Remove static pmc files (#606)
* Delete static pmc files * Counter parsing changes - Move counter parsing logic to another function - Fix counter parsing regex - Log list of counters being collected * Sanity check counters supported by rocprof - Emit warning instead of error since rocprof support counters list might be inaccurate * Do not collect these counters - TCP_TCP_LATENCY_sum (except for gfx908 and gfx90a) - SQC_DCACHE_INFLIGHT_LEVEL * Update logic of writing TCC channel counter definition yaml file * Fix bug in capture_subprocess_output() utility function - Make logging optional in capture_subprocess_output() * Fix formatting and tests * Update changelong
This commit is contained in:
gecommit door
GitHub
bovenliggende
0c0906f238
commit
58cf702d40
@@ -1,13 +0,0 @@
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES
|
||||
|
||||
pmc: CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE
|
||||
pmc: CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE
|
||||
pmc: CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION
|
||||
pmc: CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE
|
||||
pmc: CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE
|
||||
pmc: CPC_ME1_DC0_SPI_BUSY
|
||||
|
||||
range:
|
||||
gpu:
|
||||
|
||||
kernel:
|
||||
@@ -1,11 +0,0 @@
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES
|
||||
|
||||
pmc: CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL
|
||||
pmc: CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL
|
||||
pmc: CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE
|
||||
pmc: CPF_CMP_UTCL1_STALL_ON_TRANSLATION
|
||||
|
||||
range:
|
||||
gpu:
|
||||
|
||||
kernel:
|
||||
@@ -1,10 +0,0 @@
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES GRBM_SPI_BUSY
|
||||
|
||||
pmc: SPI_CSN_WINDOW_VALID SPI_CSN_BUSY SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN
|
||||
pmc: SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN
|
||||
pmc: SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN
|
||||
|
||||
range:
|
||||
gpu:
|
||||
|
||||
kernel:
|
||||
@@ -1,27 +0,0 @@
|
||||
#SQ
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU SQ_INSTS_VSKIPPED
|
||||
pmc: SQ_INSTS_SMEM SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG SQ_INSTS
|
||||
pmc: SQ_WAVE_CYCLES SQ_WAIT_ANY SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_INSTS_VALU
|
||||
pmc: SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS 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
|
||||
pmc: SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU SQ_THREAD_CYCLES_VALU SQ_IFETCH SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL
|
||||
pmc: SQ_WAVES SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 SQ_WAVES_LT_32 SQ_WAVES_LT_16 SQ_ITEMS SQ_INSTS_VSKIPPED
|
||||
pmc: SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED SQ_INSTS_SMEM_NORM
|
||||
|
||||
|
||||
#SQ:MI200
|
||||
#pmc: 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
|
||||
#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
|
||||
pmc: 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 SQC_DCACHE_REQ_READ_16
|
||||
pmc: 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
|
||||
pmc: 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
|
||||
|
||||
|
||||
|
||||
########################################
|
||||
# Filtering
|
||||
########################################
|
||||
range:
|
||||
gpu:
|
||||
kernel:
|
||||
@@ -1,10 +0,0 @@
|
||||
#################################################
|
||||
# VMEM latency
|
||||
#################################################
|
||||
pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES
|
||||
|
||||
|
||||
range:
|
||||
gpu:
|
||||
|
||||
kernel:
|
||||
@@ -1,11 +0,0 @@
|
||||
#################################################
|
||||
# SMEM latency
|
||||
#################################################
|
||||
pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES
|
||||
|
||||
|
||||
range:
|
||||
gpu:
|
||||
|
||||
|
||||
kernel:
|
||||
@@ -1,8 +0,0 @@
|
||||
#################################################
|
||||
# ifetch latency
|
||||
#################################################
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES
|
||||
|
||||
range:
|
||||
gpu:
|
||||
kernel:
|
||||
@@ -1,9 +0,0 @@
|
||||
#################################################
|
||||
# LDS latency
|
||||
#################################################
|
||||
pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES
|
||||
|
||||
range:
|
||||
gpu:
|
||||
|
||||
kernel:
|
||||
@@ -1,6 +0,0 @@
|
||||
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:
|
||||
@@ -1,11 +0,0 @@
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_WAVES SQ_WAVE_CYCLES
|
||||
|
||||
|
||||
pmc: 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 SQC_DCACHE_REQ_READ_16
|
||||
pmc: 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
|
||||
pmc: 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
|
||||
|
||||
range:
|
||||
gpu:
|
||||
|
||||
kernel:
|
||||
@@ -1,37 +0,0 @@
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_WAVES SQ_WAVE_CYCLES
|
||||
|
||||
pmc: TA_TA_BUSY_sum TA_SH_FIFO_BUSY_sum
|
||||
pmc: TA_SH_FIFO_CMD_BUSY_sum TA_SH_FIFO_ADDR_BUSY_sum
|
||||
pmc: TA_SH_FIFO_DATA_BUSY_sum TA_SH_FIFO_DATA_SFIFO_BUSY_sum
|
||||
pmc: TA_SH_FIFO_DATA_TFIFO_BUSY_sum TA_SQ_TA_CMD_CYCLES_sum
|
||||
pmc: TA_SP_TA_ADDR_CYCLES_sum TA_SP_TA_DATA_CYCLES_sum
|
||||
|
||||
|
||||
# Starvation
|
||||
pmc: TA_SH_FIFO_ADDR_STARVED_WHILE_BUSY_CYCLES_sum TA_SH_FIFO_CMD_STARVED_WHILE_BUSY_CYCLES_sum
|
||||
pmc: TA_SH_FIFO_DATA_STARVED_WHILE_BUSY_CYCLES_sum TA_TA_SH_FIFO_STARVED_sum
|
||||
|
||||
|
||||
|
||||
# buffer access
|
||||
pmc: TA_BUFFER_WAVEFRONTS_sum TA_BUFFER_READ_WAVEFRONTS_sum
|
||||
pmc: TA_BUFFER_WRITE_WAVEFRONTS_sum TA_BUFFER_ATOMIC_WAVEFRONTS_sum
|
||||
pmc: TA_BUFFER_TOTAL_CYCLES_sum TA_BUFFER_COALESCABLE_WAVEFRONTS_sum
|
||||
pmc: TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum
|
||||
|
||||
|
||||
# stalls
|
||||
pmc: TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum
|
||||
pmc: TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum
|
||||
|
||||
# flat accesses
|
||||
pmc: TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum
|
||||
pmc: TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum
|
||||
pmc: TA_FLAT_COALESCEABLE_WAVEFRONTS_sum
|
||||
|
||||
|
||||
range:
|
||||
|
||||
gpu:
|
||||
|
||||
kernel:
|
||||
@@ -1,25 +0,0 @@
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES
|
||||
|
||||
# MI50: no TCC_RW_REQ
|
||||
pmc: TCC_CYCLE[0] TCC_HIT[0] TCC_MISS[0] TCC_CYCLE[1] TCC_HIT[1] TCC_MISS[1] TCC_CYCLE[2] TCC_HIT[2] TCC_MISS[2] TCC_CYCLE[3] TCC_HIT[3] TCC_MISS[3] TCC_CYCLE[4] TCC_HIT[4] TCC_MISS[4] TCC_CYCLE[5] TCC_HIT[5] TCC_MISS[5] TCC_CYCLE[6] TCC_HIT[6] TCC_MISS[6] TCC_CYCLE[7] TCC_HIT[7] TCC_MISS[7] TCC_CYCLE[8] TCC_HIT[8] TCC_MISS[8] TCC_CYCLE[9] TCC_HIT[9] TCC_MISS[9] TCC_CYCLE[10] TCC_HIT[10] TCC_MISS[10] TCC_CYCLE[11] TCC_HIT[11] TCC_MISS[11] TCC_CYCLE[12] TCC_HIT[12] TCC_MISS[12] TCC_CYCLE[13] TCC_HIT[13] TCC_MISS[13] TCC_CYCLE[14] TCC_HIT[14] TCC_MISS[14] TCC_CYCLE[15] TCC_HIT[15] TCC_MISS[15]
|
||||
|
||||
|
||||
|
||||
pmc: TCC_REQ[0] TCC_READ[0] TCC_WRITE[0] TCC_ATOMIC[0] TCC_REQ[1] TCC_READ[1] TCC_WRITE[1] TCC_ATOMIC[1] TCC_REQ[2] TCC_READ[2] TCC_WRITE[2] TCC_ATOMIC[2] TCC_REQ[3] TCC_READ[3] TCC_WRITE[3] TCC_ATOMIC[3] TCC_REQ[4] TCC_READ[4] TCC_WRITE[4] TCC_ATOMIC[4] TCC_REQ[5] TCC_READ[5] TCC_WRITE[5] TCC_ATOMIC[5] TCC_REQ[6] TCC_READ[6] TCC_WRITE[6] TCC_ATOMIC[6] TCC_REQ[7] TCC_READ[7] TCC_WRITE[7] TCC_ATOMIC[7] TCC_REQ[8] TCC_READ[8] TCC_WRITE[8] TCC_ATOMIC[8] TCC_REQ[9] TCC_READ[9] TCC_WRITE[9] TCC_ATOMIC[9] TCC_REQ[10] TCC_READ[10] TCC_WRITE[10] TCC_ATOMIC[10] TCC_REQ[11] TCC_READ[11] TCC_WRITE[11] TCC_ATOMIC[11] TCC_REQ[12] TCC_READ[12] TCC_WRITE[12] TCC_ATOMIC[12] TCC_REQ[13] TCC_READ[13] TCC_WRITE[13] TCC_ATOMIC[13] TCC_REQ[14] TCC_READ[14] TCC_WRITE[14] TCC_ATOMIC[14] TCC_REQ[15] TCC_READ[15] TCC_WRITE[15] TCC_ATOMIC[15]
|
||||
|
||||
|
||||
|
||||
pmc: TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_WRREQ[0] TCC_EA_WRREQ_64B[0] TCC_EA_RDREQ[1] TCC_EA_RDREQ_32B[1] TCC_EA_WRREQ[1] TCC_EA_WRREQ_64B[1] TCC_EA_RDREQ[2] TCC_EA_RDREQ_32B[2] TCC_EA_WRREQ[2] TCC_EA_WRREQ_64B[2] TCC_EA_RDREQ[3] TCC_EA_RDREQ_32B[3] TCC_EA_WRREQ[3] TCC_EA_WRREQ_64B[3] TCC_EA_RDREQ[4] TCC_EA_RDREQ_32B[4] TCC_EA_WRREQ[4] TCC_EA_WRREQ_64B[4] TCC_EA_RDREQ[5] TCC_EA_RDREQ_32B[5] TCC_EA_WRREQ[5] TCC_EA_WRREQ_64B[5] TCC_EA_RDREQ[6] TCC_EA_RDREQ_32B[6] TCC_EA_WRREQ[6] TCC_EA_WRREQ_64B[6] TCC_EA_RDREQ[7] TCC_EA_RDREQ_32B[7] TCC_EA_WRREQ[7] TCC_EA_WRREQ_64B[7] TCC_EA_RDREQ[8] TCC_EA_RDREQ_32B[8] TCC_EA_WRREQ[8] TCC_EA_WRREQ_64B[8] TCC_EA_RDREQ[9] TCC_EA_RDREQ_32B[9] TCC_EA_WRREQ[9] TCC_EA_WRREQ_64B[9] TCC_EA_RDREQ[10] TCC_EA_RDREQ_32B[10] TCC_EA_WRREQ[10] TCC_EA_WRREQ_64B[10] TCC_EA_RDREQ[11] TCC_EA_RDREQ_32B[11] TCC_EA_WRREQ[11] TCC_EA_WRREQ_64B[11] TCC_EA_RDREQ[12] TCC_EA_RDREQ_32B[12] TCC_EA_WRREQ[12] TCC_EA_WRREQ_64B[12] TCC_EA_RDREQ[13] TCC_EA_RDREQ_32B[13] TCC_EA_WRREQ[13] TCC_EA_WRREQ_64B[13] TCC_EA_RDREQ[14] TCC_EA_RDREQ_32B[14] TCC_EA_WRREQ[14] TCC_EA_WRREQ_64B[14] TCC_EA_RDREQ[15] TCC_EA_RDREQ_32B[15] TCC_EA_WRREQ[15] TCC_EA_WRREQ_64B[15]
|
||||
|
||||
|
||||
pmc: TCC_EA_ATOMIC[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ_LEVEL[0] TCC_EA_ATOMIC_LEVEL[0] TCC_EA_ATOMIC[1] TCC_EA_RDREQ_LEVEL[1] TCC_EA_WRREQ_LEVEL[1] TCC_EA_ATOMIC_LEVEL[1] TCC_EA_ATOMIC[2] TCC_EA_RDREQ_LEVEL[2] TCC_EA_WRREQ_LEVEL[2] TCC_EA_ATOMIC_LEVEL[2] TCC_EA_ATOMIC[3] TCC_EA_RDREQ_LEVEL[3] TCC_EA_WRREQ_LEVEL[3] TCC_EA_ATOMIC_LEVEL[3] TCC_EA_ATOMIC[4] TCC_EA_RDREQ_LEVEL[4] TCC_EA_WRREQ_LEVEL[4] TCC_EA_ATOMIC_LEVEL[4] TCC_EA_ATOMIC[5] TCC_EA_RDREQ_LEVEL[5] TCC_EA_WRREQ_LEVEL[5] TCC_EA_ATOMIC_LEVEL[5] TCC_EA_ATOMIC[6] TCC_EA_RDREQ_LEVEL[6] TCC_EA_WRREQ_LEVEL[6] TCC_EA_ATOMIC_LEVEL[6] TCC_EA_ATOMIC[7] TCC_EA_RDREQ_LEVEL[7] TCC_EA_WRREQ_LEVEL[7] TCC_EA_ATOMIC_LEVEL[7] TCC_EA_ATOMIC[8] TCC_EA_RDREQ_LEVEL[8] TCC_EA_WRREQ_LEVEL[8] TCC_EA_ATOMIC_LEVEL[8] TCC_EA_ATOMIC[9] TCC_EA_RDREQ_LEVEL[9] TCC_EA_WRREQ_LEVEL[9] TCC_EA_ATOMIC_LEVEL[9] TCC_EA_ATOMIC[10] TCC_EA_RDREQ_LEVEL[10] TCC_EA_WRREQ_LEVEL[10] TCC_EA_ATOMIC_LEVEL[10] TCC_EA_ATOMIC[11] TCC_EA_RDREQ_LEVEL[11] TCC_EA_WRREQ_LEVEL[11] TCC_EA_ATOMIC_LEVEL[11] TCC_EA_ATOMIC[12] TCC_EA_RDREQ_LEVEL[12] TCC_EA_WRREQ_LEVEL[12] TCC_EA_ATOMIC_LEVEL[12] TCC_EA_ATOMIC[13] TCC_EA_RDREQ_LEVEL[13] TCC_EA_WRREQ_LEVEL[13] TCC_EA_ATOMIC_LEVEL[13] TCC_EA_ATOMIC[14] TCC_EA_RDREQ_LEVEL[14] TCC_EA_WRREQ_LEVEL[14] TCC_EA_ATOMIC_LEVEL[14] TCC_EA_ATOMIC[15] TCC_EA_RDREQ_LEVEL[15] TCC_EA_WRREQ_LEVEL[15] TCC_EA_ATOMIC_LEVEL[15]
|
||||
|
||||
|
||||
pmc: TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_GMI_CREDIT_STALL[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_EA_RDREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_GMI_CREDIT_STALL[1] TCC_EA_RDREQ_DRAM_CREDIT_STALL[1] TCC_EA_RDREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_GMI_CREDIT_STALL[2] TCC_EA_RDREQ_DRAM_CREDIT_STALL[2] TCC_EA_RDREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_GMI_CREDIT_STALL[3] TCC_EA_RDREQ_DRAM_CREDIT_STALL[3] TCC_EA_RDREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_GMI_CREDIT_STALL[4] TCC_EA_RDREQ_DRAM_CREDIT_STALL[4] TCC_EA_RDREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_GMI_CREDIT_STALL[5] TCC_EA_RDREQ_DRAM_CREDIT_STALL[5] TCC_EA_RDREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_GMI_CREDIT_STALL[6] TCC_EA_RDREQ_DRAM_CREDIT_STALL[6] TCC_EA_RDREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_GMI_CREDIT_STALL[7] TCC_EA_RDREQ_DRAM_CREDIT_STALL[7] TCC_EA_RDREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_GMI_CREDIT_STALL[8] TCC_EA_RDREQ_DRAM_CREDIT_STALL[8] TCC_EA_RDREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_GMI_CREDIT_STALL[9] TCC_EA_RDREQ_DRAM_CREDIT_STALL[9] TCC_EA_RDREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_GMI_CREDIT_STALL[10] TCC_EA_RDREQ_DRAM_CREDIT_STALL[10] TCC_EA_RDREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_GMI_CREDIT_STALL[11] TCC_EA_RDREQ_DRAM_CREDIT_STALL[11] TCC_EA_RDREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_GMI_CREDIT_STALL[12] TCC_EA_RDREQ_DRAM_CREDIT_STALL[12] TCC_EA_RDREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_GMI_CREDIT_STALL[13] TCC_EA_RDREQ_DRAM_CREDIT_STALL[13] TCC_EA_RDREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_GMI_CREDIT_STALL[14] TCC_EA_RDREQ_DRAM_CREDIT_STALL[14] TCC_EA_RDREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_GMI_CREDIT_STALL[15] TCC_EA_RDREQ_DRAM_CREDIT_STALL[15]
