111 KiB
111 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | SQ_INSTS_VALU_CVT | SQ_INSTS_VMEM_WR | SQ_INSTS_VMEM_RD | SQ_INSTS_VMEM | SQ_INSTS_SALU | SQ_INSTS_VSKIPPED | SQ_INSTS | SQ_INSTS_VALU | GRBM_COUNT | GRBM_GUI_ACTIVE | 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 | SQ_INSTS_VALU_FMA_F32 | SQ_INSTS_VALU_TRANS_F32 | SQC_TC_DATA_WRITE_REQ | 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 | 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 | SQC_DCACHE_REQ_READ_2 | SQC_DCACHE_REQ_READ_4 | 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 | SQ_INSTS_SMEM | SQ_INSTS_FLAT | SQ_INSTS_LDS | SQ_INSTS_GDS | SQ_INSTS_EXP_GDS | SQ_INSTS_BRANCH | SQ_INSTS_SENDMSG | SQ_WAVE_CYCLES | SQ_WAIT_ANY | SQ_WAIT_INST_ANY | SQ_ACTIVE_INST_ANY | SQ_CYCLES | SQ_BUSY_CYCLES | SQ_BUSY_CU_CYCLES | 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 | 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 | 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_LDS_MEM_VIOLATIONS | SQ_LDS_ATOMIC_RETURN | SQ_LDS_IDX_ACTIVE | SQ_WAVES_RESTORED | SQ_WAVES_SAVED | SQ_INSTS_SMEM_NORM | 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 | 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_TC_INST_REQ | SQC_TC_DATA_READ_REQ | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBufferAligned.kd | 0 | 0 | 0 | 140304 | 140304 | 33554432 | 256 | 0 | 0 | 4 | 32 | 4160 | 0x0 | 0x7fa31e804280 | 0 | 524288 | 0 | 524288 | 7340032 | 0 | 25690112 | 9437184 | 387297 | 387297 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 616 | 0 | 4718592 | 4714976 | 112 | 3702 | 1032987 | 0 | 524288 | 3670016 | 3663316 | 224 | 6476 | 1048576 | 1048576 | 1048576 | 0 | 0 | 0 | 0 | 5767168 | 1048576 | 3670016 | 524288 | 0 | 0 | 0 | 2621440 | 524288 | 237604043 | 173545637 | 39941158 | 24117248 | 3074528 | 2986378 | 38767640 | 0 | 0 | 9437184 | 11010048 | 0 | 3145728 | 524288 | 524288 | 0 | 3670016 | 7340032 | 603979776 | 4718592 | 0 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 0 | 33554432 | 0 | 0 | 0 | 0 | 0 | 7340032 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 392 | 224 | 15937487434886 | 15948461788706 | 15948462027747 | 15937635676675 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 140304 | 140304 | 32768 | 256 | 0 | 0 | 12 | 24 | 13888 | 0x0 | 0x7fa31e823f80 | 0 | 0 | 4096 | 4096 | 512 | 0 | 35328 | 26112 | 33604 | 33604 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 560 | 0 | 8192 | 6117 | 56 | 1945 | 654 | 0 | 0 | 512 | 0 | 56 | 456 | 0 | 512 | 0 | 0 | 0 | 0 | 0 | 10752 | 3584 | 512 | 4096 | 0 | 0 | 0 | 512 | 512 | 1711759 | 1665120 | 14383 | 32256 | 267784 | 158428 | 1382345 | 0 | 0 | 26112 | 1024 | 0 | 1024 | 4096 | 0 | 4096 | 512 | 512 | 1671168 | 8192 | 0 | 0 | 0 | 512 | 512 | 0 | 0 | 0 | 0 | 32768 | 0 | 0 | 0 | 0 | 0 | 1024 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 504 | 56 | 15937640838860 | 15948466868890 | 15948466882330 | 15937640983137 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 5 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 14336 | 0x7fa32177c380 | 0x7fa31e823fc0 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 4063232 | 2883584 | 164986 | 164986 | 0 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 448 | 0 | 917504 | 913647 | 0 | 3595 | 921140 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 84801032 | 48438574 | 32626906 | 3735552 | 1321240 | 1206472 | 15607412 | 0 | 0 | 2883584 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 184549376 | 917504 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 392 | 56 | 15937641031606 | 15948466952090 | 15948467044891 | 15937641379878 |
| 5 | 3 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 8 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15040 | 0x7fa32177c200 | 0x7fa31e824000 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 5308416 | 3014656 | 310666 | 310666 | 0 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 616 | 0 | 1114112 | 1110762 | 56 | 3447 | 461752 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 221193514 | 50245720 | 165967058 | 4980736 | 2459688 | 2346089 | 30393962 | 0 | 0 | 3014656 | 1245184 | 0 | 196608 | 524288 | 0 | 524288 | 65536 | 1179648 | 192937984 | 1114112 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 560 | 56 | 15937641430017 | 15948467078491 | 15948467257212 | 15937641829488 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 11 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15488 | 0x7fa32177c080 | 0x7fa31e824040 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 4063232 | 2883584 | 309961 | 309961 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 504 | 0 | 917504 | 914358 | 56 | 3038 | 675106 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 65536 | 0 | 0 | 0 | 262144 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 223483296 | 50139373 | 169608371 | 3735552 | 2471616 | 2364992 | 30630345 | 0 | 0 | 2883584 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 184549376 | 917504 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 448 | 56 | 15937641876177 | 15948467282332 | 15948467461533 | 15937642259869 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 14 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 15936 | 0x7fa31f11ff00 | 0x7fa31e824080 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 4587520 | 3342336 | 164878 | 164878 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 560 | 0 | 1048576 | 1044696 | 56 | 3803 | 458303 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 76330278 | 48340669 | 23729769 | 4259840 | 1324000 | 1213136 | 15705560 | 0 | 0 | 3342336 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 196608 | 213909504 | 1048576 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 504 | 56 | 15937642306728 | 15948467485693 | 15948467579773 | 15937642605731 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 17 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 16384 | 0x7fa31f11fd80 | 0x7fa31e8240c0 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 4194304 | 3014656 | 165698 | 165698 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 504 | 0 | 983040 | 979228 | 56 | 3383 | 915369 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 65536 | 0 | 0 | 0 | 0 | 0 | 1966080 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 84901067 | 48545294 | 32489149 | 3866624 | 1324584 | 1207551 | 15620679 | 0 | 0 | 3014656 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 192937984 | 983040 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 448 | 56 | 15937642651530 | 15948467605534 | 15948467697534 | 15937642943884 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 20 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 17088 | 0x7fa31f11fc00 | 0x7fa31e824100 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 5111808 | 3538944 | 163816 | 163816 | 0 | 0 | 0 | 0 | 0 | 0 | 655360 | 0 | 0 | 0 | 0 | 560 | 0 | 1114112 | 1111614 | 0 | 2630 | 905305 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 105705325 | 48434683 | 52748658 | 4521984 | 1305032 | 1201185 | 15544113 | 0 | 0 | 3538944 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 226492416 | 1114112 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 504 | 56 | 15937643002112 | 15948467737214 | 15948467829695 | 15937643282406 |
| 10 | 8 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 23 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 16 | 24 | 17792 | 0x7fa31f11fa80 | 0x7fa31e824140 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 6094848 | 3538944 | 308228 | 308228 | 0 | 0 | 0 | 0 | 0 | 0 | 786432 | 0 | 0 | 0 | 0 | 672 | 0 | 1310720 | 1307417 | 56 | 4397 | 457845 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 229221395 | 50738198 | 172912637 | 5570560 | 2468888 | 2359542 | 30588863 | 0 | 0 | 3538944 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 226492416 | 1310720 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 616 | 56 | 15937643327615 | 15948467861535 | 15948468041216 | 15937643723006 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 26 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 16 | 24 | 18496 | 0x7fa31f11f900 | 0x7fa31e824180 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 5242880 | 3801088 | 307534 | 307534 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 616 | 0 | 1179648 | 1175606 | 56 | 4036 | 578694 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 786432 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 212619248 | 72965197 | 135000995 | 4653056 | 2459000 | 2350476 | 30446711 | 0 | 0 | 3801088 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 243269632 | 1179648 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 560 | 56 | 15937643768465 | 15948468082016 | 15948468261537 | 15937644152457 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 29 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19200 | 0x7fa31f11f780 | 0x7fa31e8241c0 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 5439488 | 3866624 | 163966 | 163966 | 0 | 0 | 786432 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 616 | 0 | 1245184 | 1240954 | 56 | 4046 | 460097 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 94039495 | 49435766 | 39754065 | 4849664 | 1317960 | 1213543 | 15705836 | 0 | 0 | 3866624 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 247463936 | 1245184 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 560 | 56 | 15937644197116 | 15948468286497 | 15948468379777 | 15937644489859 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 32 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19904 | 0x7fa31f11f600 | 0x7fa31e824200 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 5636096 | 4063232 | 165895 | 165895 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 616 | 0 | 1245184 | 1241200 | 56 | 3922 | 750549 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 3014656 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 90450742 | 48536548 | 36933458 | 4980736 | 1313224 | 1207307 | 15620353 | 0 | 0 | 4063232 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 260046848 | 1245184 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 560 | 56 | 15937644535808 | 15948468411778 | 15948468505378 | 15937644826722 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 35 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 20608 | 0x7fa32177c480 | 0x7fa31e824240 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 5439488 | 3932160 | 164023 | 164023 | 0 | 0 | 0 | 0 | 0 | 0 | 1048576 | 0 | 0 | 0 | 0 | 616 | 0 | 1245184 | 1241446 | 56 | 3735 | 627445 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 98593284 | 47832958 | 45779590 | 4980736 | 1309680 | 1204161 | 15574587 | 0 | 0 | 3932160 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 251658240 | 1245184 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 560 | 56 | 15937644882380 | 15948468537698 | 15948468630979 | 15937645162584 |
| 15 | 13 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 38 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 16 | 24 | 21312 | 0x7fa32177c300 | 0x7fa31e824280 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 6619136 | 4063232 | 309997 | 309997 | 0 | 0 | 0 | 0 | 0 | 0 | 1310720 | 0 | 0 | 0 | 0 | 728 | 0 | 1441792 | 1438422 | 56 | 4729 | 452195 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 223235728 | 50301637 | 166839243 | 6094848 | 2482528 | 2376714 | 30766014 | 0 | 0 | 4063232 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 260046848 | 1441792 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 672 | 56 | 15937645208393 | 15948468666979 | 15948468845860 | 15937645588715 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 41 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22016 | 0x7fa32177c180 | 0x7fa31e8242c0 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 5767168 | 4325376 | 309509 | 309509 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 672 | 0 | 1310720 | 1306215 | 56 | 4160 | 450199 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 1310720 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 220698257 | 71506066 | 144014847 | 5177344 | 2471440 | 2363724 | 30627258 | 0 | 0 | 4325376 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 276824064 | 1310720 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 616 | 56 | 15937645634833 | 15948468878180 | 15948469057541 | 15937646020395 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 44 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22720 | 0x7fa32177c000 | 0x7fa31e824300 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 5963776 | 4390912 | 165286 | 165286 | 0 | 0 | 1310720 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 672 | 0 | 1376256 | 1372004 | 56 | 3917 | 686950 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 92711785 | 47272696 | 40065137 | 5373952 | 1309440 | 1206278 | 15614488 | 0 | 0 | 4390912 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 281018368 | 1376256 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 616 | 56 | 15937646067034 | 15948469086181 | 15948469180421 | 15937646400356 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 47 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 23424 | 0x7fa31f11fe80 | 0x7fa31e824340 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 6619136 | 5111808 | 165466 | 165466 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 728 | 0 | 1441792 | 1437699 | 56 | 3860 | 461559 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 4063232 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 89946306 | 47315739 | 36601255 | 6029312 | 1310728 | 1206845 | 15618748 | 0 | 0 | 5111808 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 327155712 | 1441792 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 672 | 56 | 15937646446365 | 15948469207142 | 15948469300102 | 15937646739269 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 50 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 24128 | 0x7fa31f11fd00 | 0x7fa31e824380 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 5898240 | 4325376 | 163070 | 163070 | 0 | 0 | 0 | 0 | 0 | 0 | 1441792 | 0 | 0 | 0 | 0 | 672 | 0 | 1310720 | 1306384 | 112 | 4356 | 708772 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 95169193 | 48025230 | 41770011 | 5373952 | 1306936 | 1204083 | 15585786 | 0 | 0 | 4325376 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 276824064 | 1310720 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 616 | 56 | 15937646792968 | 15948469333382 | 15948469426503 | 15937647075411 |
