37 KiB
37 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_fillBufferAligned.kd | 0 | 0 | 0 | 147544 | 147544 | 33554432 | 256 | 0 | 0 | 4 | 32 | 4160 | 0x0 | 0x7fcc98204280 | 16113797720310 | 16113797745640 | 16113797987402 | 16113798106852 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 147544 | 147544 | 32768 | 256 | 0 | 0 | 12 | 24 | 13888 | 0x0 | 0x7fcc98223f80 | 16113802783178 | 16113802798629 | 16113802811909 | 16113802830147 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 5 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 14336 | 0x7fcc9b2f0380 | 0x7fcc98223fc0 | 16113802834797 | 16113802883750 | 16113802976070 | 16113802978134 |
| 5 | 3 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 8 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15040 | 0x7fcc9b2f0200 | 0x7fcc98224000 | 16113803000023 | 16113803009831 | 16113803190152 | 16113803192349 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 11 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15488 | 0x7fcc9b2f0080 | 0x7fcc98224040 | 16113803206458 | 16113803215112 | 16113803395913 | 16113803398034 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 14 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 15936 | 0x7fcc98c4df00 | 0x7fcc98224080 | 16113803412114 | 16113803420553 | 16113803515434 | 16113803517532 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 17 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 16384 | 0x7fcc98c4dd80 | 0x7fcc982240c0 | 16113803533301 | 16113803541674 | 16113803633834 | 16113803635709 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 20 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 17088 | 0x7fcc98c4dc00 | 0x7fcc98224100 | 16113803664568 | 16113803674794 | 16113803767115 | 16113803769196 |
| 10 | 8 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 23 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 16 | 24 | 17792 | 0x7fcc98c4da80 | 0x7fcc98224140 | 16113803786326 | 16113803796235 | 16113803975596 | 16113803977651 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 26 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 16 | 24 | 18496 | 0x7fcc98c4d900 | 0x7fcc98224180 | 16113803994991 | 16113804019597 | 16113804198318 | 16113804200516 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 29 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19200 | 0x7fcc98c4d780 | 0x7fcc982241c0 | 16113804217306 | 16113804226158 | 16113804319598 | 16113804321924 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 32 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19904 | 0x7fcc98c4d600 | 0x7fcc98224200 | 16113804346143 | 16113804356719 | 16113804450639 | 16113804452621 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 35 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 20608 | 0x7fcc9b2f0480 | 0x7fcc98224240 | 16113804475670 | 16113804500719 | 16113804594320 | 16113804596318 |
| 15 | 13 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 38 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 16 | 24 | 21312 | 0x7fcc9b2f0300 | 0x7fcc98224280 | 16113804613837 | 16113804622960 | 16113804801841 | 16113804803993 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 41 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22016 | 0x7fcc9b2f0180 | 0x7fcc982242c0 | 16113804816323 | 16113804825681 | 16113805005522 | 16113805007529 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 44 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22720 | 0x7fcc9b2f0000 | 0x7fcc98224300 | 16113805027288 | 16113805043923 | 16113805137203 | 16113805139416 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 47 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 23424 | 0x7fcc98c4de80 | 0x7fcc98224340 | 16113805159505 | 16113805175123 | 16113805269204 | 16113805271373 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 50 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 24128 | 0x7fcc98c4dd00 | 0x7fcc98224380 | 16113805293652 | 16113805303764 | 16113805395925 | 16113805398030 |
| 20 | 18 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 53 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 16 | 24 | 24832 | 0x7fcc98c4db80 | 0x7fcc982243c0 | 16113805417079 | 16113805426325 | 16113805605206 | 16113805607135 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 56 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 16 | 24 | 25536 | 0x7fcc98c4da00 | 0x7fcc98224400 | 16113805622545 | 16113805631446 | 16113805809687 | 16113805811791 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 59 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26240 | 0x7fcc98c4d880 | 0x7fcc98224440 | 16113805826850 | 16113805836087 | 16113805930168 | 16113805932178 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 62 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26944 | 0x7fcc98c4d700 | 0x7fcc98224480 | 16113805952418 | 16113805968408 | 16113806061849 | 16113806063935 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 65 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 27648 | 0x7fcc9b2f0580 | 0x7fcc982244c0 | 16113806092144 | 16113806102489 | 16113806194809 | 16113806197212 |
