44 KiB
44 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | GRBM_COUNT | GRBM_GUI_ACTIVE | SQ_WAVES | SQ_IFETCH | SQ_IFETCH_LEVEL | SQ_ACCUM_PREV_HIRES | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBufferAligned.kd | 0 | 0 | 0 | 169067 | 169067 | 33554432 | 256 | 0 | 0 | 4 | 32 | 4160 | 0x0 | 0x7fc9f1804280 | 381054 | 381054 | 524288 | 4718592 | 685018 | 76662440 | 16686012409410 | 16685335266624 | 16686159441316 | 16686159553545 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 169067 | 169067 | 32768 | 256 | 0 | 0 | 12 | 24 | 13888 | 0x0 | 0x7fc9f1823f80 | 33513 | 33513 | 512 | 8192 | 6059 | 684380 | 16686164716134 | 16686159441316 | 16686164845446 | 16686164850159 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 5 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 14336 | 0x7fc9f4757380 | 0x7fc9f1823fc0 | 163951 | 163951 | 65536 | 917504 | 140001 | 15721348 | 16686164888588 | 16686164845446 | 16686165220003 | 16686165222817 |
| 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 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15040 | 0x7fc9f4757200 | 0x7fc9f1824000 | 310083 | 310083 | 65536 | 1114112 | 169884 | 19005140 | 16686165261276 | 16686165220003 | 16686165633761 | 16686165636313 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 11 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15488 | 0x7fc9f4757080 | 0x7fc9f1824040 | 309152 | 309152 | 65536 | 917504 | 140014 | 15628252 | 16686165672022 | 16686165633761 | 16686166039839 | 16686166042350 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 14 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 15936 | 0x7fc9f2103f00 | 0x7fc9f1824080 | 164822 | 164822 | 65536 | 1048576 | 159407 | 17843760 | 16686166098478 | 16686166039839 | 16686166372797 | 16686166375239 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 17 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 16384 | 0x7fc9f2103d80 | 0x7fc9f18240c0 | 163906 | 163906 | 65536 | 983040 | 147816 | 16557064 | 16686166409467 | 16686166372797 | 16686166692635 | 16686166695048 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 20 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 17088 | 0x7fc9f2103c00 | 0x7fc9f1824100 | 162246 | 162246 | 65536 | 1114112 | 163766 | 18246884 | 16686166742936 | 16686166692635 | 16686167007834 | 16686167010237 |
| 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 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 16 | 24 | 17792 | 0x7fc9f2103a80 | 0x7fc9f1824140 | 307900 | 307900 | 65536 | 1310720 | 195284 | 21914784 | 16686167045306 | 16686167007834 | 16686167413911 | 16686167416254 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 26 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 16 | 24 | 18496 | 0x7fc9f2103900 | 0x7fc9f1824180 | 306424 | 306424 | 65536 | 1179648 | 178482 | 19980932 | 16686167449903 | 16686167413911 | 16686167828149 | 16686167830530 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 29 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19200 | 0x7fc9f2103780 | 0x7fc9f18241c0 | 163956 | 163956 | 65536 | 1245184 | 189598 | 21215412 | 16686167864699 | 16686167828149 | 16686168141588 | 16686168143880 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 32 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19904 | 0x7fc9f2103600 | 0x7fc9f1824200 | 164216 | 164216 | 65536 | 1245184 | 201862 | 22624016 | 16686168179769 | 16686168141588 | 16686168453906 | 16686168456409 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 35 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 20608 | 0x7fc9f4757480 | 0x7fc9f1824240 | 164169 | 164169 | 65536 | 1245184 | 188901 | 21110328 | 16686168499778 | 16686168453906 | 16686168769104 | 16686168771389 |
| 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 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 16 | 24 | 21312 | 0x7fc9f4757300 | 0x7fc9f1824280 | 307884 | 307884 | 65536 | 1441792 | 216128 | 24180076 | 16686168808218 | 16686168769104 | 16686169170862 | 16686169173236 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 41 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22016 | 0x7fc9f4757180 | 0x7fc9f18242c0 | 307907 | 307907 | 65536 | 1310720 | 198180 | 22172136 | 16686169209064 | 16686169170862 | 16686169572780 | 16686169575212 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 44 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22720 | 0x7fc9f4757000 | 0x7fc9f1824300 | 164004 | 164004 | 65536 | 1376256 | 205947 | 23084932 | 16686169610821 | 16686169572780 | 16686169888298 | 16686169890582 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 47 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 23424 | 0x7fc9f2103e80 | 0x7fc9f1824340 | 162871 | 162871 | 65536 | 1441792 | 215590 | 24139364 | 16686169926481 | 16686169888298 | 16686170212456 | 16686170214951 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 50 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 24128 | 0x7fc9f2103d00 | 0x7fc9f1824380 | 162146 | 162146 | 65536 | 1310720 | 195793 | 21875544 | 16686170256850 | 16686170212456 | 16686170543814 | 16686170545550 |
| 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 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 16 | 24 | 24832 | 0x7fc9f2103b80 | 0x7fc9f18243c0 | 308773 | 308773 | 65536 | 1572864 | 234983 | 26324552 | 16686170581839 | 16686170543814 | 16686170921252 | 16686170923038 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 56 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 16 | 24 | 25536 | 0x7fc9f2103a00 | 0x7fc9f1824400 | 305726 | 305726 | 65536 | 1441792 | 209527 | 23463508 | 16686170958746 | 16686170921252 | 16686171296930 | 16686171298695 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 59 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26240 | 0x7fc9f2103880 | 0x7fc9f1824440 | 163338 | 163338 | 65536 | 1507328 | 224780 | 25204448 | 16686171334004 | 16686171296930 | 16686171582209 | 16686171583936 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 62 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26944 | 0x7fc9f2103700 | 0x7fc9f1824480 | 162599 | 162599 | 65536 | 1638400 | 244764 | 27420720 | 16686171620104 | 16686171582209 | 16686171867167 | 16686171868846 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 65 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 27648 | 0x7fc9f4757580 | 0x7fc9f18244c0 | 162494 | 162494 | 65536 | 1441792 | 221482 | 24845740 | 16686171911635 | 16686171867167 | 16686172158846 | 16686172160617 |
