43 KiB
43 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | SQ_INSTS_VMEM | SQ_INST_LEVEL_VMEM | SQ_ACCUM_PREV_HIRES | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBuffer.kd | 0 | 0 | 0 | 896130 | 896135 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7fd0e6a04180 | 1048576 | 11113035 | 1423723076 | 12075847189171067 | 12075847436771904 | 12075847437096223 | 12075847437209605 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 896130 | 896135 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7fd0e6a35100 | 4096 | 106978 | 13696112 | 12075847451790473 | 12075847452108439 | 12075847452114999 | 12075847452123532 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7fd216a7e900 | 0x7fd0e6a35140 | 524288 | 11732531 | 1501743840 | 12075847452175839 | 12075847452398998 | 12075847452533077 | 12075847452536279 |
| 5 | 3 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 6 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7fd216a7e800 | 0x7fd0e6a35180 | 524288 | 13261562 | 1697423292 | 12075847452603755 | 12075847452777876 | 12075847453029075 | 12075847453099706 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7fd216a7e700 | 0x7fd0e6a351c0 | 524288 | 13506013 | 1728700904 | 12075847453137517 | 12075847453329394 | 12075847453580593 | 12075847453650740 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7fd216a7e600 | 0x7fd0e6a35200 | 524288 | 10910835 | 1396551748 | 12075847453678903 | 12075847453869072 | 12075847454007471 | 12075847454010629 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7fd216a7e500 | 0x7fd0e6a35240 | 524288 | 11221602 | 1436205288 | 12075847454062666 | 12075847454236750 | 12075847454373070 | 12075847454376309 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7fd216a7e400 | 0x7fd0e6a35280 | 524288 | 12426791 | 1590669428 | 12075847454451448 | 12075847454621869 | 12075847454752908 | 12075847454755614 |
| 10 | 8 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 16 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7fd216a7e300 | 0x7fd0e6a352c0 | 524288 | 14238844 | 1822566440 | 12075847454806007 | 12075847454983467 | 12075847455237386 | 12075847455282232 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7fd216a7ea00 | 0x7fd0e6a35300 | 524288 | 14110483 | 1806147808 | 12075847455311848 | 12075847455502025 | 12075847455755304 | 12075847455799163 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7fd216a7e900 | 0x7fd0e6a35340 | 524288 | 11118541 | 1423078812 | 12075847455823088 | 12075847456015463 | 12075847456152582 | 12075847456155726 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7fd216a7e800 | 0x7fd0e6a35380 | 524288 | 13071668 | 1673228148 | 12075847456205218 | 12075847456388261 | 12075847456516741 | 12075847456519682 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7fd216a7e700 | 0x7fd0e6a353c0 | 524288 | 12083863 | 1546581892 | 12075847456584232 | 12075847456755780 | 12075847456887459 | 12075847456890091 |
| 15 | 13 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 26 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7fd216a7e600 | 0x7fd0e6a35400 | 524288 | 14120979 | 1807422788 | 12075847456939553 | 12075847457119938 | 12075847457367137 | 12075847457437668 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7fd216a7e500 | 0x7fd0e6a35440 | 524288 | 14228841 | 1821268076 | 12075847457465019 | 12075847457647456 | 12075847457897535 | 12075847457967092 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7fd216a7e400 | 0x7fd0e6a35480 | 524288 | 12526162 | 1603468116 | 12075847457994523 | 12075847458179934 | 12075847458310813 | 12075847458313797 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7fd216a7e300 | 0x7fd0e6a354c0 | 524288 | 12511934 | 1601612856 | 12075847458363118 | 12075847458541532 | 12075847458672572 | 12075847458675529 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7fd216a7ea00 | 0x7fd0e6a35500 | 524288 | 12011830 | 1537309148 | 12075847458737294 | 12075847458903611 | 12075847459036730 | 12075847459039856 |
