]Counter ID: 1982 (TCC_EA_WRREQ_64B_sum) expected 32 instances and got 1 [ERROR]Counter ID: 1983 (TCC_EA_WR_UNCACHED_32B_sum) expected 32 instances and got 1 [ERROR]Counter ID: 1984 (TCC_EA_WRREQ_STALL_sum) expected 32 instances and got 1 [ERROR]Counter ID: 1985 (TCC_EA_WRREQ_IO_CREDIT_STALL_sum) expected 32 instances and got 1 [ERROR]Counter ID: 1986 (TCC_EA_WRREQ_GMI_CREDIT_STALL_sum) expected 32 instances and got 1 [ERROR]Counter ID: 1987 (TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum) expected 32 instances and got 1 [ERROR]Counter ID: 1988 (TCC_TOO_MANY_EA_WRREQS_STALL_sum) expected 32 instances and got 1 [ERROR]Counter ID: 1989 (TCC_EA_WRREQ_LEVEL_sum) expected 32 instances and got 1 [ERROR]Counter ID: 1990 (TCC_EA_RDREQ_LEVEL_sum) expected 32 instances and got 1 [ERROR]Counter ID: 1991 (TCC_EA_ATOMIC_sum) expected 32 instances and got 1 [ERROR]Counter ID: 1992 (TCC_EA_ATOMIC_LEVEL_sum) expected 32 instances and got 1 [ERROR]Counter ID: 1993 (TCC_EA_RDREQ_sum) expected 32 instances and got 1 [ERROR]Counter ID: 1994 (TCC_EA_RDREQ_32B_sum) expected 32 instances and got 1 [ERROR]Counter ID: 1995 (TCC_EA_RD_UNCACHED_32B_sum) expected 32 instances and got 1 [ERROR]Counter ID: 1996 (TCC_EA_RDREQ_IO_CREDIT_STALL_sum) expected 32 instances and got 1 [ERROR]Counter ID: 1997 (TCC_EA_RDREQ_GMI_CREDIT_STALL_sum) expected 32 instances and got 1 [ERROR]Counter ID: 1998 (TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum) expected 32 instances and got 1 [ERROR]Counter ID: 1999 (TCC_TAG_STALL_sum) expected 32 instances and got 1 [ERROR]Counter ID: 2000 (TCC_NORMAL_WRITEBACK_sum) expected 32 instances and got 1 [ERROR]Counter ID: 2001 (TCC_ALL_TC_OP_WB_WRITEBACK_sum) expected 32 instances and got 1 [ERROR]Counter ID: 2002 (TCC_NORMAL_EVICT_sum) expected 32 instances and got 1 [ERROR]Counter ID: 2003 (TCC_ALL_TC_OP_INV_EVICT_sum) expected 32 instances and got 1 [ERROR]Counter ID: 2004 (TCC_EA_RDREQ_DRAM_sum) expected 32 instances and got 1 [ERROR]Counter ID: 2005 (TCC_EA_WRREQ_DRAM_sum) expected 32 instances and got 1 [ERROR]Counter ID: 2006 (FETCH_SIZE) expected 32 instances and got 1 [ERROR]Counter ID: 2007 (WRITE_SIZE) expected 32 instances and got 1 [ERROR]Counter ID: 2008 (WRITE_REQ_32B) expected 32 instances and got 1 [ERROR]Counter ID: 2009 (CU_OCCUPANCY) expected 1 instances and got 8 Counter ID: 2010 (CU_UTILIZATION) expected 1 instances and got 1 [ERROR]Counter ID: 2011 (TOTAL_16_OPS) expected 1 instances and got 8 [ERROR]Counter ID: 2012 (TOTAL_32_OPS) expected 1 instances and got 8 [ERROR]Counter ID: 2013 (TOTAL_64_OPS) expected 1 instances and got 8 Counter ID: 2014 (AggSysCycles) expected 1 instances and got 1 Counter ID: 2015 (GpuUtil) expected 1 instances and got 1 Counter ID: 2016 (CpUtil) expected 1 instances and got 1 Counter ID: 2017 (SpiUtil) expected 1 instances and got 1 Counter ID: 2018 (TaUtil) expected 1 instances and got 1 Counter ID: 2019 (TcUtil) expected 1 instances and got 1 Counter ID: 2020 (EaUtil) expected 1 instances and got 1 [ERROR]Counter