| 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 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 16 | 24 | 28608 | 0x7fc9f4757400 | 0x7fc9f1824500 | 306413 | 306413 | 65536 | 1703936 | 253845 | 28359880 | 16686172196515 | 16686172158846 | 16686172532763 | 16686172534524 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 71 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 16 | 24 | 29312 | 0x7fc9f4757280 | 0x7fc9f1824540 | 306518 | 306518 | 65536 | 1572864 | 232958 | 26160708 | 16686172570643 | 16686172532763 | 16686172908441 | 16686172910252 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 74 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 30016 | 0x7fc9f4757100 | 0x7fc9f1824580 | 162428 | 162428 | 65536 | 1638400 | 249461 | 27877488 | 16686172945300 | 16686172908441 | 16686173198360 | 16686173200042 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 77 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 8 | 24 | 30976 | 0x7fc9f2103f80 | 0x7fc9f18245c0 | 162776 | 162776 | 65536 | 1835008 | 273524 | 30654420 | 16686173235881 | 16686173198360 | 16686173487318 | 16686173489092 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 80 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 31680 | 0x7fc9f2103e00 | 0x7fc9f1824600 | 162441 | 162441 | 65536 | 1507328 | 224964 | 25114808 | 16686173531111 | 16686173487318 | 16686173776437 | 16686173778313 |
| 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 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 16 | 24 | 32640 | 0x7fc9f2103c80 | 0x7fc9f1824640 | 305970 | 305970 | 65536 | 1835008 | 291541 | 32577752 | 16686173813572 | 16686173776437 | 16686174155795 | 16686174157780 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 86 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 33600 | 0x7fc9f2103b00 | 0x7fc9f1824680 | 308559 | 308559 | 65536 | 1703936 | 247908 | 27850440 | 16686174193209 | 16686174155795 | 16686174535633 | 16686174537328 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 89 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 34560 | 0x7fc9f2103980 | 0x7fc9f18246c0 | 162824 | 162824 | 65536 | 1769472 | 264517 | 29658720 | 16686174573066 | 16686174535633 | 16686174826511 | 16686174828228 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 92 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 8 | 24 | 35520 | 0x7fc9f2103800 | 0x7fc9f1824700 | 163059 | 163059 | 65536 | 2031616 | 303585 | 33961012 | 16686174863047 | 16686174826511 | 16686175131629 | 16686175133438 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 95 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 36224 | 0x7fc9f2103680 | 0x7fc9f1824740 | 162458 | 162458 | 65536 | 1638400 | 245525 | 27583288 | 16686175176206 | 16686175131629 | 16686175427468 | 16686175429178 |
| 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 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 37184 | 0x7fc9f4757500 | 0x7fc9f1824780 | 305589 | 305589 | 65536 | 1966080 | 289224 | 32326480 | 16686175463817 | 16686175427468 | 16686175808426 | 16686175810135 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 101 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 38144 | 0x7fc9f4757380 | 0x7fc9f18247c0 | 303470 | 303470 | 65536 | 1835008 | 271868 | 30483516 | 16686175845874 | 16686175808426 | 16686176180744 | 16686176182443 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 104 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 39104 | 0x7fc9f4757200 | 0x7fc9f1824800 | 162329 | 162329 | 65536 | 1900544 | 282413 | 31633160 | 16686176217352 | 16686176180744 | 16686176467782 | 16686176469584 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 107 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 8 | 24 | 40320 | 0x7fc9f4757080 | 0x7fc9f1824840 | 163628 | 163628 | 65536 | 2228224 | 327854 | 36731724 | 16686176505122 | 16686176467782 | 16686176757220 | 16686176759034 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 110 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 41280 | 0x7fc9f2103f00 | 0x7fc9f1824880 | 161672 | 161672 | 65536 | 1703936 | 253635 | 28405824 | 16686176801443 | 16686176757220 | 16686177046339 | 16686177048094 |
| 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 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 42240 | 0x7fc9f2103d80 | 0x7fc9f18248c0 | 305636 | 305636 | 65536 | 2097152 | 310877 | 34788692 | 16686177083903 | 16686177046339 | 16686177422657 | 16686177424432 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 116 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 43200 | 0x7fc9f2103c00 | 0x7fc9f1824900 | 302294 | 302294 | 65536 | 1966080 | 283775 | 31768056 | 16686177460351 | 16686177422657 | 16686177805695 | 16686177807469 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 119 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 8 | 24 | 44160 | 0x7fc9f2103a80 | 0x7fc9f1824940 | 162194 | 162194 | 65536 | 2031616 | 300976 | 33809536 | 16686177842868 | 16686177805695 | 16686178094173 | 16686178096040 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 122 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 45376 | 0x7fc9f2103900 | 0x7fc9f1824980 | 162410 | 162410 | 65536 | 2424832 | 361536 | 40464544 | 16686178131688 | 16686178094173 | 16686178391771 | 16686178393610 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 125 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 46336 | 0x7fc9f2103780 | 0x7fc9f18249c0 | 161116 | 161116 | 65536 | 1835008 | 274350 | 30747848 | 16686178435028 | 16686178391771 | 16686178685210 | 16686178686910 |