| 20 | 18 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 36 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7fd216a7e900 | 0x7fd0e6a35540 | 524288 | 14116529 | 1806869008 | 12075847459088957 | 12075847459265529 | 12075847459512728 | 12075847459557107 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7fd216a7e800 | 0x7fd0e6a35580 | 524288 | 13390088 | 1713982328 | 12075847459581933 | 12075847459774807 | 12075847460030486 | 12075847460100627 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7fd216a7e700 | 0x7fd0e6a355c0 | 524288 | 12405895 | 1588055912 | 12075847460126315 | 12075847460319925 | 12075847460492884 | 12075847460495992 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7fd216a7e600 | 0x7fd0e6a35600 | 524288 | 11319776 | 1448836884 | 12075847460545103 | 12075847460712083 | 12075847460848563 | 12075847460851533 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7fd216a7e500 | 0x7fd0e6a35640 | 524288 | 12557591 | 1607301072 | 12075847460913308 | 12075847461086802 | 12075847461217521 | 12075847461220869 |
| 25 | 23 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 46 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7fd216a7e400 | 0x7fd0e6a35680 | 524288 | 13307819 | 1703395992 | 12075847461267806 | 12075847461446480 | 12075847461699119 | 12075847461769419 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7fd216a7e300 | 0x7fd0e6a356c0 | 524288 | 13921376 | 1781943968 | 12075847461792942 | 12075847461976078 | 12075847462225677 | 12075847462296398 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7fd216a7ea00 | 0x7fd0e6a35700 | 524288 | 11909327 | 1524263024 | 12075847462324480 | 12075847462508556 | 12075847462640875 | 12075847462643723 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7fd216a7e900 | 0x7fd0e6a35740 | 524288 | 12576131 | 1609734564 | 12075847462692053 | 12075847462864234 | 12075847462995274 | 12075847462998322 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7fd216a7e800 | 0x7fd0e6a35780 | 524288 | 11423184 | 1462180412 | 12075847463062822 | 12075847463227593 | 12075847463363272 | 12075847463366166 |
| 30 | 28 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 56 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7fd216a7e700 | 0x7fd0e6a357c0 | 524288 | 14123847 | 1807950532 | 12075847463416550 | 12075847463594311 | 12075847463843590 | 12075847463912181 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7fd216a7e600 | 0x7fd0e6a35800 | 524288 | 14269449 | 1826434268 | 12075847463937127 | 12075847464135109 | 12075847464388548 | 12075847464459228 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7fd216a7e500 | 0x7fd0e6a35840 | 524288 | 12402921 | 1587589672 | 12075847464486829 | 12075847464668227 | 12075847464798786 | 12075847464801814 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7fd216a7e400 | 0x7fd0e6a35880 | 524288 | 11950198 | 1529676276 | 12075847464852428 | 12075847465023585 | 12075847465158145 | 12075847465161573 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7fd216a7e300 | 0x7fd0e6a358c0 | 524288 | 11830261 | 1514175560 | 12075847465223568 | 12075847465392224 | 12075847465525503 | 12075847465528334 |
| 35 | 33 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 66 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7fd216a7ea00 | 0x7fd0e6a35900 | 524288 | 14132265 | 1808878720 | 12075847465576965 | 12075847465752062 | 12075847466004221 | 12075847466074880 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7fd216a7e900 | 0x7fd0e6a35940 | 524288 | 13923855 | 1782119968 | 12075847466098584 | 12075847466284380 | 12075847466536379 | 12075847466607199 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7fd216a7e800 | 0x7fd0e6a35980 | 524288 | 12341583 | 1579652012 | 12075847466632947 | 12075847466822618 | 12075847466954297 | 12075847466957260 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7fd216a7e700 | 0x7fd0e6a359c0 | 524288 | 10830085 | 1386247488 | 12075847467010699 | 12075847467187576 | 12075847467326456 | 12075847467329321 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7fd216a7e600 | 0x7fd0e6a35a00 | 524288 | 12136361 | 1553400304 | 12075847467390435 | 12075847467556215 | 12075847467687574 | 12075847467690372 |
| 40 | 38 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 76 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7fd216a7e500 | 0x7fd0e6a35a40 | 524288 | 13918303 | 1781546528 | 12075847467738332 | 12075847467911893 | 12075847468161972 | 12075847468232690 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7fd216a7e400 | 0x7fd0e6a35a80 | 524288 | 14256652 | 1824812892 | 12075847468256925 | 12075847468442451 | 12075847468692690 | 12075847468762866 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7fd216a7e300 | 0x7fd0e6a35ac0 | 524288 | 12380571 | 1584663204 | 12075847468789124 | 12075847468967729 | 12075847469098288 | 12075847469101355 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7fd216a7ea00 | 0x7fd0e6a35b00 | 524288 | 12211121 | 1562926796 | 12075847469148582 | 12075847469325007 | 12075847469458127 | 12075847469460943 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7fd216a7e900 | 0x7fd0e6a35b40 | 524288 | 12394432 | 1586395008 | 12075847469520924 | 12075847469688046 | 12075847469819245 | 12075847469822004 |