ID: 2021 (InstrFetchLatency) expected 1 instances and got 8 [ERROR]Counter ID: 2022 (WaveOccupancy) expected 1 instances and got 8 [ERROR]Counter ID: 2023 (WaveDuration) expected 1 instances and got 8 [ERROR]Counter ID: 2024 (WaveDepWait) expected 1 instances and got 8 [ERROR]Counter ID: 2025 (WaveIssueWait) expected 1 instances and got 8 [ERROR]Counter ID: 2026 (WaveExec) expected 1 instances and got 8 [ERROR]Counter ID: 2027 (ValuIops) expected 1 instances and got 8 [ERROR]Counter ID: 2028 (MfmaFlops) expected 1 instances and got 8 [ERROR]Counter ID: 2029 (MfmaFlopsF16) expected 1 instances and got 8 [ERROR]Counter ID: 2030 (MfmaFlopsBF16) expected 1 instances and got 8 [ERROR]Counter ID: 2031 (MfmaFlopsF32) expected 1 instances and got 8 [ERROR]Counter ID: 2032 (MfmaFlopsF64) expected 1 instances and got 8 [ERROR]Counter ID: 2033 (ScaPipeIssueUtil) expected 1 instances and got 8 [ERROR]Counter ID: 2034 (ValuPipeIssueUtil) expected 1 instances and got 8 [ERROR]Counter ID: 2035 (VmemPipeIssueUtil) expected 1 instances and got 8 [ERROR]Counter ID: 2036 (MfmaUtil) expected 1 instances and got 8 [ERROR]Counter ID: 2037 (AvgNumActiveThreads) expected 1 instances and got 8 [ERROR]Counter ID: 2038 (VmemLatency) expected 1 instances and got 8 [ERROR]Counter ID: 2039 (SmemLatency) expected 1 instances and got 8 [ERROR]Counter ID: 2040 (LdsUtil) expected 1 instances and got 8 [ERROR]Counter ID: 2041 (LdsPipeIssueUtil) expected 1 instances and got 8 [ERROR]Counter ID: 2042 (LdsLatency) expected 1 instances and got 8 [ERROR]Counter ID: 2043 (LdsBankConflict) expected 1 instances and got 8 [ERROR]Counter ID: 2044 (L1iCacheHitRate) expected 1 instances and got 8 [ERROR]Counter ID: 2045 (sL1dCacheHitRate) expected 1 instances and got 8 [ERROR]Counter ID: 2046 (vL1dBufCoalesceRate) expected 16 instances and got 1 [ERROR]Counter ID: 2047 (vL1dCacheUtil) expected 16 instances and got 1 [ERROR]Counter ID: 2048 (vL1dCacheTcbHitRate) expected 16 instances and got 1 [ERROR]Counter ID: 2049 (vL1dCacheWaveLatency) expected 16 instances and got 1 [ERROR]Counter ID: 2050 (vL1dReadFromL2Latency) expected 16 instances and got 1 [ERROR]Counter ID: 2051 (vL1dWriteToL2Latency) expected 16 instances and got 1 [ERROR]Counter ID: 2052 (vL1dRdTagConfStallRate) expected 16 instances and got 1 [ERROR]Counter ID: 2053 (vL1dWrTagConfStallRate) expected 16 instances and got 1 [ERROR]Counter ID: 2054 (vL1dAtomicTagConfStallRate) expected 16 instances and got 1 [ERROR]Counter ID: 2055 (vL1dMissReqStallRate) expected 16 instances and got 1 [ERROR]Counter ID: 2056 (vL1dDataPendRate) expected 16 instances and got 1 [ERROR]Counter ID: 2057 (vL1dDataRetStallRate) expected 16 instances and got 1 [ERROR]Counter ID: 2058 (L2CacheHitRate) expected 32 instances and got 1 [ERROR]Counter ID: 2059 (L2CacheTagRamStallRate) expected 32 instances and got 1 [ERROR]Counter ID: 2060 (EaRdLatency) expected 32 instances and got 1 [ERROR]Counter ID: 2061 (EaRdIoStallRate) expected 32 instances and got 1 [ERROR]Counter ID: 2062 (EaRdGmiStallRate) expected 32 instances and got 1 [ERROR]Counter ID: 2063 (EaRdDramStallRate) expected 32 instances and got 1 [ERROR]Counter ID: 2064 (EaWrLatency) expected 32 instances and got 1 [ERROR]Counter ID: 2065 (EaWrIoStallRate) expected 32 instances and got 1 [ERROR]Counter ID: 2066 (EaWrGmiStallRate) expected 32 instances and got 1 [ERROR]Counter ID: 2067 (EaWrDramStallRate) expected 32 instances and got 1 [ERROR]Counter ID: 2068 (EaWrStarveRate) expected 32 instances and got 1 [ERROR]Counter ID: 2069 (EaAtomicLatency) expected 32 instances and got 1 [ERROR]Counter ID: 2070 (TCP_TCP_TA_DATA_STALL_CYCLES_sum) expected 16 instances and got 1 [ERROR]Counter ID: 2071 (TCP_TCP_TA_DATA_STALL_CYCLES_max) expected 16 instances and got 1 [ERROR]Counter ID: 2072 (VFetchInsts) expected 16 instances and got 8 [ERROR]Counter ID: 2073 (VWriteInsts) expected 16 instances and got 8 [ERROR]Counter ID: 2074 (FlatVMemInsts) expected 1 instances and got 8 [ERROR]Counter ID: 2075 (LDSInsts) expected 1 instances and got 8 [ERROR]Counter ID: 2076 (FlatLDSInsts) expected 1 instances and got 8 [ERROR]Counter ID: 2077 (VALUUtilization) expected 1 instances and got 8 [ERROR]Counter ID: 2078 (VALUBusy) expected 1 instances and got 8 [ERROR]Counter ID: 2079 (SALUBusy) expected 1 instances and got 8 [ERROR]Counter ID: 2080 (FetchSize) expected 32 instances and got 1 [ERROR]Counter ID: 2081 (WriteSize) expected 32 instances and got 1 [ERROR]Counter ID: 2082 (MemWrites32B) expected 32 instances and got 1 [ERROR]Counter ID: 2083 (L2CacheHit) expected 32 instances and got 1 [ERROR]Counter ID: 2084 (MemUnitStalled) expected 16 instances and got 1 [ERROR]Counter ID: 2085 (WriteUnitStalled) expected 32 instances and got 1 [ERROR]Counter ID: 2086 (LDSBankConflict) expected 1 instances and got 8 * source formatting (clang-format v11) (#225) Co-authored-by: bwelton <bwelton@users.noreply.github.com> * cmake formatting (cmake-format) (#224) Co-authored-by: bwelton <bwelton@users.noreply.github.com> * Minor fixes * source formatting (clang-format v11) (#226) Co-authored-by: bwelton <bwelton@users.noreply.github.com> * Minor test change --------- Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: bwelton <bwelton@users.noreply.github.com> |
||
 Jonathan R. Madsen
|
086218c2eb |
Fixes licensing in files (#206)
* Update LICENSE - fix inconsistencies * Revert lib/rocprofiler/counters/parser/scanner.cpp * Update lib/rocprofiler/counters/tests/dimension.cpp - revert ending curly brace * Revert missing curly braces - missing curly braces when file did not end with a new line |
||
|
Jonathan R. Madsen
|
55f2dabbb3 |
Generalized updates (#174)
- include/rocprofiler/agent.h
- move rocprofiler_dim3_t
- include/rocprofiler/buffer_tracing.h
- size fields
- update kernel dispatch record
- include/rocprofiler/callback_tracing.h
- remove rocprofiler_callback_tracing_code_object_unload_data_t
- remove rocprofiler_callback_tracing_code_object_register_host_kernel_symbol_data_t
- include/rocprofiler/fwd.h
- added ROCPROFILER_STATUS_ERROR_CONTEXT_CONFLICT
