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 | 795609 | 795614 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7f5121e04180 | 12073948226724206 | 12073948226771836 | 12073948227096953 | 12073948227202545 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 795609 | 795614 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7f5121e35100 | 12073948241789042 | 12073948241890986 | 12073948241898026 | 12073948241903815 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7f522da65900 | 0x7f5121e35140 | 12073948241945142 | 12073948241958506 | 12073948242089384 | 12073948242093578 |
| 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 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7f522da65800 | 0x7f5121e35180 | 12073948242194545 | 12073948242211783 | 12073948242458661 | 12073948242557450 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7f522da65700 | 0x7f5121e351c0 | 12073948242580944 | 12073948242593220 | 12073948242835778 | 12073948242932507 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7f522da65600 | 0x7f5121e35200 | 12073948242993049 | 12073948243005377 | 12073948243130976 | 12073948243134793 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7f522da65500 | 0x7f5121e35240 | 12073948243159629 | 12073948243171455 | 12073948243296574 | 12073948243299990 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7f522da65400 | 0x7f5121e35280 | 12073948243355573 | 12073948243369853 | 12073948243494012 | 12073948243497126 |
| 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 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7f522da65300 | 0x7f5121e352c0 | 12073948243525519 | 12073948243538492 | 12073948243783290 | 12073948243880519 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7f522da65a00 | 0x7f5121e35300 | 12073948243903101 | 12073948243914649 | 12073948244159607 | 12073948244261136 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7f522da65900 | 0x7f5121e35340 | 12073948244282876 | 12073948244294806 | 12073948244419764 | 12073948244423007 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7f522da65800 | 0x7f5121e35380 | 12073948244451490 | 12073948244463124 | 12073948244588723 | 12073948244592111 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7f522da65700 | 0x7f5121e353c0 | 12073948244629671 | 12073948244641363 | 12073948244766002 | 12073948244769170 |
| 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 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7f522da65600 | 0x7f5121e35400 | 12073948244796160 | 12073948244808561 | 12073948245053519 | 12073948245137765 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7f522da65500 | 0x7f5121e35440 | 12073948245161229 | 12073948245172718 | 12073948245420236 | 12073948245488837 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7f522da65400 | 0x7f5121e35480 | 12073948245510628 | 12073948245522155 | 12073948245646794 | 12073948245649927 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7f522da65300 | 0x7f5121e354c0 | 12073948245676666 | 12073948245688394 | 12073948245813193 | 12073948245816306 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7f522da65a00 | 0x7f5121e35500 | 12073948245854166 | 12073948245865832 | 12073948245990311 | 12073948245993525 |
| 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 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7f522da65900 | 0x7f5121e35540 | 12073948246027048 | 12073948246038951 | 12073948246285669 | 12073948246329860 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7f522da65800 | 0x7f5121e35580 | 12073948246352072 | 12073948246364228 | 12073948246607266 | 12073948246673679 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7f522da65700 | 0x7f5121e355c0 | 12073948246697584 | 12073948246710465 | 12073948246834944 | 12073948246838025 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7f522da65600 | 0x7f5121e35600 | 12073948246865676 | 12073948246879104 | 12073948247003582 | 12073948247009333 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7f522da65500 | 0x7f5121e35640 | 12073948247046252 | 12073948247060702 | 12073948247185181 | 12073948247188506 |
| 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 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7f522da65400 | 0x7f5121e35680 | 12073948247216939 | 12073948247230781 | 12073948247477338 | 12073948247519411 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7f522da65300 | 0x7f5121e356c0 | 12073948247542404 | 12073948247555898 | 12073948247799736 | 12073948247866466 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7f522da65a00 | 0x7f5121e35700 | 12073948247889018 | 12073948247902135 | 12073948248026614 | 12073948248030030 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7f522da65900 | 0x7f5121e35740 | 12073948248058954 | 12073948248071733 | 12073948248196532 | 12073948248199685 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7f522da65800 | 0x7f5121e35780 | 12073948248236424 | 12073948248249652 | 12073948248374291 | 12073948248377546 |