| 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 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 47552 | 0x7fc9f2103600 | 0x7fc9f1824a00 | 305298 | 305298 | 65536 | 2228224 | 327865 | 36731928 | 16686178723869 | 16686178685210 | 16686179061528 | 16686179063287 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 131 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 48512 | 0x7fc9f4757480 | 0x7fc9f1824a40 | 300591 | 300591 | 65536 | 2097152 | 310272 | 34761888 | 16686179099646 | 16686179061528 | 16686179436246 | 16686179437925 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 134 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 8 | 24 | 49472 | 0x7fc9f4757300 | 0x7fc9f1824a80 | 160864 | 160864 | 65536 | 2162688 | 320122 | 35863748 | 16686179473684 | 16686179436246 | 16686179724564 | 16686179726385 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 137 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 50688 | 0x7fc9f4757180 | 0x7fc9f1824ac0 | 161741 | 161741 | 65536 | 2621440 | 386552 | 43306744 | 16686179762224 | 16686179724564 | 16686180013683 | 16686180015606 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 140 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 51648 | 0x7fc9f4757000 | 0x7fc9f1824b00 | 160740 | 160740 | 65536 | 1966080 | 292896 | 32783672 | 16686180057984 | 16686180013683 | 16686180303281 | 16686180305066 |
| 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 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 52864 | 0x7fc9f2103e80 | 0x7fc9f1824b40 | 302233 | 302233 | 65536 | 2359296 | 358466 | 40115212 | 16686180342825 | 16686180303281 | 16686180678479 | 16686180680234 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 146 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 54080 | 0x7fc9f2103d00 | 0x7fc9f1824b80 | 301646 | 301646 | 65536 | 2228224 | 336125 | 37664924 | 16686180715293 | 16686180678479 | 16686181055917 | 16686181057641 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 149 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 8 | 24 | 55296 | 0x7fc9f2103b80 | 0x7fc9f1824bc0 | 161783 | 161783 | 65536 | 2293760 | 344546 | 38528176 | 16686181092240 | 16686181055917 | 16686181344875 | 16686181346662 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 152 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 56768 | 0x7fc9f2103a00 | 0x7fc9f1824c00 | 162177 | 162177 | 65536 | 2752512 | 407048 | 45663208 | 16686181382530 | 16686181344875 | 16686181641834 | 16686181643582 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 155 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 57728 | 0x7fc9f2103880 | 0x7fc9f1824c40 | 162483 | 162483 | 65536 | 2031616 | 317854 | 35515132 | 16686181686040 | 16686181641834 | 16686181937192 | 16686181938842 |
| 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 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 58944 | 0x7fc9f2103700 | 0x7fc9f1824c80 | 301817 | 301817 | 65536 | 2490368 | 367373 | 41059096 | 16686181974611 | 16686181937192 | 16686182321670 | 16686182323429 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 161 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 60160 | 0x7fc9f4757580 | 0x7fc9f1824cc0 | 300679 | 300679 | 65536 | 2359296 | 360271 | 40357568 | 16686182359468 | 16686182321670 | 16686182700228 | 16686182702107 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 164 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 8 | 24 | 61376 | 0x7fc9f4757400 | 0x7fc9f1824d00 | 162833 | 162833 | 65536 | 2424832 | 377747 | 42293108 | 16686182737345 | 16686182700228 | 16686182986786 | 16686182988497 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 167 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 62848 | 0x7fc9f4757280 | 0x7fc9f1824d40 | 168659 | 168659 | 65536 | 2949120 | 444498 | 49834428 | 16686183023966 | 16686182986786 | 16686183279265 | 16686183280967 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 170 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 63808 | 0x7fc9f4757100 | 0x7fc9f1824d80 | 162539 | 162539 | 65536 | 2162688 | 340243 | 38129768 | 16686183324346 | 16686183279265 | 16686183578783 | 16686183580588 |
| 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 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 65024 | 0x7fc9f2103f80 | 0x7fc9f1824dc0 | 300168 | 300168 | 65536 | 2621440 | 388151 | 43458216 | 16686183616596 | 16686183578783 | 16686183962781 | 16686183964555 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 176 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 66240 | 0x7fc9f2103e00 | 0x7fc9f1824e00 | 299830 | 299830 | 65536 | 2490368 | 361783 | 40565560 | 16686184000554 | 16686183962781 | 16686184338139 | 16686184339992 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 179 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 8 | 24 | 67456 | 0x7fc9f2103c80 | 0x7fc9f1824e40 | 162660 | 162660 | 65536 | 2555904 | 383449 | 42911740 | 16686184374881 | 16686184338139 | 16686184628857 | 16686184630583 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 182 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 68928 | 0x7fc9f2103b00 | 0x7fc9f1824e80 | 175444 | 175444 | 65536 | 3145728 | 465423 | 52198752 | 16686184665901 | 16686184628857 | 16686184926296 | 16686184928093 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 185 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 70144 | 0x7fc9f2103980 | 0x7fc9f1824ec0 | 160181 | 160181 | 65536 | 2228224 | 341354 | 38232116 | 16686184971171 | 16686184926296 | 16686185211894 | 16686185213593 |