| 45 | 43 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 86 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7fd216a7e800 | 0x7fd0e6a35b80 | 524288 | 14159122 | 1812273584 | 12075847469872708 | 12075847470057004 | 12075847470320203 | 12075847470390591 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7fd216a7e700 | 0x7fd0e6a35bc0 | 524288 | 14208102 | 1818584212 | 12075847470415066 | 12075847470600362 | 12075847470851721 | 12075847470896080 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7fd216a7e600 | 0x7fd0e6a35c00 | 524288 | 12990765 | 1662735352 | 12075847470927088 | 12075847471122440 | 12075847471251399 | 12075847471254466 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7fd216a7e500 | 0x7fd0e6a35c40 | 524288 | 11639044 | 1489617964 | 12075847471302956 | 12075847471480678 | 12075847471616038 | 12075847471618883 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7fd216a7e400 | 0x7fd0e6a35c80 | 524288 | 12324768 | 1577559452 | 12075847471680288 | 12075847471845797 | 12075847471977636 | 12075847471980435 |
| 50 | 48 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 96 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7fd216a7e300 | 0x7fd0e6a35cc0 | 524288 | 12511239 | 1601408564 | 12075847472032252 | 12075847472210755 | 12075847472473954 | 12075847472542139 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7fd216a7ea00 | 0x7fd0e6a35d00 | 524288 | 12992719 | 1663057968 | 12075847472568649 | 12075847472749953 | 12075847472998912 | 12075847473069209 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7fd216a7e900 | 0x7fd0e6a35d40 | 524288 | 12232564 | 1565834356 | 12075847473094065 | 12075847473279231 | 12075847473412030 | 12075847473415062 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7fd216a7e800 | 0x7fd0e6a35d80 | 524288 | 10808912 | 1383496340 | 12075847473463241 | 12075847473638269 | 12075847473774589 | 12075847473777385 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7fd216a7e700 | 0x7fd0e6a35dc0 | 524288 | 11740658 | 1502837532 | 12075847473837016 | 12075847474000828 | 12075847474133787 | 12075847474136923 |
| 55 | 53 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 106 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7fd216a7e600 | 0x7fd0e6a35e00 | 524288 | 14221614 | 1820344224 | 12075847474185043 | 12075847474361946 | 12075847474627545 | 12075847474671246 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7fd216a7e500 | 0x7fd0e6a35e40 | 524288 | 14116723 | 1806854580 | 12075847474695722 | 12075847474880504 | 12075847475172183 | 12075847475242257 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7fd216a7e400 | 0x7fd0e6a35e80 | 524288 | 11816496 | 1512519332 | 12075847475268546 | 12075847475452342 | 12075847475587221 | 12075847475589964 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7fd216a7e300 | 0x7fd0e6a35ec0 | 524288 | 8990755 | 1150853828 | 12075847475642100 | 12075847475805620 | 12075847475947860 | 12075847475950624 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7fd216a7ea00 | 0x7fd0e6a35f00 | 524288 | 11385669 | 1457448560 | 12075847476016676 | 12075847476184179 | 12075847476318738 | 12075847476321713 |
| 60 | 58 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 116 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7fd216a7e900 | 0x7fd0e6a35f40 | 524288 | 12587832 | 1611293660 | 12075847476369963 | 12075847476545937 | 12075847476806256 | 12075847476875873 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7fd216a7e800 | 0x7fd0e6a35f80 | 524288 | 14107169 | 1805661752 | 12075847476901792 | 12075847477089935 | 12075847477343534 | 12075847477414835 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7fd216a7e700 | 0x7fd0e6a35fc0 | 524288 | 13005004 | 1664528152 | 12075847477439391 | 12075847477626092 | 12075847477755692 | 12075847477758544 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7fd216a7e600 | 0x7fd0e6a36000 | 524288 | 7711351 | 987250132 | 12075847477807214 | 12075847477974891 | 12075847478112810 | 12075847478116018 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7fd216a7e500 | 0x7fd0e6a36040 | 524288 | 11871677 | 1519593668 | 12075847478178544 | 12075847478345289 | 12075847478479049 | 12075847478481968 |
