43 KiB
43 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | SQ_INSTS_SMEM | SQ_INST_LEVEL_SMEM | SQ_ACCUM_PREV_HIRES | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBuffer.kd | 0 | 0 | 0 | 852343 | 852348 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7f1281c04180 | 4194304 | 3113414 | 398152752 | 12074899625250804 | 12074899870091626 | 12074899870413864 | 12074899870526486 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 852343 | 852348 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7f1281c35100 | 512 | 24164 | 3091584 | 12074899885466780 | 12074899885762069 | 12074899885768149 | 12074899885772278 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7f138d92a900 | 0x7f1281c35140 | 65536 | 186070 | 23892320 | 12074899885835055 | 12074899886060468 | 12074899886199187 | 12074899886202548 |
| 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 | 6 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7f138d92a800 | 0x7f1281c35180 | 65536 | 163302 | 20826632 | 12074899886271406 | 12074899886445906 | 12074899886696305 | 12074899886766606 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7f138d92a700 | 0x7f1281c351c0 | 65536 | 175516 | 22548216 | 12074899886799166 | 12074899886988303 | 12074899887236462 | 12074899887307090 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7f138d92a600 | 0x7f1281c35200 | 65536 | 187146 | 23940456 | 12074899887333139 | 12074899887522221 | 12074899887661100 | 12074899887663603 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7f138d92a500 | 0x7f1281c35240 | 65536 | 197590 | 25233016 | 12074899887716561 | 12074899887883659 | 12074899888014058 | 12074899888016659 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7f138d92a400 | 0x7f1281c35280 | 131072 | 249138 | 31591024 | 12074899888090326 | 12074899888258217 | 12074899888388777 | 12074899888391335 |
| 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 | 16 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7f138d92a300 | 0x7f1281c352c0 | 131072 | 222722 | 28445728 | 12074899888440537 | 12074899888616136 | 12074899888871814 | 12074899888915499 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7f138d92aa00 | 0x7f1281c35300 | 65536 | 184476 | 23597952 | 12074899888941057 | 12074899889132773 | 12074899889427172 | 12074899889470360 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7f138d92a900 | 0x7f1281c35340 | 131072 | 277406 | 35576904 | 12074899889494555 | 12074899889686530 | 12074899889819010 | 12074899889821523 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7f138d92a800 | 0x7f1281c35380 | 131072 | 258922 | 33117432 | 12074899889868821 | 12074899890052129 | 12074899890188928 | 12074899890191821 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7f138d92a700 | 0x7f1281c353c0 | 131072 | 258128 | 33047032 | 12074899890261781 | 12074899890429887 | 12074899890558526 | 12074899890561067 |
| 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 | 26 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7f138d92a600 | 0x7f1281c35400 | 131072 | 215294 | 27598888 | 12074899890610689 | 12074899890783965 | 12074899891044284 | 12074899891113113 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7f138d92a500 | 0x7f1281c35440 | 65536 | 184330 | 23662184 | 12074899891141796 | 12074899891325243 | 12074899891579801 | 12074899891648258 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7f138d92a400 | 0x7f1281c35480 | 131072 | 257324 | 33018024 | 12074899891674226 | 12074899891856760 | 12074899891986839 | 12074899891989432 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7f138d92a300 | 0x7f1281c354c0 | 131072 | 263962 | 33965040 | 12074899892038503 | 12074899892214678 | 12074899892347798 | 12074899892350252 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7f138d92aa00 | 0x7f1281c35500 | 131072 | 253406 | 32721760 | 12074899892413410 | 12074899892578196 | 12074899892710356 | 12074899892712846 |
