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 | 222418 | 222418 | 33554432 | 256 | 0 | 0 | 4 | 32 | 4160 | 0x0 | 0x7f66d0e04280 | 17589313238708 | 17589313263708 | 17589313504348 | 17589313614998 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 222418 | 222418 | 32768 | 256 | 0 | 0 | 12 | 24 | 13888 | 0x0 | 0x7f66d0e23f80 | 17589318283979 | 17589318300033 | 17589318313633 | 17589318330788 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 5 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 14336 | 0x7f66d3e02380 | 0x7f66d0e23fc0 | 17589318336618 | 17589318384193 | 17589318476193 | 17589318478204 |
| 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 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15040 | 0x7f66d3e02200 | 0x7f66d0e24000 | 17589318500434 | 17589318509953 | 17589318688833 | 17589318690899 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 11 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15488 | 0x7f66d3e02080 | 0x7f66d0e24040 | 17589318704439 | 17589318712833 | 17589318891074 | 17589318892904 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 14 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 15936 | 0x7f66d17d3f00 | 0x7f66d0e24080 | 17589318906773 | 17589318915074 | 17589319008674 | 17589319010541 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 17 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 16384 | 0x7f66d17d3d80 | 0x7f66d0e240c0 | 17589319025980 | 17589319034114 | 17589319125954 | 17589319127758 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 20 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 17088 | 0x7f66d17d3c00 | 0x7f66d0e24100 | 17589319154967 | 17589319165634 | 17589319257794 | 17589319259524 |
| 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 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 16 | 24 | 17792 | 0x7f66d17d3a80 | 0x7f66d0e24140 | 17589319279564 | 17589319289794 | 17589319467874 | 17589319469629 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 26 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 16 | 24 | 18496 | 0x7f66d17d3900 | 0x7f66d0e24180 | 17589319493608 | 17589319504354 | 17589319684834 | 17589319686904 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 29 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19200 | 0x7f66d17d3780 | 0x7f66d0e241c0 | 17589319708413 | 17589319718914 | 17589319812995 | 17589319814930 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 32 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19904 | 0x7f66d17d3600 | 0x7f66d0e24200 | 17589319836260 | 17589319846915 | 17589319940355 | 17589319942097 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 35 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 20608 | 0x7f66d3e02480 | 0x7f66d0e24240 | 17589319963946 | 17589319974435 | 17589320068675 | 17589320070474 |
| 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 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 16 | 24 | 21312 | 0x7f66d3e02300 | 0x7f66d0e24280 | 17589320092803 | 17589320103555 | 17589320283715 | 17589320285638 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 41 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22016 | 0x7f66d3e02180 | 0x7f66d0e242c0 | 17589320305068 | 17589320324835 | 17589320505795 | 17589320507593 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 44 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22720 | 0x7f66d3e02000 | 0x7f66d0e24300 | 17589320524252 | 17589320533315 | 17589320626115 | 17589320627980 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 47 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 23424 | 0x7f66d17d3e80 | 0x7f66d0e24340 | 17589320651369 | 17589320660996 | 17589320753796 | 17589320755676 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 50 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 24128 | 0x7f66d17d3d00 | 0x7f66d0e24380 | 17589320776826 | 17589320787396 | 17589320879716 | 17589320881433 |
| 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 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 16 | 24 | 24832 | 0x7f66d17d3b80 | 0x7f66d0e243c0 | 17589320904152 | 17589320914596 | 17589321092996 | 17589321094738 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 56 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 16 | 24 | 25536 | 0x7f66d17d3a00 | 0x7f66d0e24400 | 17589321111057 | 17589321119716 | 17589321300356 | 17589321302052 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 59 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26240 | 0x7f66d17d3880 | 0x7f66d0e24440 | 17589321318302 | 17589321345636 | 17589321438916 | 17589321440829 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 62 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26944 | 0x7f66d17d3700 | 0x7f66d0e24480 | 17589321457968 | 17589321493796 | 17589321586757 | 17589321588635 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 65 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 27648 | 0x7f66d3e02580 | 0x7f66d0e244c0 | 17589321609094 | 17589321619717 | 17589321712197 | 17589321713852 |
