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 | 770557 | 770562 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7f2efa604180 | 12073557258620671 | 12073557258668628 | 12073557258992145 | 12073557259092858 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 770557 | 770562 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7f2efa635100 | 12073557273471860 | 12073557273572174 | 12073557273578734 | 12073557273584469 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7f30061b6900 | 0x7f2efa635140 | 12073557273625886 | 12073557273638893 | 12073557273772012 | 12073557273775264 |
| 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 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7f30061b6800 | 0x7f2efa635180 | 12073557273815799 | 12073557273827851 | 12073557274074249 | 12073557274173203 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7f30061b6700 | 0x7f2efa6351c0 | 12073557274198150 | 12073557274210728 | 12073557274458726 | 12073557274550534 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7f30061b6600 | 0x7f2efa635200 | 12073557274574269 | 12073557274586725 | 12073557274712003 | 12073557274715391 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7f30061b6500 | 0x7f2efa635240 | 12073557274743243 | 12073557274755203 | 12073557274879842 | 12073557274882912 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7f30061b6400 | 0x7f2efa635280 | 12073557274938235 | 12073557274949601 | 12073557275074080 | 12073557275077363 |
| 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 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7f30061b6300 | 0x7f2efa6352c0 | 12073557275105416 | 12073557275117920 | 12073557275364318 | 12073557275455747 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7f30061b6a00 | 0x7f2efa635300 | 12073557275477878 | 12073557275490876 | 12073557275734074 | 12073557275825634 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7f30061b6900 | 0x7f2efa635340 | 12073557275847294 | 12073557275860793 | 12073557275985432 | 12073557275988507 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7f30061b6800 | 0x7f2efa635380 | 12073557276022219 | 12073557276034552 | 12073557276159830 | 12073557276162951 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7f30061b6700 | 0x7f2efa6353c0 | 12073557276200741 | 12073557276212630 | 12073557276337269 | 12073557276339940 |
| 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 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7f30061b6600 | 0x7f2efa635400 | 12073557276367231 | 12073557276378709 | 12073557276624626 | 12073557276690501 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7f30061b6500 | 0x7f2efa635440 | 12073557276712883 | 12073557276724945 | 12073557276968783 | 12073557277035522 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7f30061b6400 | 0x7f2efa635480 | 12073557277056722 | 12073557277068302 | 12073557277192941 | 12073557277196411 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7f30061b6300 | 0x7f2efa6354c0 | 12073557277222550 | 12073557277234381 | 12073557277359660 | 12073557277362640 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7f30061b6a00 | 0x7f2efa635500 | 12073557277400010 | 12073557277411499 | 12073557277535658 | 12073557277538577 |
| 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 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7f30061b6900 | 0x7f2efa635540 | 12073557277565888 | 12073557277578058 | 12073557277823016 | 12073557277886444 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7f30061b6800 | 0x7f2efa635580 | 12073557277908615 | 12073557277920455 | 12073557278163653 | 12073557278233759 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7f30061b6700 | 0x7f2efa6355c0 | 12073557278254327 | 12073557278266372 | 12073557278391010 | 12073557278393847 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7f30061b6600 | 0x7f2efa635600 | 12073557278420897 | 12073557278432450 | 12073557278557889 | 12073557278560827 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7f30061b6500 | 0x7f2efa635640 | 12073557278597505 | 12073557278610369 | 12073557278734207 | 12073557278737055 |
| 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 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7f30061b6400 | 0x7f2efa635680 | 12073557278763774 | 12073557278776607 | 12073557279022525 | 12073557279114566 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7f30061b6300 | 0x7f2efa6356c0 | 12073557279135776 | 12073557279147164 | 12073557279390362 | 12073557279481408 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7f30061b6a00 | 0x7f2efa635700 | 12073557279503138 | 12073557279514680 | 12073557279638999 | 12073557279642297 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7f30061b6900 | 0x7f2efa635740 | 12073557279669037 | 12073557279680439 | 12073557279806518 | 12073557279809438 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7f30061b6800 | 0x7f2efa635780 | 12073557279844913 | 12073557279856277 | 12073557279980596 | 12073557279983571 |