| 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 | 36 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7f138d92a900 | 0x7f1281c35540 | 131072 | 219078 | 27973728 | 12074899892762649 | 12074899892931475 | 12074899893188434 | 12074899893256667 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7f138d92a800 | 0x7f1281c35580 | 65536 | 184306 | 23566928 | 12074899893281322 | 12074899893472432 | 12074899893721551 | 12074899893789407 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7f138d92a700 | 0x7f1281c355c0 | 131072 | 252262 | 32339304 | 12074899893815495 | 12074899893995630 | 12074899894122829 | 12074899894125611 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7f138d92a600 | 0x7f1281c35600 | 131072 | 259244 | 33195000 | 12074899894181395 | 12074899894353548 | 12074899894489707 | 12074899894492183 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7f138d92a500 | 0x7f1281c35640 | 131072 | 277604 | 35529456 | 12074899894552785 | 12074899894718666 | 12074899894850666 | 12074899894853174 |
| 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 | 46 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7f138d92a400 | 0x7f1281c35680 | 131072 | 212446 | 27106296 | 12074899894900341 | 12074899895080264 | 12074899895334503 | 12074899895402665 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7f138d92a300 | 0x7f1281c356c0 | 65536 | 184988 | 23665104 | 12074899895430476 | 12074899895614022 | 12074899895866341 | 12074899895934092 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7f138d92aa00 | 0x7f1281c35700 | 131072 | 260530 | 33377736 | 12074899895959980 | 12074899896150979 | 12074899896278979 | 12074899896281919 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7f138d92a900 | 0x7f1281c35740 | 131072 | 258980 | 33168464 | 12074899896329958 | 12074899896505538 | 12074899896638337 | 12074899896640936 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7f138d92a800 | 0x7f1281c35780 | 131072 | 256854 | 32879336 | 12074899896700216 | 12074899896866656 | 12074899896999615 | 12074899897006125 |
| 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 | 56 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7f138d92a700 | 0x7f1281c357c0 | 131072 | 222644 | 28526304 | 12074899897052801 | 12074899897230974 | 12074899897481533 | 12074899897549334 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7f138d92a600 | 0x7f1281c35800 | 65536 | 188514 | 24020776 | 12074899897573679 | 12074899897756092 | 12074899898009850 | 12074899898078918 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7f138d92a500 | 0x7f1281c35840 | 131072 | 257822 | 33116688 | 12074899898106289 | 12074899898296889 | 12074899898427928 | 12074899898430492 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7f138d92a400 | 0x7f1281c35880 | 131072 | 278972 | 35711752 | 12074899898477359 | 12074899898650167 | 12074899898781687 | 12074899898784139 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7f138d92a300 | 0x7f1281c358c0 | 131072 | 257848 | 32948920 | 12074899898843429 | 12074899899007286 | 12074899899134965 | 12074899899137876 |
| 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 | 66 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7f138d92aa00 | 0x7f1281c35900 | 131072 | 217290 | 27868016 | 12074899899189061 | 12074899899361204 | 12074899899619603 | 12074899899687237 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7f138d92a900 | 0x7f1281c35940 | 65536 | 188260 | 24003640 | 12074899899715720 | 12074899899891601 | 12074899900140720 | 12074899900208596 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7f138d92a800 | 0x7f1281c35980 | 131072 | 259544 | 33215408 | 12074899900234534 | 12074899900415279 | 12074899900552078 | 12074899900554970 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7f138d92a700 | 0x7f1281c359c0 | 131072 | 263026 | 33671608 | 12074899900602859 | 12074899900783757 | 12074899900918636 | 12074899900921070 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7f138d92a600 | 0x7f1281c35a00 | 131072 | 253324 | 32426576 | 12074899900981192 | 12074899901151595 | 12074899901281515 | 12074899901283994 |
| 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 | 76 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7f138d92a500 | 0x7f1281c35a40 | 131072 | 212464 | 27191304 | 12074899901332424 | 12074899901504394 | 12074899901767112 | 12074899901834387 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7f138d92a400 | 0x7f1281c35a80 | 65536 | 189500 | 24262416 | 12074899901860416 | 12074899902052231 | 12074899902307590 | 12074899902378178 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7f138d92a300 | 0x7f1281c35ac0 | 131072 | 256224 | 32797064 | 12074899902401942 | 12074899902587108 | 12074899902722308 | 12074899902725042 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7f138d92aa00 | 0x7f1281c35b00 | 131072 | 265640 | 34071152 | 12074899902774675 | 12074899902945347 | 12074899903082146 | 12074899903085091 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7f138d92a900 | 0x7f1281c35b40 | 131072 | 263398 | 33529048 | 12074899903152447 | 12074899903319265 | 12074899903447584 | 12074899903450120 |