| 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 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 16 | 24 | 28608 | 0x7f66d3e02400 | 0x7f66d0e24500 | 17589321732571 | 17589321748837 | 17589321928357 | 17589321930076 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 71 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 16 | 24 | 29312 | 0x7f66d3e02280 | 0x7f66d0e24540 | 17589321944746 | 17589321954597 | 17589322135077 | 17589322136431 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 74 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 30016 | 0x7f66d3e02100 | 0x7f66d0e24580 | 17589322153031 | 17589322160997 | 17589322253637 | 17589322254978 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 77 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 8 | 24 | 30976 | 0x7f66d17d3f80 | 0x7f66d0e245c0 | 17589322270838 | 17589322278597 | 17589322370597 | 17589322371955 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 80 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 31680 | 0x7f66d17d3e00 | 0x7f66d0e24600 | 17589322393805 | 17589322404677 | 17589322497798 | 17589322499222 |
| 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 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 16 | 24 | 32640 | 0x7f66d17d3c80 | 0x7f66d0e24640 | 17589322515471 | 17589322523878 | 17589322703238 | 17589322704567 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 86 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 33600 | 0x7f66d17d3b00 | 0x7f66d0e24680 | 17589322723326 | 17589322731398 | 17589322913318 | 17589322914641 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 89 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 34560 | 0x7f66d17d3980 | 0x7f66d0e246c0 | 17589322929561 | 17589322937318 | 17589323031558 | 17589323032968 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 92 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 8 | 24 | 35520 | 0x7f66d17d3800 | 0x7f66d0e24700 | 17589323049148 | 17589323057318 | 17589323150918 | 17589323152135 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 95 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 36224 | 0x7f66d17d3680 | 0x7f66d0e24740 | 17589323172585 | 17589323183078 | 17589323276518 | 17589323277722 |
| 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 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 37184 | 0x7f66d3e02500 | 0x7f66d0e24780 | 17589323291952 | 17589323300039 | 17589323480359 | 17589323481567 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 101 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 38144 | 0x7f66d3e02380 | 0x7f66d0e247c0 | 17589323496877 | 17589323504839 | 17589323683719 | 17589323684982 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 104 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 39104 | 0x7f66d3e02200 | 0x7f66d0e24800 | 17589323700981 | 17589323709639 | 17589323803239 | 17589323804559 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 107 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 8 | 24 | 40320 | 0x7f66d3e02080 | 0x7f66d0e24840 | 17589323818738 | 17589323826759 | 17589323920519 | 17589323921726 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 110 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 41280 | 0x7f66d17d3f00 | 0x7f66d0e24880 | 17589323941755 | 17589323952839 | 17589324046279 | 17589324047523 |
| 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 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 42240 | 0x7f66d17d3d80 | 0x7f66d0e248c0 | 17589324061602 | 17589324069799 | 17589324247400 | 17589324248708 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 116 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 43200 | 0x7f66d17d3c00 | 0x7f66d0e24900 | 17589324262237 | 17589324270760 | 17589324451240 | 17589324452472 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 119 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 8 | 24 | 44160 | 0x7f66d17d3a80 | 0x7f66d0e24940 | 17589324467132 | 17589324477320 | 17589324571560 | 17589324572719 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 122 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 45376 | 0x7f66d17d3900 | 0x7f66d0e24980 | 17589324586559 | 17589324595080 | 17589324689480 | 17589324690776 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 125 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 46336 | 0x7f66d17d3780 | 0x7f66d0e249c0 | 17589324711376 | 17589324722600 | 17589324815240 | 17589324816543 |
| 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 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 47552 | 0x7f66d17d3600 | 0x7f66d0e24a00 | 17589324830653 | 17589324839400 | 17589325017640 | 17589325018848 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 131 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 48512 | 0x7f66d3e02480 | 0x7f66d0e24a40 | 17589325034048 | 17589325041960 | 17589325220681 | 17589325222043 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 134 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 8 | 24 | 49472 | 0x7f66d3e02300 | 0x7f66d0e24a80 | 17589325236402 | 17589325245161 | 17589325337801 | 17589325339060 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 137 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 50688 | 0x7f66d3e02180 | 0x7f66d0e24ac0 | 17589325354429 | 17589325364681 | 17589325459241 | 17589325460547 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 140 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 51648 | 0x7f66d3e02000 | 0x7f66d0e24b00 | 17589325482006 | 17589325492681 | 17589325584521 | 17589325585794 |