| 65 | 63 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 126 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7fd216a7e400 | 0x7fd0e6a36080 | 524288 | 12294602 | 1573702072 | 12075847478530809 | 12075847478706568 | 12075847478972167 | 12075847479043211 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7fd216a7e300 | 0x7fd0e6a360c0 | 524288 | 13790381 | 1765187076 | 12075847479067947 | 12075847479253286 | 12075847479505605 | 12075847479575851 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7fd216a7ea00 | 0x7fd0e6a36100 | 524288 | 13113411 | 1678582724 | 12075847479598413 | 12075847479783043 | 12075847479911843 | 12075847479914721 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7fd216a7e900 | 0x7fd0e6a36140 | 524288 | 7022453 | 898844960 | 12075847479962460 | 12075847480144002 | 12075847480287361 | 12075847480290710 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7fd216a7e800 | 0x7fd0e6a36180 | 524288 | 11917372 | 1525536416 | 12075847480350932 | 12075847480516480 | 12075847480648800 | 12075847480651580 |
| 70 | 68 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 136 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7fd216a7e700 | 0x7fd0e6a361c0 | 524288 | 13322838 | 1705217112 | 12075847480699059 | 12075847480872639 | 12075847481135358 | 12075847481187977 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7fd216a7e600 | 0x7fd0e6a36200 | 524288 | 14154295 | 1811704616 | 12075847481212172 | 12075847481396317 | 12075847481647356 | 12075847481697945 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7fd216a7e500 | 0x7fd0e6a36240 | 524288 | 13023829 | 1667055788 | 12075847481724384 | 12075847481903515 | 12075847482033274 | 12075847482036584 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7fd216a7e400 | 0x7fd0e6a36280 | 524288 | 5513594 | 705849008 | 12075847482083762 | 12075847482261753 | 12075847482411192 | 12075847482414076 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7fd216a7e300 | 0x7fd0e6a362c0 | 524288 | 11665202 | 1493153372 | 12075847482495337 | 12075847482659351 | 12075847482793751 | 12075847482796647 |
| 75 | 73 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 146 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7fd216a7ea00 | 0x7fd0e6a36300 | 524288 | 11994638 | 1535224308 | 12075847482844225 | 12075847483025110 | 12075847483292309 | 12075847483344335 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7fd216a7e900 | 0x7fd0e6a36340 | 524288 | 12873259 | 1647791320 | 12075847483369912 | 12075847483552788 | 12075847483807347 | 12075847483857809 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7fd216a7e800 | 0x7fd0e6a36380 | 524288 | 11147910 | 1427001604 | 12075847483881543 | 12075847484066226 | 12075847484202065 | 12075847484205275 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7fd216a7e700 | 0x7fd0e6a363c0 | 524288 | 4650148 | 595449560 | 12075847484253805 | 12075847484427984 | 12075847484586223 | 12075847484589108 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7fd216a7e600 | 0x7fd0e6a36400 | 524288 | 11602964 | 1485295660 | 12075847484649490 | 12075847484813422 | 12075847484947502 | 12075847484950319 |
| 80 | 78 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 156 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7fd216a7e500 | 0x7fd0e6a36440 | 524288 | 12214711 | 1563427432 | 12075847484998389 | 12075847485171501 | 12075847485433420 | 12075847485485915 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7fd216a7e400 | 0x7fd0e6a36480 | 524288 | 14112061 | 1806278136 | 12075847485511061 | 12075847485694539 | 12075847485946218 | 12075847485970325 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7fd216a7e300 | 0x7fd0e6a364c0 | 524288 | 12365231 | 1582821320 | 12075847486019997 | 12075847486186537 | 12075847486317896 | 12075847486321107 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7fd216a7ea00 | 0x7fd0e6a36500 | 524288 | 3520118 | 450617560 | 12075847486382731 | 12075847486547175 | 12075847486712615 | 12075847486715400 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7fd216a7e900 | 0x7fd0e6a36540 | 524288 | 12136916 | 1553516656 | 12075847486781192 | 12075847486946374 | 12075847487079013 | 12075847487082382 |
