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 | 143037 | 143037 | 33554432 | 256 | 0 | 0 | 4 | 32 | 4160 | 0x0 | 0x7fd1f5204280 | 15995326264762 | 15995326289103 | 15995326528944 | 15995326640693 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 143037 | 143037 | 32768 | 256 | 0 | 0 | 12 | 24 | 13888 | 0x0 | 0x7fd1f5223f80 | 15995331308630 | 15995331324002 | 15995331337762 | 15995331355039 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 5 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 14336 | 0x7fd1f8121380 | 0x7fd1f5223fc0 | 15995331360479 | 15995331407843 | 15995331500803 | 15995331502795 |
| 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 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15040 | 0x7fd1f8121200 | 0x7fd1f5224000 | 15995331524945 | 15995331534883 | 15995331713444 | 15995331715361 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 11 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15488 | 0x7fd1f8121080 | 0x7fd1f5224040 | 15995331730640 | 15995331739524 | 15995331919525 | 15995331921796 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 14 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 15936 | 0x7fd1f59cbf00 | 0x7fd1f5224080 | 15995331936366 | 15995331945125 | 15995332038885 | 15995332040893 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 17 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 16384 | 0x7fd1f59cbd80 | 0x7fd1f52240c0 | 15995332055743 | 15995332064165 | 15995332156006 | 15995332157981 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 20 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 17088 | 0x7fd1f59cbc00 | 0x7fd1f5224100 | 15995332186100 | 15995332196806 | 15995332289446 | 15995332291258 |
| 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 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 16 | 24 | 17792 | 0x7fd1f59cba80 | 0x7fd1f5224140 | 15995332311447 | 15995332333447 | 15995332512167 | 15995332514263 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 26 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 16 | 24 | 18496 | 0x7fd1f59cb900 | 0x7fd1f5224180 | 15995332531012 | 15995332540967 | 15995332720328 | 15995332722198 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 29 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19200 | 0x7fd1f59cb780 | 0x7fd1f52241c0 | 15995332742478 | 15995332760328 | 15995332854409 | 15995332856335 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 32 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19904 | 0x7fd1f59cb600 | 0x7fd1f5224200 | 15995332872625 | 15995332882889 | 15995332975689 | 15995332977482 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 35 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 20608 | 0x7fd1f8121480 | 0x7fd1f5224240 | 15995332996892 | 15995333008009 | 15995333100650 | 15995333102420 |
| 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 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 16 | 24 | 21312 | 0x7fd1f8121300 | 0x7fd1f5224280 | 15995333128319 | 15995333138730 | 15995333318731 | 15995333320645 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 41 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22016 | 0x7fd1f8121180 | 0x7fd1f52242c0 | 15995333340734 | 15995333350891 | 15995333532651 | 15995333534550 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 44 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22720 | 0x7fd1f8121000 | 0x7fd1f5224300 | 15995333551640 | 15995333560331 | 15995333654572 | 15995333656457 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 47 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 23424 | 0x7fd1f59cbe80 | 0x7fd1f5224340 | 15995333676287 | 15995333686412 | 15995333780492 | 15995333782194 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 50 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 24128 | 0x7fd1f59cbd00 | 0x7fd1f5224380 | 15995333803814 | 15995333814253 | 15995333906893 | 15995333908662 |
| 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 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 16 | 24 | 24832 | 0x7fd1f59cbb80 | 0x7fd1f52243c0 | 15995333932691 | 15995333942893 | 15995334122414 | 15995334124527 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 56 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 16 | 24 | 25536 | 0x7fd1f59cba00 | 0x7fd1f5224400 | 15995334140027 | 15995334149454 | 15995334329615 | 15995334331392 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 59 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26240 | 0x7fd1f59cb880 | 0x7fd1f5224440 | 15995334350162 | 15995334359855 | 15995334453775 | 15995334455650 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 62 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26944 | 0x7fd1f59cb700 | 0x7fd1f5224480 | 15995334475469 | 15995334485775 | 15995334579056 | 15995334580957 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 65 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 27648 | 0x7fd1f8121580 | 0x7fd1f52244c0 | 15995334602446 | 15995334612976 | 15995334704976 | 15995334706884 |
