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 | 210870 | 210870 | 33554432 | 256 | 0 | 0 | 4 | 32 | 4160 | 0x0 | 0x7f84fd804280 | 17405168998305 | 17405169023666 | 17405169263026 | 17405169346376 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 210870 | 210870 | 32768 | 256 | 0 | 0 | 12 | 24 | 13888 | 0x0 | 0x7f84fd823f80 | 17405174015724 | 17405174031030 | 17405174043990 | 17405174060933 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 5 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 14336 | 0x7f85007d2380 | 0x7f84fd823fc0 | 17405174065833 | 17405174120951 | 17405174213431 | 17405174215899 |
| 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 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15040 | 0x7f85007d2200 | 0x7f84fd824000 | 17405174237488 | 17405174247031 | 17405174425911 | 17405174427893 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 11 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15488 | 0x7f85007d2080 | 0x7f84fd824040 | 17405174440913 | 17405174449111 | 17405174628151 | 17405174629918 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 14 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 15936 | 0x7f84fe131f00 | 0x7f84fd824080 | 17405174644768 | 17405174653111 | 17405174746551 | 17405174748465 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 17 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 16384 | 0x7f84fe131d80 | 0x7f84fd8240c0 | 17405174763184 | 17405174771351 | 17405174863351 | 17405174865192 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 20 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 17088 | 0x7f84fe131c00 | 0x7f84fd824100 | 17405174891811 | 17405174902711 | 17405174994871 | 17405174996678 |
| 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 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 16 | 24 | 17792 | 0x7f84fe131a80 | 0x7f84fd824140 | 17405175014528 | 17405175023032 | 17405175201912 | 17405175203773 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 26 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 16 | 24 | 18496 | 0x7f84fe131900 | 0x7f84fd824180 | 17405175222243 | 17405175230712 | 17405175411672 | 17405175413498 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 29 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19200 | 0x7f84fe131780 | 0x7f84fd8241c0 | 17405175429727 | 17405175453912 | 17405175547032 | 17405175549084 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 32 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19904 | 0x7f84fe131600 | 0x7f84fd824200 | 17405175566034 | 17405175574712 | 17405175668312 | 17405175670121 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 35 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 20608 | 0x7f85007d2480 | 0x7f84fd824240 | 17405175689780 | 17405175700472 | 17405175793272 | 17405175795028 |
| 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 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 16 | 24 | 21312 | 0x7f85007d2300 | 0x7f84fd824280 | 17405175813437 | 17405175822072 | 17405176000793 | 17405176002712 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 41 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22016 | 0x7f85007d2180 | 0x7f84fd8242c0 | 17405176018212 | 17405176026233 | 17405176205593 | 17405176207457 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 44 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22720 | 0x7f85007d2000 | 0x7f84fd824300 | 17405176224606 | 17405176232473 | 17405176326553 | 17405176328384 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 47 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 23424 | 0x7f84fe131e80 | 0x7f84fd824340 | 17405176347043 | 17405176356633 | 17405176449913 | 17405176451771 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 50 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 24128 | 0x7f84fe131d00 | 0x7f84fd824380 | 17405176472440 | 17405176483033 | 17405176576633 | 17405176578367 |
| 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 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 16 | 24 | 24832 | 0x7f84fe131b80 | 0x7f84fd8243c0 | 17405176602987 | 17405176613113 | 17405176792793 | 17405176794642 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 56 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 16 | 24 | 25536 | 0x7f84fe131a00 | 0x7f84fd824400 | 17405176812811 | 17405176822393 | 17405177003834 | 17405177005566 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 59 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26240 | 0x7f84fe131880 | 0x7f84fd824440 | 17405177024966 | 17405177041754 | 17405177135034 | 17405177136803 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 62 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26944 | 0x7f84fe131700 | 0x7f84fd824480 | 17405177153612 | 17405177180314 | 17405177273914 | 17405177275719 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 65 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 27648 | 0x7f85007d2580 | 0x7f84fd8244c0 | 17405177296979 | 17405177307514 | 17405177399514 | 17405177401226 |