| 85 | 83 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 166 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7fd216a7e800 | 0x7fd0e6a36580 | 524288 | 10583105 | 1354598560 | 12075847487130491 | 12075847487307972 | 12075847487567811 | 12075847487617065 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7fd216a7e700 | 0x7fd0e6a365c0 | 524288 | 13204569 | 1690120436 | 12075847487644937 | 12075847487822370 | 12075847488075649 | 12075847488127023 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7fd216a7e600 | 0x7fd0e6a36600 | 524288 | 12769405 | 1634399744 | 12075847488156067 | 12075847488335488 | 12075847488465887 | 12075847488468798 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7fd216a7e500 | 0x7fd0e6a36640 | 524288 | 3682176 | 471419852 | 12075847488518100 | 12075847488688286 | 12075847488862206 | 12075847488865115 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7fd216a7e400 | 0x7fd0e6a36680 | 524288 | 12900158 | 1651120388 | 12075847488926549 | 12075847489098525 | 12075847489227484 | 12075847489230834 |
| 90 | 88 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 176 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7fd216a7e300 | 0x7fd0e6a366c0 | 524288 | 8231249 | 1053512916 | 12075847489278513 | 12075847489452123 | 12075847489708442 | 12075847489758936 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7fd216a7ea00 | 0x7fd0e6a36700 | 524288 | 14080373 | 1802332688 | 12075847489782880 | 12075847489970041 | 12075847490218520 | 12075847490271328 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7fd216a7e900 | 0x7fd0e6a36740 | 524288 | 11922394 | 1526118144 | 12075847490296585 | 12075847490483159 | 12075847490618198 | 12075847490621098 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7fd216a7e800 | 0x7fd0e6a36780 | 524288 | 3430003 | 439076732 | 12075847490668546 | 12075847490841557 | 12075847491023956 | 12075847491027263 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7fd216a7e700 | 0x7fd0e6a367c0 | 524288 | 11052850 | 1414700164 | 12075847491092104 | 12075847491259955 | 12075847491396915 | 12075847491399835 |
| 95 | 93 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 186 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7fd216a7e600 | 0x7fd0e6a36800 | 524288 | 4064982 | 520372060 | 12075847491448085 | 12075847491620914 | 12075847491886353 | 12075847491936713 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7fd216a7e500 | 0x7fd0e6a36840 | 524288 | 13993970 | 1791302776 | 12075847491960918 | 12075847492149552 | 12075847492405231 | 12075847492456409 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7fd216a7e400 | 0x7fd0e6a36880 | 524288 | 10452682 | 1337966788 | 12075847492480173 | 12075847492663150 | 12075847492803629 | 12075847492806470 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7fd216a7e300 | 0x7fd0e6a368c0 | 524288 | 3566687 | 456383628 | 12075847492853878 | 12075847493031148 | 12075847493222827 | 12075847493273948 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7fd216a7ea00 | 0x7fd0e6a36900 | 524288 | 10919828 | 1397597960 | 12075847493315896 | 12075847493484586 | 12075847493622506 | 12075847493625552 |
| 100 | 98 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 196 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7fd216a7e900 | 0x7fd0e6a36940 | 524288 | 2805623 | 359010764 | 12075847493674403 | 12075847493850025 | 12075847494135623 | 12075847494188638 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7fd216a7e800 | 0x7fd0e6a36980 | 524288 | 12984292 | 1661948832 | 12075847494214637 | 12075847494399942 | 12075847494654661 | 12075847494706651 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7fd216a7e700 | 0x7fd0e6a369c0 | 524288 | 10706156 | 1370307652 | 12075847494734182 | 12075847494915780 | 12075847495055140 | 12075847495058325 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7fd216a7e600 | 0x7fd0e6a36a00 | 524288 | 3533356 | 452031844 | 12075847495107786 | 12075847495281219 | 12075847495492418 | 12075847495543186 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7fd216a7e500 | 0x7fd0e6a36a40 | 524288 | 11052205 | 1414522700 | 12075847495581527 | 12075847495746817 | 12075847495884096 | 12075847495887135 |
