40 KiB
40 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | SQ_INSTS_LDS | SQ_INST_LEVEL_LDS | SQ_ACCUM_PREV_HIRES | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBuffer.kd | 0 | 0 | 0 | 886028 | 886033 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7fcf4e404180 | 0 | 0 | 0 | 12075646180516257 | 12075646424410985 | 12075646424734184 | 12075646424847586 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 886028 | 886033 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7fcf4e435100 | 0 | 0 | 0 | 12075646439713714 | 12075646440027638 | 12075646440034358 | 12075646440043206 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7fd05a091900 | 0x7fcf4e435140 | 0 | 0 | 0 | 12075646440101765 | 12075646440321077 | 12075646440454677 | 12075646440458067 |
| 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 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7fd05a091800 | 0x7fcf4e435180 | 0 | 0 | 0 | 12075646440525402 | 12075646440697236 | 12075646440945875 | 12075646441029148 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7fd05a091700 | 0x7fcf4e4351c0 | 0 | 0 | 0 | 12075646441059254 | 12075646441255793 | 12075646441502352 | 12075646441570835 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7fd05a091600 | 0x7fcf4e435200 | 0 | 0 | 0 | 12075646441599047 | 12075646441783151 | 12075646441916111 | 12075646441918942 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7fd05a091500 | 0x7fcf4e435240 | 0 | 0 | 0 | 12075646441968183 | 12075646442151630 | 12075646442285549 | 12075646442288739 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7fd05a091400 | 0x7fcf4e435280 | 0 | 0 | 0 | 12075646442362747 | 12075646442536908 | 12075646442667307 | 12075646442670128 |
| 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 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7fd05a091300 | 0x7fcf4e4352c0 | 0 | 0 | 0 | 12075646442719460 | 12075646442896746 | 12075646443147305 | 12075646443192128 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7fd05a091a00 | 0x7fcf4e435300 | 0 | 0 | 0 | 12075646443220541 | 12075646443406504 | 12075646443653703 | 12075646443696445 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7fd05a091900 | 0x7fcf4e435340 | 0 | 0 | 0 | 12075646443720630 | 12075646443912102 | 12075646444044582 | 12075646444047788 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7fd05a091800 | 0x7fcf4e435380 | 0 | 0 | 0 | 12075646444097811 | 12075646444276101 | 12075646444412580 | 12075646444415431 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7fd05a091700 | 0x7fcf4e4353c0 | 0 | 0 | 0 | 12075646444476996 | 12075646444646499 | 12075646444773378 | 12075646444776072 |
| 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 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7fd05a091600 | 0x7fcf4e435400 | 0 | 0 | 0 | 12075646444824071 | 12075646445001057 | 12075646445250016 | 12075646445320073 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7fd05a091500 | 0x7fcf4e435440 | 0 | 0 | 0 | 12075646445348866 | 12075646445532895 | 12075646445780894 | 12075646445849847 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7fd05a091400 | 0x7fcf4e435480 | 0 | 0 | 0 | 12075646445877028 | 12075646446073053 | 12075646446200412 | 12075646446203725 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7fd05a091300 | 0x7fcf4e4354c0 | 0 | 0 | 0 | 12075646446253868 | 12075646446423931 | 12075646446556571 | 12075646446559346 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7fd05a091a00 | 0x7fcf4e435500 | 0 | 0 | 0 | 12075646446620520 | 12075646446787770 | 12075646446915449 | 12075646446918533 |
| 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 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7fd05a091900 | 0x7fcf4e435540 | 0 | 0 | 0 | 12075646446967304 | 12075646447152728 | 12075646447404087 | 12075646447474216 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7fd05a091800 | 0x7fcf4e435580 | 0 | 0 | 0 | 12075646447499673 | 12075646447691926 | 12075646447945045 | 12075646447988983 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7fd05a091700 | 0x7fcf4e4355c0 | 0 | 0 | 0 | 12075646448022014 | 12075646448215604 | 12075646448347443 | 12075646448350274 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7fd05a091600 | 0x7fcf4e435600 | 0 | 0 | 0 | 12075646448403954 | 12075646448570642 | 12075646448700722 | 12075646448703681 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7fd05a091500 | 0x7fcf4e435640 | 0 | 0 | 0 | 12075646448769143 | 12075646448937041 | 12075646449065360 | 12075646449069030 |
