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 | 123357 | 123357 | 33554432 | 256 | 0 | 0 | 4 | 32 | 4160 | 0x0 | 0x7fafa1004280 | 15637372419940 | 15637372446181 | 15637372686822 | 15637372777182 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 123357 | 123357 | 32768 | 256 | 0 | 0 | 12 | 24 | 13888 | 0x0 | 0x7fafa1023f80 | 15637377518555 | 15637377534037 | 15637377547477 | 15637377564584 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 5 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 14336 | 0x7fafa3fb4380 | 0x7fafa1023fc0 | 15637377570134 | 15637377613717 | 15637377706678 | 15637377709121 |
| 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 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15040 | 0x7fafa3fb4200 | 0x7fafa1024000 | 15637377730661 | 15637377740118 | 15637377918038 | 15637377920336 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 11 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15488 | 0x7fafa3fb4080 | 0x7fafa1024040 | 15637377935466 | 15637377943319 | 15637378121719 | 15637378124042 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 14 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 15936 | 0x7fafa1987f00 | 0x7fafa1024080 | 15637378139241 | 15637378147959 | 15637378241080 | 15637378243409 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 17 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 16384 | 0x7fafa1987d80 | 0x7fafa10240c0 | 15637378259399 | 15637378267320 | 15637378359320 | 15637378361646 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 20 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 17088 | 0x7fafa1987c00 | 0x7fafa1024100 | 15637378389926 | 15637378400280 | 15637378492280 | 15637378494393 |
| 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 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 16 | 24 | 17792 | 0x7fafa1987a80 | 0x7fafa1024140 | 15637378516063 | 15637378532441 | 15637378711001 | 15637378713218 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 26 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 16 | 24 | 18496 | 0x7fafa1987900 | 0x7fafa1024180 | 15637378729298 | 15637378738201 | 15637378918842 | 15637378921154 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 29 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19200 | 0x7fafa1987780 | 0x7fafa10241c0 | 15637378936073 | 15637378944122 | 15637379037882 | 15637379040041 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 32 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19904 | 0x7fafa1987600 | 0x7fafa1024200 | 15637379058180 | 15637379073722 | 15637379166843 | 15637379169258 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 35 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 20608 | 0x7fafa3fb4480 | 0x7fafa1024240 | 15637379191947 | 15637379216603 | 15637379310843 | 15637379313185 |
| 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 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 16 | 24 | 21312 | 0x7fafa3fb4300 | 0x7fafa1024280 | 15637379331844 | 15637379343323 | 15637379523324 | 15637379525400 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 41 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22016 | 0x7fafa3fb4180 | 0x7fafa10242c0 | 15637379540130 | 15637379549564 | 15637379729084 | 15637379731285 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 44 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22720 | 0x7fafa3fb4000 | 0x7fafa1024300 | 15637379752265 | 15637379762525 | 15637379855965 | 15637379858082 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 47 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 23424 | 0x7fafa1987e80 | 0x7fafa1024340 | 15637379880262 | 15637379904765 | 15637379998205 | 15637380000489 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 50 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 24128 | 0x7fafa1987d00 | 0x7fafa1024380 | 15637380022639 | 15637380033085 | 15637380125726 | 15637380127936 |
| 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 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 16 | 24 | 24832 | 0x7fafa1987b80 | 0x7fafa10243c0 | 15637380146666 | 15637380155486 | 15637380335166 | 15637380337451 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 56 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 16 | 24 | 25536 | 0x7fafa1987a00 | 0x7fafa1024400 | 15637380359541 | 15637380367807 | 15637380548127 | 15637380550287 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 59 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26240 | 0x7fafa1987880 | 0x7fafa1024440 | 15637380570106 | 15637380579007 | 15637380673248 | 15637380675404 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 62 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26944 | 0x7fafa1987700 | 0x7fafa1024480 | 15637380693263 | 15637380701888 | 15637380795168 | 15637380797371 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 65 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 27648 | 0x7fafa3fb4580 | 0x7fafa10244c0 | 15637380817961 | 15637380828288 | 15637380920768 | 15637380922948 |
