41 KiB
41 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | SQ_INSTS_SMEM | SQ_INST_LEVEL_SMEM | SQ_ACCUM_PREV_HIRES | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBufferAligned.kd | 0 | 0 | 0 | 136822 | 136822 | 33554432 | 256 | 0 | 0 | 4 | 32 | 4160 | 0x0 | 0x7ff914a04280 | 3670016 | 2916842 | 326647824 | 15892871944314 | 15808676099944 | 15893020002100 | 15893020095280 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 136822 | 136822 | 32768 | 256 | 0 | 0 | 12 | 24 | 13888 | 0x0 | 0x7ff914a23f80 | 512 | 99786 | 11189496 | 15893025292904 | 15893020002100 | 15893025424675 | 15893025429601 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 5 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 14336 | 0x7ff917ab0380 | 0x7ff914a23fc0 | 65536 | 627382 | 70264104 | 15893025464240 | 15893025424675 | 15893025793636 | 15893025796253 |
| 5 | 3 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 8 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15040 | 0x7ff917ab0200 | 0x7ff914a24000 | 65536 | 657164 | 73520392 | 15893025832352 | 15893025793636 | 15893026204837 | 15893026207373 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 11 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15488 | 0x7ff917ab0080 | 0x7ff914a24040 | 65536 | 654864 | 73251264 | 15893026240573 | 15893026204837 | 15893026621798 | 15893026624494 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 14 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 15936 | 0x7ff91540df00 | 0x7ff914a24080 | 65536 | 660038 | 73868200 | 15893026656573 | 15893026621798 | 15893026942119 | 15893026944467 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 17 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 16384 | 0x7ff91540dd80 | 0x7ff914a240c0 | 65536 | 616410 | 69001208 | 15893026977876 | 15893026942119 | 15893027254760 | 15893027257330 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 20 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 17088 | 0x7ff91540dc00 | 0x7ff914a24100 | 131072 | 671442 | 75236296 | 15893027301949 | 15893027254760 | 15893027573161 | 15893027575713 |
| 10 | 8 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 23 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 16 | 24 | 17792 | 0x7ff91540da80 | 0x7ff914a24140 | 131072 | 686858 | 76994536 | 15893027607232 | 15893027573161 | 15893027972202 | 15893027974754 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 26 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 16 | 24 | 18496 | 0x7ff91540d900 | 0x7ff914a24180 | 65536 | 655240 | 73476824 | 15893028006303 | 15893027972202 | 15893028364523 | 15893028366975 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 29 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19200 | 0x7ff91540d780 | 0x7ff914a241c0 | 131072 | 686676 | 76979456 | 15893028398065 | 15893028364523 | 15893028685804 | 15893028688368 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 32 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19904 | 0x7ff91540d600 | 0x7ff914a24200 | 131072 | 686208 | 76923832 | 15893028719737 | 15893028685804 | 15893028993805 | 15893028996071 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 35 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 20608 | 0x7ff917ab0480 | 0x7ff914a24240 | 131072 | 693478 | 77736544 | 15893029036770 | 15893028993805 | 15893029301486 | 15893029303924 |
| 15 | 13 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 38 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 16 | 24 | 21312 | 0x7ff917ab0300 | 0x7ff914a24280 | 131072 | 690550 | 77338792 | 15893029336104 | 15893029301486 | 15893029699087 | 15893029701575 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 41 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22016 | 0x7ff917ab0180 | 0x7ff914a242c0 | 65536 | 659078 | 73853504 | 15893029732885 | 15893029699087 | 15893030096688 | 15893030104086 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 44 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22720 | 0x7ff917ab0000 | 0x7ff914a24300 | 131072 | 695088 | 77846680 | 15893030132486 | 15893030096688 | 15893030414129 | 15893030416789 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 47 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 23424 | 0x7ff91540de80 | 0x7ff914a24340 | 131072 | 684158 | 76527152 | 15893030448949 | 15893030414129 | 15893030723090 | 15893030725743 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 50 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 24128 | 0x7ff91540dd00 | 0x7ff914a24380 | 131072 | 683792 | 76515032 | 15893030765362 | 15893030723090 | 15893031017170 | 15893031019076 |
| 20 | 18 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 53 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 16 | 24 | 24832 | 0x7ff91540db80 | 0x7ff914a243c0 | 131072 | 708032 | 79485080 | 15893031050945 | 15893031017170 | 15893031382611 | 15893031384498 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 56 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 16 | 24 | 25536 | 0x7ff91540da00 | 0x7ff914a24400 | 65536 | 623766 | 69954416 | 15893031416637 | 15893031382611 | 15893031758613 | 15893031760610 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 59 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26240 | 0x7ff91540d880 | 0x7ff914a24440 | 131072 | 695484 | 77981688 | 15893031791879 | 15893031758613 | 15893032040213 | 15893032042293 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 62 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26944 | 0x7ff91540d700 | 0x7ff914a24480 | 131072 | 685698 | 76792704 | 15893032073003 | 15893032040213 | 15893032319894 | 15893032321917 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 65 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 27648 | 0x7ff917ab0580 | 0x7ff914a244c0 | 131072 | 658970 | 73864016 | 15893032360786 | 15893032319894 | 15893032602295 | 15893032604111 |