| 25 | 23 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 68 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 16 | 24 | 28608 | 0x7fcc9b2f0400 | 0x7fcc98224500 | 16113806211212 | 16113806220570 | 16113806398971 | 16113806401098 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 71 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 16 | 24 | 29312 | 0x7fcc9b2f0280 | 0x7fcc98224540 | 16113806415467 | 16113806425531 | 16113806605692 | 16113806607793 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 74 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 30016 | 0x7fcc9b2f0100 | 0x7fcc98224580 | 16113806624213 | 16113806634492 | 16113806726813 | 16113806728850 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 77 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 8 | 24 | 30976 | 0x7fcc98c4df80 | 0x7fcc982245c0 | 16113806743760 | 16113806753053 | 16113806845053 | 16113806847098 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 80 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 31680 | 0x7fcc98c4de00 | 0x7fcc98224600 | 16113806867827 | 16113806878173 | 16113806972094 | 16113806973925 |
| 30 | 28 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 83 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 16 | 24 | 32640 | 0x7fcc98c4dc80 | 0x7fcc98224640 | 16113806990405 | 16113806999294 | 16113807179775 | 16113807181420 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 86 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 33600 | 0x7fcc98c4db00 | 0x7fcc98224680 | 16113807194930 | 16113807202975 | 16113807383296 | 16113807384786 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 89 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 34560 | 0x7fcc98c4d980 | 0x7fcc982246c0 | 16113807399285 | 16113807407457 | 16113807501537 | 16113807502983 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 92 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 8 | 24 | 35520 | 0x7fcc98c4d800 | 0x7fcc98224700 | 16113807517993 | 16113807525857 | 16113807620098 | 16113807621641 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 95 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 36224 | 0x7fcc98c4d680 | 0x7fcc98224740 | 16113807643360 | 16113807652578 | 16113807745859 | 16113807747348 |
| 35 | 33 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 98 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 37184 | 0x7fcc9b2f0500 | 0x7fcc98224780 | 16113807762117 | 16113807770019 | 16113807949700 | 16113807951273 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 101 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 38144 | 0x7fcc9b2f0380 | 0x7fcc982247c0 | 16113807966703 | 16113807975620 | 16113808156901 | 16113808158379 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 104 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 39104 | 0x7fcc9b2f0200 | 0x7fcc98224800 | 16113808174348 | 16113808182181 | 16113808276102 | 16113808278066 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 107 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 8 | 24 | 40320 | 0x7fcc9b2f0080 | 0x7fcc98224840 | 16113808292356 | 16113808300422 | 16113808394502 | 16113808396183 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 110 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 41280 | 0x7fcc98c4df00 | 0x7fcc98224880 | 16113808416423 | 16113808427143 | 16113808521383 | 16113808523051 |
| 40 | 38 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 113 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 42240 | 0x7fcc98c4dd80 | 0x7fcc982248c0 | 16113808538730 | 16113808546823 | 16113808726504 | 16113808728036 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 116 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 43200 | 0x7fcc98c4dc00 | 0x7fcc98224900 | 16113808742916 | 16113808751785 | 16113808930986 | 16113808932551 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 119 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 8 | 24 | 44160 | 0x7fcc98c4da80 | 0x7fcc98224940 | 16113808947691 | 16113808956426 | 16113809050666 | 16113809052189 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 122 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 45376 | 0x7fcc98c4d900 | 0x7fcc98224980 | 16113809067598 | 16113809075466 | 16113809170667 | 16113809172066 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 125 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 46336 | 0x7fcc98c4d780 | 0x7fcc982249c0 | 16113809192726 | 16113809203147 | 16113809296588 | 16113809298063 |
| 45 | 43 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 128 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 47552 | 0x7fcc98c4d600 | 0x7fcc98224a00 | 16113809312573 | 16113809320588 | 16113809499309 | 16113809500779 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 131 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 48512 | 0x7fcc9b2f0480 | 0x7fcc98224a40 | 16113809517798 | 16113809525869 | 16113809704910 | 16113809706424 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 134 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 8 | 24 | 49472 | 0x7fcc9b2f0300 | 0x7fcc98224a80 | 16113809722484 | 16113809730830 | 16113809823311 | 16113809824902 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 137 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 50688 | 0x7fcc9b2f0180 | 0x7fcc98224ac0 | 16113809838951 | 16113809848111 | 16113809941552 | 16113809943029 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 140 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 51648 | 0x7fcc9b2f0000 | 0x7fcc98224b00 | 16113809963779 | 16113809974192 | 16113810065712 | 16113810067276 |