| 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 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 16 | 24 | 28608 | 0x7fd1f8121400 | 0x7fd1f5224500 | 15995334724014 | 15995334732496 | 15995334911857 | 15995334913689 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 71 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 16 | 24 | 29312 | 0x7fd1f8121280 | 0x7fd1f5224540 | 15995334929319 | 15995334939057 | 15995335118418 | 15995335120175 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 74 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 30016 | 0x7fd1f8121100 | 0x7fd1f5224580 | 15995335139374 | 15995335161778 | 15995335253938 | 15995335255792 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 77 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 8 | 24 | 30976 | 0x7fd1f59cbf80 | 0x7fd1f52245c0 | 15995335274331 | 15995335283218 | 15995335375699 | 15995335377429 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 80 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 31680 | 0x7fd1f59cbe00 | 0x7fd1f5224600 | 15995335398509 | 15995335408979 | 15995335501779 | 15995335503646 |
| 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 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 16 | 24 | 32640 | 0x7fd1f59cbc80 | 0x7fd1f5224640 | 15995335521256 | 15995335531539 | 15995335710900 | 15995335712902 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 86 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 33600 | 0x7fd1f59cbb00 | 0x7fd1f5224680 | 15995335729621 | 15995335738740 | 15995335920661 | 15995335922517 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 89 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 34560 | 0x7fd1f59cb980 | 0x7fd1f52246c0 | 15995335939617 | 15995335948661 | 15995336042902 | 15995336044774 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 92 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 8 | 24 | 35520 | 0x7fd1f59cb800 | 0x7fd1f5224700 | 15995336063674 | 15995336075862 | 15995336170102 | 15995336171961 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 95 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 36224 | 0x7fd1f59cb680 | 0x7fd1f5224740 | 15995336194461 | 15995336203222 | 15995336296983 | 15995336298809 |
| 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 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 37184 | 0x7fd1f8121500 | 0x7fd1f5224780 | 15995336318848 | 15995336329303 | 15995336508983 | 15995336510854 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 101 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 38144 | 0x7fd1f8121380 | 0x7fd1f52247c0 | 15995336530514 | 15995336541144 | 15995336720824 | 15995336722639 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 104 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 39104 | 0x7fd1f8121200 | 0x7fd1f5224800 | 15995336736309 | 15995336745144 | 15995336838745 | 15995336840657 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 107 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 8 | 24 | 40320 | 0x7fd1f8121080 | 0x7fd1f5224840 | 15995336857906 | 15995336867225 | 15995336961305 | 15995336963294 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 110 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 41280 | 0x7fd1f59cbf00 | 0x7fd1f5224880 | 15995336985893 | 15995336996505 | 15995337089306 | 15995337091021 |
| 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 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 42240 | 0x7fd1f59cbd80 | 0x7fd1f52248c0 | 15995337109761 | 15995337119066 | 15995337297947 | 15995337299826 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 116 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 43200 | 0x7fd1f59cbc00 | 0x7fd1f5224900 | 15995337319626 | 15995337329947 | 15995337509627 | 15995337511482 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 119 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 8 | 24 | 44160 | 0x7fd1f59cba80 | 0x7fd1f5224940 | 15995337531191 | 15995337551868 | 15995337646588 | 15995337648459 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 122 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 45376 | 0x7fd1f59cb900 | 0x7fd1f5224980 | 15995337671438 | 15995337682268 | 15995337777469 | 15995337779246 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 125 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 46336 | 0x7fd1f59cb780 | 0x7fd1f52249c0 | 15995337800805 | 15995337811069 | 15995337904509 | 15995337906183 |
| 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 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 47552 | 0x7fd1f59cb600 | 0x7fd1f5224a00 | 15995337926563 | 15995337937149 | 15995338115710 | 15995338118118 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 131 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 48512 | 0x7fd1f8121480 | 0x7fd1f5224a40 | 15995338136388 | 15995338145790 | 15995338325631 | 15995338327404 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 134 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 8 | 24 | 49472 | 0x7fd1f8121300 | 0x7fd1f5224a80 | 15995338347533 | 15995338356511 | 15995338449471 | 15995338451351 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 137 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 50688 | 0x7fd1f8121180 | 0x7fd1f5224ac0 | 15995338465471 | 15995338476671 | 15995338570112 | 15995338572118 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 140 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 51648 | 0x7fd1f8121000 | 0x7fd1f5224b00 | 15995338593398 | 15995338604032 | 15995338696192 | 15995338698055 |