| 25 | 23 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 68 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 16 | 24 | 28608 | 0x7ff917ab0400 | 0x7ff914a24500 | 131072 | 684364 | 76628400 | 15893032636780 | 15893032602295 | 15893032971576 | 15893032973583 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 71 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 16 | 24 | 29312 | 0x7ff917ab0280 | 0x7ff914a24540 | 65536 | 652714 | 72966784 | 15893033005122 | 15893032971576 | 15893033339417 | 15893033341325 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 74 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 30016 | 0x7ff917ab0100 | 0x7ff914a24580 | 131072 | 656468 | 73421256 | 15893033372664 | 15893033339417 | 15893033618938 | 15893033620818 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 77 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 8 | 24 | 30976 | 0x7ff91540df80 | 0x7ff914a245c0 | 131072 | 717016 | 80337144 | 15893033652408 | 15893033618938 | 15893033900059 | 15893033901872 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 80 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 31680 | 0x7ff91540de00 | 0x7ff914a24600 | 131072 | 682746 | 76439336 | 15893033941081 | 15893033900059 | 15893034193499 | 15893034195626 |
| 30 | 28 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 83 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 16 | 24 | 32640 | 0x7ff91540dc80 | 0x7ff914a24640 | 131072 | 666204 | 74643336 | 15893034227385 | 15893034193499 | 15893034570621 | 15893034572597 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 86 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 33600 | 0x7ff91540db00 | 0x7ff914a24680 | 65536 | 691246 | 77461528 | 15893034603787 | 15893034570621 | 15893034950142 | 15893034952049 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 89 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 34560 | 0x7ff91540d980 | 0x7ff914a246c0 | 131072 | 685732 | 76789808 | 15893034984168 | 15893034950142 | 15893035230782 | 15893035232812 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 92 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 8 | 24 | 35520 | 0x7ff91540d800 | 0x7ff914a24700 | 131072 | 695426 | 77865152 | 15893035264162 | 15893035230782 | 15893035511743 | 15893035513796 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 95 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 36224 | 0x7ff91540d680 | 0x7ff914a24740 | 131072 | 690222 | 77295168 | 15893035553435 | 15893035511743 | 15893035792544 | 15893035794530 |
| 35 | 33 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 98 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 37184 | 0x7ff917ab0500 | 0x7ff914a24780 | 131072 | 656370 | 73669592 | 15893035826029 | 15893035792544 | 15893036157985 | 15893036159952 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 101 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 38144 | 0x7ff917ab0380 | 0x7ff914a247c0 | 65536 | 658870 | 73736504 | 15893036192431 | 15893036157985 | 15893036526146 | 15893036528114 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 104 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 39104 | 0x7ff917ab0200 | 0x7ff914a24800 | 131072 | 691248 | 77510896 | 15893036559793 | 15893036526146 | 15893036805347 | 15893036807347 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 107 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 8 | 24 | 40320 | 0x7ff917ab0080 | 0x7ff914a24840 | 131072 | 686348 | 76800664 | 15893036839477 | 15893036805347 | 15893037088388 | 15893037090191 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 110 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 41280 | 0x7ff91540df00 | 0x7ff914a24880 | 131072 | 736546 | 82367088 | 15893037129390 | 15893037088388 | 15893037371268 | 15893037373235 |
| 40 | 38 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 113 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 42240 | 0x7ff91540dd80 | 0x7ff914a248c0 | 131072 | 694842 | 77838576 | 15893037405044 | 15893037371268 | 15893037744550 | 15893037746506 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 116 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 43200 | 0x7ff91540dc00 | 0x7ff914a24900 | 65536 | 615358 | 68873936 | 15893037778266 | 15893037744550 | 15893038111111 | 15893038113088 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 119 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 8 | 24 | 44160 | 0x7ff91540da80 | 0x7ff914a24940 | 131072 | 687108 | 76999312 | 15893038145527 | 15893038111111 | 15893038395751 | 15893038397742 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 122 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 45376 | 0x7ff91540d900 | 0x7ff914a24980 | 131072 | 687394 | 77026376 | 15893038429151 | 15893038395751 | 15893038687912 | 15893038689865 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 125 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 46336 | 0x7ff91540d780 | 0x7ff914a249c0 | 131072 | 691504 | 77365280 | 15893038728804 | 15893038687912 | 15893038972393 | 15893038974449 |
