39 KiB
39 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_fillBuffer.kd | 0 | 0 | 0 | 888717 | 888722 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7fdfc0a04180 | 12075694399763814 | 12075694399805565 | 12075694400129562 | 12075694400241953 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 888717 | 888722 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7fdfc0a35100 | 12075694414747250 | 12075694414846664 | 12075694414853544 | 12075694414858728 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7fe0cc5b8900 | 0x7fdfc0a35140 | 12075694414899373 | 12075694414912583 | 12075694415050502 | 12075694415053690 |
| 5 | 3 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 6 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7fe0cc5b8800 | 0x7fdfc0a35180 | 12075694415096389 | 12075694415114021 | 12075694415357539 | 12075694415456819 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7fe0cc5b8700 | 0x7fdfc0a351c0 | 12075694415478509 | 12075694415490018 | 12075694415736575 | 12075694415834611 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7fe0cc5b8600 | 0x7fdfc0a35200 | 12075694415860469 | 12075694415872254 | 12075694415998173 | 12075694416010598 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7fe0cc5b8500 | 0x7fdfc0a35240 | 12075694416031938 | 12075694416042812 | 12075694416168571 | 12075694416171668 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7fe0cc5b8400 | 0x7fdfc0a35280 | 12075694416222833 | 12075694416235131 | 12075694416359610 | 12075694416362131 |
| 10 | 8 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 16 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7fe0cc5b8300 | 0x7fdfc0a352c0 | 12075694416386106 | 12075694416397369 | 12075694416643927 | 12075694416742138 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7fe0cc5b8a00 | 0x7fdfc0a35300 | 12075694416761594 | 12075694416777046 | 12075694417059923 | 12075694417159744 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7fe0cc5b8900 | 0x7fdfc0a35340 | 12075694417180522 | 12075694417191762 | 12075694417316881 | 12075694417319851 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7fe0cc5b8800 | 0x7fdfc0a35380 | 12075694417344317 | 12075694417356240 | 12075694417481519 | 12075694417484427 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7fe0cc5b8700 | 0x7fdfc0a353c0 | 12075694417519032 | 12075694417530639 | 12075694417655437 | 12075694417658100 |
| 15 | 13 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 26 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7fe0cc5b8600 | 0x7fdfc0a35400 | 12075694417681103 | 12075694417692237 | 12075694417936395 | 12075694418017308 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7fe0cc5b8500 | 0x7fdfc0a35440 | 12075694418038807 | 12075694418049994 | 12075694418296712 | 12075694418367568 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7fe0cc5b8400 | 0x7fdfc0a35480 | 12075694418388077 | 12075694418399911 | 12075694418525189 | 12075694418527656 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7fe0cc5b8300 | 0x7fdfc0a354c0 | 12075694418551941 | 12075694418562789 | 12075694418688388 | 12075694418691190 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7fe0cc5b8a00 | 0x7fdfc0a35500 | 12075694418727217 | 12075694418738947 | 12075694418864066 | 12075694418866616 |
| 20 | 18 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 36 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7fe0cc5b8900 | 0x7fdfc0a35540 | 12075694418891302 | 12075694418902946 | 12075694419153824 | 12075694419225894 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7fe0cc5b8800 | 0x7fdfc0a35580 | 12075694419245861 | 12075694419257343 | 12075694419503580 | 12075694419571326 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7fe0cc5b8700 | 0x7fdfc0a355c0 | 12075694419592054 | 12075694419603259 | 12075694419727578 | 12075694419729930 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7fe0cc5b8600 | 0x7fdfc0a35600 | 12075694419755318 | 12075694419766298 | 12075694419891577 | 12075694419894386 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7fe0cc5b8500 | 0x7fdfc0a35640 | 12075694419930303 | 12075694419942456 | 12075694420066775 | 12075694420069682 |