| 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 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 16 | 24 | 28608 | 0x7f85007d2400 | 0x7f84fd824500 | 17405177420775 | 17405177437914 | 17405177618234 | 17405177620130 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 71 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 16 | 24 | 29312 | 0x7f85007d2280 | 0x7f84fd824540 | 17405177634850 | 17405177644794 | 17405177826554 | 17405177828485 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 74 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 30016 | 0x7f85007d2100 | 0x7f84fd824580 | 17405177848434 | 17405177865755 | 17405177958235 | 17405177959641 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 77 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 8 | 24 | 30976 | 0x7f84fe131f80 | 0x7f84fd8245c0 | 17405177977231 | 17405177985595 | 17405178077755 | 17405178080828 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 80 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 31680 | 0x7f84fe131e00 | 0x7f84fd824600 | 17405178101088 | 17405178111675 | 17405178204955 | 17405178206255 |
| 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 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 16 | 24 | 32640 | 0x7f84fe131c80 | 0x7f84fd824640 | 17405178224914 | 17405178233275 | 17405178414555 | 17405178416009 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 86 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 33600 | 0x7f84fe131b00 | 0x7f84fd824680 | 17405178430169 | 17405178438235 | 17405178619675 | 17405178621004 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 89 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 34560 | 0x7f84fe131980 | 0x7f84fd8246c0 | 17405178635854 | 17405178643835 | 17405178737435 | 17405178738931 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 92 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 8 | 24 | 35520 | 0x7f84fe131800 | 0x7f84fd824700 | 17405178754361 | 17405178762715 | 17405178856156 | 17405178857548 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 95 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 36224 | 0x7f84fe131680 | 0x7f84fd824740 | 17405178877697 | 17405178888156 | 17405178981596 | 17405178983035 |
| 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 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 37184 | 0x7f85007d2500 | 0x7f84fd824780 | 17405178997444 | 17405179005436 | 17405179185436 | 17405179186879 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 101 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 38144 | 0x7f85007d2380 | 0x7f84fd8247c0 | 17405179201249 | 17405179209916 | 17405179389436 | 17405179390934 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 104 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 39104 | 0x7f85007d2200 | 0x7f84fd824800 | 17405179405454 | 17405179413436 | 17405179507516 | 17405179508961 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 107 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 8 | 24 | 40320 | 0x7f85007d2080 | 0x7f84fd824840 | 17405179523190 | 17405179531516 | 17405179625596 | 17405179626968 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 110 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 41280 | 0x7f84fe131f00 | 0x7f84fd824880 | 17405179647067 | 17405179657916 | 17405179750877 | 17405179752234 |
| 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 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 42240 | 0x7f84fe131d80 | 0x7f84fd8248c0 | 17405179767114 | 17405179774877 | 17405179954237 | 17405179955759 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 116 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 43200 | 0x7f84fe131c00 | 0x7f84fd824900 | 17405179970319 | 17405179978077 | 17405180159197 | 17405180160694 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 119 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 8 | 24 | 44160 | 0x7f84fe131a80 | 0x7f84fd824940 | 17405180175103 | 17405180183677 | 17405180277117 | 17405180278421 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 122 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 45376 | 0x7f84fe131900 | 0x7f84fd824980 | 17405180293690 | 17405180301757 | 17405180396797 | 17405180398148 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 125 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 46336 | 0x7f84fe131780 | 0x7f84fd8249c0 | 17405180417747 | 17405180428637 | 17405180522557 | 17405180523894 |
| 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 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 47552 | 0x7f84fe131600 | 0x7f84fd824a00 | 17405180537964 | 17405180546237 | 17405180724158 | 17405180725379 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 131 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 48512 | 0x7f85007d2480 | 0x7f84fd824a40 | 17405180738819 | 17405180746878 | 17405180926878 | 17405180928124 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 134 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 8 | 24 | 49472 | 0x7f85007d2300 | 0x7f84fd824a80 | 17405180942353 | 17405180950878 | 17405181043358 | 17405181044571 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 137 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 50688 | 0x7f85007d2180 | 0x7f84fd824ac0 | 17405181059070 | 17405181067838 | 17405181161118 | 17405181162398 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 140 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 51648 | 0x7f85007d2000 | 0x7f84fd824b00 | 17405181182567 | 17405181193118 | 17405181284638 | 17405181285894 |