| 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 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7f30061b6700 | 0x7f2efa6357c0 | 12073557280015110 | 12073557280027636 | 12073557280275794 | 12073557280342087 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7f30061b6600 | 0x7f2efa635800 | 12073557280367545 | 12073557280378673 | 12073557280624590 | 12073557280697037 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7f30061b6500 | 0x7f2efa635840 | 12073557280722104 | 12073557280733709 | 12073557280858508 | 12073557280861954 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7f30061b6400 | 0x7f2efa635880 | 12073557280888022 | 12073557280899148 | 12073557281024587 | 12073557281027862 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7f30061b6300 | 0x7f2efa6358c0 | 12073557281066694 | 12073557281079466 | 12073557281204265 | 12073557281207125 |
| 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 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7f30061b6a00 | 0x7f2efa635900 | 12073557281233243 | 12073557281244745 | 12073557281496903 | 12073557281544342 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7f30061b6900 | 0x7f2efa635940 | 12073557281565090 | 12073557281585062 | 12073557281828580 | 12073557281875547 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7f30061b6800 | 0x7f2efa635980 | 12073557281897909 | 12073557281909219 | 12073557282033858 | 12073557282037438 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7f30061b6700 | 0x7f2efa6359c0 | 12073557282063727 | 12073557282075297 | 12073557282201376 | 12073557282204629 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7f30061b6600 | 0x7f2efa635a00 | 12073557282240235 | 12073557282254976 | 12073557282379775 | 12073557282382710 |
| 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 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7f30061b6500 | 0x7f2efa635a40 | 12073557282410050 | 12073557282422654 | 12073557282670012 | 12073557282690131 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7f30061b6400 | 0x7f2efa635a80 | 12073557282712703 | 12073557282725532 | 12073557282969049 | 12073557283019834 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7f30061b6300 | 0x7f2efa635ac0 | 12073557283043738 | 12073557283058169 | 12073557283183288 | 12073557283186293 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7f30061b6a00 | 0x7f2efa635b00 | 12073557283212452 | 12073557283223927 | 12073557283349206 | 12073557283352291 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7f30061b6900 | 0x7f2efa635b40 | 12073557283393057 | 12073557283406646 | 12073557283532084 | 12073557283534981 |
| 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 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7f30061b6800 | 0x7f2efa635b80 | 12073557283562422 | 12073557283575124 | 12073557283833522 | 12073557283856458 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7f30061b6700 | 0x7f2efa635bc0 | 12073557283878539 | 12073557283891281 | 12073557284137519 | 12073557284185840 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7f30061b6600 | 0x7f2efa635c00 | 12073557284206198 | 12073557284218798 | 12073557284343117 | 12073557284346028 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7f30061b6500 | 0x7f2efa635c40 | 12073557284372868 | 12073557284385837 | 12073557284513196 | 12073557284516425 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7f30061b6400 | 0x7f2efa635c80 | 12073557284555668 | 12073557284568075 | 12073557284693674 | 12073557284696790 |
| 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 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7f30061b6300 | 0x7f2efa635cc0 | 12073557284723149 | 12073557284736554 | 12073557284987911 | 12073557285014250 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7f30061b6a00 | 0x7f2efa635d00 | 12073557285035980 | 12073557285051271 | 12073557285301029 | 12073557285325208 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7f30061b6900 | 0x7f2efa635d40 | 12073557285346678 | 12073557285359268 | 12073557285484227 | 12073557285487229 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7f30061b6800 | 0x7f2efa635d80 | 12073557285513608 | 12073557285526307 | 12073557285655425 | 12073557285658477 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7f30061b6700 | 0x7f2efa635dc0 | 12073557285697129 | 12073557285709505 | 12073557285834784 | 12073557285837710 |
| 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 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7f30061b6600 | 0x7f2efa635e00 | 12073557285863438 | 12073557285876383 | 12073557286136861 | 12073557286167032 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7f30061b6500 | 0x7f2efa635e40 | 12073557286189153 | 12073557286201980 | 12073557286448058 | 12073557286474033 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7f30061b6400 | 0x7f2efa635e80 | 12073557286498258 | 12073557286510458 | 12073557286635897 | 12073557286639090 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7f30061b6300 | 0x7f2efa635ec0 | 12073557286664928 | 12073557286677656 | 12073557286808375 | 12073557286811590 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7f30061b6a00 | 0x7f2efa635f00 | 12073557286850312 | 12073557286861975 | 12073557286986773 | 12073557286989641 |