| 25 | 23 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 46 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7fe0cc5b8400 | 0x7fdfc0a35680 | 12075694420097263 | 12075694420108855 | 12075694420356852 | 12075694420424912 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7fe0cc5b8300 | 0x7fdfc0a356c0 | 12075694420445731 | 12075694420457811 | 12075694420701969 | 12075694420800380 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7fe0cc5b8a00 | 0x7fdfc0a35700 | 12075694420819475 | 12075694420830128 | 12075694420954287 | 12075694420957011 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7fe0cc5b8900 | 0x7fdfc0a35740 | 12075694420983230 | 12075694420994766 | 12075694421119885 | 12075694421122979 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7fe0cc5b8800 | 0x7fdfc0a35780 | 12075694421158485 | 12075694421174125 | 12075694421298924 | 12075694421301461 |
| 30 | 28 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 56 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7fe0cc5b8700 | 0x7fdfc0a357c0 | 12075694421325536 | 12075694421336683 | 12075694421618601 | 12075694421697878 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7fe0cc5b8600 | 0x7fdfc0a35800 | 12075694421711593 | 12075694421732200 | 12075694421975877 | 12075694422032269 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7fe0cc5b8500 | 0x7fdfc0a35840 | 12075694422052477 | 12075694422064356 | 12075694422188835 | 12075694422191465 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7fe0cc5b8400 | 0x7fdfc0a35880 | 12075694422216391 | 12075694422228035 | 12075694422353474 | 12075694422356321 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7fe0cc5b8300 | 0x7fdfc0a358c0 | 12075694422390695 | 12075694422404193 | 12075694422528672 | 12075694422530926 |
| 35 | 33 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 66 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7fe0cc5b8a00 | 0x7fdfc0a35900 | 12075694422554760 | 12075694422566112 | 12075694422812030 | 12075694422865478 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7fe0cc5b8900 | 0x7fdfc0a35940 | 12075694422884844 | 12075694422905149 | 12075694423148346 | 12075694423230045 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7fe0cc5b8800 | 0x7fdfc0a35980 | 12075694423251515 | 12075694423263225 | 12075694423388184 | 12075694423390794 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7fe0cc5b8700 | 0x7fdfc0a359c0 | 12075694423414308 | 12075694423425304 | 12075694423552183 | 12075694423554548 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7fe0cc5b8600 | 0x7fdfc0a35a00 | 12075694423587439 | 12075694423598902 | 12075694423723541 | 12075694423725807 |
| 40 | 38 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 76 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7fe0cc5b8500 | 0x7fdfc0a35a40 | 12075694423748048 | 12075694423759061 | 12075694424005778 | 12075694424038227 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7fe0cc5b8400 | 0x7fdfc0a35a80 | 12075694424057884 | 12075694424071058 | 12075694424315376 | 12075694424344837 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7fe0cc5b8300 | 0x7fdfc0a35ac0 | 12075694424365996 | 12075694424377295 | 12075694424503054 | 12075694424505305 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7fe0cc5b8a00 | 0x7fdfc0a35b00 | 12075694424528849 | 12075694424539853 | 12075694424665932 | 12075694424668258 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7fe0cc5b8900 | 0x7fdfc0a35b40 | 12075694424702221 | 12075694424713612 | 12075694424838091 | 12075694424840478 |
| 45 | 43 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 86 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7fe0cc5b8800 | 0x7fdfc0a35b80 | 12075694424864212 | 12075694424875530 | 12075694425136328 | 12075694425161745 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7fe0cc5b8700 | 0x7fdfc0a35bc0 | 12075694425181522 | 12075694425192967 | 12075694425437125 | 12075694425460601 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7fe0cc5b8600 | 0x7fdfc0a35c00 | 12075694425479215 | 12075694425490085 | 12075694425614403 | 12075694425616691 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7fe0cc5b8500 | 0x7fdfc0a35c40 | 12075694425641176 | 12075694425652323 | 12075694425779202 | 12075694425781607 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7fe0cc5b8400 | 0x7fdfc0a35c80 | 12075694425816312 | 12075694425827521 | 12075694425953280 | 12075694425955681 |
