37 KiB
37 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBufferAligned.kd | 0 | 0 | 0 | 173646 | 173646 | 33554432 | 256 | 0 | 0 | 4 | 32 | 4160 | 0x0 | 0x7f6e09c04280 | 16754707778416 | 16754707803636 | 16754708043475 | 16754708156254 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 173646 | 173646 | 32768 | 256 | 0 | 0 | 12 | 24 | 13888 | 0x0 | 0x7f6e09c23f80 | 16754712841564 | 16754712857214 | 16754712870174 | 16754712888122 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 5 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 14336 | 0x7f6e0ccf7380 | 0x7f6e09c23fc0 | 16754712891302 | 16754712937053 | 16754713029533 | 16754713031628 |
| 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 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15040 | 0x7f6e0ccf7200 | 0x7f6e09c24000 | 16754713053607 | 16754713063133 | 16754713241692 | 16754713243701 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 11 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15488 | 0x7f6e0ccf7080 | 0x7f6e09c24040 | 16754713257760 | 16754713266012 | 16754713445211 | 16754713447004 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 14 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 15936 | 0x7f6e0a6c9f00 | 0x7f6e09c24080 | 16754713461564 | 16754713469851 | 16754713563931 | 16754713565650 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 17 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 16384 | 0x7f6e0a6c9d80 | 0x7f6e09c240c0 | 16754713580800 | 16754713589051 | 16754713681050 | 16754713682987 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 20 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 17088 | 0x7f6e0a6c9c00 | 0x7f6e09c24100 | 16754713710216 | 16754713721050 | 16754713813050 | 16754713814842 |
| 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 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 16 | 24 | 17792 | 0x7f6e0a6c9a80 | 0x7f6e09c24140 | 16754713833612 | 16754713850970 | 16754714030969 | 16754714032925 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 26 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 16 | 24 | 18496 | 0x7f6e0a6c9900 | 0x7f6e09c24180 | 16754714057135 | 16754714068089 | 16754714247608 | 16754714249859 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 29 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19200 | 0x7f6e0a6c9780 | 0x7f6e09c241c0 | 16754714264228 | 16754714273368 | 16754714366808 | 16754714368565 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 32 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19904 | 0x7f6e0a6c9600 | 0x7f6e09c24200 | 16754714390914 | 16754714401687 | 16754714495127 | 16754714496851 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 35 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 20608 | 0x7f6e0ccf7480 | 0x7f6e09c24240 | 16754714519270 | 16754714538647 | 16754714631446 | 16754714633476 |
| 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 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 16 | 24 | 21312 | 0x7f6e0ccf7300 | 0x7f6e09c24280 | 16754714652056 | 16754714660726 | 16754714840246 | 16754714841940 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 41 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22016 | 0x7f6e0ccf7180 | 0x7f6e09c242c0 | 16754714859889 | 16754714868725 | 16754715048085 | 16754715050003 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 44 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22720 | 0x7f6e0ccf7000 | 0x7f6e09c24300 | 16754715066082 | 16754715075125 | 16754715168724 | 16754715170559 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 47 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 23424 | 0x7f6e0a6c9e80 | 0x7f6e09c24340 | 16754715193358 | 16754715202964 | 16754715296244 | 16754715298005 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 50 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 24128 | 0x7f6e0a6c9d00 | 0x7f6e09c24380 | 16754715321154 | 16754715331763 | 16754715425203 | 16754715426941 |
| 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 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 16 | 24 | 24832 | 0x7f6e0a6c9b80 | 0x7f6e09c243c0 | 16754715444150 | 16754715452723 | 16754715631442 | 16754715633464 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 56 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 16 | 24 | 25536 | 0x7f6e0a6c9a00 | 0x7f6e09c24400 | 16754715651014 | 16754715659762 | 16754715840561 | 16754715842408 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 59 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26240 | 0x7f6e0a6c9880 | 0x7f6e09c24440 | 16754715857447 | 16754715866321 | 16754715959281 | 16754715961124 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 62 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26944 | 0x7f6e0a6c9700 | 0x7f6e09c24480 | 16754715977753 | 16754716006641 | 16754716100560 | 16754716102429 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 65 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 27648 | 0x7f6e0ccf7580 | 0x7f6e09c244c0 | 16754716122749 | 16754716133200 | 16754716225520 | 16754716227365 |