| 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 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 52864 | 0x7fd1f59cbe80 | 0x7fd1f5224b40 | 15995338719135 | 15995338728352 | 15995338906753 | 15995338908681 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 146 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 54080 | 0x7fd1f59cbd00 | 0x7fd1f5224b80 | 15995338924910 | 15995338958273 | 15995339136674 | 15995339138556 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 149 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 8 | 24 | 55296 | 0x7fd1f59cbb80 | 0x7fd1f5224bc0 | 15995339165035 | 15995339175394 | 15995339270115 | 15995339271953 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 152 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 56768 | 0x7fd1f59cba00 | 0x7fd1f5224c00 | 15995339292752 | 15995339309155 | 15995339404515 | 15995339406400 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 155 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 57728 | 0x7fd1f59cb880 | 0x7fd1f5224c40 | 15995339427419 | 15995339437795 | 15995339531076 | 15995339532817 |
| 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 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 58944 | 0x7fd1f59cb700 | 0x7fd1f5224c80 | 15995339548387 | 15995339556516 | 15995339736196 | 15995339737592 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 161 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 60160 | 0x7fd1f8121580 | 0x7fd1f5224cc0 | 15995339752202 | 15995339760837 | 15995339941317 | 15995339942728 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 164 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 8 | 24 | 61376 | 0x7fd1f8121400 | 0x7fd1f5224d00 | 15995339956868 | 15995339965317 | 15995340059558 | 15995340060985 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 167 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 62848 | 0x7fd1f8121280 | 0x7fd1f5224d40 | 15995340079055 | 15995340087238 | 15995340187558 | 15995340188932 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 170 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 63808 | 0x7fd1f8121100 | 0x7fd1f5224d80 | 15995340211022 | 15995340221638 | 15995340316039 | 15995340317350 |
| 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 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 65024 | 0x7fd1f59cbf80 | 0x7fd1f5224dc0 | 15995340335259 | 15995340344839 | 15995340524200 | 15995340525595 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 176 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 66240 | 0x7fd1f59cbe00 | 0x7fd1f5224e00 | 15995340540045 | 15995340548840 | 15995340728040 | 15995340729470 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 179 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 8 | 24 | 67456 | 0x7fd1f59cbc80 | 0x7fd1f5224e40 | 15995340744950 | 15995340753001 | 15995340848041 | 15995340849308 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 182 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 68928 | 0x7fd1f59cbb00 | 0x7fd1f5224e80 | 15995340864787 | 15995340873481 | 15995340977481 | 15995340978735 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 185 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 70144 | 0x7fd1f59cb980 | 0x7fd1f5224ec0 | 15995340999284 | 15995341010122 | 15995341102922 | 15995341104262 |
| 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 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 71616 | 0x7fd1f59cb800 | 0x7fd1f5224f00 | 15995341120942 | 15995341128842 | 15995341309003 | 15995341310278 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 191 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 72832 | 0x7fd1f59cb680 | 0x7fd1f5224f40 | 15995341328267 | 15995341336683 | 15995341517484 | 15995341518823 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 194 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 8 | 24 | 74048 | 0x7fd1f8121500 | 0x7fd1f5224f80 | 15995341533173 | 15995341541804 | 15995341635884 | 15995341637290 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 197 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 75776 | 0x7fd1f8121380 | 0x7fd1f5224fc0 | 15995341652270 | 15995341661004 | 15995341768045 | 15995341769287 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 200 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 76992 | 0x7fd1f8121200 | 0x7fd1f5225000 | 15995341790697 | 15995341801485 | 15995341894765 | 15995341896185 |
| 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 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 78464 | 0x7fd1f8121080 | 0x7fd1f5225040 | 15995341911724 | 15995341919565 | 15995342100206 | 15995342101540 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 206 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 79936 | 0x7fd1f59cbf00 | 0x7fd1f5225080 | 15995342117870 | 15995342125966 | 15995342306287 | 15995342307605 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 209 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 8 | 24 | 81408 | 0x7fd1f59cbd80 | 0x7fd1f52250c0 | 15995342321655 | 15995342331087 | 15995342426447 | 15995342427963 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 212 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 83136 | 0x7fd1f59cbc00 | 0x7fd1f5225100 | 15995342442312 | 15995342450767 | 15995342566928 | 15995342568280 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 215 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 84352 | 0x7fd1f59cba80 | 0x7fd1f5225140 | 15995342602769 | 15995342612368 | 15995342705968 | 15995342707326 |