|
||||
|
||||
|
||||
pmc: TCC_EA_WRREQ_IO_CREDIT_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_EA_WRREQ_IO_CREDIT_STALL[1] TCC_EA_WRREQ_GMI_CREDIT_STALL[1] TCC_EA_WRREQ_DRAM_CREDIT_STALL[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_EA_WRREQ_IO_CREDIT_STALL[2] TCC_EA_WRREQ_GMI_CREDIT_STALL[2] TCC_EA_WRREQ_DRAM_CREDIT_STALL[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_EA_WRREQ_IO_CREDIT_STALL[3] TCC_EA_WRREQ_GMI_CREDIT_STALL[3] TCC_EA_WRREQ_DRAM_CREDIT_STALL[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_EA_WRREQ_IO_CREDIT_STALL[4] TCC_EA_WRREQ_GMI_CREDIT_STALL[4] TCC_EA_WRREQ_DRAM_CREDIT_STALL[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_EA_WRREQ_IO_CREDIT_STALL[5] TCC_EA_WRREQ_GMI_CREDIT_STALL[5] TCC_EA_WRREQ_DRAM_CREDIT_STALL[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_EA_WRREQ_IO_CREDIT_STALL[6] TCC_EA_WRREQ_GMI_CREDIT_STALL[6] TCC_EA_WRREQ_DRAM_CREDIT_STALL[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_EA_WRREQ_IO_CREDIT_STALL[7] TCC_EA_WRREQ_GMI_CREDIT_STALL[7] TCC_EA_WRREQ_DRAM_CREDIT_STALL[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_EA_WRREQ_IO_CREDIT_STALL[8] TCC_EA_WRREQ_GMI_CREDIT_STALL[8] TCC_EA_WRREQ_DRAM_CREDIT_STALL[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_EA_WRREQ_IO_CREDIT_STALL[9] TCC_EA_WRREQ_GMI_CREDIT_STALL[9] TCC_EA_WRREQ_DRAM_CREDIT_STALL[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_EA_WRREQ_IO_CREDIT_STALL[10] TCC_EA_WRREQ_GMI_CREDIT_STALL[10] TCC_EA_WRREQ_DRAM_CREDIT_STALL[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_EA_WRREQ_IO_CREDIT_STALL[11] TCC_EA_WRREQ_GMI_CREDIT_STALL[11] TCC_EA_WRREQ_DRAM_CREDIT_STALL[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_EA_WRREQ_IO_CREDIT_STALL[12] TCC_EA_WRREQ_GMI_CREDIT_STALL[12] TCC_EA_WRREQ_DRAM_CREDIT_STALL[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_EA_WRREQ_IO_CREDIT_STALL[13] TCC_EA_WRREQ_GMI_CREDIT_STALL[13] TCC_EA_WRREQ_DRAM_CREDIT_STALL[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_EA_WRREQ_IO_CREDIT_STALL[14] TCC_EA_WRREQ_GMI_CREDIT_STALL[14] TCC_EA_WRREQ_DRAM_CREDIT_STALL[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_EA_WRREQ_IO_CREDIT_STALL[15] TCC_EA_WRREQ_GMI_CREDIT_STALL[15] TCC_EA_WRREQ_DRAM_CREDIT_STALL[15] TCC_TOO_MANY_EA_WRREQS_STALL[15]
|
||||
|
||||
gpu:
|
||||
kernel:
|
||||
range:
|
||||
@@ -1,18 +0,0 @@
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES
|
||||
|
||||
pmc: TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum
|
||||
pmc: TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum
|
||||
pmc: TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum
|
||||
pmc: TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum
|
||||
pmc: TCC_EA_WRREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WR_UNCACHED_32B_sum
|
||||
pmc: 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
|
||||
pmc: TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA_ATOMIC_sum TCC_EA_RDREQ_sum TCC_EA_RDREQ_32B_sum
|
||||
pmc: TCC_EA_RD_UNCACHED_32B_sum TCC_EA_RDREQ_IO_CREDIT_STALL_sum TCC_EA_RDREQ_GMI_CREDIT_STALL_sum TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum
|
||||
pmc: TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum TCC_NORMAL_EVICT_sum
|
||||
pmc: TCC_ALL_TC_OP_INV_EVICT_sum TCC_EA_RDREQ_DRAM_sum TCC_EA_WRREQ_DRAM_sum
|
||||
pmc: TCC_EA_RDREQ_LEVEL_sum TCC_EA_WRREQ_LEVEL_sum TCC_EA_ATOMIC_LEVEL_sum
|
||||
|
||||
gpu:
|
||||
kernel:
|
||||
|
||||
range:
|
||||
@@ -1,18 +0,0 @@
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_WAVES SQ_WAVE_CYCLES
|
||||
|
||||
pmc: TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum
|
||||
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
|
||||
pmc: TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum
|
||||
pmc: TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum
|
||||
pmc: TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum
|
||||
pmc: TCP_TCP_LATENCY_sum TCP_TCC_READ_REQ_LATENCY_sum TCP_TCC_WRITE_REQ_LATENCY_sum TCP_TCC_READ_REQ_sum
|
||||
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
|
||||
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
|
||||
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
|
||||
pmc: TCP_PENDING_STALL_CYCLES_sum
|
||||
|
||||
#pmc: TCA_CYCLE_sum TCA_BUSY_sum
|
||||
|
||||
gpu:
|
||||
kernel:
|
||||
range:
|
||||
@@ -1,11 +0,0 @@
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_WAVES SQ_WAVE_CYCLES
|
||||
|
||||
pmc: TD_TD_BUSY_sum TD_TC_STALL_sum
|
||||
pmc: TD_COALESCABLE_WAVEFRONT_sum TD_LOAD_WAVEFRONT_sum
|
||||
pmc: TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum
|
||||
|
||||
|
||||
|
||||
gpu:
|
||||
range:
|
||||
kernel:
|
||||
@@ -1,13 +0,0 @@
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES
|
||||
|
||||
pmc: CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE
|
||||
pmc: CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE
|
||||
pmc: CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION
|
||||
pmc: CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE
|
||||
pmc: CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE
|
||||
pmc: CPC_ME1_DC0_SPI_BUSY
|
||||
|
||||
range:
|
||||
gpu:
|
||||
|
||||
kernel:
|
||||
@@ -1,11 +0,0 @@
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES
|
||||
|
||||
pmc: CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL
|
||||
pmc: CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL
|
||||
pmc: CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE
|
||||
pmc: CPF_CMP_UTCL1_STALL_ON_TRANSLATION
|
||||
|
||||
range:
|
||||
gpu:
|
||||
|
||||
kernel:
|
||||
@@ -1,10 +0,0 @@
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES GRBM_SPI_BUSY
|
||||
|
||||
pmc: SPI_CSN_WINDOW_VALID SPI_CSN_BUSY SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN
|
||||
pmc: SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN
|
||||
pmc: SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN
|
||||
|
||||
range:
|
||||
gpu:
|
||||
|
||||
kernel:
|
||||
@@ -1,27 +0,0 @@
|
||||
#SQ
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU SQ_INSTS_VSKIPPED
|
||||
pmc: SQ_INSTS_SMEM SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG SQ_INSTS
|
||||
pmc: SQ_WAVE_CYCLES SQ_WAIT_ANY SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_INSTS_VALU
|
||||
pmc: SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS 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
|
||||
pmc: SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU SQ_THREAD_CYCLES_VALU SQ_IFETCH SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL
|
||||
pmc: SQ_WAVES SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 SQ_WAVES_LT_32 SQ_WAVES_LT_16 SQ_ITEMS SQ_INSTS_VSKIPPED
|
||||
pmc: SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED SQ_INSTS_SMEM_NORM
|
||||
|
||||
|
||||
#SQ:MI200
|
||||
#pmc: 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
|
||||
#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
|
||||
pmc: 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 SQC_DCACHE_REQ_READ_16
|
||||
pmc: 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
|
||||
pmc: 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
|
||||
|
||||
|
||||
|
||||
########################################
|
||||
# Filtering
|
||||
########################################
|
||||
range:
|
||||
gpu:
|
||||
kernel:
|
||||
@@ -1,10 +0,0 @@
|
||||
#################################################
|
||||
# VMEM latency
|
||||
#################################################
|
||||
pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES
|
||||
|
||||
|
||||
range:
|
||||
gpu:
|
||||
|
||||
kernel:
|
||||
@@ -1,11 +0,0 @@
|
||||
#################################################
|
||||
# SMEM latency
|
||||
#################################################
|
||||
pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES
|
||||
|
||||
|
||||
range:
|
||||
gpu:
|
||||
|
||||
|
||||
kernel:
|
||||
@@ -1,8 +0,0 @@
|
||||
#################################################
|
||||
# ifetch latency
|
||||
#################################################
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES
|
||||
|
||||
range:
|
||||
gpu:
|
||||
kernel:
|
||||
@@ -1,9 +0,0 @@
|
||||
#################################################
|
||||
# LDS latency
|
||||
#################################################
|
||||
pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES
|
||||
|
||||
range:
|
||||
gpu:
|
||||
|
||||
kernel:
|
||||
@@ -1,6 +0,0 @@
|
||||
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:
|
||||
@@ -1,11 +0,0 @@
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_WAVES SQ_WAVE_CYCLES
|
||||
|
||||
|
||||
pmc: 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 SQC_DCACHE_REQ_READ_16
|
||||
pmc: 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
|
||||
pmc: 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
|
||||
|
||||
range:
|
||||
gpu:
|
||||
|
||||
kernel:
|
||||
@@ -1,25 +0,0 @@
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_WAVES SQ_WAVE_CYCLES
|
||||
|
||||
pmc: TA_TA_BUSY_sum
|
||||
|
||||
# buffer access
|
||||
pmc: TA_BUFFER_WAVEFRONTS_sum TA_BUFFER_READ_WAVEFRONTS_sum
|
||||
pmc: TA_BUFFER_WRITE_WAVEFRONTS_sum TA_BUFFER_ATOMIC_WAVEFRONTS_sum
|
||||
pmc: TA_BUFFER_TOTAL_CYCLES_sum
|
||||
pmc: TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum
|
||||
|
||||
|
||||
# stalls
|
||||
pmc: TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum
|
||||
pmc: TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum
|
||||
|
||||
# flat accesses
|
||||
pmc: TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum
|
||||
pmc: TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum
|
||||
|
||||
|
||||
range:
|
||||
|
||||
gpu:
|
||||
|
||||
kernel:
|
||||
@@ -1,25 +0,0 @@
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES
|
||||
|
||||
# MI50: no TCC_RW_REQ
|
||||
pmc: TCC_CYCLE[0] TCC_HIT[0] TCC_MISS[0] TCC_CYCLE[1] TCC_HIT[1] TCC_MISS[1] TCC_CYCLE[2] TCC_HIT[2] TCC_MISS[2] TCC_CYCLE[3] TCC_HIT[3] TCC_MISS[3] TCC_CYCLE[4] TCC_HIT[4] TCC_MISS[4] TCC_CYCLE[5] TCC_HIT[5] TCC_MISS[5] TCC_CYCLE[6] TCC_HIT[6] TCC_MISS[6] TCC_CYCLE[7] TCC_HIT[7] TCC_MISS[7] TCC_CYCLE[8] TCC_HIT[8] TCC_MISS[8] TCC_CYCLE[9] TCC_HIT[9] TCC_MISS[9] TCC_CYCLE[10] TCC_HIT[10] TCC_MISS[10] TCC_CYCLE[11] TCC_HIT[11] TCC_MISS[11] TCC_CYCLE[12] TCC_HIT[12] TCC_MISS[12] TCC_CYCLE[13] TCC_HIT[13] TCC_MISS[13] TCC_CYCLE[14] TCC_HIT[14] TCC_MISS[14] TCC_CYCLE[15] TCC_HIT[15] TCC_MISS[15]
|
||||
|
||||
|
||||
|
||||
pmc: TCC_REQ[0] TCC_READ[0] TCC_WRITE[0] TCC_ATOMIC[0] TCC_REQ[1] TCC_READ[1] TCC_WRITE[1] TCC_ATOMIC[1] TCC_REQ[2] TCC_READ[2] TCC_WRITE[2] TCC_ATOMIC[2] TCC_REQ[3] TCC_READ[3] TCC_WRITE[3] TCC_ATOMIC[3] TCC_REQ[4] TCC_READ[4] TCC_WRITE[4] TCC_ATOMIC[4] TCC_REQ[5] TCC_READ[5] TCC_WRITE[5] TCC_ATOMIC[5] TCC_REQ[6] TCC_READ[6] TCC_WRITE[6] TCC_ATOMIC[6] TCC_REQ[7] TCC_READ[7] TCC_WRITE[7] TCC_ATOMIC[7] TCC_REQ[8] TCC_READ[8] TCC_WRITE[8] TCC_ATOMIC[8] TCC_REQ[9] TCC_READ[9] TCC_WRITE[9] TCC_ATOMIC[9] TCC_REQ[10] TCC_READ[10] TCC_WRITE[10] TCC_ATOMIC[10] TCC_REQ[11] TCC_READ[11] TCC_WRITE[11] TCC_ATOMIC[11] TCC_REQ[12] TCC_READ[12] TCC_WRITE[12] TCC_ATOMIC[12] TCC_REQ[13] TCC_READ[13] TCC_WRITE[13] TCC_ATOMIC[13] TCC_REQ[14] TCC_READ[14] TCC_WRITE[14] TCC_ATOMIC[14] TCC_REQ[15] TCC_READ[15] TCC_WRITE[15] TCC_ATOMIC[15]
|
||||
|
||||
|
||||
|
||||
pmc: TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_WRREQ[0] TCC_EA_WRREQ_64B[0] TCC_EA_RDREQ[1] TCC_EA_RDREQ_32B[1] TCC_EA_WRREQ[1] TCC_EA_WRREQ_64B[1] TCC_EA_RDREQ[2] TCC_EA_RDREQ_32B[2] TCC_EA_WRREQ[2] TCC_EA_WRREQ_64B[2] TCC_EA_RDREQ[3] TCC_EA_RDREQ_32B[3] TCC_EA_WRREQ[3] TCC_EA_WRREQ_64B[3] TCC_EA_RDREQ[4] TCC_EA_RDREQ_32B[4] TCC_EA_WRREQ[4] TCC_EA_WRREQ_64B[4] TCC_EA_RDREQ[5] TCC_EA_RDREQ_32B[5] TCC_EA_WRREQ[5] TCC_EA_WRREQ_64B[5] TCC_EA_RDREQ[6] TCC_EA_RDREQ_32B[6] TCC_EA_WRREQ[6] TCC_EA_WRREQ_64B[6] TCC_EA_RDREQ[7] TCC_EA_RDREQ_32B[7] TCC_EA_WRREQ[7] TCC_EA_WRREQ_64B[7] TCC_EA_RDREQ[8] TCC_EA_RDREQ_32B[8] TCC_EA_WRREQ[8] TCC_EA_WRREQ_64B[8] TCC_EA_RDREQ[9] TCC_EA_RDREQ_32B[9] TCC_EA_WRREQ[9] TCC_EA_WRREQ_64B[9] TCC_EA_RDREQ[10] TCC_EA_RDREQ_32B[10] TCC_EA_WRREQ[10] TCC_EA_WRREQ_64B[10] TCC_EA_RDREQ[11] TCC_EA_RDREQ_32B[11] TCC_EA_WRREQ[11] TCC_EA_WRREQ_64B[11] TCC_EA_RDREQ[12] TCC_EA_RDREQ_32B[12] TCC_EA_WRREQ[12] TCC_EA_WRREQ_64B[12] TCC_EA_RDREQ[13] TCC_EA_RDREQ_32B[13] TCC_EA_WRREQ[13] TCC_EA_WRREQ_64B[13] TCC_EA_RDREQ[14] TCC_EA_RDREQ_32B[14] TCC_EA_WRREQ[14] TCC_EA_WRREQ_64B[14] TCC_EA_RDREQ[15] TCC_EA_RDREQ_32B[15] TCC_EA_WRREQ[15] TCC_EA_WRREQ_64B[15]
