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 | 56235 | 56235 | 33554432 | 256 | 0 | 0 | 4 | 32 | 4160 | 0x0 | 0x7f0cf9a04280 | 14621776193423 | 14621776217873 | 14621776456753 | 14621776568043 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 56235 | 56235 | 32768 | 256 | 0 | 0 | 12 | 24 | 13888 | 0x0 | 0x7f0cf9a23f80 | 14621781195879 | 14621781211476 | 14621781224916 | 14621781242028 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 5 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 14336 | 0x7f0cfca9a380 | 0x7f0cf9a23fc0 | 14621781247758 | 14621781290356 | 14621781382836 | 14621781384964 |
| 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 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15040 | 0x7f0cfca9a200 | 0x7f0cf9a24000 | 14621781407024 | 14621781417076 | 14621781596276 | 14621781598439 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 11 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15488 | 0x7f0cfca9a080 | 0x7f0cf9a24040 | 14621781612718 | 14621781620916 | 14621781799156 | 14621781801073 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 14 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 15936 | 0x7f0cfa405f00 | 0x7f0cf9a24080 | 14621781814813 | 14621781822836 | 14621781916116 | 14621781918210 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 17 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 16384 | 0x7f0cfa405d80 | 0x7f0cf9a240c0 | 14621781934190 | 14621781942356 | 14621782034356 | 14621782036277 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 20 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 17088 | 0x7f0cfa405c00 | 0x7f0cf9a24100 | 14621782063676 | 14621782074196 | 14621782166516 | 14621782168553 |
| 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 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 16 | 24 | 17792 | 0x7f0cfa405a80 | 0x7f0cf9a24140 | 14621782186893 | 14621782195956 | 14621782376276 | 14621782378138 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 26 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 16 | 24 | 18496 | 0x7f0cfa405900 | 0x7f0cf9a24180 | 14621782395167 | 14621782403636 | 14621782582836 | 14621782584922 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 29 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19200 | 0x7f0cfa405780 | 0x7f0cf9a241c0 | 14621782599562 | 14621782607636 | 14621782701077 | 14621782703139 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 32 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19904 | 0x7f0cfa405600 | 0x7f0cf9a24200 | 14621782720988 | 14621782745557 | 14621782839317 | 14621782841285 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 35 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 20608 | 0x7f0cfca9a480 | 0x7f0cf9a24240 | 14621782864895 | 14621782889237 | 14621782983157 | 14621782985241 |
| 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 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 16 | 24 | 21312 | 0x7f0cfca9a300 | 0x7f0cf9a24280 | 14621783012971 | 14621783023477 | 14621783202837 | 14621783204705 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 41 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22016 | 0x7f0cfca9a180 | 0x7f0cf9a242c0 | 14621783228435 | 14621783238677 | 14621783418837 | 14621783420720 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 44 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22720 | 0x7f0cfca9a000 | 0x7f0cf9a24300 | 14621783442079 | 14621783452277 | 14621783546357 | 14621783548256 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 47 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 23424 | 0x7f0cfa405e80 | 0x7f0cf9a24340 | 14621783565816 | 14621783574997 | 14621783667637 | 14621783669483 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 50 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 24128 | 0x7f0cfa405d00 | 0x7f0cf9a24380 | 14621783691562 | 14621783701877 | 14621783795477 | 14621783797360 |
| 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 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 16 | 24 | 24832 | 0x7f0cfa405b80 | 0x7f0cf9a243c0 | 14621783813519 | 14621783821877 | 14621784001717 | 14621784003644 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 56 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 16 | 24 | 25536 | 0x7f0cfa405a00 | 0x7f0cf9a24400 | 14621784019274 | 14621784028437 | 14621784208758 | 14621784210618 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 59 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26240 | 0x7f0cfa405880 | 0x7f0cf9a24440 | 14621784225188 | 14621784233878 | 14621784327318 | 14621784329325 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 62 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26944 | 0x7f0cfa405700 | 0x7f0cf9a24480 | 14621784347185 | 14621784355958 | 14621784448438 | 14621784450642 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 65 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 27648 | 0x7f0cfca9a580 | 0x7f0cf9a244c0 | 14621784470361 | 14621784480918 | 14621784573238 | 14621784575039 |