| 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 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 52864 | 0x7f66d17d3e80 | 0x7f66d0e24b40 | 17589325603393 | 17589325610601 | 17589325791721 | 17589325792968 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 146 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 54080 | 0x7f66d17d3d00 | 0x7f66d0e24b80 | 17589325807898 | 17589325815721 | 17589325996522 | 17589325997943 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 149 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 8 | 24 | 55296 | 0x7f66d17d3b80 | 0x7f66d0e24bc0 | 17589326012003 | 17589326020842 | 17589326114762 | 17589326116080 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 152 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 56768 | 0x7f66d17d3a00 | 0x7f66d0e24c00 | 17589326132380 | 17589326140362 | 17589326236362 | 17589326237587 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 155 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 57728 | 0x7f66d17d3880 | 0x7f66d0e24c40 | 17589326258337 | 17589326269322 | 17589326362762 | 17589326364134 |
| 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 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 58944 | 0x7f66d17d3700 | 0x7f66d0e24c80 | 17589326378423 | 17589326387402 | 17589326567082 | 17589326568339 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 161 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 60160 | 0x7f66d3e02580 | 0x7f66d0e24cc0 | 17589326582008 | 17589326589962 | 17589326769482 | 17589326770773 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 164 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 8 | 24 | 61376 | 0x7f66d3e02400 | 0x7f66d0e24d00 | 17589326784823 | 17589326792682 | 17589326886763 | 17589326888040 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 167 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 62848 | 0x7f66d3e02280 | 0x7f66d0e24d40 | 17589326903370 | 17589326912043 | 17589327011083 | 17589327012357 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 170 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 63808 | 0x7f66d3e02100 | 0x7f66d0e24d80 | 17589327033267 | 17589327043883 | 17589327137323 | 17589327138734 |
| 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 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 65024 | 0x7f66d17d3f80 | 0x7f66d0e24dc0 | 17589327154024 | 17589327164523 | 17589327343083 | 17589327344429 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 176 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 66240 | 0x7f66d17d3e00 | 0x7f66d0e24e00 | 17589327358288 | 17589327366923 | 17589327546283 | 17589327547574 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 179 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 8 | 24 | 67456 | 0x7f66d17d3c80 | 0x7f66d0e24e40 | 17589327561303 | 17589327569483 | 17589327663243 | 17589327664481 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 182 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 68928 | 0x7f66d17d3b00 | 0x7f66d0e24e80 | 17589327678550 | 17589327688364 | 17589327792524 | 17589327794027 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 185 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 70144 | 0x7f66d17d3980 | 0x7f66d0e24ec0 | 17589327814987 | 17589327825804 | 17589327918444 | 17589327919724 |
| 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 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 71616 | 0x7f66d17d3800 | 0x7f66d0e24f00 | 17589327936234 | 17589327944044 | 17589328124044 | 17589328125339 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 191 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 72832 | 0x7f66d17d3680 | 0x7f66d0e24f40 | 17589328139949 | 17589328149004 | 17589328330284 | 17589328331654 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 194 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 8 | 24 | 74048 | 0x7f66d3e02500 | 0x7f66d0e24f80 | 17589328344903 | 17589328353004 | 17589328445964 | 17589328447281 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 197 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 75776 | 0x7f66d3e02380 | 0x7f66d0e24fc0 | 17589328460940 | 17589328470444 | 17589328577005 | 17589328578207 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 200 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 76992 | 0x7f66d3e02200 | 0x7f66d0e25000 | 17589328599387 | 17589328610285 | 17589328704365 | 17589328705654 |
| 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 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 78464 | 0x7f66d3e02080 | 0x7f66d0e25040 | 17589328723524 | 17589328731565 | 17589328912525 | 17589328913849 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 206 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 79936 | 0x7f66d17d3f00 | 0x7f66d0e25080 | 17589328927898 | 17589328937485 | 17589329116845 | 17589329118074 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 209 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 8 | 24 | 81408 | 0x7f66d17d3d80 | 0x7f66d0e250c0 | 17589329131973 | 17589329141005 | 17589329236845 | 17589329238071 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 212 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 83136 | 0x7f66d17d3c00 | 0x7f66d0e25100 | 17589329252570 | 17589329261165 | 17589329377325 | 17589329378607 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 215 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 84352 | 0x7f66d17d3a80 | 0x7f66d0e25140 | 17589329413626 | 17589329423565 | 17589329517006 | 17589329518353 |
