37 KiB
37 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBufferAligned.kd | 0 | 0 | 0 | 216328 | 216328 | 33554432 | 256 | 0 | 0 | 4 | 32 | 4160 | 0x0 | 0x7f1872e04280 | 17483220242836 | 17483220271567 | 17483220509487 | 17483220597517 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 216328 | 216328 | 32768 | 256 | 0 | 0 | 12 | 24 | 13888 | 0x0 | 0x7f1872e23f80 | 17483225329135 | 17483225344691 | 17483225353491 | 17483225376724 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 5 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 14336 | 0x7f1875b62380 | 0x7f1872e23fc0 | 17483225377814 | 17483225425972 | 17483225517812 | 17483225520420 |
| 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 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15040 | 0x7f1875b62200 | 0x7f1872e24000 | 17483225543620 | 17483225553172 | 17483225732212 | 17483225734805 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 11 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15488 | 0x7f1875b62080 | 0x7f1872e24040 | 17483225751384 | 17483225759572 | 17483225940532 | 17483225943099 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 14 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 15936 | 0x7f1873783f00 | 0x7f1872e24080 | 17483225957199 | 17483225965012 | 17483226058132 | 17483226060726 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 17 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 16384 | 0x7f1873783d80 | 0x7f1872e240c0 | 17483226093905 | 17483226104532 | 17483226196372 | 17483226199003 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 20 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 17088 | 0x7f1873783c00 | 0x7f1872e24100 | 17483226228022 | 17483226238132 | 17483226329972 | 17483226332529 |
| 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 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 16 | 24 | 17792 | 0x7f1873783a80 | 0x7f1872e24140 | 17483226353159 | 17483226362612 | 17483226542293 | 17483226544744 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 26 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 16 | 24 | 18496 | 0x7f1873783900 | 0x7f1872e24180 | 17483226563703 | 17483226574453 | 17483226754453 | 17483226757018 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 29 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19200 | 0x7f1873783780 | 0x7f1872e241c0 | 17483226776138 | 17483226786453 | 17483226878933 | 17483226881585 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 32 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19904 | 0x7f1873783600 | 0x7f1872e24200 | 17483226910484 | 17483226920853 | 17483227013333 | 17483227015862 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 35 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 20608 | 0x7f1875b62480 | 0x7f1872e24240 | 17483227037611 | 17483227046133 | 17483227137813 | 17483227140338 |
| 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 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 16 | 24 | 21312 | 0x7f1875b62300 | 0x7f1872e24280 | 17483227162828 | 17483227172693 | 17483227352853 | 17483227355333 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 41 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22016 | 0x7f1875b62180 | 0x7f1872e242c0 | 17483227376662 | 17483227386934 | 17483227567414 | 17483227569857 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 44 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22720 | 0x7f1875b62000 | 0x7f1872e24300 | 17483227589557 | 17483227610934 | 17483227703094 | 17483227705934 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 47 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 23424 | 0x7f1873783e80 | 0x7f1872e24340 | 17483227725813 | 17483227736054 | 17483227828214 | 17483227830951 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 50 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 24128 | 0x7f1873783d00 | 0x7f1872e24380 | 17483227852110 | 17483227862134 | 17483227954614 | 17483227957027 |
| 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 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 16 | 24 | 24832 | 0x7f1873783b80 | 0x7f1872e243c0 | 17483227977687 | 17483228000854 | 17483228180854 | 17483228183621 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 56 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 16 | 24 | 25536 | 0x7f1873783a00 | 0x7f1872e24400 | 17483228202641 | 17483228211094 | 17483228392535 | 17483228394926 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 59 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26240 | 0x7f1873783880 | 0x7f1872e24440 | 17483228410786 | 17483228440855 | 17483228533335 | 17483228536212 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 62 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26944 | 0x7f1873783700 | 0x7f1872e24480 | 17483228551452 | 17483228559415 | 17483228651575 | 17483228654089 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 65 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 27648 | 0x7f1875b62580 | 0x7f1872e244c0 | 17483228675339 | 17483228685175 | 17483228777175 | 17483228779766 |