| 20 | 18 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 53 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 16 | 24 | 24832 | 0x7fa31f11fb80 | 0x7fa31e8243c0 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 7143424 | 4587520 | 309068 | 309068 | 0 | 0 | 0 | 0 | 0 | 0 | 1835008 | 0 | 0 | 0 | 0 | 784 | 0 | 1572864 | 1569350 | 56 | 3453 | 453990 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 226888178 | 49732995 | 170536047 | 6619136 | 2460344 | 2352748 | 30466009 | 0 | 0 | 4587520 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 293601280 | 1572864 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 728 | 56 | 15937647121370 | 15948469459943 | 15948469640104 | 15937647478442 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 56 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 16 | 24 | 25536 | 0x7fa31f11fa00 | 0x7fa31e824400 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 6291456 | 4849664 | 307754 | 307754 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 672 | 0 | 1441792 | 1439345 | 0 | 2569 | 888487 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 1835008 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 221188090 | 70395038 | 145091420 | 5701632 | 2458744 | 2346738 | 30409096 | 0 | 0 | 4849664 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 310378496 | 1441792 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 616 | 56 | 15937647526031 | 15948469666344 | 15948469847625 | 15937647870364 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 59 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26240 | 0x7fa31f11f880 | 0x7fa31e824440 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 6422528 | 4915200 | 164582 | 164582 | 0 | 0 | 1835008 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 728 | 0 | 1507328 | 1502654 | 56 | 5385 | 453432 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 100165233 | 48156732 | 46110261 | 5898240 | 1311032 | 1206455 | 15621378 | 0 | 0 | 4915200 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 314572800 | 1507328 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 672 | 56 | 15937647916673 | 15948469874505 | 15948469967785 | 15937648178987 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 62 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26944 | 0x7fa31f11f700 | 0x7fa31e824480 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 7733248 | 6160384 | 162490 | 162490 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 784 | 0 | 1638400 | 1634205 | 56 | 4338 | 649009 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 5111808 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 91132556 | 45000128 | 39054540 | 7077888 | 1305112 | 1200528 | 15521839 | 0 | 0 | 6160384 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 394264576 | 1638400 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 728 | 56 | 15937648225196 | 15948470001545 | 15948470094826 | 15937648487490 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 65 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 27648 | 0x7fa32177c580 | 0x7fa31e8244c0 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 6291456 | 4718592 | 163149 | 163149 | 0 | 0 | 0 | 0 | 0 | 0 | 1835008 | 0 | 0 | 0 | 0 | 672 | 0 | 1441792 | 1437256 | 56 | 3736 | 921585 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 105635341 | 47186358 | 52681815 | 5767168 | 1297128 | 1191491 | 15412967 | 0 | 0 | 4718592 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 301989888 | 1441792 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 616 | 56 | 15937648542049 | 15948470130026 | 15948470222667 | 15937648794973 |
| 25 | 23 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 68 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 16 | 24 | 28608 | 0x7fa32177c400 | 0x7fa31e824500 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 7667712 | 5111808 | 305658 | 305658 | 0 | 0 | 0 | 0 | 0 | 0 | 2359296 | 0 | 0 | 0 | 0 | 840 | 0 | 1703936 | 1700518 | 56 | 3883 | 673922 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 227365482 | 50129497 | 170092561 | 7143424 | 2437592 | 2326616 | 30141486 | 0 | 0 | 5111808 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 327155712 | 1703936 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 784 | 56 | 15937648843172 | 15948470254507 | 15948470432908 | 15937649190254 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 71 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 16 | 24 | 29312 | 0x7fa32177c280 | 0x7fa31e824540 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 6815744 | 5373952 | 307806 | 307806 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 784 | 0 | 1572864 | 1568325 | 56 | 4239 | 724409 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 2359296 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 202322680 | 69874297 | 126222463 | 6225920 | 2452264 | 2347113 | 30411156 | 0 | 0 | 5373952 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 343932928 | 1572864 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 728 | 56 | 15937649237813 | 15948470466668 | 15948470646349 | 15937649584115 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 74 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 30016 | 0x7fa32177c100 | 0x7fa31e824580 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 6946816 | 5439488 | 163472 | 163472 | 0 | 0 | 2359296 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 728 | 0 | 1638400 | 1634593 | 0 | 3826 | 870507 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 96513347 | 46395408 | 43695411 | 6422528 | 1296808 | 1190842 | 15409303 | 0 | 0 | 5439488 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 348127232 | 1638400 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 672 | 56 | 15937649631764 | 15948470675309 | 15948470767949 | 15937649889698 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 77 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 8 | 24 | 30976 | 0x7fa31f11ff80 | 0x7fa31e8245c0 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 8781824 | 7208960 | 163184 | 163184 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 840 | 0 | 1835008 | 1830695 | 0 | 4241 | 894596 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 6160384 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 97435709 | 42802427 | 46506818 | 8126464 | 1295512 | 1191479 | 15393774 | 0 | 0 | 7208960 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 461373440 | 1835008 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 784 | 56 | 15937649936997 | 15948470792429 | 15948470884270 | 15937650204151 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 80 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 31680 | 0x7fa31f11fe00 | 0x7fa31e824600 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 6684672 | 5111808 | 162864 | 162864 | 0 | 0 | 0 | 0 | 0 | 0 | 2228224 | 0 | 0 | 0 | 0 | 784 | 0 | 1507328 | 1502633 | 112 | 4677 | 616322 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 90899204 | 47324638 | 37414182 | 6160384 | 1293032 | 1187927 | 15380374 | 0 | 0 | 5111808 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 327155712 | 1507328 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 728 | 56 | 15937650258720 | 15948470917230 | 15948471010510 | 15937650519194 |
| 30 | 28 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 83 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 16 | 24 | 32640 | 0x7fa31f11fc80 | 0x7fa31e824640 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 8192000 | 5636096 | 305342 | 305342 | 0 | 0 | 0 | 0 | 0 | 0 | 2883584 | 0 | 0 | 0 | 0 | 840 | 0 | 1835008 | 1831424 | 0 | 3767 | 885971 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 223565061 | 48737392 | 167159957 | 7667712 | 2433840 | 2327610 | 30144919 | 0 | 0 | 5636096 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 360710144 | 1835008 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 784 | 56 | 15937650565113 | 15948471038191 | 15948471219472 | 15937650916936 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 86 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 33600 | 0x7fa31f11fb00 | 0x7fa31e824680 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 7340032 | 5898240 | 307087 | 307087 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 840 | 0 | 1703936 | 1700162 | 56 | 3456 | 906746 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 2883584 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 220263080 | 63646915 | 149865957 | 6750208 | 2460336 | 2350312 | 30443363 | 0 | 0 | 5898240 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 377487360 | 1703936 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 784 | 56 | 15937650963965 | 15948471251312 | 15948471431473 | 15937651309637 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 89 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 34560 | 0x7fa31f11f980 | 0x7fa31e8246c0 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 7471104 | 5963776 | 163150 | 163150 | 0 | 0 | 2883584 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 840 | 0 | 1769472 | 1764021 | 56 | 6983 | 457283 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 88296524 | 45614160 | 35735548 | 6946816 | 1305632 | 1199308 | 15508782 | 0 | 0 | 5963776 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 381681664 | 1769472 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 784 | 56 | 15937651355376 | 15948471458673 | 15948471552113 | 15937651613630 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 92 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 8 | 24 | 35520 | 0x7fa31f11f800 | 0x7fa31e824700 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 9830400 | 8257536 | 164067 | 164067 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 952 | 0 | 2031616 | 2023968 | 112 | 6228 | 456560 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 7208960 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 89077028 | 42230235 | 37671753 | 9175040 | 1306176 | 1202301 | 15517691 | 0 | 0 | 8257536 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 528482304 | 2031616 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 896 | 56 | 15937651659439 | 15948471584433 | 15948471678194 | 15937651922513 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 95 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 36224 | 0x7fa31f11f680 | 0x7fa31e824740 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 7077888 | 5505024 | 162148 | 162148 | 0 | 0 | 0 | 0 | 0 | 0 | 2621440 | 0 | 0 | 0 | 0 | 784 | 0 | 1638400 | 1633194 | 56 | 6098 | 464172 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 97269910 | 46296564 | 44419746 | 6553600 | 1303656 | 1201707 | 15541934 | 0 | 0 | 5505024 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 352321536 | 1638400 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 728 | 56 | 15937651976102 | 15948471711474 | 15948471805074 | 15937652235976 |
| 35 | 33 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 98 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 37184 | 0x7fa32177c500 | 0x7fa31e824780 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 8781824 | 6160384 | 304136 | 304136 | 0 | 0 | 0 | 0 | 0 | 0 | 3407872 | 0 | 0 | 0 | 0 | 896 | 0 | 1966080 | 1962829 | 0 | 3283 | 925281 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 223265431 | 48257252 | 166816179 | 8192000 | 2433232 | 2327916 | 30150997 | 0 | 0 | 6160384 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 394264576 | 1966080 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 840 | 56 | 15937652282125 | 15948471840595 | 15948472021236 | 15937652632618 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 101 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 38144 | 0x7fa32177c380 | 0x7fa31e8247c0 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 7929856 | 6422528 | 303190 | 303190 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 896 | 0 | 1835008 | 1830399 | 56 | 4650 | 637571 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 3407872 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 216029038 | 59515818 | 149238724 | 7274496 | 2435344 | 2327755 | 30145517 | 0 | 0 | 6422528 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 411041792 | 1835008 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 840 | 56 | 15937652678277 | 15948472057236 | 15948472238517 | 15937653026389 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 104 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 39104 | 0x7fa32177c200 | 0x7fa31e824800 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 8060928 | 6488064 | 162054 | 162054 | 0 | 0 | 3407872 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 896 | 0 | 1900544 | 1893685 | 112 | 5063 | 684469 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 93613678 | 43890470 | 42252104 | 7471104 | 1307320 | 1196593 | 15478592 | 0 | 0 | 6488064 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 415236096 | 1900544 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 840 | 56 | 15937653071258 | 15948472263157 | 15948472356597 | 15937653340062 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 107 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 8 | 24 | 40320 | 0x7fa32177c080 | 0x7fa31e824840 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 10813440 | 9306112 | 163310 | 163310 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1064 | 0 | 2228224 | 2223014 | 56 | 5522 | 445266 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 8257536 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 95638938 | 38557044 | 46858278 | 10223616 | 1305152 | 1197597 | 15444219 | 0 | 0 | 9306112 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 595591168 | 2228224 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1008 | 56 | 15937653386121 | 15948472388917 | 15948472483638 | 15937653648865 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 110 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 41280 | 0x7fa31f11ff00 | 0x7fa31e824880 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 7471104 | 5898240 | 162256 | 162256 | 0 | 0 | 0 | 0 | 0 | 0 | 3014656 | 0 | 0 | 0 | 0 | 840 | 0 | 1703936 | 1698790 | 56 | 5051 | 546455 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 90424721 | 45218528 | 38259377 | 6946816 | 1303904 | 1199458 | 15522154 | 0 | 0 | 5898240 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 377487360 | 1703936 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 784 | 56 | 15937653701934 | 15948472517878 | 15948472611318 | 15937653956098 |
| 40 | 38 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 113 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 42240 | 0x7fa31f11fd80 | 0x7fa31e8248c0 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 9306112 | 6684672 | 307010 | 307010 | 0 | 0 | 0 | 0 | 0 | 0 | 3932160 | 0 | 0 | 0 | 0 | 1008 | 0 | 2097152 | 2092961 | 56 | 4216 | 451165 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 227827035 | 48852315 | 170258432 | 8716288 | 2430568 | 2317604 | 30028425 | 0 | 0 | 6684672 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 427819008 | 2097152 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 952 | 56 | 15937654002417 | 15948472647159 | 15948472826520 | 15937654358719 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 116 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 43200 | 0x7fa31f11fc00 | 0x7fa31e824900 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 8388608 | 6946816 | 304008 | 304008 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 896 | 0 | 1966080 | 1962646 | 56 | 2862 | 887865 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 3932160 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 221222500 | 56913607 | 156510109 | 7798784 | 2419040 | 2312664 | 29979438 | 0 | 0 | 6946816 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 444596224 | 1966080 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 840 | 56 | 15937654403778 | 15948472858360 | 15948473036441 | 15937654752760 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 119 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 8 | 24 | 44160 | 0x7fa31f11fa80 | 0x7fa31e824940 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 8585216 | 7012352 | 163296 | 163296 | 0 | 0 | 3932160 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 952 | 0 | 2031616 | 2026177 | 56 | 5615 | 454108 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 105694703 | 44644520 | 53054791 | 7995392 | 1306112 | 1201877 | 15520759 | 0 | 0 | 7012352 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 448790528 | 2031616 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 896 | 56 | 15937654799259 | 15948473068921 | 15948473162521 | 15937655061674 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 122 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 45376 | 0x7fa31f11f900 | 0x7fa31e824980 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 11927552 | 10354688 | 164315 | 164315 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1120 | 0 | 2424832 | 2418026 | 56 | 6542 | 616199 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 9306112 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 92249429 | 38108176 | 42869061 | 11272192 | 1305152 | 1198359 | 15452578 | 0 | 0 | 10354688 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 662700032 | 2424832 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1064 | 56 | 15937655107433 | 15948473197081 | 15948473292442 | 15937655370497 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 125 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 46336 | 0x7fa31f11f780 | 0x7fa31e8249c0 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 7995392 | 6291456 | 161688 | 161688 | 0 | 0 | 0 | 0 | 0 | 0 | 3407872 | 0 | 0 | 0 | 0 | 896 | 0 | 1835008 | 1830069 | 56 | 5191 | 632619 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 86639894 | 44390434 | 34909428 | 7340032 | 1302624 | 1201187 | 15533530 | 0 | 0 | 6291456 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 402653184 | 1835008 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 840 | 56 | 15937655423305 | 15948473326522 | 15948473420122 | 15937655682660 |