| 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 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7fd05a091400 | 0x7fcf4e435680 | 0 | 0 | 0 | 12075646449116989 | 12075646449289359 | 12075646449536238 | 12075646449605307 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7fd05a091300 | 0x7fcf4e4356c0 | 0 | 0 | 0 | 12075646449634230 | 12075646449820717 | 12075646450069836 | 12075646450140281 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7fd05a091a00 | 0x7fcf4e435700 | 0 | 0 | 0 | 12075646450168012 | 12075646450357035 | 12075646450486314 | 12075646450489199 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7fd05a091900 | 0x7fcf4e435740 | 0 | 0 | 0 | 12075646450541316 | 12075646450708873 | 12075646450841833 | 12075646450844690 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7fd05a091800 | 0x7fcf4e435780 | 0 | 0 | 0 | 12075646450906835 | 12075646451080232 | 12075646451216391 | 12075646451219727 |
| 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 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7fd05a091700 | 0x7fcf4e4357c0 | 0 | 0 | 0 | 12075646451269339 | 12075646451447750 | 12075646451697189 | 12075646451766684 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7fd05a091600 | 0x7fcf4e435800 | 0 | 0 | 0 | 12075646451791650 | 12075646451979428 | 12075646452237667 | 12075646452306867 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7fd05a091500 | 0x7fcf4e435840 | 0 | 0 | 0 | 12075646452332305 | 12075646452519426 | 12075646452647745 | 12075646452650606 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7fd05a091400 | 0x7fcf4e435880 | 0 | 0 | 0 | 12075646452698696 | 12075646452866304 | 12075646452999424 | 12075646453006518 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7fd05a091300 | 0x7fcf4e4358c0 | 0 | 0 | 0 | 12075646453065918 | 12075646453235583 | 12075646453363102 | 12075646453366016 |
| 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 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7fd05a091a00 | 0x7fcf4e435900 | 0 | 0 | 0 | 12075646453416700 | 12075646453584061 | 12075646453838620 | 12075646453882936 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7fd05a091900 | 0x7fcf4e435940 | 0 | 0 | 0 | 12075646453908805 | 12075646454099899 | 12075646454351738 | 12075646454422810 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7fd05a091800 | 0x7fcf4e435980 | 0 | 0 | 0 | 12075646454450702 | 12075646454631417 | 12075646454764536 | 12075646454767330 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7fd05a091700 | 0x7fcf4e4359c0 | 0 | 0 | 0 | 12075646454816221 | 12075646454994455 | 12075646455128215 | 12075646455131336 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7fd05a091600 | 0x7fcf4e435a00 | 0 | 0 | 0 | 12075646455192650 | 12075646455363414 | 12075646455491253 | 12075646455494301 |
| 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 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7fd05a091500 | 0x7fcf4e435a40 | 0 | 0 | 0 | 12075646455543242 | 12075646455721492 | 12075646455982451 | 12075646456052629 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7fd05a091400 | 0x7fcf4e435a80 | 0 | 0 | 0 | 12075646456078196 | 12075646456266930 | 12075646456517009 | 12075646456586461 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7fd05a091300 | 0x7fcf4e435ac0 | 0 | 0 | 0 | 12075646456612309 | 12075646456794288 | 12075646456922447 | 12075646456925361 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7fd05a091a00 | 0x7fcf4e435b00 | 0 | 0 | 0 | 12075646456974031 | 12075646457146446 | 12075646457281966 | 12075646457284728 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7fd05a091900 | 0x7fcf4e435b40 | 0 | 0 | 0 | 12075646457346373 | 12075646457515885 | 12075646457643884 | 12075646457646741 |
| 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 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7fd05a091800 | 0x7fcf4e435b80 | 0 | 0 | 0 | 12075646457694500 | 12075646457869963 | 12075646458134762 | 12075646458205860 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7fd05a091700 | 0x7fcf4e435bc0 | 0 | 0 | 0 | 12075646458234073 | 12075646458418441 | 12075646458706440 | 12075646458776791 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7fd05a091600 | 0x7fcf4e435c00 | 0 | 0 | 0 | 12075646458803491 | 12075646458985799 | 12075646459114118 | 12075646459116984 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7fd05a091500 | 0x7fcf4e435c40 | 0 | 0 | 0 | 12075646459166786 | 12075646459335717 | 12075646459470756 | 12075646459473646 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7fd05a091400 | 0x7fcf4e435c80 | 0 | 0 | 0 | 12075646459534399 | 12075646459701636 | 12075646459833475 | 12075646459836391 |