| 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 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 16 | 24 | 28608 | 0x7f1875b62400 | 0x7f1872e24500 | 17483228798486 | 17483228806135 | 17483228986775 | 17483228989371 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 71 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 16 | 24 | 29312 | 0x7f1875b62280 | 0x7f1872e24540 | 17483229005020 | 17483229014295 | 17483229194775 | 17483229197355 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 74 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 30016 | 0x7f1875b62100 | 0x7f1872e24580 | 17483229216215 | 17483229237175 | 17483229328696 | 17483229331252 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 77 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 8 | 24 | 30976 | 0x7f1873783f80 | 0x7f1872e245c0 | 17483229350841 | 17483229361176 | 17483229453176 | 17483229455659 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 80 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 31680 | 0x7f1873783e00 | 0x7f1872e24600 | 17483229476868 | 17483229487576 | 17483229578936 | 17483229580745 |
| 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 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 16 | 24 | 32640 | 0x7f1873783c80 | 0x7f1872e24640 | 17483229598445 | 17483229607576 | 17483229787256 | 17483229789110 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 86 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 33600 | 0x7f1873783b00 | 0x7f1872e24680 | 17483229803270 | 17483229811256 | 17483229991896 | 17483229993705 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 89 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 34560 | 0x7f1873783980 | 0x7f1872e246c0 | 17483230007434 | 17483230015576 | 17483230108056 | 17483230110172 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 92 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 8 | 24 | 35520 | 0x7f1873783800 | 0x7f1872e24700 | 17483230127991 | 17483230135576 | 17483230228376 | 17483230230609 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 95 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 36224 | 0x7f1873783680 | 0x7f1872e24740 | 17483230252478 | 17483230261337 | 17483230353497 | 17483230355665 |
| 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 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 37184 | 0x7f1875b62500 | 0x7f1872e24780 | 17483230369895 | 17483230377497 | 17483230557177 | 17483230558970 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 101 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 38144 | 0x7f1875b62380 | 0x7f1872e247c0 | 17483230572900 | 17483230581017 | 17483230761177 | 17483230763085 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 104 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 39104 | 0x7f1875b62200 | 0x7f1872e24800 | 17483230778354 | 17483230786297 | 17483230878777 | 17483230880562 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 107 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 8 | 24 | 40320 | 0x7f1875b62080 | 0x7f1872e24840 | 17483230894901 | 17483230903097 | 17483230995737 | 17483230997629 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 110 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 41280 | 0x7f1873783f00 | 0x7f1872e24880 | 17483231017748 | 17483231027897 | 17483231120057 | 17483231121966 |
| 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 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 42240 | 0x7f1873783d80 | 0x7f1872e248c0 | 17483231137055 | 17483231144697 | 17483231324858 | 17483231326710 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 116 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 43200 | 0x7f1873783c00 | 0x7f1872e24900 | 17483231340970 | 17483231348538 | 17483231528538 | 17483231530415 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 119 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 8 | 24 | 44160 | 0x7f1873783a80 | 0x7f1872e24940 | 17483231545375 | 17483231553658 | 17483231646138 | 17483231647942 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 122 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 45376 | 0x7f1873783900 | 0x7f1872e24980 | 17483231662712 | 17483231670778 | 17483231763898 | 17483231765759 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 125 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 46336 | 0x7f1873783780 | 0x7f1872e249c0 | 17483231786238 | 17483231796538 | 17483231888858 | 17483231890736 |
| 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 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 47552 | 0x7f1873783600 | 0x7f1872e24a00 | 17483231905475 | 17483231913498 | 17483232093498 | 17483232095420 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 131 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 48512 | 0x7f1875b62480 | 0x7f1872e24a40 | 17483232109470 | 17483232117658 | 17483232298619 | 17483232300395 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 134 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 8 | 24 | 49472 | 0x7f1875b62300 | 0x7f1872e24a80 | 17483232313905 | 17483232321979 | 17483232414459 | 17483232416362 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 137 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 50688 | 0x7f1875b62180 | 0x7f1872e24ac0 | 17483232429872 | 17483232438459 | 17483232530459 | 17483232532419 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 140 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 51648 | 0x7f1875b62000 | 0x7f1872e24b00 | 17483232553978 | 17483232564539 | 17483232656379 | 17483232658166 |