| 105 | 103 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 206 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7fd216a7e400 | 0x7fd0e6a36a80 | 524288 | 2531281 | 324026140 | 12075847495939212 | 12075847496109695 | 12075847496416894 | 12075847496467894 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7fd216a7e300 | 0x7fd0e6a36ac0 | 524288 | 13203268 | 1690064280 | 12075847496495125 | 12075847496675933 | 12075847496936252 | 12075847496987780 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7fd216a7ea00 | 0x7fd0e6a36b00 | 524288 | 10770369 | 1378561976 | 12075847497022545 | 12075847497200251 | 12075847497338650 | 12075847497341738 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7fd216a7e900 | 0x7fd0e6a36b40 | 524288 | 3308187 | 423218884 | 12075847497395919 | 12075847497558489 | 12075847497786648 | 12075847497837680 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7fd216a7e800 | 0x7fd0e6a36b80 | 524288 | 11504049 | 1472529292 | 12075847497874759 | 12075847498048407 | 12075847498183287 | 12075847498186739 |
| 110 | 108 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 216 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7fd216a7e700 | 0x7fd0e6a36bc0 | 524288 | 2458176 | 314767436 | 12075847498234437 | 12075847498410006 | 12075847498740884 | 12075847498792274 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7fd216a7e600 | 0x7fd0e6a36c00 | 524288 | 13965277 | 1787568476 | 12075847498816309 | 12075847498997363 | 12075847499248882 | 12075847499300038 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7fd216a7e500 | 0x7fd0e6a36c40 | 524288 | 10261099 | 1313371008 | 12075847499326958 | 12075847499505521 | 12075847499645040 | 12075847499648375 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7fd216a7e400 | 0x7fd0e6a36c80 | 524288 | 3210764 | 410763388 | 12075847499699280 | 12075847499869457 | 12075847500114576 | 12075847500171287 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7fd216a7e300 | 0x7fd0e6a36cc0 | 524288 | 9438787 | 1207983908 | 12075847500206031 | 12075847500375054 | 12075847500519693 | 12075847500522419 |
| 115 | 113 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 226 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7fd216a7ea00 | 0x7fd0e6a36d00 | 524288 | 2373626 | 303814712 | 12075847500571190 | 12075847500742892 | 12075847501120651 | 12075847501145968 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7fd216a7e900 | 0x7fd0e6a36d40 | 524288 | 12840320 | 1643639256 | 12075847501190281 | 12075847501355370 | 12075847501617609 | 12075847501668379 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7fd216a7e800 | 0x7fd0e6a36d80 | 524288 | 9196031 | 1176924088 | 12075847501700699 | 12075847501875688 | 12075847502020327 | 12075847502023539 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7fd216a7e700 | 0x7fd0e6a36dc0 | 524288 | 3146772 | 402617252 | 12075847502076908 | 12075847502252646 | 12075847502533605 | 12075847502585554 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7fd216a7e600 | 0x7fd0e6a36e00 | 524288 | 7998375 | 1023768420 | 12075847502624716 | 12075847502788484 | 12075847502929924 | 12075847502933130 |
| 120 | 118 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 236 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7fd216a7e500 | 0x7fd0e6a36e40 | 524288 | 2367802 | 302902744 | 12075847502981259 | 12075847503161603 | 12075847503610241 | 12075847503661934 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7fd216a7e400 | 0x7fd0e6a36e80 | 524288 | 11244625 | 1439343740 | 12075847503687542 | 12075847503872320 | 12075847504131359 | 12075847504182742 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7fd216a7e300 | 0x7fd0e6a36ec0 | 524288 | 7550160 | 966214416 | 12075847504210043 | 12075847504394878 | 12075847504534558 | 12075847504537411 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7fd216a7ea00 | 0x7fd0e6a36f00 | 524288 | 3141846 | 402152944 | 12075847504585981 | 12075847504760317 | 12075847505075356 | 12075847505126396 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7fd216a7e900 | 0x7fd0e6a36f40 | 524288 | 3592798 | 460056432 | 12075847505173112 | 12075847505343515 | 12075847505497434 | 12075847505500341 |