| 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 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 71616 | 0x7fc9f2103800 | 0x7fc9f1824f00 | 300336 | 300336 | 65536 | 2752512 | 405883 | 45476588 | 16686185248282 | 16686185211894 | 16686185587412 | 16686185589181 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 191 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 72832 | 0x7fc9f2103680 | 0x7fc9f1824f40 | 299474 | 299474 | 65536 | 2621440 | 388842 | 43547368 | 16686185624880 | 16686185587412 | 16686185958930 | 16686185960719 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 194 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 8 | 24 | 74048 | 0x7fc9f4757500 | 0x7fc9f1824f80 | 161056 | 161056 | 65536 | 2686976 | 397866 | 44646512 | 16686185995227 | 16686185958930 | 16686186259088 | 16686186261309 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 197 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 75776 | 0x7fc9f4757380 | 0x7fc9f1824fc0 | 182890 | 182890 | 65536 | 3342336 | 519050 | 58002888 | 16686186296627 | 16686186259088 | 16686186571567 | 16686186573408 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 200 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 76992 | 0x7fc9f4757200 | 0x7fc9f1825000 | 161591 | 161591 | 65536 | 2359296 | 357077 | 40012864 | 16686186624826 | 16686186571567 | 16686186862765 | 16686186864509 |
| 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 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 78464 | 0x7fc9f4757080 | 0x7fc9f1825040 | 298618 | 298618 | 65536 | 2883584 | 428904 | 48042264 | 16686186900157 | 16686186862765 | 16686187238763 | 16686187240566 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 206 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 79936 | 0x7fc9f2103f00 | 0x7fc9f1825080 | 300338 | 300338 | 65536 | 2686976 | 417781 | 46774628 | 16686187275725 | 16686187238763 | 16686187616041 | 16686187617784 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 209 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 8 | 24 | 81408 | 0x7fc9f2103d80 | 0x7fc9f18250c0 | 163309 | 163309 | 65536 | 2818048 | 415664 | 46508680 | 16686187653132 | 16686187616041 | 16686187905479 | 16686187907324 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 212 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 83136 | 0x7fc9f2103c00 | 0x7fc9f1825100 | 192018 | 192018 | 65536 | 3538944 | 536626 | 60077124 | 16686187943403 | 16686187905479 | 16686188212998 | 16686188214854 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 215 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 84352 | 0x7fc9f2103a80 | 0x7fc9f1825140 | 160926 | 160926 | 65536 | 2424832 | 363817 | 40842080 | 16686188256732 | 16686188212998 | 16686188504356 | 16686188506114 |
| 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 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 85824 | 0x7fc9f2103900 | 0x7fc9f1825180 | 299790 | 299790 | 65536 | 3014656 | 461455 | 51680604 | 16686188540493 | 16686188504356 | 16686188882434 | 16686188884391 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 221 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 87296 | 0x7fc9f2103780 | 0x7fc9f18251c0 | 298812 | 298812 | 65536 | 2818048 | 415986 | 46583756 | 16686188919440 | 16686188882434 | 16686189256352 | 16686189258069 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 224 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 88768 | 0x7fc9f2103600 | 0x7fc9f1825200 | 162326 | 162326 | 65536 | 2949120 | 443025 | 49596680 | 16686189293778 | 16686189256352 | 16686189547550 | 16686189549409 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 227 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 90752 | 0x7fc9f4757480 | 0x7fc9f1825240 | 202142 | 202142 | 65536 | 3735552 | 566459 | 63464532 | 16686189585008 | 16686189547550 | 16686189863389 | 16686189865199 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 230 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 91968 | 0x7fc9f4757300 | 0x7fc9f1825280 | 161864 | 161864 | 65536 | 2555904 | 386725 | 43294324 | 16686189907578 | 16686189863389 | 16686190160827 | 16686190162729 |
| 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 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 93440 | 0x7fc9f4757180 | 0x7fc9f18252c0 | 300374 | 300374 | 65536 | 3145728 | 480761 | 53859652 | 16686190198808 | 16686190160827 | 16686190540025 | 16686190541866 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 236 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 94912 | 0x7fc9f4757000 | 0x7fc9f1825300 | 300008 | 300008 | 65536 | 2949120 | 434812 | 48681772 | 16686190577785 | 16686190540025 | 16686190914103 | 16686190915914 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 239 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 96384 | 0x7fc9f2103e80 | 0x7fc9f1825340 | 162029 | 162029 | 65536 | 3080192 | 463058 | 51937312 | 16686190951023 | 16686190914103 | 16686191206741 | 16686191208564 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 242 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 98368 | 0x7fc9f2103d00 | 0x7fc9f1825380 | 211228 | 211228 | 65536 | 3932160 | 589047 | 65900400 | 16686191243783 | 16686191206741 | 16686191537140 | 16686191538993 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 245 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 99584 | 0x7fc9f2103b80 | 0x7fc9f18253c0 | 161258 | 161258 | 65536 | 2621440 | 390349 | 43722460 | 16686191581012 | 16686191537140 | 16686191830098 | 16686191831934 |