| 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 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 16 | 24 | 28608 | 0x7f0cfca9a400 | 0x7f0cf9a24500 | 14621784594308 | 14621784605718 | 14621784786198 | 14621784788113 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 71 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 16 | 24 | 29312 | 0x7f0cfca9a280 | 0x7f0cf9a24540 | 14621784804602 | 14621784835638 | 14621785015158 | 14621785017277 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 74 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 30016 | 0x7f0cfca9a100 | 0x7f0cf9a24580 | 14621785032816 | 14621785041238 | 14621785133398 | 14621785135034 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 77 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 8 | 24 | 30976 | 0x7f0cfa405f80 | 0x7f0cf9a245c0 | 14621785149433 | 14621785157558 | 14621785249398 | 14621785250771 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 80 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 31680 | 0x7f0cfa405e00 | 0x7f0cf9a24600 | 14621785270770 | 14621785281558 | 14621785375478 | 14621785376807 |
| 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 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 16 | 24 | 32640 | 0x7f0cfa405c80 | 0x7f0cf9a24640 | 14621785390887 | 14621785399158 | 14621785579318 | 14621785580652 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 86 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 33600 | 0x7f0cfa405b00 | 0x7f0cf9a24680 | 14621785595501 | 14621785603638 | 14621785783799 | 14621785785316 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 89 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 34560 | 0x7f0cfa405980 | 0x7f0cf9a246c0 | 14621785801096 | 14621785809239 | 14621785902679 | 14621785904263 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 92 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 8 | 24 | 35520 | 0x7f0cfa405800 | 0x7f0cf9a24700 | 14621785919193 | 14621785926999 | 14621786020439 | 14621786021900 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 95 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 36224 | 0x7f0cfa405680 | 0x7f0cf9a24740 | 14621786044179 | 14621786054199 | 14621786147479 | 14621786148996 |
| 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 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 37184 | 0x7f0cfca9a500 | 0x7f0cf9a24780 | 14621786163916 | 14621786171959 | 14621786352599 | 14621786354081 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 101 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 38144 | 0x7f0cfca9a380 | 0x7f0cf9a247c0 | 14621786368591 | 14621786376759 | 14621786557879 | 14621786559365 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 104 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 39104 | 0x7f0cfca9a200 | 0x7f0cf9a24800 | 14621786573165 | 14621786581079 | 14621786674999 | 14621786676582 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 107 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 8 | 24 | 40320 | 0x7f0cfca9a080 | 0x7f0cf9a24840 | 14621786690902 | 14621786698999 | 14621786793399 | 14621786794739 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 110 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 41280 | 0x7f0cfa405f00 | 0x7f0cf9a24880 | 14621786815279 | 14621786825879 | 14621786919159 | 14621786920566 |
| 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 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 42240 | 0x7f0cfa405d80 | 0x7f0cf9a248c0 | 14621786935245 | 14621786942839 | 14621787123159 | 14621787124530 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 116 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 43200 | 0x7f0cfa405c00 | 0x7f0cf9a24900 | 14621787138870 | 14621787146839 | 14621787328920 | 14621787330375 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 119 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 8 | 24 | 44160 | 0x7f0cfa405a80 | 0x7f0cf9a24940 | 14621787344665 | 14621787352920 | 14621787446680 | 14621787448052 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 122 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 45376 | 0x7f0cfa405900 | 0x7f0cf9a24980 | 14621787462611 | 14621787470520 | 14621787564920 | 14621787566339 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 125 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 46336 | 0x7f0cfa405780 | 0x7f0cf9a249c0 | 14621787585178 | 14621787593080 | 14621787685560 | 14621787686985 |
| 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 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 47552 | 0x7f0cfa405600 | 0x7f0cf9a24a00 | 14621787700505 | 14621787708600 | 14621787889880 | 14621787891250 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 131 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 48512 | 0x7f0cfca9a480 | 0x7f0cf9a24a40 | 14621787906160 | 14621787914200 | 14621788096120 | 14621788097504 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 134 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 8 | 24 | 49472 | 0x7f0cfca9a300 | 0x7f0cf9a24a80 | 14621788111254 | 14621788119160 | 14621788212280 | 14621788213701 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 137 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 50688 | 0x7f0cfca9a180 | 0x7f0cf9a24ac0 | 14621788227171 | 14621788235640 | 14621788328600 | 14621788329978 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 140 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 51648 | 0x7f0cfca9a000 | 0x7f0cf9a24b00 | 14621788351728 | 14621788362360 | 14621788454520 | 14621788455955 |