| 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 | 86 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7f138d92a800 | 0x7f1281c35b80 | 131072 | 220150 | 28249000 | 12074899903500844 | 12074899903665023 | 12074899903933022 | 12074899904010091 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7f138d92a700 | 0x7f1281c35bc0 | 65536 | 183224 | 23450832 | 12074899904034346 | 12074899904221661 | 12074899904514299 | 12074899904582945 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7f138d92a600 | 0x7f1281c35c00 | 131072 | 254096 | 32500072 | 12074899904609484 | 12074899904795418 | 12074899904930937 | 12074899904933507 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7f138d92a500 | 0x7f1281c35c40 | 131072 | 244208 | 31216384 | 12074899904984111 | 12074899905172216 | 12074899905306295 | 12074899905309215 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7f138d92a400 | 0x7f1281c35c80 | 131072 | 253334 | 32414616 | 12074899905370368 | 12074899905538134 | 12074899905669814 | 12074899905672470 |
| 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 | 96 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7f138d92a300 | 0x7f1281c35cc0 | 131072 | 216902 | 27736752 | 12074899905719918 | 12074899905890933 | 12074899906154291 | 12074899906224275 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7f138d92aa00 | 0x7f1281c35d00 | 65536 | 190020 | 24306520 | 12074899906254211 | 12074899906433490 | 12074899906688849 | 12074899906757156 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7f138d92a900 | 0x7f1281c35d40 | 131072 | 253432 | 32325536 | 12074899906782493 | 12074899906960687 | 12074899907094607 | 12074899907097618 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7f138d92a800 | 0x7f1281c35d80 | 131072 | 258370 | 33011128 | 12074899907150196 | 12074899907319246 | 12074899907456525 | 12074899907459150 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7f138d92a700 | 0x7f1281c35dc0 | 131072 | 260242 | 33198752 | 12074899907518220 | 12074899907681804 | 12074899907811723 | 12074899907814400 |
| 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 | 106 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7f138d92a600 | 0x7f1281c35e00 | 131072 | 273070 | 34989992 | 12074899907864253 | 12074899908039882 | 12074899908297321 | 12074899908366737 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7f138d92a500 | 0x7f1281c35e40 | 65536 | 188950 | 24128840 | 12074899908393637 | 12074899908574920 | 12074899908830758 | 12074899908899817 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7f138d92a400 | 0x7f1281c35e80 | 131072 | 259836 | 33418336 | 12074899908923261 | 12074899909119717 | 12074899909251076 | 12074899909253735 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7f138d92a300 | 0x7f1281c35ec0 | 131072 | 259000 | 33206128 | 12074899909305281 | 12074899909474115 | 12074899909620515 | 12074899909623142 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7f138d92aa00 | 0x7f1281c35f00 | 131072 | 261068 | 33460136 | 12074899909684075 | 12074899909848513 | 12074899909987553 | 12074899909990264 |
| 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 | 116 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7f138d92a900 | 0x7f1281c35f40 | 131072 | 258390 | 33107568 | 12074899910045947 | 12074899910214432 | 12074899910481950 | 12074899910550475 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7f138d92a800 | 0x7f1281c35f80 | 65536 | 182844 | 23499752 | 12074899910577635 | 12074899910755229 | 12074899911002748 | 12074899911045795 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7f138d92a700 | 0x7f1281c35fc0 | 131072 | 279348 | 35789448 | 12074899911070131 | 12074899911253147 | 12074899911388026 | 12074899911390556 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7f138d92a600 | 0x7f1281c36000 | 131072 | 257350 | 33012472 | 12074899911441361 | 12074899911605945 | 12074899911746584 | 12074899911749123 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7f138d92a500 | 0x7f1281c36040 | 131072 | 262138 | 33638504 | 12074899911808242 | 12074899911974903 | 12074899912108023 | 12074899912110855 |