| 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 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 52864 | 0x7f1873783e80 | 0x7f1872e24b40 | 17483232673785 | 17483232681019 | 17483232859739 | 17483232861561 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 146 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 54080 | 0x7f1873783d00 | 0x7f1872e24b80 | 17483232875880 | 17483232884059 | 17483233065019 | 17483233066875 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 149 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 8 | 24 | 55296 | 0x7f1873783b80 | 0x7f1872e24bc0 | 17483233081475 | 17483233089499 | 17483233182300 | 17483233184202 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 152 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 56768 | 0x7f1873783a00 | 0x7f1872e24c00 | 17483233198742 | 17483233206620 | 17483233300060 | 17483233302009 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 155 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 57728 | 0x7f1873783880 | 0x7f1872e24c40 | 17483233321919 | 17483233332380 | 17483233425180 | 17483233426966 |
| 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 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 58944 | 0x7f1873783700 | 0x7f1872e24c80 | 17483233441506 | 17483233449020 | 17483233628060 | 17483233629951 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 161 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 60160 | 0x7f1875b62580 | 0x7f1872e24cc0 | 17483233643900 | 17483233652700 | 17483233832700 | 17483233834525 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 164 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 8 | 24 | 61376 | 0x7f1875b62400 | 0x7f1872e24d00 | 17483233848245 | 17483233856060 | 17483233948860 | 17483233950692 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 167 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 62848 | 0x7f1875b62280 | 0x7f1872e24d40 | 17483233965902 | 17483233973820 | 17483234071100 | 17483234073039 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 170 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 63808 | 0x7f1875b62100 | 0x7f1872e24d80 | 17483234103418 | 17483234113500 | 17483234206621 | 17483234208656 |
| 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 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 65024 | 0x7f1873783f80 | 0x7f1872e24dc0 | 17483234221805 | 17483234230781 | 17483234410141 | 17483234412140 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 176 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 66240 | 0x7f1873783e00 | 0x7f1872e24e00 | 17483234426930 | 17483234434941 | 17483234615101 | 17483234617305 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 179 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 8 | 24 | 67456 | 0x7f1873783c80 | 0x7f1872e24e40 | 17483234631205 | 17483234639101 | 17483234732381 | 17483234734392 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 182 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 68928 | 0x7f1873783b00 | 0x7f1872e24e80 | 17483234748832 | 17483234756701 | 17483234858781 | 17483234860829 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 185 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 70144 | 0x7f1873783980 | 0x7f1872e24ec0 | 17483234880268 | 17483234890781 | 17483234983101 | 17483234985106 |
| 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 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 71616 | 0x7f1873783800 | 0x7f1872e24f00 | 17483235000295 | 17483235008221 | 17483235188382 | 17483235190330 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 191 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 72832 | 0x7f1873783680 | 0x7f1872e24f40 | 17483235205160 | 17483235213182 | 17483235394942 | 17483235396915 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 194 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 8 | 24 | 74048 | 0x7f1875b62500 | 0x7f1872e24f80 | 17483235409915 | 17483235417662 | 17483235510142 | 17483235512252 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 197 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 75776 | 0x7f1875b62380 | 0x7f1872e24fc0 | 17483235526852 | 17483235534302 | 17483235639582 | 17483235641659 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 200 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 76992 | 0x7f1875b62200 | 0x7f1872e25000 | 17483235660928 | 17483235671582 | 17483235764222 | 17483235766225 |
| 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 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 78464 | 0x7f1875b62080 | 0x7f1872e25040 | 17483235780605 | 17483235788382 | 17483235967422 | 17483235969380 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 206 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 79936 | 0x7f1873783f00 | 0x7f1872e25080 | 17483235983980 | 17483235991742 | 17483236170783 | 17483236172805 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 209 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 8 | 24 | 81408 | 0x7f1873783d80 | 0x7f1872e250c0 | 17483236186275 | 17483236194303 | 17483236287263 | 17483236289312 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 212 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 83136 | 0x7f1873783c00 | 0x7f1872e25100 | 17483236304102 | 17483236312223 | 17483236424383 | 17483236426368 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 215 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 84352 | 0x7f1873783a80 | 0x7f1872e25140 | 17483236460638 | 17483236470143 | 17483236562943 | 17483236564865 |