| 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 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 101312 | 0x7fc9f2103a00 | 0x7fc9f1825400 | 301225 | 301225 | 65536 | 3276800 | 488339 | 54695576 | 16686191865703 | 16686191830098 | 16686192209296 | 16686192211011 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 251 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 102784 | 0x7fc9f2103880 | 0x7fc9f1825440 | 296850 | 296850 | 65536 | 3080192 | 454025 | 50793364 | 16686192246600 | 16686192209296 | 16686192582254 | 16686192584009 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 254 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 104256 | 0x7fc9f2103700 | 0x7fc9f1825480 | 161111 | 161111 | 65536 | 3211264 | 480934 | 53811768 | 16686192618558 | 16686192582254 | 16686192871692 | 16686192873439 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 257 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 106240 | 0x7fc9f4757580 | 0x7fc9f18254c0 | 219576 | 219576 | 65536 | 4128768 | 619618 | 69301500 | 16686192909238 | 16686192871692 | 16686193197610 | 16686193199418 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 260 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 107712 | 0x7fc9f4757400 | 0x7fc9f1825500 | 160605 | 160605 | 65536 | 2752512 | 411601 | 46077096 | 16686193242477 | 16686193197610 | 16686193485129 | 16686193487019 |
| 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 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 16 | 24 | 109440 | 0x7fc9f4757280 | 0x7fc9f1825540 | 298856 | 298856 | 65536 | 3407872 | 505938 | 56716376 | 16686193521968 | 16686193485129 | 16686193860327 | 16686193862086 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 266 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 16 | 24 | 111168 | 0x7fc9f4757100 | 0x7fc9f1825580 | 297087 | 297087 | 65536 | 3211264 | 478283 | 53615288 | 16686193897305 | 16686193860327 | 16686194236965 | 16686194238984 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 269 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 8 | 24 | 112896 | 0x7fc9f2103f80 | 0x7fc9f18255c0 | 161996 | 161996 | 65536 | 3276800 | 500798 | 56076964 | 16686194275333 | 16686194236965 | 16686194528643 | 16686194530374 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 272 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 115136 | 0x7fc9f2103e00 | 0x7fc9f1825600 | 229905 | 229905 | 65536 | 4325376 | 647067 | 72559828 | 16686194566203 | 16686194528643 | 16686194858721 | 16686194860473 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 275 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 116608 | 0x7fc9f2103c80 | 0x7fc9f1825640 | 161778 | 161778 | 65536 | 2818048 | 426471 | 47655168 | 16686194903692 | 16686194858721 | 16686195152480 | 16686195154383 |
| 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 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 16 | 24 | 118336 | 0x7fc9f2103b00 | 0x7fc9f1825680 | 295635 | 295635 | 65536 | 3538944 | 537190 | 60213456 | 16686195188872 | 16686195152480 | 16686195522558 | 16686195524211 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 281 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 16 | 24 | 120064 | 0x7fc9f2103980 | 0x7fc9f18256c0 | 298972 | 298972 | 65536 | 3407872 | 503568 | 56378500 | 16686195559520 | 16686195522558 | 16686195897276 | 16686195899099 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 284 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 121792 | 0x7fc9f2103800 | 0x7fc9f1825700 | 162661 | 162661 | 65536 | 3407872 | 518315 | 58045172 | 16686195934827 | 16686195897276 | 16686196189434 | 16686196191269 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 287 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 124032 | 0x7fc9f2103680 | 0x7fc9f1825740 | 238287 | 238287 | 65536 | 4521984 | 682840 | 76421792 | 16686196227708 | 16686196189434 | 16686196527992 | 16686196529798 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 290 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 125504 | 0x7fc9f4757500 | 0x7fc9f1825780 | 160587 | 160587 | 65536 | 3014656 | 448942 | 50363280 | 16686196572046 | 16686196527992 | 16686196815351 | 16686196817138 |
| 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 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 127488 | 0x7fc9f4757380 | 0x7fc9f18257c0 | 298481 | 298481 | 65536 | 3801088 | 574149 | 64275412 | 16686196851997 | 16686196815351 | 16686197194869 | 16686197196656 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 296 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 129216 | 0x7fc9f4757200 | 0x7fc9f1825800 | 298117 | 298117 | 65536 | 3670016 | 563662 | 63063592 | 16686197232044 | 16686197194869 | 16686197568787 | 16686197570573 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 299 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 130944 | 0x7fc9f4757080 | 0x7fc9f1825840 | 169373 | 169373 | 65536 | 3670016 | 543603 | 60801148 | 16686197606702 | 16686197568787 | 16686197862705 | 16686197864543 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 302 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 133440 | 0x7fc9f2103f00 | 0x7fc9f1825880 | 259247 | 259247 | 65536 | 4915200 | 738048 | 82735624 | 16686197899332 | 16686197862705 | 16686198212143 | 16686198214002 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 305 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 134912 | 0x7fc9f2103d80 | 0x7fc9f18258c0 | 160175 | 160175 | 65536 | 3145728 | 465689 | 52160452 | 16686198257940 | 16686198212143 | 16686198514061 | 16686198515852 |
