90 KiB
90 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | SQ_CYCLES | SQ_BUSY_CYCLES | SQ_BUSY_CU_CYCLES | SQ_WAVES | SQ_WAVE_CYCLES | GRBM_COUNT | GRBM_GUI_ACTIVE | TCP_GATE_EN1_sum | TCP_GATE_EN2_sum | TCP_TD_TCP_STALL_CYCLES_sum | TCP_TCR_TCP_STALL_CYCLES_sum | TCP_READ_TAGCONFLICT_STALL_CYCLES_sum | TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum | TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum | TCP_TA_TCP_STATE_READ_sum | TCP_VOLATILE_sum | TCP_TOTAL_ACCESSES_sum | TCP_TOTAL_READ_sum | TCP_TOTAL_WRITE_sum | TCP_TOTAL_ATOMIC_WITH_RET_sum | TCP_TOTAL_ATOMIC_WITHOUT_RET_sum | TCP_TOTAL_WRITEBACK_INVALIDATES_sum | TCP_TOTAL_CACHE_ACCESSES_sum | TCP_UTCL1_TRANSLATION_MISS_sum | TCP_UTCL1_TRANSLATION_HIT_sum | TCP_UTCL1_PERMISSION_MISS_sum | TCP_UTCL1_REQUEST_sum | TCP_TCP_LATENCY_sum | TCP_TCC_READ_REQ_LATENCY_sum | TCP_TCC_WRITE_REQ_LATENCY_sum | TCP_TCC_READ_REQ_sum | TCP_TCC_WRITE_REQ_sum | TCP_TCC_ATOMIC_WITH_RET_REQ_sum | TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum | TCP_TCC_NC_READ_REQ_sum | TCP_TCC_NC_WRITE_REQ_sum | TCP_TCC_NC_ATOMIC_REQ_sum | TCP_TCC_UC_READ_REQ_sum | TCP_TCC_UC_WRITE_REQ_sum | TCP_TCC_UC_ATOMIC_REQ_sum | TCP_TCC_CC_READ_REQ_sum | TCP_TCC_CC_WRITE_REQ_sum | TCP_TCC_CC_ATOMIC_REQ_sum | TCP_TCC_RW_READ_REQ_sum | TCP_TCC_RW_WRITE_REQ_sum | TCP_TCC_RW_ATOMIC_REQ_sum | TCP_PENDING_STALL_CYCLES_sum | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBufferAligned.kd | 0 | 0 | 0 | 152567 | 152567 | 33554432 | 256 | 0 | 0 | 4 | 32 | 4160 | 0x0 | 0x7f7117c04280 | 3043368 | 2955630 | 38400365 | 524288 | 238477969 | 380420 | 380420 | 38664982.0 | 37830227.0 | 11.0 | 4089548.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 0.0 | 33554432.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 13312.0 | 8242176.0 | 0.0 | 8388608.0 | 314404782.0 | 0.0 | 1469333319.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 19094396.0 | 16255303836302 | 16263272627979 | 16263272865101 | 16255451542868 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 152567 | 152567 | 32768 | 256 | 0 | 0 | 12 | 24 | 13888 | 0x0 | 0x7f7117c23f80 | 208968 | 111356 | 1076857 | 512 | 1305726 | 26120 | 26120 | 1683791.0 | 192332.0 | 180.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4096.0 | 65536.0 | 65536.0 | 65536.0 | 0.0 | 0.0 | 0.0 | 104.0 | 16384.0 | 104.0 | 15240.0 | 0.0 | 16384.0 | 7508346.0 | 8929386.0 | 0.0 | 8192.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 8192.0 | 0.0 | 0.0 | 94902.0 | 16255457325460 | 16263277888332 | 16263277896172 | 16255457561965 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 5 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 14336 | 0x7f713e388380 | 0x7f7117c23fc0 | 1363064 | 1236158 | 15988066 | 65536 | 87270038 | 170382 | 170382 | 16306243.0 | 14590160.0 | 24287.0 | 807059.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 208.0 | 2097152.0 | 6820.0 | 2025717.0 | 0.0 | 2097152.0 | 991611334.0 | 2296375566.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 11623527.0 | 16255458107063 | 16263277967853 | 16263278060333 | 16255458436986 |
| 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 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15040 | 0x7f713e388200 | 0x7f7117c24000 | 2477960 | 2373950 | 30729911 | 65536 | 226589247 | 309744 | 309744 | 31097539.0 | 29868130.0 | 0.0 | 1089111.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 12997.0 | 8246529.0 | 0.0 | 8388608.0 | 881353585.0 | 3772935906.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 20746150.0 | 16255458980164 | 16263278108814 | 16263278289295 | 16255459559411 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 11 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15488 | 0x7f713e388080 | 0x7f7117c24040 | 2523640 | 2391060 | 30963424 | 65536 | 229495576 | 315454 | 315454 | 31320021.0 | 30067789.0 | 0.0 | 920217.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 12950.0 | 8246849.0 | 0.0 | 8388608.0 | 859158811.0 | 3902746807.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 20801879.0 | 16255460094889 | 16263278316495 | 16263278497296 | 16255460515060 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 14 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 15936 | 0x7f713c149f00 | 0x7f7117c24080 | 1326928 | 1225093 | 15833666 | 65536 | 99780449 | 165865 | 165865 | 16162411.0 | 14968225.0 | 23381.0 | 1019483.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6647.0 | 2027510.0 | 0.0 | 2097152.0 | 1033272702.0 | 2219541221.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 12323012.0 | 16255461051998 | 16263278522736 | 16263278615377 | 16255461489429 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 17 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 16384 | 0x7f713c149d80 | 0x7f7117c240c0 | 1318696 | 1214938 | 15703890 | 65536 | 91784424 | 164836 | 164836 | 16030357.0 | 14877356.0 | 22417.0 | 1487286.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 208.0 | 2097152.0 | 6733.0 | 2026987.0 | 0.0 | 2097152.0 | 1007611968.0 | 2267418905.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 11710975.0 | 16255462024637 | 16263278642097 | 16263278733618 | 16255462497646 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 20 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 17088 | 0x7f713c149c00 | 0x7f7117c24100 | 1380568 | 1262082 | 16335804 | 65536 | 111140537 | 172570 | 172570 | 16643255.0 | 14222276.0 | 24768.0 | 473106.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6650.0 | 2029077.0 | 0.0 | 2097152.0 | 1030975795.0 | 2352429265.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 11665263.0 | 16255463047054 | 16263278777458 | 16263278869138 | 16255463376967 |
| 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 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 16 | 24 | 17792 | 0x7f713c149a80 | 0x7f7117c24140 | 2480808 | 2377420 | 30804721 | 65536 | 232495777 | 310100 | 310100 | 31142571.0 | 29928769.0 | 0.0 | 823150.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 208.0 | 8388608.0 | 12945.0 | 8247224.0 | 0.0 | 8388608.0 | 871615518.0 | 3718009728.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 21035836.0 | 16255463914005 | 16263278896979 | 16263279076820 | 16255464452703 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 26 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 16 | 24 | 18496 | 0x7f713c149900 | 0x7f7117c24180 | 2509880 | 2385476 | 30894571 | 65536 | 226573743 | 313734 | 313734 | 31247325.0 | 30007207.0 | 0.0 | 952258.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 12454.0 | 8252439.0 | 0.0 | 8388608.0 | 872102066.0 | 3958396847.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 20247728.0 | 16255464986591 | 16263279108980 | 16263279288821 | 16255465390992 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 29 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19200 | 0x7f713c149780 | 0x7f7117c241c0 | 1312896 | 1207992 | 15633806 | 65536 | 101377157 | 164111 | 164111 | 15940098.0 | 14709143.0 | 24884.0 | 714406.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6650.0 | 2059917.0 | 0.0 | 2097152.0 | 1009044555.0 | 2248538592.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 11586643.0 | 16255465928150 | 16263279321941 | 16263279414102 | 16255466332611 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 32 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19904 | 0x7f713c149600 | 0x7f7117c24200 | 1313752 | 1210031 | 15659193 | 65536 | 103690213 | 164218 | 164218 | 15966683.0 | 14789204.0 | 22939.0 | 1255611.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6469.0 | 2057333.0 | 0.0 | 2097152.0 | 1014725345.0 | 2283944742.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 12279931.0 | 16255466867629 | 16263279453302 | 16263279545303 | 16255467326319 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 35 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 20608 | 0x7f713e388480 | 0x7f7117c24240 | 1359784 | 1238327 | 16032697 | 65536 | 115795821 | 169972 | 169972 | 16334453.0 | 14939583.0 | 21948.0 | 1257939.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6645.0 | 2030206.0 | 0.0 | 2097152.0 | 1034110817.0 | 2191531514.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 12175219.0 | 16255467869427 | 16263279579383 | 16263279670904 | 16255468192690 |
| 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 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 16 | 24 | 21312 | 0x7f713e388300 | 0x7f7117c24280 | 2474328 | 2365972 | 30660866 | 65536 | 231295818 | 309290 | 309290 | 30993955.0 | 29788585.0 | 0.0 | 820773.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 208.0 | 8388608.0 | 12948.0 | 8247119.0 | 0.0 | 8388608.0 | 859467216.0 | 3869757729.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 20691554.0 | 16255468730209 | 16263279707064 | 16263279888185 | 16255469225338 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 41 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22016 | 0x7f713e388180 | 0x7f7117c242c0 | 2448040 | 2346470 | 30405643 | 65536 | 221149773 | 306004 | 306004 | 30740325.0 | 29526269.0 | 0.0 | 1021976.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 208.0 | 8388608.0 | 12447.0 | 8252458.0 | 0.0 | 8388608.0 | 875087505.0 | 3938750552.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 20796877.0 | 16255469762176 | 16263279928345 | 16263280107066 | 16255470242165 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 44 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22720 | 0x7f713e388000 | 0x7f7117c24300 | 1316608 | 1212994 | 15687125 | 65536 | 106156031 | 164575 | 164575 | 16005033.0 | 14796790.0 | 22978.0 | 1178876.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 208.0 | 2097152.0 | 6645.0 | 2059182.0 | 0.0 | 2097152.0 | 1040110475.0 | 2224834090.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 11743162.0 | 16255470780333 | 16263280135707 | 16263280228027 | 16255471175305 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 47 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 23424 | 0x7f713c149e80 | 0x7f7117c24340 | 1320336 | 1211930 | 15692462 | 65536 | 113767757 | 165041 | 165041 | 15991175.0 | 14803430.0 | 22199.0 | 1362601.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6640.0 | 2031344.0 | 0.0 | 2097152.0 | 1040765405.0 | 2209028144.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 11633200.0 | 16255471710903 | 16263280259067 | 16263280350748 | 16255472110814 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 50 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 24128 | 0x7f713c149d00 | 0x7f7117c24380 | 1320752 | 1212514 | 15696609 | 65536 | 111049769 | 165093 | 165093 | 15999027.0 | 14829177.0 | 22245.0 | 1444267.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 208.0 | 2097152.0 | 6605.0 | 2029915.0 | 0.0 | 2097152.0 | 1027477418.0 | 2330372762.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 12176440.0 | 16255472654132 | 16263280384988 | 16263280476669 | 16255473063803 |