| 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 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 85824 | 0x7f1873783900 | 0x7f1872e25180 | 17483236581214 | 17483236588863 | 17483236769343 | 17483236771589 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 221 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 87296 | 0x7f1873783780 | 0x7f1872e251c0 | 17483236785929 | 17483236793503 | 17483236974143 | 17483236976154 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 224 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 88768 | 0x7f1873783600 | 0x7f1872e25200 | 17483236990064 | 17483236997663 | 17483237091424 | 17483237093281 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 227 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 90752 | 0x7f1875b62480 | 0x7f1872e25240 | 17483237107781 | 17483237116384 | 17483237234144 | 17483237235957 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 230 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 91968 | 0x7f1875b62300 | 0x7f1872e25280 | 17483237260407 | 17483237270784 | 17483237363264 | 17483237365094 |
| 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 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 93440 | 0x7f1875b62180 | 0x7f1872e252c0 | 17483237380964 | 17483237388544 | 17483237568704 | 17483237570629 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 236 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 94912 | 0x7f1875b62000 | 0x7f1872e25300 | 17483237587188 | 17483237594784 | 17483237775264 | 17483237777214 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 239 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 96384 | 0x7f1873783e80 | 0x7f1872e25340 | 17483237791953 | 17483237800064 | 17483237893664 | 17483237895600 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 242 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 98368 | 0x7f1873783d00 | 0x7f1872e25380 | 17483237909800 | 17483237917984 | 17483238042465 | 17483238044327 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 245 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 99584 | 0x7f1873783b80 | 0x7f1872e253c0 | 17483238064396 | 17483238074785 | 17483238168225 | 17483238170523 |
| 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 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 101312 | 0x7f1873783a00 | 0x7f1872e25400 | 17483238187353 | 17483238195425 | 17483238373505 | 17483238375748 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 251 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 102784 | 0x7f1873783880 | 0x7f1872e25440 | 17483238390018 | 17483238397825 | 17483238576705 | 17483238578723 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 254 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 104256 | 0x7f1873783700 | 0x7f1872e25480 | 17483238592773 | 17483238600705 | 17483238693665 | 17483238695790 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 257 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 106240 | 0x7f1875b62580 | 0x7f1872e254c0 | 17483238709470 | 17483238717185 | 17483238846305 | 17483238848356 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 260 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 107712 | 0x7f1875b62400 | 0x7f1872e25500 | 17483238868285 | 17483238878625 | 17483238970786 | 17483238972933 |
| 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 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 16 | 24 | 109440 | 0x7f1875b62280 | 0x7f1872e25540 | 17483238990232 | 17483238998466 | 17483239176546 | 17483239178607 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 266 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 16 | 24 | 111168 | 0x7f1875b62100 | 0x7f1872e25580 | 17483239193427 | 17483239201346 | 17483239381346 | 17483239383562 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 269 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 8 | 24 | 112896 | 0x7f1873783f80 | 0x7f1872e255c0 | 17483239396442 | 17483239404066 | 17483239498146 | 17483239500059 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 272 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 115136 | 0x7f1873783e00 | 0x7f1872e25600 | 17483239514219 | 17483239521826 | 17483239657666 | 17483239659785 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 275 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 116608 | 0x7f1873783c80 | 0x7f1872e25640 | 17483239678805 | 17483239690626 | 17483239784226 | 17483239786362 |
| 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 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 16 | 24 | 118336 | 0x7f1873783b00 | 0x7f1872e25680 | 17483239801311 | 17483239809026 | 17483239987107 | 17483239989137 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 281 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 16 | 24 | 120064 | 0x7f1873783980 | 0x7f1872e256c0 | 17483240002946 | 17483240011267 | 17483240190147 | 17483240192141 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 284 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 121792 | 0x7f1873783800 | 0x7f1872e25700 | 17483240205781 | 17483240213507 | 17483240307907 | 17483240310038 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 287 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 124032 | 0x7f1873783680 | 0x7f1872e25740 | 17483240324948 | 17483240332387 | 17483240474947 | 17483240477134 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 290 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 125504 | 0x7f1875b62500 | 0x7f1872e25780 | 17483240497984 | 17483240508227 | 17483240601987 | 17483240603841 |