| 50 | 48 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 96 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7fe0cc5b8300 | 0x7fdfc0a35cc0 | 12075694425979725 | 12075694425992480 | 12075694426249278 | 12075694426276116 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7fe0cc5b8a00 | 0x7fdfc0a35d00 | 12075694426296143 | 12075694426307037 | 12075694426550875 | 12075694426574300 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7fe0cc5b8900 | 0x7fdfc0a35d40 | 12075694426594267 | 12075694426605274 | 12075694426730073 | 12075694426732374 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7fe0cc5b8800 | 0x7fdfc0a35d80 | 12075694426757912 | 12075694426768953 | 12075694426898072 | 12075694426900386 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7fe0cc5b8700 | 0x7fdfc0a35dc0 | 12075694426934119 | 12075694426945271 | 12075694427071030 | 12075694427073618 |
| 55 | 53 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 106 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7fe0cc5b8600 | 0x7fdfc0a35e00 | 12075694427098254 | 12075694427109590 | 12075694427368147 | 12075694427392862 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7fe0cc5b8500 | 0x7fdfc0a35e40 | 12075694427411647 | 12075694427422547 | 12075694427670544 | 12075694427693510 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7fe0cc5b8400 | 0x7fdfc0a35e80 | 12075694427716203 | 12075694427727024 | 12075694427852463 | 12075694427854800 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7fe0cc5b8300 | 0x7fdfc0a35ec0 | 12075694427879065 | 12075694427890382 | 12075694428018381 | 12075694428021079 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7fe0cc5b8a00 | 0x7fdfc0a35f00 | 12075694428056134 | 12075694428067661 | 12075694428192619 | 12075694428194942 |
| 60 | 58 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 116 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7fe0cc5b8900 | 0x7fdfc0a35f40 | 12075694428218787 | 12075694428230219 | 12075694428486057 | 12075694428509517 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7fe0cc5b8800 | 0x7fdfc0a35f80 | 12075694428529053 | 12075694428540136 | 12075694428785094 | 12075694428807982 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7fe0cc5b8700 | 0x7fdfc0a35fc0 | 12075694428828710 | 12075694428839653 | 12075694428964772 | 12075694428967107 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7fe0cc5b8600 | 0x7fdfc0a36000 | 12075694428991032 | 12075694429002212 | 12075694429137891 | 12075694429140600 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7fe0cc5b8500 | 0x7fdfc0a36040 | 12075694429176476 | 12075694429188290 | 12075694429313089 | 12075694429315395 |
| 65 | 63 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 126 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7fe0cc5b8400 | 0x7fdfc0a36080 | 12075694429339750 | 12075694429351489 | 12075694429602366 | 12075694429622135 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7fe0cc5b8300 | 0x7fdfc0a360c0 | 12075694429641631 | 12075694429652606 | 12075694429901884 | 12075694429925008 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7fe0cc5b8a00 | 0x7fdfc0a36100 | 12075694429943993 | 12075694429954843 | 12075694430122202 | 12075694430124989 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7fe0cc5b8900 | 0x7fdfc0a36140 | 12075694430149865 | 12075694430160921 | 12075694430303320 | 12075694430306086 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7fe0cc5b8800 | 0x7fdfc0a36180 | 12075694430339458 | 12075694430351319 | 12075694430476598 | 12075694430478937 |
| 70 | 68 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 136 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7fe0cc5b8700 | 0x7fdfc0a361c0 | 12075694430502671 | 12075694430513878 | 12075694430777075 | 12075694430796838 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7fe0cc5b8600 | 0x7fdfc0a36200 | 12075694430816655 | 12075694430827635 | 12075694431109552 | 12075694431138212 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7fe0cc5b8500 | 0x7fdfc0a36240 | 12075694431159652 | 12075694431170672 | 12075694431296271 | 12075694431299221 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7fe0cc5b8400 | 0x7fdfc0a36280 | 12075694431317555 | 12075694431329070 | 12075694431478829 | 12075694431481230 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7fe0cc5b8300 | 0x7fdfc0a362c0 | 12075694431533988 | 12075694431545068 | 12075694431670027 | 12075694431672786 |