| 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 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 85824 | 0x7fd1f59cb900 | 0x7fd1f5225180 | 15995342722606 | 15995342731249 | 15995342911569 | 15995342912932 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 221 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 87296 | 0x7fd1f59cb780 | 0x7fd1f52251c0 | 15995342927522 | 15995342935409 | 15995343117010 | 15995343118287 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 224 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 88768 | 0x7fd1f59cb600 | 0x7fd1f5225200 | 15995343133187 | 15995343141330 | 15995343237011 | 15995343238475 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 227 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 90752 | 0x7fd1f8121480 | 0x7fd1f5225240 | 15995343252614 | 15995343261331 | 15995343383091 | 15995343384641 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 230 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 91968 | 0x7fd1f8121300 | 0x7fd1f5225280 | 15995343405811 | 15995343416371 | 15995343511892 | 15995343513198 |
| 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 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 93440 | 0x7fd1f8121180 | 0x7fd1f52252c0 | 15995343528198 | 15995343536532 | 15995343715733 | 15995343717084 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 236 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 94912 | 0x7fd1f8121000 | 0x7fd1f5225300 | 15995343733774 | 15995343741493 | 15995343920533 | 15995343921769 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 239 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 96384 | 0x7fd1f59cbe80 | 0x7fd1f5225340 | 15995343938339 | 15995343946453 | 15995344041174 | 15995344042367 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 242 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 98368 | 0x7fd1f59cbd00 | 0x7fd1f5225380 | 15995344058736 | 15995344067894 | 15995344193814 | 15995344195133 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 245 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 99584 | 0x7fd1f59cbb80 | 0x7fd1f52253c0 | 15995344216123 | 15995344226775 | 15995344320855 | 15995344322180 |
| 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 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 101312 | 0x7fd1f59cba00 | 0x7fd1f5225400 | 15995344338650 | 15995344347255 | 15995344525976 | 15995344527286 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 251 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 102784 | 0x7fd1f59cb880 | 0x7fd1f5225440 | 15995344541915 | 15995344550616 | 15995344730297 | 15995344731721 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 254 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 104256 | 0x7fd1f59cb700 | 0x7fd1f5225480 | 15995344746981 | 15995344754937 | 15995344849337 | 15995344850519 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 257 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 106240 | 0x7fd1f8121580 | 0x7fd1f52254c0 | 15995344865188 | 15995344873177 | 15995345003258 | 15995345004655 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 260 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 107712 | 0x7fd1f8121400 | 0x7fd1f5225500 | 15995345027155 | 15995345037978 | 15995345130938 | 15995345132312 |
| 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 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 16 | 24 | 109440 | 0x7fd1f8121280 | 0x7fd1f5225540 | 15995345148992 | 15995345157978 | 15995345337659 | 15995345338908 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 266 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 16 | 24 | 111168 | 0x7fd1f8121100 | 0x7fd1f5225580 | 15995345353607 | 15995345361979 | 15995345542780 | 15995345544123 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 269 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 8 | 24 | 112896 | 0x7fd1f59cbf80 | 0x7fd1f52255c0 | 15995345558993 | 15995345567420 | 15995345664060 | 15995345665290 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 272 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 115136 | 0x7fd1f59cbe00 | 0x7fd1f5225600 | 15995345680950 | 15995345689661 | 15995345828541 | 15995345829857 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 275 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 116608 | 0x7fd1f59cbc80 | 0x7fd1f5225640 | 15995345851096 | 15995345861981 | 15995345957022 | 15995345958284 |
| 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 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 16 | 24 | 118336 | 0x7fd1f59cbb00 | 0x7fd1f5225680 | 15995345973743 | 15995345981822 | 15995346162462 | 15995346163889 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 281 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 16 | 24 | 120064 | 0x7fd1f59cb980 | 0x7fd1f52256c0 | 15995346178739 | 15995346187903 | 15995346367583 | 15995346368995 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 284 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 121792 | 0x7fd1f59cb800 | 0x7fd1f5225700 | 15995346384104 | 15995346392543 | 15995346490144 | 15995346491572 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 287 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 124032 | 0x7fd1f59cb680 | 0x7fd1f5225740 | 15995346507312 | 15995346515584 | 15995346660064 | 15995346661458 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 290 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 125504 | 0x7fd1f8121500 | 0x7fd1f5225780 | 15995346681948 | 15995346692545 | 15995346789185 | 15995346790635 |