| 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 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7f522da65700 | 0x7f5121e357c0 | 12073948248404165 | 12073948248416690 | 12073948248665648 | 12073948248717448 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7f522da65600 | 0x7f5121e35800 | 12073948248739298 | 12073948248750608 | 12073948249033965 | 12073948249116529 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7f522da65500 | 0x7f5121e35840 | 12073948249138941 | 12073948249151564 | 12073948249276843 | 12073948249280644 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7f522da65400 | 0x7f5121e35880 | 12073948249307414 | 12073948249319243 | 12073948249445162 | 12073948249448526 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7f522da65300 | 0x7f5121e358c0 | 12073948249484633 | 12073948249498921 | 12073948249623240 | 12073948249626307 |
| 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 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7f522da65a00 | 0x7f5121e35900 | 12073948249653768 | 12073948249667560 | 12073948249951877 | 12073948250013055 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7f522da65900 | 0x7f5121e35940 | 12073948250034726 | 12073948250048836 | 12073948250293794 | 12073948250371712 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7f522da65800 | 0x7f5121e35980 | 12073948250393342 | 12073948250405313 | 12073948250530112 | 12073948250533633 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7f522da65700 | 0x7f5121e359c0 | 12073948250560432 | 12073948250571872 | 12073948250697311 | 12073948250700773 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7f522da65600 | 0x7f5121e35a00 | 12073948250736890 | 12073948250749950 | 12073948250874749 | 12073948250877772 |
| 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 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7f522da65500 | 0x7f5121e35a40 | 12073948250905063 | 12073948250916029 | 12073948251167067 | 12073948251221130 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7f522da65400 | 0x7f5121e35a80 | 12073948251244053 | 12073948251256666 | 12073948251500184 | 12073948251550903 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7f522da65300 | 0x7f5121e35ac0 | 12073948251576551 | 12073948251589783 | 12073948251715222 | 12073948251718344 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7f522da65a00 | 0x7f5121e35b00 | 12073948251746236 | 12073948251759062 | 12073948251884661 | 12073948251887939 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7f522da65900 | 0x7f5121e35b40 | 12073948251925710 | 12073948251939220 | 12073948252064499 | 12073948252067844 |
| 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 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7f522da65800 | 0x7f5121e35b80 | 12073948252095575 | 12073948252107219 | 12073948252358897 | 12073948252387307 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7f522da65700 | 0x7f5121e35bc0 | 12073948252409248 | 12073948252420656 | 12073948252666574 | 12073948252688577 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7f522da65600 | 0x7f5121e35c00 | 12073948252707643 | 12073948252719854 | 12073948252844173 | 12073948252847242 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7f522da65500 | 0x7f5121e35c40 | 12073948252874182 | 12073948252885612 | 12073948253013131 | 12073948253016146 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7f522da65400 | 0x7f5121e35c80 | 12073948253055649 | 12073948253067051 | 12073948253192010 | 12073948253195199 |
| 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 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7f522da65300 | 0x7f5121e35cc0 | 12073948253221888 | 12073948253236009 | 12073948253493927 | 12073948253518349 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7f522da65a00 | 0x7f5121e35d00 | 12073948253539970 | 12073948253552487 | 12073948253798084 | 12073948253822465 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7f522da65900 | 0x7f5121e35d40 | 12073948253846559 | 12073948253859684 | 12073948253984803 | 12073948253988072 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7f522da65800 | 0x7f5121e35d80 | 12073948254014742 | 12073948254025922 | 12073948254154561 | 12073948254157998 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7f522da65700 | 0x7f5121e35dc0 | 12073948254196189 | 12073948254210081 | 12073948254335040 | 12073948254338393 |
| 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 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7f522da65600 | 0x7f5121e35e00 | 12073948254364432 | 12073948254377759 | 12073948254642237 | 12073948254662926 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7f522da65500 | 0x7f5121e35e40 | 12073948254685909 | 12073948254699837 | 12073948254944315 | 12073948254968274 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7f522da65400 | 0x7f5121e35e80 | 12073948254991878 | 12073948255005114 | 12073948255130393 | 12073948255133661 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7f522da65300 | 0x7f5121e35ec0 | 12073948255160020 | 12073948255171193 | 12073948255298872 | 12073948255301914 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7f522da65a00 | 0x7f5121e35f00 | 12073948255338832 | 12073948255352471 | 12073948255477590 | 12073948255480666 |