| 75 | 73 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 146 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7fe0cc5b8a00 | 0x7fdfc0a36300 | 12075694431696700 | 12075694431710187 | 12075694431969224 | 12075694431992139 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7fe0cc5b8900 | 0x7fdfc0a36340 | 12075694432018278 | 12075694432029224 | 12075694432274022 | 12075694432301123 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7fe0cc5b8800 | 0x7fdfc0a36380 | 12075694432325318 | 12075694432336581 | 12075694432462660 | 12075694432465148 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7fe0cc5b8700 | 0x7fdfc0a363c0 | 12075694432489634 | 12075694432501059 | 12075694432658978 | 12075694432661393 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7fe0cc5b8600 | 0x7fdfc0a36400 | 12075694432696588 | 12075694432710177 | 12075694432835456 | 12075694432837861 |
| 80 | 78 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 156 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7fe0cc5b8500 | 0x7fdfc0a36440 | 12075694432862056 | 12075694432873376 | 12075694433130814 | 12075694433155862 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7fe0cc5b8400 | 0x7fdfc0a36480 | 12075694433176360 | 12075694433187773 | 12075694433438651 | 12075694433461620 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7fe0cc5b8300 | 0x7fdfc0a364c0 | 12075694433481687 | 12075694433493370 | 12075694433618809 | 12075694433621277 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7fe0cc5b8a00 | 0x7fdfc0a36500 | 12075694433645251 | 12075694433656249 | 12075694433821207 | 12075694433823573 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7fe0cc5b8900 | 0x7fdfc0a36540 | 12075694433857366 | 12075694433868727 | 12075694433994166 | 12075694433996584 |
| 85 | 83 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 166 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7fe0cc5b8800 | 0x7fdfc0a36580 | 12075694434025398 | 12075694434036725 | 12075694434291603 | 12075694434319695 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7fe0cc5b8700 | 0x7fdfc0a365c0 | 12075694434338760 | 12075694434351762 | 12075694434602000 | 12075694434624591 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7fe0cc5b8600 | 0x7fdfc0a36600 | 12075694434646212 | 12075694434657199 | 12075694434782638 | 12075694434785140 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7fe0cc5b8500 | 0x7fdfc0a36640 | 12075694434808884 | 12075694434819918 | 12075694434992076 | 12075694434994589 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7fe0cc5b8400 | 0x7fdfc0a36680 | 12075694435036066 | 12075694435047596 | 12075694435173195 | 12075694435175756 |
| 90 | 88 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 176 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7fe0cc5b8300 | 0x7fdfc0a366c0 | 12075694435202746 | 12075694435214154 | 12075694435467432 | 12075694435491653 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7fe0cc5b8a00 | 0x7fdfc0a36700 | 12075694435510788 | 12075694435521831 | 12075694435772069 | 12075694435795157 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7fe0cc5b8900 | 0x7fdfc0a36740 | 12075694435816456 | 12075694435827428 | 12075694435952867 | 12075694435955335 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7fe0cc5b8800 | 0x7fdfc0a36780 | 12075694435979289 | 12075694435990467 | 12075694436172865 | 12075694436175754 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7fe0cc5b8700 | 0x7fdfc0a367c0 | 12075694436210940 | 12075694436221985 | 12075694436347904 | 12075694436350349 |
| 95 | 93 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 186 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7fe0cc5b8600 | 0x7fdfc0a36800 | 12075694436375546 | 12075694436386463 | 12075694436649821 | 12075694436673219 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7fe0cc5b8500 | 0x7fdfc0a36840 | 12075694436692685 | 12075694436703580 | 12075694436954618 | 12075694436977384 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7fe0cc5b8400 | 0x7fdfc0a36880 | 12075694436997832 | 12075694437013497 | 12075694437139576 | 12075694437142401 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7fe0cc5b8300 | 0x7fdfc0a368c0 | 12075694437167558 | 12075694437178936 | 12075694437371414 | 12075694437394680 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7fe0cc5b8a00 | 0x7fdfc0a36900 | 12075694437423012 | 12075694437436053 | 12075694437562452 | 12075694437565257 |