| 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 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 52864 | 0x7f84fe131e80 | 0x7f84fd824b40 | 17405181301384 | 17405181309438 | 17405181488798 | 17405181490139 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 146 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 54080 | 0x7f84fe131d00 | 0x7f84fd824b80 | 17405181504459 | 17405181512958 | 17405181694879 | 17405181696294 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 149 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 8 | 24 | 55296 | 0x7f84fe131b80 | 0x7f84fd824bc0 | 17405181709683 | 17405181718239 | 17405181812159 | 17405181813520 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 152 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 56768 | 0x7f84fe131a00 | 0x7f84fd824c00 | 17405181828320 | 17405181836959 | 17405181931839 | 17405181933107 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 155 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 57728 | 0x7f84fe131880 | 0x7f84fd824c40 | 17405181953117 | 17405181964159 | 17405182057599 | 17405182058914 |
| 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 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 58944 | 0x7f84fe131700 | 0x7f84fd824c80 | 17405182074804 | 17405182100159 | 17405182281599 | 17405182282918 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 161 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 60160 | 0x7f85007d2580 | 0x7f84fd824cc0 | 17405182297228 | 17405182305439 | 17405182485759 | 17405182487203 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 164 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 8 | 24 | 61376 | 0x7f85007d2400 | 0x7f84fd824d00 | 17405182501292 | 17405182509439 | 17405182604960 | 17405182606400 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 167 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 62848 | 0x7f85007d2280 | 0x7f84fd824d40 | 17405182621629 | 17405182629440 | 17405182728480 | 17405182729986 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 170 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 63808 | 0x7f85007d2100 | 0x7f84fd824d80 | 17405182751316 | 17405182761920 | 17405182855040 | 17405182856543 |
| 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 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 65024 | 0x7f84fe131f80 | 0x7f84fd824dc0 | 17405182874123 | 17405182882720 | 17405183062880 | 17405183064278 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 176 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 66240 | 0x7f84fe131e00 | 0x7f84fd824e00 | 17405183078027 | 17405183085920 | 17405183266560 | 17405183268062 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 179 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 8 | 24 | 67456 | 0x7f84fe131c80 | 0x7f84fd824e40 | 17405183282482 | 17405183290560 | 17405183384800 | 17405183386339 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 182 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 68928 | 0x7f84fe131b00 | 0x7f84fd824e80 | 17405183400939 | 17405183408960 | 17405183514241 | 17405183515596 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 185 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 70144 | 0x7f84fe131980 | 0x7f84fd824ec0 | 17405183535685 | 17405183546401 | 17405183639361 | 17405183640653 |
| 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 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 71616 | 0x7f84fe131800 | 0x7f84fd824f00 | 17405183655382 | 17405183663201 | 17405183844321 | 17405183845827 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 191 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 72832 | 0x7f84fe131680 | 0x7f84fd824f40 | 17405183861477 | 17405183870081 | 17405184050561 | 17405184052152 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 194 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 8 | 24 | 74048 | 0x7f85007d2500 | 0x7f84fd824f80 | 17405184065272 | 17405184073281 | 17405184166721 | 17405184168189 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 197 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 75776 | 0x7f85007d2380 | 0x7f84fd824fc0 | 17405184181548 | 17405184189601 | 17405184295521 | 17405184296905 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 200 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 76992 | 0x7f85007d2200 | 0x7f84fd825000 | 17405184317105 | 17405184327841 | 17405184422401 | 17405184423812 |
| 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 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 78464 | 0x7f85007d2080 | 0x7f84fd825040 | 17405184437702 | 17405184446721 | 17405184626562 | 17405184627907 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 206 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 79936 | 0x7f84fe131f00 | 0x7f84fd825080 | 17405184642996 | 17405184651682 | 17405184833282 | 17405184834541 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 209 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 8 | 24 | 81408 | 0x7f84fe131d80 | 0x7f84fd8250c0 | 17405184848001 | 17405184856642 | 17405184951362 | 17405184952668 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 212 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 83136 | 0x7f84fe131c00 | 0x7f84fd825100 | 17405184966788 | 17405184975362 | 17405185090562 | 17405185091885 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 215 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 84352 | 0x7f84fe131a80 | 0x7f84fd825140 | 17405185124664 | 17405185134562 | 17405185228162 | 17405185229481 |
