39 KiB
39 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBuffer.kd | 0 | 0 | 0 | 840714 | 840719 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7f3b9c404180 | 12074629941989808 | 12074629942046408 | 12074629942371205 | 12074629942479097 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 840714 | 840719 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7f3b9c435100 | 12074629956915505 | 12074629957014277 | 12074629957021157 | 12074629957026963 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7f3ca7fca900 | 0x7f3b9c435140 | 12074629957069662 | 12074629957084356 | 12074629957218435 | 12074629957221865 |
| 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 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7f3ca7fca800 | 0x7f3b9c435180 | 12074629957263482 | 12074629957275075 | 12074629957521793 | 12074629957618953 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7f3ca7fca700 | 0x7f3b9c4351c0 | 12074629957644891 | 12074629957656351 | 12074629957900189 | 12074629957996544 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7f3ca7fca600 | 0x7f3b9c435200 | 12074629958028374 | 12074629958040028 | 12074629958165147 | 12074629958168634 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7f3ca7fca500 | 0x7f3b9c435240 | 12074629958195584 | 12074629958207707 | 12074629958332665 | 12074629958335755 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7f3ca7fca400 | 0x7f3b9c435280 | 12074629958388443 | 12074629958400025 | 12074629958524664 | 12074629958527651 |
| 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 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7f3ca7fca300 | 0x7f3b9c4352c0 | 12074629958553009 | 12074629958565303 | 12074629958813141 | 12074629958910042 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7f3ca7fcaa00 | 0x7f3b9c435300 | 12074629958930871 | 12074629958942580 | 12074629959223378 | 12074629959323801 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7f3ca7fca900 | 0x7f3b9c435340 | 12074629959345101 | 12074629959357937 | 12074629959483535 | 12074629959487235 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7f3ca7fca800 | 0x7f3b9c435380 | 12074629959511440 | 12074629959523535 | 12074629959647854 | 12074629959651109 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7f3ca7fca700 | 0x7f3b9c4353c0 | 12074629959688909 | 12074629959700494 | 12074629959824972 | 12074629959828058 |
| 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 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7f3ca7fca600 | 0x7f3b9c435400 | 12074629959853415 | 12074629959865612 | 12074629960112010 | 12074629960209878 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7f3ca7fca500 | 0x7f3b9c435440 | 12074629960230376 | 12074629960243209 | 12074629960486887 | 12074629960583432 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7f3ca7fca400 | 0x7f3b9c435480 | 12074629960604000 | 12074629960616326 | 12074629960741604 | 12074629960744832 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7f3ca7fca300 | 0x7f3b9c4354c0 | 12074629960770299 | 12074629960781604 | 12074629960907043 | 12074629960910289 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7f3ca7fcaa00 | 0x7f3b9c435500 | 12074629960945865 | 12074629960957923 | 12074629961082722 | 12074629961085825 |
| 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 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7f3ca7fca900 | 0x7f3b9c435540 | 12074629961111744 | 12074629961124481 | 12074629961376799 | 12074629961474778 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7f3ca7fca800 | 0x7f3b9c435580 | 12074629961494445 | 12074629961505758 | 12074629961749276 | 12074629961816844 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7f3ca7fca700 | 0x7f3b9c4355c0 | 12074629961836791 | 12074629961848315 | 12074629961973434 | 12074629961976711 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7f3ca7fca600 | 0x7f3b9c435600 | 12074629962006336 | 12074629962017913 | 12074629962143032 | 12074629962146456 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7f3ca7fca500 | 0x7f3b9c435640 | 12074629962182884 | 12074629962194552 | 12074629962318391 | 12074629962321452 |
| 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 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7f3ca7fca400 | 0x7f3b9c435680 | 12074629962348031 | 12074629962359990 | 12074629962605428 | 12074629962673145 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7f3ca7fca300 | 0x7f3b9c4356c0 | 12074629962693052 | 12074629962705427 | 12074629962951185 | 12074629963019599 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7f3ca7fcaa00 | 0x7f3b9c435700 | 12074629963045397 | 12074629963057104 | 12074629963181743 | 12074629963184716 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7f3ca7fca900 | 0x7f3b9c435740 | 12074629963209021 | 12074629963220783 | 12074629963346382 | 12074629963349562 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7f3ca7fca800 | 0x7f3b9c435780 | 12074629963385148 | 12074629963398701 | 12074629963523340 | 12074629963526701 |