| 45 | 43 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 128 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 47552 | 0x7fa31f11f600 | 0x7fa31e824a00 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 9830400 | 7208960 | 304385 | 304385 | 0 | 0 | 0 | 0 | 0 | 0 | 4456448 | 0 | 0 | 0 | 0 | 1064 | 0 | 2228224 | 2223677 | 112 | 4961 | 454595 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 221069236 | 46729344 | 165099316 | 9240576 | 2427120 | 2318935 | 30019568 | 0 | 0 | 7208960 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 461373440 | 2228224 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1008 | 56 | 15937655729169 | 15948473458203 | 15948473637084 | 15937656078601 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 131 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 48512 | 0x7fa32177c480 | 0x7fa31e824a40 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 8912896 | 7471104 | 302291 | 302291 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1008 | 0 | 2097152 | 2091956 | 56 | 5087 | 708037 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 4456448 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 206609403 | 57083692 | 141202639 | 8323072 | 2415176 | 2309383 | 29924849 | 0 | 0 | 7471104 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 478150656 | 2097152 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 952 | 56 | 15937656124910 | 15948473683484 | 15948473862845 | 15937656476312 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 134 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 8 | 24 | 49472 | 0x7fa32177c300 | 0x7fa31e824a80 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 9109504 | 7536640 | 162109 | 162109 | 0 | 0 | 4456448 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 952 | 0 | 2162688 | 2157642 | 0 | 4791 | 914985 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 89643012 | 42482821 | 38640511 | 8519680 | 1291848 | 1186009 | 15313133 | 0 | 0 | 7536640 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 482344960 | 2162688 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 896 | 56 | 15937656521541 | 15948473891805 | 15948473984605 | 15937656793815 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 137 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 50688 | 0x7fa32177c180 | 0x7fa31e824ac0 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 12976128 | 11403264 | 161953 | 161953 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1176 | 0 | 2621440 | 2615650 | 56 | 7403 | 881564 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 10354688 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 94817026 | 35859940 | 46636318 | 12320768 | 1298312 | 1192529 | 15376508 | 0 | 0 | 11403264 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 729808896 | 2621440 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1120 | 56 | 15937656840204 | 15948474023805 | 15948474117406 | 15937657104498 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 140 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 51648 | 0x7fa32177c000 | 0x7fa31e824b00 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 8388608 | 6684672 | 162030 | 162030 | 0 | 0 | 0 | 0 | 0 | 0 | 3801088 | 0 | 0 | 0 | 0 | 896 | 0 | 1966080 | 1961161 | 0 | 6313 | 895658 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 92143695 | 43288449 | 41121998 | 7733248 | 1291800 | 1189288 | 15381788 | 0 | 0 | 6684672 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 427819008 | 1966080 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 840 | 56 | 15937657158307 | 15948474152286 | 15948474244127 | 15937657410261 |
| 50 | 48 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 143 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 52864 | 0x7fa31f11fe80 | 0x7fa31e824b40 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 10354688 | 7733248 | 302916 | 302916 | 0 | 0 | 0 | 0 | 0 | 0 | 4980736 | 0 | 0 | 0 | 0 | 1120 | 0 | 2359296 | 2353550 | 56 | 4850 | 463557 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 216912416 | 46273879 | 160873673 | 9764864 | 2421584 | 2317136 | 30003439 | 0 | 0 | 7733248 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 494927872 | 2359296 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1064 | 56 | 15937657456630 | 15948474268607 | 15948474448448 | 15937657807122 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 146 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 54080 | 0x7fa31f11fd00 | 0x7fa31e824b80 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 9437184 | 7995392 | 305052 | 305052 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1064 | 0 | 2228224 | 2222557 | 56 | 5279 | 715056 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 4980736 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 209750469 | 55683719 | 145219390 | 8847360 | 2417456 | 2310606 | 29939455 | 0 | 0 | 7995392 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 511705088 | 2228224 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1008 | 56 | 15937657852111 | 15948474472448 | 15948474652769 | 15937658207733 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 149 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 8 | 24 | 55296 | 0x7fa31f11fb80 | 0x7fa31e824bc0 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 9633792 | 8060928 | 162746 | 162746 | 0 | 0 | 4980736 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1064 | 0 | 2293760 | 2286839 | 112 | 6308 | 667216 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 85443038 | 42199114 | 34199956 | 9043968 | 1304944 | 1202924 | 15528880 | 0 | 0 | 8060928 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 515899392 | 2293760 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1008 | 56 | 15937658253532 | 15948474678689 | 15948474773089 | 15937658520186 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 152 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 56768 | 0x7fa31f11fa00 | 0x7fa31e824c00 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 14024704 | 12451840 | 162513 | 162513 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1288 | 0 | 2752512 | 2744957 | 56 | 7633 | 752219 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 11403264 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 99574453 | 32170149 | 54034960 | 13369344 | 1296784 | 1192585 | 15384854 | 0 | 0 | 12451840 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 796917760 | 2752512 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1232 | 56 | 15937658565795 | 15948474798209 | 15948474893410 | 15937658829520 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 155 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 57728 | 0x7fa31f11f880 | 0x7fa31e824c40 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 8781824 | 7077888 | 162108 | 162108 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 1008 | 0 | 2031616 | 2025785 | 56 | 4918 | 719508 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 97152820 | 41844653 | 47181703 | 8126464 | 1294816 | 1185995 | 15325111 | 0 | 0 | 7077888 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 452984832 | 2031616 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 952 | 56 | 15937658882398 | 15948474930210 | 15948475024930 | 15937659144123 |
| 55 | 53 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 158 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 58944 | 0x7fa31f11f700 | 0x7fa31e824c80 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 10878976 | 8257536 | 302678 | 302678 | 0 | 0 | 0 | 0 | 0 | 0 | 5505024 | 0 | 0 | 0 | 0 | 1120 | 0 | 2490368 | 2485899 | 56 | 4646 | 902356 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 223732171 | 46065538 | 167377481 | 10289152 | 2425648 | 2316135 | 30003821 | 0 | 0 | 8257536 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 528482304 | 2490368 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1064 | 56 | 15937659190082 | 15948475050851 | 15948475230691 | 15937659537494 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 161 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 60160 | 0x7fa32177c580 | 0x7fa31e824cc0 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 9961472 | 8519680 | 303285 | 303285 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1120 | 0 | 2359296 | 2352393 | 56 | 6904 | 462157 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 5505024 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 218456631 | 56096125 | 152988858 | 9371648 | 2433920 | 2322496 | 30091895 | 0 | 0 | 8519680 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 545259520 | 2359296 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1064 | 56 | 15937659584233 | 15948475255172 | 15948475435972 | 15937659933495 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 164 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 8 | 24 | 61376 | 0x7fa32177c400 | 0x7fa31e824d00 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 10158080 | 8585216 | 163095 | 163095 | 0 | 0 | 5505024 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1120 | 0 | 2424832 | 2415938 | 56 | 9676 | 638578 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 88020159 | 41332491 | 37119412 | 9568256 | 1303512 | 1196761 | 15453693 | 0 | 0 | 8585216 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 549453824 | 2424832 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1064 | 56 | 15937659979534 | 15948475459013 | 15948475554053 | 15937660244798 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 167 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 62848 | 0x7fa32177c280 | 0x7fa31e824d40 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 15073280 | 13500416 | 169268 | 169268 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1400 | 0 | 2949120 | 2941216 | 112 | 8503 | 457151 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 12451840 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 101729609 | 27921402 | 59390287 | 14417920 | 1361984 | 1251344 | 16136984 | 0 | 0 | 13500416 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 864026624 | 2949120 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1344 | 56 | 15937660291067 | 15948475579173 | 15948475678854 | 15937660558591 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 170 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 63808 | 0x7fa32177c100 | 0x7fa31e824d80 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 9175040 | 7471104 | 162919 | 162919 | 0 | 0 | 0 | 0 | 0 | 0 | 4587520 | 0 | 0 | 0 | 0 | 1008 | 0 | 2162688 | 2156814 | 56 | 5318 | 454086 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 101625746 | 42172400 | 50933666 | 8519680 | 1306408 | 1197887 | 15479551 | 0 | 0 | 7471104 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 478150656 | 2162688 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 952 | 56 | 15937660612100 | 15948475712134 | 15948475806054 | 15937660866994 |
| 60 | 58 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 173 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 65024 | 0x7fa31f11ff80 | 0x7fa31e824dc0 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 11403264 | 8781824 | 298714 | 298714 | 0 | 0 | 0 | 0 | 0 | 0 | 6029312 | 0 | 0 | 0 | 0 | 1176 | 0 | 2621440 | 2614551 | 0 | 5244 | 868711 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 219072895 | 45730994 | 162528461 | 10813440 | 2388680 | 2280265 | 29554934 | 0 | 0 | 8781824 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 562036736 | 2621440 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1120 | 56 | 15937660913463 | 15948475832614 | 15948476012615 | 15937661258366 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 176 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 66240 | 0x7fa31f11fe00 | 0x7fa31e824e00 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 10485760 | 9043968 | 299736 | 299736 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1120 | 0 | 2490368 | 2485755 | 56 | 3880 | 872196 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 6029312 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 210176410 | 54422252 | 145858222 | 9895936 | 2430568 | 2313046 | 29951208 | 0 | 0 | 9043968 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 578813952 | 2490368 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1064 | 56 | 15937661304345 | 15948476038055 | 15948476218376 | 15937661648007 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 179 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 8 | 24 | 67456 | 0x7fa31f11fc80 | 0x7fa31e824e40 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 10682368 | 9109504 | 163644 | 163644 | 0 | 0 | 6029312 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1176 | 0 | 2555904 | 2548298 | 56 | 6807 | 602833 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 86307125 | 41041095 | 35173486 | 10092544 | 1315704 | 1202151 | 15479012 | 0 | 0 | 9109504 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 583008256 | 2555904 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1120 | 56 | 15937661693076 | 15948476242696 | 15948476337097 | 15937661955140 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 182 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 68928 | 0x7fa31f11fb00 | 0x7fa31e824e80 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 16121856 | 14548992 | 177322 | 177322 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1456 | 0 | 3145728 | 3136801 | 56 | 8362 | 707968 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 13500416 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 105897157 | 25608294 | 64822367 | 15466496 | 1407160 | 1300170 | 16780566 | 0 | 0 | 14548992 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 931135488 | 3145728 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1400 | 56 | 15937662001649 | 15948476362857 | 15948476467178 | 15937662281343 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 185 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 70144 | 0x7fa31f11f980 | 0x7fa31e824ec0 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 9568256 | 7864320 | 161918 | 161918 | 0 | 0 | 0 | 0 | 0 | 0 | 4980736 | 0 | 0 | 0 | 0 | 1008 | 0 | 2228224 | 2222758 | 57 | 5241 | 860323 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 95237880 | 40616795 | 45708189 | 8912896 | 1282824 | 1178883 | 15227302 | 0 | 0 | 7864320 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 503316480 | 2228224 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 952 | 56 | 15937662336222 | 15948476501578 | 15948476594538 | 15937662597096 |
