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 | 80643 | 80643 | 33554432 | 256 | 0 | 0 | 4 | 32 | 4160 | 0x0 | 0x7ff682204280 | 14980298964549 | 14980298990601 | 14980299230601 | 14980299318021 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 80643 | 80643 | 32768 | 256 | 0 | 0 | 12 | 24 | 13888 | 0x0 | 0x7ff682223f80 | 14980304042106 | 14980304058133 | 14980304071573 | 14980304089435 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 5 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 14336 | 0x7ff685304380 | 0x7ff682223fc0 | 14980304094144 | 14980304142934 | 14980304236214 | 14980304238181 |
| 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 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15040 | 0x7ff685304200 | 0x7ff682224000 | 14980304261830 | 14980304271414 | 14980304450294 | 14980304452366 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 11 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15488 | 0x7ff685304080 | 0x7ff682224040 | 14980304467625 | 14980304475895 | 14980304654135 | 14980304656141 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 14 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 15936 | 0x7ff682cd7f00 | 0x7ff682224080 | 14980304670530 | 14980304678935 | 14980304772055 | 14980304774198 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 17 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 16384 | 0x7ff682cd7d80 | 0x7ff6822240c0 | 14980304790108 | 14980304798455 | 14980304890776 | 14980304892695 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 20 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 17088 | 0x7ff682cd7c00 | 0x7ff682224100 | 14980304919284 | 14980304929976 | 14980305022296 | 14980305024322 |
| 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 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 16 | 24 | 17792 | 0x7ff682cd7a80 | 0x7ff682224140 | 14980305044891 | 14980305054456 | 14980305233497 | 14980305235397 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 26 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 16 | 24 | 18496 | 0x7ff682cd7900 | 0x7ff682224180 | 14980305254026 | 14980305262937 | 14980305442617 | 14980305444512 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 29 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19200 | 0x7ff682cd7780 | 0x7ff6822241c0 | 14980305462561 | 14980305481817 | 14980305575418 | 14980305577678 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 32 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19904 | 0x7ff682cd7600 | 0x7ff682224200 | 14980305594698 | 14980305603898 | 14980305697178 | 14980305699185 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 35 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 20608 | 0x7ff685304480 | 0x7ff682224240 | 14980305718825 | 14980305729658 | 14980305822778 | 14980305824572 |
| 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 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 16 | 24 | 21312 | 0x7ff685304300 | 0x7ff682224280 | 14980305850532 | 14980305861018 | 14980306041339 | 14980306043267 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 41 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22016 | 0x7ff685304180 | 0x7ff6822242c0 | 14980306063157 | 14980306077659 | 14980306256699 | 14980306258762 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 44 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22720 | 0x7ff685304000 | 0x7ff682224300 | 14980306275061 | 14980306283899 | 14980306377020 | 14980306379079 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 47 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 23424 | 0x7ff682cd7e80 | 0x7ff682224340 | 14980306397618 | 14980306407260 | 14980306500700 | 14980306502726 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 50 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 24128 | 0x7ff682cd7d00 | 0x7ff682224380 | 14980306524265 | 14980306535100 | 14980306627740 | 14980306629713 |
| 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 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 16 | 24 | 24832 | 0x7ff682cd7b80 | 0x7ff6822243c0 | 14980306647252 | 14980306656540 | 14980306836541 | 14980306838538 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 56 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 16 | 24 | 25536 | 0x7ff682cd7a00 | 0x7ff682224400 | 14980306856387 | 14980306870781 | 14980307051102 | 14980307053162 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 59 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26240 | 0x7ff682cd7880 | 0x7ff682224440 | 14980307070622 | 14980307081502 | 14980307174942 | 14980307176899 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 62 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26944 | 0x7ff682cd7700 | 0x7ff682224480 | 14980307189669 | 14980307198942 | 14980307291422 | 14980307293347 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 65 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 27648 | 0x7ff685304580 | 0x7ff6822244c0 | 14980307313236 | 14980307323742 | 14980307416543 | 14980307418414 |