| 45 | 43 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 128 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 47552 | 0x7ff91540d600 | 0x7ff914a24a00 | 131072 | 687342 | 76953480 | 15893039006178 | 15893038972393 | 15893039337834 | 15893039339881 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 131 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 48512 | 0x7ff917ab0480 | 0x7ff914a24a40 | 65536 | 648282 | 72604216 | 15893039372330 | 15893039337834 | 15893039705995 | 15893039707803 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 134 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 8 | 24 | 49472 | 0x7ff917ab0300 | 0x7ff914a24a80 | 131072 | 697478 | 78096344 | 15893039739612 | 15893039705995 | 15893039988716 | 15893039990536 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 137 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 50688 | 0x7ff917ab0180 | 0x7ff914a24ac0 | 131072 | 658456 | 73732648 | 15893040022385 | 15893039988716 | 15893040268397 | 15893040270170 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 140 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 51648 | 0x7ff917ab0000 | 0x7ff914a24b00 | 131072 | 647254 | 72506464 | 15893040309839 | 15893040268397 | 15893040552397 | 15893040554404 |
| 50 | 48 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 143 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 52864 | 0x7ff91540de80 | 0x7ff914a24b40 | 131072 | 691546 | 77502536 | 15893040585793 | 15893040552397 | 15893040921359 | 15893040923375 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 146 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 54080 | 0x7ff91540dd00 | 0x7ff914a24b80 | 65536 | 653968 | 73276584 | 15893040954025 | 15893040921359 | 15893041287280 | 15893041289267 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 149 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 8 | 24 | 55296 | 0x7ff91540db80 | 0x7ff914a24bc0 | 131072 | 686132 | 76852552 | 15893041321446 | 15893041287280 | 15893041570640 | 15893041572651 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 152 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 56768 | 0x7ff91540da00 | 0x7ff914a24c00 | 131072 | 692666 | 77499112 | 15893041604630 | 15893041570640 | 15893041850801 | 15893041852735 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 155 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 57728 | 0x7ff91540d880 | 0x7ff914a24c40 | 131072 | 686470 | 77041992 | 15893041892484 | 15893041850801 | 15893042130482 | 15893042132678 |
| 55 | 53 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 158 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 58944 | 0x7ff91540d700 | 0x7ff914a24c80 | 131072 | 656962 | 73427272 | 15893042164828 | 15893042130482 | 15893042497043 | 15893042498950 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 161 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 60160 | 0x7ff917ab0580 | 0x7ff914a24cc0 | 65536 | 658298 | 73747232 | 15893042531089 | 15893042497043 | 15893042862484 | 15893042864272 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 164 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 8 | 24 | 61376 | 0x7ff917ab0400 | 0x7ff914a24d00 | 131072 | 690632 | 77346088 | 15893042896261 | 15893042862484 | 15893043139765 | 15893043141646 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 167 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 62848 | 0x7ff917ab0280 | 0x7ff914a24d40 | 131072 | 683802 | 76685752 | 15893043174345 | 15893043139765 | 15893043430006 | 15893043432109 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 170 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 63808 | 0x7ff917ab0100 | 0x7ff914a24d80 | 131072 | 716818 | 80383816 | 15893043471408 | 15893043430006 | 15893043709846 | 15893043711893 |
| 60 | 58 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 173 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 65024 | 0x7ff91540df80 | 0x7ff914a24dc0 | 131072 | 673474 | 75430160 | 15893043743142 | 15893043709846 | 15893044075447 | 15893044077425 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 176 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 66240 | 0x7ff91540de00 | 0x7ff914a24e00 | 65536 | 654758 | 73371344 | 15893044109314 | 15893044075447 | 15893044439448 | 15893044441307 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 179 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 8 | 24 | 67456 | 0x7ff91540dc80 | 0x7ff914a24e40 | 131072 | 692162 | 77567440 | 15893044472556 | 15893044439448 | 15893044719129 | 15893044721301 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 182 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 68928 | 0x7ff91540db00 | 0x7ff914a24e80 | 131072 | 681538 | 76394416 | 15893044752620 | 15893044719129 | 15893045009530 | 15893045011474 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 185 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 70144 | 0x7ff91540d980 | 0x7ff914a24ec0 | 131072 | 657760 | 73698128 | 15893045050273 | 15893045009530 | 15893045289051 | 15893045290928 |