| 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 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 16 | 24 | 28608 | 0x7fafa3fb4400 | 0x7fafa1024500 | 15637380946128 | 15637380956449 | 15637381136929 | 15637381139043 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 71 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 16 | 24 | 29312 | 0x7fafa3fb4280 | 0x7fafa1024540 | 15637381153603 | 15637381162529 | 15637381343490 | 15637381345779 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 74 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 30016 | 0x7fafa3fb4100 | 0x7fafa1024580 | 15637381366718 | 15637381377250 | 15637381470210 | 15637381472366 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 77 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 8 | 24 | 30976 | 0x7fafa1987f80 | 0x7fafa10245c0 | 15637381490935 | 15637381518690 | 15637381611811 | 15637381614033 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 80 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 31680 | 0x7fafa1987e00 | 0x7fafa1024600 | 15637381636182 | 15637381646371 | 15637381739331 | 15637381741520 |
| 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 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 16 | 24 | 32640 | 0x7fafa1987c80 | 0x7fafa1024640 | 15637381761669 | 15637381771811 | 15637381951652 | 15637381953305 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 86 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 33600 | 0x7fafa1987b00 | 0x7fafa1024680 | 15637381968205 | 15637381975812 | 15637382157412 | 15637382159310 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 89 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 34560 | 0x7fafa1987980 | 0x7fafa10246c0 | 15637382174050 | 15637382181893 | 15637382275333 | 15637382276978 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 92 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 8 | 24 | 35520 | 0x7fafa1987800 | 0x7fafa1024700 | 15637382291487 | 15637382299813 | 15637382393733 | 15637382395475 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 95 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 36224 | 0x7fafa1987680 | 0x7fafa1024740 | 15637382416454 | 15637382425893 | 15637382518534 | 15637382520212 |
| 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 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 37184 | 0x7fafa3fb4500 | 0x7fafa1024780 | 15637382535322 | 15637382543334 | 15637382723174 | 15637382724807 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 101 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 38144 | 0x7fafa3fb4380 | 0x7fafa10247c0 | 15637382739107 | 15637382747814 | 15637382928135 | 15637382929903 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 104 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 39104 | 0x7fafa3fb4200 | 0x7fafa1024800 | 15637382946362 | 15637382954535 | 15637383048615 | 15637383050270 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 107 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 8 | 24 | 40320 | 0x7fafa3fb4080 | 0x7fafa1024840 | 15637383064810 | 15637383072936 | 15637383166856 | 15637383168397 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 110 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 41280 | 0x7fafa1987f00 | 0x7fafa1024880 | 15637383188127 | 15637383199016 | 15637383293096 | 15637383294745 |
| 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 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 42240 | 0x7fafa1987d80 | 0x7fafa10248c0 | 15637383309904 | 15637383318216 | 15637383498057 | 15637383499710 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 116 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 43200 | 0x7fafa1987c00 | 0x7fafa1024900 | 15637383514260 | 15637383522377 | 15637383702858 | 15637383704465 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 119 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 8 | 24 | 44160 | 0x7fafa1987a80 | 0x7fafa1024940 | 15637383720295 | 15637383729418 | 15637383823818 | 15637383825433 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 122 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 45376 | 0x7fafa1987900 | 0x7fafa1024980 | 15637383841942 | 15637383849738 | 15637383944778 | 15637383946550 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 125 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 46336 | 0x7fafa1987780 | 0x7fafa10249c0 | 15637383967179 | 15637383977578 | 15637384071499 | 15637384073177 |
| 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 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 47552 | 0x7fafa1987600 | 0x7fafa1024a00 | 15637384087967 | 15637384096139 | 15637384276459 | 15637384278162 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 131 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 48512 | 0x7fafa3fb4480 | 0x7fafa1024a40 | 15637384294812 | 15637384302700 | 15637384483820 | 15637384485508 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 134 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 8 | 24 | 49472 | 0x7fafa3fb4300 | 0x7fafa1024a80 | 15637384502317 | 15637384510060 | 15637384603341 | 15637384605055 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 137 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 50688 | 0x7fafa3fb4180 | 0x7fafa1024ac0 | 15637384621385 | 15637384629901 | 15637384723181 | 15637384724822 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 140 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 51648 | 0x7fafa3fb4000 | 0x7fafa1024b00 | 15637384745272 | 15637384755501 | 15637384847341 | 15637384849110 |