| 65 | 63 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 188 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 71616 | 0x7fa31f11f800 | 0x7fa31e824f00 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 11927552 | 9306112 | 301169 | 301169 | 0 | 0 | 0 | 0 | 0 | 0 | 6553600 | 0 | 0 | 0 | 0 | 1288 | 0 | 2752512 | 2745549 | 56 | 6819 | 483690 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 219369649 | 49622401 | 158409520 | 11337728 | 2403976 | 2293345 | 29699820 | 0 | 0 | 9306112 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 595591168 | 2752512 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1232 | 56 | 15937662643185 | 15948476620298 | 15948476800299 | 15937662994397 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 191 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 72832 | 0x7fa31f11f680 | 0x7fa31e824f40 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 11010048 | 9568256 | 302336 | 302336 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1232 | 0 | 2621440 | 2615642 | 56 | 6053 | 446332 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 6553600 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 221379014 | 46597593 | 164361197 | 10420224 | 2401976 | 2295801 | 29721261 | 0 | 0 | 9568256 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 612368384 | 2621440 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1176 | 56 | 15937663042856 | 15948476825579 | 15948477006220 | 15937663390848 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 194 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 8 | 24 | 74048 | 0x7fa32177c500 | 0x7fa31e824f80 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 11141120 | 9633792 | 160926 | 160926 | 0 | 0 | 6553600 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1176 | 0 | 2686976 | 2680119 | 56 | 6015 | 894718 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 86654310 | 38146467 | 37891011 | 10616832 | 1294808 | 1191438 | 15332723 | 0 | 0 | 9633792 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 616562688 | 2686976 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1120 | 56 | 15937663437297 | 15948477030540 | 15948477124461 | 15937663700681 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 197 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 75776 | 0x7fa32177c380 | 0x7fa31e824fc0 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 17170432 | 15597568 | 182008 | 182008 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1512 | 0 | 3342336 | 3332158 | 0 | 12135 | 878725 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 14548992 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 112071750 | 22405474 | 73151204 | 16515072 | 1458912 | 1348105 | 17404067 | 0 | 0 | 15597568 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 998244352 | 3342336 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1456 | 56 | 15937663747110 | 15948477148621 | 15948477255181 | 15937664026394 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 200 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 76992 | 0x7fa32177c200 | 0x7fa31e825000 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 9961472 | 8257536 | 161726 | 161726 | 0 | 0 | 0 | 0 | 0 | 0 | 5373952 | 0 | 0 | 0 | 0 | 1120 | 0 | 2359296 | 2352113 | 56 | 5995 | 450215 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 95309447 | 40370646 | 45632689 | 9306112 | 1295176 | 1187444 | 15341984 | 0 | 0 | 8257536 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 528482304 | 2359296 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1064 | 56 | 15937664090133 | 15948477289902 | 15948477384622 | 15937664336167 |
| 70 | 68 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 203 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 78464 | 0x7fa32177c080 | 0x7fa31e825040 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 12451840 | 9830400 | 301166 | 301166 | 0 | 0 | 0 | 0 | 0 | 0 | 7077888 | 0 | 0 | 0 | 0 | 1344 | 0 | 2883584 | 2877247 | 112 | 8476 | 455882 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 215294901 | 49624403 | 153808482 | 11862016 | 2407384 | 2296491 | 29746503 | 0 | 0 | 9830400 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 629145600 | 2883584 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1288 | 56 | 15937664383066 | 15948477410382 | 15948477589263 | 15937664748728 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 206 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 79936 | 0x7fa31f11ff00 | 0x7fa31e825080 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 11534336 | 10092544 | 302804 | 302804 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1288 | 0 | 2686976 | 2681197 | 56 | 6954 | 455242 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 7077888 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 221499554 | 46748051 | 163806991 | 10944512 | 2394808 | 2283312 | 29590137 | 0 | 0 | 10092544 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 645922816 | 2686976 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1232 | 56 | 15937664794437 | 15948477614063 | 15948477793104 | 15937665150849 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 209 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 8 | 24 | 81408 | 0x7fa31f11fd80 | 0x7fa31e8250c0 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 11730944 | 10158080 | 163357 | 163357 | 0 | 0 | 7077888 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1288 | 0 | 2818048 | 2809781 | 56 | 7315 | 600543 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 95130248 | 38605305 | 45383823 | 11141120 | 1307864 | 1201463 | 15492043 | 0 | 0 | 10158080 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 650117120 | 2818048 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1232 | 56 | 15937665196638 | 15948477818864 | 15948477913425 | 15937665461682 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 212 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 83136 | 0x7fa31f11fc00 | 0x7fa31e825100 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 18219008 | 16646144 | 192114 | 192114 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1624 | 0 | 3538944 | 3521518 | 133 | 10781 | 581118 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 15597568 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 121241123 | 20678428 | 82999047 | 17563648 | 1544976 | 1431426 | 18452261 | 0 | 0 | 16646144 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 1065353216 | 3538944 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1568 | 56 | 15937665507731 | 15948477938705 | 15948478052945 | 15937665788215 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 215 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 84352 | 0x7fa31f11fa80 | 0x7fa31e825140 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 10354688 | 8650752 | 161075 | 161075 | 0 | 0 | 0 | 0 | 0 | 0 | 5767168 | 0 | 0 | 0 | 0 | 1176 | 0 | 2424832 | 2418393 | 56 | 7962 | 454414 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 94911432 | 39714757 | 45497347 | 9699328 | 1292400 | 1189887 | 15359063 | 0 | 0 | 8650752 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 553648128 | 2424832 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1120 | 56 | 15937665841553 | 15948478109906 | 15948478203666 | 15937666101748 |
| 75 | 73 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 218 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 85824 | 0x7fa31f11f900 | 0x7fa31e825180 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 12976128 | 10354688 | 301189 | 301189 | 0 | 0 | 0 | 0 | 0 | 0 | 7602176 | 0 | 0 | 0 | 0 | 1400 | 0 | 3014656 | 3005972 | 112 | 9930 | 545211 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 221340639 | 50907061 | 158047274 | 12386304 | 2430400 | 2315338 | 29976184 | 0 | 0 | 10354688 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 662700032 | 3014656 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1344 | 56 | 15937666147987 | 15948478231186 | 15948478411027 | 15937666502129 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 221 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 87296 | 0x7fa31f11f780 | 0x7fa31e8251c0 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 12058624 | 10616832 | 298372 | 298372 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1344 | 0 | 2818048 | 2811318 | 56 | 7167 | 525214 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 7602176 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 210556126 | 45872089 | 153215237 | 11468800 | 2404720 | 2293660 | 29718633 | 0 | 0 | 10616832 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 679477248 | 2818048 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1288 | 56 | 15937666547258 | 15948478434547 | 15948478613428 | 15937666895780 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 224 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 88768 | 0x7fa31f11f600 | 0x7fa31e825200 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 12255232 | 10682368 | 163763 | 163763 | 0 | 0 | 7602176 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1344 | 0 | 2949120 | 2940288 | 56 | 9965 | 451956 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 94692311 | 38639499 | 44387404 | 11665408 | 1298456 | 1192041 | 15364148 | 0 | 0 | 10682368 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 683671552 | 2949120 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1288 | 56 | 15937666941629 | 15948478640468 | 15948478735669 | 15937667206333 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 227 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 90752 | 0x7fa32177c480 | 0x7fa31e825240 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 19267584 | 17694720 | 201410 | 201410 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1736 | 0 | 3735552 | 3723814 | 112 | 12235 | 455515 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 16646144 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 121984758 | 20285021 | 83087513 | 18612224 | 1617608 | 1504557 | 19396720 | 0 | 0 | 17694720 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 1132462080 | 3735552 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1680 | 56 | 15937667251022 | 15948478761589 | 15948478882070 | 15937667545416 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 230 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 91968 | 0x7fa32177c300 | 0x7fa31e825280 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 10747904 | 9043968 | 162652 | 162652 | 0 | 0 | 0 | 0 | 0 | 0 | 6160384 | 0 | 0 | 0 | 0 | 1176 | 0 | 2555904 | 2546928 | 56 | 6881 | 456764 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 92147504 | 40514423 | 41540537 | 10092544 | 1300840 | 1194037 | 15383238 | 0 | 0 | 9043968 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 578813952 | 2555904 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1120 | 56 | 15937667598974 | 15948478914550 | 15948479008310 | 15937667861609 |
| 80 | 78 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 233 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 93440 | 0x7fa32177c180 | 0x7fa31e8252c0 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 13500416 | 10878976 | 303101 | 303101 | 0 | 0 | 0 | 0 | 0 | 0 | 8126464 | 0 | 0 | 0 | 0 | 1400 | 0 | 3145728 | 3137404 | 56 | 8013 | 453560 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 219998768 | 49612658 | 157475518 | 12910592 | 2411096 | 2307165 | 29890810 | 0 | 0 | 10878976 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 696254464 | 3145728 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1344 | 56 | 15937667907878 | 15948479032470 | 15948479212151 | 15937668256760 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 236 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 94912 | 0x7fa32177c000 | 0x7fa31e825300 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 12582912 | 11141120 | 299914 | 299914 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1400 | 0 | 2949120 | 2942972 | 56 | 7363 | 461063 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 8126464 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 207494476 | 50908029 | 144593359 | 11993088 | 2412472 | 2303869 | 29814495 | 0 | 0 | 11141120 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 713031680 | 2949120 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1344 | 56 | 15937668304079 | 15948479236631 | 15948479417112 | 15937668650851 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 239 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 96384 | 0x7fa31f11fe80 | 0x7fa31e825340 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 12845056 | 11206656 | 162904 | 162904 | 0 | 0 | 8126464 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1400 | 0 | 3080192 | 3070508 | 57 | 10120 | 698362 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 97738590 | 36444974 | 49103920 | 12189696 | 1302504 | 1188258 | 15311403 | 0 | 0 | 11206656 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 717225984 | 3080192 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1344 | 56 | 15937668696150 | 15948479442392 | 15948479538393 | 15937668961434 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 242 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 98368 | 0x7fa31f11fd00 | 0x7fa31e825380 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 20316160 | 18743296 | 210022 | 210022 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1792 | 0 | 3932160 | 3917532 | 113 | 14456 | 751080 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 17694720 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 126427161 | 19214167 | 87552194 | 19660800 | 1686088 | 1572913 | 20279848 | 0 | 0 | 18743296 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 1199570944 | 3932160 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1736 | 56 | 15937669007373 | 15948479563833 | 15948479689914 | 15937669300167 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 245 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 99584 | 0x7fa31f11fb80 | 0x7fa31e8253c0 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 11141120 | 9437184 | 161731 | 161731 | 0 | 0 | 0 | 0 | 0 | 0 | 6553600 | 0 | 0 | 0 | 0 | 1232 | 0 | 2621440 | 2612901 | 56 | 7701 | 458816 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 92724766 | 38431266 | 43807740 | 10485760 | 1291816 | 1186461 | 15311240 | 0 | 0 | 9437184 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 603979776 | 2621440 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1176 | 56 | 15937669352975 | 15948479723354 | 15948479818554 | 15937669615070 |