| 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 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7f3ca7fca700 | 0x7f3b9c4357c0 | 12074629963551367 | 12074629963562860 | 12074629963811018 | 12074629963864359 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7f3ca7fca600 | 0x7f3b9c435800 | 12074629963884296 | 12074629963895017 | 12074629964139015 | 12074629964218417 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7f3ca7fca500 | 0x7f3b9c435840 | 12074629964237011 | 12074629964249734 | 12074629964375013 | 12074629964378244 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7f3ca7fca400 | 0x7f3b9c435880 | 12074629964404212 | 12074629964415972 | 12074629964541731 | 12074629964544803 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7f3ca7fca300 | 0x7f3b9c4358c0 | 12074629964579097 | 12074629964590531 | 12074629964715810 | 12074629964718747 |
| 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 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7f3ca7fcaa00 | 0x7f3b9c435900 | 12074629964743132 | 12074629964754690 | 12074629965002527 | 12074629965059770 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7f3ca7fca900 | 0x7f3b9c435940 | 12074629965079728 | 12074629965101247 | 12074629965344764 | 12074629965374475 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7f3ca7fca800 | 0x7f3b9c435980 | 12074629965395565 | 12074629965407644 | 12074629965532603 | 12074629965535785 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7f3ca7fca700 | 0x7f3b9c4359c0 | 12074629965560952 | 12074629965571962 | 12074629965697881 | 12074629965700872 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7f3ca7fca600 | 0x7f3b9c435a00 | 12074629965734695 | 12074629965747001 | 12074629965871640 | 12074629965874575 |
| 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 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7f3ca7fca500 | 0x7f3b9c435a40 | 12074629965898810 | 12074629965910199 | 12074629966157077 | 12074629966191784 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7f3ca7fca400 | 0x7f3b9c435a80 | 12074629966211701 | 12074629966223637 | 12074629966468115 | 12074629966493305 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7f3ca7fca300 | 0x7f3b9c435ac0 | 12074629966513833 | 12074629966525394 | 12074629966649713 | 12074629966652691 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7f3ca7fcaa00 | 0x7f3b9c435b00 | 12074629966677807 | 12074629966689393 | 12074629966815152 | 12074629966818098 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7f3ca7fca900 | 0x7f3b9c435b40 | 12074629966852953 | 12074629966864751 | 12074629966990670 | 12074629966993544 |
| 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 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7f3ca7fca800 | 0x7f3b9c435b80 | 12074629967022348 | 12074629967034030 | 12074629967283948 | 12074629967310423 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7f3ca7fca700 | 0x7f3b9c435bc0 | 12074629967329899 | 12074629967341227 | 12074629967584585 | 12074629967606794 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7f3ca7fca600 | 0x7f3b9c435c00 | 12074629967625559 | 12074629967637224 | 12074629967761383 | 12074629967764276 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7f3ca7fca500 | 0x7f3b9c435c40 | 12074629967790064 | 12074629967801383 | 12074629967928262 | 12074629967931167 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7f3ca7fca400 | 0x7f3b9c435c80 | 12074629967965631 | 12074629967977541 | 12074629968101700 | 12074629968104879 |
| 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 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7f3ca7fca300 | 0x7f3b9c435cc0 | 12074629968130928 | 12074629968142820 | 12074629968401218 | 12074629968424223 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7f3ca7fcaa00 | 0x7f3b9c435d00 | 12074629968443980 | 12074629968455457 | 12074629968701855 | 12074629968724361 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7f3ca7fca900 | 0x7f3b9c435d40 | 12074629968746712 | 12074629968759295 | 12074629968884574 | 12074629968887484 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7f3ca7fca800 | 0x7f3b9c435d80 | 12074629968911779 | 12074629968922973 | 12074629969052412 | 12074629969055276 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7f3ca7fca700 | 0x7f3b9c435dc0 | 12074629969091262 | 12074629969103452 | 12074629969228411 | 12074629969231323 |