| 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 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 52864 | 0x7f0cfa405e80 | 0x7f0cf9a24b40 | 14621788473824 | 14621788481240 | 14621788660440 | 14621788661839 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 146 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 54080 | 0x7f0cfa405d00 | 0x7f0cf9a24b80 | 14621788677099 | 14621788685240 | 14621788865241 | 14621788866664 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 149 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 8 | 24 | 55296 | 0x7f0cfa405b80 | 0x7f0cf9a24bc0 | 14621788880514 | 14621788888441 | 14621788982681 | 14621788984131 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 152 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 56768 | 0x7f0cfa405a00 | 0x7f0cf9a24c00 | 14621788998200 | 14621789006201 | 14621789101561 | 14621789102958 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 155 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 57728 | 0x7f0cfa405880 | 0x7f0cf9a24c40 | 14621789123137 | 14621789134041 | 14621789227001 | 14621789228474 |
| 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 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 58944 | 0x7f0cfa405700 | 0x7f0cf9a24c80 | 14621789243574 | 14621789251481 | 14621789430681 | 14621789432049 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 161 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 60160 | 0x7f0cfca9a580 | 0x7f0cf9a24cc0 | 14621789445588 | 14621789455161 | 14621789634841 | 14621789636313 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 164 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 8 | 24 | 61376 | 0x7f0cfca9a400 | 0x7f0cf9a24d00 | 14621789650493 | 14621789659001 | 14621789754201 | 14621789755700 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 167 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 62848 | 0x7f0cfca9a280 | 0x7f0cf9a24d40 | 14621789772220 | 14621789780761 | 14621789879961 | 14621789881317 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 170 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 63808 | 0x7f0cfca9a100 | 0x7f0cf9a24d80 | 14621789901496 | 14621789912121 | 14621790005401 | 14621790006793 |
| 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 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 65024 | 0x7f0cfa405f80 | 0x7f0cf9a24dc0 | 14621790023833 | 14621790032281 | 14621790209881 | 14621790211368 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 176 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 66240 | 0x7f0cfa405e00 | 0x7f0cf9a24e00 | 14621790226518 | 14621790235161 | 14621790415642 | 14621790417092 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 179 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 8 | 24 | 67456 | 0x7f0cfa405c80 | 0x7f0cf9a24e40 | 14621790433392 | 14621790441402 | 14621790535962 | 14621790537479 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 182 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 68928 | 0x7f0cfa405b00 | 0x7f0cf9a24e80 | 14621790552759 | 14621790560762 | 14621790663962 | 14621790665346 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 185 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 70144 | 0x7f0cfa405980 | 0x7f0cf9a24ec0 | 14621790686395 | 14621790697882 | 14621790790362 | 14621790791782 |
| 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 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 71616 | 0x7f0cfa405800 | 0x7f0cf9a24f00 | 14621790808022 | 14621790815962 | 14621790997402 | 14621790998807 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 191 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 72832 | 0x7f0cfa405680 | 0x7f0cf9a24f40 | 14621791015696 | 14621791024282 | 14621791205402 | 14621791206891 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 194 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 8 | 24 | 74048 | 0x7f0cfca9a500 | 0x7f0cf9a24f80 | 14621791220011 | 14621791227802 | 14621791320922 | 14621791322308 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 197 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 75776 | 0x7f0cfca9a380 | 0x7f0cf9a24fc0 | 14621791335458 | 14621791343482 | 14621791449562 | 14621791450885 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 200 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 76992 | 0x7f0cfca9a200 | 0x7f0cf9a25000 | 14621791470244 | 14621791482362 | 14621791576602 | 14621791578021 |
| 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 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 78464 | 0x7f0cfca9a080 | 0x7f0cf9a25040 | 14621791593221 | 14621791601402 | 14621791781083 | 14621791782366 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 206 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 79936 | 0x7f0cfa405f00 | 0x7f0cf9a25080 | 14621791797615 | 14621791805723 | 14621791984603 | 14621791985990 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 209 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 8 | 24 | 81408 | 0x7f0cfa405d80 | 0x7f0cf9a250c0 | 14621792000400 | 14621792009083 | 14621792103643 | 14621792104997 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 212 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 83136 | 0x7f0cfa405c00 | 0x7f0cf9a25100 | 14621792118467 | 14621792126363 | 14621792241403 | 14621792242803 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 215 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 84352 | 0x7f0cfa405a80 | 0x7f0cf9a25140 | 14621792276063 | 14621792285883 | 14621792379963 | 14621792381460 |