| 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 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7f30061b6900 | 0x7f2efa635f40 | 12073557287023103 | 12073557287033973 | 12073557287292051 | 12073557287312732 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7f30061b6800 | 0x7f2efa635f80 | 12073557287333440 | 12073557287345330 | 12073557287589328 | 12073557287613490 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7f30061b6700 | 0x7f2efa635fc0 | 12073557287634980 | 12073557287646448 | 12073557287771406 | 12073557287774530 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7f30061b6600 | 0x7f2efa636000 | 12073557287801269 | 12073557287814126 | 12073557287951085 | 12073557287954164 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7f30061b6500 | 0x7f2efa636040 | 12073557287994378 | 12073557288006124 | 12073557288130923 | 12073557288133968 |
| 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 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7f30061b6400 | 0x7f2efa636080 | 12073557288161128 | 12073557288172203 | 12073557288425001 | 12073557288445707 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7f30061b6300 | 0x7f2efa6360c0 | 12073557288467227 | 12073557288479720 | 12073557288725798 | 12073557288750143 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7f30061b6a00 | 0x7f2efa636100 | 12073557288771943 | 12073557288785157 | 12073557288910276 | 12073557288913376 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7f30061b6900 | 0x7f2efa636140 | 12073557288939765 | 12073557288951396 | 12073557289092835 | 12073557289095996 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7f30061b6800 | 0x7f2efa636180 | 12073557289134768 | 12073557289145794 | 12073557289270753 | 12073557289273746 |
| 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 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7f30061b6700 | 0x7f2efa6361c0 | 12073557289301527 | 12073557289315393 | 12073557289574110 | 12073557289594853 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7f30061b6600 | 0x7f2efa636200 | 12073557289621232 | 12073557289632510 | 12073557289876188 | 12073557289896523 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7f30061b6500 | 0x7f2efa636240 | 12073557289921530 | 12073557289934587 | 12073557290059866 | 12073557290062862 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7f30061b6400 | 0x7f2efa636280 | 12073557290091265 | 12073557290102745 | 12073557290251704 | 12073557290255009 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7f30061b6300 | 0x7f2efa6362c0 | 12073557290311134 | 12073557290326423 | 12073557290451382 | 12073557290454710 |
| 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 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7f30061b6a00 | 0x7f2efa636300 | 12073557290480779 | 12073557290493622 | 12073557290747060 | 12073557290771419 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7f30061b6900 | 0x7f2efa636340 | 12073557290793009 | 12073557290806419 | 12073557291052337 | 12073557291073290 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7f30061b6800 | 0x7f2efa636380 | 12073557291094299 | 12073557291106896 | 12073557291233455 | 12073557291236503 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7f30061b6700 | 0x7f2efa6363c0 | 12073557291263524 | 12073557291276975 | 12073557291433294 | 12073557291436415 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7f30061b6600 | 0x7f2efa636400 | 12073557291476549 | 12073557291488973 | 12073557291614092 | 12073557291617141 |
| 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 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7f30061b6500 | 0x7f2efa636440 | 12073557291645523 | 12073557291658412 | 12073557291912649 | 12073557291937025 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7f30061b6400 | 0x7f2efa636480 | 12073557291958846 | 12073557291971529 | 12073557292217127 | 12073557292242212 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7f30061b6300 | 0x7f2efa6364c0 | 12073557292263051 | 12073557292275686 | 12073557292401765 | 12073557292404804 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7f30061b6a00 | 0x7f2efa636500 | 12073557292431815 | 12073557292443845 | 12073557292608803 | 12073557292611799 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7f30061b6900 | 0x7f2efa636540 | 12073557292649800 | 12073557292661763 | 12073557292787841 | 12073557292790842 |