| 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 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 85824 | 0x7f66d17d3900 | 0x7f66d0e25180 | 17589329533043 | 17589329541006 | 17589329721006 | 17589329722418 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 221 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 87296 | 0x7f66d17d3780 | 0x7f66d0e251c0 | 17589329737708 | 17589329745806 | 17589329926286 | 17589329927593 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 224 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 88768 | 0x7f66d17d3600 | 0x7f66d0e25200 | 17589329942133 | 17589329950286 | 17589330045166 | 17589330046470 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 227 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 90752 | 0x7f66d3e02480 | 0x7f66d0e25240 | 17589330060860 | 17589330069646 | 17589330191086 | 17589330192446 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 230 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 91968 | 0x7f66d3e02300 | 0x7f66d0e25280 | 17589330212936 | 17589330223566 | 17589330318126 | 17589330319623 |
| 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 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 93440 | 0x7f66d3e02180 | 0x7f66d0e252c0 | 17589330334423 | 17589330342287 | 17589330522927 | 17589330524508 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 236 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 94912 | 0x7f66d3e02000 | 0x7f66d0e25300 | 17589330538507 | 17589330546447 | 17589330725807 | 17589330727343 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 239 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 96384 | 0x7f66d17d3e80 | 0x7f66d0e25340 | 17589330742112 | 17589330749647 | 17589330844527 | 17589330845900 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 242 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 98368 | 0x7f66d17d3d00 | 0x7f66d0e25380 | 17589330860569 | 17589330868527 | 17589330995087 | 17589330996666 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 245 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 99584 | 0x7f66d17d3b80 | 0x7f66d0e253c0 | 17589331016015 | 17589331026927 | 17589331120047 | 17589331121443 |
| 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 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 101312 | 0x7f66d17d3a00 | 0x7f66d0e25400 | 17589331135842 | 17589331144047 | 17589331323568 | 17589331324777 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 251 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 102784 | 0x7f66d17d3880 | 0x7f66d0e25440 | 17589331338737 | 17589331346608 | 17589331526928 | 17589331528402 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 254 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 104256 | 0x7f66d17d3700 | 0x7f66d0e25480 | 17589331543152 | 17589331551248 | 17589331645488 | 17589331647009 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 257 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 106240 | 0x7f66d3e02580 | 0x7f66d0e254c0 | 17589331660659 | 17589331668528 | 17589331799248 | 17589331800615 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 260 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 107712 | 0x7f66d3e02400 | 0x7f66d0e25500 | 17589331820265 | 17589331831248 | 17589331924528 | 17589331925922 |
| 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 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 16 | 24 | 109440 | 0x7f66d3e02280 | 0x7f66d0e25540 | 17589331941792 | 17589331949648 | 17589332128529 | 17589332129947 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 266 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 16 | 24 | 111168 | 0x7f66d3e02100 | 0x7f66d0e25580 | 17589332143717 | 17589332151409 | 17589332331089 | 17589332332562 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 269 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 8 | 24 | 112896 | 0x7f66d17d3f80 | 0x7f66d0e255c0 | 17589332346742 | 17589332354609 | 17589332449969 | 17589332451389 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 272 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 115136 | 0x7f66d17d3e00 | 0x7f66d0e25600 | 17589332465949 | 17589332474609 | 17589332613009 | 17589332614385 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 275 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 116608 | 0x7f66d17d3c80 | 0x7f66d0e25640 | 17589332635234 | 17589332646769 | 17589332741649 | 17589332743012 |
| 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 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 16 | 24 | 118336 | 0x7f66d17d3b00 | 0x7f66d0e25680 | 17589332758951 | 17589332766929 | 17589332946449 | 17589332947826 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 281 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 16 | 24 | 120064 | 0x7f66d17d3980 | 0x7f66d0e256c0 | 17589332963036 | 17589332971890 | 17589333151890 | 17589333153371 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 284 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 121792 | 0x7f66d17d3800 | 0x7f66d0e25700 | 17589333167511 | 17589333177170 | 17589333274130 | 17589333275428 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 287 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 124032 | 0x7f66d17d3680 | 0x7f66d0e25740 | 17589333291328 | 17589333301010 | 17589333445490 | 17589333446774 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 290 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 125504 | 0x7f66d3e02500 | 0x7f66d0e25780 | 17589333468203 | 17589333479090 | 17589333574290 | 17589333575530 |