| 50 | 48 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 143 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 52864 | 0x7fcc98c4de80 | 0x7fcc98224b40 | 16113810097056 | 16113810106673 | 16113810285394 | 16113810287141 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 146 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 54080 | 0x7fcc98c4dd00 | 0x7fcc98224b80 | 16113810303131 | 16113810310994 | 16113810490195 | 16113810491717 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 149 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 8 | 24 | 55296 | 0x7fcc98c4db80 | 0x7fcc98224bc0 | 16113810507037 | 16113810515315 | 16113810610356 | 16113810611904 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 152 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 56768 | 0x7fcc98c4da00 | 0x7fcc98224c00 | 16113810628144 | 16113810635956 | 16113810731796 | 16113810733322 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 155 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 57728 | 0x7fcc98c4d880 | 0x7fcc98224c40 | 16113810755541 | 16113810766196 | 16113810859477 | 16113810861039 |
| 55 | 53 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 158 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 58944 | 0x7fcc98c4d700 | 0x7fcc98224c80 | 16113810876649 | 16113810884917 | 16113811063958 | 16113811065524 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 161 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 60160 | 0x7fcc9b2f0580 | 0x7fcc98224cc0 | 16113811079704 | 16113811088758 | 16113811271639 | 16113811273060 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 164 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 8 | 24 | 61376 | 0x7fcc9b2f0400 | 0x7fcc98224d00 | 16113811287219 | 16113811296280 | 16113811390680 | 16113811392237 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 167 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 62848 | 0x7fcc9b2f0280 | 0x7fcc98224d40 | 16113811408227 | 16113811417080 | 16113811516441 | 16113811518044 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 170 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 63808 | 0x7fcc9b2f0100 | 0x7fcc98224d80 | 16113811538614 | 16113811549081 | 16113811642842 | 16113811644342 |
| 60 | 58 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 173 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 65024 | 0x7fcc98c4df80 | 0x7fcc98224dc0 | 16113811661271 | 16113811670522 | 16113811851003 | 16113811852577 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 176 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 66240 | 0x7fcc98c4de00 | 0x7fcc98224e00 | 16113811866407 | 16113811875163 | 16113812055644 | 16113812057223 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 179 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 8 | 24 | 67456 | 0x7fcc98c4dc80 | 0x7fcc98224e40 | 16113812072582 | 16113812080284 | 16113812175325 | 16113812176800 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 182 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 68928 | 0x7fcc98c4db00 | 0x7fcc98224e80 | 16113812190810 | 16113812199485 | 16113812303166 | 16113812304627 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 185 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 70144 | 0x7fcc98c4d980 | 0x7fcc98224ec0 | 16113812325847 | 16113812336606 | 16113812429246 | 16113812430754 |
| 65 | 63 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 188 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 71616 | 0x7fcc98c4d800 | 0x7fcc98224f00 | 16113812447164 | 16113812454846 | 16113812635488 | 16113812637170 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 191 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 72832 | 0x7fcc98c4d680 | 0x7fcc98224f40 | 16113812652509 | 16113812662048 | 16113812843809 | 16113812845365 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 194 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 8 | 24 | 74048 | 0x7fcc9b2f0500 | 0x7fcc98224f80 | 16113812859045 | 16113812867329 | 16113812960769 | 16113812962423 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 197 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 75776 | 0x7fcc9b2f0380 | 0x7fcc98224fc0 | 16113812977302 | 16113812985090 | 16113813092450 | 16113813094070 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 200 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 76992 | 0x7fcc9b2f0200 | 0x7fcc98225000 | 16113813116259 | 16113813127010 | 16113813220611 | 16113813222157 |
| 70 | 68 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 203 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 78464 | 0x7fcc9b2f0080 | 0x7fcc98225040 | 16113813238457 | 16113813246371 | 16113813425412 | 16113813427032 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 206 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 79936 | 0x7fcc98c4df00 | 0x7fcc98225080 | 16113813442182 | 16113813450052 | 16113813629573 | 16113813631148 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 209 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 8 | 24 | 81408 | 0x7fcc98c4dd80 | 0x7fcc982250c0 | 16113813647288 | 16113813656294 | 16113813751334 | 16113813752855 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 212 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 83136 | 0x7fcc98c4dc00 | 0x7fcc98225100 | 16113813769055 | 16113813776934 | 16113813893095 | 16113813894702 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 215 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 84352 | 0x7fcc98c4da80 | 0x7fcc98225140 | 16113813928571 | 16113813938375 | 16113814032296 | 16113814033779 |
