41 KiB
41 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | SQ_INSTS_SMEM | SQ_INST_LEVEL_SMEM | SQ_ACCUM_PREV_HIRES | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBufferAligned.kd | 0 | 0 | 0 | 174935 | 174935 | 33554432 | 256 | 0 | 0 | 4 | 32 | 4160 | 0x0 | 0x7f090be04280 | 3670016 | 3123906 | 349239680 | 16790822424947 | 16785324886982 | 16790967861419 | 16790967975528 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 174935 | 174935 | 32768 | 256 | 0 | 0 | 12 | 24 | 13888 | 0x0 | 0x7f090be23f80 | 512 | 98092 | 10976944 | 16790973109527 | 16790967861419 | 16790973234676 | 16790973239113 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 5 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 14336 | 0x7f091a6f6380 | 0x7f090be23fc0 | 65536 | 651948 | 72985536 | 16790973273982 | 16790973234676 | 16790973592274 | 16790973594531 |
| 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 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15040 | 0x7f091a6f6200 | 0x7f090be24000 | 65536 | 679706 | 76136944 | 16790973630500 | 16790973592274 | 16790973988593 | 16790973990909 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 11 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15488 | 0x7f091a6f6080 | 0x7f090be24040 | 65536 | 674790 | 75512192 | 16790974023398 | 16790973988593 | 16790974394991 | 16790974397206 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 14 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 15936 | 0x7f09180c9f00 | 0x7f090be24080 | 65536 | 677330 | 75841608 | 16790974429255 | 16790974394991 | 16790974708750 | 16790974710576 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 17 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 16384 | 0x7f09180c9d80 | 0x7f090be240c0 | 65536 | 663296 | 74312208 | 16790974742685 | 16790974708750 | 16790975010669 | 16790975012677 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 20 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 17088 | 0x7f09180c9c00 | 0x7f090be24100 | 131072 | 689102 | 77104496 | 16790975055606 | 16790975010669 | 16790975313547 | 16790975315357 |
| 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 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 16 | 24 | 17792 | 0x7f09180c9a80 | 0x7f090be24140 | 131072 | 753466 | 84536800 | 16790975346386 | 16790975313547 | 16790975699786 | 16790975701855 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 26 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 16 | 24 | 18496 | 0x7f09180c9900 | 0x7f090be24180 | 65536 | 681518 | 76514816 | 16790975733164 | 16790975699786 | 16790976087624 | 16790976089703 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 29 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19200 | 0x7f09180c9780 | 0x7f090be241c0 | 131072 | 748402 | 83913632 | 16790976120742 | 16790976087624 | 16790976402663 | 16790976404753 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 32 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19904 | 0x7f09180c9600 | 0x7f090be24200 | 131072 | 721528 | 80905112 | 16790976436892 | 16790976402663 | 16790976702022 | 16790976704094 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 35 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 20608 | 0x7f091a6f6480 | 0x7f090be24240 | 131072 | 735796 | 82470016 | 16790976743992 | 16790976702022 | 16790976998980 | 16790977000894 |
| 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 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 16 | 24 | 21312 | 0x7f091a6f6300 | 0x7f090be24280 | 131072 | 723580 | 81038112 | 16790977033723 | 16790976998980 | 16790977386819 | 16790977388902 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 41 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22016 | 0x7f091a6f6180 | 0x7f090be242c0 | 65536 | 701510 | 78515656 | 16790977420401 | 16790977386819 | 16790977773697 | 16790977775710 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 44 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22720 | 0x7f091a6f6000 | 0x7f090be24300 | 131072 | 713674 | 80021664 | 16790977807979 | 16790977773697 | 16790978073216 | 16790978075040 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 47 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 23424 | 0x7f09180c9e80 | 0x7f090be24340 | 131072 | 734722 | 82280400 | 16790978111619 | 16790978073216 | 16790978402495 | 16790978404570 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 50 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 24128 | 0x7f09180c9d00 | 0x7f090be24380 | 131072 | 725040 | 81199872 | 16790978443599 | 16790978402495 | 16790978700253 | 16790978702501 |