| 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 | 126 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7f138d92a400 | 0x7f1281c36080 | 131072 | 221826 | 28305880 | 12074899912162861 | 12074899912328822 | 12074899912592180 | 12074899912661067 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7f138d92a300 | 0x7f1281c360c0 | 65536 | 178160 | 22870008 | 12074899912687707 | 12074899912867059 | 12074899913125138 | 12074899913194499 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7f138d92aa00 | 0x7f1281c36100 | 131072 | 259594 | 33276640 | 12074899913219335 | 12074899913400976 | 12074899913535376 | 12074899913537927 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7f138d92a900 | 0x7f1281c36140 | 131072 | 229760 | 29402432 | 12074899913584984 | 12074899913754255 | 12074899913900174 | 12074899913902905 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7f138d92a800 | 0x7f1281c36180 | 131072 | 271286 | 34649400 | 12074899913964610 | 12074899914136173 | 12074899914274252 | 12074899914276860 |
| 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 | 136 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7f138d92a700 | 0x7f1281c361c0 | 131072 | 244940 | 31400064 | 12074899914324639 | 12074899914495211 | 12074899914763050 | 12074899914786848 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7f138d92a600 | 0x7f1281c36200 | 65536 | 188600 | 24053704 | 12074899914827814 | 12074899914989449 | 12074899915245608 | 12074899915296585 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7f138d92a500 | 0x7f1281c36240 | 131072 | 260538 | 33078336 | 12074899915323545 | 12074899915502406 | 12074899915633286 | 12074899915636196 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7f138d92a400 | 0x7f1281c36280 | 131072 | 220408 | 28165128 | 12074899915687612 | 12074899915854245 | 12074899916004324 | 12074899916007005 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7f138d92a300 | 0x7f1281c362c0 | 131072 | 257486 | 33004424 | 12074899916095470 | 12074899916258723 | 12074899916392642 | 12074899916395347 |
| 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 | 146 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7f138d92aa00 | 0x7f1281c36300 | 131072 | 222918 | 28369208 | 12074899916442715 | 12074899916616161 | 12074899916881440 | 12074899916930842 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7f138d92a900 | 0x7f1281c36340 | 65536 | 184438 | 23507872 | 12074899916957191 | 12074899917142078 | 12074899917399677 | 12074899917449897 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7f138d92a800 | 0x7f1281c36380 | 131072 | 260154 | 33320264 | 12074899917473901 | 12074899917654236 | 12074899917786395 | 12074899917789317 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7f138d92a700 | 0x7f1281c363c0 | 131072 | 260534 | 33410336 | 12074899917835573 | 12074899918003994 | 12074899918162554 | 12074899918165597 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7f138d92a600 | 0x7f1281c36400 | 131072 | 261292 | 33365816 | 12074899918226630 | 12074899918395672 | 12074899918527992 | 12074899918530886 |
| 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 | 156 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7f138d92a500 | 0x7f1281c36440 | 131072 | 218850 | 27917272 | 12074899918577362 | 12074899918750231 | 12074899919014069 | 12074899919064407 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7f138d92a400 | 0x7f1281c36480 | 65536 | 189882 | 24309984 | 12074899919092359 | 12074899919273268 | 12074899919527347 | 12074899919576519 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7f138d92a300 | 0x7f1281c364c0 | 131072 | 256884 | 32887456 | 12074899919599491 | 12074899919781426 | 12074899919917905 | 12074899919920518 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7f138d92aa00 | 0x7f1281c36500 | 131072 | 259140 | 33118008 | 12074899919970571 | 12074899920151504 | 12074899920317103 | 12074899920320080 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7f138d92a900 | 0x7f1281c36540 | 131072 | 256656 | 32930232 | 12074899920380623 | 12074899920543982 | 12074899920678381 | 12074899920681482 |