| 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 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7f3ca7fca600 | 0x7f3b9c435e00 | 12074629969255748 | 12074629969267930 | 12074629969527128 | 12074629969550746 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7f3ca7fca500 | 0x7f3b9c435e40 | 12074629969570844 | 12074629969584087 | 12074629969832405 | 12074629969854902 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7f3ca7fca400 | 0x7f3b9c435e80 | 12074629969875330 | 12074629969886645 | 12074629970012404 | 12074629970015430 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7f3ca7fca300 | 0x7f3b9c435ec0 | 12074629970041438 | 12074629970053363 | 12074629970181842 | 12074629970184775 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7f3ca7fcaa00 | 0x7f3b9c435f00 | 12074629970222174 | 12074629970234162 | 12074629970359601 | 12074629970362595 |
| 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 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7f3ca7fca900 | 0x7f3b9c435f40 | 12074629970387662 | 12074629970400080 | 12074629970652398 | 12074629970675847 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7f3ca7fca800 | 0x7f3b9c435f80 | 12074629970695544 | 12074629970706958 | 12074629970956716 | 12074629970978860 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7f3ca7fca700 | 0x7f3b9c435fc0 | 12074629971005009 | 12074629971017035 | 12074629971142634 | 12074629971145570 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7f3ca7fca600 | 0x7f3b9c436000 | 12074629971170717 | 12074629971182314 | 12074629971320072 | 12074629971323120 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7f3ca7fca500 | 0x7f3b9c436040 | 12074629971358215 | 12074629971369832 | 12074629971495271 | 12074629971498055 |
| 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 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7f3ca7fca400 | 0x7f3b9c436080 | 12074629971523452 | 12074629971534951 | 12074629971794468 | 12074629971814072 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7f3ca7fca300 | 0x7f3b9c4360c0 | 12074629971833478 | 12074629971845028 | 12074629972090786 | 12074629972117286 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7f3ca7fcaa00 | 0x7f3b9c436100 | 12074629972139627 | 12074629972151265 | 12074629972275904 | 12074629972278826 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7f3ca7fca900 | 0x7f3b9c436140 | 12074629972302700 | 12074629972313984 | 12074629972456062 | 12074629972459271 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7f3ca7fca800 | 0x7f3b9c436180 | 12074629972493725 | 12074629972505342 | 12074629972630301 | 12074629972633265 |
| 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 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7f3ca7fca700 | 0x7f3b9c4361c0 | 12074629972656879 | 12074629972668061 | 12074629972930938 | 12074629972949753 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7f3ca7fca600 | 0x7f3b9c436200 | 12074629972969620 | 12074629972981338 | 12074629973227256 | 12074629973250812 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7f3ca7fca500 | 0x7f3b9c436240 | 12074629973269567 | 12074629973280695 | 12074629973406134 | 12074629973409077 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7f3ca7fca400 | 0x7f3b9c436280 | 12074629973434714 | 12074629973446134 | 12074629973596853 | 12074629973599871 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7f3ca7fca300 | 0x7f3b9c4362c0 | 12074629973653501 | 12074629973664852 | 12074629973789971 | 12074629973793060 |
| 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 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7f3ca7fcaa00 | 0x7f3b9c436300 | 12074629973818387 | 12074629973830451 | 12074629974092848 | 12074629974120268 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7f3ca7fca900 | 0x7f3b9c436340 | 12074629974140105 | 12074629974151728 | 12074629974400046 | 12074629974424403 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7f3ca7fca800 | 0x7f3b9c436380 | 12074629974446134 | 12074629974457485 | 12074629974583244 | 12074629974586104 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7f3ca7fca700 | 0x7f3b9c4363c0 | 12074629974610519 | 12074629974622124 | 12074629974778922 | 12074629974781848 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7f3ca7fca600 | 0x7f3b9c436400 | 12074629974816432 | 12074629974827722 | 12074629974952841 | 12074629974955751 |
| 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 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7f3ca7fca500 | 0x7f3b9c436440 | 12074629974981749 | 12074629974993160 | 12074629975255238 | 12074629975282859 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7f3ca7fca400 | 0x7f3b9c436480 | 12074629975302075 | 12074629975313478 | 12074629975559075 | 12074629975581143 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7f3ca7fca300 | 0x7f3b9c4364c0 | 12074629975603635 | 12074629975614915 | 12074629975741154 | 12074629975744186 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7f3ca7fcaa00 | 0x7f3b9c436500 | 12074629975768371 | 12074629975780034 | 12074629975946112 | 12074629975949267 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7f3ca7fca900 | 0x7f3b9c436540 | 12074629975984383 | 12074629975996352 | 12074629976121791 | 12074629976125264 |