| 75 | 73 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 218 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 85824 | 0x7fcc98c4d900 | 0x7fcc98225180 | 16113814050219 | 16113814058376 | 16113814239497 | 16113814241094 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 221 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 87296 | 0x7fcc98c4d780 | 0x7fcc982251c0 | 16113814257404 | 16113814265577 | 16113814444298 | 16113814445830 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 224 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 88768 | 0x7fcc98c4d600 | 0x7fcc98225200 | 16113814461090 | 16113814469578 | 16113814565259 | 16113814566977 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 227 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 90752 | 0x7fcc9b2f0480 | 0x7fcc98225240 | 16113814582017 | 16113814590859 | 16113814712460 | 16113814714154 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 230 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 91968 | 0x7fcc9b2f0300 | 0x7fcc98225280 | 16113814734583 | 16113814744780 | 16113814839501 | 16113814841101 |
| 80 | 78 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 233 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 93440 | 0x7fcc9b2f0180 | 0x7fcc982252c0 | 16113814855921 | 16113814864141 | 16113815043822 | 16113815045407 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 236 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 94912 | 0x7fcc9b2f0000 | 0x7fcc98225300 | 16113815059496 | 16113815067502 | 16113815247183 | 16113815248842 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 239 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 96384 | 0x7fcc98c4de80 | 0x7fcc98225340 | 16113815263942 | 16113815272143 | 16113815367504 | 16113815369079 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 242 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 98368 | 0x7fcc98c4dd00 | 0x7fcc98225380 | 16113815382879 | 16113815392144 | 16113815518225 | 16113815519726 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 245 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 99584 | 0x7fcc98c4db80 | 0x7fcc982253c0 | 16113815540606 | 16113815551025 | 16113815645425 | 16113815647003 |
| 85 | 83 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 248 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 101312 | 0x7fcc98c4da00 | 0x7fcc98225400 | 16113815665923 | 16113815677906 | 16113815856147 | 16113815857959 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 251 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 102784 | 0x7fcc98c4d880 | 0x7fcc98225440 | 16113815872678 | 16113815880627 | 16113816059348 | 16113816061034 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 254 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 104256 | 0x7fcc98c4d700 | 0x7fcc98225480 | 16113816075724 | 16113816083668 | 16113816177269 | 16113816178981 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 257 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 106240 | 0x7fcc9b2f0580 | 0x7fcc982254c0 | 16113816193791 | 16113816201749 | 16113816332469 | 16113816334098 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 260 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 107712 | 0x7fcc9b2f0400 | 0x7fcc98225500 | 16113816356598 | 16113816367030 | 16113816460150 | 16113816461635 |
| 90 | 88 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 263 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 16 | 24 | 109440 | 0x7fcc9b2f0280 | 0x7fcc98225540 | 16113816477895 | 16113816486390 | 16113816664471 | 16113816665961 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 266 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 16 | 24 | 111168 | 0x7fcc9b2f0100 | 0x7fcc98225580 | 16113816679830 | 16113816688792 | 16113816867833 | 16113816869356 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 269 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 8 | 24 | 112896 | 0x7fcc98c4df80 | 0x7fcc982255c0 | 16113816883256 | 16113816892473 | 16113816988473 | 16113816989973 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 272 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 115136 | 0x7fcc98c4de00 | 0x7fcc98225600 | 16113817006133 | 16113817014233 | 16113817152954 | 16113817154460 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 275 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 116608 | 0x7fcc98c4dc80 | 0x7fcc98225640 | 16113817176029 | 16113817186715 | 16113817281595 | 16113817283127 |
| 95 | 93 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 278 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 16 | 24 | 118336 | 0x7fcc98c4db00 | 0x7fcc98225680 | 16113817299367 | 16113817307835 | 16113817487676 | 16113817489262 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 281 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 16 | 24 | 120064 | 0x7fcc98c4d980 | 0x7fcc982256c0 | 16113817503352 | 16113817512636 | 16113817694238 | 16113817695828 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 284 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 121792 | 0x7fcc98c4d800 | 0x7fcc98225700 | 16113817711497 | 16113817720318 | 16113817817278 | 16113817818885 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 287 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 124032 | 0x7fcc98c4d680 | 0x7fcc98225740 | 16113817834265 | 16113817842718 | 16113817987199 | 16113817988741 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 290 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 125504 | 0x7fcc9b2f0500 | 0x7fcc98225780 | 16113818010541 | 16113818021119 | 16113818117280 | 16113818118968 |