| 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 | 166 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7f138d92a800 | 0x7f1281c36580 | 131072 | 216468 | 27668880 | 12074899920730844 | 12074899920902540 | 12074899921162539 | 12074899921211567 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7f138d92a700 | 0x7f1281c365c0 | 65536 | 195732 | 25146208 | 12074899921237576 | 12074899921416298 | 12074899921672137 | 12074899921721525 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7f138d92a600 | 0x7f1281c36600 | 131072 | 259314 | 33068784 | 12074899921744247 | 12074899921931655 | 12074899922070055 | 12074899922073609 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7f138d92a500 | 0x7f1281c36640 | 131072 | 256070 | 32787600 | 12074899922124363 | 12074899922292294 | 12074899922467333 | 12074899922469956 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7f138d92a400 | 0x7f1281c36680 | 131072 | 256172 | 32809648 | 12074899922531250 | 12074899922694372 | 12074899922829251 | 12074899922831898 |
| 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 | 176 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7f138d92a300 | 0x7f1281c366c0 | 131072 | 215632 | 27678736 | 12074899922879266 | 12074899923059970 | 12074899923319169 | 12074899923369968 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7f138d92aa00 | 0x7f1281c36700 | 65536 | 177302 | 22595320 | 12074899923394163 | 12074899923575967 | 12074899923828286 | 12074899923877552 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7f138d92a900 | 0x7f1281c36740 | 131072 | 254474 | 32482096 | 12074899923901726 | 12074899924092445 | 12074899924228764 | 12074899924231740 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7f138d92a800 | 0x7f1281c36780 | 131072 | 257444 | 33149536 | 12074899924280691 | 12074899924454043 | 12074899924636282 | 12074899924639287 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7f138d92a700 | 0x7f1281c367c0 | 131072 | 258356 | 32884168 | 12074899924698878 | 12074899924863321 | 12074899924999961 | 12074899925005748 |
| 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 | 186 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7f138d92a600 | 0x7f1281c36800 | 131072 | 260386 | 33151048 | 12074899925054699 | 12074899925220440 | 12074899925487318 | 12074899925536234 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7f138d92a500 | 0x7f1281c36840 | 65536 | 177708 | 22774360 | 12074899925562753 | 12074899925739637 | 12074899925997236 | 12074899926020724 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7f138d92a400 | 0x7f1281c36880 | 131072 | 272314 | 34826928 | 12074899926063804 | 12074899926228755 | 12074899926359634 | 12074899926362570 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7f138d92a300 | 0x7f1281c368c0 | 131072 | 257256 | 33030368 | 12074899926411721 | 12074899926583153 | 12074899926775152 | 12074899926824448 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7f138d92aa00 | 0x7f1281c36900 | 131072 | 251118 | 32202336 | 12074899926865053 | 12074899927036751 | 12074899927176270 | 12074899927179057 |
| 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 | 196 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7f138d92a900 | 0x7f1281c36940 | 131072 | 261280 | 33356464 | 12074899927226315 | 12074899927401549 | 12074899927687308 | 12074899927736663 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7f138d92a800 | 0x7f1281c36980 | 65536 | 191016 | 24611024 | 12074899927761690 | 12074899927945866 | 12074899928198985 | 12074899928250268 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7f138d92a700 | 0x7f1281c369c0 | 131072 | 257858 | 33003040 | 12074899928274112 | 12074899928456744 | 12074899928596583 | 12074899928599316 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7f138d92a600 | 0x7f1281c36a00 | 131072 | 260022 | 33237880 | 12074899928653407 | 12074899928813862 | 12074899929024101 | 12074899929073638 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7f138d92a500 | 0x7f1281c36a40 | 131072 | 259634 | 33184504 | 12074899929115075 | 12074899929280100 | 12074899929417219 | 12074899929420072 |