| 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 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7f30061b6800 | 0x7f2efa636580 | 12073557292816900 | 12073557292828641 | 12073557293085279 | 12073557293117108 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7f30061b6700 | 0x7f2efa6365c0 | 12073557293138638 | 12073557293151838 | 12073557293401436 | 12073557293425431 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7f30061b6600 | 0x7f2efa636600 | 12073557293448053 | 12073557293461275 | 12073557293587834 | 12073557293590899 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7f30061b6500 | 0x7f2efa636640 | 12073557293616917 | 12073557293629754 | 12073557293840632 | 12073557293860860 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7f30061b6400 | 0x7f2efa636680 | 12073557293893912 | 12073557293907831 | 12073557294033590 | 12073557294037469 |
| 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 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7f30061b6300 | 0x7f2efa6366c0 | 12073557294064869 | 12073557294077910 | 12073557294329908 | 12073557294353245 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7f30061b6a00 | 0x7f2efa636700 | 12073557294374014 | 12073557294386227 | 12073557294632465 | 12073557294653834 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7f30061b6900 | 0x7f2efa636740 | 12073557294676145 | 12073557294689104 | 12073557294815503 | 12073557294818680 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7f30061b6800 | 0x7f2efa636780 | 12073557294845240 | 12073557294857903 | 12073557295040621 | 12073557295044039 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7f30061b6700 | 0x7f2efa6367c0 | 12073557295084384 | 12073557295096141 | 12073557295221740 | 12073557295224955 |
| 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 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7f30061b6600 | 0x7f2efa636800 | 12073557295252356 | 12073557295264939 | 12073557295528137 | 12073557295548907 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7f30061b6500 | 0x7f2efa636840 | 12073557295571850 | 12073557295584616 | 12073557295831974 | 12073557295856529 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7f30061b6400 | 0x7f2efa636880 | 12073557295878290 | 12073557295890694 | 12073557296016132 | 12073557296019823 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7f30061b6300 | 0x7f2efa6368c0 | 12073557296047083 | 12073557296059652 | 12073557296251010 | 12073557296255921 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7f30061b6a00 | 0x7f2efa636900 | 12073557296292630 | 12073557296305410 | 12073557296431809 | 12073557296434964 |
| 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 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7f30061b6900 | 0x7f2efa636940 | 12073557296461023 | 12073557296473728 | 12073557296787326 | 12073557296808388 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7f30061b6800 | 0x7f2efa636980 | 12073557296832313 | 12073557296844925 | 12073557297094203 | 12073557297122231 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7f30061b6700 | 0x7f2efa6369c0 | 12073557297146587 | 12073557297160282 | 12073557297286201 | 12073557297289482 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7f30061b6600 | 0x7f2efa636a00 | 12073557297316262 | 12073557297327961 | 12073557297536279 | 12073557297560406 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7f30061b6500 | 0x7f2efa636a40 | 12073557297594038 | 12073557297607158 | 12073557297735317 | 12073557297738517 |
| 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 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7f30061b6400 | 0x7f2efa636a80 | 12073557297765557 | 12073557297778517 | 12073557298084914 | 12073557298110037 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7f30061b6300 | 0x7f2efa636ac0 | 12073557298132048 | 12073557298144753 | 12073557298390511 | 12073557298410916 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7f30061b6a00 | 0x7f2efa636b00 | 12073557298433037 | 12073557298446031 | 12073557298572270 | 12073557298575472 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7f30061b6900 | 0x7f2efa636b40 | 12073557298601911 | 12073557298614509 | 12073557298842027 | 12073557298865962 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7f30061b6800 | 0x7f2efa636b80 | 12073557298901067 | 12073557298914027 | 12073557299042025 | 12073557299045205 |
| 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 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7f30061b6700 | 0x7f2efa636bc0 | 12073557299072586 | 12073557299085865 | 12073557299414022 | 12073557299437965 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7f30061b6600 | 0x7f2efa636c00 | 12073557299460737 | 12073557299473061 | 12073557299727619 | 12073557299752018 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7f30061b6500 | 0x7f2efa636c40 | 12073557299773709 | 12073557299786499 | 12073557299914338 | 12073557299917616 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7f30061b6400 | 0x7f2efa636c80 | 12073557299943815 | 12073557299956737 | 12073557300201375 | 12073557300226089 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7f30061b6300 | 0x7f2efa636cc0 | 12073557300259532 | 12073557300272414 | 12073557300401373 | 12073557300404471 |