| 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 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7f522da65900 | 0x7f5121e35f40 | 12073948255508498 | 12073948255521590 | 12073948255780788 | 12073948255805610 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7f522da65800 | 0x7f5121e35f80 | 12073948255826839 | 12073948255840147 | 12073948256085265 | 12073948256114484 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7f522da65700 | 0x7f5121e35fc0 | 12073948256137226 | 12073948256150224 | 12073948256275343 | 12073948256278399 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7f522da65600 | 0x7f5121e36000 | 12073948256305088 | 12073948256317583 | 12073948256454062 | 12073948256457021 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7f522da65500 | 0x7f5121e36040 | 12073948256494891 | 12073948256508141 | 12073948256632780 | 12073948256636013 |
| 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 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7f522da65400 | 0x7f5121e36080 | 12073948256662673 | 12073948256675340 | 12073948256928618 | 12073948256953533 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7f522da65300 | 0x7f5121e360c0 | 12073948256975394 | 12073948256989097 | 12073948257241895 | 12073948257268188 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7f522da65a00 | 0x7f5121e36100 | 12073948257291161 | 12073948257303975 | 12073948257428933 | 12073948257432193 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7f522da65900 | 0x7f5121e36140 | 12073948257458782 | 12073948257471653 | 12073948257614372 | 12073948257617828 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7f522da65800 | 0x7f5121e36180 | 12073948257653564 | 12073948257664611 | 12073948257790210 | 12073948257793224 |
| 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 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7f522da65700 | 0x7f5121e361c0 | 12073948257820184 | 12073948257833570 | 12073948258087168 | 12073948258111836 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7f522da65600 | 0x7f5121e36200 | 12073948258131983 | 12073948258144607 | 12073948258388285 | 12073948258415410 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7f522da65500 | 0x7f5121e36240 | 12073948258440166 | 12073948258452765 | 12073948258577884 | 12073948258580988 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7f522da65400 | 0x7f5121e36280 | 12073948258607227 | 12073948258619643 | 12073948258769562 | 12073948258772634 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7f522da65300 | 0x7f5121e362c0 | 12073948258828187 | 12073948258841561 | 12073948258966840 | 12073948258970131 |
| 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 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7f522da65a00 | 0x7f5121e36300 | 12073948258995849 | 12073948259012440 | 12073948259265398 | 12073948259293432 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7f522da65900 | 0x7f5121e36340 | 12073948259315042 | 12073948259328437 | 12073948259572755 | 12073948259599671 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7f522da65800 | 0x7f5121e36380 | 12073948259620469 | 12073948259633715 | 12073948259758834 | 12073948259762133 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7f522da65700 | 0x7f5121e363c0 | 12073948259788321 | 12073948259801553 | 12073948259958352 | 12073948259961393 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7f522da65600 | 0x7f5121e36400 | 12073948259998843 | 12073948260017871 | 12073948260142990 | 12073948260146026 |
| 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 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7f522da65500 | 0x7f5121e36440 | 12073948260173337 | 12073948260184910 | 12073948260443948 | 12073948260465169 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7f522da65400 | 0x7f5121e36480 | 12073948260486529 | 12073948260500427 | 12073948260750985 | 12073948260779073 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7f522da65300 | 0x7f5121e364c0 | 12073948260799040 | 12073948260812105 | 12073948260937703 | 12073948260941034 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7f522da65a00 | 0x7f5121e36500 | 12073948260967463 | 12073948260980263 | 12073948261145062 | 12073948261148569 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7f522da65900 | 0x7f5121e36540 | 12073948261186520 | 12073948261197701 | 12073948261322820 | 12073948261326109 |