- remove ROCPROFILER_CALLBACK_TRACING_CODE_OBJECT_UNLOAD
- remove ROCPROFILER_CALLBACK_TRACING_CODE_OBJECT_DEVICE_KERNEL_SYMBOL_UNREGISTER
- add rocprofiler_kernel_id_t typedef
- add rocprofiler_dim3_t (moved from agent.h)
- lib/common/synchronized.hpp
- rlock/wlock return decltype(auto)
- separate prototype from definition
- lib/common/utility.{hpp,cpp}
- timestamp functions replicating HSA implementation(s)
- init_public_api_struct for setting size field and ensuring certain type traits
- simplified static_cleanup_wrapper
- separate prototype from definition in active_capacity_gate
- lib/rocprofiler/agent.cpp
- tweak get_rocprofiler_agent impl
- lib/rocprofiler/buffer.cpp
- fix buffer message log level
- lib/rocprofiler/context.cpp
- use new paradigm for getting active contexts
- lib/rocprofiler/internal_threading.hpp
- update to simplified static_cleanup_wrapper implementation
- lib/rocprofiler/registration.cpp
- fix deactivating contexts
- lib/rocprofiler/rocprofiler.cpp
- status string for context conflict
- lib/rocprofiler/context/context.*
- correlation_id struct
- new get_active_contexts paradigm
- lib/rocprofiler/counters/core.*
- rocprofiler_packet union
- tweak start/stop context to accept pointer instead of handle
- lib/rocprofiler/counters/dimensions.cpp
- update to new get_rocp_agent() return type
- lib/rocprofiler/hsa/hsa.*
- update to new get_active_contexts paradigm
- update to new correlation id implementation
- guard against hsa.def.cpp direct compilation
- lib/rocprofiler/hsa/queue_controller.*
- update to change in get_rocp_agent return type
- consistent aliases
- lookup function for getting queue pointer from hsa queue id
- lib/rocprofiler/hsa/queue.*
- rocprofiler_packet
- extend queue_info_session_t
- lib/rocprofiler/tests/registration.cpp
- improve diagnostic on perf check for rocprofiler_lib.callback_registration_lambda_with_result
|
||
|
Jonathan R. Madsen
|
7f631de401 |
Separate agent cache from queue controller (#145)
* Update lib/rocprofiler/agent.{hpp,cpp}
- get_agents() function for internal access to agent pointers
* Update AgentCache
- make member variables and member functions distinguish b/t hsa agent and rocprofiler agent clear
* Change ctor of AgentCache
* Update lib/rocprofiler/hsa/queue_controller.cpp
- QueueController::init uses agent::get_agent_cache
* Update lib/rocprofiler/hsa/agent_cache.*
- member function to get index
- operator== for rocprofiler_agent_t and hsa_agent_t
- removed hsa_iterate_agents from ctor (now in agent.cpp)
* Update lib/rocprofiler/agent.*
- construct_agent_cache function
- functions for rocprofiler agent <-> HSA agent
- functions for getting agent cache
* Update lib/rocprofiler/registration.cpp
- invoke construct_agent_cache when HSA table is receieved
* Update lib/rocprofiler/agent.cpp
- loosen failure conditions
- handle spurious duplicate entry warning
* Update lib/rocprofiler/agent.cpp
- improve read_map diagnostics
* Update lib/rocprofiler/agent.cpp
- avoid infinite loop in read_map