| 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 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 16 | 24 | 24832 | 0x7f713c149b80 | 0x7f7117c243c0 | 2482352 | 2375252 | 30769269 | 65536 | 231744758 | 310293 | 310293 | 31114361.0 | 29850518.0 | 0.0 | 845283.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 12854.0 | 8248206.0 | 0.0 | 8388608.0 | 893875527.0 | 3657928321.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 20670752.0 | 16255473599591 | 16263280505309 | 16263280685630 | 16255474092450 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 56 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 16 | 24 | 25536 | 0x7f713c149a00 | 0x7f7117c24400 | 2439000 | 2338017 | 30300492 | 65536 | 220408171 | 304874 | 304874 | 30630163.0 | 29459030.0 | 0.0 | 859713.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 208.0 | 8388608.0 | 12576.0 | 8251175.0 | 0.0 | 8388608.0 | 877284230.0 | 3977014695.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 20695046.0 | 16255474629308 | 16263280735070 | 16263280913952 | 16255475110747 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 59 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26240 | 0x7f713c149880 | 0x7f7117c24440 | 1319448 | 1217313 | 15755267 | 65536 | 107505758 | 164930 | 164930 | 16061089.0 | 14843758.0 | 20874.0 | 1775573.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6647.0 | 2031240.0 | 0.0 | 2097152.0 | 1027033606.0 | 2270008447.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 12245966.0 | 16255475646386 | 16263280960032 | 16263281052513 | 16255476030917 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 62 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26944 | 0x7f713c149700 | 0x7f7117c24480 | 1304472 | 1203300 | 15564646 | 65536 | 107560526 | 163058 | 163058 | 15879063.0 | 14673297.0 | 24415.0 | 818286.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6625.0 | 2030429.0 | 0.0 | 2097152.0 | 1017675973.0 | 2270134028.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 12147736.0 | 16255476566985 | 16263281080993 | 16263281172833 | 16255476950237 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 65 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 27648 | 0x7f713e388580 | 0x7f7117c244c0 | 1296336 | 1194290 | 15457344 | 65536 | 109742117 | 162041 | 162041 | 15762037.0 | 14636726.0 | 23788.0 | 914789.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 208.0 | 2097152.0 | 6641.0 | 2032239.0 | 0.0 | 2097152.0 | 1028766683.0 | 2270603673.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 12131650.0 | 16255477493595 | 16263281206914 | 16263281297954 | 16255477903806 |
| 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 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 16 | 24 | 28608 | 0x7f713e388400 | 0x7f7117c24500 | 2468440 | 2360376 | 30592660 | 65536 | 229923124 | 308554 | 308554 | 30921103.0 | 29702427.0 | 0.0 | 617191.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 12937.0 | 8247286.0 | 0.0 | 8388608.0 | 884402468.0 | 3640006591.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 20607047.0 | 16255478440794 | 16263281322914 | 16263281502115 | 16255478920663 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 71 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 16 | 24 | 29312 | 0x7f713e388280 | 0x7f7117c24540 | 2450392 | 2345023 | 30402361 | 65536 | 223538009 | 306298 | 306298 | 30721605.0 | 29521136.0 | 0.0 | 948989.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 12479.0 | 8252480.0 | 0.0 | 8388608.0 | 869070947.0 | 3905828880.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 20456316.0 | 16255479456652 | 16263281527716 | 16263281707877 | 16255479980540 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 74 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 30016 | 0x7f713e388100 | 0x7f7117c24580 | 1293808 | 1191048 | 15428160 | 65536 | 99247764 | 161725 | 161725 | 15719969.0 | 14608417.0 | 25373.0 | 759631.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6632.0 | 2029974.0 | 0.0 | 2097152.0 | 1011808472.0 | 2304396609.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 12107981.0 | 16255480516548 | 16263281732037 | 16263281823717 | 16255480893470 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 77 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 8 | 24 | 30976 | 0x7f713c149f80 | 0x7f7117c245c0 | 1302032 | 1200096 | 15513321 | 65536 | 91447021 | 162753 | 162753 | 15837619.0 | 14695602.0 | 23274.0 | 1125094.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6626.0 | 2030563.0 | 0.0 | 2097152.0 | 1000535046.0 | 2229911639.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 11933435.0 | 16255481429598 | 16263281848678 | 16263281939878 | 16255481816849 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 80 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 31680 | 0x7f713c149e00 | 0x7f7117c24600 | 1306312 | 1199360 | 15526844 | 65536 | 111117180 | 163288 | 163288 | 15827869.0 | 14677331.0 | 23113.0 | 1055611.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6604.0 | 2030188.0 | 0.0 | 2097152.0 | 1002444947.0 | 2351198614.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 12197473.0 | 16255482359907 | 16263281972198 | 16263282064359 | 16255482759448 |
| 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 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 16 | 24 | 32640 | 0x7f713c149c80 | 0x7f7117c24640 | 2458256 | 2353444 | 30493830 | 65536 | 229712940 | 307281 | 307281 | 30830883.0 | 29709663.0 | 0.0 | 822141.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 208.0 | 8388608.0 | 12825.0 | 8248703.0 | 0.0 | 8388608.0 | 892801323.0 | 3642915055.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 19929033.0 | 16255483295026 | 16263282098599 | 16263282277960 | 16255483769016 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 86 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 33600 | 0x7f713c149b00 | 0x7f7117c24680 | 2462008 | 2349680 | 30441485 | 65536 | 223822199 | 307750 | 307750 | 30782081.0 | 29592227.0 | 0.0 | 986849.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 208.0 | 8388608.0 | 12655.0 | 8250599.0 | 0.0 | 8388608.0 | 866746445.0 | 4005125854.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 20739248.0 | 16255484305674 | 16263282303241 | 16263282483402 | 16255484778534 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 89 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 34560 | 0x7f713c149980 | 0x7f7117c246c0 | 1299040 | 1193235 | 15446699 | 65536 | 99827787 | 162379 | 162379 | 15748153.0 | 14552780.0 | 23695.0 | 1196009.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6634.0 | 2031069.0 | 0.0 | 2097152.0 | 1016392676.0 | 2333348009.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 12161020.0 | 16255485313572 | 16263282508362 | 16263282600843 | 16255485703293 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 92 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 8 | 24 | 35520 | 0x7f713c149800 | 0x7f7117c24700 | 1314200 | 1208968 | 15599159 | 65536 | 100249784 | 164274 | 164274 | 15952851.0 | 14689208.0 | 23307.0 | 1111969.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6619.0 | 2030051.0 | 0.0 | 2097152.0 | 982602351.0 | 2364534179.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 12069877.0 | 16255486239891 | 16263282624843 | 16263282717003 | 16255486653922 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 95 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 36224 | 0x7f713c149680 | 0x7f7117c24740 | 1305048 | 1203642 | 15577260 | 65536 | 109595991 | 163130 | 163130 | 15883457.0 | 14692105.0 | 23739.0 | 1039919.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6625.0 | 2031325.0 | 0.0 | 2097152.0 | 1026811844.0 | 2207019372.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 12089112.0 | 16255487197490 | 16263282750123 | 16263282842444 | 16255487585162 |
| 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 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 37184 | 0x7f713e388500 | 0x7f7117c24780 | 2447384 | 2344696 | 30399022 | 65536 | 229646062 | 305922 | 305922 | 30717133.0 | 29531087.0 | 0.0 | 923639.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 12937.0 | 8247491.0 | 0.0 | 8388608.0 | 870412994.0 | 3793852210.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 20735315.0 | 16255488120720 | 16263282866764 | 16263283045325 | 16255488591099 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 101 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 38144 | 0x7f713e388380 | 0x7f7117c247c0 | 2459800 | 2356925 | 30509447 | 65536 | 223570066 | 307474 | 307474 | 30876045.0 | 29646352.0 | 0.0 | 1016321.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 12894.0 | 8247926.0 | 0.0 | 8388608.0 | 887668956.0 | 3814480286.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 20561057.0 | 16255489126968 | 16263283069486 | 16263283249327 | 16255489602657 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 104 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 39104 | 0x7f713e388200 | 0x7f7117c24800 | 1297920 | 1195837 | 15460717 | 65536 | 102256212 | 162239 | 162239 | 15782135.0 | 14591216.0 | 23641.0 | 921281.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6601.0 | 2030006.0 | 0.0 | 2097152.0 | 1012545910.0 | 2280435468.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 12212342.0 | 16255490143485 | 16263283274127 | 16263283366607 | 16255490552076 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 107 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 8 | 24 | 40320 | 0x7f713e388080 | 0x7f7117c24840 | 1292592 | 1185907 | 15308184 | 65536 | 92786752 | 161573 | 161573 | 15653071.0 | 14436537.0 | 24614.0 | 664708.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6652.0 | 2056481.0 | 0.0 | 2097152.0 | 951721147.0 | 2159017714.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 12013769.0 | 16255491088084 | 16263283390288 | 16263283482288 | 16255491475646 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 110 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 41280 | 0x7f713c149f00 | 0x7f7117c24880 | 1311592 | 1208891 | 15636997 | 65536 | 100995151 | 163948 | 163948 | 15951629.0 | 14643781.0 | 21796.0 | 1505703.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6624.0 | 2029769.0 | 0.0 | 2097152.0 | 1018196891.0 | 2308911312.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 12068056.0 | 16255492021154 | 16263283514768 | 16263283606609 | 16255492417705 |