| 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 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 16 | 24 | 28608 | 0x7ff685304400 | 0x7ff682224500 | 14980307440303 | 14980307450623 | 14980307629663 | 14980307631598 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 71 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 16 | 24 | 29312 | 0x7ff685304280 | 0x7ff682224540 | 14980307645908 | 14980307656063 | 14980307838144 | 14980307840163 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 74 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 30016 | 0x7ff685304100 | 0x7ff682224580 | 14980307857603 | 14980307889344 | 14980307981504 | 14980307983620 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 77 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 8 | 24 | 30976 | 0x7ff682cd7f80 | 0x7ff6822245c0 | 14980308002389 | 14980308011744 | 14980308104224 | 14980308106137 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 80 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 31680 | 0x7ff682cd7e00 | 0x7ff682224600 | 14980308128376 | 14980308138784 | 14980308231425 | 14980308233424 |
| 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 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 16 | 24 | 32640 | 0x7ff682cd7c80 | 0x7ff682224640 | 14980308249623 | 14980308259585 | 14980308438785 | 14980308440729 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 86 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 33600 | 0x7ff682cd7b00 | 0x7ff682224680 | 14980308458228 | 14980308467105 | 14980308648546 | 14980308650714 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 89 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 34560 | 0x7ff682cd7980 | 0x7ff6822246c0 | 14980308667203 | 14980308677506 | 14980308771426 | 14980308772821 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 92 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 8 | 24 | 35520 | 0x7ff682cd7800 | 0x7ff682224700 | 14980308790100 | 14980308798146 | 14980308892387 | 14980308893838 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 95 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 36224 | 0x7ff682cd7680 | 0x7ff682224740 | 14980308917867 | 14980308927427 | 14980309021667 | 14980309023164 |
| 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 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 37184 | 0x7ff685304500 | 0x7ff682224780 | 14980309038384 | 14980309046467 | 14980309226307 | 14980309227739 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 101 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 38144 | 0x7ff685304380 | 0x7ff6822247c0 | 14980309244009 | 14980309254308 | 14980309434308 | 14980309435804 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 104 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 39104 | 0x7ff685304200 | 0x7ff682224800 | 14980309451534 | 14980309460868 | 14980309553828 | 14980309555312 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 107 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 8 | 24 | 40320 | 0x7ff685304080 | 0x7ff682224840 | 14980309570751 | 14980309580388 | 14980309674469 | 14980309675959 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 110 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 41280 | 0x7ff682cd7f00 | 0x7ff682224880 | 14980309696638 | 14980309707429 | 14980309800549 | 14980309801946 |
| 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 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 42240 | 0x7ff682cd7d80 | 0x7ff6822248c0 | 14980309819195 | 14980309827429 | 14980310007110 | 14980310008610 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 116 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 43200 | 0x7ff682cd7c00 | 0x7ff682224900 | 14980310023860 | 14980310032390 | 14980310212710 | 14980310214455 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 119 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 8 | 24 | 44160 | 0x7ff682cd7a80 | 0x7ff682224940 | 14980310229955 | 14980310238950 | 14980310332550 | 14980310334173 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 122 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 45376 | 0x7ff682cd7900 | 0x7ff682224980 | 14980310348792 | 14980310356870 | 14980310452551 | 14980310454100 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 125 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 46336 | 0x7ff682cd7780 | 0x7ff6822249c0 | 14980310474669 | 14980310485031 | 14980310578791 | 14980310580307 |
| 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 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 47552 | 0x7ff682cd7600 | 0x7ff682224a00 | 14980310595496 | 14980310603591 | 14980310781672 | 14980310783322 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 131 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 48512 | 0x7ff685304480 | 0x7ff682224a40 | 14980310797361 | 14980310805672 | 14980310985832 | 14980310987317 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 134 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 8 | 24 | 49472 | 0x7ff685304300 | 0x7ff682224a80 | 14980311001416 | 14980311009832 | 14980311102473 | 14980311104024 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 137 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 50688 | 0x7ff685304180 | 0x7ff682224ac0 | 14980311119064 | 14980311128393 | 14980311222313 | 14980311223971 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 140 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 51648 | 0x7ff685304000 | 0x7ff682224b00 | 14980311245251 | 14980311255593 | 14980311347433 | 14980311348928 |