| 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 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 85824 | 0x7f0cfa405900 | 0x7f0cf9a25180 | 14621792395999 | 14621792404283 | 14621792583963 | 14621792585314 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 221 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 87296 | 0x7f0cfa405780 | 0x7f0cf9a251c0 | 14621792601054 | 14621792609563 | 14621792789243 | 14621792790619 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 224 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 88768 | 0x7f0cfa405600 | 0x7f0cf9a25200 | 14621792804718 | 14621792813243 | 14621792908763 | 14621792910086 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 227 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 90752 | 0x7f0cfca9a480 | 0x7f0cf9a25240 | 14621792925505 | 14621792934043 | 14621793054363 | 14621793055732 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 230 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 91968 | 0x7f0cfca9a300 | 0x7f0cf9a25280 | 14621793075471 | 14621793086363 | 14621793179483 | 14621793180928 |
| 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 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 93440 | 0x7f0cfca9a180 | 0x7f0cf9a252c0 | 14621793195208 | 14621793203323 | 14621793381884 | 14621793383213 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 236 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 94912 | 0x7f0cfca9a000 | 0x7f0cf9a25300 | 14621793399472 | 14621793407484 | 14621793587964 | 14621793589347 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 239 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 96384 | 0x7f0cfa405e80 | 0x7f0cf9a25340 | 14621793605597 | 14621793612924 | 14621793708444 | 14621793710074 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 242 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 98368 | 0x7f0cfa405d00 | 0x7f0cf9a25380 | 14621793725534 | 14621793734204 | 14621793860604 | 14621793862070 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 245 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 99584 | 0x7f0cfa405b80 | 0x7f0cf9a253c0 | 14621793882059 | 14621793892604 | 14621793985884 | 14621793987227 |
| 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 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 101312 | 0x7f0cfa405a00 | 0x7f0cf9a25400 | 14621794002946 | 14621794010844 | 14621794191964 | 14621794193361 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 251 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 102784 | 0x7f0cfa405880 | 0x7f0cf9a25440 | 14621794208331 | 14621794216604 | 14621794399804 | 14621794401246 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 254 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 104256 | 0x7f0cfa405700 | 0x7f0cf9a25480 | 14621794416125 | 14621794424124 | 14621794518844 | 14621794520302 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 257 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 106240 | 0x7f0cfca9a580 | 0x7f0cf9a254c0 | 14621794535342 | 14621794543484 | 14621794674684 | 14621794676008 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 260 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 107712 | 0x7f0cfca9a400 | 0x7f0cf9a25500 | 14621794696688 | 14621794707324 | 14621794800284 | 14621794801655 |
| 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 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 16 | 24 | 109440 | 0x7f0cfca9a280 | 0x7f0cf9a25540 | 14621794817594 | 14621794825405 | 14621795004765 | 14621795006249 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 266 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 16 | 24 | 111168 | 0x7f0cfca9a100 | 0x7f0cf9a25580 | 14621795020179 | 14621795028605 | 14621795208125 | 14621795209554 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 269 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 8 | 24 | 112896 | 0x7f0cfa405f80 | 0x7f0cf9a255c0 | 14621795224884 | 14621795233085 | 14621795328445 | 14621795330051 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 272 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 115136 | 0x7f0cfa405e00 | 0x7f0cf9a25600 | 14621795344580 | 14621795352605 | 14621795491645 | 14621795493046 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 275 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 116608 | 0x7f0cfa405c80 | 0x7f0cf9a25640 | 14621795513616 | 14621795524285 | 14621795618525 | 14621795619903 |
| 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 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 16 | 24 | 118336 | 0x7f0cfa405b00 | 0x7f0cf9a25680 | 14621795634123 | 14621795642205 | 14621795821245 | 14621795822648 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 281 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 16 | 24 | 120064 | 0x7f0cfa405980 | 0x7f0cf9a256c0 | 14621795835797 | 14621795844605 | 14621796024605 | 14621796026052 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 284 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 121792 | 0x7f0cfa405800 | 0x7f0cf9a25700 | 14621796039492 | 14621796047325 | 14621796144285 | 14621796145729 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 287 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 124032 | 0x7f0cfa405680 | 0x7f0cf9a25740 | 14621796161819 | 14621796169885 | 14621796316285 | 14621796317764 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 290 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 125504 | 0x7f0cfca9a500 | 0x7f0cf9a25780 | 14621796336674 | 14621796344606 | 14621796439486 | 14621796440781 |