| 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 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 42240 | 0x7f713c149d80 | 0x7f7117c248c0 | 2456952 | 2348407 | 30422083 | 65536 | 230253262 | 307118 | 307118 | 30765493.0 | 29538446.0 | 0.0 | 848775.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 12837.0 | 8248682.0 | 0.0 | 8388608.0 | 856580466.0 | 3800922874.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 20680277.0 | 16255492953383 | 16263283631249 | 16263283811730 | 16255493438612 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 116 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 43200 | 0x7f713c149c00 | 0x7f7117c24900 | 2457576 | 2344959 | 30377276 | 65536 | 225505907 | 307196 | 307196 | 30720695.0 | 29544896.0 | 0.0 | 1256534.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 12641.0 | 8250643.0 | 0.0 | 8388608.0 | 870625582.0 | 3806534865.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 20650727.0 | 16255493972590 | 16263283836530 | 16263284017812 | 16255494514278 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 119 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 8 | 24 | 44160 | 0x7f713c149a80 | 0x7f7117c24940 | 1311248 | 1199978 | 15508604 | 65536 | 103593994 | 163905 | 163905 | 15835825.0 | 14613877.0 | 22429.0 | 1405166.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6634.0 | 2030631.0 | 0.0 | 2097152.0 | 1014049292.0 | 2340908701.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 12014380.0 | 16255495050667 | 16263284044052 | 16263284136212 | 16255495445138 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 122 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 45376 | 0x7f713c149900 | 0x7f7117c24980 | 1303664 | 1193662 | 15392843 | 65536 | 94676579 | 162957 | 162957 | 15753717.0 | 14450916.0 | 23413.0 | 985228.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6627.0 | 2039629.0 | 0.0 | 2097152.0 | 967241326.0 | 2197694776.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 12053083.0 | 16255495981916 | 16263284161813 | 16263284255253 | 16255496367448 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 125 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 46336 | 0x7f713c149780 | 0x7f7117c249c0 | 1299632 | 1192229 | 15420941 | 65536 | 102615747 | 162453 | 162453 | 15735231.0 | 14534007.0 | 22325.0 | 1488244.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6623.0 | 2041610.0 | 0.0 | 2097152.0 | 1005580679.0 | 2346964343.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 12004748.0 | 16255496909066 | 16263284288853 | 16263284380854 | 16255497366376 |
| 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 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 47552 | 0x7f713c149600 | 0x7f7117c24a00 | 2435464 | 2333939 | 30245437 | 65536 | 226226413 | 304432 | 304432 | 30577357.0 | 29385240.0 | 0.0 | 808173.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 12597.0 | 8251255.0 | 0.0 | 8388608.0 | 869926778.0 | 3774662155.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 20498252.0 | 16255497900204 | 16263284405974 | 16263284585655 | 16255498462431 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 131 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 48512 | 0x7f713e388480 | 0x7f7117c24a40 | 2420528 | 2318889 | 30042762 | 65536 | 219130140 | 302565 | 302565 | 30381655.0 | 29145888.0 | 0.0 | 946183.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 12580.0 | 8251667.0 | 0.0 | 8388608.0 | 870825980.0 | 3907390722.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 20238269.0 | 16255498998790 | 16263284609975 | 16263284789177 | 16255499497059 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 134 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 8 | 24 | 49472 | 0x7f713e388300 | 0x7f7117c24a80 | 1294688 | 1190353 | 15361901 | 65536 | 94913179 | 161835 | 161835 | 15710713.0 | 14552945.0 | 23796.0 | 911641.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6626.0 | 2029884.0 | 0.0 | 2097152.0 | 986656802.0 | 2227218489.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 12070654.0 | 16255500032127 | 16263284813017 | 16263284904697 | 16255500498076 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 137 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 50688 | 0x7f713e388180 | 0x7f7117c24ac0 | 1290520 | 1185334 | 15262368 | 65536 | 100271018 | 161314 | 161314 | 15645635.0 | 14372807.0 | 24690.0 | 575350.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6638.0 | 2038581.0 | 0.0 | 2097152.0 | 894340445.0 | 2018176973.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 12058195.0 | 16255501033364 | 16263284929497 | 16263285021978 | 16255501476235 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 140 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 51648 | 0x7f713e388000 | 0x7f7117c24b00 | 1301296 | 1196923 | 15477507 | 65536 | 97863922 | 162661 | 162661 | 15796227.0 | 14625384.0 | 23030.0 | 1237232.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6643.0 | 2040876.0 | 0.0 | 2097152.0 | 1007074785.0 | 2225393840.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 12075482.0 | 16255502023033 | 16263285055738 | 16263285146779 | 16255502504542 |
| 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 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 52864 | 0x7f713c149e80 | 0x7f7117c24b40 | 2419368 | 2315804 | 30011888 | 65536 | 226167929 | 302420 | 302420 | 30341563.0 | 29127554.0 | 0.0 | 925705.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 12619.0 | 8250901.0 | 0.0 | 8388608.0 | 871905693.0 | 3788775439.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 20323074.0 | 16255503038810 | 16263285171739 | 16263285351420 | 16255503571198 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 146 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 54080 | 0x7f713c149d00 | 0x7f7117c24b80 | 2410376 | 2309216 | 29912134 | 65536 | 220099488 | 301296 | 301296 | 30255841.0 | 29030346.0 | 0.0 | 863476.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 12552.0 | 8251717.0 | 0.0 | 8388608.0 | 861939296.0 | 3923206702.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 20256654.0 | 16255504104217 | 16263285375420 | 16263285557182 | 16255504640105 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 149 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 8 | 24 | 55296 | 0x7f713c149b80 | 0x7f7117c24bc0 | 1294392 | 1192398 | 15387087 | 65536 | 93857092 | 161798 | 161798 | 15737519.0 | 14479747.0 | 24264.0 | 840290.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6627.0 | 2029086.0 | 0.0 | 2097152.0 | 996642743.0 | 2222332183.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 12110126.0 | 16255505172773 | 16263285581022 | 16263285674622 | 16255505617813 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 152 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 56768 | 0x7f713c149a00 | 0x7f7117c24c00 | 1297880 | 1195016 | 15428867 | 65536 | 101886283 | 162234 | 162234 | 15771475.0 | 14418247.0 | 24888.0 | 331505.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6653.0 | 2057932.0 | 0.0 | 2097152.0 | 777230783.0 | 1937413957.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 11917079.0 | 16255506151992 | 16263285700862 | 16263285794463 | 16255506603052 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 155 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 57728 | 0x7f713c149880 | 0x7f7117c24c40 | 1298560 | 1189079 | 15377654 | 65536 | 95443069 | 162319 | 162319 | 15694359.0 | 14485219.0 | 24085.0 | 1137953.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6633.0 | 2041389.0 | 0.0 | 2097152.0 | 996286109.0 | 2220961458.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 12023478.0 | 16255507147710 | 16263285828703 | 16263285920544 | 16255507604279 |
| 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 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 58944 | 0x7f713c149700 | 0x7f7117c24c80 | 2432952 | 2320553 | 30056324 | 65536 | 223457257 | 304118 | 304118 | 30403391.0 | 29187386.0 | 0.0 | 1070769.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 12638.0 | 8250920.0 | 0.0 | 8388608.0 | 856807792.0 | 3931801475.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 20392991.0 | 16255508145157 | 16263285945664 | 16263286124545 | 16255508681156 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 161 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 60160 | 0x7f713e388580 | 0x7f7117c24cc0 | 2437944 | 2332420 | 30217179 | 65536 | 220270977 | 304742 | 304742 | 30557519.0 | 29359186.0 | 0.0 | 880315.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 12652.0 | 8250866.0 | 0.0 | 8388608.0 | 855636865.0 | 3918732611.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 20162397.0 | 16255509215974 | 16263286149505 | 16263286329667 | 16255509752842 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 164 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 8 | 24 | 61376 | 0x7f713e388400 | 0x7f7117c24d00 | 1297360 | 1192099 | 15400942 | 65536 | 89704768 | 162169 | 162169 | 15733411.0 | 14474019.0 | 24794.0 | 706856.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6601.0 | 2029107.0 | 0.0 | 2097152.0 | 946967809.0 | 2344056841.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 11986238.0 | 16255510286360 | 16263286352867 | 16263286445827 | 16255510732240 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 167 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 62848 | 0x7f713e388280 | 0x7f7117c24d40 | 1356136 | 1244812 | 16062975 | 65536 | 105420551 | 169516 | 169516 | 16418641.0 | 14723016.0 | 23139.0 | 256646.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6632.0 | 2038990.0 | 0.0 | 2097152.0 | 673004796.0 | 1781067783.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 12048953.0 | 16255511264958 | 16263286471267 | 16263286568228 | 16255511713249 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 170 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 63808 | 0x7f713e388100 | 0x7f7117c24d80 | 1295912 | 1192701 | 15423483 | 65536 | 92086277 | 161988 | 161988 | 15741289.0 | 14548448.0 | 23366.0 | 1052345.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6626.0 | 2042032.0 | 0.0 | 2097152.0 | 1001290529.0 | 2288245267.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 12014241.0 | 16255512254957 | 16263286600388 | 16263286692549 | 16255512695217 |