| 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 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 127488 | 0x7f66d3e02380 | 0x7f66d0e257c0 | 17589333591600 | 17589333601170 | 17589333782610 | 17589333783965 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 296 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 129216 | 0x7f66d3e02200 | 0x7f66d0e25800 | 17589333798415 | 17589333806610 | 17589333989491 | 17589333990750 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 299 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 130944 | 0x7f66d3e02080 | 0x7f66d0e25840 | 17589334004710 | 17589334014931 | 17589334114931 | 17589334116287 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 302 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 133440 | 0x7f66d17d3f00 | 0x7f66d0e25880 | 17589334132116 | 17589334140051 | 17589334295411 | 17589334296692 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 305 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 134912 | 0x7f66d17d3d80 | 0x7f66d0e258c0 | 17589334317962 | 17589334329331 | 17589334425171 | 17589334426359 |
| 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 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 136896 | 0x7f66d17d3c00 | 0x7f66d0e25900 | 17589334442768 | 17589334450451 | 17589334629971 | 17589334631364 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 311 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 138880 | 0x7f66d17d3a80 | 0x7f66d0e25940 | 17589334646753 | 17589334654611 | 17589334835892 | 17589334837228 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 314 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 140864 | 0x7f66d17d3900 | 0x7f66d0e25980 | 17589334851958 | 17589334860052 | 17589334967092 | 17589334968365 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 317 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 143616 | 0x7f66d17d3780 | 0x7f66d0e259c0 | 17589334983785 | 17589334991732 | 17589335162612 | 17589335163910 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 320 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 145344 | 0x7f66d17d3600 | 0x7f66d0e25a00 | 17589335185189 | 17589335195892 | 17589335290612 | 17589335291957 |
| 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 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 147584 | 0x7f66d3e02480 | 0x7f66d0e25a40 | 17589335307866 | 17589335315892 | 17589335496532 | 17589335497891 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 326 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 149568 | 0x7f66d3e02300 | 0x7f66d0e25a80 | 17589335512721 | 17589335520852 | 17589335702773 | 17589335704046 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 329 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 151552 | 0x7f66d3e02180 | 0x7f66d0e25ac0 | 17589335719096 | 17589335727093 | 17589335836853 | 17589335838193 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 332 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 154304 | 0x7f66d3e02000 | 0x7f66d0e25b00 | 17589335853982 | 17589335861973 | 17589336043093 | 17589336044268 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 335 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 156288 | 0x7f66d17d3e80 | 0x7f66d0e25b40 | 17589336066637 | 17589336076533 | 17589336177493 | 17589336178684 |
| 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 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 158784 | 0x7f66d17d3d00 | 0x7f66d0e25b80 | 17589336195834 | 17589336203733 | 17589336389813 | 17589336391059 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 341 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 161024 | 0x7f66d17d3b80 | 0x7f66d0e25bc0 | 17589336405248 | 17589336415253 | 17589336601334 | 17589336602643 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 344 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 163264 | 0x7f66d17d3a00 | 0x7f66d0e25c00 | 17589336617393 | 17589336627574 | 17589336749174 | 17589336750460 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 347 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 166528 | 0x7f66d17d3880 | 0x7f66d0e25c40 | 17589336765039 | 17589336773654 | 17589336980054 | 17589337001643 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 350 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 168512 | 0x7f66d17d3700 | 0x7f66d0e25c80 | 17589337017113 | 17589337028054 | 17589337140054 | 17589337141460 |