| 85 | 83 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 248 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 101312 | 0x7fa31f11fa00 | 0x7fa31e825400 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 14024704 | 11403264 | 300256 | 300256 | 0 | 0 | 0 | 0 | 0 | 0 | 8650752 | 0 | 0 | 0 | 0 | 1456 | 0 | 3276800 | 3267444 | 0 | 7482 | 878141 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 217388974 | 45415190 | 158538904 | 13434880 | 2398272 | 2287418 | 29617750 | 0 | 0 | 11403264 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 729808896 | 3276800 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1400 | 56 | 15937669661639 | 15948479843514 | 15948480023835 | 15937670010471 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 251 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 102784 | 0x7fa31f11f880 | 0x7fa31e825440 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 13041664 | 11599872 | 298208 | 298208 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1456 | 0 | 3080192 | 3074184 | 56 | 6773 | 715460 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 8650752 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 214675976 | 49972677 | 152251459 | 12451840 | 2380720 | 2278112 | 29515201 | 0 | 0 | 11599872 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 742391808 | 3080192 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1400 | 56 | 15937670056920 | 15948480048475 | 15948480230076 | 15937670413502 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 254 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 104256 | 0x7fa31f11f700 | 0x7fa31e825480 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 13303808 | 11730944 | 162452 | 162452 | 0 | 0 | 8650752 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1400 | 0 | 3211264 | 3203915 | 0 | 8145 | 883258 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 98740381 | 36577340 | 49449057 | 12713984 | 1299008 | 1187471 | 15291191 | 0 | 0 | 11730944 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 750780416 | 3211264 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1344 | 56 | 15937670459531 | 15948480255516 | 15948480349757 | 15937670725245 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 257 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 106240 | 0x7fa32177c580 | 0x7fa31e8254c0 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 21364736 | 19791872 | 219466 | 219466 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1848 | 0 | 4128768 | 4115548 | 56 | 13767 | 860737 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 18743296 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 140304464 | 18766067 | 100829021 | 20709376 | 1752592 | 1639174 | 21156497 | 0 | 0 | 19791872 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 1266679808 | 4128768 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1792 | 56 | 15937670770924 | 15948480375357 | 15948480505598 | 15937671071387 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 260 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 107712 | 0x7fa32177c400 | 0x7fa31e825500 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 11534336 | 9830400 | 161406 | 161406 | 0 | 0 | 0 | 0 | 0 | 0 | 6946816 | 0 | 0 | 0 | 0 | 1232 | 0 | 2752512 | 2745090 | 0 | 8983 | 900970 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 89143689 | 38139533 | 40125180 | 10878976 | 1284640 | 1178808 | 15200312 | 0 | 0 | 9830400 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 629145600 | 2752512 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1176 | 56 | 15937671126056 | 15948480539358 | 15948480632318 | 15937671390260 |
| 90 | 88 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 263 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 16 | 24 | 109440 | 0x7fa32177c280 | 0x7fa31e825540 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 14548992 | 11927552 | 297690 | 297690 | 0 | 0 | 0 | 0 | 0 | 0 | 9175040 | 0 | 0 | 0 | 0 | 1568 | 0 | 3407872 | 3399607 | 112 | 8412 | 584843 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 215260647 | 45530403 | 155771076 | 13959168 | 2379000 | 2277604 | 29497502 | 0 | 0 | 11927552 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 763363328 | 3407872 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1512 | 56 | 15937671437469 | 15948480658878 | 15948480838079 | 15937671789911 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 266 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 16 | 24 | 111168 | 0x7fa32177c100 | 0x7fa31e825580 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 13565952 | 12124160 | 299487 | 299487 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1512 | 0 | 3211264 | 3205457 | 56 | 6844 | 573348 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 9175040 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 211541631 | 47688346 | 150877157 | 12976128 | 2379648 | 2277814 | 29504944 | 0 | 0 | 12124160 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 775946240 | 3211264 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1456 | 56 | 15937671836190 | 15948480863999 | 15948481045120 | 15937672192542 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 269 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 8 | 24 | 112896 | 0x7fa31f11ff80 | 0x7fa31e8255c0 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 13828096 | 12255232 | 162127 | 162127 | 0 | 0 | 9175040 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1512 | 0 | 3276800 | 3265600 | 56 | 12804 | 459275 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 103533044 | 35398476 | 54896296 | 13238272 | 1298440 | 1193527 | 15405900 | 0 | 0 | 12255232 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 784334848 | 3276800 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1456 | 56 | 15937672239481 | 15948481069440 | 15948481165601 | 15937672506165 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 272 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 115136 | 0x7fa31f11fe00 | 0x7fa31e825600 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 22413312 | 20840448 | 229851 | 229851 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1960 | 0 | 4325376 | 4309022 | 122 | 14385 | 682734 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 19791872 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 139802097 | 18508322 | 99535823 | 21757952 | 1835184 | 1722029 | 22235823 | 0 | 0 | 20840448 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 1333788672 | 4325376 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1904 | 56 | 15937672552164 | 15948481191041 | 15948481330402 | 15937672856647 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 275 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 116608 | 0x7fa31f11fc80 | 0x7fa31e825640 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 11796480 | 10223616 | 162165 | 162165 | 0 | 0 | 0 | 0 | 0 | 0 | 7340032 | 0 | 0 | 0 | 0 | 1288 | 0 | 2818048 | 2808693 | 56 | 9465 | 599071 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 96716177 | 36445454 | 48998531 | 11272192 | 1287328 | 1180373 | 15216899 | 0 | 0 | 10223616 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 654311424 | 2818048 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1232 | 56 | 15937672910426 | 15948481363842 | 15948481458242 | 15937673172750 |
| 95 | 93 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 278 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 16 | 24 | 118336 | 0x7fa31f11fb00 | 0x7fa31e825680 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 15073280 | 12451840 | 297001 | 297001 | 0 | 0 | 0 | 0 | 0 | 0 | 9699328 | 0 | 0 | 0 | 0 | 1624 | 0 | 3538944 | 3528672 | 112 | 9140 | 504426 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 212998299 | 45108531 | 153406312 | 14483456 | 2385968 | 2276946 | 29456095 | 0 | 0 | 12451840 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 796917760 | 3538944 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1568 | 56 | 15937673219019 | 15948481484162 | 15948481663363 | 15937673566271 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 281 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 16 | 24 | 120064 | 0x7fa31f11f980 | 0x7fa31e8256c0 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 14221312 | 12713984 | 298704 | 298704 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1568 | 0 | 3407872 | 3399685 | 56 | 7822 | 750013 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 9699328 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 209843762 | 50670513 | 145607297 | 13565952 | 2393904 | 2286220 | 29611673 | 0 | 0 | 12713984 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 813694976 | 3407872 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1512 | 56 | 15937673613130 | 15948481689444 | 15948481868644 | 15937673962623 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 284 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 121792 | 0x7fa31f11f800 | 0x7fa31e825700 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 14352384 | 12779520 | 163246 | 163246 | 0 | 0 | 9699328 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1568 | 0 | 3407872 | 3394468 | 112 | 9967 | 456227 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 102546728 | 31748737 | 57035431 | 13762560 | 1317856 | 1210313 | 15597940 | 0 | 0 | 12779520 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 817889280 | 3407872 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1512 | 56 | 15937674008662 | 15948481893765 | 15948481990405 | 15937674285735 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 287 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 124032 | 0x7fa31f11f680 | 0x7fa31e825740 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 23461888 | 21889024 | 239044 | 239044 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2072 | 0 | 4521984 | 4505466 | 73 | 18787 | 746808 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 20840448 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 165784311 | 18563508 | 124414275 | 22806528 | 1907520 | 1798729 | 23246313 | 0 | 0 | 21889024 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 1400897536 | 4521984 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2016 | 56 | 15937674331054 | 15948482015365 | 15948482161446 | 15937674652197 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 290 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 125504 | 0x7fa32177c500 | 0x7fa31e825780 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 12582912 | 11010048 | 161460 | 161460 | 0 | 0 | 0 | 0 | 0 | 0 | 8126464 | 0 | 0 | 0 | 0 | 1400 | 0 | 3014656 | 3002467 | 112 | 11457 | 561682 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 97108488 | 37854506 | 47195358 | 12058624 | 1295472 | 1183349 | 15248093 | 0 | 0 | 11010048 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 704643072 | 3014656 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1344 | 56 | 15937674705486 | 15948482194086 | 15948482289606 | 15937674969200 |
| 100 | 98 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 293 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 127488 | 0x7fa32177c380 | 0x7fa31e8257c0 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 16121856 | 13500416 | 298073 | 298073 | 0 | 0 | 0 | 0 | 0 | 0 | 10747904 | 0 | 0 | 0 | 0 | 1736 | 0 | 3801088 | 3792721 | 56 | 9082 | 627098 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 189673827 | 57656620 | 116485175 | 15532032 | 2380512 | 2269764 | 29365496 | 0 | 0 | 13500416 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 864026624 | 3801088 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1680 | 56 | 15937675015959 | 15948482314247 | 15948482493928 | 15937675365121 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 296 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 129216 | 0x7fa32177c200 | 0x7fa31e825800 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 15269888 | 13762560 | 297847 | 297847 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1680 | 0 | 3670016 | 3657806 | 129 | 9272 | 556892 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 10747904 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 201186909 | 53837981 | 132734400 | 14614528 | 2390368 | 2274590 | 29427247 | 0 | 0 | 13762560 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 880803840 | 3670016 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1624 | 56 | 15937675412280 | 15948482518248 | 15948482698249 | 15937675761442 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 299 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 130944 | 0x7fa32177c080 | 0x7fa31e825840 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 15400960 | 13828096 | 169941 | 169941 | 0 | 0 | 10747904 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1624 | 0 | 3670016 | 3658327 | 0 | 19647 | 696582 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 101655407 | 28275934 | 58568337 | 14811136 | 1367104 | 1253789 | 16181845 | 0 | 0 | 13828096 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 884998144 | 3670016 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1568 | 56 | 15937675807671 | 15948482723049 | 15948482824009 | 15937676076195 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 302 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 133440 | 0x7fa31f11ff00 | 0x7fa31e825880 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 25559040 | 23986176 | 259287 | 259287 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2184 | 0 | 4915200 | 4894937 | 73 | 19210 | 932830 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 22937600 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 175371565 | 17655403 | 132812482 | 24903680 | 2076848 | 1963458 | 25359078 | 0 | 0 | 23986176 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 1535115264 | 4915200 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2128 | 56 | 15937676123284 | 15948482848329 | 15948483003690 | 15937676452277 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 305 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 134912 | 0x7fa31f11fd80 | 0x7fa31e8258c0 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 13303808 | 11796480 | 161898 | 161898 | 0 | 0 | 0 | 0 | 0 | 0 | 8912896 | 0 | 0 | 0 | 0 | 1456 | 0 | 3145728 | 3135863 | 59 | 12636 | 1037523 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 101509157 | 33301417 | 55362684 | 12845056 | 1286384 | 1181643 | 15237386 | 0 | 0 | 11796480 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 754974720 | 3145728 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1400 | 56 | 15937676506216 | 15948483037450 | 15948483132491 | 15937676763020 |
| 105 | 103 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 308 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 136896 | 0x7fa31f11fc00 | 0x7fa31e825900 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 17104896 | 14548992 | 295551 | 295551 | 0 | 0 | 0 | 0 | 0 | 0 | 11796480 | 0 | 0 | 0 | 0 | 1792 | 0 | 4063232 | 4051118 | 0 | 9697 | 912270 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 206743667 | 60858370 | 129304689 | 16580608 | 2376920 | 2266169 | 29316925 | 0 | 0 | 14548992 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 931135488 | 4063232 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1736 | 56 | 15937676808199 | 15948483157611 | 15948483336332 | 15937677162301 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 311 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 138880 | 0x7fa31f11fa80 | 0x7fa31e825940 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 16252928 | 14811136 | 296411 | 296411 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1792 | 0 | 3932160 | 3922168 | 56 | 10714 | 455453 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 11796480 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 216118560 | 44392370 | 156063086 | 15663104 | 2360600 | 2252377 | 29162169 | 0 | 0 | 14811136 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 947912704 | 3932160 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1736 | 56 | 15937677209130 | 15948483361932 | 15948483541453 | 15937677555902 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 314 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 140864 | 0x7fa31f11f900 | 0x7fa31e825980 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 16449536 | 14876672 | 179271 | 179271 | 0 | 0 | 11796480 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1792 | 0 | 3932160 | 3915250 | 56 | 20093 | 458049 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 103434055 | 24339365 | 63234978 | 15859712 | 1441144 | 1330655 | 17163132 | 0 | 0 | 14876672 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 952107008 | 3932160 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1736 | 56 | 15937677601751 | 15948483565293 | 15948483672333 | 15937677876305 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 317 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 143616 | 0x7fa31f11f780 | 0x7fa31e8259c0 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 27656192 | 26083328 | 280391 | 280391 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2408 | 0 | 5308416 | 5287049 | 57 | 17737 | 461062 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 25034752 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 186295203 | 18302817 | 140991554 | 27000832 | 2248520 | 2129429 | 27499631 | 0 | 0 | 26083328 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 1669332992 | 5308416 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2352 | 56 | 15937677920524 | 15948483695693 | 15948483866094 | 15937678268686 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 320 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 145344 | 0x7fa31f11f600 | 0x7fa31e825a00 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 14090240 | 12582912 | 162313 | 162313 | 0 | 0 | 0 | 0 | 0 | 0 | 9699328 | 0 | 0 | 0 | 0 | 1568 | 0 | 3342336 | 3333182 | 112 | 10009 | 1035987 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 101375979 | 28187880 | 59556611 | 13631488 | 1298128 | 1188498 | 15318171 | 0 | 0 | 12582912 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 805306368 | 3342336 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1512 | 56 | 15937678322695 | 15948483898094 | 15948483994095 | 15937678581550 |