| 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 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 65024 | 0x7f713c149f80 | 0x7f7117c24dc0 | 2431512 | 2326893 | 30131957 | 65536 | 225293212 | 303938 | 303938 | 30485759.0 | 29265345.0 | 0.0 | 1120643.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 12648.0 | 8250714.0 | 0.0 | 8388608.0 | 865037062.0 | 3888946217.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 20187507.0 | 16255513229045 | 16263286720229 | 16263286899270 | 16255513770083 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 176 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 66240 | 0x7f713c149e00 | 0x7f7117c24e00 | 2426312 | 2317079 | 29983118 | 65536 | 216913934 | 303288 | 303288 | 30358229.0 | 29150306.0 | 0.0 | 1145854.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 12618.0 | 8251163.0 | 0.0 | 8388608.0 | 872352287.0 | 4006502727.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 20212536.0 | 16255514304182 | 16263286923910 | 16263287102631 | 16255514859389 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 179 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 8 | 24 | 67456 | 0x7f713c149c80 | 0x7f7117c24e40 | 1296152 | 1192268 | 15372694 | 65536 | 99764324 | 162018 | 162018 | 15735673.0 | 14356017.0 | 24657.0 | 678857.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6620.0 | 2027562.0 | 0.0 | 2097152.0 | 986068858.0 | 2222386241.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 11962200.0 | 16255515392527 | 16263287126952 | 16263287219752 | 16255515840387 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 182 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 68928 | 0x7f713c149b00 | 0x7f7117c24e80 | 1399200 | 1293914 | 16661585 | 65536 | 116056479 | 174899 | 174899 | 17056967.0 | 14955174.0 | 22165.0 | 102311.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6640.0 | 2038302.0 | 0.0 | 2097152.0 | 627889123.0 | 1636404858.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 12370202.0 | 16255516374336 | 16263287243592 | 16263287345673 | 16255516840035 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 185 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 70144 | 0x7f713c149980 | 0x7f7117c24ec0 | 1278344 | 1175244 | 15182199 | 65536 | 95597434 | 159792 | 159792 | 15514153.0 | 14364321.0 | 24417.0 | 628797.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6639.0 | 2041910.0 | 0.0 | 2097152.0 | 969057966.0 | 2245677982.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 11995874.0 | 16255517381433 | 16263287378953 | 16263287470954 | 16255517817044 |
| 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 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 71616 | 0x7f713c149800 | 0x7f7117c24f00 | 2440624 | 2332732 | 30204337 | 65536 | 223681440 | 305077 | 305077 | 30561705.0 | 29268182.0 | 0.0 | 1154496.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 12819.0 | 8249022.0 | 0.0 | 8388608.0 | 876233306.0 | 3794428659.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 20489710.0 | 16255518350352 | 16263287495754 | 16263287676235 | 16255518882190 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 191 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 72832 | 0x7f713c149680 | 0x7f7117c24f40 | 2428560 | 2317166 | 30030228 | 65536 | 224281933 | 303569 | 303569 | 30359243.0 | 29087746.0 | 0.0 | 1099653.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 12717.0 | 8250077.0 | 0.0 | 8388608.0 | 858690993.0 | 3883065849.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 20041767.0 | 16255519414638 | 16263287701675 | 16263287881997 | 16255519948167 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 194 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 8 | 24 | 74048 | 0x7f713e388500 | 0x7f7117c24f80 | 1291584 | 1187487 | 15325705 | 65536 | 96697518 | 161447 | 161447 | 15673533.0 | 14420906.0 | 23079.0 | 1062709.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6643.0 | 2056409.0 | 0.0 | 2097152.0 | 984494462.0 | 2087678491.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 11972628.0 | 16255520480925 | 16263287906157 | 16263287998477 | 16255520921815 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 197 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 75776 | 0x7f713e388380 | 0x7f7117c24fc0 | 1456696 | 1350777 | 17419040 | 65536 | 120945590 | 182086 | 182086 | 17796277.0 | 15504263.0 | 20884.0 | 125659.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6640.0 | 2038783.0 | 0.0 | 2097152.0 | 540176599.0 | 1446690851.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 12518962.0 | 16255521454994 | 16263288022477 | 16263288128398 | 16255521930243 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 200 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 76992 | 0x7f713e388200 | 0x7f7117c25000 | 1290600 | 1187229 | 15344587 | 65536 | 103554311 | 161324 | 161324 | 15670205.0 | 14438942.0 | 24464.0 | 633375.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6613.0 | 2042725.0 | 0.0 | 2097152.0 | 999552226.0 | 2269553815.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 11540090.0 | 16255522483031 | 16263288161518 | 16263288253999 | 16255522931721 |
| 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 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 78464 | 0x7f713e388080 | 0x7f7117c25040 | 2422608 | 2312417 | 29961034 | 65536 | 220467980 | 302825 | 302825 | 30297623.0 | 29020406.0 | 0.0 | 765652.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 12762.0 | 8249811.0 | 0.0 | 8388608.0 | 868008872.0 | 3901610174.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 19434574.0 | 16255523464719 | 16263288278159 | 16263288458480 | 16255524003617 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 206 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 79936 | 0x7f713c149f00 | 0x7f7117c25080 | 2412312 | 2306373 | 29839146 | 65536 | 222714472 | 301538 | 301538 | 30218869.0 | 28917857.0 | 0.0 | 586771.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 12609.0 | 8251160.0 | 0.0 | 8388608.0 | 873406239.0 | 3767714043.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 19648587.0 | 16255524536355 | 16263288483120 | 16263288661842 | 16255525069394 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 209 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 8 | 24 | 81408 | 0x7f713c149d80 | 0x7f7117c250c0 | 1300616 | 1191727 | 15361567 | 65536 | 91750815 | 162576 | 162576 | 15728497.0 | 14424256.0 | 24399.0 | 777247.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6619.0 | 2039260.0 | 0.0 | 2097152.0 | 943385619.0 | 2267587735.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 11923171.0 | 16255525608042 | 16263288688882 | 16263288782162 | 16255526063861 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 212 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 83136 | 0x7f713c149c00 | 0x7f7117c25100 | 1533208 | 1425469 | 18383710 | 65536 | 124978288 | 191650 | 191650 | 18767091.0 | 15521397.0 | 20916.0 | 95018.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6636.0 | 2040335.0 | 0.0 | 2097152.0 | 454264252.0 | 1228436906.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 12131925.0 | 16255526596510 | 16263288807282 | 16263288918963 | 16255527071369 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 215 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 84352 | 0x7f713c149a80 | 0x7f7117c25140 | 1287232 | 1187247 | 15331458 | 65536 | 104467972 | 160903 | 160903 | 15670413.0 | 14433992.0 | 23432.0 | 929230.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6622.0 | 2042311.0 | 0.0 | 2097152.0 | 993665081.0 | 2265632528.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 11949378.0 | 16255527612797 | 16263288969044 | 16263289062004 | 16255528049878 |
| 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 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 85824 | 0x7f713c149900 | 0x7f7117c25180 | 2418184 | 2317494 | 30003431 | 65536 | 223381431 | 302272 | 302272 | 30363533.0 | 29062371.0 | 0.0 | 1020094.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 12745.0 | 8249915.0 | 0.0 | 8388608.0 | 872198121.0 | 3791509472.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 20049279.0 | 16255528582736 | 16263289087444 | 16263289267925 | 16255529139104 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 221 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 87296 | 0x7f713c149780 | 0x7f7117c251c0 | 2421208 | 2315546 | 29967696 | 65536 | 220064918 | 302650 | 302650 | 30338235.0 | 29066384.0 | 0.0 | 960231.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 12636.0 | 8251013.0 | 0.0 | 8388608.0 | 871228173.0 | 3763784690.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 20200551.0 | 16255529672312 | 16263289292726 | 16263289472567 | 16255530208520 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 224 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 88768 | 0x7f713c149600 | 0x7f7117c25200 | 1297560 | 1189889 | 15330592 | 65536 | 95207182 | 162194 | 162194 | 15704759.0 | 14375445.0 | 25002.0 | 641893.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6622.0 | 2038689.0 | 0.0 | 2097152.0 | 959829197.0 | 2204778656.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 11894552.0 | 16255530741978 | 16263289497207 | 16263289590648 | 16255531217528 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 227 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 90752 | 0x7f713e388480 | 0x7f7117c25240 | 1600016 | 1495050 | 19267357 | 65536 | 132287818 | 200001 | 200001 | 19671891.0 | 15806935.0 | 19868.0 | 56965.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6635.0 | 2041581.0 | 0.0 | 2097152.0 | 435325125.0 | 1145194636.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 12526629.0 | 16255531753086 | 16263289615928 | 16263289734008 | 16255532232025 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 230 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 91968 | 0x7f713e388300 | 0x7f7117c25280 | 1290216 | 1185300 | 15299780 | 65536 | 98069093 | 161276 | 161276 | 15645167.0 | 14399980.0 | 23325.0 | 962791.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6597.0 | 2042986.0 | 0.0 | 2097152.0 | 968748473.0 | 2302710515.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 11890390.0 | 16255532774843 | 16263289766969 | 16263289859129 | 16255533218253 |
| 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 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 93440 | 0x7f713e388180 | 0x7f7117c252c0 | 2419320 | 2317900 | 30030489 | 65536 | 223804741 | 302414 | 302414 | 30368759.0 | 28985747.0 | 0.0 | 841674.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 12741.0 | 8250184.0 | 0.0 | 8388608.0 | 863926533.0 | 3837600654.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 20073337.0 | 16255533752432 | 16263289883289 | 16263290063131 | 16255534295940 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 236 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 94912 | 0x7f713e388000 | 0x7f7117c25300 | 2398920 | 2294936 | 29721273 | 65536 | 216463917 | 299864 | 299864 | 30070461.0 | 28765209.0 | 0.0 | 825556.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 12607.0 | 8251187.0 | 0.0 | 8388608.0 | 864398217.0 | 3842588202.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 19878014.0 | 16255534829118 | 16263290102971 | 16263290283132 | 16255535360086 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 239 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 96384 | 0x7f713c149e80 | 0x7f7117c25340 | 1300120 | 1189085 | 15327433 | 65536 | 101636825 | 162514 | 162514 | 15694229.0 | 14356928.0 | 24055.0 | 805193.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6607.0 | 2039459.0 | 0.0 | 2097152.0 | 923620921.0 | 2156214745.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 11906659.0 | 16255535892134 | 16263290309372 | 16263290403453 | 16255536360784 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 242 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 98368 | 0x7f713c149d00 | 0x7f7117c25380 | 1672544 | 1566683 | 20200198 | 65536 | 141268474 | 209067 | 209067 | 20602977.0 | 16525691.0 | 18914.0 | 31683.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6656.0 | 2041085.0 | 0.0 | 2097152.0 | 403221582.0 | 1086200329.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 12979406.0 | 16255536894732 | 16263290428253 | 16263290551774 | 16255537384451 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 245 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 99584 | 0x7f713c149b80 | 0x7f7117c253c0 | 1296232 | 1187491 | 15313157 | 65536 | 94753975 | 162028 | 162028 | 15673611.0 | 14399097.0 | 23996.0 | 884984.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6623.0 | 2040017.0 | 0.0 | 2097152.0 | 980621516.0 | 2185377232.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 12004635.0 | 16255537924789 | 16263290584574 | 16263290677375 | 16255538395639 |