| 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 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 171264 | 0x7f66d3e02580 | 0x7f66d0e25cc0 | 17589337156499 | 17589337165014 | 17589337349654 | 17589337351014 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 356 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 173760 | 0x7f66d3e02400 | 0x7f66d0e25d00 | 17589337365884 | 17589337374135 | 17589337561175 | 17589337562399 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 359 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 176256 | 0x7f66d3e02280 | 0x7f66d0e25d40 | 17589337577068 | 17589337586775 | 17589337721495 | 17589337722815 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 362 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 179776 | 0x7f66d3e02100 | 0x7f66d0e25d80 | 17589337736834 | 17589337745655 | 17589337977815 | 17589337996778 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 365 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 182272 | 0x7f66d17d3f80 | 0x7f66d0e25dc0 | 17589338011227 | 17589338022295 | 17589338149015 | 17589338150454 |
| 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 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 185536 | 0x7f66d17d3e00 | 0x7f66d0e25e00 | 17589338165563 | 17589338173175 | 17589338364056 | 17589338365588 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 371 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 188544 | 0x7f66d17d3c80 | 0x7f66d0e25e40 | 17589338379878 | 17589338388056 | 17589338579896 | 17589338581373 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 374 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 191552 | 0x7f66d17d3b00 | 0x7f66d0e25e80 | 17589338595513 | 17589338603416 | 17589338763256 | 17589338764678 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 377 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 195840 | 0x7f66d17d3980 | 0x7f66d0e25ec0 | 17589338779378 | 17589338793176 | 17589339076056 | 17589339119869 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 380 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 198592 | 0x7f66d17d3800 | 0x7f66d0e25f00 | 17589339135479 | 17589339146297 | 17589339294777 | 17589339296125 |
| 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 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 202368 | 0x7f66d17d3680 | 0x7f66d0e25f40 | 17589339311404 | 17589339318937 | 17589339527737 | 17589339571198 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 386 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 205888 | 0x7f66d3e02500 | 0x7f66d0e25f80 | 17589339578808 | 17589339589017 | 17589339797337 | 17589339837571 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 389 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 209408 | 0x7f66d3e02380 | 0x7f66d0e25fc0 | 17589339844761 | 17589339855577 | 17589340041498 | 17589340042826 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 392 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 214464 | 0x7f66d3e02200 | 0x7f66d0e26000 | 17589340058635 | 17589340066618 | 17589340401178 | 17589340441546 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 395 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 217728 | 0x7f66d3e02080 | 0x7f66d0e26040 | 17589340458105 | 17589340469018 | 17589340636058 | 17589340637321 |
| 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 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 222016 | 0x7f66d17d3f00 | 0x7f66d0e26080 | 17589340651780 | 17589340659898 | 17589340888699 | 17589340929013 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 401 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 226048 | 0x7f66d17d3d80 | 0x7f66d0e260c0 | 17589340936203 | 17589340946619 | 17589341175579 | 17589341192257 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 404 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 230080 | 0x7f66d17d3c00 | 0x7f66d0e26100 | 17589341200117 | 17589341210139 | 17589341421499 | 17589341437701 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 407 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 235904 | 0x7f66d17d3a80 | 0x7f66d0e26140 | 17589341446800 | 17589341456379 | 17589341841980 | 17589341857320 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 410 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 239424 | 0x7f66d17d3900 | 0x7f66d0e26180 | 17589341873179 | 17589341883900 | 17589342071580 | 17589342072924 |
| 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 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 244224 | 0x7f66d17d3780 | 0x7f66d0e261c0 | 17589342097494 | 17589342107900 | 17589342357820 | 17589342400046 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 416 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 248768 | 0x7f66d17d3600 | 0x7f66d0e26200 | 17589342407536 | 17589342417980 | 17589342666781 | 17589342710088 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 419 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 253312 | 0x7f66d3e02480 | 0x7f66d0e26240 | 17589342717578 | 17589342728221 | 17589342964541 | 17589342984161 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 422 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 8 | 24 | 255552 | 0x7f66d3e02300 | 0x7f66d0e26280 | 17589342991931 | 17589343002461 | 17589343456381 | 17589343475249 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 425 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 259840 | 0x7f66d3e02180 | 0x7f66d0e262c0 | 17589343492078 | 17589343502781 | 17589343729022 | 17589343772681 |