| 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 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 85824 | 0x7f84fe131900 | 0x7f84fd825180 | 17405185243711 | 17405185251842 | 17405185431683 | 17405185433186 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 221 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 87296 | 0x7f84fe131780 | 0x7f84fd8251c0 | 17405185447475 | 17405185455523 | 17405185635363 | 17405185636640 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 224 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 88768 | 0x7f84fe131600 | 0x7f84fd825200 | 17405185651310 | 17405185660163 | 17405185755203 | 17405185756597 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 227 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 90752 | 0x7f85007d2480 | 0x7f84fd825240 | 17405185770267 | 17405185778883 | 17405185899363 | 17405185900863 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 230 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 91968 | 0x7f85007d2300 | 0x7f84fd825280 | 17405185920863 | 17405185931683 | 17405186024963 | 17405186026280 |
| 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 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 93440 | 0x7f85007d2180 | 0x7f84fd8252c0 | 17405186040550 | 17405186048803 | 17405186229603 | 17405186231055 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 236 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 94912 | 0x7f85007d2000 | 0x7f84fd825300 | 17405186245204 | 17405186253123 | 17405186433924 | 17405186435309 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 239 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 96384 | 0x7f84fe131e80 | 0x7f84fd825340 | 17405186450269 | 17405186458244 | 17405186553764 | 17405186555156 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 242 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 98368 | 0x7f84fe131d00 | 0x7f84fd825380 | 17405186569616 | 17405186577604 | 17405186704324 | 17405186705852 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 245 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 99584 | 0x7f84fe131b80 | 0x7f84fd8253c0 | 17405186725102 | 17405186736324 | 17405186830724 | 17405186832109 |
| 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 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 101312 | 0x7f84fe131a00 | 0x7f84fd825400 | 17405186847149 | 17405186855204 | 17405187033924 | 17405187035404 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 251 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 102784 | 0x7f84fe131880 | 0x7f84fd825440 | 17405187049413 | 17405187057284 | 17405187236324 | 17405187237798 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 254 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 104256 | 0x7f84fe131700 | 0x7f84fd825480 | 17405187251638 | 17405187259684 | 17405187353765 | 17405187355155 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 257 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 106240 | 0x7f85007d2580 | 0x7f84fd8254c0 | 17405187368975 | 17405187377125 | 17405187507685 | 17405187508921 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 260 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 107712 | 0x7f85007d2400 | 0x7f84fd825500 | 17405187528641 | 17405187539685 | 17405187632805 | 17405187634278 |
| 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 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 16 | 24 | 109440 | 0x7f85007d2280 | 0x7f84fd825540 | 17405187649588 | 17405187657925 | 17405187836805 | 17405187838413 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 266 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 16 | 24 | 111168 | 0x7f85007d2100 | 0x7f84fd825580 | 17405187853092 | 17405187861125 | 17405188040165 | 17405188041647 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 269 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 8 | 24 | 112896 | 0x7f84fe131f80 | 0x7f84fd8255c0 | 17405188055677 | 17405188063365 | 17405188158725 | 17405188160194 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 272 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 115136 | 0x7f84fe131e00 | 0x7f84fd825600 | 17405188175224 | 17405188183205 | 17405188322726 | 17405188324070 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 275 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 116608 | 0x7f84fe131c80 | 0x7f84fd825640 | 17405188343970 | 17405188354886 | 17405188449126 | 17405188450467 |
| 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 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 16 | 24 | 118336 | 0x7f84fe131b00 | 0x7f84fd825680 | 17405188465946 | 17405188474086 | 17405188652806 | 17405188654161 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 281 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 16 | 24 | 120064 | 0x7f84fe131980 | 0x7f84fd8256c0 | 17405188667921 | 17405188676806 | 17405188856166 | 17405188857536 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 284 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 121792 | 0x7f84fe131800 | 0x7f84fd825700 | 17405188871306 | 17405188879526 | 17405188976966 | 17405188978203 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 287 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 124032 | 0x7f84fe131680 | 0x7f84fd825740 | 17405188994252 | 17405189002406 | 17405189147206 | 17405189148468 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 290 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 125504 | 0x7f85007d2500 | 0x7f84fd825780 | 17405189168038 | 17405189179047 | 17405189273927 | 17405189275245 |