| 100 | 98 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 196 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7fe0cc5b8900 | 0x7fdfc0a36940 | 12075694437590163 | 12075694437601652 | 12075694437883569 | 12075694437906681 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7fe0cc5b8800 | 0x7fdfc0a36980 | 12075694437927129 | 12075694437937969 | 12075694438188686 | 12075694438215745 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7fe0cc5b8700 | 0x7fdfc0a369c0 | 12075694438236885 | 12075694438247726 | 12075694438374605 | 12075694438377155 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7fe0cc5b8600 | 0x7fdfc0a36a00 | 12075694438402242 | 12075694438413004 | 12075694438622442 | 12075694438645374 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7fe0cc5b8500 | 0x7fdfc0a36a40 | 12075694438674428 | 12075694438688202 | 12075694438816361 | 12075694438818876 |
| 105 | 103 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 206 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7fe0cc5b8400 | 0x7fdfc0a36a80 | 12075694438843081 | 12075694438854120 | 12075694439190597 | 12075694439218589 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7fe0cc5b8300 | 0x7fdfc0a36ac0 | 12075694439238366 | 12075694439249157 | 12075694439498114 | 12075694439522374 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7fe0cc5b8a00 | 0x7fdfc0a36b00 | 12075694439542371 | 12075694439553474 | 12075694439681473 | 12075694439684004 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7fe0cc5b8900 | 0x7fdfc0a36b40 | 12075694439708309 | 12075694439719392 | 12075694439948030 | 12075694439971178 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7fe0cc5b8800 | 0x7fdfc0a36b80 | 12075694440008106 | 12075694440019549 | 12075694440147228 | 12075694440149860 |
| 110 | 108 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 216 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7fe0cc5b8700 | 0x7fdfc0a36bc0 | 12075694440175057 | 12075694440186108 | 12075694440514905 | 12075694440538773 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7fe0cc5b8600 | 0x7fdfc0a36c00 | 12075694440559581 | 12075694440572344 | 12075694440823382 | 12075694440846925 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7fe0cc5b8500 | 0x7fdfc0a36c40 | 12075694440866291 | 12075694440877301 | 12075694441005300 | 12075694441008195 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7fe0cc5b8400 | 0x7fdfc0a36c80 | 12075694441032951 | 12075694441044180 | 12075694441288978 | 12075694441316338 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7fe0cc5b8300 | 0x7fdfc0a36cc0 | 12075694441345001 | 12075694441356177 | 12075694441485776 | 12075694441488518 |
| 115 | 113 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 226 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7fe0cc5b8a00 | 0x7fdfc0a36d00 | 12075694441513214 | 12075694441524975 | 12075694441900972 | 12075694441924338 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7fe0cc5b8900 | 0x7fdfc0a36d40 | 12075694441944876 | 12075694441957291 | 12075694442214889 | 12075694442242028 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7fe0cc5b8800 | 0x7fdfc0a36d80 | 12075694442264039 | 12075694442274888 | 12075694442404327 | 12075694442406965 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7fe0cc5b8700 | 0x7fdfc0a36dc0 | 12075694442431440 | 12075694442442407 | 12075694442720964 | 12075694442744522 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7fe0cc5b8600 | 0x7fdfc0a36e00 | 12075694442774007 | 12075694442784804 | 12075694442920002 | 12075694442922803 |