| 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 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 16 | 24 | 24832 | 0x7f09180c9b80 | 0x7f090be243c0 | 131072 | 721090 | 80809520 | 16790978733580 | 16790978700253 | 16790979088572 | 16790979090148 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 56 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 16 | 24 | 25536 | 0x7f09180c9a00 | 0x7f090be24400 | 65536 | 676164 | 75662352 | 16790979120757 | 16790979088572 | 16790979452090 | 16790979453487 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 59 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26240 | 0x7f09180c9880 | 0x7f090be24440 | 131072 | 713442 | 79943040 | 16790979484376 | 16790979452090 | 16790979722649 | 16790979724208 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 62 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26944 | 0x7f09180c9700 | 0x7f090be24480 | 131072 | 717428 | 80369272 | 16790979755387 | 16790979722649 | 16790979991768 | 16790979993200 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 65 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 27648 | 0x7f091a6f6580 | 0x7f090be244c0 | 131072 | 736828 | 82454504 | 16790980031709 | 16790979991768 | 16790980264727 | 16790980266191 |
| 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 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 16 | 24 | 28608 | 0x7f091a6f6400 | 0x7f090be24500 | 131072 | 721732 | 80797488 | 16790980297390 | 16790980264727 | 16790980619286 | 16790980620660 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 71 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 16 | 24 | 29312 | 0x7f091a6f6280 | 0x7f090be24540 | 65536 | 693790 | 77696536 | 16790980652559 | 16790980619286 | 16790980976724 | 16790980977989 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 74 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 30016 | 0x7f091a6f6100 | 0x7f090be24580 | 131072 | 677676 | 75807696 | 16790981009948 | 16790980976724 | 16790981251123 | 16790981252540 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 77 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 8 | 24 | 30976 | 0x7f09180c9f80 | 0x7f090be245c0 | 131072 | 678008 | 75858048 | 16790981284569 | 16790981251123 | 16790981522802 | 16790981524172 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 80 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 31680 | 0x7f09180c9e00 | 0x7f090be24600 | 131072 | 721696 | 80833024 | 16790981562980 | 16790981522802 | 16790981796241 | 16790981797603 |
| 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 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 16 | 24 | 32640 | 0x7f09180c9c80 | 0x7f090be24640 | 131072 | 695856 | 78028224 | 16790981828162 | 16790981796241 | 16790982155279 | 16790982157142 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 86 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 33600 | 0x7f09180c9b00 | 0x7f090be24680 | 65536 | 667768 | 74743616 | 16790982188281 | 16790982155279 | 16790982518798 | 16790982520270 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 89 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 34560 | 0x7f09180c9980 | 0x7f090be246c0 | 131072 | 718534 | 80510720 | 16790982550699 | 16790982518798 | 16790982789997 | 16790982791302 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 92 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 8 | 24 | 35520 | 0x7f09180c9800 | 0x7f090be24700 | 131072 | 712316 | 79791016 | 16790982822941 | 16790982789997 | 16790983058476 | 16790983060193 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 95 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 36224 | 0x7f09180c9680 | 0x7f090be24740 | 131072 | 716410 | 80252424 | 16790983098412 | 16790983058476 | 16790983334634 | 16790983336005 |
| 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 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 37184 | 0x7f091a6f6500 | 0x7f090be24780 | 131072 | 687448 | 77015776 | 16790983366674 | 16790983334634 | 16790983689033 | 16790983690424 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 101 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 38144 | 0x7f091a6f6380 | 0x7f090be247c0 | 65536 | 702736 | 78661376 | 16790983721093 | 16790983689033 | 16790984047912 | 16790984049262 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 104 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 39104 | 0x7f091a6f6200 | 0x7f090be24800 | 131072 | 713584 | 79825336 | 16790984080561 | 16790984047912 | 16790984316390 | 16790984317764 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 107 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 8 | 24 | 40320 | 0x7f091a6f6080 | 0x7f090be24840 | 131072 | 711940 | 79852064 | 16790984349123 | 16790984316390 | 16790984585509 | 16790984586806 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 110 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 41280 | 0x7f09180c9f00 | 0x7f090be24880 | 131072 | 708982 | 79470000 | 16790984625104 | 16790984585509 | 16790984855268 | 16790984856757 |