| 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 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 52864 | 0x7ff682cd7e80 | 0x7ff682224b40 | 14980311365238 | 14980311373513 | 14980311553354 | 14980311554893 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 146 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 54080 | 0x7ff682cd7d00 | 0x7ff682224b80 | 14980311568203 | 14980311576394 | 14980311755274 | 14980311756908 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 149 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 8 | 24 | 55296 | 0x7ff682cd7b80 | 0x7ff682224bc0 | 14980311770728 | 14980311778634 | 14980311873995 | 14980311875555 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 152 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 56768 | 0x7ff682cd7a00 | 0x7ff682224c00 | 14980311890375 | 14980311898795 | 14980311993835 | 14980311995322 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 155 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 57728 | 0x7ff682cd7880 | 0x7ff682224c40 | 14980312015572 | 14980312026635 | 14980312119915 | 14980312121509 |
| 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 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 58944 | 0x7ff682cd7700 | 0x7ff682224c80 | 14980312137059 | 14980312145035 | 14980312323916 | 14980312325394 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 161 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 60160 | 0x7ff685304580 | 0x7ff682224cc0 | 14980312339714 | 14980312348396 | 14980312530956 | 14980312532319 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 164 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 8 | 24 | 61376 | 0x7ff685304400 | 0x7ff682224d00 | 14980312549049 | 14980312556876 | 14980312651117 | 14980312652567 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 167 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 62848 | 0x7ff685304280 | 0x7ff682224d40 | 14980312667666 | 14980312676077 | 14980312775757 | 14980312777284 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 170 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 63808 | 0x7ff685304100 | 0x7ff682224d80 | 14980312797233 | 14980312807917 | 14980312902477 | 14980312903920 |
| 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 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 65024 | 0x7ff682cd7f80 | 0x7ff682224dc0 | 14980312923520 | 14980312934478 | 14980313113998 | 14980313115485 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 176 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 66240 | 0x7ff682cd7e00 | 0x7ff682224e00 | 14980313130905 | 14980313139278 | 14980313318479 | 14980313319910 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 179 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 8 | 24 | 67456 | 0x7ff682cd7c80 | 0x7ff682224e40 | 14980313336670 | 14980313344719 | 14980313439279 | 14980313440707 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 182 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 68928 | 0x7ff682cd7b00 | 0x7ff682224e80 | 14980313455667 | 14980313463919 | 14980313567279 | 14980313568774 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 185 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 70144 | 0x7ff682cd7980 | 0x7ff682224ec0 | 14980313588644 | 14980313599599 | 14980313692400 | 14980313693831 |
| 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 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 71616 | 0x7ff682cd7800 | 0x7ff682224f00 | 14980313709111 | 14980313717200 | 14980313895760 | 14980313897276 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 191 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 72832 | 0x7ff682cd7680 | 0x7ff682224f40 | 14980313912766 | 14980313921680 | 14980314100881 | 14980314102411 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 194 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 8 | 24 | 74048 | 0x7ff685304500 | 0x7ff682224f80 | 14980314119021 | 14980314127441 | 14980314220881 | 14980314222379 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 197 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 75776 | 0x7ff685304380 | 0x7ff682224fc0 | 14980314236558 | 14980314244881 | 14980314351921 | 14980314353375 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 200 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 76992 | 0x7ff685304200 | 0x7ff682225000 | 14980314372955 | 14980314384241 | 14980314477682 | 14980314479112 |
| 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 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 78464 | 0x7ff685304080 | 0x7ff682225040 | 14980314494772 | 14980314502962 | 14980314682642 | 14980314684137 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 206 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 79936 | 0x7ff682cd7f00 | 0x7ff682225080 | 14980314698507 | 14980314706962 | 14980314887923 | 14980314889292 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 209 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 8 | 24 | 81408 | 0x7ff682cd7d80 | 0x7ff6822250c0 | 14980314903342 | 14980314912563 | 14980315007763 | 14980315009289 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 212 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 83136 | 0x7ff682cd7c00 | 0x7ff682225100 | 14980315023889 | 14980315032563 | 14980315148084 | 14980315149506 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 215 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 84352 | 0x7ff682cd7a80 | 0x7ff682225140 | 14980315185895 | 14980315195764 | 14980315289524 | 14980315290993 |