| 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 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 101312 | 0x7f713c149a00 | 0x7f7117c25400 | 2398160 | 2294145 | 29723387 | 65536 | 221196712 | 299769 | 299769 | 30060009.0 | 28890657.0 | 0.0 | 880120.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 12622.0 | 8250886.0 | 0.0 | 8388608.0 | 860617197.0 | 3880744662.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 19889375.0 | 16255538930427 | 16263290702975 | 16263290880416 | 16255539473525 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 251 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 102784 | 0x7f713c149880 | 0x7f7117c25440 | 2392680 | 2288300 | 29615035 | 65536 | 215933668 | 299084 | 299084 | 29983959.0 | 28732732.0 | 0.0 | 867746.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 12557.0 | 8251601.0 | 0.0 | 8388608.0 | 859107793.0 | 3839398956.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 20047338.0 | 16255540006483 | 16263290905376 | 16263291083777 | 16255540542791 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 254 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 104256 | 0x7f713c149700 | 0x7f7117c25480 | 1294760 | 1185080 | 15286486 | 65536 | 102601063 | 161844 | 161844 | 15642281.0 | 14300033.0 | 24919.0 | 351728.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6633.0 | 2039071.0 | 0.0 | 2097152.0 | 888682569.0 | 2166574658.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 11907215.0 | 16255541073780 | 16263291108257 | 16263291201218 | 16255541527710 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 257 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 106240 | 0x7f713e388580 | 0x7f7117c254c0 | 1755736 | 1644868 | 21214938 | 65536 | 149107230 | 219466 | 219466 | 21619317.0 | 16717195.0 | 18569.0 | 36115.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6654.0 | 2041412.0 | 0.0 | 2097152.0 | 370478390.0 | 1041294179.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 12943440.0 | 16255542061118 | 16263291225858 | 16263291354819 | 16255542569937 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 260 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 107712 | 0x7f713e388400 | 0x7f7117c25500 | 1282392 | 1176898 | 15166319 | 65536 | 100103887 | 160298 | 160298 | 15535889.0 | 14212343.0 | 24789.0 | 640308.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6606.0 | 2041810.0 | 0.0 | 2097152.0 | 928376543.0 | 2246325852.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 11936702.0 | 16255543113755 | 16263291387299 | 16263291479460 | 16255543545175 |
| 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 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 16 | 24 | 109440 | 0x7f713e388280 | 0x7f7117c25540 | 2392616 | 2285551 | 29579532 | 65536 | 218176132 | 299076 | 299076 | 29948417.0 | 28681397.0 | 0.0 | 683312.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 12620.0 | 8250882.0 | 0.0 | 8388608.0 | 853123460.0 | 3986138167.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 19805386.0 | 16255544080633 | 16263291505220 | 16263291684261 | 16255544551633 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 266 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 16 | 24 | 111168 | 0x7f713e388100 | 0x7f7117c25580 | 2374800 | 2273076 | 29451289 | 65536 | 216532913 | 296849 | 296849 | 29786151.0 | 28563337.0 | 0.0 | 687902.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 12346.0 | 8253956.0 | 0.0 | 8388608.0 | 836726519.0 | 3843706968.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 20059801.0 | 16255545087791 | 16263291708581 | 16263291888742 | 16255545595480 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 269 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 8 | 24 | 112896 | 0x7f713c149f80 | 0x7f7117c255c0 | 1295720 | 1194966 | 15406447 | 65536 | 106101327 | 161964 | 161964 | 15770643.0 | 14250693.0 | 24801.0 | 241509.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6673.0 | 2056329.0 | 0.0 | 2097152.0 | 844324128.0 | 1935768367.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 11990404.0 | 16255546128608 | 16263291913062 | 16263292006983 | 16255546596398 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 272 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 115136 | 0x7f713c149e00 | 0x7f7117c25600 | 1817992 | 1713572 | 22139596 | 65536 | 158854689 | 227248 | 227248 | 22512469.0 | 16829509.0 | 18176.0 | 31819.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6658.0 | 2041456.0 | 0.0 | 2097152.0 | 357754948.0 | 1018313254.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 12627159.0 | 16255547132776 | 16263292031303 | 16263292167464 | 16255547567846 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 275 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 116608 | 0x7f713c149c80 | 0x7f7117c25640 | 1298864 | 1190313 | 15351794 | 65536 | 98844462 | 162357 | 162357 | 15710219.0 | 14366091.0 | 23762.0 | 822648.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6596.0 | 2042479.0 | 0.0 | 2097152.0 | 961443464.0 | 2226069217.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 11849684.0 | 16255548110024 | 16263292200424 | 16263292294025 | 16255548471246 |
| 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 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 16 | 24 | 118336 | 0x7f713c149b00 | 0x7f7117c25680 | 2377256 | 2274821 | 29469284 | 65536 | 217850603 | 297156 | 297156 | 29808771.0 | 28549842.0 | 0.0 | 751638.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 12563.0 | 8251564.0 | 0.0 | 8388608.0 | 856942841.0 | 3874625742.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 19595916.0 | 16255549006255 | 16263292318185 | 16263292497546 | 16255549461495 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 281 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 16 | 24 | 120064 | 0x7f713c149980 | 0x7f7117c256c0 | 2410144 | 2297500 | 29734736 | 65536 | 218420620 | 301267 | 301267 | 30103767.0 | 28847883.0 | 0.0 | 1010725.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 12631.0 | 8250849.0 | 0.0 | 8388608.0 | 855539355.0 | 3917669653.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 19814632.0 | 16255549996513 | 16263292522186 | 16263292702508 | 16255550464452 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 284 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 121792 | 0x7f713c149800 | 0x7f7117c25700 | 1298848 | 1192651 | 15393666 | 65536 | 106374426 | 162355 | 162355 | 15740509.0 | 14343006.0 | 24315.0 | 234251.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6658.0 | 2059288.0 | 0.0 | 2097152.0 | 751056380.0 | 1849868481.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 11999095.0 | 16255550999211 | 16263292726988 | 16263292822188 | 16255551356493 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 287 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 124032 | 0x7f713c149680 | 0x7f7117c25740 | 1900888 | 1799537 | 23248590 | 65536 | 168544749 | 237610 | 237610 | 23630183.0 | 17365458.0 | 17813.0 | 30216.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6674.0 | 2041461.0 | 0.0 | 2097152.0 | 327591784.0 | 936572930.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 13103749.0 | 16255551890681 | 16263292847628 | 16263292989709 | 16255552298052 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 290 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 125504 | 0x7f713e388500 | 0x7f7117c25780 | 1282312 | 1179708 | 15213929 | 65536 | 101092376 | 160288 | 160288 | 15572471.0 | 14217858.0 | 24313.0 | 636847.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6605.0 | 2040371.0 | 0.0 | 2097152.0 | 919310100.0 | 2035007281.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 11792339.0 | 16255552840550 | 16263293024110 | 16263293117390 | 16255553201092 |
| 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 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 127488 | 0x7f713e388380 | 0x7f7117c257c0 | 2396856 | 2287654 | 29593712 | 65536 | 204626446 | 299606 | 299606 | 29975769.0 | 28600361.0 | 0.0 | 1185457.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 12157.0 | 8256061.0 | 0.0 | 8388608.0 | 841370353.0 | 3951637905.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 19643228.0 | 16255553736090 | 16263293142350 | 16263293320272 | 16255554205889 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 296 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 129216 | 0x7f713e388200 | 0x7f7117c25800 | 2391704 | 2287457 | 29612044 | 65536 | 214898859 | 298962 | 298962 | 29973013.0 | 28674203.0 | 0.0 | 1150069.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 12397.0 | 8253645.0 | 0.0 | 8388608.0 | 857050786.0 | 3870643095.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 19738097.0 | 16255554741948 | 16263293344752 | 16263293523793 | 16255555203288 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 299 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 130944 | 0x7f713e388080 | 0x7f7117c25840 | 1359760 | 1253933 | 16185895 | 65536 | 111562965 | 169969 | 169969 | 16537175.0 | 15094767.0 | 22622.0 | 173128.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6651.0 | 2038971.0 | 0.0 | 2097152.0 | 677604479.0 | 1767242814.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 12589620.0 | 16255555738476 | 16263293549713 | 16263293648754 | 16255556106708 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 302 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 133440 | 0x7f713c149f00 | 0x7f7117c25880 | 2063144 | 1960676 | 25328487 | 65536 | 187951760 | 257892 | 257892 | 25724899.0 | 17184747.0 | 19022.0 | 39261.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6672.0 | 2040936.0 | 0.0 | 2097152.0 | 337077703.0 | 966689500.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 12347126.0 | 16255556642576 | 16263293674034 | 16263293827155 | 16255557131975 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 305 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 134912 | 0x7f713c149d80 | 0x7f7117c258c0 | 1284960 | 1179971 | 15218038 | 65536 | 98668414 | 160619 | 160619 | 15575643.0 | 14280253.0 | 23978.0 | 519803.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6617.0 | 2039851.0 | 0.0 | 2097152.0 | 875767331.0 | 2055459500.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 11857378.0 | 16255557676073 | 16263293861875 | 16263293954996 | 16255558063675 |