| 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 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 42240 | 0x7f09180c9d80 | 0x7f090be248c0 | 131072 | 711318 | 79763272 | 16790984887176 | 16790984855268 | 16790985217507 | 16790985218906 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 116 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 43200 | 0x7f09180c9c00 | 0x7f090be24900 | 65536 | 673966 | 75438144 | 16790985250035 | 16790985217507 | 16790985572865 | 16790985574325 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 119 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 8 | 24 | 44160 | 0x7f09180c9a80 | 0x7f090be24940 | 131072 | 719574 | 80635216 | 16790985605484 | 16790985572865 | 16790985843904 | 16790985845496 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 122 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 45376 | 0x7f09180c9900 | 0x7f090be24980 | 131072 | 748816 | 83893744 | 16790985875855 | 16790985843904 | 16790986117023 | 16790986118527 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 125 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 46336 | 0x7f09180c9780 | 0x7f090be249c0 | 131072 | 708184 | 79392992 | 16790986157946 | 16790986117023 | 16790986395422 | 16790986396799 |
| 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 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 47552 | 0x7f09180c9600 | 0x7f090be24a00 | 131072 | 715430 | 80092088 | 16790986428158 | 16790986395422 | 16790986752860 | 16790986754357 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 131 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 48512 | 0x7f091a6f6480 | 0x7f090be24a40 | 65536 | 674812 | 75530800 | 16790986786046 | 16790986752860 | 16790987109339 | 16790987110926 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 134 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 8 | 24 | 49472 | 0x7f091a6f6300 | 0x7f090be24a80 | 131072 | 685584 | 76843152 | 16790987142105 | 16790987109339 | 16790987378938 | 16790987380618 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 137 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 50688 | 0x7f091a6f6180 | 0x7f090be24ac0 | 131072 | 680918 | 76383832 | 16790987412377 | 16790987378938 | 16790987648857 | 16790987650189 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 140 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 51648 | 0x7f091a6f6000 | 0x7f090be24b00 | 131072 | 687744 | 77084712 | 16790987689028 | 16790987648857 | 16790987931096 | 16790987932630 |
| 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 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 52864 | 0x7f09180c9e80 | 0x7f090be24b40 | 131072 | 716482 | 80250352 | 16790987964439 | 16790987931096 | 16790988295894 | 16790988297319 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 146 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 54080 | 0x7f09180c9d00 | 0x7f090be24b80 | 65536 | 692156 | 77547264 | 16790988328148 | 16790988295894 | 16790988653973 | 16790988655368 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 149 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 8 | 24 | 55296 | 0x7f09180c9b80 | 0x7f090be24bc0 | 131072 | 707828 | 79346848 | 16790988686707 | 16790988653973 | 16790988923732 | 16790988925169 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 152 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 56768 | 0x7f09180c9a00 | 0x7f090be24c00 | 131072 | 707322 | 79153376 | 16790988955928 | 16790988923732 | 16790989195570 | 16790989196850 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 155 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 57728 | 0x7f09180c9880 | 0x7f090be24c40 | 131072 | 711426 | 79794472 | 16790989234319 | 16790989195570 | 16790989467569 | 16790989468962 |
| 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 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 58944 | 0x7f09180c9700 | 0x7f090be24c80 | 131072 | 706950 | 79049720 | 16790989499701 | 16790989467569 | 16790989826768 | 16790989828171 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 161 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 60160 | 0x7f091a6f6580 | 0x7f090be24cc0 | 65536 | 686154 | 76861320 | 16790989858690 | 16790989826768 | 16790990182926 | 16790990184359 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 164 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 8 | 24 | 61376 | 0x7f091a6f6400 | 0x7f090be24d00 | 131072 | 708116 | 79382712 | 16790990216918 | 16790990182926 | 16790990458445 | 16790990459981 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 167 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 62848 | 0x7f091a6f6280 | 0x7f090be24d40 | 131072 | 714088 | 79958632 | 16790990491760 | 16790990458445 | 16790990739564 | 16790990741032 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 170 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 63808 | 0x7f091a6f6100 | 0x7f090be24d80 | 131072 | 737536 | 82596256 | 16790990780021 | 16790990739564 | 16790991011083 | 16790991012453 |
| 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 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 65024 | 0x7f09180c9f80 | 0x7f090be24dc0 | 131072 | 678846 | 76047088 | 16790991043562 | 16790991011083 | 16790991367881 | 16790991369312 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 176 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 66240 | 0x7f09180c9e00 | 0x7f090be24e00 | 65536 | 646040 | 72481120 | 16790991400421 | 16790991367881 | 16790991725640 | 16790991727101 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 179 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 8 | 24 | 67456 | 0x7f09180c9c80 | 0x7f090be24e40 | 131072 | 710350 | 79612184 | 16790991758270 | 16790991725640 | 16790991996199 | 16790991997642 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 182 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 68928 | 0x7f09180c9b00 | 0x7f090be24e80 | 131072 | 730048 | 81687648 | 16790992029151 | 16790991996199 | 16790992275878 | 16790992277523 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 185 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 70144 | 0x7f09180c9980 | 0x7f090be24ec0 | 131072 | 688796 | 77000728 | 16790992315402 | 16790992275878 | 16790992547717 | 16790992549065 |