* Update lib/rocprofiler/agent.cpp
- handle empty kfd node properties file
* Update lib/rocprofiler/agent.cpp
- check for permissions to read a node properties file
* Update lib/rocprofiler/agent.cpp
- more checks on file readability
* Update lib/rocprofiler/tests/agent.cpp
- print virtual kfd topology
* Update lib/rocprofiler/tests/agent.cpp
- verify id.handle == hsa_agent internal node id
* Update lib/rocprofiler/tests/agent.cpp
- check node_id
- check location id
- check device id
- update abi test
* Update include/rocprofiler/agent.h
- add node_id field
- add reserved0 field to ensure new field increases struct size
* Update lib/rocprofiler/agent.cpp
- node_id instead of id.handle
* Update lib/rocprofiler/agent_cache.cpp
- node_id instead of id.handle
* Update samples/pc_sampling
- node_id for agent instead of id.handle
* Update lib/rocprofiler/buffer.cpp
- remove debug prints
|
||
|
Jonathan R. Madsen
|
d1518c65b2 |
Miscellaneous Updates (const-correctness, logic fixes, etc.) (#126)
* Update lib/rocprofiler/hsa/hsa.cpp
- fix logic for constructing callback_contexts and buffered_contexts arrays
* Update include/rocprofiler/{agent,fwd,pc_sampling}.h
- remove rocprofiler_pc_sampling_config_array_t due to const problems
- update rocprofiler_agent_t to use arrays to const data
- remove redundant rocprofiler_query_pc_sampling_agent_configurations
- this implementation is quite literally looking up info in the agent struct that was passed
* Update lib/rocprofiler/pc_sampling.cpp
- remove rocprofiler_query_pc_sampling_agent_configurations
* update lib/rocprofiler/agent.cpp
- handle const fields
- make mi200_pc_sampling_config variable static
* Update lib/rocprofiler/tests/agent.cpp
- tweak to pc_sampling_configs offset
* Update samples/pc_sampling
- Update sample to reflect minor tweaks to pc_sampling_configs in rocprofiler_agent_t
* Update CI workflow
- remove 'if: ${{ always() }}'
- I suspect this is why the jobs do not cancel in progress correctly
|
||
|
Jonathan R. Madsen
|
a798a26227 |
Agent information w/o using hsa-runtime (#100)
* Agent information w/o using hsa-runtime
- remove lib/rocprofiler/hsa/agent.{hpp,cpp}
- update include/rocprofiler/agent.h
- basically all possible info from /sys/class/kfd/kfd/topology/nodes/*
* Print topology in rocprofiler_lib.agent test
- hack to help diagnose errors
* Update lib/rocprofiler/tests/details/agent.cpp
- use LOG_IF(WARNING, ...) instead of LOG_IF(FATAL, ...)
* Update lib/rocprofiler/tests/agent.cpp
- print rocminfo at beginning of test
- fix comparison of agent handle
- misc other checks
* Updte lib/rocprofiler/agent.cpp
- handle unreadable /sys/class/kfd/kfd/topology/nodes/<N>/properties file
* Update lib/tests/buffering/CMakeLists.txt
- increase timeout to 120
- buffering.parallel will timeout when thread sanitizing is enabled
* Update cmake: rocprofiler-drm
- find drm headers and libraries
* Update include/rocprofiler/agent.h
- add family_id field
* Update lib/rocprofiler/agent.cpp
- parse /proc/cpuinfo for name, family, apicid, etc.