| 110 | 108 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 323 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 147584 | 0x7fa32177c480 | 0x7fa31e825a40 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 18219008 | 15597568 | 296565 | 296565 | 0 | 0 | 0 | 0 | 0 | 0 | 12845056 | 0 | 0 | 0 | 0 | 1960 | 0 | 4325376 | 4309404 | 56 | 16363 | 451919 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 201989093 | 42627902 | 141732007 | 17629184 | 2373120 | 2261310 | 29265176 | 0 | 0 | 15597568 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 998244352 | 4325376 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1904 | 56 | 15937678627679 | 15948484018575 | 15948484200496 | 15937678981201 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 326 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 149568 | 0x7fa32177c300 | 0x7fa31e825a80 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 17301504 | 15859712 | 295797 | 295797 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1904 | 0 | 4194304 | 4181699 | 112 | 12629 | 695374 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 12845056 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 200136156 | 43531652 | 139892824 | 16711680 | 2375472 | 2261287 | 29241770 | 0 | 0 | 15859712 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 1015021568 | 4194304 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1848 | 56 | 15937679027280 | 15948484223696 | 15948484406897 | 15937679379962 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 329 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 151552 | 0x7fa32177c180 | 0x7fa31e825ac0 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 17498112 | 15925248 | 187110 | 187110 | 0 | 0 | 12845056 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1848 | 0 | 4194304 | 4179459 | 0 | 16021 | 900503 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 115676374 | 21189355 | 77578731 | 16908288 | 1494688 | 1381243 | 17803592 | 0 | 0 | 15925248 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 1019215872 | 4194304 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1792 | 56 | 15937679426051 | 15948484431377 | 15948484543058 | 15937679704775 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 332 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 154304 | 0x7fa32177c000 | 0x7fa31e825b00 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 29753344 | 28180480 | 301032 | 301032 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2520 | 0 | 5701632 | 5682354 | 56 | 19140 | 868948 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 27131904 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 211043978 | 17396603 | 164549391 | 29097984 | 2402560 | 2289128 | 29525600 | 0 | 0 | 28180480 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 1803550720 | 5701632 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2464 | 56 | 15937679751154 | 15948484567378 | 15948484748499 | 15937680104006 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 335 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 156288 | 0x7fa31f11fe80 | 0x7fa31e825b40 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 15663104 | 14155776 | 174076 | 174076 | 0 | 0 | 0 | 0 | 0 | 0 | 11272192 | 0 | 0 | 0 | 0 | 1680 | 0 | 3735552 | 3721243 | 1 | 16848 | 1024535 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 103418986 | 23537562 | 64677072 | 15204352 | 1372544 | 1262405 | 16282562 | 0 | 0 | 14155776 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 905969664 | 3735552 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1624 | 56 | 15937680157575 | 15948484782099 | 15948484884019 | 15937680421799 |
| 115 | 113 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 338 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 158784 | 0x7fa31f11fd00 | 0x7fa31e825b80 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 20316160 | 17694720 | 302654 | 302654 | 0 | 0 | 0 | 0 | 0 | 0 | 14942208 | 0 | 0 | 0 | 0 | 2184 | 0 | 4849664 | 4828603 | 142 | 17820 | 455357 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 191210546 | 66313736 | 105170474 | 19726336 | 2401664 | 2261147 | 29214505 | 0 | 0 | 17694720 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 1132462080 | 4849664 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2128 | 56 | 15937680468568 | 15948484908659 | 15948485094900 | 15937680822750 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 341 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 161024 | 0x7fa31f11fb80 | 0x7fa31e825bc0 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 19398656 | 17956864 | 296448 | 296448 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2128 | 0 | 4718592 | 4701418 | 112 | 16080 | 454691 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 14942208 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 200388263 | 56773947 | 124805484 | 18808832 | 2385488 | 2254196 | 29119240 | 0 | 0 | 17956864 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 1149239296 | 4718592 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2072 | 56 | 15937680870749 | 15948485118581 | 15948485302261 | 15937681222251 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 344 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 163264 | 0x7fa31f11fa00 | 0x7fa31e825c00 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 19595264 | 18022400 | 205896 | 205896 | 0 | 0 | 14942208 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2072 | 0 | 4718592 | 4698704 | 0 | 22225 | 879201 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 131125021 | 20249640 | 91869941 | 19005440 | 1650600 | 1536082 | 19811366 | 0 | 0 | 18022400 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 1153433600 | 4718592 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2016 | 56 | 15937681268010 | 15948485327702 | 15948485449622 | 15937681559983 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 347 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 166528 | 0x7fa31f11f880 | 0x7fa31e825c40 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 33947648 | 32374784 | 340810 | 340810 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2856 | 0 | 6488064 | 6463998 | 57 | 25259 | 876137 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 31326208 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 240101275 | 17433417 | 189375570 | 33292288 | 2729816 | 2611425 | 33717008 | 0 | 0 | 32374784 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 2071986176 | 6488064 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2800 | 56 | 15937681604533 | 15948485475222 | 15948485681623 | 15937682004974 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 350 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 168512 | 0x7fa31f11f700 | 0x7fa31e825c80 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 17235968 | 15728640 | 183756 | 183756 | 0 | 0 | 0 | 0 | 0 | 0 | 12845056 | 0 | 0 | 0 | 0 | 1904 | 0 | 4128768 | 4112508 | 76 | 14325 | 1031172 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 112394187 | 18992898 | 76624073 | 16777216 | 1469608 | 1355768 | 17490071 | 0 | 0 | 15728640 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 1006632960 | 4128768 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1848 | 56 | 15937682040403 | 15948485729624 | 15948485840344 | 15937682339786 |
| 120 | 118 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 353 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 171264 | 0x7fa32177c580 | 0x7fa31e825cc0 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 22347776 | 19791872 | 297321 | 297321 | 0 | 0 | 0 | 0 | 0 | 0 | 17039360 | 0 | 0 | 0 | 0 | 2352 | 0 | 5373952 | 5349686 | 56 | 18262 | 902971 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 165714221 | 65721649 | 78169084 | 21823488 | 2369096 | 2238134 | 28916960 | 0 | 0 | 19791872 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 1266679808 | 5373952 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2296 | 56 | 15937682385955 | 15948485866264 | 15948486050425 | 15937682742417 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 356 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 173760 | 0x7fa32177c400 | 0x7fa31e825d00 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 21495808 | 20054016 | 298717 | 298717 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2352 | 0 | 5242880 | 5225646 | 112 | 22208 | 454500 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 17039360 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 188871574 | 68466768 | 99498822 | 20905984 | 2382280 | 2254876 | 29132279 | 0 | 0 | 20054016 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 1283457024 | 5242880 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2296 | 56 | 15937682789616 | 15948486074905 | 15948486262106 | 15937683141778 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 359 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 176256 | 0x7fa32177c280 | 0x7fa31e825d40 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 21692416 | 20119552 | 226457 | 226457 | 0 | 0 | 17039360 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2296 | 0 | 5242880 | 5221331 | 0 | 21251 | 875375 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 148655320 | 16929581 | 110623147 | 21102592 | 1810904 | 1693660 | 21820273 | 0 | 0 | 20119552 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 1287651328 | 5242880 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2240 | 56 | 15937683187937 | 15948486286106 | 15948486420987 | 15937683492960 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 362 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 179776 | 0x7fa32177c100 | 0x7fa31e825d80 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 38141952 | 36569088 | 380593 | 380593 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3192 | 0 | 7274496 | 7244367 | 75 | 30298 | 916757 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 35520512 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 272499818 | 17272869 | 217740357 | 37486592 | 3054488 | 2934914 | 37871617 | 0 | 0 | 36569088 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 2340421632 | 7274496 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3136 | 56 | 15937683539769 | 15948486444507 | 15948486676508 | 15937683984929 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 365 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 182272 | 0x7fa31f11ff80 | 0x7fa31e825dc0 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 20381696 | 18874368 | 211099 | 211099 | 0 | 0 | 0 | 0 | 0 | 0 | 15990784 | 0 | 0 | 0 | 0 | 2184 | 0 | 4915200 | 4894543 | 99 | 19363 | 1028858 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 133230924 | 14850569 | 98457411 | 19922944 | 1692392 | 1577876 | 20367068 | 0 | 0 | 18874368 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 1207959552 | 4915200 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2128 | 56 | 15937684005959 | 15948486749949 | 15948486876989 | 15937684304062 |
| 125 | 123 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 368 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 185536 | 0x7fa31f11fe00 | 0x7fa31e825e00 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 26607616 | 23986176 | 307687 | 307687 | 0 | 0 | 0 | 0 | 0 | 0 | 21233664 | 0 | 0 | 0 | 0 | 2856 | 0 | 6422528 | 6395081 | 147 | 30198 | 452807 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 177132073 | 47264488 | 103849793 | 26017792 | 2476896 | 2353473 | 30319381 | 0 | 0 | 23986176 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 1535115264 | 6422528 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2800 | 56 | 15937684349581 | 15948486901149 | 15948487091070 | 15937684761362 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 371 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 188544 | 0x7fa31f11fc80 | 0x7fa31e825e40 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 25690112 | 24248320 | 309530 | 309530 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2800 | 0 | 6291456 | 6263086 | 57 | 38024 | 459423 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 21233664 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 177466333 | 51025514 | 101340531 | 25100288 | 2476920 | 2339727 | 30157995 | 0 | 0 | 24248320 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 1551892480 | 6291456 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2744 | 56 | 15937684772362 | 15948487115390 | 15948487310911 | 15937685159633 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 374 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 191552 | 0x7fa31f11fb00 | 0x7fa31e825e80 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 25886720 | 24313856 | 266102 | 266102 | 0 | 0 | 21233664 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2744 | 0 | 6291456 | 6264975 | 56 | 30741 | 889764 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 182869141 | 17779108 | 139793137 | 25296896 | 2142040 | 2030205 | 26187672 | 0 | 0 | 24313856 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 1556086784 | 6291456 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2688 | 56 | 15937685190012 | 15948487336672 | 15948487497152 | 15937685522905 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 377 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 195840 | 0x7fa31f11f980 | 0x7fa31e825ec0 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 46596096 | 45023232 | 462771 | 462771 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3808 | 0 | 8847360 | 8811132 | 60 | 43869 | 880951 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 43974656 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 341838999 | 17329847 | 278568416 | 45940736 | 3690056 | 3579258 | 46301578 | 0 | 0 | 45023232 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 2881486848 | 8847360 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3752 | 56 | 15937685568704 | 15948487521632 | 15948487805474 | 15937686041233 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 380 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 198592 | 0x7fa31f11f800 | 0x7fa31e825f00 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 23461888 | 22020096 | 242835 | 242835 | 0 | 0 | 0 | 0 | 0 | 0 | 19136512 | 0 | 0 | 0 | 0 | 2576 | 0 | 5701632 | 5671486 | 145 | 25942 | 1014828 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 150661670 | 14866757 | 112726241 | 23068672 | 1942760 | 1834203 | 23698713 | 0 | 0 | 22020096 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 1409286144 | 5701632 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2520 | 56 | 15937686085282 | 15948487856034 | 15948488005155 | 15937686414165 |