| 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 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 71616 | 0x7f09180c9800 | 0x7f090be24f00 | 131072 | 708960 | 79432080 | 16790992580504 | 16790992547717 | 16790992907715 | 16790992909143 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 191 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 72832 | 0x7f09180c9680 | 0x7f090be24f40 | 65536 | 675764 | 75729840 | 16790992939802 | 16790992907715 | 16790993264994 | 16790993266522 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 194 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 8 | 24 | 74048 | 0x7f091a6f6500 | 0x7f090be24f80 | 131072 | 674978 | 75574936 | 16790993297691 | 16790993264994 | 16790993538913 | 16790993540474 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 197 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 75776 | 0x7f091a6f6380 | 0x7f090be24fc0 | 131072 | 681316 | 76263240 | 16790993571043 | 16790993538913 | 16790993822111 | 16790993823515 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 200 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 76992 | 0x7f091a6f6200 | 0x7f090be25000 | 131072 | 710712 | 79729864 | 16790993862473 | 16790993822111 | 16790994092990 | 16790994094696 |
| 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 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 78464 | 0x7f091a6f6080 | 0x7f090be25040 | 131072 | 712380 | 79727288 | 16790994128195 | 16790994092990 | 16790994454589 | 16790994456035 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 206 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 79936 | 0x7f09180c9f00 | 0x7f090be25080 | 65536 | 669748 | 75088544 | 16790994488734 | 16790994454589 | 16790994811707 | 16790994813114 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 209 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 8 | 24 | 81408 | 0x7f09180c9d80 | 0x7f090be250c0 | 131072 | 713658 | 79913152 | 16790994843743 | 16790994811707 | 16790995085626 | 16790995087025 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 212 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 83136 | 0x7f09180c9c00 | 0x7f090be25100 | 131072 | 709352 | 79473408 | 16790995118014 | 16790995085626 | 16790995376985 | 16790995378406 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 215 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 84352 | 0x7f09180c9a80 | 0x7f090be25140 | 131072 | 714690 | 80002256 | 16790995426284 | 16790995376985 | 16790995653624 | 16790995655137 |
| 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 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 85824 | 0x7f09180c9900 | 0x7f090be25180 | 131072 | 708084 | 79415336 | 16790995685446 | 16790995653624 | 16790996011222 | 16790996012726 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 221 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 87296 | 0x7f09180c9780 | 0x7f090be251c0 | 65536 | 708698 | 79324992 | 16790996043515 | 16790996011222 | 16790996376181 | 16790996377795 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 224 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 88768 | 0x7f09180c9600 | 0x7f090be25200 | 131072 | 714694 | 80194104 | 16790996408274 | 16790996376181 | 16790996648980 | 16790996650646 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 227 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 90752 | 0x7f091a6f6480 | 0x7f090be25240 | 131072 | 720598 | 80740720 | 16790996682015 | 16790996648980 | 16790996946739 | 16790996948127 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 230 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 91968 | 0x7f091a6f6300 | 0x7f090be25280 | 131072 | 711680 | 79691552 | 16790996986155 | 16790996946739 | 16790997219857 | 16790997221168 |
| 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 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 93440 | 0x7f091a6f6180 | 0x7f090be252c0 | 131072 | 746154 | 83699336 | 16790997251717 | 16790997219857 | 16790997577456 | 16790997578917 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 236 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 94912 | 0x7f091a6f6000 | 0x7f090be25300 | 65536 | 682648 | 76473872 | 16790997610776 | 16790997577456 | 16790997933295 | 16790997934706 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 239 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 96384 | 0x7f09180c9e80 | 0x7f090be25340 | 131072 | 733458 | 82227856 | 16790997965695 | 16790997933295 | 16790998216653 | 16790998218087 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 242 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 98368 | 0x7f09180c9d00 | 0x7f090be25380 | 131072 | 718694 | 80528936 | 16790998249506 | 16790998216653 | 16790998520812 | 16790998522247 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 245 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 99584 | 0x7f09180c9b80 | 0x7f090be253c0 | 131072 | 714232 | 79943464 | 16790998560716 | 16790998520812 | 16790998792331 | 16790998793679 |