| 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 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7f3ca7fca800 | 0x7f3b9c436580 | 12074629976149600 | 12074629976160830 | 12074629976426428 | 12074629976447363 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7f3ca7fca700 | 0x7f3b9c4365c0 | 12074629976467210 | 12074629976478747 | 12074629976724345 | 12074629976746980 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7f3ca7fca600 | 0x7f3b9c436600 | 12074629976766426 | 12074629976777785 | 12074629976903224 | 12074629976906256 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7f3ca7fca500 | 0x7f3b9c436640 | 12074629976931703 | 12074629976942743 | 12074629977114902 | 12074629977118220 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7f3ca7fca400 | 0x7f3b9c436680 | 12074629977155339 | 12074629977167061 | 12074629977292500 | 12074629977295609 |
| 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 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7f3ca7fca300 | 0x7f3b9c4366c0 | 12074629977320055 | 12074629977331700 | 12074629977588498 | 12074629977611476 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7f3ca7fcaa00 | 0x7f3b9c436700 | 12074629977629951 | 12074629977642417 | 12074629977888015 | 12074629977914349 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7f3ca7fca900 | 0x7f3b9c436740 | 12074629977934797 | 12074629977945935 | 12074629978071374 | 12074629978074366 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7f3ca7fca800 | 0x7f3b9c436780 | 12074629978098942 | 12074629978110573 | 12074629978293292 | 12074629978296680 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7f3ca7fca700 | 0x7f3b9c4367c0 | 12074629978330873 | 12074629978342091 | 12074629978467690 | 12074629978470953 |
| 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 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7f3ca7fca600 | 0x7f3b9c436800 | 12074629978494577 | 12074629978507050 | 12074629978770728 | 12074629978797711 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7f3ca7fca500 | 0x7f3b9c436840 | 12074629978817147 | 12074629978828167 | 12074629979072805 | 12074629979100554 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7f3ca7fca400 | 0x7f3b9c436880 | 12074629979123456 | 12074629979134884 | 12074629979260963 | 12074629979263877 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7f3ca7fca300 | 0x7f3b9c4368c0 | 12074629979287611 | 12074629979298883 | 12074629979490081 | 12074629979493123 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7f3ca7fcaa00 | 0x7f3b9c436900 | 12074629979529070 | 12074629979540481 | 12074629979667360 | 12074629979670653 |
| 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 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7f3ca7fca900 | 0x7f3b9c436940 | 12074629979695669 | 12074629979707359 | 12074629980020957 | 12074629980049287 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7f3ca7fca800 | 0x7f3b9c436980 | 12074629980070015 | 12074629980081276 | 12074629980329754 | 12074629980356938 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7f3ca7fca700 | 0x7f3b9c4369c0 | 12074629980376475 | 12074629980388153 | 12074629980513912 | 12074629980517106 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7f3ca7fca600 | 0x7f3b9c436a00 | 12074629980543555 | 12074629980554872 | 12074629980764150 | 12074629980786907 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7f3ca7fca500 | 0x7f3b9c436a40 | 12074629980817885 | 12074629980829750 | 12074629980957748 | 12074629980960981 |
| 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 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7f3ca7fca400 | 0x7f3b9c436a80 | 12074629980985557 | 12074629980997268 | 12074629981303185 | 12074629981329576 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7f3ca7fca300 | 0x7f3b9c436ac0 | 12074629981349823 | 12074629981361265 | 12074629981609903 | 12074629981632619 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7f3ca7fcaa00 | 0x7f3b9c436b00 | 12074629981653808 | 12074629981665262 | 12074629981791821 | 12074629981794971 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7f3ca7fca900 | 0x7f3b9c436b40 | 12074629981819887 | 12074629981831021 | 12074629982058539 | 12074629982082425 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7f3ca7fca800 | 0x7f3b9c436b80 | 12074629982112661 | 12074629982124458 | 12074629982251177 | 12074629982254374 |
| 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 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7f3ca7fca700 | 0x7f3b9c436bc0 | 12074629982279321 | 12074629982290377 | 12074629982619334 | 12074629982641614 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7f3ca7fca600 | 0x7f3b9c436c00 | 12074629982661601 | 12074629982673094 | 12074629982924611 | 12074629982947863 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7f3ca7fca500 | 0x7f3b9c436c40 | 12074629982968672 | 12074629982979811 | 12074629983108290 | 12074629983111507 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7f3ca7fca400 | 0x7f3b9c436c80 | 12074629983137255 | 12074629983148289 | 12074629983391487 | 12074629983417366 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7f3ca7fca300 | 0x7f3b9c436cc0 | 12074629983446279 | 12074629983458207 | 12074629983588126 | 12074629983591229 |