| 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 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 136896 | 0x7f713c149c00 | 0x7f7117c25900 | 2360296 | 2254191 | 29160039 | 65536 | 210618081 | 295036 | 295036 | 29540555.0 | 28317157.0 | 0.0 | 823384.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 12229.0 | 8255149.0 | 0.0 | 8388608.0 | 838443313.0 | 3881034498.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 19752591.0 | 16255558599283 | 16263293980916 | 16263294158997 | 16255559094742 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 311 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 138880 | 0x7f713c149a80 | 0x7f7117c25940 | 2365736 | 2263707 | 29310985 | 65536 | 216619353 | 295716 | 295716 | 29664445.0 | 28372336.0 | 0.0 | 974933.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 12604.0 | 8251263.0 | 0.0 | 8388608.0 | 841468260.0 | 3944579850.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 19617822.0 | 16255559630840 | 16263294184437 | 16263294363158 | 16255560122829 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 314 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 140864 | 0x7f713c149900 | 0x7f7117c25980 | 1441288 | 1335889 | 17245443 | 65536 | 122309569 | 180160 | 180160 | 17602733.0 | 15739281.0 | 20158.0 | 195539.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6629.0 | 2039195.0 | 0.0 | 2097152.0 | 539137549.0 | 1425708839.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 13156350.0 | 16255560656677 | 16263294386838 | 16263294490679 | 16255561090077 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 317 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 143616 | 0x7f713c149780 | 0x7f7117c259c0 | 2227320 | 2117515 | 27365521 | 65536 | 201159904 | 278414 | 278414 | 27763819.0 | 17407645.0 | 18984.0 | 32776.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6678.0 | 2041208.0 | 0.0 | 2097152.0 | 311754234.0 | 923362275.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 12160803.0 | 16255561630455 | 16263294514359 | 16263294681880 | 16255562088855 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 320 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 145344 | 0x7f713c149600 | 0x7f7117c25a00 | 1298584 | 1195564 | 15423516 | 65536 | 104324221 | 162322 | 162322 | 15778521.0 | 14407802.0 | 23047.0 | 375882.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6630.0 | 2041053.0 | 0.0 | 2097152.0 | 770787395.0 | 1899661782.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 11877882.0 | 16255562633273 | 16263294714521 | 16263294808601 | 16255563040774 |
| 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 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 147584 | 0x7f713e388480 | 0x7f7117c25a40 | 2367448 | 2259761 | 29234284 | 65536 | 209421072 | 295930 | 295930 | 29613121.0 | 28222534.0 | 0.0 | 514535.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 12557.0 | 8251398.0 | 0.0 | 8388608.0 | 821545153.0 | 3998795276.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 19375145.0 | 16255563577863 | 16263294832761 | 16263295011802 | 16255564076632 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 326 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 149568 | 0x7f713e388300 | 0x7f7117c25a80 | 2365568 | 2259199 | 29172109 | 65536 | 210266308 | 295695 | 295695 | 29605841.0 | 28224018.0 | 0.0 | 1133603.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 12490.0 | 8252364.0 | 0.0 | 8388608.0 | 826660110.0 | 3918501568.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 19460388.0 | 16255564611990 | 16263295035483 | 16263295215164 | 16255565083999 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 329 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 151552 | 0x7f713e388180 | 0x7f7117c25ac0 | 1489440 | 1386898 | 17869129 | 65536 | 125170909 | 186179 | 186179 | 18265811.0 | 16657831.0 | 16421.0 | 155889.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6645.0 | 2040180.0 | 0.0 | 2097152.0 | 451238099.0 | 1192132932.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 14023731.0 | 16255565619978 | 16263295239324 | 16263295347965 | 16255566052338 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 332 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 154304 | 0x7f713e388000 | 0x7f7117c25b00 | 2388264 | 2278695 | 29431522 | 65536 | 215341594 | 298532 | 298532 | 29859081.0 | 17921232.0 | 18435.0 | 48845.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6665.0 | 2041083.0 | 0.0 | 2097152.0 | 305250461.0 | 879453456.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 12323646.0 | 16255566588846 | 16263295372285 | 16263295551166 | 16255567067616 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 335 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 156288 | 0x7f713c149e80 | 0x7f7117c25b40 | 1383264 | 1281137 | 16511227 | 65536 | 112459625 | 172907 | 172907 | 16890983.0 | 15127920.0 | 22217.0 | 228895.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6629.0 | 2038638.0 | 0.0 | 2097152.0 | 621558807.0 | 1627724410.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 12458255.0 | 16255567610794 | 16263295583486 | 16263295683647 | 16255568029444 |
| 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 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 158784 | 0x7f713c149d00 | 0x7f7117c25b80 | 2388384 | 2260548 | 29205882 | 65536 | 187214644 | 298547 | 298547 | 29623261.0 | 28283933.0 | 0.0 | 699312.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 11727.0 | 8260827.0 | 0.0 | 8388608.0 | 839358743.0 | 3846610150.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 19329525.0 | 16255568564372 | 16263295709887 | 16263295891968 | 16255569035122 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 341 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 161024 | 0x7f713c149b80 | 0x7f7117c25bc0 | 2363480 | 2254387 | 29145275 | 65536 | 196580696 | 295434 | 295434 | 29543207.0 | 28193465.0 | 0.0 | 633691.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 12181.0 | 8255677.0 | 0.0 | 8388608.0 | 837697073.0 | 3835522714.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 19709776.0 | 16255569570480 | 16263295915968 | 16263296099489 | 16255570059759 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 344 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 163264 | 0x7f713c149a00 | 0x7f7117c25c00 | 1642696 | 1536244 | 19828538 | 65536 | 143632815 | 205336 | 205336 | 20207231.0 | 18167395.0 | 15880.0 | 55377.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6626.0 | 2039615.0 | 0.0 | 2097152.0 | 416103063.0 | 1129930029.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 15410810.0 | 16255570594957 | 16263296123650 | 16263296244610 | 16255571055627 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 347 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 166528 | 0x7f713c149880 | 0x7f7117c25c40 | 2699928 | 2600014 | 33622093 | 65536 | 250879408 | 337490 | 337490 | 34036267.0 | 17978004.0 | 18854.0 | 48175.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6737.0 | 2041857.0 | 0.0 | 2097152.0 | 309292166.0 | 904709859.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 12655285.0 | 16255571591036 | 16263296269091 | 16263296472932 | 16255572149913 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 350 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 168512 | 0x7f713c149700 | 0x7f7117c25c80 | 1466464 | 1361790 | 17572647 | 65536 | 123075471 | 183307 | 183307 | 17939355.0 | 16035873.0 | 19638.0 | 48637.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6654.0 | 2037005.0 | 0.0 | 2097152.0 | 481770767.0 | 1218419076.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 13375501.0 | 16255572628063 | 16263296542852 | 16263296651013 | 16255573046694 |
| 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 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 171264 | 0x7f713e388580 | 0x7f7117c25cc0 | 2386064 | 2275213 | 29349310 | 65536 | 202159234 | 298257 | 298257 | 29813893.0 | 28242145.0 | 0.0 | 501094.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 12171.0 | 8255703.0 | 0.0 | 8388608.0 | 810711678.0 | 3935260275.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 19222791.0 | 16255573580822 | 16263296677253 | 16263296859814 | 16255574090461 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 356 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 173760 | 0x7f713e388400 | 0x7f7117c25d00 | 2376432 | 2267370 | 29255496 | 65536 | 202636444 | 297053 | 297053 | 29712077.0 | 28290892.0 | 0.0 | 720779.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 12146.0 | 8255903.0 | 0.0 | 8388608.0 | 823019278.0 | 3879739964.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 19203161.0 | 16255574624129 | 16263296884454 | 16263297069896 | 16255575107178 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 359 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 176256 | 0x7f713e388280 | 0x7f7117c25d40 | 1787600 | 1685173 | 21794579 | 65536 | 161111875 | 223449 | 223449 | 22143425.0 | 20203417.0 | 14198.0 | 82488.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6637.0 | 2036948.0 | 0.0 | 2097152.0 | 318787943.0 | 939524810.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 16432076.0 | 16255575641826 | 16263297096616 | 16263297229097 | 16255576077166 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 362 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 179776 | 0x7f713e388100 | 0x7f7117c25d80 | 3027896 | 2924883 | 37805207 | 65536 | 282635860 | 378486 | 378486 | 38259681.0 | 18524222.0 | 18854.0 | 60046.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6725.0 | 2041918.0 | 0.0 | 2097152.0 | 318055860.0 | 917713495.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 12496525.0 | 16255576612245 | 16263297253097 | 16263297484138 | 16255577224831 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 365 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 182272 | 0x7f713c149f80 | 0x7f7117c25dc0 | 1691152 | 1582270 | 20429648 | 65536 | 145247317 | 211393 | 211393 | 20805569.0 | 18394253.0 | 17425.0 | 135312.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6635.0 | 2050113.0 | 0.0 | 2097152.0 | 345611706.0 | 996781250.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 14420642.0 | 16255577700271 | 16263297528779 | 16263297654059 | 16255578156560 |