| 65 | 63 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 188 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 71616 | 0x7ff91540d800 | 0x7ff914a24f00 | 131072 | 686144 | 76746440 | 15893045322207 | 15893045289051 | 15893045654172 | 15893045656080 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 191 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 72832 | 0x7ff91540d680 | 0x7ff914a24f40 | 65536 | 682936 | 76504552 | 15893045687969 | 15893045654172 | 15893046019613 | 15893046021561 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 194 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 8 | 24 | 74048 | 0x7ff917ab0500 | 0x7ff914a24f80 | 131072 | 682074 | 76351112 | 15893046052091 | 15893046019613 | 15893046312254 | 15893046314405 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 197 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 75776 | 0x7ff917ab0380 | 0x7ff914a24fc0 | 131072 | 649294 | 72733928 | 15893046346174 | 15893046312254 | 15893046618015 | 15893046619888 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 200 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 76992 | 0x7ff917ab0200 | 0x7ff914a25000 | 131072 | 683478 | 76563000 | 15893046659007 | 15893046618015 | 15893046898175 | 15893046900102 |
| 70 | 68 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 203 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 78464 | 0x7ff917ab0080 | 0x7ff914a25040 | 131072 | 688702 | 77013880 | 15893046932211 | 15893046898175 | 15893047263136 | 15893047265144 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 206 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 79936 | 0x7ff91540df00 | 0x7ff914a25080 | 65536 | 654626 | 73326120 | 15893047297343 | 15893047263136 | 15893047628418 | 15893047630376 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 209 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 8 | 24 | 81408 | 0x7ff91540dd80 | 0x7ff914a250c0 | 131072 | 727314 | 81583728 | 15893047661995 | 15893047628418 | 15893047907778 | 15893047909589 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 212 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 83136 | 0x7ff91540dc00 | 0x7ff914a25100 | 131072 | 692104 | 77548608 | 15893047941429 | 15893047907778 | 15893048205699 | 15893048207683 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 215 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 84352 | 0x7ff91540da80 | 0x7ff914a25140 | 131072 | 684676 | 76687232 | 15893048259221 | 15893048205699 | 15893048486660 | 15893048488486 |
| 75 | 73 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 218 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 85824 | 0x7ff91540d900 | 0x7ff914a25180 | 131072 | 687250 | 76907880 | 15893048520396 | 15893048486660 | 15893048851461 | 15893048853408 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 221 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 87296 | 0x7ff91540d780 | 0x7ff914a251c0 | 65536 | 648534 | 72661288 | 15893048885217 | 15893048851461 | 15893049222662 | 15893049224500 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 224 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 88768 | 0x7ff91540d600 | 0x7ff914a25200 | 131072 | 684888 | 76771320 | 15893049255929 | 15893049222662 | 15893049509703 | 15893049511663 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 227 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 90752 | 0x7ff917ab0480 | 0x7ff914a25240 | 131072 | 694054 | 77755480 | 15893049543073 | 15893049509703 | 15893049814024 | 15893049816027 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 230 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 91968 | 0x7ff917ab0300 | 0x7ff914a25280 | 131072 | 684614 | 76686232 | 15893049854716 | 15893049814024 | 15893050096265 | 15893050098190 |
| 80 | 78 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 233 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 93440 | 0x7ff917ab0180 | 0x7ff914a252c0 | 131072 | 688742 | 77219312 | 15893050130450 | 15893050096265 | 15893050470986 | 15893050472872 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 236 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 94912 | 0x7ff917ab0000 | 0x7ff914a25300 | 65536 | 670096 | 74977744 | 15893050505271 | 15893050470986 | 15893050838827 | 15893050840714 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 239 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 96384 | 0x7ff91540de80 | 0x7ff914a25340 | 131072 | 690708 | 77347016 | 15893050871843 | 15893050838827 | 15893051116587 | 15893051118538 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 242 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 98368 | 0x7ff91540dd00 | 0x7ff914a25380 | 131072 | 720664 | 80793088 | 15893051149087 | 15893051116587 | 15893051429868 | 15893051431731 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 245 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 99584 | 0x7ff91540db80 | 0x7ff914a253c0 | 131072 | 686400 | 76867176 | 15893051470480 | 15893051429868 | 15893051712109 | 15893051714045 |