| 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 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7f522da65800 | 0x7f5121e36580 | 12073948261352448 | 12073948261364580 | 12073948261621058 | 12073948261644831 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7f522da65700 | 0x7f5121e365c0 | 12073948261666121 | 12073948261679777 | 12073948261928895 | 12073948261951622 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7f522da65600 | 0x7f5121e36600 | 12073948261975055 | 12073948261986975 | 12073948262111613 | 12073948262114865 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7f522da65500 | 0x7f5121e36640 | 12073948262143759 | 12073948262155293 | 12073948262328252 | 12073948262331427 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7f522da65400 | 0x7f5121e36680 | 12073948262367915 | 12073948262382171 | 12073948262508090 | 12073948262511131 |
| 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 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7f522da65300 | 0x7f5121e366c0 | 12073948262537861 | 12073948262549850 | 12073948262804088 | 12073948262823692 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7f522da65a00 | 0x7f5121e36700 | 12073948262844311 | 12073948262855927 | 12073948263102165 | 12073948263129581 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7f522da65900 | 0x7f5121e36740 | 12073948263153084 | 12073948263165524 | 12073948263290963 | 12073948263294417 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7f522da65800 | 0x7f5121e36780 | 12073948263319985 | 12073948263330643 | 12073948263514161 | 12073948263517351 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7f522da65700 | 0x7f5121e367c0 | 12073948263554851 | 12073948263568401 | 12073948263694000 | 12073948263697105 |
| 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 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7f522da65600 | 0x7f5121e36800 | 12073948263724005 | 12073948263737040 | 12073948263999917 | 12073948264028431 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7f522da65500 | 0x7f5121e36840 | 12073948264049019 | 12073948264062157 | 12073948264308555 | 12073948264335412 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7f522da65400 | 0x7f5121e36880 | 12073948264358164 | 12073948264370794 | 12073948264496713 | 12073948264500068 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7f522da65300 | 0x7f5121e368c0 | 12073948264527008 | 12073948264538633 | 12073948264729831 | 12073948264756735 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7f522da65a00 | 0x7f5121e36900 | 12073948264786961 | 12073948264798311 | 12073948264924709 | 12073948264927913 |
| 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 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7f522da65900 | 0x7f5121e36940 | 12073948264954412 | 12073948264968069 | 12073948265250787 | 12073948265279867 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7f522da65800 | 0x7f5121e36980 | 12073948265301347 | 12073948265314626 | 12073948265567264 | 12073948265591526 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7f522da65700 | 0x7f5121e369c0 | 12073948265616743 | 12073948265630143 | 12073948265756382 | 12073948265759638 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7f522da65600 | 0x7f5121e36a00 | 12073948265786158 | 12073948265797502 | 12073948266007260 | 12073948266036553 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7f522da65500 | 0x7f5121e36a40 | 12073948266067801 | 12073948266080540 | 12073948266206778 | 12073948266210045 |
| 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 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7f522da65400 | 0x7f5121e36a80 | 12073948266237046 | 12073948266250138 | 12073948266556696 | 12073948266581295 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7f522da65300 | 0x7f5121e36ac0 | 12073948266603807 | 12073948266616375 | 12073948266864373 | 12073948266891382 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7f522da65a00 | 0x7f5121e36b00 | 12073948266912761 | 12073948266926612 | 12073948267054291 | 12073948267057791 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7f522da65900 | 0x7f5121e36b40 | 12073948267085222 | 12073948267097811 | 12073948267324689 | 12073948267354252 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7f522da65800 | 0x7f5121e36b80 | 12073948267386221 | 12073948267397488 | 12073948267524687 | 12073948267527854 |
| 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 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7f522da65700 | 0x7f5121e36bc0 | 12073948267554404 | 12073948267566127 | 12073948267894924 | 12073948267918571 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7f522da65600 | 0x7f5121e36c00 | 12073948267941253 | 12073948267954284 | 12073948268201641 | 12073948268230039 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7f522da65500 | 0x7f5121e36c40 | 12073948268251088 | 12073948268264361 | 12073948268393000 | 12073948268396228 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7f522da65400 | 0x7f5121e36c80 | 12073948268422747 | 12073948268435399 | 12073948268678757 | 12073948268702016 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7f522da65300 | 0x7f5121e36cc0 | 12073948268733405 | 12073948268747397 | 12073948268876356 | 12073948268879596 |