| 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 | 206 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7f138d92a400 | 0x7f1281c36a80 | 131072 | 258834 | 33272168 | 12074899929467440 | 12074899929637058 | 12074899929943937 | 12074899929970004 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7f138d92a300 | 0x7f1281c36ac0 | 65536 | 183180 | 23508080 | 12074899930017893 | 12074899930181696 | 12074899930439455 | 12074899930467708 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7f138d92aa00 | 0x7f1281c36b00 | 131072 | 259928 | 33150664 | 12074899930511019 | 12074899930676893 | 12074899930812573 | 12074899930815375 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7f138d92a900 | 0x7f1281c36b40 | 131072 | 259916 | 33182392 | 12074899930868273 | 12074899931035932 | 12074899931264251 | 12074899931291028 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7f138d92a800 | 0x7f1281c36b80 | 131072 | 285394 | 36486016 | 12074899931354877 | 12074899931522329 | 12074899931661049 | 12074899931663921 |
| 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 | 216 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7f138d92a700 | 0x7f1281c36bc0 | 131072 | 258774 | 33077392 | 12074899931711820 | 12074899931892248 | 12074899932251926 | 12074899932280367 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7f138d92a600 | 0x7f1281c36c00 | 65536 | 187546 | 24009808 | 12074899932323337 | 12074899932491925 | 12074899932751923 | 12074899932776629 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7f138d92a500 | 0x7f1281c36c40 | 131072 | 254456 | 32590768 | 12074899932819198 | 12074899932980471 | 12074899933120471 | 12074899933127421 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7f138d92a400 | 0x7f1281c36c80 | 131072 | 249968 | 31785264 | 12074899933171493 | 12074899933347029 | 12074899933591827 | 12074899933616961 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7f138d92a300 | 0x7f1281c36cc0 | 131072 | 254750 | 32735184 | 12074899933672053 | 12074899933836626 | 12074899933978066 | 12074899933980607 |
| 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 | 226 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7f138d92aa00 | 0x7f1281c36d00 | 131072 | 258044 | 33149400 | 12074899934034577 | 12074899934208625 | 12074899934584783 | 12074899934612391 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7f138d92a900 | 0x7f1281c36d40 | 65536 | 172106 | 22136032 | 12074899934649099 | 12074899934810382 | 12074899935067821 | 12074899935095609 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7f138d92a800 | 0x7f1281c36d80 | 131072 | 229808 | 29399424 | 12074899935137807 | 12074899935302860 | 12074899935446219 | 12074899935449026 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7f138d92a700 | 0x7f1281c36dc0 | 131072 | 260568 | 33364712 | 12074899935500692 | 12074899935667018 | 12074899935947337 | 12074899935973841 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7f138d92a600 | 0x7f1281c36e00 | 131072 | 263530 | 33540472 | 12074899936037269 | 12074899936207016 | 12074899936350215 | 12074899936352895 |
| 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 | 236 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7f138d92a500 | 0x7f1281c36e40 | 131072 | 255496 | 32760280 | 12074899936401315 | 12074899936574214 | 12074899937000452 | 12074899937026687 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7f138d92a400 | 0x7f1281c36e80 | 65536 | 191784 | 24631120 | 12074899937075168 | 12074899937246531 | 12074899937505570 | 12074899937530263 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7f138d92a300 | 0x7f1281c36ec0 | 131072 | 262818 | 33340608 | 12074899937581278 | 12074899937748929 | 12074899937892928 | 12074899937895422 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7f138d92aa00 | 0x7f1281c36f00 | 131072 | 259204 | 33193088 | 12074899937947839 | 12074899938117407 | 12074899938432286 | 12074899938461384 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7f138d92a900 | 0x7f1281c36f40 | 131072 | 256140 | 33006584 | 12074899938518710 | 12074899938682844 | 12074899938834684 | 12074899938837182 |