| 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 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 85824 | 0x7ff682cd7900 | 0x7ff682225180 | 14980315306092 | 14980315314484 | 14980315493204 | 14980315494738 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 221 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 87296 | 0x7ff682cd7780 | 0x7ff6822251c0 | 14980315510967 | 14980315518805 | 14980315698645 | 14980315700093 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 224 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 88768 | 0x7ff682cd7600 | 0x7ff682225200 | 14980315715222 | 14980315723765 | 14980315818485 | 14980315819990 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 227 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 90752 | 0x7ff685304480 | 0x7ff682225240 | 14980315834869 | 14980315843765 | 14980315965686 | 14980315967086 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 230 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 91968 | 0x7ff685304300 | 0x7ff682225280 | 14980315988266 | 14980315998646 | 14980316092886 | 14980316094273 |
| 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 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 93440 | 0x7ff685304180 | 0x7ff6822252c0 | 14980316111013 | 14980316119286 | 14980316299447 | 14980316300898 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 236 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 94912 | 0x7ff685304000 | 0x7ff682225300 | 14980316317148 | 14980316325207 | 14980316507447 | 14980316508863 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 239 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 96384 | 0x7ff682cd7e80 | 0x7ff682225340 | 14980316523803 | 14980316532407 | 14980316627128 | 14980316628640 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 242 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 98368 | 0x7ff682cd7d00 | 0x7ff682225380 | 14980316645830 | 14980316654488 | 14980316780888 | 14980316782376 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 245 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 99584 | 0x7ff682cd7b80 | 0x7ff6822253c0 | 14980316804106 | 14980316814968 | 14980316908568 | 14980316910093 |
| 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 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 101312 | 0x7ff682cd7a00 | 0x7ff682225400 | 14980316926203 | 14980316934488 | 14980317114809 | 14980317116198 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 251 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 102784 | 0x7ff682cd7880 | 0x7ff682225440 | 14980317131498 | 14980317139929 | 14980317320889 | 14980317322323 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 254 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 104256 | 0x7ff682cd7700 | 0x7ff682225480 | 14980317337153 | 14980317345209 | 14980317439610 | 14980317441040 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 257 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 106240 | 0x7ff685304580 | 0x7ff6822254c0 | 14980317456560 | 14980317464730 | 14980317595450 | 14980317596816 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 260 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 107712 | 0x7ff685304400 | 0x7ff682225500 | 14980317617576 | 14980317628090 | 14980317721371 | 14980317722803 |
| 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 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 16 | 24 | 109440 | 0x7ff685304280 | 0x7ff682225540 | 14980317738073 | 14980317746811 | 14980317926971 | 14980317928428 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 266 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 16 | 24 | 111168 | 0x7ff685304100 | 0x7ff682225580 | 14980317944618 | 14980317952731 | 14980318133532 | 14980318135203 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 269 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 8 | 24 | 112896 | 0x7ff682cd7f80 | 0x7ff6822255c0 | 14980318151313 | 14980318159932 | 14980318256252 | 14980318257980 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 272 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 115136 | 0x7ff682cd7e00 | 0x7ff682225600 | 14980318272310 | 14980318280732 | 14980318418492 | 14980318420066 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 275 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 116608 | 0x7ff682cd7c80 | 0x7ff682225640 | 14980318439746 | 14980318450812 | 14980318545853 | 14980318547443 |
| 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 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 16 | 24 | 118336 | 0x7ff682cd7b00 | 0x7ff682225680 | 14980318562763 | 14980318571293 | 14980318751293 | 14980318752838 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 281 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 16 | 24 | 120064 | 0x7ff682cd7980 | 0x7ff6822256c0 | 14980318767458 | 14980318777053 | 14980318956254 | 14980318957773 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 284 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 121792 | 0x7ff682cd7800 | 0x7ff682225700 | 14980318971743 | 14980318979934 | 14980319077214 | 14980319078660 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 287 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 124032 | 0x7ff682cd7680 | 0x7ff682225740 | 14980319094730 | 14980319103134 | 14980319248415 | 14980319249846 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 290 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 125504 | 0x7ff685304500 | 0x7ff682225780 | 14980319271586 | 14980319282335 | 14980319377855 | 14980319379333 |