| 85 | 83 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 248 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 101312 | 0x7ff91540da00 | 0x7ff914a25400 | 131072 | 646172 | 72275152 | 15893051745704 | 15893051712109 | 15893052087790 | 15893052089776 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 251 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 102784 | 0x7ff91540d880 | 0x7ff914a25440 | 65536 | 648286 | 72537448 | 15893052121506 | 15893052087790 | 15893052452591 | 15893052454578 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 254 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 104256 | 0x7ff91540d700 | 0x7ff914a25480 | 131072 | 661964 | 74063032 | 15893052485917 | 15893052452591 | 15893052735472 | 15893052737252 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 257 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 106240 | 0x7ff917ab0580 | 0x7ff914a254c0 | 131072 | 657926 | 73626448 | 15893052768531 | 15893052735472 | 15893053052753 | 15893053054655 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 260 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 107712 | 0x7ff917ab0400 | 0x7ff914a25500 | 131072 | 652506 | 73160080 | 15893053094424 | 15893053052753 | 15893053333394 | 15893053335329 |
| 90 | 88 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 263 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 16 | 24 | 109440 | 0x7ff917ab0280 | 0x7ff914a25540 | 131072 | 714438 | 80104240 | 15893053367748 | 15893053333394 | 15893053699795 | 15893053701720 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 266 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 16 | 24 | 111168 | 0x7ff917ab0100 | 0x7ff914a25580 | 65536 | 686404 | 76964544 | 15893053733120 | 15893053699795 | 15893054067316 | 15893054069102 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 269 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 8 | 24 | 112896 | 0x7ff91540df80 | 0x7ff914a255c0 | 131072 | 706018 | 79078896 | 15893054101272 | 15893054067316 | 15893054352597 | 15893054354506 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 272 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 115136 | 0x7ff91540de00 | 0x7ff914a25600 | 131072 | 703996 | 78793744 | 15893054386645 | 15893054352597 | 15893054675317 | 15893054677149 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 275 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 116608 | 0x7ff91540dc80 | 0x7ff914a25640 | 131072 | 689618 | 77239880 | 15893054716198 | 15893054675317 | 15893054958998 | 15893054960822 |
| 95 | 93 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 278 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 16 | 24 | 118336 | 0x7ff91540db00 | 0x7ff914a25680 | 131072 | 697690 | 78211112 | 15893054991612 | 15893054958998 | 15893055334519 | 15893055336344 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 281 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 16 | 24 | 120064 | 0x7ff91540d980 | 0x7ff914a256c0 | 65536 | 649286 | 72572704 | 15893055367843 | 15893055334519 | 15893055702200 | 15893055704226 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 284 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 121792 | 0x7ff91540d800 | 0x7ff914a25700 | 131072 | 685756 | 76891920 | 15893055735785 | 15893055702200 | 15893055985561 | 15893055987429 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 287 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 124032 | 0x7ff91540d680 | 0x7ff914a25740 | 131072 | 684404 | 76636360 | 15893056019019 | 15893055985561 | 15893056314682 | 15893056316642 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 290 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 125504 | 0x7ff917ab0500 | 0x7ff914a25780 | 131072 | 690874 | 77411144 | 15893056356501 | 15893056314682 | 15893056595483 | 15893056597356 |
| 100 | 98 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 293 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 127488 | 0x7ff917ab0380 | 0x7ff914a257c0 | 131072 | 698088 | 78265184 | 15893056628755 | 15893056595483 | 15893056961084 | 15893056962988 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 296 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 129216 | 0x7ff917ab0200 | 0x7ff914a25800 | 65536 | 651094 | 72912840 | 15893056995347 | 15893056961084 | 15893057330045 | 15893057332109 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 299 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 130944 | 0x7ff917ab0080 | 0x7ff914a25840 | 131072 | 654566 | 73368512 | 15893057363439 | 15893057330045 | 15893057614366 | 15893057616313 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 302 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 133440 | 0x7ff91540df00 | 0x7ff914a25880 | 131072 | 667206 | 74823552 | 15893057648182 | 15893057614366 | 15893057954527 | 15893057956405 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 305 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 134912 | 0x7ff91540dd80 | 0x7ff914a258c0 | 131072 | 1016346 | 114037392 | 15893057994775 | 15893057954527 | 15893058249568 | 15893058251879 |