| 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 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 101312 | 0x7f09180c9a00 | 0x7f090be25400 | 131072 | 692510 | 77452160 | 16790998825008 | 16790998792331 | 16790999151690 | 16790999153207 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 251 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 102784 | 0x7f09180c9880 | 0x7f090be25440 | 65536 | 677086 | 75745424 | 16790999183916 | 16790999151690 | 16790999507048 | 16790999508416 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 254 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 104256 | 0x7f09180c9700 | 0x7f090be25480 | 131072 | 694684 | 77764808 | 16790999539685 | 16790999507048 | 16790999777447 | 16790999778828 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 257 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 106240 | 0x7f091a6f6580 | 0x7f090be254c0 | 131072 | 691564 | 77418512 | 16790999809987 | 16790999777447 | 16791000084326 | 16791000085748 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 260 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 107712 | 0x7f091a6f6400 | 0x7f090be25500 | 131072 | 713650 | 79919408 | 16791000125167 | 16791000084326 | 16791000361765 | 16791000363139 |
| 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 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 16 | 24 | 109440 | 0x7f091a6f6280 | 0x7f090be25540 | 131072 | 710804 | 79500776 | 16791000394708 | 16791000361765 | 16791000717123 | 16791000718428 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 266 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 16 | 24 | 111168 | 0x7f091a6f6100 | 0x7f090be25580 | 65536 | 674786 | 75639656 | 16791000749847 | 16791000717123 | 16791001077602 | 16791001079127 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 269 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 8 | 24 | 112896 | 0x7f09180c9f80 | 0x7f090be255c0 | 131072 | 716710 | 80239872 | 16791001110416 | 16791001077602 | 16791001353600 | 16791001354938 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 272 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 115136 | 0x7f09180c9e00 | 0x7f090be25600 | 131072 | 751722 | 84187384 | 16791001386797 | 16791001353600 | 16791001669279 | 16791001670818 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 275 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 116608 | 0x7f09180c9c80 | 0x7f090be25640 | 131072 | 710268 | 79462248 | 16791001708497 | 16791001669279 | 16791001940318 | 16791001941999 |
| 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 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 16 | 24 | 118336 | 0x7f09180c9b00 | 0x7f090be25680 | 131072 | 716222 | 80198848 | 16791001972328 | 16791001940318 | 16791002308157 | 16791002309888 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 281 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 16 | 24 | 120064 | 0x7f09180c9980 | 0x7f090be256c0 | 65536 | 678266 | 75944984 | 16791002341127 | 16791002308157 | 16791002678875 | 16791002680266 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 284 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 121792 | 0x7f09180c9800 | 0x7f090be25700 | 131072 | 715416 | 80172456 | 16791002711295 | 16791002678875 | 16791002951354 | 16791002952878 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 287 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 124032 | 0x7f09180c9680 | 0x7f090be25740 | 131072 | 721470 | 80806912 | 16791002983857 | 16791002951354 | 16791003271513 | 16791003273087 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 290 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 125504 | 0x7f091a6f6500 | 0x7f090be25780 | 131072 | 710946 | 79665664 | 16791003311516 | 16791003271513 | 16791003546711 | 16791003548239 |
| 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 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 127488 | 0x7f091a6f6380 | 0x7f090be257c0 | 131072 | 721252 | 80848288 | 16791003579638 | 16791003546711 | 16791003902070 | 16791003903618 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 296 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 129216 | 0x7f091a6f6200 | 0x7f090be25800 | 65536 | 669486 | 75051760 | 16791003934987 | 16791003902070 | 16791004260149 | 16791004261536 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 299 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 130944 | 0x7f091a6f6080 | 0x7f090be25840 | 131072 | 677402 | 75909544 | 16791004292715 | 16791004260149 | 16791004539667 | 16791004541147 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 302 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 133440 | 0x7f09180c9f00 | 0x7f090be25880 | 131072 | 685830 | 76775232 | 16791004572966 | 16791004539667 | 16791004871826 | 16791004873157 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 305 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 134912 | 0x7f09180c9d80 | 0x7f090be258c0 | 131072 | 1055734 | 118432344 | 16791004913006 | 16791004871826 | 16791005157105 | 16791005158598 |