| 100 | 98 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 293 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 127488 | 0x7fcc9b2f0380 | 0x7fcc982257c0 | 16113818135018 | 16113818142880 | 16113818323681 | 16113818325184 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 296 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 129216 | 0x7fcc9b2f0200 | 0x7fcc98225800 | 16113818339344 | 16113818347361 | 16113818528002 | 16113818529619 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 299 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 130944 | 0x7fcc9b2f0080 | 0x7fcc98225840 | 16113818542969 | 16113818552003 | 16113818651043 | 16113818652507 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 302 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 133440 | 0x7fcc98c4df00 | 0x7fcc98225880 | 16113818666376 | 16113818674243 | 16113818830244 | 16113818831833 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 305 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 134912 | 0x7fcc98c4dd80 | 0x7fcc982258c0 | 16113818852132 | 16113818862884 | 16113818958725 | 16113818960490 |
| 105 | 103 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 308 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 136896 | 0x7fcc98c4dc00 | 0x7fcc98225900 | 16113818978029 | 16113818986085 | 16113819164646 | 16113819166475 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 311 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 138880 | 0x7fcc98c4da80 | 0x7fcc98225940 | 16113819181635 | 16113819189606 | 16113819369607 | 16113819371271 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 314 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 140864 | 0x7fcc98c4d900 | 0x7fcc98225980 | 16113819385180 | 16113819393128 | 16113819500808 | 16113819502448 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 317 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 143616 | 0x7fcc98c4d780 | 0x7fcc982259c0 | 16113819517837 | 16113819526248 | 16113819697449 | 16113819699153 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 320 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 145344 | 0x7fcc98c4d600 | 0x7fcc98225a00 | 16113819720773 | 16113819731370 | 16113819826890 | 16113819828501 |
| 110 | 108 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 323 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 147584 | 0x7fcc9b2f0480 | 0x7fcc98225a40 | 16113819843480 | 16113819851530 | 16113820035851 | 16113820037766 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 326 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 149568 | 0x7fcc9b2f0300 | 0x7fcc98225a80 | 16113820051626 | 16113820059532 | 16113820240813 | 16113820242441 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 329 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 151552 | 0x7fcc9b2f0180 | 0x7fcc98225ac0 | 16113820257401 | 16113820265613 | 16113820376973 | 16113820378708 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 332 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 154304 | 0x7fcc9b2f0000 | 0x7fcc98225b00 | 16113820393078 | 16113820400814 | 16113820582095 | 16113820583784 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 335 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 156288 | 0x7fcc98c4de80 | 0x7fcc98225b40 | 16113820604613 | 16113820614255 | 16113820715375 | 16113820716841 |
| 115 | 113 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 338 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 158784 | 0x7fcc98c4dd00 | 0x7fcc98225b80 | 16113820731761 | 16113820739696 | 16113820926417 | 16113820927906 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 341 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 161024 | 0x7fcc98c4db80 | 0x7fcc98225bc0 | 16113820941766 | 16113820950097 | 16113821134738 | 16113821136202 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 344 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 163264 | 0x7fcc98c4da00 | 0x7fcc98225c00 | 16113821149781 | 16113821158098 | 16113821280819 | 16113821282408 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 347 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 166528 | 0x7fcc98c4d880 | 0x7fcc98225c40 | 16113821297728 | 16113821305939 | 16113821512820 | 16113821534983 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 350 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 168512 | 0x7fcc98c4d700 | 0x7fcc98225c80 | 16113821550922 | 16113821561780 | 16113821672501 | 16113821674100 |