| 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 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 52864 | 0x7fafa1987e80 | 0x7fafa1024b40 | 15637384865029 | 15637384872781 | 15637385053102 | 15637385054845 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 146 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 54080 | 0x7fafa1987d00 | 0x7fafa1024b80 | 15637385069355 | 15637385077742 | 15637385259823 | 15637385261420 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 149 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 8 | 24 | 55296 | 0x7fafa1987b80 | 0x7fafa1024bc0 | 15637385274810 | 15637385283183 | 15637385377583 | 15637385379198 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 152 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 56768 | 0x7fafa1987a00 | 0x7fafa1024c00 | 15637385393577 | 15637385402063 | 15637385497264 | 15637385498825 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 155 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 57728 | 0x7fafa1987880 | 0x7fafa1024c40 | 15637385518875 | 15637385529904 | 15637385622544 | 15637385624212 |
| 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 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 58944 | 0x7fafa1987700 | 0x7fafa1024c80 | 15637385639382 | 15637385647504 | 15637385827505 | 15637385829168 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 161 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 60160 | 0x7fafa3fb4580 | 0x7fafa1024cc0 | 15637385844107 | 15637385852785 | 15637386033745 | 15637386035353 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 164 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 8 | 24 | 61376 | 0x7fafa3fb4400 | 0x7fafa1024d00 | 15637386049923 | 15637386058545 | 15637386153906 | 15637386155670 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 167 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 62848 | 0x7fafa3fb4280 | 0x7fafa1024d40 | 15637386171410 | 15637386179346 | 15637386279026 | 15637386280877 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 170 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 63808 | 0x7fafa3fb4100 | 0x7fafa1024d80 | 15637386300217 | 15637386311346 | 15637386405267 | 15637386407075 |
| 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 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 65024 | 0x7fafa1987f80 | 0x7fafa1024dc0 | 15637386424314 | 15637386433427 | 15637386612467 | 15637386614450 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 176 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 66240 | 0x7fafa1987e00 | 0x7fafa1024e00 | 15637386629030 | 15637386637107 | 15637386817108 | 15637386818835 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 179 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 8 | 24 | 67456 | 0x7fafa1987c80 | 0x7fafa1024e40 | 15637386833445 | 15637386841108 | 15637386936148 | 15637386937893 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 182 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 68928 | 0x7fafa1987b00 | 0x7fafa1024e80 | 15637386952552 | 15637386960628 | 15637387065429 | 15637387067190 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 185 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 70144 | 0x7fafa1987980 | 0x7fafa1024ec0 | 15637387087549 | 15637387097909 | 15637387190709 | 15637387192407 |
| 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 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 71616 | 0x7fafa1987800 | 0x7fafa1024f00 | 15637387207377 | 15637387215349 | 15637387393910 | 15637387395752 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 191 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 72832 | 0x7fafa1987680 | 0x7fafa1024f40 | 15637387411782 | 15637387419990 | 15637387600310 | 15637387602148 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 194 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 8 | 24 | 74048 | 0x7fafa3fb4500 | 0x7fafa1024f80 | 15637387616777 | 15637387624471 | 15637387717751 | 15637387719525 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 197 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 75776 | 0x7fafa3fb4380 | 0x7fafa1024fc0 | 15637387733255 | 15637387740951 | 15637387847191 | 15637387849122 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 200 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 76992 | 0x7fafa3fb4200 | 0x7fafa1025000 | 15637387868822 | 15637387879351 | 15637387973752 | 15637387975469 |
| 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 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 78464 | 0x7fafa3fb4080 | 0x7fafa1025040 | 15637387990509 | 15637387998552 | 15637388178072 | 15637388179675 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 206 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 79936 | 0x7fafa1987f00 | 0x7fafa1025080 | 15637388193764 | 15637388201912 | 15637388380633 | 15637388382380 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 209 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 8 | 24 | 81408 | 0x7fafa1987d80 | 0x7fafa10250c0 | 15637388399040 | 15637388406873 | 15637388502233 | 15637388503897 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 212 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 83136 | 0x7fafa1987c00 | 0x7fafa1025100 | 15637388519167 | 15637388527034 | 15637388642714 | 15637388644444 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 215 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 84352 | 0x7fafa1987a80 | 0x7fafa1025140 | 15637388680183 | 15637388689594 | 15637388784154 | 15637388785881 |