| 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 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7fd05a091300 | 0x7fcf4e435cc0 | 0 | 0 | 0 | 12075646459885642 | 12075646460075714 | 12075646460340193 | 12075646460410638 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7fd05a091a00 | 0x7fcf4e435d00 | 0 | 0 | 0 | 12075646460438149 | 12075646460623072 | 12075646460874751 | 12075646460918983 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7fd05a091900 | 0x7fcf4e435d40 | 0 | 0 | 0 | 12075646460942206 | 12075646461135389 | 12075646461272029 | 12075646461275245 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7fd05a091800 | 0x7fcf4e435d80 | 0 | 0 | 0 | 12075646461326991 | 12075646461497788 | 12075646461634907 | 12075646461637859 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7fd05a091700 | 0x7fcf4e435dc0 | 0 | 0 | 0 | 12075646461698010 | 12075646461863386 | 12075646461993786 | 12075646461996776 |
| 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 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7fd05a091600 | 0x7fcf4e435e00 | 0 | 0 | 0 | 12075646462046578 | 12075646462222265 | 12075646462485304 | 12075646462555664 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7fd05a091500 | 0x7fcf4e435e40 | 0 | 0 | 0 | 12075646462580010 | 12075646462764503 | 12075646463014422 | 12075646463084187 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7fd05a091400 | 0x7fcf4e435e80 | 0 | 0 | 0 | 12075646463114643 | 12075646463302740 | 12075646463435220 | 12075646463438054 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7fd05a091300 | 0x7fcf4e435ec0 | 0 | 0 | 0 | 12075646463486043 | 12075646463657459 | 12075646463799858 | 12075646463802702 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7fd05a091a00 | 0x7fcf4e435f00 | 0 | 0 | 0 | 12075646463866160 | 12075646464036977 | 12075646464165457 | 12075646464168742 |
| 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 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7fd05a091900 | 0x7fcf4e435f40 | 0 | 0 | 0 | 12075646464217533 | 12075646464392176 | 12075646464658415 | 12075646464727671 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7fd05a091800 | 0x7fcf4e435f80 | 0 | 0 | 0 | 12075646464754300 | 12075646464936333 | 12075646465186892 | 12075646465257456 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7fd05a091700 | 0x7fcf4e435fc0 | 0 | 0 | 0 | 12075646465284686 | 12075646465465931 | 12075646465598571 | 12075646465601685 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7fd05a091600 | 0x7fcf4e436000 | 0 | 0 | 0 | 12075646465650265 | 12075646465817930 | 12075646465958249 | 12075646465960993 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7fd05a091500 | 0x7fcf4e436040 | 0 | 0 | 0 | 12075646466029330 | 12075646466191688 | 12075646466327688 | 12075646466330850 |
| 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 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7fd05a091400 | 0x7fcf4e436080 | 0 | 0 | 0 | 12075646466379932 | 12075646466554407 | 12075646466815205 | 12075646466883387 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7fd05a091300 | 0x7fcf4e4360c0 | 0 | 0 | 0 | 12075646466911950 | 12075646467103044 | 12075646467360323 | 12075646467431466 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7fd05a091a00 | 0x7fcf4e436100 | 0 | 0 | 0 | 12075646467459798 | 12075646467645282 | 12075646467774241 | 12075646467777108 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7fd05a091900 | 0x7fcf4e436140 | 0 | 0 | 0 | 12075646467825829 | 12075646468000001 | 12075646468143360 | 12075646468146715 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7fd05a091800 | 0x7fcf4e436180 | 0 | 0 | 0 | 12075646468208370 | 12075646468375359 | 12075646468509438 | 12075646468512335 |
| 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 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7fd05a091700 | 0x7fcf4e4361c0 | 0 | 0 | 0 | 12075646468559893 | 12075646468731517 | 12075646468993916 | 12075646469046107 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7fd05a091600 | 0x7fcf4e436200 | 0 | 0 | 0 | 12075646469072886 | 12075646469256155 | 12075646469507834 | 12075646469557928 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7fd05a091500 | 0x7fcf4e436240 | 0 | 0 | 0 | 12075646469585699 | 12075646469762553 | 12075646469896473 | 12075646469899703 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7fd05a091400 | 0x7fcf4e436280 | 0 | 0 | 0 | 12075646469946810 | 12075646470126232 | 12075646470275831 | 12075646470278727 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7fd05a091300 | 0x7fcf4e4362c0 | 0 | 0 | 0 | 12075646470359898 | 12075646470522230 | 12075646470658389 | 12075646470661378 |