| 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 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7f522da65a00 | 0x7f5121e36d00 | 12073948268905945 | 12073948268918915 | 12073948269293792 | 12073948269325154 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7f522da65900 | 0x7f5121e36d40 | 12073948269346755 | 12073948269360352 | 12073948269613629 | 12073948269636924 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7f522da65800 | 0x7f5121e36d80 | 12073948269660818 | 12073948269673949 | 12073948269803708 | 12073948269807020 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7f522da65700 | 0x7f5121e36dc0 | 12073948269833850 | 12073948269846747 | 12073948270124345 | 12073948270149206 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7f522da65600 | 0x7f5121e36e00 | 12073948270181466 | 12073948270194744 | 12073948270329303 | 12073948270332687 |
| 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 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7f522da65500 | 0x7f5121e36e40 | 12073948270359266 | 12073948270372823 | 12073948270796339 | 12073948270819401 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7f522da65400 | 0x7f5121e36e80 | 12073948270840701 | 12073948270853619 | 12073948271118737 | 12073948271147551 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7f522da65300 | 0x7f5121e36ec0 | 12073948271169071 | 12073948271180656 | 12073948271315215 | 12073948271318769 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7f522da65a00 | 0x7f5121e36f00 | 12073948271346200 | 12073948271359215 | 12073948271674092 | 12073948271697173 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7f522da65900 | 0x7f5121e36f40 | 12073948271730114 | 12073948271743851 | 12073948271895370 | 12073948271898667 |
| 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 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7f522da65800 | 0x7f5121e36f80 | 12073948271925427 | 12073948271937290 | 12073948272454565 | 12073948272479266 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7f522da65700 | 0x7f5121e36fc0 | 12073948272501036 | 12073948272513605 | 12073948272813442 | 12073948272836390 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7f522da65600 | 0x7f5121e37000 | 12073948272857860 | 12073948272869442 | 12073948273023840 | 12073948273027174 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7f522da65500 | 0x7f5121e37040 | 12073948273055306 | 12073948273066880 | 12073948273451357 | 12073948273476449 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7f522da65400 | 0x7f5121e37080 | 12073948273511785 | 12073948273523036 | 12073948273698555 | 12073948273701848 |
| 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 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7f522da65300 | 0x7f5121e370c0 | 12073948273728798 | 12073948273742714 | 12073948274353429 | 12073948274381551 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7f522da65a00 | 0x7f5121e37100 | 12073948274404053 | 12073948274416788 | 12073948274743346 | 12073948274766677 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7f522da65900 | 0x7f5121e37140 | 12073948274792725 | 12073948274805425 | 12073948274983024 | 12073948274986445 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7f522da65800 | 0x7f5121e37180 | 12073948275019206 | 12073948275031023 | 12073948275486219 | 12073948275518484 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7f522da65700 | 0x7f5121e371c0 | 12073948275553840 | 12073948275566699 | 12073948275765737 | 12073948275792373 |
| 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 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7f522da65600 | 0x7f5121e37200 | 12073948275816378 | 12073948275829576 | 12073948276533090 | 12073948276567383 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7f522da65500 | 0x7f5121e37240 | 12073948276592550 | 12073948276603490 | 12073948276975487 | 12073948277007511 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7f522da65400 | 0x7f5121e37280 | 12073948277031927 | 12073948277043806 | 12073948277245884 | 12073948277274648 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7f522da65300 | 0x7f5121e372c0 | 12073948277296929 | 12073948277307804 | 12073948277833879 | 12073948277860937 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7f522da65a00 | 0x7f5121e37300 | 12073948277894429 | 12073948277905879 | 12073948278129237 | 12073948278161706 |