| 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 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 16 | 24 | 28608 | 0x7f6e0ccf7400 | 0x7f6e09c24500 | 16754716249335 | 16754716260240 | 16754716439439 | 16754716441148 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 71 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 16 | 24 | 29312 | 0x7f6e0ccf7280 | 0x7f6e09c24540 | 16754716456168 | 16754716464719 | 16754716644398 | 16754716646312 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 74 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 30016 | 0x7f6e0ccf7100 | 0x7f6e09c24580 | 16754716664721 | 16754716703598 | 16754716795277 | 16754716797487 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 77 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 8 | 24 | 30976 | 0x7f6e0a6c9f80 | 0x7f6e09c245c0 | 16754716818296 | 16754716828557 | 16754716920397 | 16754716921743 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 80 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 31680 | 0x7f6e0a6c9e00 | 0x7f6e09c24600 | 16754716942182 | 16754716953197 | 16754717046796 | 16754717047939 |
| 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 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 16 | 24 | 32640 | 0x7f6e0a6c9c80 | 0x7f6e09c24640 | 16754717062338 | 16754717070956 | 16754717251115 | 16754717252392 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 86 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 33600 | 0x7f6e0a6c9b00 | 0x7f6e09c24680 | 16754717265972 | 16754717274155 | 16754717456235 | 16754717457436 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 89 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 34560 | 0x7f6e0a6c9980 | 0x7f6e09c246c0 | 16754717471215 | 16754717479274 | 16754717572714 | 16754717573962 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 92 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 8 | 24 | 35520 | 0x7f6e0a6c9800 | 0x7f6e09c24700 | 16754717588282 | 16754717596074 | 16754717689354 | 16754717690458 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 95 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 36224 | 0x7f6e0a6c9680 | 0x7f6e09c24740 | 16754717711628 | 16754717721833 | 16754717814473 | 16754717815684 |
| 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 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 37184 | 0x7f6e0ccf7500 | 0x7f6e09c24780 | 16754717829224 | 16754717837513 | 16754718017192 | 16754718018468 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 101 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 38144 | 0x7f6e0ccf7380 | 0x7f6e09c247c0 | 16754718032777 | 16754718041832 | 16754718222311 | 16754718223621 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 104 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 39104 | 0x7f6e0ccf7200 | 0x7f6e09c24800 | 16754718238601 | 16754718246951 | 16754718340711 | 16754718342118 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 107 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 8 | 24 | 40320 | 0x7f6e0ccf7080 | 0x7f6e09c24840 | 16754718356247 | 16754718364071 | 16754718457990 | 16754718459364 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 110 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 41280 | 0x7f6e0a6c9f00 | 0x7f6e09c24880 | 16754718480763 | 16754718491750 | 16754718584710 | 16754718586210 |
| 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 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 42240 | 0x7f6e0a6c9d80 | 0x7f6e09c248c0 | 16754718602029 | 16754718609990 | 16754718789189 | 16754718790793 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 116 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 43200 | 0x7f6e0a6c9c00 | 0x7f6e09c24900 | 16754718805203 | 16754718813349 | 16754718993508 | 16754718994937 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 119 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 8 | 24 | 44160 | 0x7f6e0a6c9a80 | 0x7f6e09c24940 | 16754719009986 | 16754719018788 | 16754719113188 | 16754719114463 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 122 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 45376 | 0x7f6e0a6c9900 | 0x7f6e09c24980 | 16754719130042 | 16754719138148 | 16754719232387 | 16754719233749 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 125 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 46336 | 0x7f6e0a6c9780 | 0x7f6e09c249c0 | 16754719253908 | 16754719264707 | 16754719357827 | 16754719359045 |
| 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 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 47552 | 0x7f6e0a6c9600 | 0x7f6e09c24a00 | 16754719372915 | 16754719380867 | 16754719559906 | 16754719561108 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 131 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 48512 | 0x7f6e0ccf7480 | 0x7f6e09c24a40 | 16754719575288 | 16754719583746 | 16754719764545 | 16754719765792 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 134 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 8 | 24 | 49472 | 0x7f6e0ccf7300 | 0x7f6e09c24a80 | 16754719780081 | 16754719788705 | 16754719881664 | 16754719882998 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 137 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 50688 | 0x7f6e0ccf7180 | 0x7f6e09c24ac0 | 16754719898878 | 16754719908224 | 16754720001024 | 16754720002414 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 140 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 51648 | 0x7f6e0ccf7000 | 0x7f6e09c24b00 | 16754720022064 | 16754720033504 | 16754720125023 | 16754720126260 |