| 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 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 85824 | 0x7fafa1987900 | 0x7fafa1025180 | 15637388800941 | 15637388809114 | 15637388988315 | 15637388990126 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 221 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 87296 | 0x7fafa1987780 | 0x7fafa10251c0 | 15637389005046 | 15637389012955 | 15637389191676 | 15637389193372 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 224 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 88768 | 0x7fafa1987600 | 0x7fafa1025200 | 15637389208322 | 15637389216636 | 15637389312316 | 15637389314009 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 227 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 90752 | 0x7fafa3fb4480 | 0x7fafa1025240 | 15637389329039 | 15637389338236 | 15637389459037 | 15637389460756 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 230 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 91968 | 0x7fafa3fb4300 | 0x7fafa1025280 | 15637389481655 | 15637389492317 | 15637389586237 | 15637389587973 |
| 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 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 93440 | 0x7fafa3fb4180 | 0x7fafa10252c0 | 15637389602863 | 15637389611037 | 15637389789918 | 15637389791588 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 236 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 94912 | 0x7fafa3fb4000 | 0x7fafa1025300 | 15637389806258 | 15637389814558 | 15637389994238 | 15637389995884 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 239 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 96384 | 0x7fafa1987e80 | 0x7fafa1025340 | 15637390011023 | 15637390019518 | 15637390114719 | 15637390116481 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 242 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 98368 | 0x7fafa1987d00 | 0x7fafa1025380 | 15637390134481 | 15637390143199 | 15637390270079 | 15637390271988 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 245 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 99584 | 0x7fafa1987b80 | 0x7fafa10253c0 | 15637390293517 | 15637390303519 | 15637390397120 | 15637390398735 |
| 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 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 101312 | 0x7fafa1987a00 | 0x7fafa1025400 | 15637390414694 | 15637390422880 | 15637390601440 | 15637390603210 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 251 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 102784 | 0x7fafa1987880 | 0x7fafa1025440 | 15637390618360 | 15637390626560 | 15637390807041 | 15637390808645 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 254 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 104256 | 0x7fafa1987700 | 0x7fafa1025480 | 15637390823945 | 15637390832001 | 15637390925921 | 15637390927683 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 257 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 106240 | 0x7fafa3fb4580 | 0x7fafa10254c0 | 15637390943082 | 15637390951202 | 15637391081602 | 15637391083289 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 260 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 107712 | 0x7fafa3fb4400 | 0x7fafa1025500 | 15637391103529 | 15637391114082 | 15637391207202 | 15637391208896 |
| 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 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 16 | 24 | 109440 | 0x7fafa3fb4280 | 0x7fafa1025540 | 15637391226116 | 15637391234402 | 15637391413763 | 15637391415412 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 266 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 16 | 24 | 111168 | 0x7fafa3fb4100 | 0x7fafa1025580 | 15637391429611 | 15637391438083 | 15637391618084 | 15637391619737 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 269 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 8 | 24 | 112896 | 0x7fafa1987f80 | 0x7fafa10255c0 | 15637391633777 | 15637391642244 | 15637391737924 | 15637391739614 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 272 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 115136 | 0x7fafa1987e00 | 0x7fafa1025600 | 15637391753904 | 15637391762404 | 15637391900645 | 15637391902401 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 275 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 116608 | 0x7fafa1987c80 | 0x7fafa1025640 | 15637391923720 | 15637391934565 | 15637392029925 | 15637392031608 |
| 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 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 16 | 24 | 118336 | 0x7fafa1987b00 | 0x7fafa1025680 | 15637392046937 | 15637392054725 | 15637392234726 | 15637392236393 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 281 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 16 | 24 | 120064 | 0x7fafa1987980 | 0x7fafa10256c0 | 15637392252173 | 15637392261926 | 15637392441126 | 15637392442868 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 284 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 121792 | 0x7fafa1987800 | 0x7fafa1025700 | 15637392459018 | 15637392467047 | 15637392564167 | 15637392565906 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 287 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 124032 | 0x7fafa1987680 | 0x7fafa1025740 | 15637392582325 | 15637392590407 | 15637392736007 | 15637392737652 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 290 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 125504 | 0x7fafa3fb4500 | 0x7fafa1025780 | 15637392758081 | 15637392768648 | 15637392864328 | 15637392865999 |