| 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 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7f3ca7fcaa00 | 0x7f3b9c436d00 | 12074629983615674 | 12074629983627165 | 12074629984001882 | 12074629984030605 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7f3ca7fca900 | 0x7f3b9c436d40 | 12074629984049741 | 12074629984060761 | 12074629984312119 | 12074629984339199 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7f3ca7fca800 | 0x7f3b9c436d80 | 12074629984358905 | 12074629984370359 | 12074629984499158 | 12074629984502362 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7f3ca7fca700 | 0x7f3b9c436dc0 | 12074629984527699 | 12074629984538997 | 12074629984817875 | 12074629984844909 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7f3ca7fca600 | 0x7f3b9c436e00 | 12074629984875776 | 12074629984887154 | 12074629985022513 | 12074629985025865 |
| 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 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7f3ca7fca500 | 0x7f3b9c436e40 | 12074629985051322 | 12074629985063153 | 12074629985484749 | 12074629985513301 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7f3ca7fca400 | 0x7f3b9c436e80 | 12074629985534500 | 12074629985545389 | 12074629985802506 | 12074629985829078 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7f3ca7fca300 | 0x7f3b9c436ec0 | 12074629985848293 | 12074629985859146 | 12074629985994665 | 12074629985997781 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7f3ca7fcaa00 | 0x7f3b9c436f00 | 12074629986024601 | 12074629986035624 | 12074629986350022 | 12074629986377457 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7f3ca7fca900 | 0x7f3b9c436f40 | 12074629986407452 | 12074629986419301 | 12074629986571460 | 12074629986574553 |
| 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 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7f3ca7fca800 | 0x7f3b9c436f80 | 12074629986599279 | 12074629986610819 | 12074629987126975 | 12074629987154441 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7f3ca7fca700 | 0x7f3b9c436fc0 | 12074629987175069 | 12074629987186174 | 12074629987485532 | 12074629987512466 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7f3ca7fca600 | 0x7f3b9c437000 | 12074629987534777 | 12074629987546491 | 12074629987699450 | 12074629987702619 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7f3ca7fca500 | 0x7f3b9c437040 | 12074629987727015 | 12074629987738969 | 12074629988123286 | 12074629988152215 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7f3ca7fca400 | 0x7f3b9c437080 | 12074629988186038 | 12074629988197845 | 12074629988373364 | 12074629988376822 |
| 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 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7f3ca7fca300 | 0x7f3b9c4370c0 | 12074629988401468 | 12074629988413364 | 12074629989022158 | 12074629989050214 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7f3ca7fcaa00 | 0x7f3b9c437100 | 12074629989075060 | 12074629989087598 | 12074629989417675 | 12074629989443705 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7f3ca7fca900 | 0x7f3b9c437140 | 12074629989465796 | 12074629989478474 | 12074629989655753 | 12074629989659025 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7f3ca7fca800 | 0x7f3b9c437180 | 12074629989683210 | 12074629989694152 | 12074629990149508 | 12074629990177789 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7f3ca7fca700 | 0x7f3b9c4371c0 | 12074629990213866 | 12074629990225028 | 12074629990423906 | 12074629990450826 |
| 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 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7f3ca7fca600 | 0x7f3b9c437200 | 12074629990468519 | 12074629990480386 | 12074629991183419 | 12074629991211871 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7f3ca7fca500 | 0x7f3b9c437240 | 12074629991234363 | 12074629991245179 | 12074629991616696 | 12074629991643262 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7f3ca7fca400 | 0x7f3b9c437280 | 12074629991664542 | 12074629991675735 | 12074629991879573 | 12074629991905560 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7f3ca7fca300 | 0x7f3b9c4372c0 | 12074629991924786 | 12074629991936853 | 12074629992462128 | 12074629992495406 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7f3ca7fcaa00 | 0x7f3b9c437300 | 12074629992523258 | 12074629992534768 | 12074629992759406 | 12074629992785315 |