| 130 | 128 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 383 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 202368 | 0x7fa31f11f680 | 0x7fa31e825f40 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 30801920 | 28180480 | 338886 | 338886 | 0 | 0 | 0 | 0 | 0 | 0 | 25427968 | 0 | 0 | 0 | 0 | 3248 | 0 | 7471104 | 7435975 | 133 | 31848 | 1019101 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 218559830 | 41645304 | 146702430 | 30212096 | 2667536 | 2546643 | 32808988 | 0 | 0 | 28180480 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 1803550720 | 7471104 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3192 | 56 | 15937686460204 | 15948488028995 | 15948488236516 | 15937686887705 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 386 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 205888 | 0x7fa32177c500 | 0x7fa31e825f80 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 29884416 | 28442624 | 329586 | 329586 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3248 | 0 | 7340032 | 7305922 | 112 | 32178 | 558179 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 25427968 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 191453940 | 40123434 | 122035914 | 29294592 | 2643472 | 2523166 | 32482764 | 0 | 0 | 28442624 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 1820327936 | 7340032 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3192 | 56 | 15937686898454 | 15948488277796 | 15948488486277 | 15937687335415 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 389 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 209408 | 0x7fa32177c380 | 0x7fa31e825fc0 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 30081024 | 28508160 | 307086 | 307086 | 0 | 0 | 25427968 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3192 | 0 | 7340032 | 7306996 | 56 | 38497 | 887147 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 211706855 | 18565428 | 163650227 | 29491200 | 2457152 | 2344679 | 30274713 | 0 | 0 | 28508160 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 1824522240 | 7340032 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3136 | 56 | 15937687347125 | 15948488523557 | 15948488709638 | 15937687715596 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 392 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 214464 | 0x7fa32177c200 | 0x7fa31e826000 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 54984704 | 53411840 | 542238 | 542238 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4480 | 0 | 10420224 | 10375256 | 68 | 52971 | 898689 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 52363264 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 402599357 | 17669283 | 330600730 | 54329344 | 4339352 | 4221534 | 54678054 | 0 | 0 | 53411840 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 3418357760 | 10420224 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4424 | 56 | 15937687762765 | 15948488733798 | 15948489068200 | 15937688306043 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 395 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 217728 | 0x7fa32177c080 | 0x7fa31e826040 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 26673152 | 25165824 | 273098 | 273098 | 0 | 0 | 0 | 0 | 0 | 0 | 22282240 | 0 | 0 | 0 | 0 | 2912 | 0 | 6488064 | 6455823 | 196 | 31891 | 1047621 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 174663594 | 15390803 | 133058391 | 26214400 | 2180120 | 2069995 | 26748792 | 0 | 0 | 25165824 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 1610612736 | 6488064 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2856 | 56 | 15937688327023 | 15948489110440 | 15948489278121 | 15937688671855 |
| 135 | 133 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 398 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 222016 | 0x7fa31f11ff00 | 0x7fa31e826080 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 34996224 | 32374784 | 366562 | 366562 | 0 | 0 | 0 | 0 | 0 | 0 | 29622272 | 0 | 0 | 0 | 0 | 3752 | 0 | 8519680 | 8474116 | 186 | 49714 | 1035670 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 239104611 | 35746019 | 168952192 | 34406400 | 2929920 | 2811983 | 36177885 | 0 | 0 | 32374784 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 2071986176 | 8519680 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3696 | 56 | 15937688718524 | 15948489302441 | 15948489529482 | 15937689161944 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 401 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 226048 | 0x7fa31f11fd80 | 0x7fa31e8260c0 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 34078720 | 32636928 | 365387 | 365387 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3696 | 0 | 8388608 | 8347250 | 113 | 49830 | 677784 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 29622272 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 245684460 | 38702808 | 173492756 | 33488896 | 2916368 | 2806250 | 36150941 | 0 | 0 | 32636928 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 2088763392 | 8388608 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3640 | 56 | 15937689173774 | 15948489563243 | 15948489793164 | 15937689619334 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 404 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 230080 | 0x7fa31f11fc00 | 0x7fa31e826100 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 34275328 | 32702464 | 347572 | 347572 | 0 | 0 | 29622272 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3640 | 0 | 8388608 | 8343931 | 56 | 40525 | 893952 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 248722343 | 19167970 | 195868869 | 33685504 | 2785248 | 2671410 | 34445179 | 0 | 0 | 32702464 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 2092957696 | 8388608 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3584 | 56 | 15937689630864 | 15948489828364 | 15948490039565 | 15937690036385 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 407 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 235904 | 0x7fa31f11fa80 | 0x7fa31e826140 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 63373312 | 61800448 | 624735 | 624735 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5152 | 0 | 11993088 | 11941481 | 56 | 52238 | 906597 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 60751872 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 474031057 | 18020385 | 393292720 | 62717952 | 5000000 | 4876549 | 63069587 | 0 | 0 | 61800448 | 262144 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 131072 | 3955228672 | 11993088 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5096 | 56 | 15937690066324 | 15948490075245 | 15948490461487 | 15937690681710 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 410 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 239424 | 0x7fa31f11f900 | 0x7fa31e826180 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 29818880 | 28311552 | 303157 | 303157 | 0 | 0 | 0 | 0 | 0 | 0 | 25427968 | 0 | 0 | 0 | 0 | 3248 | 0 | 7274496 | 7230466 | 173 | 41909 | 1034947 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 214735070 | 16595922 | 168779020 | 29360128 | 2432760 | 2319608 | 29919972 | 0 | 0 | 28311552 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 1811939328 | 7274496 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3192 | 56 | 15937690701870 | 15948490531247 | 15948490718128 | 15937691059642 |
| 140 | 138 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 413 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 244224 | 0x7fa31f11f780 | 0x7fa31e8261c0 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 39190528 | 36569088 | 397905 | 397905 | 0 | 0 | 0 | 0 | 0 | 0 | 33816576 | 0 | 0 | 0 | 0 | 4144 | 0 | 9568256 | 9521753 | 198 | 48781 | 1053046 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 270865451 | 31401786 | 200862961 | 38600704 | 3173032 | 3060891 | 39500982 | 0 | 0 | 36569088 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 2340421632 | 9568256 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4088 | 56 | 15937691106151 | 15948490743888 | 15948490993810 | 15937691571011 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 416 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 248768 | 0x7fa31f11f600 | 0x7fa31e826200 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 38273024 | 36831232 | 392032 | 392032 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4144 | 0 | 9437184 | 9385522 | 112 | 53376 | 455351 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 33816576 | 0 | 1507328 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 293362066 | 29450753 | 226228113 | 37683200 | 3131752 | 3018009 | 39073695 | 0 | 0 | 36831232 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 2357198848 | 9437184 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4088 | 56 | 15937691581730 | 15948491032210 | 15948491279411 | 15937692056110 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 419 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 253312 | 0x7fa32177c480 | 0x7fa31e826240 | 0 | 0 | 524288 | 524288 | 196608 | 0 | 38469632 | 36896768 | 388304 | 388304 | 0 | 0 | 33816576 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4032 | 0 | 9437184 | 9382752 | 56 | 61332 | 878419 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 277362420 | 21093526 | 218389086 | 37879808 | 3107912 | 2993075 | 38665803 | 0 | 0 | 36896768 | 327680 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 196608 | 2361393152 | 9437184 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3976 | 56 | 15937692066980 | 15948491317011 | 15948491553812 | 15937692527089 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 422 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 8 | 24 | 255552 | 0x7fa32177c300 | 0x7fa31e826280 | 0 | 0 | 524288 | 524288 | 4784128 | 0 | 81002496 | 71172096 | 719444 | 719444 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2016 | 0 | 16056320 | 16051741 | 56 | 4384 | 1039607 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 69468160 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 2162688 | 65536 | 544827572 | 83151835 | 382835929 | 78839808 | 5754864 | 5630964 | 72915912 | 0 | 0 | 71172096 | 4915200 | 0 | 2228224 | 524288 | 0 | 524288 | 131072 | 4784128 | 4555014144 | 16056320 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1960 | 56 | 15937692538689 | 15948491592693 | 15948492045655 | 15937693211464 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 425 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 259840 | 0x7fa32177c180 | 0x7fa31e8262c0 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 36110336 | 34603008 | 362851 | 362851 | 0 | 0 | 0 | 0 | 0 | 0 | 31719424 | 0 | 0 | 0 | 0 | 3920 | 0 | 8847360 | 8806604 | 205 | 42882 | 1036584 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1507328 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 241378092 | 16218598 | 189507910 | 35651584 | 2912720 | 2799598 | 36178483 | 0 | 0 | 34603008 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 2214592512 | 8847360 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3864 | 56 | 15937693231893 | 15948492091255 | 15948492317816 | 15937693667824 |
| 145 | 143 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 428 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 265664 | 0x7fa32177c000 | 0x7fa31e826300 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 47644672 | 45023232 | 470495 | 470495 | 0 | 0 | 0 | 0 | 0 | 0 | 42205184 | 0 | 0 | 0 | 0 | 5040 | 0 | 11665408 | 11589795 | 112 | 64976 | 1038601 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1572864 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 350367735 | 30341089 | 272971798 | 47054848 | 3756584 | 3640159 | 47074995 | 0 | 0 | 45023232 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 2881486848 | 11665408 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4984 | 56 | 15937693679473 | 15948492356376 | 15948492654778 | 15937694188612 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 431 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 271232 | 0x7fa31f11fe80 | 0x7fa31e826340 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 46727168 | 45285376 | 471006 | 471006 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5040 | 0 | 11468800 | 11406853 | 244 | 69782 | 722544 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 42205184 | 0 | 1572864 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 345915461 | 29759415 | 270018702 | 46137344 | 3775408 | 3665553 | 47369001 | 0 | 0 | 45285376 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 2898264064 | 11468800 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4984 | 56 | 15937694210722 | 15948492692378 | 15948492990620 | 15937694728840 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 434 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 8 | 24 | 273216 | 0x7fa31f11fd00 | 0x7fa31e826380 | 0 | 0 | 524288 | 524288 | 4849664 | 0 | 56229888 | 46333952 | 482343 | 482343 | 0 | 0 | 42205184 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1792 | 0 | 14090240 | 14085199 | 0 | 4377 | 1048833 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1900544 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 2162688 | 65536 | 357516452 | 87783803 | 215665449 | 54067200 | 3870592 | 3750614 | 48509243 | 0 | 0 | 46333952 | 4980736 | 0 | 2228224 | 524288 | 0 | 524288 | 131072 | 4849664 | 2965372928 | 14090240 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1736 | 56 | 15937694739580 | 15948493029660 | 15948493326621 | 15937695256378 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 437 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 8 | 24 | 275712 | 0x7fa31f11fb80 | 0x7fa31e8263c0 | 0 | 0 | 524288 | 524288 | 4784128 | 0 | 97779712 | 87949312 | 878675 | 878675 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2352 | 0 | 19202048 | 19195146 | 113 | 7149 | 1039877 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 86245376 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 2162688 | 65536 | 677947154 | 83416933 | 498913197 | 95617024 | 7041568 | 6927974 | 89715954 | 0 | 0 | 87949312 | 4915200 | 0 | 2228224 | 524288 | 0 | 524288 | 131072 | 4784128 | 5628755968 | 19202048 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2296 | 56 | 15937695267638 | 15948493363101 | 15948493919904 | 15937696019021 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 440 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 280768 | 0x7fa31f11fa00 | 0x7fa31e826400 | 0 | 0 | 524288 | 524288 | 262144 | 0 | 42401792 | 40960000 | 426972 | 426972 | 0 | 0 | 0 | 0 | 0 | 0 | 38010880 | 0 | 0 | 0 | 0 | 4480 | 0 | 10420224 | 10367090 | 71 | 62199 | 1041314 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1572864 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 312114544 | 18606458 | 251499510 | 42008576 | 3418336 | 3304229 | 42695745 | 0 | 0 | 40960000 | 393216 | 0 | 131072 | 524288 | 0 | 524288 | 131072 | 262144 | 2621440000 | 10420224 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4424 | 56 | 15937696056630 | 15948493962944 | 15948494226146 | 15937696515480 |