| 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 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 136896 | 0x7fc9f2103c00 | 0x7fc9f1825900 | 297443 | 297443 | 65536 | 4063232 | 602369 | 67371372 | 16686198550461 | 16686198514061 | 16686198887019 | 16686198888779 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 311 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 138880 | 0x7fc9f2103a80 | 0x7fc9f1825940 | 296591 | 296591 | 65536 | 3932160 | 584545 | 65441972 | 16686198924248 | 16686198887019 | 16686199259177 | 16686199261047 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 314 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 140864 | 0x7fc9f2103900 | 0x7fc9f1825980 | 178891 | 178891 | 65536 | 3932160 | 591701 | 66247568 | 16686199295676 | 16686199259177 | 16686199564456 | 16686199566237 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 317 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 143616 | 0x7fc9f2103780 | 0x7fc9f18259c0 | 279540 | 279540 | 65536 | 5308416 | 796830 | 89389248 | 16686199601406 | 16686199564456 | 16686199928134 | 16686199929935 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 320 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 145344 | 0x7fc9f2103600 | 0x7fc9f1825a00 | 161676 | 161676 | 65536 | 3342336 | 497506 | 55678256 | 16686199972903 | 16686199928134 | 16686200225572 | 16686200227295 |
| 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 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 147584 | 0x7fc9f4757480 | 0x7fc9f1825a40 | 295996 | 295996 | 65536 | 4325376 | 650468 | 72882136 | 16686200262734 | 16686200225572 | 16686200602370 | 16686200604113 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 326 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 149568 | 0x7fc9f4757300 | 0x7fc9f1825a80 | 293336 | 293336 | 65536 | 4194304 | 643844 | 72157912 | 16686200639871 | 16686200602370 | 16686200974048 | 16686200975930 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 329 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 151552 | 0x7fc9f4757180 | 0x7fc9f1825ac0 | 186046 | 186046 | 65536 | 4194304 | 632382 | 70858524 | 16686201011199 | 16686200974048 | 16686201280926 | 16686201282740 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 332 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 154304 | 0x7fc9f4757000 | 0x7fc9f1825b00 | 300430 | 300430 | 65536 | 5701632 | 856650 | 95964956 | 16686201318379 | 16686201280926 | 16686201658524 | 16686201660337 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 335 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 156288 | 0x7fc9f2103e80 | 0x7fc9f1825b40 | 170900 | 170900 | 65536 | 3735552 | 555032 | 62156200 | 16686201702446 | 16686201658524 | 16686201956443 | 16686201958338 |
| 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 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 158784 | 0x7fc9f2103d00 | 0x7fc9f1825b80 | 298064 | 298064 | 65536 | 4849664 | 779883 | 87278552 | 16686201992816 | 16686201956443 | 16686202341720 | 16686202343435 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 341 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 161024 | 0x7fc9f2103b80 | 0x7fc9f1825bc0 | 297832 | 297832 | 65536 | 4718592 | 732178 | 81966240 | 16686202379064 | 16686202341720 | 16686202723958 | 16686202725762 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 344 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 163264 | 0x7fc9f2103a00 | 0x7fc9f1825c00 | 207072 | 207072 | 65536 | 4718592 | 736122 | 82352036 | 16686202760981 | 16686202723958 | 16686203042197 | 16686203044072 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 347 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 166528 | 0x7fc9f2103880 | 0x7fc9f1825c40 | 339770 | 339770 | 65536 | 6488064 | 988952 | 110753632 | 16686203079140 | 16686203042197 | 16686203443634 | 16686203489327 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 350 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 168512 | 0x7fc9f2103700 | 0x7fc9f1825c80 | 183934 | 183934 | 65536 | 4128768 | 636417 | 71340100 | 16686203510526 | 16686203443634 | 16686203778673 | 16686203780507 |
| 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 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 171264 | 0x7fc9f4757580 | 0x7fc9f1825cc0 | 296506 | 296506 | 65536 | 5373952 | 834708 | 93511712 | 16686203816456 | 16686203778673 | 16686204155631 | 16686204157245 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 356 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 173760 | 0x7fc9f4757400 | 0x7fc9f1825d00 | 298081 | 298081 | 65536 | 5242880 | 827626 | 92733172 | 16686204192383 | 16686204155631 | 16686204539308 | 16686204541112 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 359 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 176256 | 0x7fc9f4757280 | 0x7fc9f1825d40 | 225237 | 225237 | 65536 | 5242880 | 786285 | 88080172 | 16686204576011 | 16686204539308 | 16686204871467 | 16686204873241 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 362 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 179776 | 0x7fc9f4757100 | 0x7fc9f1825d80 | 380596 | 380596 | 65536 | 7274496 | 1149452 | 128750904 | 16686204908350 | 16686204871467 | 16686205305384 | 16686205325336 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 365 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 182272 | 0x7fc9f2103f80 | 0x7fc9f1825dc0 | 211303 | 211303 | 65536 | 4915200 | 744505 | 83346260 | 16686205350075 | 16686205305384 | 16686205645382 | 16686205647235 |
| 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 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 185536 | 0x7fc9f2103e00 | 0x7fc9f1825e00 | 304548 | 304548 | 65536 | 6422528 | 1035333 | 115962404 | 16686205683264 | 16686205645382 | 16686206036900 | 16686206039232 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 371 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 188544 | 0x7fc9f2103c80 | 0x7fc9f1825e40 | 312770 | 312770 | 65536 | 6291456 | 1025873 | 114830972 | 16686206073761 | 16686206036900 | 16686206431618 | 16686206479998 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 374 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 191552 | 0x7fc9f2103b00 | 0x7fc9f1825e80 | 265701 | 265701 | 65536 | 6291456 | 954095 | 106847920 | 16686206492427 | 16686206431618 | 16686206820416 | 16686206822136 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 377 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 195840 | 0x7fc9f2103980 | 0x7fc9f1825ec0 | 461221 | 461221 | 65536 | 8847360 | 1336267 | 149610028 | 16686206858045 | 16686206820416 | 16686207299293 | 16686207345179 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 380 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 198592 | 0x7fc9f2103800 | 0x7fc9f1825f00 | 243241 | 243241 | 65536 | 5701632 | 862682 | 96537616 | 16686207365068 | 16686207299293 | 16686207675771 | 16686207677488 |