| 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 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 185536 | 0x7f713c149e00 | 0x7f7117c25e00 | 2487112 | 2363503 | 30455903 | 65536 | 196637526 | 310888 | 310888 | 30961741.0 | 28609563.0 | 0.0 | 480144.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 12502.0 | 8251603.0 | 0.0 | 8388608.0 | 686150028.0 | 3368018271.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 19141067.0 | 16255578691769 | 16263297679020 | 16263297870701 | 16255579247536 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 371 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 188544 | 0x7f713c149c80 | 0x7f7117c25e40 | 2523680 | 2386740 | 30774631 | 65536 | 194043733 | 315459 | 315459 | 31263965.0 | 29435024.0 | 0.0 | 536680.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 12759.0 | 8248841.0 | 0.0 | 8388608.0 | 688784584.0 | 3462872011.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 19955880.0 | 16255579720266 | 16263297896301 | 16263298090862 | 16255580275493 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 374 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 191552 | 0x7f713c149b00 | 0x7f7117c25e80 | 2114040 | 2011522 | 26031925 | 65536 | 194442387 | 264254 | 264254 | 26385871.0 | 23081986.0 | 15671.0 | 63177.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6640.0 | 2030917.0 | 0.0 | 2097152.0 | 322377474.0 | 932561909.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 16173304.0 | 16255580751033 | 16263298127502 | 16263298285584 | 16255581204803 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 377 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 195840 | 0x7f713c149980 | 0x7f7117c25ec0 | 3671352 | 3562285 | 46118237 | 65536 | 348568314 | 458918 | 458918 | 46545959.0 | 18645517.0 | 18879.0 | 49623.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6706.0 | 2040777.0 | 0.0 | 2097152.0 | 315964416.0 | 889869034.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 13348241.0 | 16255581739671 | 16263298310224 | 16263298591345 | 16255582378997 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 380 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 198592 | 0x7f713c149800 | 0x7f7117c25f00 | 1922728 | 1822688 | 23574885 | 65536 | 175092219 | 240340 | 240340 | 23931159.0 | 21778724.0 | 13493.0 | 10084.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6650.0 | 2048819.0 | 0.0 | 2097152.0 | 314328380.0 | 933175434.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 19339588.0 | 16255582858476 | 16263298636626 | 16263298782227 | 16255583310046 |
| 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 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 202368 | 0x7f713c149680 | 0x7f7117c25f40 | 2680552 | 2566417 | 33063070 | 65536 | 213162259 | 335068 | 335068 | 33599467.0 | 29637236.0 | 0.0 | 173678.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 12614.0 | 8250294.0 | 0.0 | 8388608.0 | 636247245.0 | 3087043766.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 20124165.0 | 16255583844975 | 16263298809267 | 16263299021268 | 16255584409572 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 386 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 205888 | 0x7f713e388500 | 0x7f7117c25f80 | 2653568 | 2539940 | 32695441 | 65536 | 224088779 | 331695 | 331695 | 33255409.0 | 30855224.0 | 0.0 | 286460.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 12600.0 | 8250386.0 | 0.0 | 8388608.0 | 546899727.0 | 2896333661.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 21678067.0 | 16255584879442 | 16263299059989 | 16263299270550 | 16255585484348 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 389 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 209408 | 0x7f713e388380 | 0x7f7117c25fc0 | 2441776 | 2335151 | 30231804 | 65536 | 227990593 | 305221 | 305221 | 30593269.0 | 23218128.0 | 16161.0 | 79656.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6620.0 | 2029527.0 | 0.0 | 2097152.0 | 302921113.0 | 885942045.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 16710712.0 | 16255585957568 | 16263299331510 | 16263299515511 | 16255586468287 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 392 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 214464 | 0x7f713e388200 | 0x7f7117c26000 | 4320584 | 4210645 | 54540126 | 65536 | 414215106 | 540072 | 540072 | 54974587.0 | 17812061.0 | 19960.0 | 26335.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6704.0 | 2041516.0 | 0.0 | 2097152.0 | 319642958.0 | 907510184.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 13302734.0 | 16255587004575 | 16263299540472 | 16263299873274 | 16255587733419 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 395 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 217728 | 0x7f713e388080 | 0x7f7117c26040 | 2166224 | 2063948 | 26694556 | 65536 | 199575242 | 270777 | 270777 | 27067565.0 | 20923431.0 | 15652.0 | 44507.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6624.0 | 2047408.0 | 0.0 | 2097152.0 | 316233029.0 | 921796817.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 15349294.0 | 16255588218148 | 16263299916634 | 16263300080635 | 16255588700577 |
| 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 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 222016 | 0x7f713c149f00 | 0x7f7117c26080 | 2959936 | 2844314 | 36586316 | 65536 | 249889761 | 369991 | 369991 | 37212297.0 | 30566761.0 | 0.0 | 178162.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 12630.0 | 8249911.0 | 0.0 | 8388608.0 | 540009298.0 | 2693693397.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 20518306.0 | 16255589237695 | 16263300106555 | 16263300338397 | 16255589800753 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 401 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 226048 | 0x7f713c149d80 | 0x7f7117c260c0 | 2942416 | 2829519 | 36428224 | 65536 | 260394776 | 367801 | 367801 | 37019845.0 | 33931572.0 | 0.0 | 175475.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 12951.0 | 8246461.0 | 0.0 | 8388608.0 | 470521969.0 | 2388822031.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 24194656.0 | 16255590298482 | 16263300373117 | 16263300602078 | 16255590890999 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 404 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 230080 | 0x7f713c149c00 | 0x7f7117c26100 | 2761944 | 2656797 | 34406013 | 65536 | 259198477 | 345242 | 345242 | 34774563.0 | 23855858.0 | 15564.0 | 36229.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6613.0 | 2031843.0 | 0.0 | 2097152.0 | 307528789.0 | 913444553.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 16834933.0 | 16255591360968 | 16263300638879 | 16263300848640 | 16255591943846 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 407 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 235904 | 0x7f713c149a80 | 0x7f7117c26140 | 4965304 | 4861392 | 62985364 | 65536 | 479509387 | 620662 | 620662 | 63434259.0 | 18676401.0 | 19602.0 | 75954.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6721.0 | 2041074.0 | 0.0 | 2097152.0 | 314206598.0 | 902268763.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 13368460.0 | 16255592414635 | 16263300881760 | 16263301264483 | 16255593162719 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 410 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 239424 | 0x7f713c149900 | 0x7f7117c26180 | 2423408 | 2315728 | 29981927 | 65536 | 225246183 | 302925 | 302925 | 30340757.0 | 21694346.0 | 15552.0 | 29883.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6643.0 | 2046778.0 | 0.0 | 2097152.0 | 313470347.0 | 911902182.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 16304134.0 | 16255593644488 | 16263301305763 | 16263301489924 | 16255594155097 |
| 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 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 244224 | 0x7f713c149780 | 0x7f7117c261c0 | 3214640 | 3105506 | 40048526 | 65536 | 274211041 | 401829 | 401829 | 40607819.0 | 31444715.0 | 0.0 | 90367.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 12847.0 | 8247560.0 | 0.0 | 8388608.0 | 463909659.0 | 2400525117.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 21404877.0 | 16255594691265 | 16263301515364 | 16263301767366 | 16255595337041 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 416 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 248768 | 0x7f713c149600 | 0x7f7117c26200 | 3124496 | 3021820 | 39126301 | 65536 | 297993041 | 390561 | 390561 | 39519771.0 | 35026344.0 | 0.0 | 107647.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 13142.0 | 8244086.0 | 0.0 | 8388608.0 | 315452876.0 | 1800505020.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 23819257.0 | 16255595807740 | 16263301802246 | 16263302047848 | 16255596410907 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 419 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 253312 | 0x7f713e388480 | 0x7f7117c26240 | 3093824 | 2990604 | 38768474 | 65536 | 297730973 | 386727 | 386727 | 39113989.0 | 23938588.0 | 16785.0 | 31006.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6628.0 | 2029571.0 | 0.0 | 2097152.0 | 354728513.0 | 1023273976.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 17080468.0 | 16255596880917 | 16263302087528 | 16263302322890 | 16255597470413 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 422 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 8 | 24 | 255552 | 0x7f713e388300 | 0x7f7117c26280 | 5708504 | 5601301 | 72579736 | 65536 | 553274694 | 713562 | 713562 | 73053115.0 | 68566664.0 | 897.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 7126.0 | 2065332.0 | 0.0 | 2097152.0 | 232617145.0 | 802443452.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 63273653.0 | 16255597943433 | 16263302382090 | 16263302832013 | 16255598803214 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 425 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 259840 | 0x7f713e388180 | 0x7f7117c262c0 | 2896768 | 2793184 | 36171135 | 65536 | 272524370 | 362095 | 362095 | 36547321.0 | 24330646.0 | 13930.0 | 30958.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6632.0 | 2045983.0 | 0.0 | 2097152.0 | 301960098.0 | 907784017.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 18409614.0 | 16255599281714 | 16263302902253 | 16263303124655 | 16255599868731 |
| 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 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 265664 | 0x7f713e388000 | 0x7f7117c26300 | 3760808 | 3658543 | 47405514 | 65536 | 361172498 | 470100 | 470100 | 47797105.0 | 33741527.0 | 0.0 | 44317.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 13078.0 | 8244802.0 | 0.0 | 8388608.0 | 305096668.0 | 1723478098.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 22688174.0 | 16255600343110 | 16263303186415 | 16263303485297 | 16255601045905 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 431 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 271232 | 0x7f713c149e80 | 0x7f7117c26340 | 3810056 | 3702092 | 47838818 | 65536 | 349894521 | 476256 | 476256 | 48363333.0 | 33362066.0 | 0.0 | 42049.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 12873.0 | 8247097.0 | 0.0 | 8388608.0 | 355702033.0 | 1957995201.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 20627571.0 | 16255601517264 | 16263303544337 | 16263303841779 | 16255602185680 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 434 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 8 | 24 | 273216 | 0x7f713c149d00 | 0x7f7117c26380 | 3835592 | 3727847 | 48213755 | 65536 | 364096803 | 479448 | 479448 | 48698265.0 | 47118559.0 | 1433.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 7662.0 | 2063703.0 | 0.0 | 2097152.0 | 235487319.0 | 806413171.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 44415517.0 | 16255602680249 | 16263303905620 | 16263304199222 | 16255603346754 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 437 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 8 | 24 | 275712 | 0x7f713c149b80 | 0x7f7117c263c0 | 7010312 | 6900284 | 89410807 | 65536 | 688051576 | 876288 | 876288 | 89939985.0 | 76177492.0 | 949.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6833.0 | 2063976.0 | 0.0 | 2097152.0 | 231842692.0 | 799688158.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 67676676.0 | 16255603814863 | 16263304260662 | 16263304814106 | 16255604719813 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 440 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 280768 | 0x7f713c149a00 | 0x7f7117c26400 | 3405184 | 3299843 | 42754765 | 65536 | 324040306 | 425647 | 425647 | 43134005.0 | 30253145.0 | 11846.0 | 69206.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6644.0 | 2028447.0 | 0.0 | 2097152.0 | 310868537.0 | 941311951.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 21997767.0 | 16255605198293 | 16263304879546 | 16263305141148 | 16255605852218 |