| 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 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7f3ca7fca900 | 0x7f3b9c437340 | 12074629992805462 | 12074629992816685 | 12074629993614918 | 12074629993643319 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7f3ca7fca800 | 0x7f3b9c437380 | 12074629993662305 | 12074629993673318 | 12074629994091874 | 12074629994119995 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7f3ca7fca700 | 0x7f3b9c4373c0 | 12074629994142417 | 12074629994153794 | 12074629994380192 | 12074629994406728 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7f3ca7fca600 | 0x7f3b9c437400 | 12074629994425613 | 12074629994436671 | 12074629995032986 | 12074629995060192 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7f3ca7fca500 | 0x7f3b9c437440 | 12074629995092021 | 12074629995103225 | 12074629995371063 | 12074629995398611 |
| 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 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7f3ca7fca400 | 0x7f3b9c437480 | 12074629995418528 | 12074629995429942 | 12074629996414574 | 12074629996443122 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7f3ca7fca300 | 0x7f3b9c4374c0 | 12074629996464532 | 12074629996475533 | 12074629996988969 | 12074629997017540 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7f3ca7fcaa00 | 0x7f3b9c437500 | 12074629997041825 | 12074629997052968 | 12074629997324646 | 12074629997351891 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7f3ca7fca900 | 0x7f3b9c437540 | 12074629997372439 | 12074629997384165 | 12074629998121119 | 12074629998149473 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7f3ca7fca800 | 0x7f3b9c437580 | 12074629998180992 | 12074629998192958 | 12074629998507996 | 12074629998535120 |
| 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 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7f3ca7fca700 | 0x7f3b9c4375c0 | 12074629998555157 | 12074629998566235 | 12074629999736625 | 12074629999764735 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7f3ca7fca600 | 0x7f3b9c437600 | 12074629999783390 | 12074629999794544 | 12074630000406059 | 12074630000436003 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7f3ca7fca500 | 0x7f3b9c437640 | 12074630000458304 | 12074630000469419 | 12074630000788296 | 12074630000816029 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7f3ca7fca400 | 0x7f3b9c437680 | 12074630000837148 | 12074630000848615 | 12074630001726048 | 12074630001760784 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7f3ca7fca300 | 0x7f3b9c4376c0 | 12074630001790440 | 12074630001802207 | 12074630002211803 | 12074630002240586 |
| 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 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7f3ca7fcaa00 | 0x7f3b9c437700 | 12074630002263368 | 12074630002274843 | 12074630003824109 | 12074630003897455 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7f3ca7fca900 | 0x7f3b9c437740 | 12074630003918655 | 12074630003930348 | 12074630004723942 | 12074630004797388 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7f3ca7fca800 | 0x7f3b9c437780 | 12074630004821803 | 12074630004833231 | 12074630005246508 | 12074630005325409 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7f3ca7fca700 | 0x7f3b9c4377c0 | 12074630005344134 | 12074630005355946 | 12074630006513858 | 12074630006586633 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7f3ca7fca600 | 0x7f3b9c437800 | 12074630006618261 | 12074630006630657 | 12074630007415611 | 12074630007488018 |
| 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 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7f3ca7fca500 | 0x7f3b9c437840 | 12074630007509658 | 12074630007521370 | 12074630010571267 | 12074630010643712 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7f3ca7fca400 | 0x7f3b9c437880 | 12074630010664711 | 12074630010676386 | 12074630012216215 | 12074630012288709 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7f3ca7fca300 | 0x7f3b9c4378c0 | 12074630012308265 | 12074630012320054 | 12074630013108688 | 12074630013180587 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7f3ca7fcaa00 | 0x7f3b9c437900 | 12074630013201616 | 12074630013213007 | 12074630015493950 | 12074630015566851 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7f3ca7fca900 | 0x7f3b9c437940 | 12074630015601295 | 12074630015612829 | 12074630017148018 | 12074630017220644 |
| 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 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7f3ca7fca800 | 0x7f3b9c437980 | 12074630017240832 | 12074630017252337 | 12074630023306052 | 12074630023379039 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7f3ca7fca700 | 0x7f3b9c4379c0 | 12074630023400188 | 12074630023411331 | 12074630026454668 | 12074630026527550 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7f3ca7fca600 | 0x7f3b9c437a00 | 12074630026548259 | 12074630026559627 | 12074630028098656 | 12074630028171345 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 840714 | 840719 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7f3ca7fca500 | 0x7f3b9c437a40 | 12074630028189869 | 12074630028201215 | 12074630032727261 | 12074630032799406 |