| 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 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 127488 | 0x7f1875b62380 | 0x7f1872e257c0 | 17483240620190 | 17483240627907 | 17483240806147 | 17483240808026 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 296 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 129216 | 0x7f1875b62200 | 0x7f1872e25800 | 17483240824775 | 17483240832387 | 17483241011748 | 17483241013510 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 299 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 130944 | 0x7f1875b62080 | 0x7f1872e25840 | 17483241027140 | 17483241035428 | 17483241134788 | 17483241136657 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 302 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 133440 | 0x7f1873783f00 | 0x7f1872e25880 | 17483241151447 | 17483241159428 | 17483241313188 | 17483241315133 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 305 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 134912 | 0x7f1873783d80 | 0x7f1872e258c0 | 17483241334892 | 17483241345668 | 17483241439268 | 17483241441239 |
| 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 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 136896 | 0x7f1873783c00 | 0x7f1872e25900 | 17483241456179 | 17483241464068 | 17483241643268 | 17483241645234 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 311 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 138880 | 0x7f1873783a80 | 0x7f1872e25940 | 17483241659744 | 17483241667428 | 17483241849029 | 17483241851089 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 314 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 140864 | 0x7f1873783900 | 0x7f1872e25980 | 17483241864908 | 17483241872869 | 17483241977189 | 17483241979026 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 317 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 143616 | 0x7f1873783780 | 0x7f1872e259c0 | 17483241993165 | 17483242000869 | 17483242168709 | 17483242170971 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 320 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 145344 | 0x7f1873783600 | 0x7f1872e25a00 | 17483242192280 | 17483242201989 | 17483242295589 | 17483242297757 |
| 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 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 147584 | 0x7f1875b62480 | 0x7f1872e25a40 | 17483242311967 | 17483242319589 | 17483242498149 | 17483242500272 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 326 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 149568 | 0x7f1875b62300 | 0x7f1872e25a80 | 17483242513952 | 17483242522309 | 17483242702309 | 17483242704557 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 329 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 151552 | 0x7f1875b62180 | 0x7f1872e25ac0 | 17483242717956 | 17483242725669 | 17483242834150 | 17483242836183 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 332 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 154304 | 0x7f1875b62000 | 0x7f1872e25b00 | 17483242850073 | 17483242858150 | 17483243037350 | 17483243039378 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 335 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 156288 | 0x7f1873783e80 | 0x7f1872e25b40 | 17483243059968 | 17483243069510 | 17483243169350 | 17483243171375 |
| 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 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 158784 | 0x7f1873783d00 | 0x7f1872e25b80 | 17483243186284 | 17483243193670 | 17483243374310 | 17483243376489 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 341 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 161024 | 0x7f1873783b80 | 0x7f1872e25bc0 | 17483243390189 | 17483243398310 | 17483243580230 | 17483243582114 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 344 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 163264 | 0x7f1873783a00 | 0x7f1872e25c00 | 17483243596244 | 17483243603910 | 17483243724550 | 17483243726820 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 347 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 166528 | 0x7f1873783880 | 0x7f1872e25c40 | 17483243740410 | 17483243748390 | 17483243952711 | 17483243996813 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 350 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 168512 | 0x7f1873783700 | 0x7f1872e25c80 | 17483244013043 | 17483244023431 | 17483244131591 | 17483244133450 |