| 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 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 127488 | 0x7f85007d2380 | 0x7f84fd8257c0 | 17405189290215 | 17405189298567 | 17405189477607 | 17405189478860 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 296 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 129216 | 0x7f85007d2200 | 0x7f84fd825800 | 17405189492549 | 17405189501127 | 17405189681447 | 17405189682744 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 299 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 130944 | 0x7f85007d2080 | 0x7f84fd825840 | 17405189696304 | 17405189705287 | 17405189804967 | 17405189806241 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 302 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 133440 | 0x7f84fe131f00 | 0x7f84fd825880 | 17405189819471 | 17405189828167 | 17405189983527 | 17405189984787 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 305 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 134912 | 0x7f84fe131d80 | 0x7f84fd8258c0 | 17405190005416 | 17405190016007 | 17405190110087 | 17405190111753 |
| 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 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 136896 | 0x7f84fe131c00 | 0x7f84fd825900 | 17405190127053 | 17405190135528 | 17405190314568 | 17405190316028 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 311 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 138880 | 0x7f84fe131a80 | 0x7f84fd825940 | 17405190330828 | 17405190339048 | 17405190518248 | 17405190519523 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 314 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 140864 | 0x7f84fe131900 | 0x7f84fd825980 | 17405190533792 | 17405190541768 | 17405190648648 | 17405190650009 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 317 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 143616 | 0x7f84fe131780 | 0x7f84fd8259c0 | 17405190664279 | 17405190672648 | 17405190843208 | 17405190844474 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 320 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 145344 | 0x7f84fe131600 | 0x7f84fd825a00 | 17405190864754 | 17405190875368 | 17405190971528 | 17405190972821 |
| 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 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 147584 | 0x7f85007d2480 | 0x7f84fd825a40 | 17405190987010 | 17405190995048 | 17405191175689 | 17405191176956 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 326 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 149568 | 0x7f85007d2300 | 0x7f84fd825a80 | 17405191190975 | 17405191199369 | 17405191382729 | 17405191384080 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 329 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 151552 | 0x7f85007d2180 | 0x7f84fd825ac0 | 17405191397980 | 17405191406249 | 17405191517929 | 17405191519257 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 332 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 154304 | 0x7f85007d2000 | 0x7f84fd825b00 | 17405191533416 | 17405191541929 | 17405191722889 | 17405191724211 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 335 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 156288 | 0x7f84fe131e80 | 0x7f84fd825b40 | 17405191749901 | 17405191759849 | 17405191861129 | 17405191862548 |
| 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 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 158784 | 0x7f84fe131d00 | 0x7f84fd825b80 | 17405191878387 | 17405191886409 | 17405192071210 | 17405192072542 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 341 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 161024 | 0x7f84fe131b80 | 0x7f84fd825bc0 | 17405192086492 | 17405192094570 | 17405192279050 | 17405192280407 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 344 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 163264 | 0x7f84fe131a00 | 0x7f84fd825c00 | 17405192295016 | 17405192304810 | 17405192426730 | 17405192428113 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 347 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 166528 | 0x7f84fe131880 | 0x7f84fd825c40 | 17405192441723 | 17405192450410 | 17405192656490 | 17405192678196 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 350 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 168512 | 0x7f84fe131700 | 0x7f84fd825c80 | 17405192693466 | 17405192705450 | 17405192817930 | 17405192819263 |