| 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 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 287616 | 0x7f713c149880 | 0x7f7117c26440 | 4410744 | 4307895 | 55719768 | 65536 | 412843618 | 551342 | 551342 | 56238889.0 | 35689981.0 | 0.0 | 56491.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 13007.0 | 8245601.0 | 0.0 | 8388608.0 | 331601105.0 | 1876940464.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 21855452.0 | 16255606326268 | 16263305204188 | 16263305555390 | 16255607054162 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 446 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 294208 | 0x7f713c149700 | 0x7f7117c26480 | 4413248 | 4308340 | 55742193 | 65536 | 416972250 | 551655 | 551655 | 56244557.0 | 34874806.0 | 0.0 | 120505.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 13119.0 | 8244391.0 | 0.0 | 8388608.0 | 332172506.0 | 1866319133.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 17257303.0 | 16255607525761 | 16263305600351 | 16263305950113 | 16255608233866 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 449 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 8 | 24 | 296960 | 0x7f713e388580 | 0x7f7117c264c0 | 4477528 | 4365806 | 56533604 | 65536 | 427915716 | 559690 | 559690 | 56991823.0 | 55039825.0 | 1228.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 7715.0 | 2063573.0 | 0.0 | 2097152.0 | 236186302.0 | 808258419.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 51861581.0 | 16255608704805 | 16263305989153 | 16263306333315 | 16255609452279 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 452 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 8 | 24 | 299968 | 0x7f713e388400 | 0x7f7117c26500 | 8305216 | 8195608 | 106168110 | 65536 | 810060689 | 1038151 | 1038151 | 106779275.0 | 84850934.0 | 848.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6837.0 | 2064118.0 | 0.0 | 2097152.0 | 235363339.0 | 810733391.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 73579448.0 | 16255609924079 | 16263306394276 | 16263307051240 | 16255610948776 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 455 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 8 | 24 | 302720 | 0x7f713e388280 | 0x7f7117c26540 | 5737432 | 5630379 | 72954298 | 65536 | 555456135 | 717178 | 717178 | 73430999.0 | 68447194.0 | 1004.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 7647.0 | 2063179.0 | 0.0 | 2097152.0 | 235447415.0 | 811271581.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 62348048.0 | 16255611428675 | 16263307126920 | 16263307569963 | 16255612237447 |
| 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 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 305472 | 0x7f713e388100 | 0x7f7117c26580 | 5750864 | 5646073 | 73140043 | 65536 | 557363425 | 718857 | 718857 | 73635099.0 | 69123389.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 13220.0 | 8243188.0 | 0.0 | 8388608.0 | 239051359.0 | 1595482571.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 57710835.0 | 16255612708667 | 16263307635884 | 16263308096687 | 16255613522719 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 461 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 308224 | 0x7f713c149f80 | 0x7f7117c265c0 | 5746752 | 5638604 | 73024788 | 65536 | 560989114 | 718343 | 718343 | 73538015.0 | 69039485.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 13204.0 | 8243364.0 | 0.0 | 8388608.0 | 240889711.0 | 1609361348.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 57750810.0 | 16255613993938 | 16263308163727 | 16263308621330 | 16255614816840 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 464 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 8 | 24 | 310976 | 0x7f713c149e00 | 0x7f7117c26600 | 5766624 | 5664763 | 73406677 | 65536 | 562230076 | 720827 | 720827 | 73878069.0 | 68645924.0 | 1019.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 7647.0 | 2063320.0 | 0.0 | 2097152.0 | 232829451.0 | 805157462.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 62951679.0 | 16255615284880 | 16263308685330 | 16263309133973 | 16255616125971 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 467 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 8 | 24 | 313216 | 0x7f713c149c80 | 0x7f7117c26640 | 10906488 | 10790894 | 139803336 | 65536 | 1079766768 | 1363310 | 1363310 | 140517759.0 | 95383202.0 | 853.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6835.0 | 2065379.0 | 0.0 | 2097152.0 | 235304970.0 | 810929336.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 82978088.0 | 16255616598021 | 16263309197814 | 16263310062619 | 16255617830574 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 470 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 8 | 24 | 315968 | 0x7f713c149b00 | 0x7f7117c26680 | 10924424 | 10823745 | 140243865 | 65536 | 1084052948 | 1365552 | 1365552 | 140944861.0 | 94956898.0 | 998.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 7537.0 | 2063301.0 | 0.0 | 2097152.0 | 237378753.0 | 818400841.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 80102439.0 | 16255618310203 | 16263310145340 | 16263310994305 | 16255619564106 |
| 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 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 318720 | 0x7f713c149980 | 0x7f7117c266c0 | 10957568 | 10837614 | 140401411 | 65536 | 1079193168 | 1369695 | 1369695 | 141125041.0 | 97672308.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 13273.0 | 8242605.0 | 0.0 | 8388608.0 | 237197157.0 | 1587099462.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 78585800.0 | 16255620040215 | 16263311060706 | 16263311941671 | 16255621296567 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 476 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 321472 | 0x7f713c149800 | 0x7f7117c26700 | 10936944 | 10825700 | 140250109 | 65536 | 1082265192 | 1367117 | 1367117 | 140970315.0 | 98057218.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 13168.0 | 8243760.0 | 0.0 | 8388608.0 | 235565270.0 | 1585538120.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 78351342.0 | 16255621771027 | 16263312007752 | 16263312882958 | 16255623012839 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 479 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 8 | 24 | 324224 | 0x7f713c149680 | 0x7f7117c26740 | 10970776 | 10861946 | 140749924 | 65536 | 1086829529 | 1371346 | 1371346 | 141441539.0 | 92845851.0 | 864.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 7523.0 | 2063374.0 | 0.0 | 2097152.0 | 237439586.0 | 819270887.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 82304668.0 | 16255623482199 | 16263312953678 | 16263313808403 | 16255624717602 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 482 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 8 | 24 | 326464 | 0x7f713e388500 | 0x7f7117c26780 | 21276520 | 21163564 | 274275597 | 65536 | 2131606966 | 2659564 | 2659564 | 275362599.0 | 116834804.0 | 538.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6793.0 | 2065151.0 | 0.0 | 2097152.0 | 241864455.0 | 833728798.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 96033261.0 | 16255625186811 | 16263313873364 | 16263315566495 | 16255627276495 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 485 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 8 | 24 | 329216 | 0x7f713e388380 | 0x7f7117c267c0 | 21312496 | 21204588 | 274759575 | 65536 | 2133454297 | 2664061 | 2664061 | 275895807.0 | 130961548.0 | 555.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 7916.0 | 2061986.0 | 0.0 | 2097152.0 | 242028555.0 | 838837868.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 108299586.0 | 16255627752795 | 16263315668735 | 16263317329706 | 16255629777740 |
| 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 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 331968 | 0x7f713e388200 | 0x7f7117c26800 | 21324080 | 21212638 | 274941774 | 65536 | 2135561526 | 2665509 | 2665509 | 276000405.0 | 134592988.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 13255.0 | 8242803.0 | 0.0 | 8388608.0 | 234277669.0 | 1595795102.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 107600960.0 | 16255630251989 | 16263317416907 | 16263319136438 | 16255632379042 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 491 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 12 | 24 | 334720 | 0x7f713e388080 | 0x7f7117c26840 | 21319912 | 21210595 | 274829538 | 65536 | 2128090099 | 2664988 | 2664988 | 275973885.0 | 137588191.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 33554432.0 | 33554432.0 | 33554432.0 | 0.0 | 0.0 | 0.0 | 104.0 | 8388608.0 | 13141.0 | 8244057.0 | 0.0 | 8388608.0 | 234601779.0 | 1599584988.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 4194304.0 | 0.0 | 0.0 | 111131695.0 | 16255632847792 | 16263319226678 | 16263320937889 | 16255634924676 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 494 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 8 | 24 | 337472 | 0x7f713c149f00 | 0x7f7117c26880 | 21347240 | 21239467 | 275277582 | 65536 | 2138771696 | 2668404 | 2668404 | 276349247.0 | 129343979.0 | 625.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 8000.0 | 2061984.0 | 0.0 | 2097152.0 | 241863765.0 | 838629466.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 109943191.0 | 16255635398025 | 16263321023330 | 16263322692301 | 16255637425861 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 497 | 152567 | 152567 | 4194304 | 256 | 0 | 0 | 8 | 24 | 0 | 0x7f713c149d80 | 0x7f7117c268c0 | 42015664 | 41902939 | 543111979 | 65536 | 4236378116 | 5251957 | 5251957 | 544974357.0 | 113838432.0 | 451.0 | 0.0 | 0.0 | 0.0 | 0.0 | 524288.0 | 8388608.0 | 8388608.0 | 8388608.0 | 0.0 | 0.0 | 0.0 | 104.0 | 2097152.0 | 6748.0 | 2066081.0 | 0.0 | 2097152.0 | 244282680.0 | 845748474.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 2097152.0 | 0.0 | 0.0 | 92086761.0 | 16255637900450 | 16263322781101 | 16263326133923 | 16255641643247 |