| 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 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 136896 | 0x7f09180c9c00 | 0x7f090be25900 | 131072 | 702906 | 78746688 | 16791005189547 | 16791005157105 | 16791005515663 | 16791005517097 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 311 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 138880 | 0x7f09180c9a80 | 0x7f090be25940 | 65536 | 681954 | 76261128 | 16791005548226 | 16791005515663 | 16791005872942 | 16791005874315 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 314 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 140864 | 0x7f09180c9900 | 0x7f090be25980 | 131072 | 710058 | 79599992 | 16791005905214 | 16791005872942 | 16791006154221 | 16791006155677 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 317 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 143616 | 0x7f09180c9780 | 0x7f090be259c0 | 131072 | 711846 | 79701856 | 16791006187536 | 16791006154221 | 16791006501259 | 16791006502586 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 320 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 145344 | 0x7f09180c9600 | 0x7f090be25a00 | 131072 | 1047508 | 117271832 | 16791006542044 | 16791006501259 | 16791006772458 | 16791006773987 |
| 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 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 147584 | 0x7f091a6f6480 | 0x7f090be25a40 | 131072 | 708984 | 79472360 | 16791006804846 | 16791006772458 | 16791007127657 | 16791007129276 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 326 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 149568 | 0x7f091a6f6300 | 0x7f090be25a80 | 65536 | 674648 | 75540000 | 16791007160315 | 16791007127657 | 16791007488615 | 16791007489965 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 329 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 151552 | 0x7f091a6f6180 | 0x7f090be25ac0 | 131072 | 696816 | 77964728 | 16791007521044 | 16791007488615 | 16791007775334 | 16791007776806 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 332 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 154304 | 0x7f091a6f6000 | 0x7f090be25b00 | 131072 | 683710 | 76546048 | 16791007808505 | 16791007775334 | 16791008138853 | 16791008140294 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 335 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 156288 | 0x7f09180c9e80 | 0x7f090be25b40 | 131072 | 1017244 | 113912128 | 16791008179343 | 16791008138853 | 16791008419011 | 16791008420386 |
| 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 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 158784 | 0x7f09180c9d00 | 0x7f090be25b80 | 131072 | 714758 | 80035304 | 16791008450625 | 16791008419011 | 16791008776290 | 16791008777794 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 341 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 161024 | 0x7f09180c9b80 | 0x7f090be25bc0 | 65536 | 669916 | 75060120 | 16791008808353 | 16791008776290 | 16791009134049 | 16791009135413 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 344 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 163264 | 0x7f09180c9a00 | 0x7f090be25c00 | 131072 | 680180 | 76151968 | 16791009165322 | 16791009134049 | 16791009435007 | 16791009436514 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 347 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 166528 | 0x7f09180c9880 | 0x7f090be25c40 | 131072 | 681834 | 76348432 | 16791009467543 | 16791009435007 | 16791009819006 | 16791009838231 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 350 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 168512 | 0x7f09180c9700 | 0x7f090be25c80 | 131072 | 1055778 | 118262600 | 16791009859070 | 16791009819006 | 16791010111805 | 16791010113203 |
| 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 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 171264 | 0x7f091a6f6580 | 0x7f090be25cc0 | 131072 | 683164 | 76567040 | 16791010145202 | 16791010111805 | 16791010473083 | 16791010474561 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 356 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 173760 | 0x7f091a6f6400 | 0x7f090be25d00 | 65536 | 676648 | 75796928 | 16791010505680 | 16791010473083 | 16791010835002 | 16791010836400 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 359 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 176256 | 0x7f091a6f6280 | 0x7f090be25d40 | 131072 | 712672 | 79745408 | 16791010867469 | 16791010835002 | 16791011152600 | 16791011154030 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 362 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 179776 | 0x7f091a6f6100 | 0x7f090be25d80 | 131072 | 718274 | 80376904 | 16791011185819 | 16791011152600 | 16791011562519 | 16791011607715 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 365 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 182272 | 0x7f09180c9f80 | 0x7f090be25dc0 | 131072 | 1027632 | 114982160 | 16791011626785 | 16791011562519 | 16791011901397 | 16791011902696 |