| 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 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7f30061b6a00 | 0x7f2efa636d00 | 12073557300430910 | 12073557300443933 | 12073557300845049 | 12073557300866039 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7f30061b6900 | 0x7f2efa636d40 | 12073557300889332 | 12073557300901689 | 12073557301153686 | 12073557301178960 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7f30061b6800 | 0x7f2efa636d80 | 12073557301202534 | 12073557301215446 | 12073557301345525 | 12073557301348746 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7f30061b6700 | 0x7f2efa636dc0 | 12073557301375966 | 12073557301388564 | 12073557301666802 | 12073557301690841 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7f30061b6600 | 0x7f2efa636e00 | 12073557301724183 | 12073557301736721 | 12073557301871920 | 12073557301875625 |
| 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 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7f30061b6500 | 0x7f2efa636e40 | 12073557301901924 | 12073557301915120 | 12073557302337676 | 12073557302359444 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7f30061b6400 | 0x7f2efa636e80 | 12073557302381585 | 12073557302393675 | 12073557302650953 | 12073557302675551 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7f30061b6300 | 0x7f2efa636ec0 | 12073557302697071 | 12073557302710152 | 12073557302845831 | 12073557302849044 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7f30061b6a00 | 0x7f2efa636f00 | 12073557302875573 | 12073557302888231 | 12073557303201508 | 12073557303231314 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7f30061b6900 | 0x7f2efa636f40 | 12073557303265929 | 12073557303278467 | 12073557303429506 | 12073557303432759 |
| 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 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7f30061b6800 | 0x7f2efa636f80 | 12073557303459017 | 12073557303472546 | 12073557303987901 | 12073557304011003 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7f30061b6700 | 0x7f2efa636fc0 | 12073557304033686 | 12073557304046141 | 12073557304345658 | 12073557304369940 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7f30061b6600 | 0x7f2efa637000 | 12073557304391961 | 12073557304404697 | 12073557304558776 | 12073557304561987 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7f30061b6500 | 0x7f2efa637040 | 12073557304588497 | 12073557304599896 | 12073557304984372 | 12073557305011182 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7f30061b6400 | 0x7f2efa637080 | 12073557305050134 | 12073557305061331 | 12073557305237330 | 12073557305240648 |
| 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 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7f30061b6300 | 0x7f2efa6370c0 | 12073557305267548 | 12073557305278769 | 12073557305888364 | 12073557305913529 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7f30061b6a00 | 0x7f2efa637100 | 12073557305934298 | 12073557305946443 | 12073557306275881 | 12073557306302151 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7f30061b6900 | 0x7f2efa637140 | 12073557306324372 | 12073557306337160 | 12073557306514598 | 12073557306517792 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7f30061b6800 | 0x7f2efa637180 | 12073557306544792 | 12073557306557318 | 12073557307011874 | 12073557307036776 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7f30061b6700 | 0x7f2efa6371c0 | 12073557307070930 | 12073557307083553 | 12073557307283071 | 12073557307307339 |
| 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 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7f30061b6600 | 0x7f2efa637200 | 12073557307327557 | 12073557307338911 | 12073557308041145 | 12073557308065969 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7f30061b6500 | 0x7f2efa637240 | 12073557308088591 | 12073557308100024 | 12073557308472021 | 12073557308496870 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7f30061b6400 | 0x7f2efa637280 | 12073557308519031 | 12073557308531700 | 12073557308733618 | 12073557308757494 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7f30061b6300 | 0x7f2efa6372c0 | 12073557308779144 | 12073557308791698 | 12073557309317133 | 12073557309341750 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7f30061b6a00 | 0x7f2efa637300 | 12073557309376975 | 12073557309390093 | 12073557309614571 | 12073557309638722 |