| 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 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 127488 | 0x7fafa3fb4380 | 0x7fafa10257c0 | 15637392882178 | 15637392890408 | 15637393070889 | 15637393072604 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 296 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 129216 | 0x7fafa3fb4200 | 0x7fafa1025800 | 15637393086854 | 15637393095529 | 15637393276649 | 15637393278229 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 299 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 130944 | 0x7fafa3fb4080 | 0x7fafa1025840 | 15637393294559 | 15637393304009 | 15637393404170 | 15637393405876 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 302 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 133440 | 0x7fafa1987f00 | 0x7fafa1025880 | 15637393422106 | 15637393429770 | 15637393585610 | 15637393587452 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 305 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 134912 | 0x7fafa1987d80 | 0x7fafa10258c0 | 15637393610192 | 15637393620650 | 15637393716331 | 15637393717959 |
| 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 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 136896 | 0x7fafa1987c00 | 0x7fafa1025900 | 15637393734659 | 15637393742571 | 15637393922251 | 15637393924005 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 311 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 138880 | 0x7fafa1987a80 | 0x7fafa1025940 | 15637393940734 | 15637393948971 | 15637394130092 | 15637394131950 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 314 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 140864 | 0x7fafa1987900 | 0x7fafa1025980 | 15637394146990 | 15637394155532 | 15637394263052 | 15637394264907 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 317 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 143616 | 0x7fafa1987780 | 0x7fafa10259c0 | 15637394278427 | 15637394287053 | 15637394458413 | 15637394460213 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 320 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 145344 | 0x7fafa1987600 | 0x7fafa1025a00 | 15637394480172 | 15637394490573 | 15637394585774 | 15637394587660 |
| 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 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 147584 | 0x7fafa3fb4480 | 0x7fafa1025a40 | 15637394602779 | 15637394610574 | 15637394790414 | 15637394791905 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 326 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 149568 | 0x7fafa3fb4300 | 0x7fafa1025a80 | 15637394805865 | 15637394813774 | 15637394993775 | 15637394995521 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 329 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 151552 | 0x7fafa3fb4180 | 0x7fafa1025ac0 | 15637395009030 | 15637395016975 | 15637395127055 | 15637395128708 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 332 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 154304 | 0x7fafa3fb4000 | 0x7fafa1025b00 | 15637395142617 | 15637395150415 | 15637395331216 | 15637395332813 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 335 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 156288 | 0x7fafa1987e80 | 0x7fafa1025b40 | 15637395354133 | 15637395363376 | 15637395465296 | 15637395466960 |
| 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 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 158784 | 0x7fafa1987d00 | 0x7fafa1025b80 | 15637395482620 | 15637395490257 | 15637395675217 | 15637395676805 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 341 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 161024 | 0x7fafa1987b80 | 0x7fafa1025bc0 | 15637395691095 | 15637395698737 | 15637395883858 | 15637395885521 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 344 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 163264 | 0x7fafa1987a00 | 0x7fafa1025c00 | 15637395898750 | 15637395906738 | 15637396029298 | 15637396030897 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 347 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 166528 | 0x7fafa1987880 | 0x7fafa1025c40 | 15637396045327 | 15637396053618 | 15637396259699 | 15637396302671 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 350 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 168512 | 0x7fafa1987700 | 0x7fafa1025c80 | 15637396317241 | 15637396328179 | 15637396439380 | 15637396441128 |