| 105 | 103 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 308 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 136896 | 0x7ff91540dc00 | 0x7ff914a25900 | 131072 | 652884 | 73245088 | 15893058283708 | 15893058249568 | 15893058617569 | 15893058619421 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 311 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 138880 | 0x7ff91540da80 | 0x7ff914a25940 | 65536 | 650092 | 72789232 | 15893058651660 | 15893058617569 | 15893058985410 | 15893058987512 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 314 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 140864 | 0x7ff91540d900 | 0x7ff914a25980 | 131072 | 689452 | 77176896 | 15893059018162 | 15893058985410 | 15893059277411 | 15893059279316 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 317 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 143616 | 0x7ff91540d780 | 0x7ff914a259c0 | 131072 | 691186 | 77433536 | 15893059311275 | 15893059277411 | 15893059631172 | 15893059633008 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 320 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 145344 | 0x7ff91540d600 | 0x7ff914a25a00 | 131072 | 1022538 | 114721632 | 15893059675617 | 15893059631172 | 15893059917412 | 15893059919372 |
| 110 | 108 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 323 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 147584 | 0x7ff917ab0480 | 0x7ff914a25a40 | 131072 | 691024 | 77448728 | 15893059950981 | 15893059917412 | 15893060282693 | 15893060284603 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 326 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 149568 | 0x7ff917ab0300 | 0x7ff914a25a80 | 65536 | 651870 | 73022464 | 15893060317113 | 15893060282693 | 15893060650534 | 15893060652415 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 329 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 151552 | 0x7ff917ab0180 | 0x7ff914a25ac0 | 131072 | 682954 | 76497640 | 15893060683825 | 15893060650534 | 15893060949415 | 15893060951329 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 332 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 154304 | 0x7ff917ab0000 | 0x7ff914a25b00 | 131072 | 661514 | 74006672 | 15893060983238 | 15893060949415 | 15893061321576 | 15893061323540 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 335 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 156288 | 0x7ff91540de80 | 0x7ff914a25b40 | 131072 | 956280 | 107102648 | 15893061362889 | 15893061321576 | 15893061612777 | 15893061614654 |
| 115 | 113 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 338 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 158784 | 0x7ff91540dd00 | 0x7ff914a25b80 | 131072 | 693718 | 77697552 | 15893061646993 | 15893061612777 | 15893061979818 | 15893061981786 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 341 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 161024 | 0x7ff91540db80 | 0x7ff914a25bc0 | 65536 | 652436 | 73156256 | 15893062012805 | 15893061979818 | 15893062359819 | 15893062361907 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 344 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 163264 | 0x7ff91540da00 | 0x7ff914a25c00 | 131072 | 661620 | 74134792 | 15893062393896 | 15893062359819 | 15893062671980 | 15893062674130 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 347 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 166528 | 0x7ff91540d880 | 0x7ff914a25c40 | 131072 | 655730 | 73537296 | 15893062706099 | 15893062671980 | 15893063068141 | 15893063113990 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 350 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 168512 | 0x7ff91540d700 | 0x7ff914a25c80 | 131072 | 1019348 | 113995832 | 15893063135110 | 15893063068141 | 15893063399662 | 15893063401604 |
| 120 | 118 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 353 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 171264 | 0x7ff917ab0580 | 0x7ff914a25cc0 | 131072 | 653390 | 73247688 | 15893063434173 | 15893063399662 | 15893063769583 | 15893063771456 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 356 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 173760 | 0x7ff917ab0400 | 0x7ff914a25d00 | 65536 | 647938 | 72598864 | 15893063803595 | 15893063769583 | 15893064139824 | 15893064141817 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 359 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 176256 | 0x7ff917ab0280 | 0x7ff914a25d40 | 131072 | 652938 | 73182704 | 15893064174107 | 15893064139824 | 15893064464785 | 15893064466700 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 362 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 179776 | 0x7ff917ab0100 | 0x7ff914a25d80 | 131072 | 653104 | 73159760 | 15893064498019 | 15893064464785 | 15893064881426 | 15893064926940 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 365 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 182272 | 0x7ff91540df80 | 0x7ff914a25dc0 | 131072 | 1036162 | 116153256 | 15893064947009 | 15893064881426 | 15893065228627 | 15893065230683 |
| 125 | 123 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 368 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 185536 | 0x7ff91540de00 | 0x7ff914a25e00 | 131072 | 684032 | 76633536 | 15893065261432 | 15893065228627 | 15893065604468 | 15893065607995 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 371 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 188544 | 0x7ff91540dc80 | 0x7ff914a25e40 | 65536 | 646432 | 72497704 | 15893065638134 | 15893065604468 | 15893065986870 | 15893065988966 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 374 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 191552 | 0x7ff91540db00 | 0x7ff914a25e80 | 131072 | 644738 | 72140432 | 15893066020015 | 15893065986870 | 15893066354071 | 15893066356098 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 377 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 195840 | 0x7ff91540d980 | 0x7ff914a25ec0 | 131072 | 648644 | 72645968 | 15893066388167 | 15893066354071 | 15893066828792 | 15893066874476 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 380 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 198592 | 0x7ff91540d800 | 0x7ff914a25f00 | 131072 | 1023214 | 114530432 | 15893066894006 | 15893066828792 | 15893067203353 | 15893067205289 |