| 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 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 127488 | 0x7fd1f8121380 | 0x7fd1f52257c0 | 15995346806165 | 15995346814785 | 15995346994466 | 15995346995841 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 296 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 129216 | 0x7fd1f8121200 | 0x7fd1f5225800 | 15995347010250 | 15995347018466 | 15995347198307 | 15995347199796 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 299 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 130944 | 0x7fd1f8121080 | 0x7fd1f5225840 | 15995347213536 | 15995347222467 | 15995347322467 | 15995347323964 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 302 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 133440 | 0x7fd1f59cbf00 | 0x7fd1f5225880 | 15995347340533 | 15995347348547 | 15995347504228 | 15995347505539 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 305 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 134912 | 0x7fd1f59cbd80 | 0x7fd1f52258c0 | 15995347526709 | 15995347537508 | 15995347633668 | 15995347635157 |
| 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 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 136896 | 0x7fd1f59cbc00 | 0x7fd1f5225900 | 15995347650886 | 15995347659108 | 15995347837989 | 15995347839462 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 311 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 138880 | 0x7fd1f59cba80 | 0x7fd1f5225940 | 15995347855032 | 15995347863269 | 15995348043590 | 15995348044968 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 314 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 140864 | 0x7fd1f59cb900 | 0x7fd1f5225980 | 15995348060447 | 15995348069030 | 15995348176871 | 15995348178385 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 317 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 143616 | 0x7fd1f59cb780 | 0x7fd1f52259c0 | 15995348192664 | 15995348201511 | 15995348372711 | 15995348374140 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 320 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 145344 | 0x7fd1f59cb600 | 0x7fd1f5225a00 | 15995348394630 | 15995348405191 | 15995348501032 | 15995348502247 |
| 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 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 147584 | 0x7fd1f8121480 | 0x7fd1f5225a40 | 15995348517277 | 15995348525672 | 15995348706313 | 15995348707683 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 326 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 149568 | 0x7fd1f8121300 | 0x7fd1f5225a80 | 15995348722033 | 15995348730793 | 15995348912554 | 15995348913918 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 329 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 151552 | 0x7fd1f8121180 | 0x7fd1f5225ac0 | 15995348929198 | 15995348937674 | 15995349048554 | 15995349049755 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 332 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 154304 | 0x7fd1f8121000 | 0x7fd1f5225b00 | 15995349066295 | 15995349074634 | 15995349256235 | 15995349257571 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 335 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 156288 | 0x7fd1f59cbe80 | 0x7fd1f5225b40 | 15995349281240 | 15995349290635 | 15995349392715 | 15995349394198 |
| 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 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 158784 | 0x7fd1f59cbd00 | 0x7fd1f5225b80 | 15995349410127 | 15995349418476 | 15995349604716 | 15995349605973 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 341 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 161024 | 0x7fd1f59cbb80 | 0x7fd1f5225bc0 | 15995349622343 | 15995349630316 | 15995349815117 | 15995349816558 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 344 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 163264 | 0x7fd1f59cba00 | 0x7fd1f5225c00 | 15995349832218 | 15995349840397 | 15995349962638 | 15995349963975 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 347 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 166528 | 0x7fd1f59cb880 | 0x7fd1f5225c40 | 15995349979595 | 15995349987598 | 15995350193999 | 15995350243349 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 350 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 168512 | 0x7fd1f59cb700 | 0x7fd1f5225c80 | 15995350260958 | 15995350271439 | 15995350382479 | 15995350383806 |