| 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 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 171264 | 0x7fafa3fb4580 | 0x7fafa1025cc0 | 15637396457518 | 15637396465620 | 15637396648180 | 15637396649933 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 356 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 173760 | 0x7fafa3fb4400 | 0x7fafa1025d00 | 15637396664123 | 15637396672180 | 15637396860021 | 15637396861679 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 359 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 176256 | 0x7fafa3fb4280 | 0x7fafa1025d40 | 15637396877108 | 15637396885141 | 15637397019702 | 15637397021405 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 362 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 179776 | 0x7fafa3fb4100 | 0x7fafa1025d80 | 15637397034935 | 15637397042902 | 15637397275222 | 15637397293349 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 365 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 182272 | 0x7fafa1987f80 | 0x7fafa1025dc0 | 15637397308319 | 15637397319223 | 15637397445463 | 15637397447165 |
| 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 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 185536 | 0x7fafa1987e00 | 0x7fafa1025e00 | 15637397462135 | 15637397470423 | 15637397659704 | 15637397661381 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 371 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 188544 | 0x7fafa1987c80 | 0x7fafa1025e40 | 15637397675880 | 15637397684664 | 15637397876984 | 15637397878616 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 374 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 191552 | 0x7fafa1987b00 | 0x7fafa1025e80 | 15637397894295 | 15637397901944 | 15637398061945 | 15637398063562 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 377 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 195840 | 0x7fafa1987980 | 0x7fafa1025ec0 | 15637398098441 | 15637398108665 | 15637398392346 | 15637398412234 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 380 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 198592 | 0x7fafa1987800 | 0x7fafa1025f00 | 15637398427253 | 15637398437786 | 15637398587547 | 15637398589160 |
| 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 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 202368 | 0x7fafa1987680 | 0x7fafa1025f40 | 15637398605639 | 15637398613627 | 15637398821948 | 15637398841254 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 386 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 205888 | 0x7fafa3fb4500 | 0x7fafa1025f80 | 15637398849404 | 15637398859548 | 15637399068188 | 15637399084359 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 389 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 209408 | 0x7fafa3fb4380 | 0x7fafa1025fc0 | 15637399092138 | 15637399102428 | 15637399288509 | 15637399290054 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 392 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 214464 | 0x7fafa3fb4200 | 0x7fafa1026000 | 15637399306674 | 15637399314589 | 15637399648990 | 15637399665536 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 395 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 217728 | 0x7fafa3fb4080 | 0x7fafa1026040 | 15637399681435 | 15637399691870 | 15637399858431 | 15637399860151 |
| 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 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 222016 | 0x7fafa1987f00 | 0x7fafa1026080 | 15637399874821 | 15637399882591 | 15637400109792 | 15637400125955 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 401 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 226048 | 0x7fafa1987d80 | 0x7fafa10260c0 | 15637400133805 | 15637400143872 | 15637400372353 | 15637400388189 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 404 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 230080 | 0x7fafa1987c00 | 0x7fafa1026100 | 15637400396179 | 15637400405633 | 15637400617153 | 15637400633114 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 407 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 235904 | 0x7fafa1987a80 | 0x7fafa1026140 | 15637400642554 | 15637400651554 | 15637401037155 | 15637401052974 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 410 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 239424 | 0x7fafa1987900 | 0x7fafa1026180 | 15637401068854 | 15637401079395 | 15637401266276 | 15637401267919 |
| 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 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 244224 | 0x7fafa1987780 | 0x7fafa10261c0 | 15637401283199 | 15637401290596 | 15637401540356 | 15637401556533 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 416 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 248768 | 0x7fafa1987600 | 0x7fafa1026200 | 15637401564493 | 15637401574437 | 15637401823717 | 15637401839507 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 419 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 253312 | 0x7fafa3fb4480 | 0x7fafa1026240 | 15637401848626 | 15637401858438 | 15637402095398 | 15637402117170 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 422 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 8 | 24 | 255552 | 0x7fafa3fb4300 | 0x7fafa1026280 | 15637402126200 | 15637402135718 | 15637402590120 | 15637402605879 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 425 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 259840 | 0x7fafa3fb4180 | 0x7fafa10262c0 | 15637402623249 | 15637402633640 | 15637402858601 | 15637402877473 |