| 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 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 127488 | 0x7f0cfca9a380 | 0x7f0cf9a257c0 | 14621796455451 | 14621796463166 | 14621796644126 | 14621796645466 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 296 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 129216 | 0x7f0cfca9a200 | 0x7f0cf9a25800 | 14621796659395 | 14621796667486 | 14621796848766 | 14621796850140 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 299 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 130944 | 0x7f0cfca9a080 | 0x7f0cf9a25840 | 14621796863870 | 14621796872446 | 14621796972926 | 14621796974337 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 302 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 133440 | 0x7f0cfa405f00 | 0x7f0cf9a25880 | 14621796987707 | 14621796995806 | 14621797151006 | 14621797152412 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 305 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 134912 | 0x7f0cfa405d80 | 0x7f0cf9a258c0 | 14621797172522 | 14621797183326 | 14621797278526 | 14621797279849 |
| 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 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 136896 | 0x7f0cfa405c00 | 0x7f0cf9a25900 | 14621797294088 | 14621797301886 | 14621797481246 | 14621797482543 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 311 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 138880 | 0x7f0cfa405a80 | 0x7f0cf9a25940 | 14621797497053 | 14621797505086 | 14621797685246 | 14621797686638 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 314 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 140864 | 0x7f0cfa405900 | 0x7f0cf9a25980 | 14621797700198 | 14621797708126 | 14621797814206 | 14621797815604 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 317 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 143616 | 0x7f0cfa405780 | 0x7f0cf9a259c0 | 14621797829034 | 14621797837566 | 14621798008127 | 14621798009549 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 320 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 145344 | 0x7f0cfa405600 | 0x7f0cf9a25a00 | 14621798030689 | 14621798041407 | 14621798136927 | 14621798138396 |
| 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 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 147584 | 0x7f0cfca9a480 | 0x7f0cf9a25a40 | 14621798154175 | 14621798162047 | 14621798341727 | 14621798343040 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 326 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 149568 | 0x7f0cfca9a300 | 0x7f0cf9a25a80 | 14621798356430 | 14621798364287 | 14621798546527 | 14621798547925 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 329 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 151552 | 0x7f0cfca9a180 | 0x7f0cf9a25ac0 | 14621798562924 | 14621798571007 | 14621798682367 | 14621798683771 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 332 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 154304 | 0x7f0cfca9a000 | 0x7f0cf9a25b00 | 14621798699641 | 14621798707967 | 14621798888767 | 14621798890256 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 335 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 156288 | 0x7f0cfa405e80 | 0x7f0cf9a25b40 | 14621798911195 | 14621798921087 | 14621799022367 | 14621799023752 |
| 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 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 158784 | 0x7f0cfa405d00 | 0x7f0cf9a25b80 | 14621799038942 | 14621799047007 | 14621799233567 | 14621799234976 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 341 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 161024 | 0x7f0cfa405b80 | 0x7f0cf9a25bc0 | 14621799248256 | 14621799256127 | 14621799438368 | 14621799439801 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 344 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 163264 | 0x7f0cfa405a00 | 0x7f0cf9a25c00 | 14621799454061 | 14621799462368 | 14621799584288 | 14621799585667 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 347 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 166528 | 0x7f0cfa405880 | 0x7f0cf9a25c40 | 14621799599547 | 14621799607648 | 14621799814048 | 14621799834860 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 350 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 168512 | 0x7f0cfa405700 | 0x7f0cf9a25c80 | 14621799848930 | 14621799859648 | 14621799971168 | 14621799972577 |