| 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 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 185536 | 0x7f09180c9e00 | 0x7f090be25e00 | 131072 | 710122 | 79676712 | 16791011933435 | 16791011901397 | 16791012273236 | 16791012295414 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 371 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 188544 | 0x7f09180c9c80 | 0x7f090be25e40 | 65536 | 677130 | 75795432 | 16791012306313 | 16791012273236 | 16791012651154 | 16791012671512 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 374 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 191552 | 0x7f09180c9b00 | 0x7f090be25e80 | 131072 | 691930 | 77431752 | 16791012683452 | 16791012651154 | 16791012994353 | 16791012995682 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 377 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 195840 | 0x7f09180c9980 | 0x7f090be25ec0 | 131072 | 688290 | 77035856 | 16791013026771 | 16791012994353 | 16791013451631 | 16791013469527 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 380 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 198592 | 0x7f09180c9800 | 0x7f090be25f00 | 131072 | 1052372 | 117842648 | 16791013491446 | 16791013451631 | 16791013785069 | 16791013786497 |
| 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 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 202368 | 0x7f09180c9680 | 0x7f090be25f40 | 131072 | 1022780 | 114590176 | 16791013817336 | 16791013785069 | 16791014170508 | 16791014197374 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 386 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 205888 | 0x7f091a6f6500 | 0x7f090be25f80 | 65536 | 679426 | 76128008 | 16791014209073 | 16791014170508 | 16791014579146 | 16791014621130 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 389 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 209408 | 0x7f091a6f6380 | 0x7f090be25fc0 | 131072 | 728164 | 81476072 | 16791014631800 | 16791014579146 | 16791014979785 | 16791014981309 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 392 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 214464 | 0x7f091a6f6200 | 0x7f090be26000 | 131072 | 689704 | 77223680 | 16791015012548 | 16791014979785 | 16791015492262 | 16791015534072 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 395 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 217728 | 0x7f091a6f6080 | 0x7f090be26040 | 131072 | 1062762 | 118999496 | 16791015552681 | 16791015492262 | 16791015864741 | 16791015866151 |
| 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 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 222016 | 0x7f09180c9f00 | 0x7f090be26080 | 131072 | 1049364 | 117396624 | 16791015896980 | 16791015864741 | 16791016272419 | 16791016314447 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 401 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 226048 | 0x7f09180c9d80 | 0x7f090be260c0 | 65536 | 678140 | 75939984 | 16791016325697 | 16791016272419 | 16791016708417 | 16791016750573 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 404 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 230080 | 0x7f09180c9c00 | 0x7f090be26100 | 131072 | 679580 | 76105568 | 16791016761533 | 16791016708417 | 16791017126336 | 16791017167670 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 407 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 235904 | 0x7f09180c9a80 | 0x7f090be26140 | 131072 | 687238 | 76810264 | 16791017178610 | 16791017126336 | 16791017715773 | 16791017733732 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 410 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 239424 | 0x7f09180c9900 | 0x7f090be26180 | 131072 | 1055032 | 118268328 | 16791017755252 | 16791017715773 | 16791018090172 | 16791018092011 |
| 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 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 244224 | 0x7f09180c9780 | 0x7f090be261c0 | 131072 | 1027528 | 115132944 | 16791018122780 | 16791018090172 | 16791018530650 | 16791018551187 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 416 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 248768 | 0x7f09180c9600 | 0x7f090be26200 | 65536 | 702974 | 78814928 | 16791018562526 | 16791018530650 | 16791018963928 | 16791018981193 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 419 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 253312 | 0x7f091a6f6480 | 0x7f090be26240 | 131072 | 685698 | 76806512 | 16791018996373 | 16791018963928 | 16791019381686 | 16791019398680 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 422 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 8 | 24 | 255552 | 0x7f091a6f6300 | 0x7f090be26280 | 131072 | 1048488 | 117641416 | 16791019414370 | 16791019381686 | 16791020011924 | 16791020030500 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 425 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 259840 | 0x7f091a6f6180 | 0x7f090be262c0 | 131072 | 1049136 | 117500648 | 16791020052330 | 16791020011924 | 16791020419122 | 16791020435788 |