| 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 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 127488 | 0x7ff685304380 | 0x7ff6822257c0 | 14980319394243 | 14980319402175 | 14980319582016 | 14980319583408 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 296 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 129216 | 0x7ff685304200 | 0x7ff682225800 | 14980319598048 | 14980319606976 | 14980319788576 | 14980319790053 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 299 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 130944 | 0x7ff685304080 | 0x7ff682225840 | 14980319803593 | 14980319812896 | 14980319913216 | 14980319914720 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 302 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 133440 | 0x7ff682cd7f00 | 0x7ff682225880 | 14980319928650 | 14980319937217 | 14980320092577 | 14980320094096 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 305 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 134912 | 0x7ff682cd7d80 | 0x7ff6822258c0 | 14980320115065 | 14980320126017 | 14980320221537 | 14980320223052 |
| 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 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 136896 | 0x7ff682cd7c00 | 0x7ff682225900 | 14980320239962 | 14980320248257 | 14980320427938 | 14980320429337 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 311 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 138880 | 0x7ff682cd7a80 | 0x7ff682225940 | 14980320447397 | 14980320455138 | 14980320635458 | 14980320636972 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 314 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 140864 | 0x7ff682cd7900 | 0x7ff682225980 | 14980320651422 | 14980320659458 | 14980320766659 | 14980320768169 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 317 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 143616 | 0x7ff682cd7780 | 0x7ff6822259c0 | 14980320782529 | 14980320791139 | 14980320962499 | 14980320963954 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 320 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 145344 | 0x7ff682cd7600 | 0x7ff682225a00 | 14980320984834 | 14980320995299 | 14980321090340 | 14980321091711 |
| 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 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 147584 | 0x7ff685304480 | 0x7ff682225a40 | 14980321109021 | 14980321117220 | 14980321298340 | 14980321299826 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 326 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 149568 | 0x7ff685304300 | 0x7ff682225a80 | 14980321314076 | 14980321323300 | 14980321505381 | 14980321506911 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 329 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 151552 | 0x7ff685304180 | 0x7ff682225ac0 | 14980321520861 | 14980321529381 | 14980321639621 | 14980321641058 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 332 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 154304 | 0x7ff685304000 | 0x7ff682225b00 | 14980321657828 | 14980321666821 | 14980321848262 | 14980321849713 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 335 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 156288 | 0x7ff682cd7e80 | 0x7ff682225b40 | 14980321872722 | 14980321882022 | 14980321982822 | 14980321984280 |
| 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 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 158784 | 0x7ff682cd7d00 | 0x7ff682225b80 | 14980322000779 | 14980322008742 | 14980322194983 | 14980322196424 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 341 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 161024 | 0x7ff682cd7b80 | 0x7ff682225bc0 | 14980322211554 | 14980322219783 | 14980322407143 | 14980322408909 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 344 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 163264 | 0x7ff682cd7a00 | 0x7ff682225c00 | 14980322423039 | 14980322431143 | 14980322554184 | 14980322555766 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 347 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 166528 | 0x7ff682cd7880 | 0x7ff682225c40 | 14980322571485 | 14980322579944 | 14980322786984 | 14980322831149 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 350 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 168512 | 0x7ff682cd7700 | 0x7ff682225c80 | 14980322847059 | 14980322857864 | 14980322969065 | 14980322970636 |
