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

3 línte
25 KiB
CSV
Amh Amharc Gnáth Stair

Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCC_EA_ATOMIC_LEVEL_sum,wave_size_1,obj_1,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_2,obj_2,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_3,obj_3,SQ_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_4,obj_4,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_5,obj_5,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_6,obj_6,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_7,obj_7,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC
1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f4267d48ec0,0.0,64,0x7f154235cec0,252974,360448,163840,0,0,180224,114688,0,72098156.0,205624058.0,79937933.0,131072.0,0.0,579965.0,0,0,23936,51961.0,0.0,0.0,51961.0,64,0x7fea9f808ec0,113611,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,12075,28459,7646,588,0,37215,262192.0,0.0,47.0,262145.0,64,0x7f57301b8ec0,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,67195.0,135446.0,64,0x7f562a114ec0,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86428.0,0.0,131110.0,0.0,64,0x7f6480768ec0,131072.0,131072.0,0.0,2639990.0,0.0,0.0,129626343.0,46793288.0,64,0x7f0d1d088ec0,32768,0,0,0,16384,16384,393216,21692773,0.0,524288.0,0.0,524288.0,745965.0,32768.0,0,0,0,11953,86327.0,86327.0,0.0,86327.0,64,0x7f709c740ec0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,64,0x7f3dad7bcec0,0,0,48,0,65536,65536,0,0,28737,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,435,38380,1668,0,48.0,0.0,0.0,262144.0,64,0x7f51327c8ec0,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,38252,0,131120.0,131072.0,0.0,86600.0,64,0x7f2dbf19cec0,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f32328d4ec0,1797,0,0,1419232,2725,0,0,1492039,3935,0,0,1698918,2133,0,0,1422824,2371,0,0,1516659,319,0,0,1269903,2901,0,0,1561232,613,0,0,1288778,3131,0,0,1613631,1082,0,0,1301401,1835,0,0,1454284,262,0,0,1150553,5583,0,0,1770491,3689,0,0,1619523,1559,0,0,1452131,1140,0,0,1298180,1803,0,0,1420660,1270,0,0,1380046,1325,0,0,1370964,3119,0,0,1588779,3256,0,0,1584324,1943,0,0,1458358,6823,0,0,1844206,3740,0,0,1643762,2742,0,0,1511587,638,0,0,1375747,5997,0,0,1767655,3482,0,0,1500656,6435,0,0,1824708,1905,0,0,1366283,3759,0,0,1678284,231,0,0,1086636,64,0x7f8e65960ec0,4096,0,1207,0,4096,0,346,0,4096,0,480,0,4096,0,993,0,4096,0,0,0,4096,0,2051,0,4096,0,0,0,4096,0,3524,0,4096,0,789,0,4096,0,2526,0,4096,0,4,0,4096,0,3453,0,4096,0,84,0,4096,0,2672,0,4096,0,1875,0,4096,0,39,0,4096,0,94,0,4096,0,8005,0,4096,0,582,0,4096,0,569,0,4096,0,313,0,4096,0,2218,0,4096,0,3213,0,4096,0,434,0,4096,0,3317,0,4096,0,5039,0,4096,0,3262,0,4097,0,673,0,4096,0,0,0,4096,0,1880,0,4096,0,0,0,4096,0,2494,0,64,0x7f72c1b44ec0,0,3201079,2700,2700,0,3371631,2678,2678,0,4928613,2684,2684,0,4270062,2702,2702,0,3939416,2684,2684,0,4497023,2704,2704,0,4015027,2730,2730,0,4928821,2696,2696,0,4131016,2692,2692,0,4591016,2678,2678,0,4711285,2722,2722,0,4914711,2738,2738,0,3425347,2692,2692,0,4898007,2668,2668,0,4910902,2696,2696,0,3536786,2704,2704,0,4246514,2692,2692,0,4570000,2680,2680,0,3563609,2716,2716,0,3558400,2708,2708,0,2726778,2699,2699,0,3473475,2740,2740,0,4627566,2690,2690,0,4380839,2680,2680,0,3783259,2666,2666,0,3729235,2694,2694,0,3732210,2748,2748,0,4496181,2706,2706,0,4362865,2707,2707,0,3315326,2676,2676,0,4634774,2726,2726,0,4549916,2700,2700,64,0x7f3f50d84ec0,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,409