| 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 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 265664 | 0x7f66d3e02000 | 0x7f66d0e26300 | 17589343780761 | 17589343791102 | 17589344089182 | 17589344132342 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 431 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 271232 | 0x7f66d17d3e80 | 0x7f66d0e26340 | 17589344141602 | 17589344151262 | 17589344449503 | 17589344492603 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 434 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 8 | 24 | 273216 | 0x7f66d17d3d00 | 0x7f66d0e26380 | 17589344501142 | 17589344511583 | 17589344808223 | 17589344827854 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 437 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 8 | 24 | 275712 | 0x7f66d17d3b80 | 0x7f66d0e263c0 | 17589344836504 | 17589344846783 | 17589345403584 | 17589345419329 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 440 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 280768 | 0x7f66d17d3a00 | 0x7f66d0e26400 | 17589345435889 | 17589345446464 | 17589345710624 | 17589345726521 |
| 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 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 287616 | 0x7f66d17d3880 | 0x7f66d0e26440 | 17589345734161 | 17589345744384 | 17589346094944 | 17589346119021 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 446 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 294208 | 0x7f66d17d3700 | 0x7f66d0e26480 | 17589346126501 | 17589346140704 | 17589346491265 | 17589346510451 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 449 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 8 | 24 | 296960 | 0x7f66d3e02580 | 0x7f66d0e264c0 | 17589346519121 | 17589346529505 | 17589346876705 | 17589346920471 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 452 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 8 | 24 | 299968 | 0x7f66d3e02400 | 0x7f66d0e26500 | 17589346928371 | 17589346938465 | 17589347600226 | 17589347643722 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 455 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 8 | 24 | 302720 | 0x7f66d3e02280 | 0x7f66d0e26540 | 17589347661702 | 17589347671426 | 17589348118947 | 17589348162819 |
| 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 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 305472 | 0x7f66d3e02100 | 0x7f66d0e26580 | 17589348170239 | 17589348180867 | 17589348644867 | 17589348688206 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 461 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 308224 | 0x7f66d17d3f80 | 0x7f66d0e265c0 | 17589348695675 | 17589348705987 | 17589349167908 | 17589349211152 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 464 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 8 | 24 | 310976 | 0x7f66d17d3e00 | 0x7f66d0e26600 | 17589349218722 | 17589349229028 | 17589349680549 | 17589349723669 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 467 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 8 | 24 | 313216 | 0x7f66d17d3c80 | 0x7f66d0e26640 | 17589349731509 | 17589349741989 | 17589350611430 | 17589350659275 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 470 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 8 | 24 | 315968 | 0x7f66d17d3b00 | 0x7f66d0e26680 | 17589350677735 | 17589350688230 | 17589351541191 | 17589351587202 |
| 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 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 318720 | 0x7f66d17d3980 | 0x7f66d0e266c0 | 17589351595962 | 17589351606311 | 17589352491272 | 17589352535398 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 476 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 321472 | 0x7f66d17d3800 | 0x7f66d0e26700 | 17589352543488 | 17589352553832 | 17589353432073 | 17589353475604 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 479 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 8 | 24 | 324224 | 0x7f66d17d3680 | 0x7f66d0e26740 | 17589353484194 | 17589353494793 | 17589354355274 | 17589354406140 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 482 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 8 | 24 | 326464 | 0x7f66d3e02500 | 0x7f66d0e26780 | 17589354414770 | 17589354425034 | 17589356122796 | 17589356192305 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 485 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 8 | 24 | 329216 | 0x7f66d3e02380 | 0x7f66d0e267c0 | 17589356208704 | 17589356219116 | 17589357884238 | 17589357954710 |
| 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 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 331968 | 0x7f66d3e02200 | 0x7f66d0e26800 | 17589357964060 | 17589357974158 | 17589359699760 | 17589359768664 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 491 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 12 | 24 | 334720 | 0x7f66d3e02080 | 0x7f66d0e26840 | 17589359776754 | 17589359787920 | 17589361504082 | 17589361573898 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 494 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 8 | 24 | 337472 | 0x7f66d17d3f00 | 0x7f66d0e26880 | 17589361583538 | 17589361594002 | 17589363267764 | 17589363344463 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 497 | 222418 | 222418 | 4194304 | 256 | 0 | 0 | 8 | 24 | 0 | 0x7f66d17d3d80 | 0x7f66d0e268c0 | 17589363352753 | 17589363381524 | 17589366739288 | 17589366811185 |