| 120 | 118 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 353 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 171264 | 0x7fcc9b2f0580 | 0x7fcc98225cc0 | 16113821690969 | 16113821699861 | 16113821883062 | 16113821884535 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 356 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 173760 | 0x7fcc9b2f0400 | 0x7fcc98225d00 | 16113821898675 | 16113821907702 | 16113822094904 | 16113822096480 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 359 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 176256 | 0x7fcc9b2f0280 | 0x7fcc98225d40 | 16113822112630 | 16113822120824 | 16113822255385 | 16113822256887 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 362 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 179776 | 0x7fcc9b2f0100 | 0x7fcc98225d80 | 16113822271416 | 16113822279225 | 16113822511226 | 16113822555610 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 365 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 182272 | 0x7fcc98c4df80 | 0x7fcc98225dc0 | 16113822571200 | 16113822581786 | 16113822708667 | 16113822710117 |
| 125 | 123 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 368 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 185536 | 0x7fcc98c4de00 | 0x7fcc98225e00 | 16113822726496 | 16113822734747 | 16113822928829 | 16113822930532 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 371 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 188544 | 0x7fcc98c4dc80 | 0x7fcc98225e40 | 16113822945881 | 16113822954269 | 16113823146750 | 16113823148347 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 374 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 191552 | 0x7fcc98c4db00 | 0x7fcc98225e80 | 16113823162857 | 16113823171070 | 16113823331071 | 16113823332683 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 377 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 195840 | 0x7fcc98c4d980 | 0x7fcc98225ec0 | 16113823347033 | 16113823355071 | 16113823638753 | 16113823682905 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 380 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 198592 | 0x7fcc98c4d800 | 0x7fcc98225f00 | 16113823697185 | 16113823707873 | 16113823856994 | 16113823858551 |
| 130 | 128 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 383 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 202368 | 0x7fcc98c4d680 | 0x7fcc98225f40 | 16113823875261 | 16113823883234 | 16113824092515 | 16113824135895 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 386 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 205888 | 0x7fcc9b2f0500 | 0x7fcc98225f80 | 16113824143955 | 16113824154276 | 16113824360517 | 16113824403669 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 389 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 209408 | 0x7fcc9b2f0380 | 0x7fcc98225fc0 | 16113824415089 | 16113824425477 | 16113824611398 | 16113824612934 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 392 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 214464 | 0x7fcc9b2f0200 | 0x7fcc98226000 | 16113824627974 | 16113824637159 | 16113824971721 | 16113824988496 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 395 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 217728 | 0x7fcc9b2f0080 | 0x7fcc98226040 | 16113825004446 | 16113825014921 | 16113825182602 | 16113825184122 |
| 135 | 133 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 398 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 222016 | 0x7fcc98c4df00 | 0x7fcc98226080 | 16113825199771 | 16113825207562 | 16113825437163 | 16113825453066 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 401 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 226048 | 0x7fcc98c4dd80 | 0x7fcc982260c0 | 16113825461156 | 16113825471244 | 16113825700205 | 16113825716830 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 404 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 230080 | 0x7fcc98c4dc00 | 0x7fcc98226100 | 16113825729340 | 16113825739565 | 16113825951086 | 16113825966764 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 407 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 235904 | 0x7fcc98c4da80 | 0x7fcc98226140 | 16113825976534 | 16113825985167 | 16113826370769 | 16113826414125 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 410 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 239424 | 0x7fcc98c4d900 | 0x7fcc98226180 | 16113826430534 | 16113826441649 | 16113826629810 | 16113826631420 |
| 140 | 138 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 413 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 244224 | 0x7fcc98c4d780 | 0x7fcc982261c0 | 16113826646199 | 16113826653971 | 16113826904052 | 16113826946203 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 416 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 248768 | 0x7fcc98c4d600 | 0x7fcc98226200 | 16113826956122 | 16113826965972 | 16113827214454 | 16113827259926 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 419 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 253312 | 0x7fcc9b2f0480 | 0x7fcc98226240 | 16113827270126 | 16113827280374 | 16113827517496 | 16113827562579 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 422 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 8 | 24 | 255552 | 0x7fcc9b2f0300 | 0x7fcc98226280 | 16113827570929 | 16113827581176 | 16113828035259 | 16113828077358 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 425 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 259840 | 0x7fcc9b2f0180 | 0x7fcc982262c0 | 16113828093557 | 16113828103899 | 16113828330301 | 16113828372351 |