| 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 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7fd05a091a00 | 0x7fcf4e436300 | 0 | 0 | 0 | 12075646470713395 | 12075646470882868 | 12075646471146547 | 12075646471198917 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7fd05a091900 | 0x7fcf4e436340 | 0 | 0 | 0 | 12075646471225727 | 12075646471407506 | 12075646471660465 | 12075646471711179 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7fd05a091800 | 0x7fcf4e436380 | 0 | 0 | 0 | 12075646471736076 | 12075646471919824 | 12075646472055183 | 12075646472058144 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7fd05a091700 | 0x7fcf4e4363c0 | 0 | 0 | 0 | 12075646472108488 | 12075646472284622 | 12075646472443502 | 12075646472446496 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7fd05a091600 | 0x7fcf4e436400 | 0 | 0 | 0 | 12075646472508281 | 12075646472672621 | 12075646472808940 | 12075646472812286 |
| 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 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7fd05a091500 | 0x7fcf4e436440 | 0 | 0 | 0 | 12075646472860205 | 12075646473035659 | 12075646473298218 | 12075646473350937 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7fd05a091400 | 0x7fcf4e436480 | 0 | 0 | 0 | 12075646473378839 | 12075646473561897 | 12075646473817096 | 12075646473841118 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7fd05a091300 | 0x7fcf4e4364c0 | 0 | 0 | 0 | 12075646473883006 | 12075646474053575 | 12075646474187974 | 12075646474191309 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7fd05a091a00 | 0x7fcf4e436500 | 0 | 0 | 0 | 12075646474238667 | 12075646474414213 | 12075646474578853 | 12075646474581945 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7fd05a091900 | 0x7fcf4e436540 | 0 | 0 | 0 | 12075646474642147 | 12075646474807332 | 12075646474937731 | 12075646474940691 |
| 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 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7fd05a091800 | 0x7fcf4e436580 | 0 | 0 | 0 | 12075646474989913 | 12075646475170210 | 12075646475434689 | 12075646475488169 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7fd05a091700 | 0x7fcf4e4365c0 | 0 | 0 | 0 | 12075646475513336 | 12075646475695808 | 12075646475947647 | 12075646475997926 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7fd05a091600 | 0x7fcf4e436600 | 0 | 0 | 0 | 12075646476030367 | 12075646476219326 | 12075646476355325 | 12075646476359117 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7fd05a091500 | 0x7fcf4e436640 | 0 | 0 | 0 | 12075646476406696 | 12075646476578044 | 12075646476751484 | 12075646476754733 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7fd05a091400 | 0x7fcf4e436680 | 0 | 0 | 0 | 12075646476815235 | 12075646476980923 | 12075646477112602 | 12075646477116064 |
| 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 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7fd05a091300 | 0x7fcf4e4366c0 | 0 | 0 | 0 | 12075646477163783 | 12075646477339321 | 12075646477597080 | 12075646477647832 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7fd05a091a00 | 0x7fcf4e436700 | 0 | 0 | 0 | 12075646477674171 | 12075646477853719 | 12075646478105878 | 12075646478157369 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7fd05a091900 | 0x7fcf4e436740 | 0 | 0 | 0 | 12075646478184440 | 12075646478364597 | 12075646478497396 | 12075646478500417 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7fd05a091800 | 0x7fcf4e436780 | 0 | 0 | 0 | 12075646478548396 | 12075646478721715 | 12075646478904275 | 12075646478907333 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7fd05a091700 | 0x7fcf4e4367c0 | 0 | 0 | 0 | 12075646478967755 | 12075646479137554 | 12075646479277073 | 12075646479280246 |