| 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 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 171264 | 0x7fd1f8121580 | 0x7fd1f5225cc0 | 15995350400585 | 15995350409200 | 15995350592080 | 15995350593471 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 356 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 173760 | 0x7fd1f8121400 | 0x7fd1f5225d00 | 15995350607151 | 15995350615280 | 15995350803921 | 15995350805366 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 359 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 176256 | 0x7fd1f8121280 | 0x7fd1f5225d40 | 15995350820766 | 15995350828881 | 15995350963762 | 15995350965143 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 362 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 179776 | 0x7fd1f8121100 | 0x7fd1f5225d80 | 15995350980052 | 15995350987922 | 15995351219923 | 15995351263786 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 365 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 182272 | 0x7fd1f59cbf80 | 0x7fd1f5225dc0 | 15995351280216 | 15995351291283 | 15995351418164 | 15995351419493 |
| 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 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 185536 | 0x7fd1f59cbe00 | 0x7fd1f5225e00 | 15995351436872 | 15995351444884 | 15995351635765 | 15995351637288 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 371 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 188544 | 0x7fd1f59cbc80 | 0x7fd1f5225e40 | 15995351651388 | 15995351660085 | 15995351853205 | 15995351854583 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 374 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 191552 | 0x7fd1f59cbb00 | 0x7fd1f5225e80 | 15995351869893 | 15995351878006 | 15995352038006 | 15995352039539 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 377 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 195840 | 0x7fd1f59cb980 | 0x7fd1f5225ec0 | 15995352054429 | 15995352062486 | 15995352346007 | 15995352390041 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 380 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 198592 | 0x7fd1f59cb800 | 0x7fd1f5225f00 | 15995352406931 | 15995352417528 | 15995352566648 | 15995352568047 |
| 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 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 202368 | 0x7fd1f59cb680 | 0x7fd1f5225f40 | 15995352583477 | 15995352591768 | 15995352799289 | 15995352842241 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 386 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 205888 | 0x7fd1f8121500 | 0x7fd1f5225f80 | 15995352850241 | 15995352860409 | 15995353066330 | 15995353085246 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 389 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 209408 | 0x7fd1f8121380 | 0x7fd1f5225fc0 | 15995353093736 | 15995353104250 | 15995353290331 | 15995353291731 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 392 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 214464 | 0x7fd1f8121200 | 0x7fd1f5226000 | 15995353306871 | 15995353314971 | 15995353649213 | 15995353665383 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 395 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 217728 | 0x7fd1f8121080 | 0x7fd1f5226040 | 15995353682023 | 15995353692573 | 15995353859774 | 15995353861089 |
| 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 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 222016 | 0x7fd1f59cbf00 | 0x7fd1f5226080 | 15995353876528 | 15995353884734 | 15995354113695 | 15995354137472 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 401 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 226048 | 0x7fd1f59cbd80 | 0x7fd1f52260c0 | 15995354147102 | 15995354157215 | 15995354386656 | 15995354428816 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 404 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 230080 | 0x7fd1f59cbc00 | 0x7fd1f5226100 | 15995354439936 | 15995354450496 | 15995354662177 | 15995354701580 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 407 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 235904 | 0x7fd1f59cba80 | 0x7fd1f5226140 | 15995354712730 | 15995354722017 | 15995355107459 | 15995355147090 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 410 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 239424 | 0x7fd1f59cb900 | 0x7fd1f5226180 | 15995355163979 | 15995355174659 | 15995355362020 | 15995355363235 |
| 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 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 244224 | 0x7fd1f59cb780 | 0x7fd1f52261c0 | 15995355379045 | 15995355387140 | 15995355636421 | 15995355675978 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 416 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 248768 | 0x7fd1f59cb600 | 0x7fd1f5226200 | 15995355685218 | 15995355695141 | 15995355943302 | 15995355986131 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 419 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 253312 | 0x7fd1f8121480 | 0x7fd1f5226240 | 15995355996761 | 15995356007142 | 15995356244423 | 15995356267555 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 422 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 8 | 24 | 255552 | 0x7fd1f8121300 | 0x7fd1f5226280 | 15995356277725 | 15995356288103 | 15995356741865 | 15995356785993 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 425 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 259840 | 0x7fd1f8121180 | 0x7fd1f52262c0 | 15995356803173 | 15995356813545 | 15995357039306 | 15995357055127 |