|
||||
|
||||
|
||||
pmc: TCC_EA_ATOMIC[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ_LEVEL[0] TCC_EA_ATOMIC_LEVEL[0] TCC_EA_ATOMIC[1] TCC_EA_RDREQ_LEVEL[1] TCC_EA_WRREQ_LEVEL[1] TCC_EA_ATOMIC_LEVEL[1] TCC_EA_ATOMIC[2] TCC_EA_RDREQ_LEVEL[2] TCC_EA_WRREQ_LEVEL[2] TCC_EA_ATOMIC_LEVEL[2] TCC_EA_ATOMIC[3] TCC_EA_RDREQ_LEVEL[3] TCC_EA_WRREQ_LEVEL[3] TCC_EA_ATOMIC_LEVEL[3] TCC_EA_ATOMIC[4] TCC_EA_RDREQ_LEVEL[4] TCC_EA_WRREQ_LEVEL[4] TCC_EA_ATOMIC_LEVEL[4] TCC_EA_ATOMIC[5] TCC_EA_RDREQ_LEVEL[5] TCC_EA_WRREQ_LEVEL[5] TCC_EA_ATOMIC_LEVEL[5] TCC_EA_ATOMIC[6] TCC_EA_RDREQ_LEVEL[6] TCC_EA_WRREQ_LEVEL[6] TCC_EA_ATOMIC_LEVEL[6] TCC_EA_ATOMIC[7] TCC_EA_RDREQ_LEVEL[7] TCC_EA_WRREQ_LEVEL[7] TCC_EA_ATOMIC_LEVEL[7] TCC_EA_ATOMIC[8] TCC_EA_RDREQ_LEVEL[8] TCC_EA_WRREQ_LEVEL[8] TCC_EA_ATOMIC_LEVEL[8] TCC_EA_ATOMIC[9] TCC_EA_RDREQ_LEVEL[9] TCC_EA_WRREQ_LEVEL[9] TCC_EA_ATOMIC_LEVEL[9] TCC_EA_ATOMIC[10] TCC_EA_RDREQ_LEVEL[10] TCC_EA_WRREQ_LEVEL[10] TCC_EA_ATOMIC_LEVEL[10] TCC_EA_ATOMIC[11] TCC_EA_RDREQ_LEVEL[11] TCC_EA_WRREQ_LEVEL[11] TCC_EA_ATOMIC_LEVEL[11] TCC_EA_ATOMIC[12] TCC_EA_RDREQ_LEVEL[12] TCC_EA_WRREQ_LEVEL[12] TCC_EA_ATOMIC_LEVEL[12] TCC_EA_ATOMIC[13] TCC_EA_RDREQ_LEVEL[13] TCC_EA_WRREQ_LEVEL[13] TCC_EA_ATOMIC_LEVEL[13] TCC_EA_ATOMIC[14] TCC_EA_RDREQ_LEVEL[14] TCC_EA_WRREQ_LEVEL[14] TCC_EA_ATOMIC_LEVEL[14] TCC_EA_ATOMIC[15] TCC_EA_RDREQ_LEVEL[15] TCC_EA_WRREQ_LEVEL[15] TCC_EA_ATOMIC_LEVEL[15]
|
||||
|
||||
|
||||
pmc: TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_GMI_CREDIT_STALL[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_EA_RDREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_GMI_CREDIT_STALL[1] TCC_EA_RDREQ_DRAM_CREDIT_STALL[1] TCC_EA_RDREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_GMI_CREDIT_STALL[2] TCC_EA_RDREQ_DRAM_CREDIT_STALL[2] TCC_EA_RDREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_GMI_CREDIT_STALL[3] TCC_EA_RDREQ_DRAM_CREDIT_STALL[3] TCC_EA_RDREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_GMI_CREDIT_STALL[4] TCC_EA_RDREQ_DRAM_CREDIT_STALL[4] TCC_EA_RDREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_GMI_CREDIT_STALL[5] TCC_EA_RDREQ_DRAM_CREDIT_STALL[5] TCC_EA_RDREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_GMI_CREDIT_STALL[6] TCC_EA_RDREQ_DRAM_CREDIT_STALL[6] TCC_EA_RDREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_GMI_CREDIT_STALL[7] TCC_EA_RDREQ_DRAM_CREDIT_STALL[7] TCC_EA_RDREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_GMI_CREDIT_STALL[8] TCC_EA_RDREQ_DRAM_CREDIT_STALL[8] TCC_EA_RDREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_GMI_CREDIT_STALL[9] TCC_EA_RDREQ_DRAM_CREDIT_STALL[9] TCC_EA_RDREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_GMI_CREDIT_STALL[10] TCC_EA_RDREQ_DRAM_CREDIT_STALL[10] TCC_EA_RDREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_GMI_CREDIT_STALL[11] TCC_EA_RDREQ_DRAM_CREDIT_STALL[11] TCC_EA_RDREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_GMI_CREDIT_STALL[12] TCC_EA_RDREQ_DRAM_CREDIT_STALL[12] TCC_EA_RDREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_GMI_CREDIT_STALL[13] TCC_EA_RDREQ_DRAM_CREDIT_STALL[13] TCC_EA_RDREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_GMI_CREDIT_STALL[14] TCC_EA_RDREQ_DRAM_CREDIT_STALL[14] TCC_EA_RDREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_GMI_CREDIT_STALL[15] TCC_EA_RDREQ_DRAM_CREDIT_STALL[15]
|
||||
|
||||
|
||||
pmc: TCC_EA_WRREQ_IO_CREDIT_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_EA_WRREQ_IO_CREDIT_STALL[1] TCC_EA_WRREQ_GMI_CREDIT_STALL[1] TCC_EA_WRREQ_DRAM_CREDIT_STALL[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_EA_WRREQ_IO_CREDIT_STALL[2] TCC_EA_WRREQ_GMI_CREDIT_STALL[2] TCC_EA_WRREQ_DRAM_CREDIT_STALL[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_EA_WRREQ_IO_CREDIT_STALL[3] TCC_EA_WRREQ_GMI_CREDIT_STALL[3] TCC_EA_WRREQ_DRAM_CREDIT_STALL[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_EA_WRREQ_IO_CREDIT_STALL[4] TCC_EA_WRREQ_GMI_CREDIT_STALL[4] TCC_EA_WRREQ_DRAM_CREDIT_STALL[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_EA_WRREQ_IO_CREDIT_STALL[5] TCC_EA_WRREQ_GMI_CREDIT_STALL[5] TCC_EA_WRREQ_DRAM_CREDIT_STALL[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_EA_WRREQ_IO_CREDIT_STALL[6] TCC_EA_WRREQ_GMI_CREDIT_STALL[6] TCC_EA_WRREQ_DRAM_CREDIT_STALL[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_EA_WRREQ_IO_CREDIT_STALL[7] TCC_EA_WRREQ_GMI_CREDIT_STALL[7] TCC_EA_WRREQ_DRAM_CREDIT_STALL[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_EA_WRREQ_IO_CREDIT_STALL[8] TCC_EA_WRREQ_GMI_CREDIT_STALL[8] TCC_EA_WRREQ_DRAM_CREDIT_STALL[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_EA_WRREQ_IO_CREDIT_STALL[9] TCC_EA_WRREQ_GMI_CREDIT_STALL[9] TCC_EA_WRREQ_DRAM_CREDIT_STALL[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_EA_WRREQ_IO_CREDIT_STALL[10] TCC_EA_WRREQ_GMI_CREDIT_STALL[10] TCC_EA_WRREQ_DRAM_CREDIT_STALL[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_EA_WRREQ_IO_CREDIT_STALL[11] TCC_EA_WRREQ_GMI_CREDIT_STALL[11] TCC_EA_WRREQ_DRAM_CREDIT_STALL[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_EA_WRREQ_IO_CREDIT_STALL[12] TCC_EA_WRREQ_GMI_CREDIT_STALL[12] TCC_EA_WRREQ_DRAM_CREDIT_STALL[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_EA_WRREQ_IO_CREDIT_STALL[13] TCC_EA_WRREQ_GMI_CREDIT_STALL[13] TCC_EA_WRREQ_DRAM_CREDIT_STALL[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_EA_WRREQ_IO_CREDIT_STALL[14] TCC_EA_WRREQ_GMI_CREDIT_STALL[14] TCC_EA_WRREQ_DRAM_CREDIT_STALL[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_EA_WRREQ_IO_CREDIT_STALL[15] TCC_EA_WRREQ_GMI_CREDIT_STALL[15] TCC_EA_WRREQ_DRAM_CREDIT_STALL[15] TCC_TOO_MANY_EA_WRREQS_STALL[15]
|
||||
|
||||
gpu:
|
||||
kernel:
|
||||
range:
|
||||
@@ -1,18 +0,0 @@
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES
|
||||
|
||||
pmc: TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum
|
||||
pmc: TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum
|
||||
pmc: TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum
|
||||
pmc: TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum
|
||||
pmc: TCC_EA_WRREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WR_UNCACHED_32B_sum TCC_EA_WRREQ_DRAM_sum
|
||||
pmc: 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
|
||||
pmc: TCC_EA_RDREQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RD_UNCACHED_32B_sum TCC_EA_RDREQ_DRAM_sum
|
||||
pmc: TCC_EA_RDREQ_IO_CREDIT_STALL_sum TCC_EA_RDREQ_GMI_CREDIT_STALL_sum TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum
|
||||
pmc: TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum TCC_NORMAL_EVICT_sum
|
||||
pmc: TCC_ALL_TC_OP_INV_EVICT_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA_ATOMIC_sum
|
||||
pmc: TCC_EA_RDREQ_LEVEL_sum TCC_EA_WRREQ_LEVEL_sum TCC_EA_ATOMIC_LEVEL_sum
|
||||
|
||||
gpu:
|
||||
kernel:
|
||||
|
||||
range:
|
||||
@@ -1,18 +0,0 @@
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_WAVES SQ_WAVE_CYCLES
|
||||
|
||||
pmc: TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum
|
||||
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
|
||||
pmc: TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum
|
||||
pmc: TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum
|
||||
pmc: TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum
|
||||
pmc: TCP_TCP_LATENCY_sum TCP_TCC_READ_REQ_LATENCY_sum TCP_TCC_WRITE_REQ_LATENCY_sum TCP_TCC_READ_REQ_sum
|
||||
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
|
||||
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
|
||||
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
|
||||
pmc: TCP_PENDING_STALL_CYCLES_sum
|
||||
|
||||
#pmc: TCA_CYCLE_sum TCA_BUSY_sum
|
||||
|
||||
gpu:
|
||||
kernel:
|
||||
range:
|
||||
@@ -1,11 +0,0 @@
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_WAVES SQ_WAVE_CYCLES
|
||||
|
||||
pmc: TD_TD_BUSY_sum TD_TC_STALL_sum
|
||||
pmc: TD_COALESCABLE_WAVEFRONT_sum TD_LOAD_WAVEFRONT_sum
|
||||
pmc: TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum
|
||||
|
||||
|
||||
|
||||
gpu:
|
||||
range:
|
||||
kernel:
|
||||
@@ -1,13 +0,0 @@
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES
|
||||
|
||||
pmc: CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE
|
||||
pmc: CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE
|
||||
pmc: CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION
|
||||
pmc: CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE
|
||||
pmc: CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE
|
||||
pmc: CPC_ME1_DC0_SPI_BUSY
|
||||
|
||||
range:
|
||||
gpu:
|
||||
|
||||
kernel:
|
||||
@@ -1,11 +0,0 @@
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES
|
||||
|
||||
pmc: CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL
|
||||
pmc: CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL
|
||||
pmc: CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE
|
||||
pmc: CPF_CMP_UTCL1_STALL_ON_TRANSLATION
|
||||
|
||||
range:
|
||||
gpu:
|
||||
|
||||
kernel:
|
||||
@@ -1,10 +0,0 @@
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES GRBM_SPI_BUSY
|
||||
|
||||
pmc: SPI_CSN_WINDOW_VALID SPI_CSN_BUSY SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN
|
||||
pmc: SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN
|
||||
pmc: SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN
|
||||
|
||||
range:
|
||||
gpu:
|
||||
|
||||
kernel:
|
||||
@@ -1,27 +0,0 @@
|
||||
#SQ
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU SQ_INSTS_VSKIPPED
|
||||
pmc: SQ_INSTS_SMEM SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG SQ_INSTS
|
||||
pmc: SQ_WAVE_CYCLES SQ_WAIT_ANY SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_INSTS_VALU
|
||||
pmc: SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS 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
|
||||
pmc: SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU SQ_THREAD_CYCLES_VALU SQ_IFETCH SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL
|
||||
pmc: SQ_WAVES SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 SQ_WAVES_LT_32 SQ_WAVES_LT_16 SQ_ITEMS SQ_INSTS_VSKIPPED
|
||||
pmc: SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED SQ_INSTS_SMEM_NORM
|
||||
|
||||
|
||||
#SQ:MI200
|
||||
#pmc: 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
|
||||
#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
|
||||
pmc: 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 SQC_DCACHE_REQ_READ_16
|
||||
pmc: 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
|
||||
pmc: 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
|
||||
|
||||
|
||||
|
||||
########################################
|
||||
# Filtering
|
||||
########################################
|
||||
range:
|
||||
gpu:
|
||||
kernel:
|
||||
@@ -1,10 +0,0 @@
|
||||
#################################################
|
||||
# VMEM latency
|
||||
#################################################
|
||||
pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES
|
||||
|
||||
|
||||
range:
|
||||
gpu:
|
||||
|
||||
kernel:
|
||||
@@ -1,11 +0,0 @@
|
||||
#################################################
|
||||
# SMEM latency
|
||||
#################################################
|
||||
pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES
|
||||
|
||||
|
||||
range:
|
||||
gpu:
|
||||
|
||||
|
||||
kernel:
|
||||
@@ -1,8 +0,0 @@
|
||||
#################################################
|
||||
# ifetch latency
|
||||
#################################################
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES
|
||||
|
||||
range:
|
||||
gpu:
|
||||
kernel:
|
||||
@@ -1,9 +0,0 @@
|
||||
#################################################
|
||||
# LDS latency
|
||||
#################################################
|
||||
pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES
|
||||
|
||||
range:
|
||||
gpu:
|
||||
|
||||
kernel:
|
||||
@@ -1,6 +0,0 @@
|
||||
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:
|
||||
@@ -1,11 +0,0 @@
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_WAVES SQ_WAVE_CYCLES
|
||||
|
||||
|
||||
pmc: 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 SQC_DCACHE_REQ_READ_16
|
||||
pmc: 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
|
||||
pmc: 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
|
||||
|
||||
range:
|
||||
gpu:
|
||||
|
||||
kernel:
|
||||
@@ -1,25 +0,0 @@
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_WAVES SQ_WAVE_CYCLES
|
||||
|
||||
pmc: TA_TA_BUSY_sum
|
||||
|
||||
# buffer access
|
||||
pmc: TA_BUFFER_WAVEFRONTS_sum TA_BUFFER_READ_WAVEFRONTS_sum
|
||||