| 120 | 118 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 236 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7fe0cc5b8500 | 0x7fdfc0a36e40 | 12075694442947028 | 12075694442957922 | 12075694443381118 | 12075694443409879 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7fe0cc5b8400 | 0x7fdfc0a36e80 | 12075694443428754 | 12075694443441118 | 12075694443704635 | 12075694443727529 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7fe0cc5b8300 | 0x7fdfc0a36ec0 | 12075694443747937 | 12075694443758555 | 12075694443894073 | 12075694443896603 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7fe0cc5b8a00 | 0x7fdfc0a36f00 | 12075694443921109 | 12075694443932153 | 12075694444246390 | 12075694444270959 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7fe0cc5b8900 | 0x7fdfc0a36f40 | 12075694444302928 | 12075694444314070 | 12075694444466548 | 12075694444469358 |
| 125 | 123 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 246 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7fe0cc5b8800 | 0x7fdfc0a36f80 | 12075694444492951 | 12075694444503508 | 12075694445020783 | 12075694445050478 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7fe0cc5b8700 | 0x7fdfc0a36fc0 | 12075694445074392 | 12075694445087022 | 12075694445382540 | 12075694445409986 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7fe0cc5b8600 | 0x7fdfc0a37000 | 12075694445430374 | 12075694445443179 | 12075694445598058 | 12075694445600860 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7fe0cc5b8500 | 0x7fdfc0a37040 | 12075694445624805 | 12075694445635817 | 12075694446021254 | 12075694446049394 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7fe0cc5b8400 | 0x7fdfc0a37080 | 12075694446085741 | 12075694446097253 | 12075694446273091 | 12075694446275955 |
| 130 | 128 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 256 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7fe0cc5b8300 | 0x7fdfc0a370c0 | 12075694446300631 | 12075694446311971 | 12075694446923005 | 12075694446946611 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7fe0cc5b8a00 | 0x7fdfc0a37100 | 12075694446966579 | 12075694446977245 | 12075694447303642 | 12075694447335294 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7fe0cc5b8900 | 0x7fdfc0a37140 | 12075694447357695 | 12075694447371001 | 12075694447550359 | 12075694447553509 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7fe0cc5b8800 | 0x7fdfc0a37180 | 12075694447576392 | 12075694447587159 | 12075694448042515 | 12075694448071242 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7fe0cc5b8700 | 0x7fdfc0a371c0 | 12075694448103151 | 12075694448114354 | 12075694448314352 | 12075694448340782 |
| 135 | 133 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 266 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7fe0cc5b8600 | 0x7fdfc0a37200 | 12075694448359227 | 12075694448369872 | 12075694449073545 | 12075694449102809 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7fe0cc5b8500 | 0x7fdfc0a37240 | 12075694449125020 | 12075694449136105 | 12075694449507781 | 12075694449534371 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7fe0cc5b8400 | 0x7fdfc0a37280 | 12075694449555700 | 12075694449566981 | 12075694449768899 | 12075694449795636 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7fe0cc5b8300 | 0x7fdfc0a372c0 | 12075694449814020 | 12075694449826818 | 12075694450352733 | 12075694450386053 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7fe0cc5b8a00 | 0x7fdfc0a37300 | 12075694450420257 | 12075694450432413 | 12075694450657370 | 12075694450683977 |
| 140 | 138 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 276 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7fe0cc5b8900 | 0x7fdfc0a37340 | 12075694450702201 | 12075694450713210 | 12075694451512403 | 12075694451541210 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7fe0cc5b8800 | 0x7fdfc0a37380 | 12075694451566708 | 12075694451577362 | 12075694451997038 | 12075694452026222 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7fe0cc5b8700 | 0x7fdfc0a373c0 | 12075694452052160 | 12075694452063117 | 12075694452289195 | 12075694452315900 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7fe0cc5b8600 | 0x7fdfc0a37400 | 12075694452336849 | 12075694452347755 | 12075694452957189 | 12075694452984002 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7fe0cc5b8500 | 0x7fdfc0a37440 | 12075694453026310 | 12075694453037508 | 12075694453306626 | 12075694453335184 |