| 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 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 171264 | 0x7f0cfca9a580 | 0x7f0cf9a25cc0 | 14621799988046 | 14621799996448 | 14621800182208 | 14621800183651 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 356 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 173760 | 0x7f0cfca9a400 | 0x7f0cf9a25d00 | 14621800198251 | 14621800205888 | 14621800394048 | 14621800395485 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 359 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 176256 | 0x7f0cfca9a280 | 0x7f0cf9a25d40 | 14621800410515 | 14621800418528 | 14621800552448 | 14621800553911 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 362 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 179776 | 0x7f0cfca9a100 | 0x7f0cf9a25d80 | 14621800567231 | 14621800575168 | 14621800807808 | 14621800827044 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 365 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 182272 | 0x7f0cfa405f80 | 0x7f0cf9a25dc0 | 14621800840933 | 14621800851808 | 14621800978529 | 14621800979880 |
| 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 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 185536 | 0x7f0cfa405e00 | 0x7f0cf9a25e00 | 14621800994599 | 14621801002529 | 14621801194369 | 14621801195704 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 371 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 188544 | 0x7f0cfa405c80 | 0x7f0cf9a25e40 | 14621801209883 | 14621801218209 | 14621801410849 | 14621801412178 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 374 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 191552 | 0x7f0cfa405b00 | 0x7f0cf9a25e80 | 14621801427798 | 14621801435969 | 14621801595809 | 14621801597173 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 377 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 195840 | 0x7f0cfa405980 | 0x7f0cf9a25ec0 | 14621801611513 | 14621801619489 | 14621801902529 | 14621801922164 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 380 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 198592 | 0x7f0cfa405800 | 0x7f0cf9a25f00 | 14621801937324 | 14621801948129 | 14621802098369 | 14621802099919 |
| 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 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 202368 | 0x7f0cfa405680 | 0x7f0cf9a25f40 | 14621802117739 | 14621802125409 | 14621802335169 | 14621802359183 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 386 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 205888 | 0x7f0cfca9a500 | 0x7f0cf9a25f80 | 14621802367432 | 14621802377729 | 14621802587650 | 14621802607206 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 389 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 209408 | 0x7f0cfca9a380 | 0x7f0cf9a25fc0 | 14621802615476 | 14621802625730 | 14621802811330 | 14621802812780 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 392 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 214464 | 0x7f0cfca9a200 | 0x7f0cf9a26000 | 14621802827600 | 14621802835970 | 14621803170370 | 14621803189530 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 395 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 217728 | 0x7f0cfca9a080 | 0x7f0cf9a26040 | 14621803204870 | 14621803215810 | 14621803383970 | 14621803385395 |
| 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 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 222016 | 0x7f0cfa405f00 | 0x7f0cf9a26080 | 14621803400165 | 14621803407970 | 14621803636770 | 14621803655448 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 401 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 226048 | 0x7f0cfa405d80 | 0x7f0cf9a260c0 | 14621803663278 | 14621803673410 | 14621803902850 | 14621803921651 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 404 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 230080 | 0x7f0cfa405c00 | 0x7f0cf9a26100 | 14621803932280 | 14621803942691 | 14621804153731 | 14621804172594 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 407 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 235904 | 0x7f0cfa405a80 | 0x7f0cf9a26140 | 14621804182054 | 14621804191331 | 14621804576771 | 14621804595702 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 410 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 239424 | 0x7f0cfa405900 | 0x7f0cf9a26180 | 14621804611132 | 14621804622211 | 14621804808611 | 14621804809987 |
| 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 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 244224 | 0x7f0cfa405780 | 0x7f0cf9a261c0 | 14621804825686 | 14621804833411 | 14621805083011 | 14621805101939 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 416 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 248768 | 0x7f0cfa405600 | 0x7f0cf9a26200 | 14621805110569 | 14621805120451 | 14621805368291 | 14621805387331 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 419 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 253312 | 0x7f0cfca9a480 | 0x7f0cf9a26240 | 14621805395461 | 14621805405891 | 14621805642692 | 14621805658784 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 422 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 8 | 24 | 255552 | 0x7f0cfca9a300 | 0x7f0cf9a26280 | 14621805666494 | 14621805676932 | 14621806130372 | 14621806150491 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 425 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 259840 | 0x7f0cfca9a180 | 0x7f0cf9a262c0 | 14621806165840 | 14621806176772 | 14621806402852 | 14621806421964 |