| 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 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 171264 | 0x7f85007d2580 | 0x7f84fd825cc0 | 17405192833982 | 17405192842250 | 17405193027691 | 17405193029057 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 356 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 173760 | 0x7f85007d2400 | 0x7f84fd825d00 | 17405193043007 | 17405193051691 | 17405193240011 | 17405193241232 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 359 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 176256 | 0x7f85007d2280 | 0x7f84fd825d40 | 17405193257461 | 17405193265931 | 17405193400491 | 17405193401728 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 362 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 179776 | 0x7f85007d2100 | 0x7f84fd825d80 | 17405193415667 | 17405193424011 | 17405193655851 | 17405193675361 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 365 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 182272 | 0x7f84fe131f80 | 0x7f84fd825dc0 | 17405193690760 | 17405193701771 | 17405193828011 | 17405193829417 |
| 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 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 185536 | 0x7f84fe131e00 | 0x7f84fd825e00 | 17405193854286 | 17405193864651 | 17405194056172 | 17405194057501 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 371 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 188544 | 0x7f84fe131c80 | 0x7f84fd825e40 | 17405194074400 | 17405194092172 | 17405194288012 | 17405194289355 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 374 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 191552 | 0x7f84fe131b00 | 0x7f84fd825e80 | 17405194302664 | 17405194310572 | 17405194470572 | 17405194472030 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 377 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 195840 | 0x7f84fe131980 | 0x7f84fd825ec0 | 17405194486679 | 17405194494732 | 17405194778252 | 17405194822271 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 380 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 198592 | 0x7f84fe131800 | 0x7f84fd825f00 | 17405194838090 | 17405194848973 | 17405194999053 | 17405195000286 |
| 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 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 202368 | 0x7f84fe131680 | 0x7f84fd825f40 | 17405195017045 | 17405195024813 | 17405195231853 | 17405195275169 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 386 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 205888 | 0x7f85007d2500 | 0x7f84fd825f80 | 17405195283099 | 17405195293293 | 17405195501613 | 17405195544752 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 389 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 209408 | 0x7f85007d2380 | 0x7f84fd825fc0 | 17405195552631 | 17405195563373 | 17405195748813 | 17405195750106 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 392 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 214464 | 0x7f85007d2200 | 0x7f84fd826000 | 17405195764886 | 17405195772973 | 17405196106894 | 17405196146826 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 395 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 217728 | 0x7f85007d2080 | 0x7f84fd826040 | 17405196163215 | 17405196173934 | 17405196341934 | 17405196343221 |
| 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 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 222016 | 0x7f84fe131f00 | 0x7f84fd826080 | 17405196357740 | 17405196365774 | 17405196594574 | 17405196634333 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 401 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 226048 | 0x7f84fe131d80 | 0x7f84fd8260c0 | 17405196642283 | 17405196653294 | 17405196882255 | 17405196898246 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 404 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 230080 | 0x7f84fe131c00 | 0x7f84fd826100 | 17405196907266 | 17405196916975 | 17405197127855 | 17405197143820 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 407 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 235904 | 0x7f84fe131a80 | 0x7f84fd826140 | 17405197154110 | 17405197163375 | 17405197548815 | 17405197563749 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 410 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 239424 | 0x7f84fe131900 | 0x7f84fd826180 | 17405197580248 | 17405197590735 | 17405197778256 | 17405197779523 |
| 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 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 244224 | 0x7f84fe131780 | 0x7f84fd8261c0 | 17405197795533 | 17405197803696 | 17405198053936 | 17405198069396 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 416 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 248768 | 0x7f84fe131600 | 0x7f84fd826200 | 17405198082365 | 17405198090896 | 17405198338096 | 17405198379707 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 419 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 253312 | 0x7f85007d2480 | 0x7f84fd826240 | 17405198387567 | 17405198398096 | 17405198634897 | 17405198678120 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 422 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 8 | 24 | 255552 | 0x7f85007d2300 | 0x7f84fd826280 | 17405198686169 | 17405198696337 | 17405199149137 | 17405199192496 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 425 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 259840 | 0x7f85007d2180 | 0x7f84fd8262c0 | 17405199208516 | 17405199219377 | 17405199445937 | 17405199488638 |