| 125 | 123 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 246 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7fd216a7e800 | 0x7fd0e6a36f80 | 524288 | 2298134 | 294312620 | 12075847505550774 | 12075847505721753 | 12075847506239511 | 12075847506290249 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7fd216a7e700 | 0x7fd0e6a36fc0 | 524288 | 7815105 | 1000307932 | 12075847506322869 | 12075847506499190 | 12075847506797269 | 12075847506848226 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7fd216a7e600 | 0x7fd0e6a37000 | 524288 | 3007610 | 385014816 | 12075847506872010 | 12075847507075188 | 12075847507230227 | 12075847507233291 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7fd216a7e500 | 0x7fd0e6a37040 | 524288 | 3451303 | 441893908 | 12075847507282312 | 12075847507465906 | 12075847507851505 | 12075847507903006 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7fd216a7e400 | 0x7fd0e6a37080 | 524288 | 3192718 | 408847344 | 12075847507942519 | 12075847508111024 | 12075847508287503 | 12075847508290837 |
| 130 | 128 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 256 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7fd216a7e300 | 0x7fd0e6a370c0 | 524288 | 2309548 | 295580536 | 12075847508338415 | 12075847508511022 | 12075847509134860 | 12075847509186882 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7fd216a7ea00 | 0x7fd0e6a37100 | 524288 | 3972015 | 508516888 | 12075847509211608 | 12075847509403979 | 12075847509729898 | 12075847509780545 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7fd216a7e900 | 0x7fd0e6a37140 | 524288 | 3319836 | 424752012 | 12075847509809519 | 12075847509992457 | 12075847510172776 | 12075847510176431 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7fd216a7e800 | 0x7fd0e6a37180 | 524288 | 3403239 | 435671076 | 12075847510228768 | 12075847510400935 | 12075847510856933 | 12075847510907079 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7fd216a7e700 | 0x7fd0e6a371c0 | 524288 | 3217738 | 412019400 | 12075847510946512 | 12075847511118052 | 12075847511319171 | 12075847511371582 |
| 135 | 133 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 266 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7fd216a7e600 | 0x7fd0e6a37200 | 524288 | 2292078 | 293002636 | 12075847511396819 | 12075847511584610 | 12075847512288128 | 12075847512339711 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7fd216a7e500 | 0x7fd0e6a37240 | 524288 | 3489849 | 446753616 | 12075847512367092 | 12075847512555647 | 12075847512929565 | 12075847512981193 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7fd216a7e400 | 0x7fd0e6a37280 | 524288 | 3276682 | 419272940 | 12075847513012241 | 12075847513205244 | 12075847513407483 | 12075847513458971 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7fd216a7e300 | 0x7fd0e6a372c0 | 524288 | 3898965 | 499091608 | 12075847513483727 | 12075847513666042 | 12075847514192760 | 12075847514245082 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7fd216a7ea00 | 0x7fd0e6a37300 | 524288 | 3072261 | 393319236 | 12075847514287331 | 12075847514457079 | 12075847514681878 | 12075847514731957 |
| 140 | 138 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 276 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7fd216a7e900 | 0x7fd0e6a37340 | 524288 | 2310361 | 295789292 | 12075847514757455 | 12075847514938837 | 12075847515737714 | 12075847515790124 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7fd216a7e800 | 0x7fd0e6a37380 | 524288 | 3521637 | 450917852 | 12075847515817865 | 12075847515997713 | 12075847516440112 | 12075847516492499 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7fd216a7e700 | 0x7fd0e6a373c0 | 524288 | 3180430 | 407204788 | 12075847516518778 | 12075847516701551 | 12075847516929390 | 12075847516981007 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7fd216a7e600 | 0x7fd0e6a37400 | 524288 | 4276407 | 547471316 | 12075847517013627 | 12075847517193549 | 12075847517790506 | 12075847517843249 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7fd216a7e500 | 0x7fd0e6a37440 | 524288 | 3246750 | 415553800 | 12075847517879948 | 12075847518081545 | 12075847518351624 | 12075847518404442 |
| 145 | 143 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 286 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7fd216a7e400 | 0x7fd0e6a37480 | 524288 | 2310517 | 295494628 | 12075847518432535 | 12075847518612583 | 12075847519598179 | 12075847519669744 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7fd216a7e300 | 0x7fd0e6a374c0 | 524288 | 3268621 | 418269600 | 12075847519704058 | 12075847519884098 | 12075847520397696 | 12075847520470211 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7fd216a7ea00 | 0x7fd0e6a37500 | 524288 | 3261056 | 417546128 | 12075847520506008 | 12075847520692575 | 12075847520995774 | 12075847521043928 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7fd216a7e900 | 0x7fd0e6a37540 | 524288 | 2236342 | 286231772 | 12075847521075587 | 12075847521250813 | 12075847521989850 | 12075847522061509 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7fd216a7e800 | 0x7fd0e6a37580 | 524288 | 3173000 | 405969388 | 12075847522101804 | 12075847522267769 | 12075847522586008 | 12075847522656184 |