| 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 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7f522da65900 | 0x7f5121e37340 | 12073948278184268 | 12073948278195636 | 12073948278996589 | 12073948279025622 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7f522da65800 | 0x7f5121e37380 | 12073948279046490 | 12073948279059469 | 12073948279479945 | 12073948279507056 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7f522da65700 | 0x7f5121e373c0 | 12073948279528717 | 12073948279541865 | 12073948279767623 | 12073948279794611 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7f522da65600 | 0x7f5121e37400 | 12073948279817924 | 12073948279830342 | 12073948280427617 | 12073948280461440 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7f522da65500 | 0x7f5121e37440 | 12073948280492658 | 12073948280506016 | 12073948280776254 | 12073948280803836 |
| 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 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7f522da65400 | 0x7f5121e37480 | 12073948280825877 | 12073948280838814 | 12073948281824405 | 12073948281853747 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7f522da65300 | 0x7f5121e374c0 | 12073948281874666 | 12073948281887285 | 12073948282402640 | 12073948282431441 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7f522da65a00 | 0x7f5121e37500 | 12073948282457850 | 12073948282469040 | 12073948282740077 | 12073948282767355 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7f522da65900 | 0x7f5121e37540 | 12073948282789486 | 12073948282801677 | 12073948283539431 | 12073948283570508 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7f522da65800 | 0x7f5121e37580 | 12073948283602087 | 12073948283614790 | 12073948283929987 | 12073948283958178 |
| 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 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7f522da65700 | 0x7f5121e375c0 | 12073948283979197 | 12073948283992387 | 12073948285166297 | 12073948285200627 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7f522da65600 | 0x7f5121e37600 | 12073948285223700 | 12073948285236216 | 12073948285845651 | 12073948285876123 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7f522da65500 | 0x7f5121e37640 | 12073948285900919 | 12073948285913810 | 12073948286233008 | 12073948286263783 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7f522da65400 | 0x7f5121e37680 | 12073948286287337 | 12073948286298767 | 12073948287176199 | 12073948287207166 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7f522da65300 | 0x7f5121e376c0 | 12073948287241079 | 12073948287252839 | 12073948287661315 | 12073948287690013 |
| 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 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7f522da65a00 | 0x7f5121e37700 | 12073948287714028 | 12073948287724995 | 12073948289276342 | 12073948289349728 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7f522da65900 | 0x7f5121e37740 | 12073948289371829 | 12073948289383176 | 12073948290178850 | 12073948290255160 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7f522da65800 | 0x7f5121e37780 | 12073948290275989 | 12073948290287648 | 12073948290701725 | 12073948290773273 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7f522da65700 | 0x7f5121e377c0 | 12073948290796006 | 12073948290809084 | 12073948291967156 | 12073948292042051 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7f522da65600 | 0x7f5121e37800 | 12073948292077006 | 12073948292089075 | 12073948292875149 | 12073948292945650 |
| 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 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7f522da65500 | 0x7f5121e37840 | 12073948292969635 | 12073948292982028 | 12073948296038165 | 12073948296114599 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7f522da65400 | 0x7f5121e37880 | 12073948296136270 | 12073948296149845 | 12073948297694313 | 12073948297767080 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7f522da65300 | 0x7f5121e378c0 | 12073948297791416 | 12073948297802472 | 12073948298590786 | 12073948298663166 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7f522da65a00 | 0x7f5121e37900 | 12073948298686178 | 12073948298697826 | 12073948300980208 | 12073948301053107 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7f522da65900 | 0x7f5121e37940 | 12073948301086058 | 12073948301097968 | 12073948302632996 | 12073948302706340 |
| 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 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7f522da65800 | 0x7f5121e37980 | 12073948302728230 | 12073948302740355 | 12073948308799830 | 12073948308872609 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7f522da65700 | 0x7f5121e379c0 | 12073948308894970 | 12073948308907509 | 12073948311953407 | 12073948312028664 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7f522da65600 | 0x7f5121e37a00 | 12073948312051627 | 12073948312064926 | 12073948313604274 | 12073948313676867 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 795609 | 795614 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7f522da65500 | 0x7f5121e37a40 | 12073948313699148 | 12073948313710194 | 12073948318237680 | 12073948318310248 |