| 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 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 171264 | 0x7f1875b62580 | 0x7f1872e25cc0 | 17483244147980 | 17483244156391 | 17483244338951 | 17483244340855 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 356 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 173760 | 0x7f1875b62400 | 0x7f1872e25d00 | 17483244354824 | 17483244362951 | 17483244547751 | 17483244549679 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 359 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 176256 | 0x7f1875b62280 | 0x7f1872e25d40 | 17483244563789 | 17483244571911 | 17483244704551 | 17483244706405 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 362 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 179776 | 0x7f1875b62100 | 0x7f1872e25d80 | 17483244721485 | 17483244729511 | 17483244960072 | 17483244978968 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 365 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 182272 | 0x7f1873783f80 | 0x7f1872e25dc0 | 17483244994688 | 17483245005352 | 17483245130472 | 17483245132284 |
| 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 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 185536 | 0x7f1873783e00 | 0x7f1872e25e00 | 17483245147344 | 17483245155272 | 17483245346632 | 17483245348418 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 371 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 188544 | 0x7f1873783c80 | 0x7f1872e25e40 | 17483245365008 | 17483245372712 | 17483245563912 | 17483245565783 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 374 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 191552 | 0x7f1873783b00 | 0x7f1872e25e80 | 17483245580352 | 17483245589032 | 17483245746953 | 17483245748858 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 377 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 195840 | 0x7f1873783980 | 0x7f1872e25ec0 | 17483245765558 | 17483245773033 | 17483246054793 | 17483246080060 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 380 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 198592 | 0x7f1873783800 | 0x7f1872e25f00 | 17483246097949 | 17483246108233 | 17483246255113 | 17483246257125 |
| 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 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 202368 | 0x7f1873783680 | 0x7f1872e25f40 | 17483246272795 | 17483246280393 | 17483246489353 | 17483246534608 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 386 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 205888 | 0x7f1875b62500 | 0x7f1872e25f80 | 17483246544158 | 17483246553833 | 17483246762154 | 17483246783111 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 389 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 209408 | 0x7f1875b62380 | 0x7f1872e25fc0 | 17483246791571 | 17483246801354 | 17483246985034 | 17483246987116 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 392 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 214464 | 0x7f1875b62200 | 0x7f1872e26000 | 17483247001866 | 17483247009674 | 17483247342154 | 17483247361076 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 395 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 217728 | 0x7f1875b62080 | 0x7f1872e26040 | 17483247378846 | 17483247389674 | 17483247554154 | 17483247556071 |
| 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 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 222016 | 0x7f1873783f00 | 0x7f1872e26080 | 17483247571151 | 17483247578794 | 17483247806475 | 17483247824984 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 401 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 226048 | 0x7f1873783d80 | 0x7f1872e260c0 | 17483247832964 | 17483247843275 | 17483248073835 | 17483248092418 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 404 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 230080 | 0x7f1873783c00 | 0x7f1872e26100 | 17483248100777 | 17483248110955 | 17483248320395 | 17483248335341 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 407 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 235904 | 0x7f1873783a80 | 0x7f1872e26140 | 17483248344921 | 17483248354635 | 17483248737836 | 17483248752681 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 410 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 239424 | 0x7f1873783900 | 0x7f1872e26180 | 17483248769080 | 17483248779276 | 17483248963116 | 17483248965005 |
| 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 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 244224 | 0x7f1873783780 | 0x7f1872e261c0 | 17483248980235 | 17483248987916 | 17483249238796 | 17483249255098 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 416 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 248768 | 0x7f1873783600 | 0x7f1872e26200 | 17483249267177 | 17483249277196 | 17483249523276 | 17483249539250 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 419 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 253312 | 0x7f1875b62480 | 0x7f1872e26240 | 17483249547890 | 17483249557996 | 17483249793517 | 17483249809573 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 422 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 8 | 24 | 255552 | 0x7f1875b62300 | 0x7f1872e26280 | 17483249820523 | 17483249830317 | 17483250280717 | 17483250301810 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 425 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 259840 | 0x7f1875b62180 | 0x7f1872e262c0 | 17483250319300 | 17483250329357 | 17483250553198 | 17483250576433 |