| 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 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 52864 | 0x7f6e0a6c9e80 | 0x7f6e09c24b40 | 16754720143530 | 16754720151583 | 16754720330143 | 16754720331434 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 146 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 54080 | 0x7f6e0a6c9d00 | 0x7f6e09c24b80 | 16754720346253 | 16754720355422 | 16754720535742 | 16754720537027 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 149 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 8 | 24 | 55296 | 0x7f6e0a6c9b80 | 0x7f6e09c24bc0 | 16754720551287 | 16754720559902 | 16754720653501 | 16754720654803 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 152 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 56768 | 0x7f6e0a6c9a00 | 0x7f6e09c24c00 | 16754720669133 | 16754720677661 | 16754720772861 | 16754720774080 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 155 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 57728 | 0x7f6e0a6c9880 | 0x7f6e09c24c40 | 16754720794279 | 16754720805501 | 16754720899420 | 16754720900786 |
| 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 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 58944 | 0x7f6e0a6c9700 | 0x7f6e09c24c80 | 16754720915315 | 16754720923580 | 16754721103579 | 16754721104759 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 161 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 60160 | 0x7f6e0ccf7580 | 0x7f6e09c24cc0 | 16754721119779 | 16754721128539 | 16754721308058 | 16754721309353 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 164 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 8 | 24 | 61376 | 0x7f6e0ccf7400 | 0x7f6e09c24d00 | 16754721322792 | 16754721331098 | 16754721425818 | 16754721427099 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 167 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 62848 | 0x7f6e0ccf7280 | 0x7f6e09c24d40 | 16754721440948 | 16754721449498 | 16754721548377 | 16754721549665 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 170 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 63808 | 0x7f6e0ccf7100 | 0x7f6e09c24d80 | 16754721569494 | 16754721580377 | 16754721673657 | 16754721674871 |
| 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 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 65024 | 0x7f6e0a6c9f80 | 0x7f6e09c24dc0 | 16754721692030 | 16754721701337 | 16754721880696 | 16754721881984 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 176 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 66240 | 0x7f6e0a6c9e00 | 0x7f6e09c24e00 | 16754721895524 | 16754721904216 | 16754722084375 | 16754722086018 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 179 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 8 | 24 | 67456 | 0x7f6e0a6c9c80 | 0x7f6e09c24e40 | 16754722104097 | 16754722112055 | 16754722207415 | 16754722208694 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 182 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 68928 | 0x7f6e0a6c9b00 | 0x7f6e09c24e80 | 16754722224323 | 16754722232695 | 16754722337334 | 16754722338500 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 185 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 70144 | 0x7f6e0a6c9980 | 0x7f6e09c24ec0 | 16754722359879 | 16754722370614 | 16754722463094 | 16754722464336 |
| 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 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 71616 | 0x7f6e0a6c9800 | 0x7f6e09c24f00 | 16754722479875 | 16754722488054 | 16754722668533 | 16754722669729 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 191 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 72832 | 0x7f6e0a6c9680 | 0x7f6e09c24f40 | 16754722686458 | 16754722694933 | 16754722875092 | 16754722876522 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 194 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 8 | 24 | 74048 | 0x7f6e0ccf7500 | 0x7f6e09c24f80 | 16754722891622 | 16754722899252 | 16754722992211 | 16754722993519 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 197 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 75776 | 0x7f6e0ccf7380 | 0x7f6e09c24fc0 | 16754723007228 | 16754723015251 | 16754723122131 | 16754723123424 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 200 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 76992 | 0x7f6e0ccf7200 | 0x7f6e09c25000 | 16754723143654 | 16754723154611 | 16754723249330 | 16754723250560 |
| 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 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 78464 | 0x7f6e0ccf7080 | 0x7f6e09c25040 | 16754723264980 | 16754723273490 | 16754723453649 | 16754723454964 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 206 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 79936 | 0x7f6e0a6c9f00 | 0x7f6e09c25080 | 16754723468923 | 16754723477649 | 16754723656529 | 16754723657817 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 209 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 8 | 24 | 81408 | 0x7f6e0a6c9d80 | 0x7f6e09c250c0 | 16754723670457 | 16754723678929 | 16754723773168 | 16754723774514 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 212 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 83136 | 0x7f6e0a6c9c00 | 0x7f6e09c25100 | 16754723788623 | 16754723796688 | 16754723911728 | 16754723912919 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 215 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 84352 | 0x7f6e0a6c9a80 | 0x7f6e09c25140 | 16754723948058 | 16754723957967 | 16754724052047 | 16754724053415 |