| 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 | 246 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7f138d92a800 | 0x7f1281c36f80 | 131072 | 259940 | 33051016 | 12074899938890812 | 12074899939073243 | 12074899939591640 | 12074899939618744 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7f138d92a700 | 0x7f1281c36fc0 | 65536 | 183288 | 23530696 | 12074899939670240 | 12074899939834839 | 12074899940132918 | 12074899940160391 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7f138d92a600 | 0x7f1281c37000 | 131072 | 253866 | 32526816 | 12074899940204924 | 12074899940370037 | 12074899940524436 | 12074899940526942 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7f138d92a500 | 0x7f1281c37040 | 131072 | 258060 | 33135712 | 12074899940576645 | 12074899940750035 | 12074899941136433 | 12074899941163876 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7f138d92a400 | 0x7f1281c37080 | 131072 | 263036 | 33481888 | 12074899941223517 | 12074899941390352 | 12074899941565711 | 12074899941568297 |
| 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 | 256 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7f138d92a300 | 0x7f1281c370c0 | 131072 | 260654 | 33428240 | 12074899941615034 | 12074899941796750 | 12074899942408748 | 12074899942438705 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7f138d92aa00 | 0x7f1281c37100 | 65536 | 212372 | 27337200 | 12074899942479681 | 12074899942644266 | 12074899942971305 | 12074899942997203 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7f138d92a900 | 0x7f1281c37140 | 131072 | 256158 | 32823216 | 12074899943048869 | 12074899943219464 | 12074899943398343 | 12074899943401294 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7f138d92a800 | 0x7f1281c37180 | 131072 | 259142 | 33098128 | 12074899943449684 | 12074899943621222 | 12074899944077220 | 12074899944102397 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7f138d92a700 | 0x7f1281c371c0 | 131072 | 258018 | 33206128 | 12074899944164372 | 12074899944330179 | 12074899944530498 | 12074899944579323 |
| 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 | 266 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7f138d92a600 | 0x7f1281c37200 | 131072 | 260830 | 33409976 | 12074899944609749 | 12074899944783937 | 12074899945488094 | 12074899945538335 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7f138d92a500 | 0x7f1281c37240 | 65536 | 185850 | 23713456 | 12074899945562720 | 12074899945749532 | 12074899946123771 | 12074899946173686 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7f138d92a400 | 0x7f1281c37280 | 131072 | 257428 | 32923616 | 12074899946198161 | 12074899946388410 | 12074899946591769 | 12074899946639742 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7f138d92a300 | 0x7f1281c372c0 | 131072 | 255904 | 32811464 | 12074899946666572 | 12074899946844247 | 12074899947370485 | 12074899947422096 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7f138d92aa00 | 0x7f1281c37300 | 131072 | 259318 | 33195008 | 12074899947462000 | 12074899947627924 | 12074899947852403 | 12074899947900836 |
| 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 | 276 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7f138d92a900 | 0x7f1281c37340 | 131072 | 249498 | 32229328 | 12074899947926964 | 12074899948121842 | 12074899948921998 | 12074899948974771 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7f138d92a800 | 0x7f1281c37380 | 65536 | 187940 | 23987672 | 12074899949007071 | 12074899949187757 | 12074899949609195 | 12074899949660325 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7f138d92a700 | 0x7f1281c373c0 | 131072 | 251452 | 32306432 | 12074899949687085 | 12074899949863914 | 12074899950089993 | 12074899950141620 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7f138d92a600 | 0x7f1281c37400 | 131072 | 261494 | 33609112 | 12074899950169271 | 12074899950350312 | 12074899950947269 | 12074899950996969 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7f138d92a500 | 0x7f1281c37440 | 131072 | 271166 | 34579552 | 12074899951047724 | 12074899951214148 | 12074899951515106 | 12074899951566698 |
| 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 | 286 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7f138d92a400 | 0x7f1281c37480 | 131072 | 244900 | 31618368 | 12074899951591464 | 12074899951776065 | 12074899952762941 | 12074899952831889 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7f138d92a300 | 0x7f1281c374c0 | 65536 | 193530 | 24722048 | 12074899952863658 | 12074899953054939 | 12074899953569977 | 12074899953639210 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7f138d92aa00 | 0x7f1281c37500 | 131072 | 259908 | 33243088 | 12074899953663375 | 12074899953852376 | 12074899954123415 | 12074899954192728 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7f138d92a900 | 0x7f1281c37540 | 131072 | 255460 | 32827208 | 12074899954224067 | 12074899954400693 | 12074899955140210 | 12074899955208726 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7f138d92a800 | 0x7f1281c37580 | 131072 | 277252 | 35373984 | 12074899955250374 | 12074899955418289 | 12074899955735087 | 12074899955803892 |