pmc: TA_BUFFER_WRITE_WAVEFRONTS_sum TA_BUFFER_ATOMIC_WAVEFRONTS_sum
|
||||
pmc: TA_BUFFER_TOTAL_CYCLES_sum
|
||||
pmc: TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum
|
||||
|
||||
|
||||
# stalls
|
||||
pmc: TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum
|
||||
pmc: TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum
|
||||
|
||||
# flat accesses
|
||||
pmc: TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum
|
||||
pmc: TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum
|
||||
|
||||
|
||||
range:
|
||||
|
||||
gpu:
|
||||
|
||||
kernel:
|
||||
@@ -1,26 +0,0 @@
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES
|
||||
|
||||
pmc: TCC_CYCLE[0] TCC_RW_REQ[0] TCC_HIT[0] TCC_MISS[0] TCC_CYCLE[1] TCC_RW_REQ[1] TCC_HIT[1] TCC_MISS[1] TCC_CYCLE[2] TCC_RW_REQ[2] TCC_HIT[2] TCC_MISS[2] TCC_CYCLE[3] TCC_RW_REQ[3] TCC_HIT[3] TCC_MISS[3] TCC_CYCLE[4] TCC_RW_REQ[4] TCC_HIT[4] TCC_MISS[4] TCC_CYCLE[5] TCC_RW_REQ[5] TCC_HIT[5] TCC_MISS[5] TCC_CYCLE[6] TCC_RW_REQ[6] TCC_HIT[6] TCC_MISS[6] TCC_CYCLE[7] TCC_RW_REQ[7] TCC_HIT[7] TCC_MISS[7] TCC_CYCLE[8] TCC_RW_REQ[8] TCC_HIT[8] TCC_MISS[8] TCC_CYCLE[9] TCC_RW_REQ[9] TCC_HIT[9] TCC_MISS[9] TCC_CYCLE[10] TCC_RW_REQ[10] TCC_HIT[10] TCC_MISS[10] TCC_CYCLE[11] TCC_RW_REQ[11] TCC_HIT[11] TCC_MISS[11] TCC_CYCLE[12] TCC_RW_REQ[12] TCC_HIT[12] TCC_MISS[12] TCC_CYCLE[13] TCC_RW_REQ[13] TCC_HIT[13] TCC_MISS[13] TCC_CYCLE[14] TCC_RW_REQ[14] TCC_HIT[14] TCC_MISS[14] TCC_CYCLE[15] TCC_RW_REQ[15] TCC_HIT[15] TCC_MISS[15] TCC_CYCLE[16] TCC_RW_REQ[16] TCC_HIT[16] TCC_MISS[16] TCC_CYCLE[17] TCC_RW_REQ[17] TCC_HIT[17] TCC_MISS[17] TCC_CYCLE[18] TCC_RW_REQ[18] TCC_HIT[18] TCC_MISS[18] TCC_CYCLE[19] TCC_RW_REQ[19] TCC_HIT[19] TCC_MISS[19] TCC_CYCLE[20] TCC_RW_REQ[20] TCC_HIT[20] TCC_MISS[20] TCC_CYCLE[21] TCC_RW_REQ[21] TCC_HIT[21] TCC_MISS[21] TCC_CYCLE[22] TCC_RW_REQ[22] TCC_HIT[22] TCC_MISS[22] TCC_CYCLE[23] TCC_RW_REQ[23] TCC_HIT[23] TCC_MISS[23] TCC_CYCLE[24] TCC_RW_REQ[24] TCC_HIT[24] TCC_MISS[24] TCC_CYCLE[25] TCC_RW_REQ[25] TCC_HIT[25] TCC_MISS[25] TCC_CYCLE[26] TCC_RW_REQ[26] TCC_HIT[26] TCC_MISS[26] TCC_CYCLE[27] TCC_RW_REQ[27] TCC_HIT[27] TCC_MISS[27] TCC_CYCLE[28] TCC_RW_REQ[28] TCC_HIT[28] TCC_MISS[28] TCC_CYCLE[29] TCC_RW_REQ[29] TCC_HIT[29] TCC_MISS[29] TCC_CYCLE[30] TCC_RW_REQ[30] TCC_HIT[30] TCC_MISS[30] TCC_CYCLE[31] TCC_RW_REQ[31] TCC_HIT[31] TCC_MISS[31]
|
||||
|
||||
|
||||
|
||||
pmc: TCC_REQ[0] TCC_READ[0] TCC_WRITE[0] TCC_ATOMIC[0] TCC_REQ[1] TCC_READ[1] TCC_WRITE[1] TCC_ATOMIC[1] TCC_REQ[2] TCC_READ[2] TCC_WRITE[2] TCC_ATOMIC[2] TCC_REQ[3] TCC_READ[3] TCC_WRITE[3] TCC_ATOMIC[3] TCC_REQ[4] TCC_READ[4] TCC_WRITE[4] TCC_ATOMIC[4] TCC_REQ[5] TCC_READ[5] TCC_WRITE[5] TCC_ATOMIC[5] TCC_REQ[6] TCC_READ[6] TCC_WRITE[6] TCC_ATOMIC[6] TCC_REQ[7] TCC_READ[7] TCC_WRITE[7] TCC_ATOMIC[7] TCC_REQ[8] TCC_READ[8] TCC_WRITE[8] TCC_ATOMIC[8] TCC_REQ[9] TCC_READ[9] TCC_WRITE[9] TCC_ATOMIC[9] TCC_REQ[10] TCC_READ[10] TCC_WRITE[10] TCC_ATOMIC[10] TCC_REQ[11] TCC_READ[11] TCC_WRITE[11] TCC_ATOMIC[11] TCC_REQ[12] TCC_READ[12] TCC_WRITE[12] TCC_ATOMIC[12] TCC_REQ[13] TCC_READ[13] TCC_WRITE[13] TCC_ATOMIC[13] TCC_REQ[14] TCC_READ[14] TCC_WRITE[14] TCC_ATOMIC[14] TCC_REQ[15] TCC_READ[15] TCC_WRITE[15] TCC_ATOMIC[15] TCC_REQ[16] TCC_READ[16] TCC_WRITE[16] TCC_ATOMIC[16] TCC_REQ[17] TCC_READ[17] TCC_WRITE[17] TCC_ATOMIC[17] TCC_REQ[18] TCC_READ[18] TCC_WRITE[18] TCC_ATOMIC[18] TCC_REQ[19] TCC_READ[19] TCC_WRITE[19] TCC_ATOMIC[19] TCC_REQ[20] TCC_READ[20] TCC_WRITE[20] TCC_ATOMIC[20] TCC_REQ[21] TCC_READ[21] TCC_WRITE[21] TCC_ATOMIC[21] TCC_REQ[22] TCC_READ[22] TCC_WRITE[22] TCC_ATOMIC[22] TCC_REQ[23] TCC_READ[23] TCC_WRITE[23] TCC_ATOMIC[23] TCC_REQ[24] TCC_READ[24] TCC_WRITE[24] TCC_ATOMIC[24] TCC_REQ[25] TCC_READ[25] TCC_WRITE[25] TCC_ATOMIC[25] TCC_REQ[26] TCC_READ[26] TCC_WRITE[26] TCC_ATOMIC[26] TCC_REQ[27] TCC_READ[27] TCC_WRITE[27] TCC_ATOMIC[27] TCC_REQ[28] TCC_READ[28] TCC_WRITE[28] TCC_ATOMIC[28] TCC_REQ[29] TCC_READ[29] TCC_WRITE[29] TCC_ATOMIC[29] TCC_REQ[30] TCC_READ[30] TCC_WRITE[30] TCC_ATOMIC[30] TCC_REQ[31] TCC_READ[31] TCC_WRITE[31] TCC_ATOMIC[31]
|
||||
|
||||
|
||||
|
||||
pmc: TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_WRREQ[0] TCC_EA_WRREQ_64B[0] TCC_EA_RDREQ[1] TCC_EA_RDREQ_32B[1] TCC_EA_WRREQ[1] TCC_EA_WRREQ_64B[1] TCC_EA_RDREQ[2] TCC_EA_RDREQ_32B[2] TCC_EA_WRREQ[2] TCC_EA_WRREQ_64B[2] TCC_EA_RDREQ[3] TCC_EA_RDREQ_32B[3] TCC_EA_WRREQ[3] TCC_EA_WRREQ_64B[3] TCC_EA_RDREQ[4] TCC_EA_RDREQ_32B[4] TCC_EA_WRREQ[4] TCC_EA_WRREQ_64B[4] TCC_EA_RDREQ[5] TCC_EA_RDREQ_32B[5] TCC_EA_WRREQ[5] TCC_EA_WRREQ_64B[5] TCC_EA_RDREQ[6] TCC_EA_RDREQ_32B[6] TCC_EA_WRREQ[6] TCC_EA_WRREQ_64B[6] TCC_EA_RDREQ[7] TCC_EA_RDREQ_32B[7] TCC_EA_WRREQ[7] TCC_EA_WRREQ_64B[7] TCC_EA_RDREQ[8] TCC_EA_RDREQ_32B[8] TCC_EA_WRREQ[8] TCC_EA_WRREQ_64B[8] TCC_EA_RDREQ[9] TCC_EA_RDREQ_32B[9] TCC_EA_WRREQ[9] TCC_EA_WRREQ_64B[9] TCC_EA_RDREQ[10] TCC_EA_RDREQ_32B[10] TCC_EA_WRREQ[10] TCC_EA_WRREQ_64B[10] TCC_EA_RDREQ[11] TCC_EA_RDREQ_32B[11] TCC_EA_WRREQ[11] TCC_EA_WRREQ_64B[11] TCC_EA_RDREQ[12] TCC_EA_RDREQ_32B[12] TCC_EA_WRREQ[12] TCC_EA_WRREQ_64B[12] TCC_EA_RDREQ[13] TCC_EA_RDREQ_32B[13] TCC_EA_WRREQ[13] TCC_EA_WRREQ_64B[13] TCC_EA_RDREQ[14] TCC_EA_RDREQ_32B[14] TCC_EA_WRREQ[14] TCC_EA_WRREQ_64B[14] TCC_EA_RDREQ[15] TCC_EA_RDREQ_32B[15] TCC_EA_WRREQ[15] TCC_EA_WRREQ_64B[15] TCC_EA_RDREQ[16] TCC_EA_RDREQ_32B[16] TCC_EA_WRREQ[16] TCC_EA_WRREQ_64B[16] TCC_EA_RDREQ[17] TCC_EA_RDREQ_32B[17] TCC_EA_WRREQ[17] TCC_EA_WRREQ_64B[17] TCC_EA_RDREQ[18] TCC_EA_RDREQ_32B[18] TCC_EA_WRREQ[18] TCC_EA_WRREQ_64B[18] TCC_EA_RDREQ[19] TCC_EA_RDREQ_32B[19] TCC_EA_WRREQ[19] TCC_EA_WRREQ_64B[19] TCC_EA_RDREQ[20] TCC_EA_RDREQ_32B[20] TCC_EA_WRREQ[20] TCC_EA_WRREQ_64B[20] TCC_EA_RDREQ[21] TCC_EA_RDREQ_32B[21] TCC_EA_WRREQ[21] TCC_EA_WRREQ_64B[21] TCC_EA_RDREQ[22] TCC_EA_RDREQ_32B[22] TCC_EA_WRREQ[22] TCC_EA_WRREQ_64B[22] TCC_EA_RDREQ[23] TCC_EA_RDREQ_32B[23] TCC_EA_WRREQ[23] TCC_EA_WRREQ_64B[23] TCC_EA_RDREQ[24] TCC_EA_RDREQ_32B[24] TCC_EA_WRREQ[24] TCC_EA_WRREQ_64B[24] TCC_EA_RDREQ[25] TCC_EA_RDREQ_32B[25] TCC_EA_WRREQ[25] TCC_EA_WRREQ_64B[25] TCC_EA_RDREQ[26] TCC_EA_RDREQ_32B[26] TCC_EA_WRREQ[26] TCC_EA_WRREQ_64B[26] TCC_EA_RDREQ[27] TCC_EA_RDREQ_32B[27] TCC_EA_WRREQ[27] TCC_EA_WRREQ_64B[27] TCC_EA_RDREQ[28] TCC_EA_RDREQ_32B[28] TCC_EA_WRREQ[28] TCC_EA_WRREQ_64B[28] TCC_EA_RDREQ[29] TCC_EA_RDREQ_32B[29] TCC_EA_WRREQ[29] TCC_EA_WRREQ_64B[29] TCC_EA_RDREQ[30] TCC_EA_RDREQ_32B[30] TCC_EA_WRREQ[30] TCC_EA_WRREQ_64B[30] TCC_EA_RDREQ[31] TCC_EA_RDREQ_32B[31] TCC_EA_WRREQ[31] TCC_EA_WRREQ_64B[31]
|
||||
|
||||
|
||||
pmc: TCC_EA_ATOMIC[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ_LEVEL[0] TCC_EA_ATOMIC_LEVEL[0] TCC_EA_ATOMIC[1] TCC_EA_RDREQ_LEVEL[1] TCC_EA_WRREQ_LEVEL[1] TCC_EA_ATOMIC_LEVEL[1] TCC_EA_ATOMIC[2] TCC_EA_RDREQ_LEVEL[2] TCC_EA_WRREQ_LEVEL[2] TCC_EA_ATOMIC_LEVEL[2] TCC_EA_ATOMIC[3] TCC_EA_RDREQ_LEVEL[3] TCC_EA_WRREQ_LEVEL[3] TCC_EA_ATOMIC_LEVEL[3] TCC_EA_ATOMIC[4] TCC_EA_RDREQ_LEVEL[4] TCC_EA_WRREQ_LEVEL[4] TCC_EA_ATOMIC_LEVEL[4] TCC_EA_ATOMIC[5] TCC_EA_RDREQ_LEVEL[5] TCC_EA_WRREQ_LEVEL[5] TCC_EA_ATOMIC_LEVEL[5] TCC_EA_ATOMIC[6] TCC_EA_RDREQ_LEVEL[6] TCC_EA_WRREQ_LEVEL[6] TCC_EA_ATOMIC_LEVEL[6] TCC_EA_ATOMIC[7] TCC_EA_RDREQ_LEVEL[7] TCC_EA_WRREQ_LEVEL[7] TCC_EA_ATOMIC_LEVEL[7] TCC_EA_ATOMIC[8] TCC_EA_RDREQ_LEVEL[8] TCC_EA_WRREQ_LEVEL[8] TCC_EA_ATOMIC_LEVEL[8] TCC_EA_ATOMIC[9] TCC_EA_RDREQ_LEVEL[9] TCC_EA_WRREQ_LEVEL[9] TCC_EA_ATOMIC_LEVEL[9] TCC_EA_ATOMIC[10] TCC_EA_RDREQ_LEVEL[10] TCC_EA_WRREQ_LEVEL[10] TCC_EA_ATOMIC_LEVEL[10] TCC_EA_ATOMIC[11] TCC_EA_RDREQ_LEVEL[11] TCC_EA_WRREQ_LEVEL[11] TCC_EA_ATOMIC_LEVEL[11] TCC_EA_ATOMIC[12] TCC_EA_RDREQ_LEVEL[12] TCC_EA_WRREQ_LEVEL[12] TCC_EA_ATOMIC_LEVEL[12] TCC_EA_ATOMIC[13] TCC_EA_RDREQ_LEVEL[13] TCC_EA_WRREQ_LEVEL[13] TCC_EA_ATOMIC_LEVEL[13] TCC_EA_ATOMIC[14] TCC_EA_RDREQ_LEVEL[14] TCC_EA_WRREQ_LEVEL[14] TCC_EA_ATOMIC_LEVEL[14] TCC_EA_ATOMIC[15] TCC_EA_RDREQ_LEVEL[15] TCC_EA_WRREQ_LEVEL[15] TCC_EA_ATOMIC_LEVEL[15] TCC_EA_ATOMIC[16] TCC_EA_RDREQ_LEVEL[16] TCC_EA_WRREQ_LEVEL[16] TCC_EA_ATOMIC_LEVEL[16] TCC_EA_ATOMIC[17] TCC_EA_RDREQ_LEVEL[17] TCC_EA_WRREQ_LEVEL[17] TCC_EA_ATOMIC_LEVEL[17] TCC_EA_ATOMIC[18] TCC_EA_RDREQ_LEVEL[18] TCC_EA_WRREQ_LEVEL[18] TCC_EA_ATOMIC_LEVEL[18] TCC_EA_ATOMIC[19] TCC_EA_RDREQ_LEVEL[19] TCC_EA_WRREQ_LEVEL[19] TCC_EA_ATOMIC_LEVEL[19] TCC_EA_ATOMIC[20] TCC_EA_RDREQ_LEVEL[20] TCC_EA_WRREQ_LEVEL[20] TCC_EA_ATOMIC_LEVEL[20] TCC_EA_ATOMIC[21] TCC_EA_RDREQ_LEVEL[21] TCC_EA_WRREQ_LEVEL[21] TCC_EA_ATOMIC_LEVEL[21] TCC_EA_ATOMIC[22] TCC_EA_RDREQ_LEVEL[22] TCC_EA_WRREQ_LEVEL[22] TCC_EA_ATOMIC_LEVEL[22] TCC_EA_ATOMIC[23] TCC_EA_RDREQ_LEVEL[23] TCC_EA_WRREQ_LEVEL[23] TCC_EA_ATOMIC_LEVEL[23] TCC_EA_ATOMIC[24] TCC_EA_RDREQ_LEVEL[24] TCC_EA_WRREQ_LEVEL[24] TCC_EA_ATOMIC_LEVEL[24] TCC_EA_ATOMIC[25] TCC_EA_RDREQ_LEVEL[25] TCC_EA_WRREQ_LEVEL[25] TCC_EA_ATOMIC_LEVEL[25] TCC_EA_ATOMIC[26] TCC_EA_RDREQ_LEVEL[26] TCC_EA_WRREQ_LEVEL[26] TCC_EA_ATOMIC_LEVEL[26] TCC_EA_ATOMIC[27] TCC_EA_RDREQ_LEVEL[27] TCC_EA_WRREQ_LEVEL[27] TCC_EA_ATOMIC_LEVEL[27] TCC_EA_ATOMIC[28] TCC_EA_RDREQ_LEVEL[28] TCC_EA_WRREQ_LEVEL[28] TCC_EA_ATOMIC_LEVEL[28] TCC_EA_ATOMIC[29] TCC_EA_RDREQ_LEVEL[29] TCC_EA_WRREQ_LEVEL[29] TCC_EA_ATOMIC_LEVEL[29] TCC_EA_ATOMIC[30] TCC_EA_RDREQ_LEVEL[30] TCC_EA_WRREQ_LEVEL[30] TCC_EA_ATOMIC_LEVEL[30] TCC_EA_ATOMIC[31] TCC_EA_RDREQ_LEVEL[31] TCC_EA_WRREQ_LEVEL[31] TCC_EA_ATOMIC_LEVEL[31]
|
||||
|
||||
|
||||
|
||||
|
||||
pmc: TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_GMI_CREDIT_STALL[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_EA_RDREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_GMI_CREDIT_STALL[1] TCC_EA_RDREQ_DRAM_CREDIT_STALL[1] TCC_EA_RDREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_GMI_CREDIT_STALL[2] TCC_EA_RDREQ_DRAM_CREDIT_STALL[2] TCC_EA_RDREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_GMI_CREDIT_STALL[3] TCC_EA_RDREQ_DRAM_CREDIT_STALL[3] TCC_EA_RDREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_GMI_CREDIT_STALL[4] TCC_EA_RDREQ_DRAM_CREDIT_STALL[4] TCC_EA_RDREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_GMI_CREDIT_STALL[5] TCC_EA_RDREQ_DRAM_CREDIT_STALL[5] TCC_EA_RDREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_GMI_CREDIT_STALL[6] TCC_EA_RDREQ_DRAM_CREDIT_STALL[6] TCC_EA_RDREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_GMI_CREDIT_STALL[7] TCC_EA_RDREQ_DRAM_CREDIT_STALL[7] TCC_EA_RDREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_GMI_CREDIT_STALL[8] TCC_EA_RDREQ_DRAM_CREDIT_STALL[8] TCC_EA_RDREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_GMI_CREDIT_STALL[9] TCC_EA_RDREQ_DRAM_CREDIT_STALL[9] TCC_EA_RDREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_GMI_CREDIT_STALL[10] TCC_EA_RDREQ_DRAM_CREDIT_STALL[10] TCC_EA_RDREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_GMI_CREDIT_STALL[11] TCC_EA_RDREQ_DRAM_CREDIT_STALL[11] TCC_EA_RDREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_GMI_CREDIT_STALL[12] TCC_EA_RDREQ_DRAM_CREDIT_STALL[12] TCC_EA_RDREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_GMI_CREDIT_STALL[13] TCC_EA_RDREQ_DRAM_CREDIT_STALL[13] TCC_EA_RDREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_GMI_CREDIT_STALL[14] TCC_EA_RDREQ_DRAM_CREDIT_STALL[14] TCC_EA_RDREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_GMI_CREDIT_STALL[15] TCC_EA_RDREQ_DRAM_CREDIT_STALL[15] TCC_EA_RDREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_GMI_CREDIT_STALL[16] TCC_EA_RDREQ_DRAM_CREDIT_STALL[16] TCC_EA_RDREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_GMI_CREDIT_STALL[17] TCC_EA_RDREQ_DRAM_CREDIT_STALL[17] TCC_EA_RDREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_GMI_CREDIT_STALL[18] TCC_EA_RDREQ_DRAM_CREDIT_STALL[18] TCC_EA_RDREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_GMI_CREDIT_STALL[19] TCC_EA_RDREQ_DRAM_CREDIT_STALL[19] TCC_EA_RDREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_GMI_CREDIT_STALL[20] TCC_EA_RDREQ_DRAM_CREDIT_STALL[20] TCC_EA_RDREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_GMI_CREDIT_STALL[21] TCC_EA_RDREQ_DRAM_CREDIT_STALL[21] TCC_EA_RDREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_GMI_CREDIT_STALL[22] TCC_EA_RDREQ_DRAM_CREDIT_STALL[22] TCC_EA_RDREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_GMI_CREDIT_STALL[23] TCC_EA_RDREQ_DRAM_CREDIT_STALL[23] TCC_EA_RDREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_GMI_CREDIT_STALL[24] TCC_EA_RDREQ_DRAM_CREDIT_STALL[24] TCC_EA_RDREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_GMI_CREDIT_STALL[25] TCC_EA_RDREQ_DRAM_CREDIT_STALL[25] TCC_EA_RDREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_GMI_CREDIT_STALL[26] TCC_EA_RDREQ_DRAM_CREDIT_STALL[26] TCC_EA_RDREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_GMI_CREDIT_STALL[27] TCC_EA_RDREQ_DRAM_CREDIT_STALL[27] TCC_EA_RDREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_GMI_CREDIT_STALL[28] TCC_EA_RDREQ_DRAM_CREDIT_STALL[28] TCC_EA_RDREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_GMI_CREDIT_STALL[29] TCC_EA_RDREQ_DRAM_CREDIT_STALL[29] TCC_EA_RDREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_GMI_CREDIT_STALL[30] TCC_EA_RDREQ_DRAM_CREDIT_STALL[30] TCC_EA_RDREQ_IO_CREDIT_STALL[31] TCC_EA_RDREQ_GMI_CREDIT_STALL[31] TCC_EA_RDREQ_DRAM_CREDIT_STALL[31]