| 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 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 85824 | 0x7f6e0a6c9900 | 0x7f6e09c25180 | 16754724068384 | 16754724077007 | 16754724256206 | 16754724257458 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 221 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 87296 | 0x7f6e0a6c9780 | 0x7f6e09c251c0 | 16754724270768 | 16754724279086 | 16754724457325 | 16754724458612 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 224 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 88768 | 0x7f6e0a6c9600 | 0x7f6e09c25200 | 16754724472211 | 16754724480205 | 16754724575245 | 16754724576478 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 227 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 90752 | 0x7f6e0ccf7480 | 0x7f6e09c25240 | 16754724595237 | 16754724603085 | 16754724724364 | 16754724725583 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 230 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 91968 | 0x7f6e0ccf7300 | 0x7f6e09c25280 | 16754724746332 | 16754724757964 | 16754724851564 | 16754724852809 |
| 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 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 93440 | 0x7f6e0ccf7180 | 0x7f6e09c252c0 | 16754724868549 | 16754724876844 | 16754725056203 | 16754725057412 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 236 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 94912 | 0x7f6e0ccf7000 | 0x7f6e09c25300 | 16754725073432 | 16754725081643 | 16754725260522 | 16754725261736 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 239 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 96384 | 0x7f6e0a6c9e80 | 0x7f6e09c25340 | 16754725277725 | 16754725286442 | 16754725381801 | 16754725383012 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 242 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 98368 | 0x7f6e0a6c9d00 | 0x7f6e09c25380 | 16754725402301 | 16754725416841 | 16754725543241 | 16754725544567 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 245 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 99584 | 0x7f6e0a6c9b80 | 0x7f6e09c253c0 | 16754725564356 | 16754725575561 | 16754725669800 | 16754725670983 |
| 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 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 101312 | 0x7f6e0a6c9a00 | 0x7f6e09c25400 | 16754725685632 | 16754725693480 | 16754725873639 | 16754725874856 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 251 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 102784 | 0x7f6e0a6c9880 | 0x7f6e09c25440 | 16754725888496 | 16754725896679 | 16754726078598 | 16754726080620 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 254 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 104256 | 0x7f6e0a6c9700 | 0x7f6e09c25480 | 16754726097579 | 16754726105798 | 16754726200038 | 16754726201366 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 257 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 106240 | 0x7f6e0ccf7580 | 0x7f6e09c254c0 | 16754726216395 | 16754726224838 | 16754726355397 | 16754726356691 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 260 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 107712 | 0x7f6e0ccf7400 | 0x7f6e09c25500 | 16754726377110 | 16754726387717 | 16754726481157 | 16754726482407 |
| 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 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 16 | 24 | 109440 | 0x7f6e0ccf7280 | 0x7f6e09c25540 | 16754726498106 | 16754726507237 | 16754726688196 | 16754726689520 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 266 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 16 | 24 | 111168 | 0x7f6e0ccf7100 | 0x7f6e09c25580 | 16754726703530 | 16754726711396 | 16754726891875 | 16754726893094 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 269 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 8 | 24 | 112896 | 0x7f6e0a6c9f80 | 0x7f6e09c255c0 | 16754726905913 | 16754726914115 | 16754727010275 | 16754727011740 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 272 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 115136 | 0x7f6e0a6c9e00 | 0x7f6e09c25600 | 16754727025649 | 16754727033795 | 16754727172674 | 16754727174085 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 275 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 116608 | 0x7f6e0a6c9c80 | 0x7f6e09c25640 | 16754727194094 | 16754727204994 | 16754727299233 | 16754727300641 |
| 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 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 16 | 24 | 118336 | 0x7f6e0a6c9b00 | 0x7f6e09c25680 | 16754727315160 | 16754727323233 | 16754727502913 | 16754727504284 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 281 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 16 | 24 | 120064 | 0x7f6e0a6c9980 | 0x7f6e09c256c0 | 16754727517414 | 16754727526112 | 16754727706912 | 16754727708298 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 284 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 121792 | 0x7f6e0a6c9800 | 0x7f6e09c25700 | 16754727722207 | 16754727730272 | 16754727827551 | 16754727828904 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 287 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 124032 | 0x7f6e0a6c9680 | 0x7f6e09c25740 | 16754727843753 | 16754727851551 | 16754727996990 | 16754727998388 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 290 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 125504 | 0x7f6e0ccf7500 | 0x7f6e09c25780 | 16754728018028 | 16754728028830 | 16754728123390 | 16754728124784 |