| 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 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 265664 | 0x7fd1f8121000 | 0x7fd1f5226300 | 15995357067207 | 15995357077867 | 15995357375628 | 15995357391660 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 431 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 271232 | 0x7fd1f59cbe80 | 0x7fd1f5226340 | 15995357402119 | 15995357411468 | 15995357710989 | 15995357729382 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 434 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 8 | 24 | 273216 | 0x7fd1f59cbd00 | 0x7fd1f5226380 | 15995357738462 | 15995357748589 | 15995358045230 | 15995358063555 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 437 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 8 | 24 | 275712 | 0x7fd1f59cbb80 | 0x7fd1f52263c0 | 15995358073924 | 15995358097071 | 15995358653553 | 15995358696021 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 440 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 280768 | 0x7fd1f59cba00 | 0x7fd1f5226400 | 15995358714500 | 15995358725073 | 15995358989394 | 15995359034053 |
| 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 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 287616 | 0x7fd1f59cb880 | 0x7fd1f5226440 | 15995359043413 | 15995359053555 | 15995359403636 | 15995359446404 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 446 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 294208 | 0x7fd1f59cb700 | 0x7fd1f5226480 | 15995359457794 | 15995359473876 | 15995359824598 | 15995359867055 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 449 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 8 | 24 | 296960 | 0x7fd1f8121580 | 0x7fd1f52264c0 | 15995359883594 | 15995359893878 | 15995360241399 | 15995360283905 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 452 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 8 | 24 | 299968 | 0x7fd1f8121400 | 0x7fd1f5226500 | 15995360292885 | 15995360303000 | 15995360963482 | 15995361006339 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 455 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 8 | 24 | 302720 | 0x7fd1f8121280 | 0x7fd1f5226540 | 15995361024289 | 15995361033723 | 15995361481564 | 15995361524238 |
| 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 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 305472 | 0x7fd1f8121100 | 0x7fd1f5226580 | 15995361534758 | 15995361545085 | 15995362009726 | 15995362025627 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 461 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 308224 | 0x7fd1f59cbf80 | 0x7fd1f52265c0 | 15995362036727 | 15995362047007 | 15995362508769 | 15995362556425 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 464 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 8 | 24 | 310976 | 0x7fd1f59cbe00 | 0x7fd1f5226600 | 15995362565265 | 15995362575489 | 15995363027331 | 15995363072133 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 467 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 8 | 24 | 313216 | 0x7fd1f59cbc80 | 0x7fd1f5226640 | 15995363080773 | 15995363090851 | 15995363960774 | 15995364010593 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 470 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 8 | 24 | 315968 | 0x7fd1f59cbb00 | 0x7fd1f5226680 | 15995364027592 | 15995364038215 | 15995364891178 | 15995364938182 |
| 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 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 318720 | 0x7fd1f59cb980 | 0x7fd1f52266c0 | 15995364948132 | 15995364958698 | 15995365844462 | 15995365893200 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 476 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 321472 | 0x7fd1f59cb800 | 0x7fd1f5226700 | 15995365903220 | 15995365913422 | 15995366792626 | 15995366841879 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 479 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 8 | 24 | 324224 | 0x7fd1f59cb680 | 0x7fd1f5226740 | 15995366852859 | 15995366870386 | 15995367731030 | 15995367778179 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 482 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 8 | 24 | 326464 | 0x7fd1f8121500 | 0x7fd1f5226780 | 15995367788128 | 15995367798070 | 15995369496317 | 15995369562099 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 485 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 8 | 24 | 329216 | 0x7fd1f8121380 | 0x7fd1f52267c0 | 15995369579819 | 15995369590237 | 15995371255684 | 15995371325750 |
| 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 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 331968 | 0x7fd1f8121200 | 0x7fd1f5226800 | 15995371337600 | 15995371354724 | 15995373081131 | 15995373155739 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 491 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 12 | 24 | 334720 | 0x7fd1f8121080 | 0x7fd1f5226840 | 15995373167089 | 15995373218252 | 15995374934259 | 15995375005218 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 494 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 8 | 24 | 337472 | 0x7fd1f59cbf00 | 0x7fd1f5226880 | 15995375015768 | 15995375025939 | 15995376700026 | 15995376772119 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 497 | 143037 | 143037 | 4194304 | 256 | 0 | 0 | 8 | 24 | 0 | 0x7fd1f59cbd80 | 0x7fd1f52268c0 | 15995376781339 | 15995376793466 | 15995380151560 | 15995380222812 |