| 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 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 265664 | 0x7f1875b62000 | 0x7f1872e26300 | 17483250586943 | 17483250596558 | 17483250895438 | 17483250916585 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 431 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 271232 | 0x7f1873783e80 | 0x7f1872e26340 | 17483250927944 | 17483250936718 | 17483251236238 | 17483251257746 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 434 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 8 | 24 | 273216 | 0x7f1873783d00 | 0x7f1872e26380 | 17483251269725 | 17483251280078 | 17483251573999 | 17483251592557 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 437 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 8 | 24 | 275712 | 0x7f1873783b80 | 0x7f1872e263c0 | 17483251602337 | 17483251613199 | 17483252167279 | 17483252188442 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 440 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 280768 | 0x7f1873783a00 | 0x7f1872e26400 | 17483252206911 | 17483252217359 | 17483252478960 | 17483252500254 |
| 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 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 287616 | 0x7f1873783880 | 0x7f1872e26440 | 17483252509143 | 17483252519760 | 17483252869840 | 17483252891004 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 446 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 294208 | 0x7f1873783700 | 0x7f1872e26480 | 17483252899913 | 17483252910000 | 17483253260560 | 17483253278534 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 449 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 8 | 24 | 296960 | 0x7f1875b62580 | 0x7f1872e264c0 | 17483253288703 | 17483253298640 | 17483253643441 | 17483253658794 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 452 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 8 | 24 | 299968 | 0x7f1875b62400 | 0x7f1872e26500 | 17483253668433 | 17483253677841 | 17483254336401 | 17483254359266 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 455 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 8 | 24 | 302720 | 0x7f1875b62280 | 0x7f1872e26540 | 17483254378165 | 17483254387121 | 17483254831762 | 17483254853423 |
| 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 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 305472 | 0x7f1875b62100 | 0x7f1872e26580 | 17483254863573 | 17483254874002 | 17483255335762 | 17483255356850 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 461 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 308224 | 0x7f1873783f80 | 0x7f1872e265c0 | 17483255366060 | 17483255375603 | 17483255834163 | 17483255855217 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 464 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 8 | 24 | 310976 | 0x7f1873783e00 | 0x7f1872e26600 | 17483255863677 | 17483255873523 | 17483256322803 | 17483256344024 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 467 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 8 | 24 | 313216 | 0x7f1873783c80 | 0x7f1872e26640 | 17483256353034 | 17483256362964 | 17483257228884 | 17483257247641 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 470 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 8 | 24 | 315968 | 0x7f1873783b00 | 0x7f1872e26680 | 17483257266040 | 17483257276084 | 17483258127125 | 17483258152758 |
| 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 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 318720 | 0x7f1873783980 | 0x7f1872e266c0 | 17483258162017 | 17483258171765 | 17483259053526 | 17483259098883 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 476 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 321472 | 0x7f1873783800 | 0x7f1872e26700 | 17483259107843 | 17483259117686 | 17483259994807 | 17483260039629 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 479 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 8 | 24 | 324224 | 0x7f1873783680 | 0x7f1872e26740 | 17483260051099 | 17483260062167 | 17483260917848 | 17483260960475 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 482 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 8 | 24 | 326464 | 0x7f1875b62500 | 0x7f1872e26780 | 17483260973415 | 17483260982968 | 17483262678810 | 17483262749359 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 485 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 8 | 24 | 329216 | 0x7f1875b62380 | 0x7f1872e267c0 | 17483262766989 | 17483262776890 | 17483264439292 | 17483264507304 |
| 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 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 331968 | 0x7f1875b62200 | 0x7f1872e26800 | 17483264517204 | 17483264527292 | 17483266249694 | 17483266318317 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 491 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 12 | 24 | 334720 | 0x7f1875b62080 | 0x7f1872e26840 | 17483266330487 | 17483266338974 | 17483268051616 | 17483268117781 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 494 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 8 | 24 | 337472 | 0x7f1873783f00 | 0x7f1872e26880 | 17483268129480 | 17483268145856 | 17483269817217 | 17483269884005 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 497 | 216328 | 216328 | 4194304 | 256 | 0 | 0 | 8 | 24 | 0 | 0x7f1873783d80 | 0x7f1872e268c0 | 17483269892915 | 17483269906818 | 17483273261701 | 17483273338186 |