| 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 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 202368 | 0x7fc9f2103680 | 0x7fc9f1825f40 | 333259 | 333259 | 65536 | 7471104 | 1161176 | 129861880 | 16686207714667 | 16686207675771 | 16686208080089 | 16686208125553 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 386 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 205888 | 0x7fc9f4757500 | 0x7fc9f1825f80 | 331653 | 331653 | 65536 | 7340032 | 1155469 | 129432736 | 16686208136263 | 16686208080089 | 16686208516087 | 16686208558569 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 389 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 209408 | 0x7fc9f4757380 | 0x7fc9f1825fc0 | 306261 | 306261 | 65536 | 7340032 | 1125931 | 125910116 | 16686208570218 | 16686208516087 | 16686208935924 | 16686208937786 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 392 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 214464 | 0x7fc9f4757200 | 0x7fc9f1826000 | 543704 | 543704 | 65536 | 10420224 | 1589361 | 178085460 | 16686208973815 | 16686208935924 | 16686209465841 | 16686209509257 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 395 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 217728 | 0x7fc9f4757080 | 0x7fc9f1826040 | 272548 | 272548 | 65536 | 6488064 | 999696 | 111878772 | 16686209530026 | 16686209465841 | 16686209857359 | 16686209859235 |
| 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 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 222016 | 0x7fc9f2103f00 | 0x7fc9f1826080 | 367785 | 367785 | 65536 | 8519680 | 1366598 | 152971800 | 16686209894094 | 16686209857359 | 16686210284077 | 16686210330420 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 401 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 226048 | 0x7fc9f2103d80 | 0x7fc9f18260c0 | 364803 | 364803 | 65536 | 8388608 | 1318416 | 147741864 | 16686210342539 | 16686210284077 | 16686210745514 | 16686210790405 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 404 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 230080 | 0x7fc9f2103c00 | 0x7fc9f1826100 | 347802 | 347802 | 65536 | 8388608 | 1291010 | 144566928 | 16686210802414 | 16686210745514 | 16686211181672 | 16686211223770 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 407 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 235904 | 0x7fc9f2103a80 | 0x7fc9f1826140 | 624303 | 624303 | 65536 | 11993088 | 1847123 | 206837168 | 16686211236360 | 16686211181672 | 16686211789669 | 16686211831850 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 410 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 239424 | 0x7fc9f2103900 | 0x7fc9f1826180 | 304471 | 304471 | 65536 | 7274496 | 1129345 | 126495716 | 16686211851070 | 16686211789669 | 16686212201347 | 16686212203088 |
| 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 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 244224 | 0x7fc9f2103780 | 0x7fc9f18261c0 | 396881 | 396881 | 65536 | 9568256 | 1513365 | 169506116 | 16686212239907 | 16686212201347 | 16686212644544 | 16686212687352 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 416 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 248768 | 0x7fc9f2103600 | 0x7fc9f1826200 | 390594 | 390594 | 65536 | 9437184 | 1512643 | 169335988 | 16686212698802 | 16686212644544 | 16686213112222 | 16686213154646 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 419 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 253312 | 0x7fc9f4757480 | 0x7fc9f1826240 | 388467 | 388467 | 65536 | 9437184 | 1459821 | 163584340 | 16686213167226 | 16686213112222 | 16686213572219 | 16686213614671 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 422 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 8 | 24 | 255552 | 0x7fc9f4757300 | 0x7fc9f1826280 | 719985 | 719985 | 65536 | 16056320 | 2304427 | 258090712 | 16686213625311 | 16686213572219 | 16686214245815 | 16686214291059 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 425 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 259840 | 0x7fc9f4757180 | 0x7fc9f18262c0 | 363510 | 363510 | 65536 | 8847360 | 1367906 | 153222244 | 16686214311758 | 16686214245815 | 16686214698613 | 16686214743244 |
| 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 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 265664 | 0x7fc9f4757000 | 0x7fc9f1826300 | 467845 | 467845 | 65536 | 11665408 | 1799137 | 201407388 | 16686214754304 | 16686214698613 | 16686215219090 | 16686215261287 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 431 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 271232 | 0x7fc9f2103e80 | 0x7fc9f1826340 | 470292 | 470292 | 65536 | 11468800 | 1819910 | 203794388 | 16686215272986 | 16686215219090 | 16686215737487 | 16686215780130 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 434 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 8 | 24 | 273216 | 0x7fc9f2103d00 | 0x7fc9f1826380 | 483427 | 483427 | 65536 | 14090240 | 2021046 | 226432624 | 16686215791059 | 16686215737487 | 16686216259404 | 16686216301712 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 437 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 8 | 24 | 275712 | 0x7fc9f2103b80 | 0x7fc9f18263c0 | 879602 | 879602 | 65536 | 19202048 | 2758644 | 309112796 | 16686216313442 | 16686216259404 | 16686217039080 | 16686217080976 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 440 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 280768 | 0x7fc9f2103a00 | 0x7fc9f1826400 | 426741 | 426741 | 65536 | 10420224 | 1603652 | 179638380 | 16686217101576 | 16686217039080 | 16686217524357 | 16686217567020 |