|
||||
|
||||
|
||||
pmc: TCC_EA_WRREQ_IO_CREDIT_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_EA_WRREQ_IO_CREDIT_STALL[1] TCC_EA_WRREQ_GMI_CREDIT_STALL[1] TCC_EA_WRREQ_DRAM_CREDIT_STALL[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_EA_WRREQ_IO_CREDIT_STALL[2] TCC_EA_WRREQ_GMI_CREDIT_STALL[2] TCC_EA_WRREQ_DRAM_CREDIT_STALL[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_EA_WRREQ_IO_CREDIT_STALL[3] TCC_EA_WRREQ_GMI_CREDIT_STALL[3] TCC_EA_WRREQ_DRAM_CREDIT_STALL[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_EA_WRREQ_IO_CREDIT_STALL[4] TCC_EA_WRREQ_GMI_CREDIT_STALL[4] TCC_EA_WRREQ_DRAM_CREDIT_STALL[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_EA_WRREQ_IO_CREDIT_STALL[5] TCC_EA_WRREQ_GMI_CREDIT_STALL[5] TCC_EA_WRREQ_DRAM_CREDIT_STALL[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_EA_WRREQ_IO_CREDIT_STALL[6] TCC_EA_WRREQ_GMI_CREDIT_STALL[6] TCC_EA_WRREQ_DRAM_CREDIT_STALL[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_EA_WRREQ_IO_CREDIT_STALL[7] TCC_EA_WRREQ_GMI_CREDIT_STALL[7] TCC_EA_WRREQ_DRAM_CREDIT_STALL[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_EA_WRREQ_IO_CREDIT_STALL[8] TCC_EA_WRREQ_GMI_CREDIT_STALL[8] TCC_EA_WRREQ_DRAM_CREDIT_STALL[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_EA_WRREQ_IO_CREDIT_STALL[9] TCC_EA_WRREQ_GMI_CREDIT_STALL[9] TCC_EA_WRREQ_DRAM_CREDIT_STALL[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_EA_WRREQ_IO_CREDIT_STALL[10] TCC_EA_WRREQ_GMI_CREDIT_STALL[10] TCC_EA_WRREQ_DRAM_CREDIT_STALL[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_EA_WRREQ_IO_CREDIT_STALL[11] TCC_EA_WRREQ_GMI_CREDIT_STALL[11] TCC_EA_WRREQ_DRAM_CREDIT_STALL[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_EA_WRREQ_IO_CREDIT_STALL[12] TCC_EA_WRREQ_GMI_CREDIT_STALL[12] TCC_EA_WRREQ_DRAM_CREDIT_STALL[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_EA_WRREQ_IO_CREDIT_STALL[13] TCC_EA_WRREQ_GMI_CREDIT_STALL[13] TCC_EA_WRREQ_DRAM_CREDIT_STALL[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_EA_WRREQ_IO_CREDIT_STALL[14] TCC_EA_WRREQ_GMI_CREDIT_STALL[14] TCC_EA_WRREQ_DRAM_CREDIT_STALL[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_EA_WRREQ_IO_CREDIT_STALL[15] TCC_EA_WRREQ_GMI_CREDIT_STALL[15] TCC_EA_WRREQ_DRAM_CREDIT_STALL[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_EA_WRREQ_IO_CREDIT_STALL[16] TCC_EA_WRREQ_GMI_CREDIT_STALL[16] TCC_EA_WRREQ_DRAM_CREDIT_STALL[16] TCC_TOO_MANY_EA_WRREQS_STALL[16] TCC_EA_WRREQ_IO_CREDIT_STALL[17] TCC_EA_WRREQ_GMI_CREDIT_STALL[17] TCC_EA_WRREQ_DRAM_CREDIT_STALL[17] TCC_TOO_MANY_EA_WRREQS_STALL[17] TCC_EA_WRREQ_IO_CREDIT_STALL[18] TCC_EA_WRREQ_GMI_CREDIT_STALL[18] TCC_EA_WRREQ_DRAM_CREDIT_STALL[18] TCC_TOO_MANY_EA_WRREQS_STALL[18] TCC_EA_WRREQ_IO_CREDIT_STALL[19] TCC_EA_WRREQ_GMI_CREDIT_STALL[19] TCC_EA_WRREQ_DRAM_CREDIT_STALL[19] TCC_TOO_MANY_EA_WRREQS_STALL[19] TCC_EA_WRREQ_IO_CREDIT_STALL[20] TCC_EA_WRREQ_GMI_CREDIT_STALL[20] TCC_EA_WRREQ_DRAM_CREDIT_STALL[20] TCC_TOO_MANY_EA_WRREQS_STALL[20] TCC_EA_WRREQ_IO_CREDIT_STALL[21] TCC_EA_WRREQ_GMI_CREDIT_STALL[21] TCC_EA_WRREQ_DRAM_CREDIT_STALL[21] TCC_TOO_MANY_EA_WRREQS_STALL[21] TCC_EA_WRREQ_IO_CREDIT_STALL[22] TCC_EA_WRREQ_GMI_CREDIT_STALL[22] TCC_EA_WRREQ_DRAM_CREDIT_STALL[22] TCC_TOO_MANY_EA_WRREQS_STALL[22] TCC_EA_WRREQ_IO_CREDIT_STALL[23] TCC_EA_WRREQ_GMI_CREDIT_STALL[23] TCC_EA_WRREQ_DRAM_CREDIT_STALL[23] TCC_TOO_MANY_EA_WRREQS_STALL[23] TCC_EA_WRREQ_IO_CREDIT_STALL[24] TCC_EA_WRREQ_GMI_CREDIT_STALL[24] TCC_EA_WRREQ_DRAM_CREDIT_STALL[24] TCC_TOO_MANY_EA_WRREQS_STALL[24] TCC_EA_WRREQ_IO_CREDIT_STALL[25] TCC_EA_WRREQ_GMI_CREDIT_STALL[25] TCC_EA_WRREQ_DRAM_CREDIT_STALL[25] TCC_TOO_MANY_EA_WRREQS_STALL[25] TCC_EA_WRREQ_IO_CREDIT_STALL[26] TCC_EA_WRREQ_GMI_CREDIT_STALL[26] TCC_EA_WRREQ_DRAM_CREDIT_STALL[26] TCC_TOO_MANY_EA_WRREQS_STALL[26] TCC_EA_WRREQ_IO_CREDIT_STALL[27] TCC_EA_WRREQ_GMI_CREDIT_STALL[27] TCC_EA_WRREQ_DRAM_CREDIT_STALL[27] TCC_TOO_MANY_EA_WRREQS_STALL[27] TCC_EA_WRREQ_IO_CREDIT_STALL[28] TCC_EA_WRREQ_GMI_CREDIT_STALL[28] TCC_EA_WRREQ_DRAM_CREDIT_STALL[28] TCC_TOO_MANY_EA_WRREQS_STALL[28] TCC_EA_WRREQ_IO_CREDIT_STALL[29] TCC_EA_WRREQ_GMI_CREDIT_STALL[29] TCC_EA_WRREQ_DRAM_CREDIT_STALL[29] TCC_TOO_MANY_EA_WRREQS_STALL[29] TCC_EA_WRREQ_IO_CREDIT_STALL[30] TCC_EA_WRREQ_GMI_CREDIT_STALL[30] TCC_EA_WRREQ_DRAM_CREDIT_STALL[30] TCC_TOO_MANY_EA_WRREQS_STALL[30] TCC_EA_WRREQ_IO_CREDIT_STALL[31] TCC_EA_WRREQ_GMI_CREDIT_STALL[31] TCC_EA_WRREQ_DRAM_CREDIT_STALL[31] TCC_TOO_MANY_EA_WRREQS_STALL[31]
|
||||
|
||||
gpu:
|
||||
kernel:
|
||||
range:
|
||||
@@ -1,18 +0,0 @@
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES
|
||||
|
||||
pmc: TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum
|
||||
pmc: TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum
|
||||
pmc: TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum
|
||||
pmc: TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum
|
||||
pmc: TCC_EA_WRREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WR_UNCACHED_32B_sum TCC_EA_WRREQ_DRAM_sum
|
||||
pmc: 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
|
||||
pmc: TCC_EA_RDREQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RD_UNCACHED_32B_sum TCC_EA_RDREQ_DRAM_sum
|
||||
pmc: TCC_EA_RDREQ_IO_CREDIT_STALL_sum TCC_EA_RDREQ_GMI_CREDIT_STALL_sum TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum
|
||||
pmc: TCC_TAG_STALL_sum TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum TCC_NORMAL_EVICT_sum
|
||||
pmc: TCC_ALL_TC_OP_INV_EVICT_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA_ATOMIC_sum
|
||||
pmc: TCC_EA_RDREQ_LEVEL_sum TCC_EA_WRREQ_LEVEL_sum TCC_EA_ATOMIC_LEVEL_sum
|
||||
|
||||
gpu:
|
||||
kernel:
|
||||
|
||||
range:
|
||||
@@ -1,18 +0,0 @@
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_WAVES SQ_WAVE_CYCLES
|
||||
|
||||
pmc: TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum
|
||||
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
|
||||
pmc: TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum
|
||||
pmc: TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum
|
||||
pmc: TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum
|
||||
pmc: TCP_TCP_LATENCY_sum TCP_TCC_READ_REQ_LATENCY_sum TCP_TCC_WRITE_REQ_LATENCY_sum TCP_TCC_READ_REQ_sum
|
||||
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
|
||||
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
|
||||
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
|
||||
pmc: TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum TCP_PENDING_STALL_CYCLES_sum
|
||||
|
||||
#pmc: TCA_CYCLE_sum TCA_BUSY_sum
|
||||
|
||||
gpu:
|
||||
kernel:
|
||||
range:
|
||||
@@ -1,11 +0,0 @@
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_WAVES SQ_WAVE_CYCLES
|
||||
|
||||
pmc: TD_TD_BUSY_sum TD_TC_STALL_sum
|
||||
pmc: TD_COALESCABLE_WAVEFRONT_sum TD_LOAD_WAVEFRONT_sum
|
||||
pmc: TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum
|
||||
|
||||
|
||||
|
||||
gpu:
|
||||
range:
|
||||
kernel:
|
||||
@@ -1,13 +0,0 @@
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES
|
||||
|
||||
pmc: CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE
|
||||
pmc: CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE
|
||||
pmc: CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION
|
||||
pmc: CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE
|
||||
pmc: CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE
|
||||
pmc: CPC_ME1_DC0_SPI_BUSY
|
||||
|
||||
range:
|
||||
gpu:
|
||||
|
||||
kernel:
|
||||
@@ -1,11 +0,0 @@
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES
|
||||
|
||||
pmc: CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL
|
||||
pmc: CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL
|
||||
pmc: CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE
|
||||
pmc: CPF_CMP_UTCL1_STALL_ON_TRANSLATION
|
||||
|
||||
range:
|
||||
gpu:
|
||||
|
||||
kernel:
|
||||
@@ -1,10 +0,0 @@
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES GRBM_SPI_BUSY
|
||||
|
||||
pmc: SPI_CSN_WINDOW_VALID SPI_CSN_BUSY SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN
|
||||
pmc: SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN
|
||||
pmc: SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN
|
||||
|
||||
range:
|
||||
gpu:
|
||||
|
||||
kernel:
|
||||
@@ -1,29 +0,0 @@
|
||||
#SQ
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_INSTS_VALU_CVT SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU SQ_INSTS_VSKIPPED
|
||||
pmc: 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 SQ_INSTS_VALU_MUL_F32
|
||||
pmc: 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 SQ_INSTS_VALU_INT64
|
||||
pmc: SQ_INSTS_SMEM SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG
|
||||
pmc: SQ_WAVE_CYCLES SQ_WAIT_ANY SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES
|
||||
pmc: SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS 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
|
||||
pmc: SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU SQ_THREAD_CYCLES_VALU SQ_IFETCH SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL
|
||||
pmc: SQ_WAVES SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 SQ_WAVES_LT_32 SQ_WAVES_LT_16 SQ_ITEMS SQ_INSTS_VSKIPPED
|
||||
pmc: SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED SQ_INSTS_SMEM_NORM
|
||||
|
||||
|
||||
#SQ:MI200
|
||||
pmc: 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
|
||||
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
|
||||
pmc: 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 SQC_DCACHE_REQ_READ_16
|
||||
pmc: 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
|
||||
pmc: 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
|
||||
|
||||
|
||||
|
||||
########################################
|
||||
# Filtering
|
||||
########################################
|
||||
range:
|
||||
gpu:
|
||||
kernel:
|
||||
@@ -1,10 +0,0 @@
|
||||
#################################################
|
||||
# VMEM latency
|
||||
#################################################
|
||||
pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES
|
||||
|
||||
|
||||
range:
|
||||
gpu:
|
||||
|
||||
kernel:
|
||||
@@ -1,11 +0,0 @@
|
||||
#################################################
|
||||
# SMEM latency
|
||||
#################################################
|
||||
pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES
|
||||
|
||||
|
||||
range:
|
||||
gpu:
|
||||
|
||||
|
||||
kernel:
|
||||
@@ -1,8 +0,0 @@
|
||||
#################################################
|
||||
# ifetch latency
|
||||
#################################################
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES
|
||||
|
||||
range:
|
||||
gpu:
|
||||
kernel:
|
||||
@@ -1,9 +0,0 @@
|
||||
#################################################
|
||||
# LDS latency
|
||||
#################################################
|
||||
pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES
|
||||
|
||||
range:
|
||||
gpu:
|
||||
|
||||
kernel:
|
||||
@@ -1,6 +0,0 @@
|
||||
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:
|
||||
@@ -1,11 +0,0 @@
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_WAVES SQ_WAVE_CYCLES
|
||||
|
||||
|
||||
pmc: 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 SQC_DCACHE_REQ_READ_16
|
||||
pmc: 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
|
||||
pmc: 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
|
||||
|
||||
range:
|
||||
gpu:
|
||||
|
||||
kernel:
|
||||
@@ -1,25 +0,0 @@
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_WAVES SQ_WAVE_CYCLES
|
||||
|
||||
pmc: TA_TA_BUSY_sum
|
||||
|
||||
# buffer access
|
||||
pmc: TA_BUFFER_WAVEFRONTS_sum TA_BUFFER_READ_WAVEFRONTS_sum
|
||||
pmc: TA_BUFFER_WRITE_WAVEFRONTS_sum TA_BUFFER_ATOMIC_WAVEFRONTS_sum
|
||||
pmc: TA_BUFFER_TOTAL_CYCLES_sum
|
||||
pmc: TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum
|
||||
|
||||
|
||||
# stalls
|
||||
pmc: TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum
|
||||
pmc: TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum
|
||||
|
||||
# flat accesses
|
||||
pmc: TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum
|
||||
pmc: TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum
|
||||
|
||||
|
||||
range:
|
||||
|
||||
gpu:
|
||||
|
||||
kernel:
|
||||
@@ -1,26 +0,0 @@
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES
|
||||
|
||||
pmc: TCC_CYCLE[0] TCC_RW_REQ[0] TCC_HIT[0] TCC_MISS[0] TCC_CYCLE[1] TCC_RW_REQ[1] TCC_HIT[1] TCC_MISS[1] TCC_CYCLE[2] TCC_RW_REQ[2] TCC_HIT[2] TCC_MISS[2] TCC_CYCLE[3] TCC_RW_REQ[3] TCC_HIT[3] TCC_MISS[3] TCC_CYCLE[4] TCC_RW_REQ[4] TCC_HIT[4] TCC_MISS[4] TCC_CYCLE[5] TCC_RW_REQ[5] TCC_HIT[5] TCC_MISS[5] TCC_CYCLE[6] TCC_RW_REQ[6] TCC_HIT[6] TCC_MISS[6] TCC_CYCLE[7] TCC_RW_REQ[7] TCC_HIT[7] TCC_MISS[7] TCC_CYCLE[8] TCC_RW_REQ[8] TCC_HIT[8] TCC_MISS[8] TCC_CYCLE[9] TCC_RW_REQ[9] TCC_HIT[9] TCC_MISS[9] TCC_CYCLE[10] TCC_RW_REQ[10] TCC_HIT[10] TCC_MISS[10] TCC_CYCLE[11] TCC_RW_REQ[11] TCC_HIT[11] TCC_MISS[11] TCC_CYCLE[12] TCC_RW_REQ[12] TCC_HIT[12] TCC_MISS[12] TCC_CYCLE[13] TCC_RW_REQ[13] TCC_HIT[13] TCC_MISS[13] TCC_CYCLE[14] TCC_RW_REQ[14] TCC_HIT[14] TCC_MISS[14] TCC_CYCLE[15] TCC_RW_REQ[15] TCC_HIT[15] TCC_MISS[15] TCC_CYCLE[16] TCC_RW_REQ[16] TCC_HIT[16] TCC_MISS[16] TCC_CYCLE[17] TCC_RW_REQ[17] TCC_HIT[17] TCC_MISS[17] TCC_CYCLE[18] TCC_RW_REQ[18] TCC_HIT[18] TCC_MISS[18] TCC_CYCLE[19] TCC_RW_REQ[19] TCC_HIT[19] TCC_MISS[19] TCC_CYCLE[20] TCC_RW_REQ[20] TCC_HIT[20] TCC_MISS[20] TCC_CYCLE[21] TCC_RW_REQ[21] TCC_HIT[21] TCC_MISS[21] TCC_CYCLE[22] TCC_RW_REQ[22] TCC_HIT[22] TCC_MISS[22] TCC_CYCLE[23] TCC_RW_REQ[23] TCC_HIT[23] TCC_MISS[23] TCC_CYCLE[24] TCC_RW_REQ[24] TCC_HIT[24] TCC_MISS[24] TCC_CYCLE[25] TCC_RW_REQ[25] TCC_HIT[25] TCC_MISS[25] TCC_CYCLE[26] TCC_RW_REQ[26] TCC_HIT[26] TCC_MISS[26] TCC_CYCLE[27] TCC_RW_REQ[27] TCC_HIT[27] TCC_MISS[27] TCC_CYCLE[28] TCC_RW_REQ[28] TCC_HIT[28] TCC_MISS[28] TCC_CYCLE[29] TCC_RW_REQ[29] TCC_HIT[29] TCC_MISS[29] TCC_CYCLE[30] TCC_RW_REQ[30] TCC_HIT[30] TCC_MISS[30] TCC_CYCLE[31] TCC_RW_REQ[31] TCC_HIT[31] TCC_MISS[31]
|
||||
|
||||
|
||||
|
||||
pmc: TCC_REQ[0] TCC_READ[0] TCC_WRITE[0] TCC_ATOMIC[0] TCC_REQ[1] TCC_READ[1] TCC_WRITE[1] TCC_ATOMIC[1] TCC_REQ[2] TCC_READ[2] TCC_WRITE[2] TCC_ATOMIC[2] TCC_REQ[3] TCC_READ[3] TCC_WRITE[3] TCC_ATOMIC[3] TCC_REQ[4] TCC_READ[4] TCC_WRITE[4] TCC_ATOMIC[4] TCC_REQ[5] TCC_READ[5] TCC_WRITE[5] TCC_ATOMIC[5] TCC_REQ[6] TCC_READ[6] TCC_WRITE[6] TCC_ATOMIC[6] TCC_REQ[7] TCC_READ[7] TCC_WRITE[7] TCC_ATOMIC[7] TCC_REQ[8] TCC_READ[8] TCC_WRITE[8] TCC_ATOMIC[8] TCC_REQ[9] TCC_READ[9] TCC_WRITE[9] TCC_ATOMIC[9] TCC_REQ[10] TCC_READ[10] TCC_WRITE[10] TCC_ATOMIC[10] TCC_REQ[11] TCC_READ[11] TCC_WRITE[11] TCC_ATOMIC[11] TCC_REQ[12] TCC_READ[12] TCC_WRITE[12] TCC_ATOMIC[12] TCC_REQ[13] TCC_READ[13] TCC_WRITE[13] TCC_ATOMIC[13] TCC_REQ[14] TCC_READ[14] TCC_WRITE[14] TCC_ATOMIC[14] TCC_REQ[15] TCC_READ[15] TCC_WRITE[15] TCC_ATOMIC[15] TCC_REQ[16] TCC_READ[16] TCC_WRITE[16] TCC_ATOMIC[16] TCC_REQ[17] TCC_READ[17] TCC_WRITE[17] TCC_ATOMIC[17] TCC_REQ[18] TCC_READ[18] TCC_WRITE[18] TCC_ATOMIC[18] TCC_REQ[19] TCC_READ[19] TCC_WRITE[19] TCC_ATOMIC[19] TCC_REQ[20] TCC_READ[20] TCC_WRITE[20] TCC_ATOMIC[20] TCC_REQ[21] TCC_READ[21] TCC_WRITE[21] TCC_ATOMIC[21] TCC_REQ[22] TCC_READ[22] TCC_WRITE[22] TCC_ATOMIC[22] TCC_REQ[23] TCC_READ[23] TCC_WRITE[23] TCC_ATOMIC[23] TCC_REQ[24] TCC_READ[24] TCC_WRITE[24] TCC_ATOMIC[24] TCC_REQ[25] TCC_READ[25] TCC_WRITE[25] TCC_ATOMIC[25] TCC_REQ[26] TCC_READ[26] TCC_WRITE[26] TCC_ATOMIC[26] TCC_REQ[27] TCC_READ[27] TCC_WRITE[27] TCC_ATOMIC[27] TCC_REQ[28] TCC_READ[28] TCC_WRITE[28] TCC_ATOMIC[28] TCC_REQ[29] TCC_READ[29] TCC_WRITE[29] TCC_ATOMIC[29] TCC_REQ[30] TCC_READ[30] TCC_WRITE[30] TCC_ATOMIC[30] TCC_REQ[31] TCC_READ[31] TCC_WRITE[31] TCC_ATOMIC[31]
|
||||
|
||||
|
||||
|
||||
pmc: TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_WRREQ[0] TCC_EA_WRREQ_64B[0] TCC_EA_RDREQ[1] TCC_EA_RDREQ_32B[1] TCC_EA_WRREQ[1] TCC_EA_WRREQ_64B[1] TCC_EA_RDREQ[2] TCC_EA_RDREQ_32B[2] TCC_EA_WRREQ[2] TCC_EA_WRREQ_64B[2] TCC_EA_RDREQ[3] TCC_EA_RDREQ_32B[3] TCC_EA_WRREQ[3] TCC_EA_WRREQ_64B[3] TCC_EA_RDREQ[4] TCC_EA_RDREQ_32B[4] TCC_EA_WRREQ[4] TCC_EA_WRREQ_64B[4] TCC_EA_RDREQ[5] TCC_EA_RDREQ_32B[5] TCC_EA_WRREQ[5] TCC_EA_WRREQ_64B[5] TCC_EA_RDREQ[6] TCC_EA_RDREQ_32B[6] TCC_EA_WRREQ[6] TCC_EA_WRREQ_64B[6] TCC_EA_RDREQ[7] TCC_EA_RDREQ_32B[7] TCC_EA_WRREQ[7] TCC_EA_WRREQ_64B[7] TCC_EA_RDREQ[8] TCC_EA_RDREQ_32B[8] TCC_EA_WRREQ[8] TCC_EA_WRREQ_64B[8] TCC_EA_RDREQ[9] TCC_EA_RDREQ_32B[9] TCC_EA_WRREQ[9] TCC_EA_WRREQ_64B[9] TCC_EA_RDREQ[10] TCC_EA_RDREQ_32B[10] TCC_EA_WRREQ[10] TCC_EA_WRREQ_64B[10] TCC_EA_RDREQ[11] TCC_EA_RDREQ_32B[11] TCC_EA_WRREQ[11] TCC_EA_WRREQ_64B[11] TCC_EA_RDREQ[12] TCC_EA_RDREQ_32B[12] TCC_EA_WRREQ[12] TCC_EA_WRREQ_64B[12] TCC_EA_RDREQ[13] TCC_EA_RDREQ_32B[13] TCC_EA_WRREQ[13] TCC_EA_WRREQ_64B[13] TCC_EA_RDREQ[14] TCC_EA_RDREQ_32B[14] TCC_EA_WRREQ[14] TCC_EA_WRREQ_64B[14] TCC_EA_RDREQ[15] TCC_EA_RDREQ_32B[15] TCC_EA_WRREQ[15] TCC_EA_WRREQ_64B[15] TCC_EA_RDREQ[16] TCC_EA_RDREQ_32B[16] TCC_EA_WRREQ[16] TCC_EA_WRREQ_64B[16] TCC_EA_RDREQ[17] TCC_EA_RDREQ_32B[17] TCC_EA_WRREQ[17] TCC_EA_WRREQ_64B[17] TCC_EA_RDREQ[18] TCC_EA_RDREQ_32B[18] TCC_EA_WRREQ[18] TCC_EA_WRREQ_64B[18] TCC_EA_RDREQ[19] TCC_EA_RDREQ_32B[19] TCC_EA_WRREQ[19] TCC_EA_WRREQ_64B[19] TCC_EA_RDREQ[20] TCC_EA_RDREQ_32B[20] TCC_EA_WRREQ[20] TCC_EA_WRREQ_64B[20] TCC_EA_RDREQ[21] TCC_EA_RDREQ_32B[21] TCC_EA_WRREQ[21] TCC_EA_WRREQ_64B[21] TCC_EA_RDREQ[22] TCC_EA_RDREQ_32B[22] TCC_EA_WRREQ[22] TCC_EA_WRREQ_64B[22] TCC_EA_RDREQ[23] TCC_EA_RDREQ_32B[23] TCC_EA_WRREQ[23] TCC_EA_WRREQ_64B[23] TCC_EA_RDREQ[24] TCC_EA_RDREQ_32B[24] TCC_EA_WRREQ[24] TCC_EA_WRREQ_64B[24] TCC_EA_RDREQ[25] TCC_EA_RDREQ_32B[25] TCC_EA_WRREQ[25] TCC_EA_WRREQ_64B[25] TCC_EA_RDREQ[26] TCC_EA_RDREQ_32B[26] TCC_EA_WRREQ[26] TCC_EA_WRREQ_64B[26] TCC_EA_RDREQ[27] TCC_EA_RDREQ_32B[27] TCC_EA_WRREQ[27] TCC_EA_WRREQ_64B[27] TCC_EA_RDREQ[28] TCC_EA_RDREQ_32B[28] TCC_EA_WRREQ[28] TCC_EA_WRREQ_64B[28] TCC_EA_RDREQ[29] TCC_EA_RDREQ_32B[29] TCC_EA_WRREQ[29] TCC_EA_WRREQ_64B[29] TCC_EA_RDREQ[30] TCC_EA_RDREQ_32B[30] TCC_EA_WRREQ[30] TCC_EA_WRREQ_64B[30] TCC_EA_RDREQ[31] TCC_EA_RDREQ_32B[31] TCC_EA_WRREQ[31] TCC_EA_WRREQ_64B[31]
|
||||
|
||||
|
||||
pmc: TCC_EA_ATOMIC[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ_LEVEL[0] TCC_EA_ATOMIC_LEVEL[0] TCC_EA_ATOMIC[1] TCC_EA_RDREQ_LEVEL[1] TCC_EA_WRREQ_LEVEL[1] TCC_EA_ATOMIC_LEVEL[1] TCC_EA_ATOMIC[2] TCC_EA_RDREQ_LEVEL[2] TCC_EA_WRREQ_LEVEL[2] TCC_EA_ATOMIC_LEVEL[2] TCC_EA_ATOMIC[3] TCC_EA_RDREQ_LEVEL[3] TCC_EA_WRREQ_LEVEL[3] TCC_EA_ATOMIC_LEVEL[3] TCC_EA_ATOMIC[4] TCC_EA_RDREQ_LEVEL[4] TCC_EA_WRREQ_LEVEL[4] TCC_EA_ATOMIC_LEVEL[4] TCC_EA_ATOMIC[5] TCC_EA_RDREQ_LEVEL[5] TCC_EA_WRREQ_LEVEL[5] TCC_EA_ATOMIC_LEVEL[5] TCC_EA_ATOMIC[6] TCC_EA_RDREQ_LEVEL[6] TCC_EA_WRREQ_LEVEL[6] TCC_EA_ATOMIC_LEVEL[6] TCC_EA_ATOMIC[7] TCC_EA_RDREQ_LEVEL[7] TCC_EA_WRREQ_LEVEL[7] TCC_EA_ATOMIC_LEVEL[7] TCC_EA_ATOMIC[8] TCC_EA_RDREQ_LEVEL[8] TCC_EA_WRREQ_LEVEL[8] TCC_EA_ATOMIC_LEVEL[8] TCC_EA_ATOMIC[9] TCC_EA_RDREQ_LEVEL[9] TCC_EA_WRREQ_LEVEL[9] TCC_EA_ATOMIC_LEVEL[9] TCC_EA_ATOMIC[10] TCC_EA_RDREQ_LEVEL[10] TCC_EA_WRREQ_LEVEL[10] TCC_EA_ATOMIC_LEVEL[10] TCC_EA_ATOMIC[11] TCC_EA_RDREQ_LEVEL[11] TCC_EA_WRREQ_LEVEL[11] TCC_EA_ATOMIC_LEVEL[11] TCC_EA_ATOMIC[12] TCC_EA_RDREQ_LEVEL[12] TCC_EA_WRREQ_LEVEL[12] TCC_EA_ATOMIC_LEVEL[12] TCC_EA_ATOMIC[13] TCC_EA_RDREQ_LEVEL[13] TCC_EA_WRREQ_LEVEL[13] TCC_EA_ATOMIC_LEVEL[13] TCC_EA_ATOMIC[14] TCC_EA_RDREQ_LEVEL[14] TCC_EA_WRREQ_LEVEL[14] TCC_EA_ATOMIC_LEVEL[14] TCC_EA_ATOMIC[15] TCC_EA_RDREQ_LEVEL[15] TCC_EA_WRREQ_LEVEL[15] TCC_EA_ATOMIC_LEVEL[15] TCC_EA_ATOMIC[16] TCC_EA_RDREQ_LEVEL[16] TCC_EA_WRREQ_LEVEL[16] TCC_EA_ATOMIC_LEVEL[16] TCC_EA_ATOMIC[17] TCC_EA_RDREQ_LEVEL[17] TCC_EA_WRREQ_LEVEL[17] TCC_EA_ATOMIC_LEVEL[17] TCC_EA_ATOMIC[18] TCC_EA_RDREQ_LEVEL[18] TCC_EA_WRREQ_LEVEL[18] TCC_EA_ATOMIC_LEVEL[18] TCC_EA_ATOMIC[19] TCC_EA_RDREQ_LEVEL[19] TCC_EA_WRREQ_LEVEL[19] TCC_EA_ATOMIC_LEVEL[19] TCC_EA_ATOMIC[20] TCC_EA_RDREQ_LEVEL[20] TCC_EA_WRREQ_LEVEL[20] TCC_EA_ATOMIC_LEVEL[20] TCC_EA_ATOMIC[21] TCC_EA_RDREQ_LEVEL[21] TCC_EA_WRREQ_LEVEL[21] TCC_EA_ATOMIC_LEVEL[21] TCC_EA_ATOMIC[22] TCC_EA_RDREQ_LEVEL[22] TCC_EA_WRREQ_LEVEL[22] TCC_EA_ATOMIC_LEVEL[22] TCC_EA_ATOMIC[23] TCC_EA_RDREQ_LEVEL[23] TCC_EA_WRREQ_LEVEL[23] TCC_EA_ATOMIC_LEVEL[23] TCC_EA_ATOMIC[24] TCC_EA_RDREQ_LEVEL[24] TCC_EA_WRREQ_LEVEL[24] TCC_EA_ATOMIC_LEVEL[24] TCC_EA_ATOMIC[25] TCC_EA_RDREQ_LEVEL[25] TCC_EA_WRREQ_LEVEL[25] TCC_EA_ATOMIC_LEVEL[25] TCC_EA_ATOMIC[26] TCC_EA_RDREQ_LEVEL[26] TCC_EA_WRREQ_LEVEL[26] TCC_EA_ATOMIC_LEVEL[26] TCC_EA_ATOMIC[27] TCC_EA_RDREQ_LEVEL[27] TCC_EA_WRREQ_LEVEL[27] TCC_EA_ATOMIC_LEVEL[27] TCC_EA_ATOMIC[28] TCC_EA_RDREQ_LEVEL[28] TCC_EA_WRREQ_LEVEL[28] TCC_EA_ATOMIC_LEVEL[28] TCC_EA_ATOMIC[29] TCC_EA_RDREQ_LEVEL[29] TCC_EA_WRREQ_LEVEL[29] TCC_EA_ATOMIC_LEVEL[29] TCC_EA_ATOMIC[30] TCC_EA_RDREQ_LEVEL[30] TCC_EA_WRREQ_LEVEL[30] TCC_EA_ATOMIC_LEVEL[30] TCC_EA_ATOMIC[31] TCC_EA_RDREQ_LEVEL[31] TCC_EA_WRREQ_LEVEL[31] TCC_EA_ATOMIC_LEVEL[31]
|
||||
|
||||
|
||||
|
||||
|
||||
pmc: TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_GMI_CREDIT_STALL[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_EA_RDREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_GMI_CREDIT_STALL[1] TCC_EA_RDREQ_DRAM_CREDIT_STALL[1] TCC_EA_RDREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_GMI_CREDIT_STALL[2] TCC_EA_RDREQ_DRAM_CREDIT_STALL[2] TCC_EA_RDREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_GMI_CREDIT_STALL[3] TCC_EA_RDREQ_DRAM_CREDIT_STALL[3] TCC_EA_RDREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_GMI_CREDIT_STALL[4] TCC_EA_RDREQ_DRAM_CREDIT_STALL[4] TCC_EA_RDREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_GMI_CREDIT_STALL[5] TCC_EA_RDREQ_DRAM_CREDIT_STALL[5] TCC_EA_RDREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_GMI_CREDIT_STALL[6] TCC_EA_RDREQ_DRAM_CREDIT_STALL[6] TCC_EA_RDREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_GMI_CREDIT_STALL[7] TCC_EA_RDREQ_DRAM_CREDIT_STALL[7] TCC_EA_RDREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_GMI_CREDIT_STALL[8] TCC_EA_RDREQ_DRAM_CREDIT_STALL[8] TCC_EA_RDREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_GMI_CREDIT_STALL[9] TCC_EA_RDREQ_DRAM_CREDIT_STALL[9] TCC_EA_RDREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_GMI_CREDIT_STALL[10] TCC_EA_RDREQ_DRAM_CREDIT_STALL[10] TCC_EA_RDREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_GMI_CREDIT_STALL[11] TCC_EA_RDREQ_DRAM_CREDIT_STALL[11] TCC_EA_RDREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_GMI_CREDIT_STALL[12] TCC_EA_RDREQ_DRAM_CREDIT_STALL[12] TCC_EA_RDREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_GMI_CREDIT_STALL[13] TCC_EA_RDREQ_DRAM_CREDIT_STALL[13] TCC_EA_RDREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_GMI_CREDIT_STALL[14] TCC_EA_RDREQ_DRAM_CREDIT_STALL[14] TCC_EA_RDREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_GMI_CREDIT_STALL[15] TCC_EA_RDREQ_DRAM_CREDIT_STALL[15] TCC_EA_RDREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_GMI_CREDIT_STALL[16] TCC_EA_RDREQ_DRAM_CREDIT_STALL[16] TCC_EA_RDREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_GMI_CREDIT_STALL[17] TCC_EA_RDREQ_DRAM_CREDIT_STALL[17] TCC_EA_RDREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_GMI_CREDIT_STALL[18] TCC_EA_RDREQ_DRAM_CREDIT_STALL[18] TCC_EA_RDREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_GMI_CREDIT_STALL[19] TCC_EA_RDREQ_DRAM_CREDIT_STALL[19] TCC_EA_RDREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_GMI_CREDIT_STALL[20] TCC_EA_RDREQ_DRAM_CREDIT_STALL[20] TCC_EA_RDREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_GMI_CREDIT_STALL[21] TCC_EA_RDREQ_DRAM_CREDIT_STALL[21] TCC_EA_RDREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_GMI_CREDIT_STALL[22] TCC_EA_RDREQ_DRAM_CREDIT_STALL[22] TCC_EA_RDREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_GMI_CREDIT_STALL[23] TCC_EA_RDREQ_DRAM_CREDIT_STALL[23] TCC_EA_RDREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_GMI_CREDIT_STALL[24] TCC_EA_RDREQ_DRAM_CREDIT_STALL[24] TCC_EA_RDREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_GMI_CREDIT_STALL[25] TCC_EA_RDREQ_DRAM_CREDIT_STALL[25] TCC_EA_RDREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_GMI_CREDIT_STALL[26] TCC_EA_RDREQ_DRAM_CREDIT_STALL[26] TCC_EA_RDREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_GMI_CREDIT_STALL[27] TCC_EA_RDREQ_DRAM_CREDIT_STALL[27] TCC_EA_RDREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_GMI_CREDIT_STALL[28] TCC_EA_RDREQ_DRAM_CREDIT_STALL[28] TCC_EA_RDREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_GMI_CREDIT_STALL[29] TCC_EA_RDREQ_DRAM_CREDIT_STALL[29] TCC_EA_RDREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_GMI_CREDIT_STALL[30] TCC_EA_RDREQ_DRAM_CREDIT_STALL[30] TCC_EA_RDREQ_IO_CREDIT_STALL[31] TCC_EA_RDREQ_GMI_CREDIT_STALL[31] TCC_EA_RDREQ_DRAM_CREDIT_STALL[31]