| 150 | 148 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 296 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7fd216a7e700 | 0x7fd0e6a375c0 | 524288 | 2315363 | 296373680 | 12075847522683495 | 12075847522861847 | 12075847524033362 | 12075847524105618 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7fd216a7e600 | 0x7fd0e6a37600 | 524288 | 3303227 | 422707916 | 12075847524137918 | 12075847524316881 | 12075847524927119 | 12075847524998136 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7fd216a7e500 | 0x7fd0e6a37640 | 524288 | 3272258 | 418696828 | 12075847525029585 | 12075847525210158 | 12075847525529677 | 12075847525601919 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7fd216a7e400 | 0x7fd0e6a37680 | 524288 | 2230225 | 285288096 | 12075847525627606 | 12075847525814155 | 12075847526692872 | 12075847526765241 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7fd216a7e300 | 0x7fd0e6a376c0 | 524288 | 3188830 | 408343196 | 12075847526805676 | 12075847526971911 | 12075847527384549 | 12075847527455684 |
| 155 | 153 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 306 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7fd216a7ea00 | 0x7fd0e6a37700 | 524288 | 2305839 | 295377512 | 12075847527482443 | 12075847527671588 | 12075847529221342 | 12075847529292758 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7fd216a7e900 | 0x7fd0e6a37740 | 524288 | 2249916 | 288034248 | 12075847529325158 | 12075847529509181 | 12075847530306938 | 12075847530377814 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7fd216a7e800 | 0x7fd0e6a37780 | 524288 | 2201515 | 281442664 | 12075847530411457 | 12075847530582297 | 12075847530998295 | 12075847531069199 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7fd216a7e700 | 0x7fd0e6a377c0 | 524288 | 2224047 | 284391160 | 12075847531102521 | 12075847531281654 | 12075847532441810 | 12075847532513373 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7fd216a7e600 | 0x7fd0e6a37800 | 524288 | 2252306 | 288192828 | 12075847532559649 | 12075847532727089 | 12075847533513486 | 12075847533583933 |
| 160 | 158 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 316 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7fd216a7e500 | 0x7fd0e6a37840 | 524288 | 2613295 | 334500684 | 12075847533616874 | 12075847533792845 | 12075847536843073 | 12075847536915925 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7fd216a7e400 | 0x7fd0e6a37880 | 524288 | 2291162 | 293510972 | 12075847536949277 | 12075847537135872 | 12075847538680346 | 12075847538752799 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7fd216a7e300 | 0x7fd0e6a378c0 | 524288 | 2233698 | 286080716 | 12075847538788255 | 12075847538971225 | 12075847539760982 | 12075847539833547 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7fd216a7ea00 | 0x7fd0e6a37900 | 524288 | 2493173 | 318967844 | 12075847539866148 | 12075847540049620 | 12075847542331692 | 12075847542403003 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7fd216a7e900 | 0x7fd0e6a37940 | 524288 | 2450429 | 313638924 | 12075847542449810 | 12075847542619531 | 12075847544155365 | 12075847544226071 |
| 165 | 163 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 326 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7fd216a7e800 | 0x7fd0e6a37980 | 524288 | 2853674 | 365240256 | 12075847544259032 | 12075847544440804 | 12075847550495020 | 12075847550566674 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7fd216a7e700 | 0x7fd0e6a379c0 | 524288 | 3014210 | 386021032 | 12075847550598884 | 12075847550777419 | 12075847553818047 | 12075847553892175 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7fd216a7e600 | 0x7fd0e6a37a00 | 524288 | 2407279 | 307913940 | 12075847553921569 | 12075847554110846 | 12075847555650360 | 12075847555726844 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 896130 | 896135 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7fd216a7e500 | 0x7fd0e6a37a40 | 524288 | 2587289 | 330937476 | 12075847555757431 | 12075847555943479 | 12075847560469862 | 12075847560544347 |