| 130 | 128 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 383 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 202368 | 0x7ff91540d680 | 0x7ff914a25f40 | 131072 | 959884 | 107577184 | 15893067238288 | 15893067203353 | 15893067596954 | 15893067642089 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 386 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 205888 | 0x7ff917ab0500 | 0x7ff914a25f80 | 65536 | 645856 | 72353848 | 15893067653819 | 15893067596954 | 15893068026715 | 15893068072490 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 389 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 209408 | 0x7ff917ab0380 | 0x7ff914a25fc0 | 131072 | 652430 | 73128968 | 15893068083670 | 15893068026715 | 15893068433276 | 15893068435112 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 392 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 214464 | 0x7ff917ab0200 | 0x7ff914a26000 | 131072 | 651944 | 73033056 | 15893068467041 | 15893068433276 | 15893068954398 | 15893068996689 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 395 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 217728 | 0x7ff917ab0080 | 0x7ff914a26040 | 131072 | 1030582 | 115491624 | 15893069015969 | 15893068954398 | 15893069337119 | 15893069339062 |
| 135 | 133 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 398 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 222016 | 0x7ff91540df00 | 0x7ff914a26080 | 131072 | 1054922 | 118205280 | 15893069370601 | 15893069337119 | 15893069755040 | 15893069774072 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 401 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 226048 | 0x7ff91540dd80 | 0x7ff914a260c0 | 65536 | 653754 | 73242624 | 15893069787982 | 15893069755040 | 15893070177921 | 15893070223992 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 404 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 230080 | 0x7ff91540dc00 | 0x7ff914a26100 | 131072 | 652898 | 73091304 | 15893070235792 | 15893070177921 | 15893070613283 | 15893070656922 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 407 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 235904 | 0x7ff91540da80 | 0x7ff914a26140 | 131072 | 685532 | 76714528 | 15893070669422 | 15893070613283 | 15893071222244 | 15893071242049 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 410 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 239424 | 0x7ff91540d900 | 0x7ff914a26180 | 131072 | 1024174 | 114931744 | 15893071262979 | 15893071222244 | 15893071601925 | 15893071603791 |
| 140 | 138 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 413 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 244224 | 0x7ff91540d780 | 0x7ff914a261c0 | 131072 | 960916 | 107717632 | 15893071634481 | 15893071601925 | 15893072043047 | 15893072085041 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 416 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 248768 | 0x7ff91540d600 | 0x7ff914a26200 | 65536 | 688900 | 77271256 | 15893072097470 | 15893072043047 | 15893072505928 | 15893072547450 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 419 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 253312 | 0x7ff917ab0480 | 0x7ff914a26240 | 131072 | 646052 | 72296624 | 15893072559160 | 15893072505928 | 15893072965289 | 15893073007550 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 422 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 8 | 24 | 255552 | 0x7ff917ab0300 | 0x7ff914a26280 | 131072 | 1034830 | 115916472 | 15893073018910 | 15893072965289 | 15893073634891 | 15893073678015 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 425 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 259840 | 0x7ff917ab0180 | 0x7ff914a262c0 | 131072 | 1018504 | 114170664 | 15893073697495 | 15893073634891 | 15893074079052 | 15893074149054 |
| 145 | 143 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 428 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 265664 | 0x7ff917ab0000 | 0x7ff914a26300 | 131072 | 1021588 | 114548056 | 15893074161444 | 15893074079052 | 15893074716654 | 15893074795960 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 431 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 271232 | 0x7ff91540de80 | 0x7ff914a26340 | 65536 | 651574 | 72899416 | 15893074807710 | 15893074716654 | 15893075348336 | 15893075425606 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 434 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 8 | 24 | 273216 | 0x7ff91540dd00 | 0x7ff914a26380 | 131072 | 974576 | 109133840 | 15893075437146 | 15893075348336 | 15893075975698 | 15893076051232 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 437 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 8 | 24 | 275712 | 0x7ff91540db80 | 0x7ff914a263c0 | 131072 | 1024274 | 114801608 | 15893076063522 | 15893075975698 | 15893076861780 | 15893076937912 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 440 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 280768 | 0x7ff91540da00 | 0x7ff914a26400 | 131072 | 958506 | 107279616 | 15893076957632 | 15893076861780 | 15893077467062 | 15893077544029 |