- read_topology uses unique pointers to cleanup memory allocations
- implement name and gfxip
* Update lib/rocprofiler/tests/agent.cpp
- improved failure message
- check name/gfxip
- remove check against hsa_agent_t.handle
- this value is dependent on the address of C++ class
* Update lib/rocprofiler/tests/details/agent.cpp
- tweak gfxip_ variable which is broken for CPU
* Update lib/rocprofiler/agent.cpp
- update string handling for name and gfxip
* Update lib/rocprofiler/tests/agent.cpp
- minor output tweak
* Update lib/rocprofiler/registration.{hpp,cpp}
- registration::init_logging() function
* Update lib/rocprofiler/agent.cpp
- fix hex handling of GFX step version
* Update lib/rocprofiler/tests/details/agent.cpp
- fix format string when nearest CPUs not found
* Update lib/rocprofiler/tests/CMakeLists.txt
- exclude details/agent.cpp from being parsed for gtest tests
* Update include/rocprofiler/fwd.h
- add ROCPROFILER_STATUS_ERROR_INCOMPATIBLE_ABI status
* Update lib/rocprofiler/tests/details/agent.{hpp,cpp}
- replace with slightly modified implementation of rocminfo
- primary change was not printing
* Update lib/rocprofiler/tests/agent.cpp
- update test to use rocminfo data
* Update lib/rocprofiler/agent.cpp
- add pc_sampling_configs
- return error on incompatible ABI
* Update counters and counters tests
- rename test names for consistency
- fixed incorrect spelling of derived
* Add lib/rocprofiler/tests/{timestamp,version}.cpp
- add timestamp and version tests for rocprofiler_get_timestamp and rocprofiler_get_version, respectively
* Update lib/rocprofiler/tests/agent
- fix double free of name_str from isa_info_t
* Update include/rocprofiler/agent.h
- comments for rocprofiler_agent_mem_bank_t
- add rocprofiler_dim3_t
- comments for rocprofiler_agent_t
- add new fields to rocprofiler_agent_t
- cu_count
- workgroup_max_size
- workgroup_max_dim
- grid_max_size
- grid_max_dim
- vendor_name
- product_name
- change prototype of rocprofiler_available_agents_cb_t to be const agent**
* Update lib/rocprofiler/agent.cpp
- set size field
- implement:
- product_name
- vendor_name
- workgroup_max_size
- workgroup_max_dim
- grid_max_size
- grid_max_dim
- cu_count
* Update lib/rocprofiler/tests/agent.cpp
- changes for const agent*
* Update samples/pc_sampling
- updates for const agent*
* Update lib/rocprofiler/agent.cpp
- fix ABI compatibility check
- return incompatible if tool agent is larger than our agent
* Update include/rocprofiler/agent.h
- doxygen comments
- make size field of rocprofiler_agent_t uint64_t for consistency
- add gpu_id via /sys/class/kfd/kfd/.../<idx>/gpu_id
- add model_name via /sys/class/kfd/kfd/.../<idx>/name
* Update lib/rocprofiler/agent.cpp
- add read_file function (vector of strings)
- support enum in read_property
- assign model_name and gpu_id fields
- remove unique_id
* Update lib/rocprofiler/tests/details/agent.*
- support family id, ucode_version, sdma_ucode_version
* Update lib/rocprofiler/tests/agent.cpp
- Add rocprofiler_lib.agent_abi test
- Verify family_id, ucode_version, sdma_ucode_version
|
||
|
Jonathan R. Madsen
|
6fb9000fa1 |
Agent Implementation (#78)
* Agent Implementation
* Remove unused Findrocprofiler
* Update lib/rocprofiler/hsa/agent.{hpp,cpp}
- default AgentInfo ctor
- getNumaNode() const
- noexcept move ctors
- default initializers for member variables
- fixed clang-tidy recommentations
- preallocate
- static in anon namespace
- AgentInfo::setName uses strncpy and ensures that it is terminated
* Update lib/rocprofiler/rocprofiler.cpp (agent.cpp and pc_sampling.cpp)
- move public PC sampling function implementations to pc_sampling.cpp
- move public agent function implementation to agent.cpp
|