|
||||
|
||||
|
||||
pmc: TCC_EA_WRREQ_IO_CREDIT_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_EA_WRREQ_IO_CREDIT_STALL[1] TCC_EA_WRREQ_GMI_CREDIT_STALL[1] TCC_EA_WRREQ_DRAM_CREDIT_STALL[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_EA_WRREQ_IO_CREDIT_STALL[2] TCC_EA_WRREQ_GMI_CREDIT_STALL[2] TCC_EA_WRREQ_DRAM_CREDIT_STALL[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_EA_WRREQ_IO_CREDIT_STALL[3] TCC_EA_WRREQ_GMI_CREDIT_STALL[3] TCC_EA_WRREQ_DRAM_CREDIT_STALL[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_EA_WRREQ_IO_CREDIT_STALL[4] TCC_EA_WRREQ_GMI_CREDIT_STALL[4] TCC_EA_WRREQ_DRAM_CREDIT_STALL[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_EA_WRREQ_IO_CREDIT_STALL[5] TCC_EA_WRREQ_GMI_CREDIT_STALL[5] TCC_EA_WRREQ_DRAM_CREDIT_STALL[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_EA_WRREQ_IO_CREDIT_STALL[6] TCC_EA_WRREQ_GMI_CREDIT_STALL[6] TCC_EA_WRREQ_DRAM_CREDIT_STALL[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_EA_WRREQ_IO_CREDIT_STALL[7] TCC_EA_WRREQ_GMI_CREDIT_STALL[7] TCC_EA_WRREQ_DRAM_CREDIT_STALL[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_EA_WRREQ_IO_CREDIT_STALL[8] TCC_EA_WRREQ_GMI_CREDIT_STALL[8] TCC_EA_WRREQ_DRAM_CREDIT_STALL[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_EA_WRREQ_IO_CREDIT_STALL[9] TCC_EA_WRREQ_GMI_CREDIT_STALL[9] TCC_EA_WRREQ_DRAM_CREDIT_STALL[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_EA_WRREQ_IO_CREDIT_STALL[10] TCC_EA_WRREQ_GMI_CREDIT_STALL[10] TCC_EA_WRREQ_DRAM_CREDIT_STALL[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_EA_WRREQ_IO_CREDIT_STALL[11] TCC_EA_WRREQ_GMI_CREDIT_STALL[11] TCC_EA_WRREQ_DRAM_CREDIT_STALL[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_EA_WRREQ_IO_CREDIT_STALL[12] TCC_EA_WRREQ_GMI_CREDIT_STALL[12] TCC_EA_WRREQ_DRAM_CREDIT_STALL[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_EA_WRREQ_IO_CREDIT_STALL[13] TCC_EA_WRREQ_GMI_CREDIT_STALL[13] TCC_EA_WRREQ_DRAM_CREDIT_STALL[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_EA_WRREQ_IO_CREDIT_STALL[14] TCC_EA_WRREQ_GMI_CREDIT_STALL[14] TCC_EA_WRREQ_DRAM_CREDIT_STALL[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_EA_WRREQ_IO_CREDIT_STALL[15] TCC_EA_WRREQ_GMI_CREDIT_STALL[15] TCC_EA_WRREQ_DRAM_CREDIT_STALL[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_EA_WRREQ_IO_CREDIT_STALL[16] TCC_EA_WRREQ_GMI_CREDIT_STALL[16] TCC_EA_WRREQ_DRAM_CREDIT_STALL[16] TCC_TOO_MANY_EA_WRREQS_STALL[16] TCC_EA_WRREQ_IO_CREDIT_STALL[17] TCC_EA_WRREQ_GMI_CREDIT_STALL[17] TCC_EA_WRREQ_DRAM_CREDIT_STALL[17] TCC_TOO_MANY_EA_WRREQS_STALL[17] TCC_EA_WRREQ_IO_CREDIT_STALL[18] TCC_EA_WRREQ_GMI_CREDIT_STALL[18] TCC_EA_WRREQ_DRAM_CREDIT_STALL[18] TCC_TOO_MANY_EA_WRREQS_STALL[18] TCC_EA_WRREQ_IO_CREDIT_STALL[19] TCC_EA_WRREQ_GMI_CREDIT_STALL[19] TCC_EA_WRREQ_DRAM_CREDIT_STALL[19] TCC_TOO_MANY_EA_WRREQS_STALL[19] TCC_EA_WRREQ_IO_CREDIT_STALL[20] TCC_EA_WRREQ_GMI_CREDIT_STALL[20] TCC_EA_WRREQ_DRAM_CREDIT_STALL[20] TCC_TOO_MANY_EA_WRREQS_STALL[20] TCC_EA_WRREQ_IO_CREDIT_STALL[21] TCC_EA_WRREQ_GMI_CREDIT_STALL[21] TCC_EA_WRREQ_DRAM_CREDIT_STALL[21] TCC_TOO_MANY_EA_WRREQS_STALL[21] TCC_EA_WRREQ_IO_CREDIT_STALL[22] TCC_EA_WRREQ_GMI_CREDIT_STALL[22] TCC_EA_WRREQ_DRAM_CREDIT_STALL[22] TCC_TOO_MANY_EA_WRREQS_STALL[22] TCC_EA_WRREQ_IO_CREDIT_STALL[23] TCC_EA_WRREQ_GMI_CREDIT_STALL[23] TCC_EA_WRREQ_DRAM_CREDIT_STALL[23] TCC_TOO_MANY_EA_WRREQS_STALL[23] TCC_EA_WRREQ_IO_CREDIT_STALL[24] TCC_EA_WRREQ_GMI_CREDIT_STALL[24] TCC_EA_WRREQ_DRAM_CREDIT_STALL[24] TCC_TOO_MANY_EA_WRREQS_STALL[24] TCC_EA_WRREQ_IO_CREDIT_STALL[25] TCC_EA_WRREQ_GMI_CREDIT_STALL[25] TCC_EA_WRREQ_DRAM_CREDIT_STALL[25] TCC_TOO_MANY_EA_WRREQS_STALL[25] TCC_EA_WRREQ_IO_CREDIT_STALL[26] TCC_EA_WRREQ_GMI_CREDIT_STALL[26] TCC_EA_WRREQ_DRAM_CREDIT_STALL[26] TCC_TOO_MANY_EA_WRREQS_STALL[26] TCC_EA_WRREQ_IO_CREDIT_STALL[27] TCC_EA_WRREQ_GMI_CREDIT_STALL[27] TCC_EA_WRREQ_DRAM_CREDIT_STALL[27] TCC_TOO_MANY_EA_WRREQS_STALL[27] TCC_EA_WRREQ_IO_CREDIT_STALL[28] TCC_EA_WRREQ_GMI_CREDIT_STALL[28] TCC_EA_WRREQ_DRAM_CREDIT_STALL[28] TCC_TOO_MANY_EA_WRREQS_STALL[28] TCC_EA_WRREQ_IO_CREDIT_STALL[29] TCC_EA_WRREQ_GMI_CREDIT_STALL[29] TCC_EA_WRREQ_DRAM_CREDIT_STALL[29] TCC_TOO_MANY_EA_WRREQS_STALL[29] TCC_EA_WRREQ_IO_CREDIT_STALL[30] TCC_EA_WRREQ_GMI_CREDIT_STALL[30] TCC_EA_WRREQ_DRAM_CREDIT_STALL[30] TCC_TOO_MANY_EA_WRREQS_STALL[30] TCC_EA_WRREQ_IO_CREDIT_STALL[31] TCC_EA_WRREQ_GMI_CREDIT_STALL[31] TCC_EA_WRREQ_DRAM_CREDIT_STALL[31] TCC_TOO_MANY_EA_WRREQS_STALL[31]
|
||||
|
||||
gpu:
|
||||
kernel:
|
||||
range:
|
||||
@@ -1,17 +0,0 @@
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES
|
||||
|
||||
pmc: TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum
|
||||
pmc: TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum
|
||||
pmc: TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum
|
||||
pmc: TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum
|
||||
pmc: TCC_EA_WRREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WR_UNCACHED_32B_sum TCC_EA_WRREQ_DRAM_sum
|
||||
pmc: TCC_EA_WRREQ_STALL_sum
|
||||
pmc: TCC_EA_RDREQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RD_UNCACHED_32B_sum TCC_EA_RDREQ_DRAM_sum
|
||||
pmc: TCC_TAG_STALL_sum TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum TCC_NORMAL_EVICT_sum
|
||||
pmc: TCC_ALL_TC_OP_INV_EVICT_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA_ATOMIC_sum
|
||||
pmc: TCC_EA_RDREQ_LEVEL_sum TCC_EA_WRREQ_LEVEL_sum TCC_EA_ATOMIC_LEVEL_sum
|
||||
|
||||
gpu:
|
||||
kernel:
|
||||
|
||||
range:
|
||||
@@ -1,18 +0,0 @@
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_WAVES SQ_WAVE_CYCLES
|
||||
|
||||
pmc: TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum
|
||||
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
|
||||
pmc: TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum
|
||||
pmc: TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum
|
||||
pmc: TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum
|
||||
pmc: TCP_TCP_LATENCY_sum TCP_TCC_READ_REQ_LATENCY_sum TCP_TCC_WRITE_REQ_LATENCY_sum TCP_TCC_READ_REQ_sum
|
||||
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
|
||||
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
|
||||
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
|
||||
pmc: TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum TCP_PENDING_STALL_CYCLES_sum
|
||||
|
||||
#pmc: TCA_CYCLE_sum TCA_BUSY_sum
|
||||
|
||||
gpu:
|
||||
kernel:
|
||||
range:
|
||||
@@ -1,12 +0,0 @@
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_WAVES SQ_WAVE_CYCLES
|
||||
|
||||
pmc: TD_TD_BUSY_sum TD_TC_STALL_sum
|
||||
pmc: TD_SPI_STALL_sum TD_LOAD_WAVEFRONT_sum
|
||||
pmc: TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum
|
||||
pmc: TD_COALESCABLE_WAVEFRONT_sum
|
||||
|
||||
|
||||
|
||||
gpu:
|
||||
range:
|
||||
kernel:
|
||||
@@ -1,13 +0,0 @@
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES
|
||||
|
||||
pmc: CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE
|
||||
pmc: CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE
|
||||
pmc: CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION
|
||||
pmc: CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE
|
||||
pmc: CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE
|
||||
pmc: CPC_ME1_DC0_SPI_BUSY
|
||||
|
||||
range:
|
||||
gpu:
|
||||
|
||||
kernel:
|
||||
@@ -1,11 +0,0 @@
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES
|
||||
|
||||
pmc: CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL
|
||||
pmc: CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL
|
||||
pmc: CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE
|
||||
pmc: CPF_CMP_UTCL1_STALL_ON_TRANSLATION
|
||||
|
||||
range:
|
||||
gpu:
|
||||
|
||||
kernel:
|
||||
@@ -1,10 +0,0 @@
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES GRBM_SPI_BUSY
|
||||
|
||||
pmc: SPI_CSN_WINDOW_VALID SPI_CSN_BUSY SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN
|
||||
pmc: SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN
|
||||
pmc: SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN
|
||||
|
||||
range:
|
||||
gpu:
|
||||
|
||||
kernel:
|
||||
@@ -1,33 +0,0 @@
|
||||
#SQ
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_INSTS_VALU_CVT SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU SQ_INSTS_VSKIPPED
|
||||
pmc: 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 SQ_INSTS_VALU_MUL_F32
|
||||
pmc: 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 SQ_INSTS_VALU_INT64
|
||||
pmc: SQ_INSTS_SMEM SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG
|
||||
pmc: SQ_WAVE_CYCLES SQ_WAIT_ANY SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES
|
||||
pmc: SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS 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
|
||||
pmc: SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU SQ_THREAD_CYCLES_VALU SQ_IFETCH SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL
|
||||
pmc: SQ_WAVES SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 SQ_WAVES_LT_32 SQ_WAVES_LT_16 SQ_ITEMS SQ_INSTS_VSKIPPED
|
||||
pmc: SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED SQ_INSTS_SMEM_NORM
|
||||
|
||||
|
||||
#SQ:MI200
|
||||
pmc: 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
|
||||
pmc: 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
|
||||
|
||||
#SQ:MI300
|
||||
pmc: SQ_INSTS_VALU_MFMA_F8
|
||||
pmc: SQ_INSTS_VALU_MFMA_MOPS_F8
|
||||
|
||||
#SQC
|
||||
pmc: 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 SQC_DCACHE_REQ_READ_16
|
||||
pmc: 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
|
||||
pmc: 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
|
||||
|
||||
|
||||
|
||||
########################################
|
||||
# Filtering
|
||||
########################################
|
||||
range:
|
||||
gpu:
|
||||
kernel:
|
||||
@@ -1,10 +0,0 @@
|
||||
#################################################
|
||||
# VMEM latency
|
||||
#################################################
|
||||
pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES
|
||||
|
||||
|
||||
range:
|
||||
gpu:
|
||||
|
||||
kernel:
|
||||
@@ -1,11 +0,0 @@
|
||||
#################################################
|
||||
# SMEM latency
|
||||
#################################################
|
||||
pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES
|
||||
|
||||
|
||||
range:
|
||||
gpu:
|
||||
|
||||
|
||||
kernel:
|
||||
@@ -1,8 +0,0 @@
|
||||
#################################################
|
||||
# ifetch latency
|
||||
#################################################
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES
|
||||
|
||||
range:
|
||||
gpu:
|
||||
kernel:
|
||||
@@ -1,9 +0,0 @@
|
||||
#################################################
|
||||
# LDS latency
|
||||
#################################################
|
||||
pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES
|
||||
|
||||
range:
|
||||
gpu:
|
||||
|
||||
kernel:
|
||||
@@ -1,6 +0,0 @@
|
||||
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:
|
||||
@@ -1,11 +0,0 @@
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_WAVES SQ_WAVE_CYCLES
|
||||
|
||||
|
||||
pmc: 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 SQC_DCACHE_REQ_READ_16
|
||||
pmc: 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
|
||||
pmc: 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
|
||||
|
||||
range:
|
||||
gpu:
|
||||
|
||||
kernel:
|
||||
@@ -1,25 +0,0 @@
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_WAVES SQ_WAVE_CYCLES
|
||||
|
||||
pmc: TA_TA_BUSY_sum
|
||||
|
||||
# buffer access
|
||||
pmc: TA_BUFFER_WAVEFRONTS_sum TA_BUFFER_READ_WAVEFRONTS_sum
|
||||
pmc: TA_BUFFER_WRITE_WAVEFRONTS_sum TA_BUFFER_ATOMIC_WAVEFRONTS_sum
|
||||
pmc: TA_BUFFER_TOTAL_CYCLES_sum
|
||||
pmc: TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum
|
||||
|
||||
|
||||
# stalls
|
||||
pmc: TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum
|
||||
pmc: TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum
|
||||
|
||||
# flat accesses
|
||||
pmc: TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum
|
||||
pmc: TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum
|
||||
|
||||
|
||||
range:
|
||||