| 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 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 265664 | 0x7f0cfca9a000 | 0x7f0cf9a26300 | 14621806430183 | 14621806440452 | 14621806739012 | 14621806758495 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 431 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 271232 | 0x7f0cfa405e80 | 0x7f0cf9a26340 | 14621806769664 | 14621806779812 | 14621807078853 | 14621807100235 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 434 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 8 | 24 | 273216 | 0x7f0cfa405d00 | 0x7f0cf9a26380 | 14621807108815 | 14621807118853 | 14621807415173 | 14621807433287 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 437 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 8 | 24 | 275712 | 0x7f0cfa405b80 | 0x7f0cf9a263c0 | 14621807443456 | 14621807454053 | 14621808012453 | 14621808034071 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 440 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 280768 | 0x7f0cfa405a00 | 0x7f0cf9a26400 | 14621808048870 | 14621808059653 | 14621808323493 | 14621808344802 |
| 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 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 287616 | 0x7f0cfa405880 | 0x7f0cf9a26440 | 14621808353092 | 14621808363653 | 14621808714534 | 14621808735492 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 446 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 294208 | 0x7f0cfa405700 | 0x7f0cf9a26480 | 14621808743532 | 14621808754054 | 14621809103654 | 14621809124931 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 449 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 8 | 24 | 296960 | 0x7f0cfca9a580 | 0x7f0cf9a264c0 | 14621809134541 | 14621809144934 | 14621809492294 | 14621809510781 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 452 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 8 | 24 | 299968 | 0x7f0cfca9a400 | 0x7f0cf9a26500 | 14621809519551 | 14621809529414 | 14621810191335 | 14621810218822 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 455 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 8 | 24 | 302720 | 0x7f0cfca9a280 | 0x7f0cf9a26540 | 14621810235962 | 14621810245895 | 14621810694215 | 14621810716099 |
| 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 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 305472 | 0x7f0cfca9a100 | 0x7f0cf9a26580 | 14621810724069 | 14621810734215 | 14621811198375 | 14621811222475 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 461 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 308224 | 0x7f0cfa405f80 | 0x7f0cf9a265c0 | 14621811233275 | 14621811250695 | 14621811711176 | 14621811734252 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 464 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 8 | 24 | 310976 | 0x7f0cfa405e00 | 0x7f0cf9a26600 | 14621811742131 | 14621811752296 | 14621812205096 | 14621812228598 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 467 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 8 | 24 | 313216 | 0x7f0cfa405c80 | 0x7f0cf9a26640 | 14621812237518 | 14621812248136 | 14621813117577 | 14621813140744 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 470 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 8 | 24 | 315968 | 0x7f0cfa405b00 | 0x7f0cf9a26680 | 14621813158203 | 14621813169097 | 14621814022857 | 14621814042700 |
| 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 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 318720 | 0x7f0cfa405980 | 0x7f0cf9a266c0 | 14621814054259 | 14621814071177 | 14621814955498 | 14621814981454 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 476 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 321472 | 0x7f0cfa405800 | 0x7f0cf9a26700 | 14621814990554 | 14621815000298 | 14621815880458 | 14621815905220 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 479 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 8 | 24 | 324224 | 0x7f0cfa405680 | 0x7f0cf9a26740 | 14621815916679 | 14621815926538 | 14621816785899 | 14621816810075 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 482 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 8 | 24 | 326464 | 0x7f0cfca9a500 | 0x7f0cf9a26780 | 14621816818105 | 14621816837419 | 14621818536460 | 14621818610357 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 485 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 8 | 24 | 329216 | 0x7f0cfca9a380 | 0x7f0cf9a267c0 | 14621818627977 | 14621818638540 | 14621820303661 | 14621820372330 |
| 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 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 331968 | 0x7f0cfca9a200 | 0x7f0cf9a26800 | 14621820381310 | 14621820391181 | 14621822115822 | 14621822185092 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 491 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 12 | 24 | 334720 | 0x7f0cfca9a080 | 0x7f0cf9a26840 | 14621822193971 | 14621822204623 | 14621823919984 | 14621823989673 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 494 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 8 | 24 | 337472 | 0x7f0cfa405f00 | 0x7f0cf9a26880 | 14621823999213 | 14621824009424 | 14621825683345 | 14621825747926 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 497 | 56235 | 56235 | 4194304 | 256 | 0 | 0 | 8 | 24 | 0 | 0x7f0cfa405d80 | 0x7f0cf9a268c0 | 14621825756356 | 14621825776305 | 14621829133747 | 14621829208604 |