| 145 | 143 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 286 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7fe0cc5b8400 | 0x7fdfc0a37480 | 12075694453359810 | 12075694453371425 | 12075694454358136 | 12075694454386608 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7fe0cc5b8300 | 0x7fdfc0a374c0 | 12075694454410713 | 12075694454423575 | 12075694454937491 | 12075694454964242 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7fe0cc5b8a00 | 0x7fdfc0a37500 | 12075694454991162 | 12075694455001650 | 12075694455274448 | 12075694455306057 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7fe0cc5b8900 | 0x7fdfc0a37540 | 12075694455331124 | 12075694455342447 | 12075694456081320 | 12075694456109610 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7fe0cc5b8800 | 0x7fdfc0a37580 | 12075694456143023 | 12075694456154119 | 12075694456470436 | 12075694456497231 |
| 150 | 148 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 296 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7fe0cc5b8700 | 0x7fdfc0a375c0 | 12075694456519172 | 12075694456530756 | 12075694457705305 | 12075694457734530 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7fe0cc5b8600 | 0x7fdfc0a37600 | 12075694457756431 | 12075694457767064 | 12075694458379379 | 12075694458408833 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7fe0cc5b8500 | 0x7fdfc0a37640 | 12075694458428730 | 12075694458439858 | 12075694458788335 | 12075694458815219 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7fe0cc5b8400 | 0x7fdfc0a37680 | 12075694458837250 | 12075694458848334 | 12075694459726406 | 12075694459756057 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7fe0cc5b8300 | 0x7fdfc0a376c0 | 12075694459794809 | 12075694459806085 | 12075694460216802 | 12075694460243683 |
| 155 | 153 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 306 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7fe0cc5b8a00 | 0x7fdfc0a37700 | 12075694460267548 | 12075694460278241 | 12075694461828947 | 12075694461901484 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7fe0cc5b8900 | 0x7fdfc0a37740 | 12075694461926631 | 12075694461937106 | 12075694462733098 | 12075694462807168 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7fe0cc5b8800 | 0x7fdfc0a37780 | 12075694462829168 | 12075694462840520 | 12075694463255237 | 12075694463334337 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7fe0cc5b8700 | 0x7fdfc0a377c0 | 12075694463354675 | 12075694463366595 | 12075694464525946 | 12075694464597765 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7fe0cc5b8600 | 0x7fdfc0a37800 | 12075694464629695 | 12075694464641305 | 12075694465427699 | 12075694465499491 |
| 160 | 158 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 316 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7fe0cc5b8500 | 0x7fdfc0a37840 | 12075694465521873 | 12075694465533138 | 12075694468588315 | 12075694468660205 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7fe0cc5b8400 | 0x7fdfc0a37880 | 12075694468682266 | 12075694468693594 | 12075694470236782 | 12075694470309059 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7fe0cc5b8300 | 0x7fdfc0a378c0 | 12075694470331331 | 12075694470342861 | 12075694471133095 | 12075694471205395 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7fe0cc5b8a00 | 0x7fdfc0a37900 | 12075694471230652 | 12075694471241894 | 12075694473523956 | 12075694473597120 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7fe0cc5b8900 | 0x7fdfc0a37940 | 12075694473634089 | 12075694473646355 | 12075694475182184 | 12075694475254380 |
| 165 | 163 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 326 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7fe0cc5b8800 | 0x7fdfc0a37980 | 12075694475276070 | 12075694475289863 | 12075694481345176 | 12075694481417464 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7fe0cc5b8700 | 0x7fdfc0a379c0 | 12075694481444404 | 12075694481455895 | 12075694484497951 | 12075694484570213 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7fe0cc5b8600 | 0x7fdfc0a37a00 | 12075694484591292 | 12075694484602750 | 12075694486142259 | 12075694486215070 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 888717 | 888722 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7fe0cc5b8500 | 0x7fdfc0a37a40 | 12075694486239596 | 12075694486251698 | 12075694490778543 | 12075694490851036 |