| 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 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 265664 | 0x7fafa3fb4000 | 0x7fafa1026300 | 15637402885443 | 15637402895401 | 15637403193642 | 15637403237615 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 431 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 271232 | 0x7fafa1987e80 | 0x7fafa1026340 | 15637403246725 | 15637403255882 | 15637403554603 | 15637403598477 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 434 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 8 | 24 | 273216 | 0x7fafa1987d00 | 0x7fafa1026380 | 15637403606807 | 15637403617003 | 15637403913324 | 15637403933169 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 437 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 8 | 24 | 275712 | 0x7fafa1987b80 | 0x7fafa10263c0 | 15637403941629 | 15637403951244 | 15637404508686 | 15637404552565 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 440 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 280768 | 0x7fafa1987a00 | 0x7fafa1026400 | 15637404568535 | 15637404579087 | 15637404842927 | 15637404887048 |
| 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 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 287616 | 0x7fafa1987880 | 0x7fafa1026440 | 15637404896277 | 15637404906608 | 15637405256369 | 15637405277999 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 446 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 294208 | 0x7fafa1987700 | 0x7fafa1026480 | 15637405285518 | 15637405300689 | 15637405650770 | 15637405666940 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 449 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 8 | 24 | 296960 | 0x7fafa3fb4580 | 0x7fafa10264c0 | 15637405677580 | 15637405687730 | 15637406034931 | 15637406051551 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 452 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 8 | 24 | 299968 | 0x7fafa3fb4400 | 0x7fafa1026500 | 15637406060281 | 15637406070131 | 15637406731894 | 15637406754595 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 455 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 8 | 24 | 302720 | 0x7fafa3fb4280 | 0x7fafa1026540 | 15637406773045 | 15637406782134 | 15637407229015 | 15637407252934 |
| 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 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 305472 | 0x7fafa3fb4100 | 0x7fafa1026580 | 15637407261484 | 15637407271735 | 15637407735417 | 15637407754113 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 461 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 308224 | 0x7fafa1987f80 | 0x7fafa10265c0 | 15637407762573 | 15637407772697 | 15637408235099 | 15637408255781 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 464 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 8 | 24 | 310976 | 0x7fafa1987e00 | 0x7fafa1026600 | 15637408263911 | 15637408274139 | 15637408725020 | 15637408745140 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 467 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 8 | 24 | 313216 | 0x7fafa1987c80 | 0x7fafa1026640 | 15637408754940 | 15637408764060 | 15637409633663 | 15637409654350 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 470 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 8 | 24 | 315968 | 0x7fafa1987b00 | 0x7fafa1026680 | 15637409671820 | 15637409682463 | 15637410535426 | 15637410586419 |
| 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 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 318720 | 0x7fafa1987980 | 0x7fafa10266c0 | 15637410595309 | 15637410605506 | 15637411490629 | 15637411538967 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 476 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 321472 | 0x7fafa1987800 | 0x7fafa1026700 | 15637411547427 | 15637411557670 | 15637412437032 | 15637412483216 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 479 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 8 | 24 | 324224 | 0x7fafa1987680 | 0x7fafa1026740 | 15637412493856 | 15637412509353 | 15637413369516 | 15637413415975 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 482 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 8 | 24 | 326464 | 0x7fafa3fb4500 | 0x7fafa1026780 | 15637413425325 | 15637413435276 | 15637415134161 | 15637415204874 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 485 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 8 | 24 | 329216 | 0x7fafa3fb4380 | 0x7fafa10267c0 | 15637415222484 | 15637415232882 | 15637416898647 | 15637416972415 |
| 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 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 331968 | 0x7fafa3fb4200 | 0x7fafa1026800 | 15637416984594 | 15637417047768 | 15637418772253 | 15637418843263 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 491 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 12 | 24 | 334720 | 0x7fafa3fb4080 | 0x7fafa1026840 | 15637418852072 | 15637418862014 | 15637420577699 | 15637420645502 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 494 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 8 | 24 | 337472 | 0x7fafa1987f00 | 0x7fafa1026880 | 15637420657592 | 15637420721860 | 15637422395465 | 15637422467741 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 497 | 123357 | 123357 | 4194304 | 256 | 0 | 0 | 8 | 24 | 0 | 0x7fafa1987d80 | 0x7fafa10268c0 | 15637422503100 | 15637422518186 | 15637425876597 | 15637425955492 |