| 150 | 148 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 443 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 287616 | 0x7fa31f11f880 | 0x7fa31e826440 | 0 | 0 | 524288 | 524288 | 1179648 | 0 | 55967744 | 53411840 | 551230 | 551230 | 0 | 0 | 0 | 0 | 0 | 0 | 50593792 | 0 | 0 | 0 | 0 | 5992 | 0 | 13762560 | 13683798 | 363 | 84265 | 1047796 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1572864 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 131072 | 65536 | 399023656 | 26179383 | 317400817 | 55443456 | 4387968 | 4279821 | 55410486 | 0 | 0 | 53411840 | 1310720 | 0 | 196608 | 524288 | 0 | 524288 | 131072 | 1179648 | 3418357760 | 13762560 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5936 | 56 | 15937696543889 | 15948494268706 | 15948494619748 | 15937697084977 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 446 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 294208 | 0x7fa31f11f700 | 0x7fa31e826480 | 0 | 0 | 524288 | 524288 | 131072 | 0 | 55115776 | 53673984 | 550036 | 550036 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5936 | 0 | 13565952 | 13467838 | 451 | 88698 | 458545 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 50593792 | 0 | 1572864 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 65536 | 65536 | 414640957 | 27812580 | 332302425 | 54525952 | 4413792 | 4300039 | 55624310 | 0 | 0 | 53673984 | 196608 | 0 | 131072 | 524288 | 0 | 524288 | 65536 | 131072 | 3435134976 | 13565952 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5880 | 56 | 15937697113817 | 15948494661028 | 15948495010950 | 15937697652815 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 449 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 8 | 24 | 296960 | 0x7fa32177c580 | 0x7fa31e8264c0 | 0 | 0 | 524288 | 524288 | 3801088 | 0 | 62521344 | 54722560 | 564108 | 564108 | 0 | 0 | 50593792 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2464 | 0 | 15466496 | 15457346 | 1 | 9186 | 1039641 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1900544 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 1638400 | 65536 | 418241705 | 85475989 | 271882772 | 60882944 | 4513712 | 4391205 | 56817367 | 0 | 0 | 54722560 | 3932160 | 0 | 1703936 | 524288 | 0 | 524288 | 131072 | 3801088 | 3502243840 | 15466496 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2408 | 56 | 15937697681724 | 15948495053990 | 15948495401192 | 15937698256191 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 452 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 8 | 24 | 299968 | 0x7fa32177c400 | 0x7fa31e826500 | 0 | 0 | 524288 | 524288 | 4784128 | 0 | 114556928 | 104726528 | 1041011 | 1041011 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2688 | 0 | 22347776 | 22337683 | 112 | 10053 | 1039146 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 103022592 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 2162688 | 65536 | 792746808 | 84247509 | 596105059 | 112394240 | 8334144 | 8217860 | 106421863 | 0 | 0 | 104726528 | 4915200 | 0 | 2228224 | 524288 | 0 | 524288 | 131072 | 4784128 | 6702497792 | 22347776 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2632 | 56 | 15937698267621 | 15948495440232 | 15948496101035 | 15937699152251 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 455 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 8 | 24 | 302720 | 0x7fa32177c280 | 0x7fa31e826540 | 0 | 0 | 524288 | 524288 | 4784128 | 0 | 80871424 | 71041024 | 721404 | 721404 | 0 | 0 | 0 | 0 | 0 | 0 | 67371008 | 0 | 0 | 0 | 0 | 2464 | 0 | 20250624 | 20242251 | 112 | 7590 | 1034360 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1900544 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 2162688 | 65536 | 548988402 | 90668561 | 379611105 | 78708736 | 5771808 | 5656952 | 73211558 | 0 | 0 | 71041024 | 4915200 | 0 | 2228224 | 524288 | 0 | 524288 | 131072 | 4784128 | 4546625536 | 20250624 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2408 | 56 | 15937699171891 | 15948496148555 | 15948496595598 | 15937699831816 |
| 155 | 153 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 458 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 305472 | 0x7fa32177c100 | 0x7fa31e826580 | 0 | 0 | 524288 | 524288 | 5832704 | 0 | 82116608 | 71172096 | 721981 | 721981 | 0 | 0 | 0 | 0 | 0 | 0 | 67371008 | 0 | 0 | 0 | 0 | 2520 | 0 | 20447232 | 20437804 | 56 | 9146 | 1038431 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1900544 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 2228224 | 65536 | 541554644 | 96283761 | 365316963 | 79953920 | 5784904 | 5666483 | 73394977 | 0 | 0 | 71172096 | 5963776 | 0 | 2293760 | 524288 | 0 | 524288 | 131072 | 5832704 | 4555014144 | 20447232 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2464 | 56 | 15937699843086 | 15948496636078 | 15948497101680 | 15937700525801 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 461 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 308224 | 0x7fa31f11ff80 | 0x7fa31e8265c0 | 0 | 0 | 524288 | 524288 | 4784128 | 0 | 80805888 | 71041024 | 722713 | 722713 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2464 | 0 | 19595264 | 19587282 | 112 | 8866 | 458987 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 67371008 | 0 | 1900544 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 2162688 | 65536 | 547457973 | 98143955 | 370670818 | 78643200 | 5775160 | 5657875 | 73256048 | 0 | 0 | 71041024 | 4849664 | 0 | 2228224 | 524288 | 0 | 524288 | 65536 | 4784128 | 4546625536 | 19595264 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2408 | 56 | 15937700536901 | 15948497142320 | 15948497604403 | 15937701218226 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 464 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 8 | 24 | 310976 | 0x7fa31f11fe00 | 0x7fa31e826600 | 0 | 0 | 524288 | 524288 | 4849664 | 0 | 81395712 | 71499776 | 726146 | 726146 | 0 | 0 | 67371008 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2520 | 0 | 20381696 | 20372526 | 112 | 8844 | 1049390 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1900544 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 2162688 | 65536 | 545652151 | 91660747 | 374758380 | 79233024 | 5803208 | 5692232 | 73695410 | 0 | 0 | 71499776 | 4980736 | 0 | 2228224 | 524288 | 0 | 524288 | 131072 | 4849664 | 4575985664 | 20381696 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2464 | 56 | 15937701229925 | 15948497642483 | 15948498094165 | 15937701900350 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 467 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 8 | 24 | 313216 | 0x7fa31f11fc80 | 0x7fa31e826640 | 0 | 0 | 524288 | 524288 | 8978432 | 0 | 156499968 | 138280960 | 1367926 | 1367926 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2016 | 0 | 31522816 | 31517316 | 56 | 4668 | 1036237 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 136577024 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 4259840 | 65536 | 1064336542 | 96410368 | 815686046 | 152240128 | 10953416 | 10822717 | 140176556 | 0 | 0 | 138280960 | 9109504 | 0 | 4325376 | 524288 | 0 | 524288 | 131072 | 8978432 | 8849981440 | 31522816 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1960 | 56 | 15937701910640 | 15948498137365 | 15948499006969 | 15937703022295 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 470 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 8 | 24 | 315968 | 0x7fa31f11fb00 | 0x7fa31e826680 | 0 | 0 | 524288 | 524288 | 8978432 | 0 | 156368896 | 138149888 | 1370692 | 1370692 | 0 | 0 | 0 | 0 | 0 | 0 | 134479872 | 0 | 0 | 0 | 0 | 2464 | 0 | 38993920 | 38985923 | 112 | 8029 | 1041125 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1900544 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 4259840 | 65536 | 1078204296 | 111049927 | 815045313 | 152109056 | 10956216 | 10845020 | 140502501 | 0 | 0 | 138149888 | 9109504 | 0 | 4325376 | 524288 | 0 | 524288 | 131072 | 8978432 | 8841592832 | 38993920 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2408 | 56 | 15937703043515 | 15948499059930 | 15948499913374 | 15937704135261 |
| 160 | 158 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 473 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 318720 | 0x7fa31f11f980 | 0x7fa31e8266c0 | 0 | 0 | 524288 | 524288 | 10027008 | 0 | 157614080 | 138280960 | 1374962 | 1374962 | 0 | 0 | 0 | 0 | 0 | 0 | 134479872 | 0 | 0 | 0 | 0 | 2520 | 0 | 39124992 | 39116638 | 114 | 8561 | 1042511 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1900544 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 4325376 | 65536 | 1065894602 | 115522908 | 797017454 | 153354240 | 10995688 | 10859501 | 140686562 | 0 | 0 | 138280960 | 10158080 | 0 | 4390912 | 524288 | 0 | 524288 | 131072 | 10027008 | 8849981440 | 39124992 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2464 | 56 | 15937704146650 | 15948499962494 | 15948500847779 | 15937705276155 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 476 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 321472 | 0x7fa31f11f800 | 0x7fa31e826700 | 0 | 0 | 524288 | 524288 | 8978432 | 0 | 156303360 | 138149888 | 1370706 | 1370706 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2464 | 0 | 38469632 | 38462249 | 56 | 7606 | 662947 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 134479872 | 0 | 1900544 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 4259840 | 65536 | 1068917502 | 114722242 | 802151740 | 152043520 | 10966024 | 10844553 | 140500626 | 0 | 0 | 138149888 | 9043968 | 0 | 4325376 | 524288 | 0 | 524288 | 65536 | 8978432 | 8841592832 | 38469632 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2408 | 56 | 15937705286935 | 15948500918979 | 15948501799303 | 15937706413590 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 479 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 8 | 24 | 324224 | 0x7fa31f11f680 | 0x7fa31e826740 | 0 | 0 | 524288 | 524288 | 9043968 | 0 | 156893184 | 138608640 | 1377868 | 1377868 | 0 | 0 | 134479872 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2520 | 0 | 39059456 | 39051205 | 113 | 9106 | 1051922 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1900544 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 4259840 | 65536 | 1086768323 | 111558686 | 822576293 | 152633344 | 11016744 | 10878598 | 140971567 | 0 | 0 | 138608640 | 9175040 | 0 | 4325376 | 524288 | 0 | 524288 | 131072 | 9043968 | 8870952960 | 39059456 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2464 | 56 | 15937706424779 | 15948501868744 | 15948502728588 | 15937707536145 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 482 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 8 | 24 | 326464 | 0x7fa32177c500 | 0x7fa31e826780 | 0 | 0 | 524288 | 524288 | 17367040 | 0 | 307494912 | 272498688 | 2662822 | 2662822 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2016 | 0 | 60489728 | 60484369 | 112 | 4770 | 1033692 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 270794752 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 8454144 | 65536 | 2129360719 | 117854965 | 1712464986 | 299040768 | 21288208 | 21179631 | 274517742 | 0 | 0 | 272498688 | 17498112 | 0 | 8519680 | 524288 | 0 | 524288 | 131072 | 17367040 | 17439916032 | 60489728 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1960 | 56 | 15937707546685 | 15948502796908 | 15948504496117 | 15937709493501 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 485 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 8 | 24 | 329216 | 0x7fa32177c380 | 0x7fa31e8267c0 | 0 | 0 | 524288 | 524288 | 17367040 | 0 | 307363840 | 272367616 | 2671582 | 2671582 | 0 | 0 | 0 | 0 | 0 | 0 | 268697600 | 0 | 0 | 0 | 0 | 2464 | 0 | 77266944 | 77258582 | 56 | 8123 | 1036717 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1900544 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 8454144 | 65536 | 2127450462 | 149855318 | 1678685448 | 298909696 | 21363664 | 21224830 | 275033950 | 0 | 0 | 272367616 | 17498112 | 0 | 8519680 | 524288 | 0 | 524288 | 131072 | 17367040 | 17431527424 | 77266944 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2408 | 56 | 15937709512221 | 15948504570517 | 15948506234845 | 15937711437108 |
| 165 | 163 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 488 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 331968 | 0x7fa32177c200 | 0x7fa31e826800 | 0 | 0 | 524288 | 524288 | 18415616 | 0 | 308609024 | 272498688 | 2669510 | 2669510 | 0 | 0 | 0 | 0 | 0 | 0 | 268697600 | 0 | 0 | 0 | 0 | 2520 | 0 | 77398016 | 77389972 | 113 | 8039 | 1013687 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 1900544 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 8519680 | 65536 | 2126174231 | 154218401 | 1671800950 | 300154880 | 21354272 | 21237916 | 275201020 | 0 | 0 | 272498688 | 18546688 | 0 | 8585216 | 524288 | 0 | 524288 | 131072 | 18415616 | 17439916032 | 77398016 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2464 | 56 | 15937711449788 | 15948506329726 | 15948508055334 | 15937713444503 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 491 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 12 | 24 | 334720 | 0x7fa32177c080 | 0x7fa31e826840 | 0 | 0 | 524288 | 524288 | 17367040 | 0 | 307298304 | 272367616 | 2669900 | 2669900 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2464 | 0 | 76218368 | 76210599 | 113 | 7540 | 447348 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 0 | 0 | 268697600 | 0 | 1900544 | 458752 | 65536 | 524288 | 0 | 0 | 0 | 8454144 | 65536 | 2117547539 | 150427118 | 1668276261 | 298844160 | 21373504 | 21227739 | 275066859 | 0 | 0 | 272367616 | 17432576 | 0 | 8519680 | 524288 | 0 | 524288 | 65536 | 17367040 | 17431527424 | 76218368 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 131072 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2408 | 56 | 15937713456073 | 15948508152775 | 15948509868943 | 15937715437169 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 494 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 8 | 24 | 337472 | 0x7fa31f11ff00 | 0x7fa31e826880 | 0 | 0 | 524288 | 524288 | 17432576 | 0 | 307888128 | 272826368 | 2673542 | 2673542 | 0 | 0 | 268697600 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2520 | 0 | 77332480 | 77324088 | 57 | 8670 | 1017295 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 1900544 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 8454144 | 65536 | 2118854575 | 149731038 | 1669689553 | 299433984 | 21382528 | 21259816 | 275484754 | 0 | 0 | 272826368 | 17563648 | 0 | 8519680 | 524288 | 0 | 524288 | 131072 | 17432576 | 17460887552 | 77332480 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2464 | 56 | 15937715449209 | 15948509958064 | 15948511632632 | 15937717393236 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 497 | 140304 | 140304 | 4194304 | 256 | 0 | 0 | 8 | 24 | 0 | 0x7fa31f11fd80 | 0x7fa31e8268c0 | 0 | 0 | 524288 | 524288 | 34144256 | 0 | 609484800 | 540934144 | 5255932 | 5255932 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2016 | 0 | 120258560 | 120252935 | 112 | 5386 | 1042622 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 0 | 0 | 0 | 0 | 539230208 | 458752 | 131072 | 524288 | 0 | 0 | 0 | 16842752 | 65536 | 4228948327 | 168207188 | 3468099091 | 592642048 | 42071600 | 41926953 | 543380837 | 0 | 0 | 540934144 | 34275328 | 0 | 16908288 | 524288 | 0 | 524288 | 131072 | 34144256 | 34619785216 | 120258560 | 0 | 0 | 0 | 65536 | 65536 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 262144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1960 | 56 | 15937717404635 | 15948511736633 | 15948515092969 | 15937721038114 |