| 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 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 171264 | 0x7ff685304580 | 0x7ff682225cc0 | 14980322985415 | 14980322994185 | 14980323176105 | 14980323177701 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 356 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 173760 | 0x7ff685304400 | 0x7ff682225d00 | 14980323191910 | 14980323200265 | 14980323388906 | 14980323390465 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 359 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 176256 | 0x7ff685304280 | 0x7ff682225d40 | 14980323405195 | 14980323413546 | 14980323547946 | 14980323549562 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 362 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 179776 | 0x7ff685304100 | 0x7ff682225d80 | 14980323564141 | 14980323572106 | 14980323804427 | 14980323848864 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 365 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 182272 | 0x7ff682cd7f80 | 0x7ff682225dc0 | 14980323864154 | 14980323874987 | 14980324002188 | 14980324003560 |
| 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 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 185536 | 0x7ff682cd7e00 | 0x7ff682225e00 | 14980324018330 | 14980324026348 | 14980324217708 | 14980324219205 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 371 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 188544 | 0x7ff682cd7c80 | 0x7ff682225e40 | 14980324233805 | 14980324242508 | 14980324435949 | 14980324437580 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 374 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 191552 | 0x7ff682cd7b00 | 0x7ff682225e80 | 14980324452570 | 14980324460749 | 14980324620749 | 14980324622175 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 377 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 195840 | 0x7ff682cd7980 | 0x7ff682225ec0 | 14980324637055 | 14980324645069 | 14980324928270 | 14980324972037 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 380 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 198592 | 0x7ff682cd7800 | 0x7ff682225f00 | 14980324987837 | 14980324998830 | 14980325147631 | 14980325149173 |
| 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 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 202368 | 0x7ff682cd7680 | 0x7ff682225f40 | 14980325165882 | 14980325174031 | 14980325382831 | 14980325401516 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 386 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 205888 | 0x7ff685304500 | 0x7ff682225f80 | 14980325412196 | 14980325422351 | 14980325631952 | 14980325650660 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 389 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 209408 | 0x7ff685304380 | 0x7ff682225fc0 | 14980325659310 | 14980325669552 | 14980325855153 | 14980325856595 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 392 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 214464 | 0x7ff685304200 | 0x7ff682226000 | 14980325870925 | 14980325879473 | 14980326214354 | 14980326257926 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 395 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 217728 | 0x7ff685304080 | 0x7ff682226040 | 14980326275845 | 14980326286514 | 14980326454514 | 14980326455961 |
| 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 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 222016 | 0x7ff682cd7f00 | 0x7ff682226080 | 14980326472970 | 14980326481234 | 14980326710195 | 14980326750034 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 401 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 226048 | 0x7ff682cd7d80 | 0x7ff6822260c0 | 14980326760073 | 14980326770195 | 14980327000916 | 14980327044236 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 404 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 230080 | 0x7ff682cd7c00 | 0x7ff682226100 | 14980327055336 | 14980327065556 | 14980327276916 | 14980327317000 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 407 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 235904 | 0x7ff682cd7a80 | 0x7ff682226140 | 14980327329090 | 14980327338197 | 14980327723638 | 14980327763869 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 410 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 239424 | 0x7ff682cd7900 | 0x7ff682226180 | 14980327780029 | 14980327790998 | 14980327978518 | 14980327980004 |
| 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 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 244224 | 0x7ff682cd7780 | 0x7ff6822261c0 | 14980327994573 | 14980328002998 | 14980328253079 | 14980328296206 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 416 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 248768 | 0x7ff682cd7600 | 0x7ff682226200 | 14980328303596 | 14980328314039 | 14980328562680 | 14980328602579 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 419 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 253312 | 0x7ff685304480 | 0x7ff682226240 | 14980328610398 | 14980328620920 | 14980328857881 | 14980328876792 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 422 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 8 | 24 | 255552 | 0x7ff685304300 | 0x7ff682226280 | 14980328885512 | 14980328895641 | 14980329350362 | 14980329365580 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 425 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 259840 | 0x7ff685304180 | 0x7ff6822262c0 | 14980329383010 | 14980329393722 | 14980329618683 | 14980329634553 |