| 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 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 127488 | 0x7f6e0ccf7380 | 0x7f6e09c257c0 | 16754728138684 | 16754728147070 | 16754728328989 | 16754728330288 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 296 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 129216 | 0x7f6e0ccf7200 | 0x7f6e09c25800 | 16754728344157 | 16754728352349 | 16754728533948 | 16754728535221 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 299 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 130944 | 0x7f6e0ccf7080 | 0x7f6e09c25840 | 16754728548261 | 16754728557148 | 16754728657148 | 16754728658397 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 302 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 133440 | 0x7f6e0a6c9f00 | 0x7f6e09c25880 | 16754728671867 | 16754728680188 | 16754728835387 | 16754728836651 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 305 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 134912 | 0x7f6e0a6c9d80 | 0x7f6e09c258c0 | 16754728856261 | 16754728867387 | 16754728962266 | 16754728963587 |
| 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 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 136896 | 0x7f6e0a6c9c00 | 0x7f6e09c25900 | 16754728977797 | 16754728986266 | 16754729165786 | 16754729166991 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 311 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 138880 | 0x7f6e0a6c9a80 | 0x7f6e09c25940 | 16754729181670 | 16754729190105 | 16754729369625 | 16754729370894 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 314 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 140864 | 0x7f6e0a6c9900 | 0x7f6e09c25980 | 16754729385034 | 16754729393625 | 16754729500184 | 16754729501450 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 317 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 143616 | 0x7f6e0a6c9780 | 0x7f6e09c259c0 | 16754729516000 | 16754729524184 | 16754729693943 | 16754729695394 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 320 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 145344 | 0x7f6e0a6c9600 | 0x7f6e09c25a00 | 16754729716543 | 16754729727383 | 16754729823223 | 16754729824460 |
| 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 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 147584 | 0x7f6e0ccf7480 | 0x7f6e09c25a40 | 16754729840359 | 16754729848343 | 16754730030262 | 16754730031513 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 326 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 149568 | 0x7f6e0ccf7300 | 0x7f6e09c25a80 | 16754730047573 | 16754730055862 | 16754730238421 | 16754730239747 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 329 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 151552 | 0x7f6e0ccf7180 | 0x7f6e09c25ac0 | 16754730253976 | 16754730261941 | 16754730372501 | 16754730373832 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 332 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 154304 | 0x7f6e0ccf7000 | 0x7f6e09c25b00 | 16754730387992 | 16754730396020 | 16754730577300 | 16754730578706 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 335 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 156288 | 0x7f6e0a6c9e80 | 0x7f6e09c25b40 | 16754730599385 | 16754730609460 | 16754730710579 | 16754730711971 |
| 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 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 158784 | 0x7f6e0a6c9d00 | 0x7f6e09c25b80 | 16754730726621 | 16754730734739 | 16754730917138 | 16754730918545 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 341 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 161024 | 0x7f6e0a6c9b80 | 0x7f6e09c25bc0 | 16754730932444 | 16754730940658 | 16754731125777 | 16754731127218 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 344 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 163264 | 0x7f6e0a6c9a00 | 0x7f6e09c25c00 | 16754731142818 | 16754731150897 | 16754731273137 | 16754731274633 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 347 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 166528 | 0x7f6e0a6c9880 | 0x7f6e09c25c40 | 16754731289803 | 16754731298097 | 16754731504496 | 16754731526445 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 350 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 168512 | 0x7f6e0a6c9700 | 0x7f6e09c25c80 | 16754731541205 | 16754731552336 | 16754731664015 | 16754731665291 |
