Files
rocm-systems/tests/workloads/dispatch_2/MI100/pmc_perf.csv
T

3 lines
25 KiB
CSV
Raw Normal View History

2024-03-01 17:12:44 -06:00
Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_1,obj_1,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_2,obj_2,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_3,obj_3,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_4,obj_4,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_5,obj_5,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_T
1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f8236e3ce80,32768,0,0,0,16384,16384,393216,22241342,0.0,524288.0,0.0,524288.0,719375.0,32768.0,0,0,0,12013,86583.0,86583.0,0.0,86583.0,64,0x7fac5c1fce80,136682,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13329,29713,7604,1462,0,36927,262194.0,0.0,47.0,262147.0,64,0x7fc0c15ece80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,56341.0,126058.0,64,0x7ff9bc0e4e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,38044,0,131120.0,131072.0,0.0,86505.0,64,0x7f5afe336e80,0,0,48,0,65536,65536,0,0,28348,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,436,37902,1745,0,48.0,0.0,0.0,262144.0,64,0x7f0614fdce80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fde1eda0e80,131072.0,131072.0,0.0,2611243.0,0.0,0.0,127446147.0,47598095.0,64,0x7f0a74f6ee80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131073.0,0.0,0.0,131072.0,64,0x7f93da470e80,0,4733576,2698,2698,0,4950371,2718,2718,0,3343062,2660,2660,0,4991429,2702,2702,0,3814454,2673,2673,0,4827291,2716,2716,0,3802294,2710,2710,0,4550844,2712,2712,0,4653501,2690,2690,0,4533577,2692,2692,0,3784597,2692,2692,0,4495445,2730,2730,0,4357469,2693,2693,0,3624396,2680,2680,0,4607537,2694,2694,0,3314040,2680,2680,0,4364060,2666,2666,0,4878204,2726,2726,0,3991236,2666,2666,0,4773393,2712,2712,0,3896694,2704,2704,0,3887271,2741,2741,0,4288052,2676,2676,0,4492545,2690,2690,0,3336323,2690,2690,0,4847770,2682,2682,0,4614927,2722,2722,0,4009045,2708,2708,0,3916086,2706,2706,0,4042568,2693,2693,0,4519454,2698,2698,0,3888336,2682,2682,64,0x7fd8e037ce80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86550.0,0.0,131110.0,0.0,64,0x7f82c9fdce80,309840,214878,3145099,16384,22497534,0,48,0,38729,38729,3513076.0,2970065.0,5756.0,1077804.0,1946413.0,0.0,2960237.0,2648110.0,308319,222962,38729,0,38729,0,1239328.0,804950.0,0.0,0.0,64,0x7fab341e8e80,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,0,38751,0,0,64,0x7f29c3e04e80,4137,0,0,1636048,2067,0,0,1435641,1065,0,0,1297932,1785,0,0,1428162,1967,0,0,1530501,2415,0,0,1523447,808,0,0,1393467,796,0,0,1285312,1258,0,0,1320082,2453,0,0,1403696,1134,0,0,1375485,1140,0,0,1285513,3047,0,0,1572917,1062,0,0,1327053,1736,0,0,1478458,1681,0,0,1487434,2035,0,0,1460776,2120,0,0,1508369,2571,0,0,1511321,1734,0,0,1389877,420,0,0,1197709,901,0,0,1261289,3420,0,0,1673728,5642,0,0,1775752,3028,0,0,1583374,1358,0,0,1382535,3126,0,0,1626562,1167,0,0,1332831,1751,0,0,1448080,5578,0,0,1842878,1881,0,0,1446346,1003,0,0,1339746,64,0x7f7bf4c16e80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,64,0x7f3e474d6e80,224643,360448,163840,0,0,180224,114688,0,71268791.0,213987650.0,80373920.0,131072.0,0.0,577044.0,0,0,23408,78640.0,0.0,0.0,78640.0,64,0x7fcaf3f3ce80,4096,0,1506,0,4096,0,515,0,4096,0,4904,0,4096,0,3332,0,4096,0,2278,0,4096