| 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 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 265664 | 0x7ff685304000 | 0x7ff682226300 | 14980329643393 | 14980329653563 | 14980329952124 | 14980329968215 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 431 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 271232 | 0x7ff682cd7e80 | 0x7ff682226340 | 14980329979485 | 14980329989564 | 14980330287005 | 14980330332696 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 434 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 8 | 24 | 273216 | 0x7ff682cd7d00 | 0x7ff682226380 | 14980330345906 | 14980330356765 | 14980330653726 | 14980330700787 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 437 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 8 | 24 | 275712 | 0x7ff682cd7b80 | 0x7ff6822263c0 | 14980330709987 | 14980330720286 | 14980331278367 | 14980331321472 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 440 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 280768 | 0x7ff682cd7a00 | 0x7ff682226400 | 14980331338822 | 14980331349248 | 14980331613248 | 14980331656794 |
| 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 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 287616 | 0x7ff682cd7880 | 0x7ff682226440 | 14980331669334 | 14980331679808 | 14980332030529 | 14980332073424 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 446 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 294208 | 0x7ff682cd7700 | 0x7ff682226480 | 14980332082114 | 14980332092770 | 14980332443651 | 14980332486904 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 449 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 8 | 24 | 296960 | 0x7ff685304580 | 0x7ff6822264c0 | 14980332497834 | 14980332508131 | 14980332855492 | 14980332898704 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 452 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 8 | 24 | 299968 | 0x7ff685304400 | 0x7ff682226500 | 14980332910954 | 14980332921572 | 14980333582694 | 14980333624646 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 455 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 8 | 24 | 302720 | 0x7ff685304280 | 0x7ff682226540 | 14980333646446 | 14980333655654 | 14980334102855 | 14980334129744 |
| 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 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 305472 | 0x7ff685304100 | 0x7ff682226580 | 14980334142014 | 14980334161415 | 14980334626376 | 14980334672781 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 461 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 308224 | 0x7ff682cd7f80 | 0x7ff6822265c0 | 14980334684190 | 14980334701257 | 14980335164618 | 14980335210108 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 464 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 8 | 24 | 310976 | 0x7ff682cd7e00 | 0x7ff682226600 | 14980335220107 | 14980335231018 | 14980335681899 | 14980335726585 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 467 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 8 | 24 | 313216 | 0x7ff682cd7c80 | 0x7ff682226640 | 14980335736555 | 14980335747339 | 14980336616942 | 14980336662422 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 470 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 8 | 24 | 315968 | 0x7ff682cd7b00 | 0x7ff682226680 | 14980336682072 | 14980336693102 | 14980337547024 | 14980337592760 |
| 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 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 318720 | 0x7ff682cd7980 | 0x7ff6822266c0 | 14980337602759 | 14980337612785 | 14980338498387 | 14980338548356 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 476 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 321472 | 0x7ff682cd7800 | 0x7ff682226700 | 14980338560656 | 14980338577427 | 14980339458550 | 14980339506313 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 479 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 8 | 24 | 324224 | 0x7ff682cd7680 | 0x7ff682226740 | 14980339519123 | 14980339542710 | 14980340403032 | 14980340450141 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 482 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 8 | 24 | 326464 | 0x7ff685304500 | 0x7ff682226780 | 14980340458620 | 14980340477112 | 14980342176157 | 14980342244527 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 485 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 8 | 24 | 329216 | 0x7ff685304380 | 0x7ff6822267c0 | 14980342264087 | 14980342279517 | 14980343945602 | 14980344015034 |
| 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 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 331968 | 0x7ff685304200 | 0x7ff682226800 | 14980344026774 | 14980344042402 | 14980345767047 | 14980345836020 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 491 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 12 | 24 | 334720 | 0x7ff685304080 | 0x7ff682226840 | 14980345847659 | 14980345863207 | 14980347579852 | 14980347648746 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 494 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 8 | 24 | 337472 | 0x7ff682cd7f00 | 0x7ff682226880 | 14980347658535 | 14980347669292 | 14980349342896 | 14980349411583 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 497 | 80643 | 80643 | 4194304 | 256 | 0 | 0 | 8 | 24 | 0 | 0x7ff682cd7d80 | 0x7ff6822268c0 | 14980349421162 | 14980349432497 | 14980352790586 | 14980352866959 |