| 150 | 148 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 443 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 287616 | 0x7ff91540d880 | 0x7ff914a26440 | 131072 | 1022880 | 114487184 | 15893077556398 | 15893077467062 | 15893078149944 | 15893078228023 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 446 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 294208 | 0x7ff91540d700 | 0x7ff914a26480 | 65536 | 649082 | 72646016 | 15893078240273 | 15893078149944 | 15893078836186 | 15893078915448 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 449 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 8 | 24 | 296960 | 0x7ff917ab0580 | 0x7ff914a264c0 | 131072 | 970228 | 108633712 | 15893078927428 | 15893078836186 | 15893079517308 | 15893079564913 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 452 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 8 | 24 | 299968 | 0x7ff917ab0400 | 0x7ff914a26500 | 131072 | 1027892 | 114773792 | 15893079576453 | 15893079517308 | 15893080430270 | 15893080476223 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 455 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 8 | 24 | 302720 | 0x7ff917ab0280 | 0x7ff914a26540 | 131072 | 1028852 | 115270440 | 15893080495873 | 15893080430270 | 15893081126752 | 15893081200037 |
| 155 | 153 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 458 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 305472 | 0x7ff917ab0100 | 0x7ff914a26580 | 131072 | 1030780 | 115454976 | 15893081212447 | 15893081126752 | 15893081919555 | 15893081968020 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 461 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 308224 | 0x7ff91540df80 | 0x7ff914a265c0 | 65536 | 650536 | 72852416 | 15893081979919 | 15893081919689 | 15893082674571 | 15893082795051 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 464 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 8 | 24 | 310976 | 0x7ff91540de00 | 0x7ff914a26600 | 131072 | 1023702 | 114651424 | 15893082808061 | 15893082674571 | 15893083510573 | 15893083608813 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 467 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 8 | 24 | 313216 | 0x7ff91540dc80 | 0x7ff914a26640 | 131072 | 1019584 | 114157160 | 15893083621963 | 15893083510573 | 15893084741297 | 15893084830936 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 470 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 8 | 24 | 315968 | 0x7ff91540db00 | 0x7ff914a26680 | 131072 | 1026110 | 114824744 | 15893084851915 | 15893084741297 | 15893085917780 | 15893086007489 |
| 160 | 158 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 473 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 318720 | 0x7ff91540d980 | 0x7ff914a266c0 | 131072 | 1015286 | 113815048 | 15893086019759 | 15893085917780 | 15893087136984 | 15893087228822 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 476 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 321472 | 0x7ff91540d800 | 0x7ff914a26700 | 65536 | 651960 | 72879632 | 15893087241232 | 15893087136984 | 15893088344028 | 15893088434556 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 479 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 8 | 24 | 324224 | 0x7ff91540d680 | 0x7ff914a26740 | 131072 | 1051272 | 117543392 | 15893088447005 | 15893088344028 | 15893089528991 | 15893089620219 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 482 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 8 | 24 | 326464 | 0x7ff917ab0500 | 0x7ff914a26780 | 131072 | 1025178 | 114689800 | 15893089632879 | 15893089528991 | 15893091546598 | 15893091647164 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 485 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 8 | 24 | 329216 | 0x7ff917ab0380 | 0x7ff914a267c0 | 131072 | 1024354 | 115060696 | 15893091667244 | 15893091546598 | 15893093551404 | 15893093644050 |
| 165 | 163 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 488 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 331968 | 0x7ff917ab0200 | 0x7ff914a26800 | 131072 | 1006802 | 112784936 | 15893093656229 | 15893093551404 | 15893095609490 | 15893095706753 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 491 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 12 | 24 | 334720 | 0x7ff917ab0080 | 0x7ff914a26840 | 65536 | 653216 | 73297752 | 15893095718833 | 15893095609490 | 15893097669337 | 15893097762908 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 494 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 8 | 24 | 337472 | 0x7ff91540df00 | 0x7ff914a26880 | 131072 | 1023250 | 114517368 | 15893097775727 | 15893097669337 | 15893099687583 | 15893099791182 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 497 | 136822 | 136822 | 4194304 | 256 | 0 | 0 | 8 | 24 | 0 | 0x7ff91540dd80 | 0x7ff914a268c0 | 131072 | 1018410 | 114315416 | 15893099803802 | 15893099687583 | 15893103396074 | 15893103487300 |