| 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 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 265664 | 0x7f85007d2000 | 0x7f84fd826300 | 17405199497158 | 17405199507537 | 17405199805618 | 17405199849319 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 431 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 271232 | 0x7f84fe131e80 | 0x7f84fd826340 | 17405199859249 | 17405199869138 | 17405200168338 | 17405200211539 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 434 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 8 | 24 | 273216 | 0x7f84fe131d00 | 0x7f84fd826380 | 17405200222149 | 17405200232658 | 17405200529459 | 17405200569390 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 437 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 8 | 24 | 275712 | 0x7f84fe131b80 | 0x7f84fd8263c0 | 17405200577630 | 17405200588019 | 17405201146579 | 17405201162585 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 440 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 280768 | 0x7f84fe131a00 | 0x7f84fd826400 | 17405201178324 | 17405201188979 | 17405201452659 | 17405201471697 |
| 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 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 287616 | 0x7f84fe131880 | 0x7f84fd826440 | 17405201480786 | 17405201491060 | 17405201841140 | 17405201859216 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 446 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 294208 | 0x7f84fe131700 | 0x7f84fd826480 | 17405201871356 | 17405201886900 | 17405202236340 | 17405202288525 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 449 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 8 | 24 | 296960 | 0x7f85007d2580 | 0x7f84fd8264c0 | 17405202297775 | 17405202307700 | 17405202654741 | 17405202697994 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 452 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 8 | 24 | 299968 | 0x7f85007d2400 | 0x7f84fd826500 | 17405202708484 | 17405202718581 | 17405203380342 | 17405203420815 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 455 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 8 | 24 | 302720 | 0x7f85007d2280 | 0x7f84fd826540 | 17405203437755 | 17405203447702 | 17405203895222 | 17405203938042 |
| 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 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 305472 | 0x7f85007d2100 | 0x7f84fd826580 | 17405203946782 | 17405203956822 | 17405204421943 | 17405204465648 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 461 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 308224 | 0x7f84fe131f80 | 0x7f84fd8265c0 | 17405204474338 | 17405204484983 | 17405204946583 | 17405204989664 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 464 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 8 | 24 | 310976 | 0x7f84fe131e00 | 0x7f84fd826600 | 17405204998184 | 17405205008503 | 17405205460664 | 17405205505111 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 467 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 8 | 24 | 313216 | 0x7f84fe131c80 | 0x7f84fd826640 | 17405205513431 | 17405205523864 | 17405206392185 | 17405206440276 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 470 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 8 | 24 | 315968 | 0x7f84fe131b00 | 0x7f84fd826680 | 17405206457446 | 17405206468185 | 17405207322426 | 17405207365542 |
| 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 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 318720 | 0x7f84fe131980 | 0x7f84fd8266c0 | 17405207376212 | 17405207386266 | 17405208271547 | 17405208314588 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 476 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 321472 | 0x7f84fe131800 | 0x7f84fd826700 | 17405208322718 | 17405208332827 | 17405209212508 | 17405209255583 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 479 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 8 | 24 | 324224 | 0x7f84fe131680 | 0x7f84fd826740 | 17405209266903 | 17405209282428 | 17405210141469 | 17405210188299 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 482 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 8 | 24 | 326464 | 0x7f85007d2500 | 0x7f84fd826780 | 17405210197219 | 17405210207389 | 17405211905151 | 17405211975422 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 485 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 8 | 24 | 329216 | 0x7f85007d2380 | 0x7f84fd8267c0 | 17405211991572 | 17405212002431 | 17405213667392 | 17405213735436 |
| 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 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 331968 | 0x7f85007d2200 | 0x7f84fd826800 | 17405213745226 | 17405213754913 | 17405215480034 | 17405215549289 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 491 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 12 | 24 | 334720 | 0x7f85007d2080 | 0x7f84fd826840 | 17405215560548 | 17405215569474 | 17405217285476 | 17405217352241 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 494 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 8 | 24 | 337472 | 0x7f84fe131f00 | 0x7f84fd826880 | 17405217361561 | 17405217372036 | 17405219045478 | 17405219114965 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 497 | 210870 | 210870 | 4194304 | 256 | 0 | 0 | 8 | 24 | 0 | 0x7f84fe131d80 | 0x7f84fd8268c0 | 17405219123685 | 17405219134598 | 17405222490922 | 17405222566576 |