| 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 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7fd05a091600 | 0x7fcf4e436800 | 0 | 0 | 0 | 12075646479328265 | 12075646479503312 | 12075646479769711 | 12075646479792588 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7fd05a091500 | 0x7fcf4e436840 | 0 | 0 | 0 | 12075646479837842 | 12075646480003310 | 12075646480262829 | 12075646480313567 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7fd05a091400 | 0x7fcf4e436880 | 0 | 0 | 0 | 12075646480340396 | 12075646480522828 | 12075646480659627 | 12075646480662956 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7fd05a091300 | 0x7fcf4e4368c0 | 0 | 0 | 0 | 12075646480710023 | 12075646480879946 | 12075646481071945 | 12075646481121939 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7fd05a091a00 | 0x7fcf4e436900 | 0 | 0 | 0 | 12075646481162795 | 12075646481328744 | 12075646481463304 | 12075646481466349 |
| 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 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7fd05a091900 | 0x7fcf4e436940 | 0 | 0 | 0 | 12075646481514779 | 12075646481686183 | 12075646481970182 | 12075646482023965 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7fd05a091800 | 0x7fcf4e436980 | 0 | 0 | 0 | 12075646482052328 | 12075646482236580 | 12075646482491299 | 12075646482542429 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7fd05a091700 | 0x7fcf4e4369c0 | 0 | 0 | 0 | 12075646482569699 | 12075646482750178 | 12075646482887618 | 12075646482890746 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7fd05a091600 | 0x7fcf4e436a00 | 0 | 0 | 0 | 12075646482939907 | 12075646483119137 | 12075646483328736 | 12075646483380015 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7fd05a091500 | 0x7fcf4e436a40 | 0 | 0 | 0 | 12075646483419629 | 12075646483587135 | 12075646483726654 | 12075646483729785 |
| 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 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7fd05a091400 | 0x7fcf4e436a80 | 0 | 0 | 0 | 12075646483779037 | 12075646483957213 | 12075646484264412 | 12075646484316285 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7fd05a091300 | 0x7fcf4e436ac0 | 0 | 0 | 0 | 12075646484341162 | 12075646484526011 | 12075646484785530 | 12075646484836101 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7fd05a091a00 | 0x7fcf4e436b00 | 0 | 0 | 0 | 12075646484861929 | 12075646485050169 | 12075646485190168 | 12075646485193245 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7fd05a091900 | 0x7fcf4e436b40 | 0 | 0 | 0 | 12075646485241154 | 12075646485415287 | 12075646485642806 | 12075646485693194 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7fd05a091800 | 0x7fcf4e436b80 | 0 | 0 | 0 | 12075646485734050 | 12075646485903125 | 12075646486039604 | 12075646486043105 |
| 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 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7fd05a091700 | 0x7fcf4e436bc0 | 0 | 0 | 0 | 12075646486095432 | 12075646486266643 | 12075646486596722 | 12075646486647849 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7fd05a091600 | 0x7fcf4e436c00 | 0 | 0 | 0 | 12075646486673326 | 12075646486855441 | 12075646487106960 | 12075646487134914 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7fd05a091500 | 0x7fcf4e436c40 | 0 | 0 | 0 | 12075646487177884 | 12075646487341500 | 12075646487475900 | 12075646487483041 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7fd05a091400 | 0x7fcf4e436c80 | 0 | 0 | 0 | 12075646487526552 | 12075646487698298 | 12075646487944217 | 12075646487993760 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7fd05a091300 | 0x7fcf4e436cc0 | 0 | 0 | 0 | 12075646488035698 | 12075646488212856 | 12075646488354295 | 12075646488357265 |
| 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 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7fd05a091a00 | 0x7fcf4e436d00 | 0 | 0 | 0 | 12075646488405225 | 12075646488577655 | 12075646488955893 | 12075646489011451 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7fd05a091900 | 0x7fcf4e436d40 | 0 | 0 | 0 | 12075646489040475 | 12075646489223093 | 12075646489479092 | 12075646489530526 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7fd05a091800 | 0x7fcf4e436d80 | 0 | 0 | 0 | 12075646489559189 | 12075646489738611 | 12075646489877490 | 12075646489879955 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7fd05a091700 | 0x7fcf4e436dc0 | 0 | 0 | 0 | 12075646489929688 | 12075646490117649 | 12075646490398288 | 12075646490451337 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7fd05a091600 | 0x7fcf4e436e00 | 0 | 0 | 0 | 12075646490489678 | 12075646490654928 | 12075646490797647 | 12075646490800105 |