| 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 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 287616 | 0x7fc9f2103880 | 0x7fc9f1826440 | 547814 | 547814 | 65536 | 13762560 | 2177266 | 243834748 | 16686217579290 | 16686217524357 | 16686218096034 | 16686218119622 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 446 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 294208 | 0x7fc9f2103700 | 0x7fc9f1826480 | 549572 | 549572 | 65536 | 13565952 | 2138061 | 239508808 | 16686218133901 | 16686218096034 | 16686218651231 | 16686218696323 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 449 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 8 | 24 | 296960 | 0x7fc9f4757580 | 0x7fc9f18264c0 | 563218 | 563218 | 65536 | 15466496 | 2227303 | 249458752 | 16686218708212 | 16686218651231 | 16686219223708 | 16686219265984 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 452 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 8 | 24 | 299968 | 0x7fc9f4757400 | 0x7fc9f1826500 | 1041513 | 1041513 | 65536 | 22347776 | 3209704 | 359504100 | 16686219277143 | 16686219223708 | 16686220103703 | 16686220146285 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 455 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 8 | 24 | 302720 | 0x7fc9f4757280 | 0x7fc9f1826540 | 722557 | 722557 | 65536 | 20250624 | 2906241 | 325653596 | 16686220166244 | 16686220103703 | 16686220774260 | 16686220821442 |
| 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 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 305472 | 0x7fc9f4757100 | 0x7fc9f1826580 | 722791 | 722791 | 65536 | 20447232 | 2942925 | 329687204 | 16686220833812 | 16686220774260 | 16686221469136 | 16686221512989 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 461 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 308224 | 0x7fc9f2103f80 | 0x7fc9f18265c0 | 722061 | 722061 | 65536 | 19595264 | 2819309 | 315684220 | 16686221524969 | 16686221469111 | 16686222167667 | 16686222219896 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 464 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 8 | 24 | 310976 | 0x7fc9f2103e00 | 0x7fc9f1826600 | 724685 | 724685 | 65536 | 20381696 | 2926603 | 327933668 | 16686222233105 | 16686222167667 | 16686222867662 | 16686222914573 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 467 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 8 | 24 | 313216 | 0x7fc9f2103c80 | 0x7fc9f1826640 | 1369833 | 1369833 | 65536 | 31522816 | 4513272 | 505462788 | 16686222927252 | 16686222867662 | 16686223978536 | 16686224026496 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 470 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 8 | 24 | 315968 | 0x7fc9f2103b00 | 0x7fc9f1826680 | 1369031 | 1369031 | 65536 | 38993920 | 5589152 | 626169592 | 16686224046685 | 16686223978536 | 16686225072130 | 16686225137669 |
| 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 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 318720 | 0x7fc9f2103980 | 0x7fc9f18266c0 | 1373511 | 1373511 | 65536 | 39124992 | 5607091 | 628000560 | 16686225150449 | 16686225072130 | 16686226216283 | 16686226283471 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 476 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 321472 | 0x7fc9f2103800 | 0x7fc9f1826700 | 1369893 | 1369893 | 65536 | 38469632 | 5510191 | 617144700 | 16686226295331 | 16686226216283 | 16686227359957 | 16686227426813 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 479 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 8 | 24 | 324224 | 0x7fc9f2103680 | 0x7fc9f1826740 | 1375330 | 1375330 | 65536 | 39059456 | 5599125 | 627076380 | 16686227439153 | 16686227359957 | 16686228478991 | 16686228545846 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 482 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 8 | 24 | 326464 | 0x7fc9f4757500 | 0x7fc9f1826780 | 2663955 | 2663955 | 65536 | 60489728 | 8650857 | 969039736 | 16686228557025 | 16686228478991 | 16686230445700 | 16686230517760 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 485 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 8 | 24 | 329216 | 0x7fc9f4757380 | 0x7fc9f18267c0 | 2669630 | 2669630 | 65536 | 77266944 | 11057256 | 1238346912 | 16686230539490 | 16686230445700 | 16686232385209 | 16686232452656 |
| 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 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 331968 | 0x7fc9f4757200 | 0x7fc9f1826800 | 2670325 | 2670325 | 65536 | 77398016 | 11072561 | 1240321052 | 16686232465106 | 16686232385209 | 16686234371278 | 16686234442770 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 491 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 12 | 24 | 334720 | 0x7fc9f4757080 | 0x7fc9f1826840 | 2669750 | 2669750 | 65536 | 76218368 | 10906222 | 1221381504 | 16686234456080 | 16686234371278 | 16686236365187 | 16686236435254 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 494 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 8 | 24 | 337472 | 0x7fc9f2103f00 | 0x7fc9f1826880 | 2673728 | 2673728 | 65536 | 77332480 | 11071993 | 1240091672 | 16686236447754 | 16686236365187 | 16686238305977 | 16686238378739 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 497 | 169067 | 169067 | 4194304 | 256 | 0 | 0 | 8 | 24 | 0 | 0x7fc9f2103d80 | 0x7fc9f18268c0 | 5256343 | 5256343 | 65536 | 120258560 | 17191805 | 1925612488 | 16686238391659 | 16686238305977 | 16686241961317 | 16686242032858 |