| 145 | 143 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 428 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 265664 | 0x7fcc9b2f0000 | 0x7fcc98226300 | 16113828384201 | 16113828394461 | 16113828692543 | 16113828734593 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 431 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 271232 | 0x7fcc98c4de80 | 0x7fcc98226340 | 16113828746423 | 16113828755743 | 16113829054625 | 16113829099985 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 434 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 8 | 24 | 273216 | 0x7fcc98c4dd00 | 0x7fcc98226380 | 16113829109325 | 16113829119105 | 16113829415747 | 16113829461227 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 437 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 8 | 24 | 275712 | 0x7fcc98c4db80 | 0x7fcc982263c0 | 16113829473157 | 16113829483427 | 16113830040391 | 16113830056574 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 440 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 280768 | 0x7fcc98c4da00 | 0x7fcc98226400 | 16113830072763 | 16113830094791 | 16113830358473 | 16113830404876 |
| 150 | 148 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 443 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 287616 | 0x7fcc98c4d880 | 0x7fcc98226440 | 16113830413356 | 16113830423433 | 16113830773835 | 16113830819157 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 446 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 294208 | 0x7fcc98c4d700 | 0x7fcc98226480 | 16113830827897 | 16113830838315 | 16113831188237 | 16113831233588 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 449 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 8 | 24 | 296960 | 0x7fcc9b2f0580 | 0x7fcc982264c0 | 16113831245937 | 16113831256078 | 16113831603600 | 16113831643349 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 452 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 8 | 24 | 299968 | 0x7fcc9b2f0400 | 0x7fcc98226500 | 16113831654798 | 16113831665200 | 16113832326964 | 16113832370302 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 455 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 8 | 24 | 302720 | 0x7fcc9b2f0280 | 0x7fcc98226540 | 16113832389532 | 16113832398965 | 16113832846007 | 16113832889301 |
| 155 | 153 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 458 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 305472 | 0x7fcc9b2f0100 | 0x7fcc98226580 | 16113832900091 | 16113832910328 | 16113833375610 | 16113833420539 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 461 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 308224 | 0x7fcc98c4df80 | 0x7fcc982265c0 | 16113833431559 | 16113833447771 | 16113833910494 | 16113833931658 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 464 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 8 | 24 | 310976 | 0x7fcc98c4de00 | 0x7fcc98226600 | 16113833941478 | 16113833950974 | 16113834402976 | 16113834452176 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 467 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 8 | 24 | 313216 | 0x7fcc98c4dc80 | 0x7fcc98226640 | 16113834462326 | 16113834472417 | 16113835342182 | 16113835389645 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 470 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 8 | 24 | 315968 | 0x7fcc98c4db00 | 0x7fcc98226680 | 16113835407635 | 16113835418182 | 16113836271948 | 16113836316815 |
| 160 | 158 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 473 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 318720 | 0x7fcc98c4d980 | 0x7fcc982266c0 | 16113836326665 | 16113836336588 | 16113837221553 | 16113837266434 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 476 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 321472 | 0x7fcc98c4d800 | 0x7fcc98226700 | 16113837276344 | 16113837286194 | 16113838164759 | 16113838214463 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 479 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 8 | 24 | 324224 | 0x7fcc98c4d680 | 0x7fcc98226740 | 16113838224633 | 16113838242199 | 16113839102364 | 16113839152632 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 482 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 8 | 24 | 326464 | 0x7fcc9b2f0500 | 0x7fcc98226780 | 16113839163212 | 16113839172605 | 16113840871175 | 16113840945692 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 485 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 8 | 24 | 329216 | 0x7fcc9b2f0380 | 0x7fcc982267c0 | 16113840963272 | 16113840973735 | 16113842639185 | 16113842709213 |
| 165 | 163 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 488 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 331968 | 0x7fcc9b2f0200 | 0x7fcc98226800 | 16113842720283 | 16113842729586 | 16113844454876 | 16113844523993 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 491 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 12 | 24 | 334720 | 0x7fcc9b2f0080 | 0x7fcc98226840 | 16113844533423 | 16113844543837 | 16113846258567 | 16113846330853 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 494 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 8 | 24 | 337472 | 0x7fcc98c4df00 | 0x7fcc98226880 | 16113846341273 | 16113846350887 | 16113848025137 | 16113848092994 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 497 | 147544 | 147544 | 4194304 | 256 | 0 | 0 | 8 | 24 | 0 | 0x7fcc98c4dd80 | 0x7fcc982268c0 | 16113848102134 | 16113848112978 | 16113851470598 | 16113851547517 |