| 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 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7fd05a091500 | 0x7fcf4e436e40 | 0 | 0 | 0 | 12075646490846852 | 12075646491026606 | 12075646491453485 | 12075646491505045 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7fd05a091400 | 0x7fcf4e436e80 | 0 | 0 | 0 | 12075646491530012 | 12075646491718924 | 12075646491978123 | 12075646492028929 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7fd05a091300 | 0x7fcf4e436ec0 | 0 | 0 | 0 | 12075646492062622 | 12075646492234442 | 12075646492374122 | 12075646492376675 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7fd05a091a00 | 0x7fcf4e436f00 | 0 | 0 | 0 | 12075646492425125 | 12075646492599401 | 12075646492913960 | 12075646492963656 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7fd05a091900 | 0x7fcf4e436f40 | 0 | 0 | 0 | 12075646493008860 | 12075646493177319 | 12075646493330438 | 12075646493333333 |
| 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 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7fd05a091800 | 0x7fcf4e436f80 | 0 | 0 | 0 | 12075646493383817 | 12075646493560198 | 12075646494095236 | 12075646494146304 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7fd05a091700 | 0x7fcf4e436fc0 | 0 | 0 | 0 | 12075646494173645 | 12075646494362915 | 12075646494662594 | 12075646494712647 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7fd05a091600 | 0x7fcf4e437000 | 0 | 0 | 0 | 12075646494739236 | 12075646494923073 | 12075646495078112 | 12075646495081061 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7fd05a091500 | 0x7fcf4e437040 | 0 | 0 | 0 | 12075646495135182 | 12075646495322751 | 12075646495708670 | 12075646495758340 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7fd05a091400 | 0x7fcf4e437080 | 0 | 0 | 0 | 12075646495797843 | 12075646495965629 | 12075646496140829 | 12075646496143826 |
| 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 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7fd05a091300 | 0x7fcf4e4370c0 | 0 | 0 | 0 | 12075646496191946 | 12075646496369788 | 12075646496992026 | 12075646497042807 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7fd05a091a00 | 0x7fcf4e437100 | 0 | 0 | 0 | 12075646497071030 | 12075646497251385 | 12075646497577144 | 12075646497626532 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7fd05a091900 | 0x7fcf4e437140 | 0 | 0 | 0 | 12075646497655987 | 12075646497834743 | 12075646498013142 | 12075646498015735 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7fd05a091800 | 0x7fcf4e437180 | 0 | 0 | 0 | 12075646498067732 | 12075646498246101 | 12075646498703380 | 12075646498755290 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7fd05a091700 | 0x7fcf4e4371c0 | 0 | 0 | 0 | 12075646498794783 | 12075646498960979 | 12075646499160498 | 12075646499211828 |
| 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 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7fd05a091600 | 0x7fcf4e437200 | 0 | 0 | 0 | 12075646499244739 | 12075646499425617 | 12075646500130415 | 12075646500181250 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7fd05a091500 | 0x7fcf4e437240 | 0 | 0 | 0 | 12075646500213550 | 12075646500388814 | 12075646500761773 | 12075646500810730 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7fd05a091400 | 0x7fcf4e437280 | 0 | 0 | 0 | 12075646500837640 | 12075646501022252 | 12075646501226251 | 12075646501276275 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7fd05a091300 | 0x7fcf4e4372c0 | 0 | 0 | 0 | 12075646501304006 | 12075646501485610 | 12075646502028648 | 12075646502079528 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7fd05a091a00 | 0x7fcf4e437300 | 0 | 0 | 0 | 12075646502120454 | 12075646502290087 | 12075646502512807 | 12075646502560902 |
| 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 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7fd05a091900 | 0x7fcf4e437340 | 0 | 0 | 0 | 12075646502587381 | 12075646502767846 | 12075646503568483 | 12075646503620692 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7fd05a091800 | 0x7fcf4e437380 | 0 | 0 | 0 | 12075646503648143 | 12075646503831042 | 12075646504275841 | 12075646504328277 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7fd05a091700 | 0x7fcf4e4373c0 | 0 | 0 | 0 | 12075646504355387 | 12075646504549920 | 12075646504776639 | 12075646504826062 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7fd05a091600 | 0x7fcf4e437400 | 0 | 0 | 0 | 12075646504851900 | 12075646505044798 | 12075646505642236 | 12075646505694446 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7fd05a091500 | 0x7fcf4e437440 | 0 | 0 | 0 | 12075646505735312 | 12075646505901595 | 12075646506172154 | 12075646506222517 |