|
||||
gpu:
|
||||
|
||||
kernel:
|
||||
@@ -1,22 +0,0 @@
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES
|
||||
|
||||
pmc: TCC_CYCLE[0] TCC_RW_REQ[0] TCC_HIT[0] TCC_MISS[0] TCC_CYCLE[1] TCC_RW_REQ[1] TCC_HIT[1] TCC_MISS[1] TCC_CYCLE[2] TCC_RW_REQ[2] TCC_HIT[2] TCC_MISS[2] TCC_CYCLE[3] TCC_RW_REQ[3] TCC_HIT[3] TCC_MISS[3] TCC_CYCLE[4] TCC_RW_REQ[4] TCC_HIT[4] TCC_MISS[4] TCC_CYCLE[5] TCC_RW_REQ[5] TCC_HIT[5] TCC_MISS[5] TCC_CYCLE[6] TCC_RW_REQ[6] TCC_HIT[6] TCC_MISS[6] TCC_CYCLE[7] TCC_RW_REQ[7] TCC_HIT[7] TCC_MISS[7] TCC_CYCLE[8] TCC_RW_REQ[8] TCC_HIT[8] TCC_MISS[8] TCC_CYCLE[9] TCC_RW_REQ[9] TCC_HIT[9] TCC_MISS[9] TCC_CYCLE[10] TCC_RW_REQ[10] TCC_HIT[10] TCC_MISS[10] TCC_CYCLE[11] TCC_RW_REQ[11] TCC_HIT[11] TCC_MISS[11] TCC_CYCLE[12] TCC_RW_REQ[12] TCC_HIT[12] TCC_MISS[12] TCC_CYCLE[13] TCC_RW_REQ[13] TCC_HIT[13] TCC_MISS[13] TCC_CYCLE[14] TCC_RW_REQ[14] TCC_HIT[14] TCC_MISS[14] TCC_CYCLE[15] TCC_RW_REQ[15] TCC_HIT[15] TCC_MISS[15]
|
||||
|
||||
|
||||
|
||||
pmc: TCC_REQ[0] TCC_READ[0] TCC_WRITE[0] TCC_ATOMIC[0] TCC_REQ[1] TCC_READ[1] TCC_WRITE[1] TCC_ATOMIC[1] TCC_REQ[2] TCC_READ[2] TCC_WRITE[2] TCC_ATOMIC[2] TCC_REQ[3] TCC_READ[3] TCC_WRITE[3] TCC_ATOMIC[3] TCC_REQ[4] TCC_READ[4] TCC_WRITE[4] TCC_ATOMIC[4] TCC_REQ[5] TCC_READ[5] TCC_WRITE[5] TCC_ATOMIC[5] TCC_REQ[6] TCC_READ[6] TCC_WRITE[6] TCC_ATOMIC[6] TCC_REQ[7] TCC_READ[7] TCC_WRITE[7] TCC_ATOMIC[7] TCC_REQ[8] TCC_READ[8] TCC_WRITE[8] TCC_ATOMIC[8] TCC_REQ[9] TCC_READ[9] TCC_WRITE[9] TCC_ATOMIC[9] TCC_REQ[10] TCC_READ[10] TCC_WRITE[10] TCC_ATOMIC[10] TCC_REQ[11] TCC_READ[11] TCC_WRITE[11] TCC_ATOMIC[11] TCC_REQ[12] TCC_READ[12] TCC_WRITE[12] TCC_ATOMIC[12] TCC_REQ[13] TCC_READ[13] TCC_WRITE[13] TCC_ATOMIC[13] TCC_REQ[14] TCC_READ[14] TCC_WRITE[14] TCC_ATOMIC[14] TCC_REQ[15] TCC_READ[15] TCC_WRITE[15] TCC_ATOMIC[15]
|
||||
|
||||
|
||||
|
||||
pmc: TCC_EA0_RDREQ[0] TCC_EA0_RDREQ_32B[0] TCC_EA0_WRREQ[0] TCC_EA0_WRREQ_64B[0] TCC_EA0_RDREQ[1] TCC_EA0_RDREQ_32B[1] TCC_EA0_WRREQ[1] TCC_EA0_WRREQ_64B[1] TCC_EA0_RDREQ[2] TCC_EA0_RDREQ_32B[2] TCC_EA0_WRREQ[2] TCC_EA0_WRREQ_64B[2] TCC_EA0_RDREQ[3] TCC_EA0_RDREQ_32B[3] TCC_EA0_WRREQ[3] TCC_EA0_WRREQ_64B[3] TCC_EA0_RDREQ[4] TCC_EA0_RDREQ_32B[4] TCC_EA0_WRREQ[4] TCC_EA0_WRREQ_64B[4] TCC_EA0_RDREQ[5] TCC_EA0_RDREQ_32B[5] TCC_EA0_WRREQ[5] TCC_EA0_WRREQ_64B[5] TCC_EA0_RDREQ[6] TCC_EA0_RDREQ_32B[6] TCC_EA0_WRREQ[6] TCC_EA0_WRREQ_64B[6] TCC_EA0_RDREQ[7] TCC_EA0_RDREQ_32B[7] TCC_EA0_WRREQ[7] TCC_EA0_WRREQ_64B[7] TCC_EA0_RDREQ[8] TCC_EA0_RDREQ_32B[8] TCC_EA0_WRREQ[8] TCC_EA0_WRREQ_64B[8] TCC_EA0_RDREQ[9] TCC_EA0_RDREQ_32B[9] TCC_EA0_WRREQ[9] TCC_EA0_WRREQ_64B[9] TCC_EA0_RDREQ[10] TCC_EA0_RDREQ_32B[10] TCC_EA0_WRREQ[10] TCC_EA0_WRREQ_64B[10] TCC_EA0_RDREQ[11] TCC_EA0_RDREQ_32B[11] TCC_EA0_WRREQ[11] TCC_EA0_WRREQ_64B[11] TCC_EA0_RDREQ[12] TCC_EA0_RDREQ_32B[12] TCC_EA0_WRREQ[12] TCC_EA0_WRREQ_64B[12] TCC_EA0_RDREQ[13] TCC_EA0_RDREQ_32B[13] TCC_EA0_WRREQ[13] TCC_EA0_WRREQ_64B[13] TCC_EA0_RDREQ[14] TCC_EA0_RDREQ_32B[14] TCC_EA0_WRREQ[14] TCC_EA0_WRREQ_64B[14] TCC_EA0_RDREQ[15] TCC_EA0_RDREQ_32B[15] TCC_EA0_WRREQ[15] TCC_EA0_WRREQ_64B[15]
|
||||
|
||||
|
||||
pmc: TCC_EA0_ATOMIC[0] TCC_EA0_RDREQ_LEVEL[0] TCC_EA0_WRREQ_LEVEL[0] TCC_EA0_ATOMIC_LEVEL[0] TCC_EA0_ATOMIC[1] TCC_EA0_RDREQ_LEVEL[1] TCC_EA0_WRREQ_LEVEL[1] TCC_EA0_ATOMIC_LEVEL[1] TCC_EA0_ATOMIC[2] TCC_EA0_RDREQ_LEVEL[2] TCC_EA0_WRREQ_LEVEL[2] TCC_EA0_ATOMIC_LEVEL[2] TCC_EA0_ATOMIC[3] TCC_EA0_RDREQ_LEVEL[3] TCC_EA0_WRREQ_LEVEL[3] TCC_EA0_ATOMIC_LEVEL[3] TCC_EA0_ATOMIC[4] TCC_EA0_RDREQ_LEVEL[4] TCC_EA0_WRREQ_LEVEL[4] TCC_EA0_ATOMIC_LEVEL[4] TCC_EA0_ATOMIC[5] TCC_EA0_RDREQ_LEVEL[5] TCC_EA0_WRREQ_LEVEL[5] TCC_EA0_ATOMIC_LEVEL[5] TCC_EA0_ATOMIC[6] TCC_EA0_RDREQ_LEVEL[6] TCC_EA0_WRREQ_LEVEL[6] TCC_EA0_ATOMIC_LEVEL[6] TCC_EA0_ATOMIC[7] TCC_EA0_RDREQ_LEVEL[7] TCC_EA0_WRREQ_LEVEL[7] TCC_EA0_ATOMIC_LEVEL[7] TCC_EA0_ATOMIC[8] TCC_EA0_RDREQ_LEVEL[8] TCC_EA0_WRREQ_LEVEL[8] TCC_EA0_ATOMIC_LEVEL[8] TCC_EA0_ATOMIC[9] TCC_EA0_RDREQ_LEVEL[9] TCC_EA0_WRREQ_LEVEL[9] TCC_EA0_ATOMIC_LEVEL[9] TCC_EA0_ATOMIC[10] TCC_EA0_RDREQ_LEVEL[10] TCC_EA0_WRREQ_LEVEL[10] TCC_EA0_ATOMIC_LEVEL[10] TCC_EA0_ATOMIC[11] TCC_EA0_RDREQ_LEVEL[11] TCC_EA0_WRREQ_LEVEL[11] TCC_EA0_ATOMIC_LEVEL[11] TCC_EA0_ATOMIC[12] TCC_EA0_RDREQ_LEVEL[12] TCC_EA0_WRREQ_LEVEL[12] TCC_EA0_ATOMIC_LEVEL[12] TCC_EA0_ATOMIC[13] TCC_EA0_RDREQ_LEVEL[13] TCC_EA0_WRREQ_LEVEL[13] TCC_EA0_ATOMIC_LEVEL[13] TCC_EA0_ATOMIC[14] TCC_EA0_RDREQ_LEVEL[14] TCC_EA0_WRREQ_LEVEL[14] TCC_EA0_ATOMIC_LEVEL[14] TCC_EA0_ATOMIC[15] TCC_EA0_RDREQ_LEVEL[15] TCC_EA0_WRREQ_LEVEL[15] TCC_EA0_ATOMIC_LEVEL[15]
|
||||
|
||||
pmc: TCC_TAG_STALL[0] TCC_BUBBLE[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_TAG_STALL[1] TCC_BUBBLE[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_TAG_STALL[2] TCC_BUBBLE[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_TAG_STALL[3] TCC_BUBBLE[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_TAG_STALL[4] TCC_BUBBLE[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_TAG_STALL[5] TCC_BUBBLE[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_TAG_STALL[6] TCC_BUBBLE[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_TAG_STALL[7] TCC_BUBBLE[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_TAG_STALL[8] TCC_BUBBLE[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_TAG_STALL[9] TCC_BUBBLE[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_TAG_STALL[10] TCC_BUBBLE[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_TAG_STALL[11] TCC_BUBBLE[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_TAG_STALL[12] TCC_BUBBLE[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_TAG_STALL[13] TCC_BUBBLE[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_TAG_STALL[14] TCC_BUBBLE[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_TAG_STALL[15] TCC_BUBBLE[15] TCC_TOO_MANY_EA_WRREQS_STALL[15]
|
||||
|
||||
|
||||
|
||||
gpu:
|
||||
kernel:
|
||||
range:
|
||||
@@ -1,17 +0,0 @@
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES
|
||||
|
||||
pmc: TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum
|
||||
pmc: TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum
|
||||
pmc: TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum
|
||||
pmc: TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum
|
||||
pmc: TCC_EA0_WRREQ_sum TCC_EA0_WRREQ_64B_sum TCC_EA0_WR_UNCACHED_32B_sum TCC_EA0_WRREQ_DRAM_sum
|
||||
pmc: TCC_EA0_RDREQ_sum TCC_EA0_RDREQ_32B_sum TCC_BUBBLE_sum
|
||||
pmc: TCC_EA0_RD_UNCACHED_32B_sum TCC_EA0_RDREQ_DRAM_sum
|
||||
pmc: TCC_TAG_STALL_sum TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum TCC_NORMAL_EVICT_sum
|
||||
pmc: TCC_ALL_TC_OP_INV_EVICT_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA0_ATOMIC_sum
|
||||
pmc: TCC_EA0_RDREQ_LEVEL_sum TCC_EA0_WRREQ_LEVEL_sum TCC_EA0_ATOMIC_LEVEL_sum TCC_EA0_WRREQ_STALL_sum
|
||||
|
||||
gpu:
|
||||
kernel:
|
||||
|
||||
range:
|
||||
@@ -1,18 +0,0 @@
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_WAVES SQ_WAVE_CYCLES
|
||||
|
||||
pmc: TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum
|
||||
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
|
||||
pmc: TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum
|
||||
pmc: TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum
|
||||
pmc: TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum
|
||||
pmc: TCP_TCC_READ_REQ_sum
|
||||
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
|
||||
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
|
||||
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
|
||||
pmc: TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum TCP_PENDING_STALL_CYCLES_sum
|
||||
|
||||
#pmc: TCA_CYCLE_sum TCA_BUSY_sum
|
||||
|
||||
gpu:
|
||||
kernel:
|
||||
range:
|
||||
@@ -1,12 +0,0 @@
|
||||
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_WAVES SQ_WAVE_CYCLES
|
||||
|
||||
pmc: TD_TD_BUSY_sum TD_TC_STALL_sum
|
||||
pmc: TD_SPI_STALL_sum TD_LOAD_WAVEFRONT_sum
|
||||
pmc: TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum
|
||||
pmc: TD_COALESCABLE_WAVEFRONT_sum
|
||||
|
||||
|
||||
|
||||
gpu:
|
||||
range:
|
||||
kernel:
|
||||
Diff onderdrukt omdat het te groot bestand
Laad Diff
@@ -33,15 +33,6 @@ class gfx906_soc(OmniSoC_Base):
|
||||
def __init__(self, args, mspec):
|
||||
super().__init__(args, mspec)
|
||||
self.set_arch("gfx906")
|
||||
self.set_perfmon_dir(
|
||||
str(
|
||||
Path(str(config.rocprof_compute_home)).joinpath(
|
||||
"rocprof_compute_soc",
|
||||
"profile_configs",
|
||||
self.get_arch(),
|
||||
)
|
||||
)
|
||||
)
|
||||
self.set_compatible_profilers(["rocprofv1", "rocscope"])
|
||||
# Per IP block max number of simultaneous counters. GFX IP Blocks
|
||||
self.set_perfmon_config(
|
||||
@@ -56,7 +47,6 @@ class gfx906_soc(OmniSoC_Base):
|
||||
"SPI": 2,
|
||||
"GRBM": 2,
|
||||
"GDS": 4,
|
||||
"TCC_channels": 16,
|
||||
}
|
||||
)
|
||||
|
||||
|
||||
@@ -33,15 +33,6 @@ class gfx908_soc(OmniSoC_Base):
|
||||
def __init__(self, args, mspec):
|
||||
super().__init__(args, mspec)
|
||||
self.set_arch("gfx908")
|
||||
self.set_perfmon_dir(
|
||||
str(
|
||||
Path(str(config.rocprof_compute_home)).joinpath(
|
||||
"rocprof_compute_soc",
|
||||
"profile_configs",
|
||||
self.get_arch(),
|
||||
)
|
||||
)
|
||||
)
|
||||
self.set_compatible_profilers(["rocprofv1", "rocscope", "rocprofv3"])
|
||||
# Per IP block max number of simultaneous counters. GFX IP Blocks
|
||||
self.set_perfmon_config(
|
||||
@@ -56,7 +47,6 @@ class gfx908_soc(OmniSoC_Base):
|
||||
"SPI": 2,
|
||||
"GRBM": 2,
|
||||
"GDS": 4,
|
||||
"TCC_channels": 32,
|
||||
}
|
||||
)
|
||||
|
||||
|
||||
@@ -45,16 +45,6 @@ class gfx90a_soc(OmniSoC_Base):
|
||||
)
|
||||
)
|
||||
)
|
||||
else:
|
||||
self.set_perfmon_dir(
|
||||
str(
|
||||
Path(str(config.rocprof_compute_home)).joinpath(
|
||||
"rocprof_compute_soc",
|
||||
"profile_configs",
|
||||
self.get_arch(),
|
||||
)
|
||||
)
|
||||
)
|
||||
self.set_compatible_profilers(["rocprofv1", "rocscope", "rocprofv2", "rocprofv3"])
|
||||
# Per IP block max number of simultaneous counters. GFX IP Blocks
|
||||
self.set_perfmon_config(
|
||||
@@ -69,7 +59,6 @@ class gfx90a_soc(OmniSoC_Base):
|
||||
"SPI": 2,
|
||||
"GRBM": 2,
|
||||
"GDS": 4,
|
||||
"TCC_channels": 32,
|
||||
}
|
||||
)
|
||||
self.roofline_obj = Roofline(args, self._mspec)
|
||||
|
||||
@@ -45,17 +45,6 @@ class gfx940_soc(OmniSoC_Base):
|
||||
)
|
||||
)
|
||||
)
|
||||
else:
|
||||
# NB: We're using generalized Mi300 perfmon configs
|
||||
self.set_perfmon_dir(
|
||||
set(
|
||||
Path(str(config.rocprof_compute_home)).joinpath(
|
||||
"rocprof_compute_soc",
|
||||
"profile_configs",
|
||||
"gfx940",
|
||||
)
|
||||
)
|
||||
)
|
||||
self.set_compatible_profilers(["rocprofv1", "rocprofv2", "rocprofv3"])
|
||||
# Per IP block max number of simultaneous counters. GFX IP Blocks
|
||||
self.set_perfmon_config(
|
||||
@@ -70,7 +59,6 @@ class gfx940_soc(OmniSoC_Base):
|
||||
"SPI": 2,
|
||||
"GRBM": 2,
|
||||
"GDS": 4,
|
||||
"TCC_channels": 32,
|
||||
}
|
||||
)
|
||||
self.roofline_obj = Roofline(args, self._mspec)
|
||||
|
||||
@@ -45,17 +45,6 @@ class gfx941_soc(OmniSoC_Base):
|
||||
)
|
||||
)
|
||||
)
|
||||
else:
|
||||
# NB: We're using generalized Mi300 perfmon configs
|
||||
self.set_perfmon_dir(
|
||||
str(
|
||||
Path(str(config.rocprof_compute_home)).joinpath(
|
||||
"rocprof_compute_soc",
|
||||
"profile_configs",
|
||||
"gfx940",
|
||||
)
|
||||
)
|
||||
)
|
||||
self.set_compatible_profilers(["rocprofv1", "rocprofv2", "rocprofv3"])
|
||||
# Per IP block max number of simultaneous counters. GFX IP Blocks
|
||||
self.set_perfmon_config(
|
||||
@@ -70,7 +59,6 @@ class gfx941_soc(OmniSoC_Base):
|
||||
"SPI": 2,
|
||||
"GRBM": 2,
|
||||
"GDS": 4,
|
||||
"TCC_channels": 32,
|
||||
}
|
||||
)
|
||||
self.roofline_obj = Roofline(args, self._mspec)
|
||||
|
||||
@@ -45,17 +45,6 @@ class gfx942_soc(OmniSoC_Base):
|
||||
)
|
||||
)
|
||||
)
|
||||
else:
|
||||
# NB: We're using generalized Mi300 perfmon configs
|
||||
self.set_perfmon_dir(
|
||||
str(
|
||||
Path(str(config.rocprof_compute_home)).joinpath(
|
||||
"rocprof_compute_soc",
|
||||
"profile_configs",
|
||||
"gfx940",
|
||||
)
|
||||
)
|
||||
)
|
||||
self.set_compatible_profilers(["rocprofv1", "rocprofv2", "rocprofv3"])
|
||||
# Per IP block max number of simultaneous counters. GFX IP Blocks
|
||||
self.set_perfmon_config(
|
||||
@@ -70,7 +59,6 @@ class gfx942_soc(OmniSoC_Base):
|
||||
"SPI": 2,
|
||||
"GRBM": 2,
|
||||
"GDS": 4,
|
||||
"TCC_channels": 16,
|
||||
}
|
||||
)
|
||||
self.roofline_obj = Roofline(args, self._mspec)
|
||||
|
||||
Verwijs in nieuw issue
Block a user