| 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 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 171264 | 0x7f6e0ccf7580 | 0x7f6e09c25cc0 | 16754731679560 | 16754731688015 | 16754731873134 | 16754731874454 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 356 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 173760 | 0x7f6e0ccf7400 | 0x7f6e09c25d00 | 16754731889324 | 16754731897454 | 16754732084013 | 16754732085507 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 359 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 176256 | 0x7f6e0ccf7280 | 0x7f6e09c25d40 | 16754732100127 | 16754732108013 | 16754732242893 | 16754732244172 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 362 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 179776 | 0x7f6e0ccf7100 | 0x7f6e09c25d80 | 16754732257802 | 16754732265773 | 16754732497932 | 16754732540763 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 365 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 182272 | 0x7f6e0a6c9f80 | 0x7f6e09c25dc0 | 16754732555452 | 16754732566731 | 16754732693611 | 16754732694908 |
| 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 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 185536 | 0x7f6e0a6c9e00 | 0x7f6e09c25e00 | 16754732710967 | 16754732718891 | 16754732909290 | 16754732910771 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 371 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 188544 | 0x7f6e0a6c9c80 | 0x7f6e09c25e40 | 16754732924981 | 16754732933610 | 16754733124169 | 16754733125544 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 374 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 191552 | 0x7f6e0a6c9b00 | 0x7f6e09c25e80 | 16754733139404 | 16754733147529 | 16754733307528 | 16754733308788 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 377 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 195840 | 0x7f6e0a6c9980 | 0x7f6e09c25ec0 | 16754733322528 | 16754733330728 | 16754733614087 | 16754733635148 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 380 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 198592 | 0x7f6e0a6c9800 | 0x7f6e09c25f00 | 16754733650467 | 16754733661767 | 16754733811366 | 16754733812622 |
| 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 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 202368 | 0x7f6e0a6c9680 | 0x7f6e09c25f40 | 16754733830382 | 16754733838406 | 16754734046405 | 16754734065214 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 386 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 205888 | 0x7f6e0ccf7500 | 0x7f6e09c25f80 | 16754734072984 | 16754734095685 | 16754734306244 | 16754734352795 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 389 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 209408 | 0x7f6e0ccf7380 | 0x7f6e09c25fc0 | 16754734360725 | 16754734370884 | 16754734556483 | 16754734557788 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 392 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 214464 | 0x7f6e0ccf7200 | 0x7f6e09c26000 | 16754734572608 | 16754734580803 | 16754734915362 | 16754734934076 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 395 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 217728 | 0x7f6e0ccf7080 | 0x7f6e09c26040 | 16754734949196 | 16754734960001 | 16754735127841 | 16754735129060 |
| 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 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 222016 | 0x7f6e0a6c9f00 | 0x7f6e09c26080 | 16754735143690 | 16754735151681 | 16754735379200 | 16754735398161 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 401 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 226048 | 0x7f6e0a6c9d80 | 0x7f6e09c260c0 | 16754735406101 | 16754735416479 | 16754735645438 | 16754735664293 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 404 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 230080 | 0x7f6e0a6c9c00 | 0x7f6e09c26100 | 16754735672053 | 16754735682078 | 16754735893437 | 16754735912185 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 407 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 235904 | 0x7f6e0a6c9a80 | 0x7f6e09c26140 | 16754735921485 | 16754735930717 | 16754736316316 | 16754736334691 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 410 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 239424 | 0x7f6e0a6c9900 | 0x7f6e09c26180 | 16754736349961 | 16754736360955 | 16754736548315 | 16754736549545 |
| 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 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 244224 | 0x7f6e0a6c9780 | 0x7f6e09c261c0 | 16754736565424 | 16754736573435 | 16754736823514 | 16754736842365 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 416 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 248768 | 0x7f6e0a6c9600 | 0x7f6e09c26200 | 16754736850685 | 16754736860793 | 16754737109432 | 16754737127636 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 419 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 253312 | 0x7f6e0ccf7480 | 0x7f6e09c26240 | 16754737135106 | 16754737145592 | 16754737382391 | 16754737397997 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 422 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 8 | 24 | 255552 | 0x7f6e0ccf7300 | 0x7f6e09c26280 | 16754737406957 | 16754737417591 | 16754737871509 | 16754737886952 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 425 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 259840 | 0x7f6e0ccf7180 | 0x7f6e09c262c0 | 16754737901951 | 16754737912949 | 16754738138868 | 16754738158723 |