| 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 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7fd05a091400 | 0x7fcf4e437480 | 0 | 0 | 0 | 12075646506249517 | 12075646506430553 | 12075646507416630 | 12075646507487378 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7fd05a091300 | 0x7fcf4e4374c0 | 0 | 0 | 0 | 12075646507520309 | 12075646507703349 | 12075646508218707 | 12075646508289479 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7fd05a091a00 | 0x7fcf4e437500 | 0 | 0 | 0 | 12075646508325616 | 12075646508491826 | 12075646508794865 | 12075646508863355 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7fd05a091900 | 0x7fcf4e437540 | 0 | 0 | 0 | 12075646508894543 | 12075646509087664 | 12075646509826702 | 12075646509896074 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7fd05a091800 | 0x7fcf4e437580 | 0 | 0 | 0 | 12075646509941298 | 12075646510117421 | 12075646510435179 | 12075646510505808 |
| 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 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7fd05a091700 | 0x7fcf4e4375c0 | 0 | 0 | 0 | 12075646510537016 | 12075646510722058 | 12075646511892934 | 12075646511962264 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7fd05a091600 | 0x7fcf4e437600 | 0 | 0 | 0 | 12075646511997239 | 12075646512188613 | 12075646512798211 | 12075646512869500 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7fd05a091500 | 0x7fcf4e437640 | 0 | 0 | 0 | 12075646512897583 | 12075646513084930 | 12075646513404129 | 12075646513474375 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7fd05a091400 | 0x7fcf4e437680 | 0 | 0 | 0 | 12075646513501886 | 12075646513682688 | 12075646514561725 | 12075646514631866 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7fd05a091300 | 0x7fcf4e4376c0 | 0 | 0 | 0 | 12075646514673212 | 12075646514841084 | 12075646515253883 | 12075646515323852 |
| 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 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7fd05a091a00 | 0x7fcf4e437700 | 0 | 0 | 0 | 12075646515357394 | 12075646515529722 | 12075646517077077 | 12075646517148393 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7fd05a091900 | 0x7fcf4e437740 | 0 | 0 | 0 | 12075646517182055 | 12075646517361716 | 12075646518157233 | 12075646518227298 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7fd05a091800 | 0x7fcf4e437780 | 0 | 0 | 0 | 12075646518259948 | 12075646518438832 | 12075646518853870 | 12075646518923872 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7fd05a091700 | 0x7fcf4e4377c0 | 0 | 0 | 0 | 12075646518954770 | 12075646519144909 | 12075646520303785 | 12075646520375199 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7fd05a091600 | 0x7fcf4e437800 | 0 | 0 | 0 | 12075646520423219 | 12075646520590504 | 12075646521376422 | 12075646521446871 |
| 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 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7fd05a091500 | 0x7fcf4e437840 | 0 | 0 | 0 | 12075646521478680 | 12075646521662661 | 12075646524711610 | 12075646524782370 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7fd05a091400 | 0x7fcf4e437880 | 0 | 0 | 0 | 12075646524814900 | 12075646524997049 | 12075646526542324 | 12075646526614525 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7fd05a091300 | 0x7fcf4e4378c0 | 0 | 0 | 0 | 12075646526643479 | 12075646526834003 | 12075646527623600 | 12075646527694592 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7fd05a091a00 | 0x7fcf4e437900 | 0 | 0 | 0 | 12075646527722464 | 12075646527907119 | 12075646530189351 | 12075646530259769 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7fd05a091900 | 0x7fcf4e437940 | 0 | 0 | 0 | 12075646530305965 | 12075646530478470 | 12075646532013665 | 12075646532083729 |
| 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 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7fd05a091800 | 0x7fcf4e437980 | 0 | 0 | 0 | 12075646532117011 | 12075646532299264 | 12075646538356523 | 12075646538426527 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7fd05a091700 | 0x7fcf4e4379c0 | 0 | 0 | 0 | 12075646538457595 | 12075646538636682 | 12075646541680832 | 12075646541751446 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7fd05a091600 | 0x7fcf4e437a00 | 0 | 0 | 0 | 12075646541783025 | 12075646541969471 | 12075646543509305 | 12075646543581718 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 886028 | 886033 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7fd05a091500 | 0x7fcf4e437a40 | 0 | 0 | 0 | 12075646543613837 | 12075646543799064 | 12075646548327849 | 12075646548401255 |