| 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 | 296 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7f138d92a700 | 0x7f1281c375c0 | 131072 | 278814 | 35726784 | 12074899955834589 | 12074899956024046 | 12074899957196841 | 12074899957267943 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7f138d92a600 | 0x7f1281c37600 | 65536 | 191114 | 24273224 | 12074899957300143 | 12074899957475079 | 12074899958087397 | 12074899958156925 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7f138d92a500 | 0x7f1281c37640 | 131072 | 253468 | 32417120 | 12074899958187602 | 12074899958371715 | 12074899958690914 | 12074899958759836 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7f138d92a400 | 0x7f1281c37680 | 131072 | 256704 | 32866848 | 12074899958791555 | 12074899958968033 | 12074899959847069 | 12074899959917988 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7f138d92a300 | 0x7f1281c376c0 | 131072 | 271748 | 35018880 | 12074899959964615 | 12074899960139387 | 12074899960551065 | 12074899960620874 |
| 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 | 306 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7f138d92aa00 | 0x7f1281c37700 | 131072 | 261156 | 33300480 | 12074899960645089 | 12074899960832664 | 12074899962381937 | 12074899962451696 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7f138d92a900 | 0x7f1281c37740 | 65536 | 203734 | 26160144 | 12074899962486030 | 12074899962666416 | 12074899963463212 | 12074899963533747 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7f138d92a800 | 0x7f1281c37780 | 131072 | 257492 | 33018696 | 12074899963565216 | 12074899963743851 | 12074899964159209 | 12074899964229290 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7f138d92a700 | 0x7f1281c377c0 | 131072 | 268504 | 34295768 | 12074899964261420 | 12074899964437448 | 12074899965596483 | 12074899965665769 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7f138d92a600 | 0x7f1281c37800 | 131072 | 255656 | 32716768 | 12074899965710523 | 12074899965879041 | 12074899966664478 | 12074899966734706 |
| 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 | 316 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7f138d92a500 | 0x7f1281c37840 | 131072 | 259800 | 33376480 | 12074899966765974 | 12074899966949597 | 12074899970002223 | 12074899970073070 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7f138d92a400 | 0x7f1281c37880 | 65536 | 189396 | 24081568 | 12074899970104107 | 12074899970285901 | 12074899971829414 | 12074899971898532 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7f138d92a300 | 0x7f1281c378c0 | 131072 | 258350 | 33319280 | 12074899971930321 | 12074899972111333 | 12074899972902210 | 12074899972973440 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7f138d92aa00 | 0x7f1281c37900 | 131072 | 259854 | 33292208 | 12074899973010378 | 12074899973199328 | 12074899975482678 | 12074899975552723 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7f138d92a900 | 0x7f1281c37940 | 131072 | 274112 | 35074824 | 12074899975599209 | 12074899975765877 | 12074899977302510 | 12074899977373236 |
| 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 | 326 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7f138d92a800 | 0x7f1281c37980 | 131072 | 275238 | 35312840 | 12074899977404083 | 12074899977588428 | 12074899983648401 | 12074899983722075 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7f138d92a700 | 0x7f1281c379c0 | 65536 | 186788 | 23763104 | 12074899983748965 | 12074899983934320 | 12074899986979906 | 12074899987051622 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7f138d92a600 | 0x7f1281c37a00 | 131072 | 253162 | 32410080 | 12074899987082349 | 12074899987267905 | 12074899988807258 | 12074899988877435 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 852343 | 852348 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7f138d92a500 | 0x7f1281c37a40 | 131072 | 271888 | 34530368 | 12074899988908453 | 12074899989098136 | 12074899993626596 | 12074899993701430 |