| 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 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7f30061b6900 | 0x7f2efa637340 | 12073557309661083 | 12073557309673450 | 12073557310471363 | 12073557310497908 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7f30061b6800 | 0x7f2efa637380 | 12073557310521372 | 12073557310534242 | 12073557310951679 | 12073557310975997 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7f30061b6700 | 0x7f2efa6373c0 | 12073557310996365 | 12073557311012958 | 12073557311238236 | 12073557311262519 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7f30061b6600 | 0x7f2efa637400 | 12073557311283979 | 12073557311296316 | 12073557311892790 | 12073557311917096 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7f30061b6500 | 0x7f2efa637440 | 12073557311949947 | 12073557311963030 | 12073557312232307 | 12073557312261786 |
| 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 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7f30061b6400 | 0x7f2efa637480 | 12073557312282535 | 12073557312293747 | 12073557313278058 | 12073557313303412 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7f30061b6300 | 0x7f2efa6374c0 | 12073557313324131 | 12073557313335337 | 12073557313850213 | 12073557313875145 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7f30061b6a00 | 0x7f2efa637500 | 12073557313899800 | 12073557313911492 | 12073557314183490 | 12073557314212301 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7f30061b6900 | 0x7f2efa637540 | 12073557314233150 | 12073557314244449 | 12073557314981722 | 12073557315007379 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7f30061b6800 | 0x7f2efa637580 | 12073557315040871 | 12073557315053402 | 12073557315368119 | 12073557315393216 |
| 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 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7f30061b6700 | 0x7f2efa6375c0 | 12073557315415888 | 12073557315427318 | 12073557316598188 | 12073557316623242 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7f30061b6600 | 0x7f2efa637600 | 12073557316645543 | 12073557316656747 | 12073557317267942 | 12073557317293678 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7f30061b6500 | 0x7f2efa637640 | 12073557317314977 | 12073557317327781 | 12073557317645219 | 12073557317670578 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7f30061b6400 | 0x7f2efa637680 | 12073557317692409 | 12073557317704898 | 12073557318582170 | 12073557318608261 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7f30061b6300 | 0x7f2efa6376c0 | 12073557318642053 | 12073557318655290 | 12073557319065046 | 12073557319091679 |
| 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 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7f30061b6a00 | 0x7f2efa637700 | 12073557319115493 | 12073557319128405 | 12073557320676231 | 12073557320745482 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7f30061b6900 | 0x7f2efa637740 | 12073557320769076 | 12073557320779910 | 12073557321573023 | 12073557321641578 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7f30061b6800 | 0x7f2efa637780 | 12073557321663268 | 12073557321674784 | 12073557322088061 | 12073557322160502 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7f30061b6700 | 0x7f2efa6377c0 | 12073557322181912 | 12073557322193339 | 12073557323351091 | 12073557323419542 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7f30061b6600 | 0x7f2efa637800 | 12073557323451321 | 12073557323464370 | 12073557324251724 | 12073557324319805 |
| 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 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7f30061b6500 | 0x7f2efa637840 | 12073557324341926 | 12073557324355083 | 12073557327407700 | 12073557327477423 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7f30061b6400 | 0x7f2efa637880 | 12073557327501237 | 12073557327514579 | 12073557329055368 | 12073557329123662 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7f30061b6300 | 0x7f2efa6378c0 | 12073557329148088 | 12073557329162247 | 12073557329951361 | 12073557330020228 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7f30061b6a00 | 0x7f2efa637900 | 12073557330042680 | 12073557330055360 | 12073557332336303 | 12073557332404589 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7f30061b6900 | 0x7f2efa637940 | 12073557332438132 | 12073557332452142 | 12073557333987331 | 12073557334055598 |
| 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 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7f30061b6800 | 0x7f2efa637980 | 12073557334078650 | 12073557334091490 | 12073557340148245 | 12073557340217329 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7f30061b6700 | 0x7f2efa6379c0 | 12073557340237436 | 12073557340250484 | 12073557343293501 | 12073557343361752 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7f30061b6600 | 0x7f2efa637a00 | 12073557343385196 | 12073557343398461 | 12073557344938129 | 12073557345007130 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 770557 | 770562 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7f30061b6500 | 0x7f2efa637a40 | 12073557345034771 | 12073557345048048 | 12073557349574894 | 12073557349647083 |