| 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 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 265664 | 0x7f6e0ccf7000 | 0x7f6e09c26300 | 16754738169503 | 16754738179988 | 16754738477907 | 16754738497292 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 431 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 271232 | 0x7f6e0a6c9e80 | 0x7f6e09c26340 | 16754738508132 | 16754738518226 | 16754738816945 | 16754738838981 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 434 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 8 | 24 | 273216 | 0x7f6e0a6c9d00 | 0x7f6e09c26380 | 16754738848301 | 16754738858705 | 16754739155184 | 16754739176470 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 437 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 8 | 24 | 275712 | 0x7f6e0a6c9b80 | 0x7f6e09c263c0 | 16754739184930 | 16754739195344 | 16754739753261 | 16754739769051 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 440 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 280768 | 0x7f6e0a6c9a00 | 0x7f6e09c26400 | 16754739785261 | 16754739796141 | 16754740059980 | 16754740081651 |
| 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 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 287616 | 0x7f6e0a6c9880 | 0x7f6e09c26440 | 16754740089541 | 16754740099980 | 16754740451978 | 16754740473139 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 446 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 294208 | 0x7f6e0a6c9700 | 0x7f6e09c26480 | 16754740481159 | 16754740495818 | 16754740846057 | 16754740867846 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 449 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 8 | 24 | 296960 | 0x7f6e0ccf7580 | 0x7f6e09c264c0 | 16754740876656 | 16754740887017 | 16754741234375 | 16754741252674 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 452 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 8 | 24 | 299968 | 0x7f6e0ccf7400 | 0x7f6e09c26500 | 16754741261084 | 16754741271175 | 16754741932292 | 16754741954691 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 455 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 8 | 24 | 302720 | 0x7f6e0ccf7280 | 0x7f6e09c26540 | 16754741971051 | 16754741980772 | 16754742429250 | 16754742453155 |
| 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 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 305472 | 0x7f6e0ccf7100 | 0x7f6e09c26580 | 16754742462215 | 16754742472450 | 16754742937408 | 16754742961669 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 461 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 308224 | 0x7f6e0a6c9f80 | 0x7f6e09c265c0 | 16754742972989 | 16754742989408 | 16754743451006 | 16754743474483 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 464 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 8 | 24 | 310976 | 0x7f6e0a6c9e00 | 0x7f6e09c26600 | 16754743482383 | 16754743492766 | 16754743945244 | 16754743968967 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 467 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 8 | 24 | 313216 | 0x7f6e0a6c9c80 | 0x7f6e09c26640 | 16754743978637 | 16754743988444 | 16754744858200 | 16754744881088 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 470 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 8 | 24 | 315968 | 0x7f6e0a6c9b00 | 0x7f6e09c26680 | 16754744898067 | 16754744909400 | 16754745763796 | 16754745786889 |
| 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 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 318720 | 0x7f6e0a6c9980 | 0x7f6e09c266c0 | 16754745798258 | 16754745813556 | 16754746698992 | 16754746726399 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 476 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 321472 | 0x7f6e0a6c9800 | 0x7f6e09c26700 | 16754746735608 | 16754746746192 | 16754747626188 | 16754747650549 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 479 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 8 | 24 | 324224 | 0x7f6e0a6c9680 | 0x7f6e09c26740 | 16754747660409 | 16754747676908 | 16754748536105 | 16754748560530 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 482 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 8 | 24 | 326464 | 0x7f6e0ccf7500 | 0x7f6e09c26780 | 16754748570410 | 16754748580104 | 16754750279297 | 16754750354462 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 485 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 8 | 24 | 329216 | 0x7f6e0ccf7380 | 0x7f6e09c267c0 | 16754750372972 | 16754750383777 | 16754752049530 | 16754752117996 |
| 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 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 331968 | 0x7f6e0ccf7200 | 0x7f6e09c26800 | 16754752129436 | 16754752144089 | 16754753869842 | 16754753939198 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 491 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 12 | 24 | 334720 | 0x7f6e0ccf7080 | 0x7f6e09c26840 | 16754753950177 | 16754753964402 | 16754755680395 | 16754755749780 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 494 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 8 | 24 | 337472 | 0x7f6e0a6c9f00 | 0x7f6e09c26880 | 16754755760109 | 16754755769674 | 16754757444547 | 16754757510853 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 497 | 173646 | 173646 | 4194304 | 256 | 0 | 0 | 8 | 24 | 0 | 0x7f6e0a6c9d80 | 0x7f6e09c268c0 | 16754757520743 | 16754757530627 | 16754760889013 | 16754760965263 |