| 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 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 265664 | 0x7f091a6f6000 | 0x7f090be26300 | 131072 | 1025728 | 114759720 | 16791020451927 | 16791020419122 | 16791020899120 | 16791020916472 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 431 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 271232 | 0x7f09180c9e80 | 0x7f090be26340 | 65536 | 678066 | 75692040 | 16791020931772 | 16791020899120 | 16791021377198 | 16791021394747 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 434 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 8 | 24 | 273216 | 0x7f09180c9d00 | 0x7f090be26380 | 131072 | 1055758 | 118413608 | 16791021409227 | 16791021377198 | 16791021854476 | 16791021872732 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 437 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 8 | 24 | 275712 | 0x7f09180c9b80 | 0x7f090be263c0 | 131072 | 1048116 | 117673400 | 16791021887532 | 16791021854476 | 16791022589673 | 16791022635078 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 440 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 280768 | 0x7f09180c9a00 | 0x7f090be26400 | 131072 | 1033912 | 115757520 | 16791022654798 | 16791022589673 | 16791023073671 | 16791023115453 |
| 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 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 287616 | 0x7f09180c9880 | 0x7f090be26440 | 131072 | 1096276 | 122711736 | 16791023126563 | 16791023073671 | 16791023631109 | 16791023672836 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 446 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 294208 | 0x7f09180c9700 | 0x7f090be26480 | 65536 | 677728 | 75864128 | 16791023684175 | 16791023631109 | 16791024188547 | 16791024230438 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 449 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 8 | 24 | 296960 | 0x7f091a6f6580 | 0x7f090be264c0 | 131072 | 1024000 | 114596600 | 16791024241918 | 16791024188547 | 16791024742304 | 16791024783871 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 452 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 8 | 24 | 299968 | 0x7f091a6f6400 | 0x7f090be26500 | 131072 | 1053126 | 118105544 | 16791024795600 | 16791024742304 | 16791025608541 | 16791025650163 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 455 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 8 | 24 | 302720 | 0x7f091a6f6280 | 0x7f090be26540 | 131072 | 1057584 | 118581576 | 16791025668823 | 16791025608541 | 16791026261018 | 16791026307073 |
| 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 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 305472 | 0x7f091a6f6100 | 0x7f090be26580 | 131072 | 1054382 | 118123248 | 16791026318452 | 16791026261018 | 16791026939095 | 16791026982601 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 461 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 308224 | 0x7f09180c9f80 | 0x7f090be265c0 | 65536 | 690216 | 77264008 | 16791026993591 | 16791026939095 | 16791027610133 | 16791027653220 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 464 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 8 | 24 | 310976 | 0x7f09180c9e00 | 0x7f090be26600 | 131072 | 1046732 | 117517288 | 16791027664040 | 16791027610133 | 16791028281650 | 16791028326659 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 467 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 8 | 24 | 313216 | 0x7f09180c9c80 | 0x7f090be26640 | 131072 | 1056970 | 118313144 | 16791028337989 | 16791028281650 | 16791029380845 | 16791029424984 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 470 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 8 | 24 | 315968 | 0x7f09180c9b00 | 0x7f090be26680 | 131072 | 1068798 | 119616392 | 16791029444974 | 16791029380845 | 16791030455881 | 16791030501851 |
| 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 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 318720 | 0x7f09180c9980 | 0x7f090be266c0 | 131072 | 1046588 | 117001296 | 16791030513940 | 16791030455829 | 16791031570063 | 16791031636445 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 476 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 321472 | 0x7f09180c9800 | 0x7f090be26700 | 65536 | 679928 | 76191888 | 16791031648525 | 16791031570063 | 16791032695499 | 16791032761580 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 479 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 8 | 24 | 324224 | 0x7f09180c9680 | 0x7f090be26740 | 131072 | 1050710 | 117441800 | 16791032772899 | 16791032695499 | 16791033799014 | 16791033863665 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 482 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 8 | 24 | 326464 | 0x7f091a6f6500 | 0x7f090be26780 | 131072 | 1051252 | 117427608 | 16791033875625 | 16791033799014 | 16791035739006 | 16791035805734 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 485 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 8 | 24 | 329216 | 0x7f091a6f6380 | 0x7f090be267c0 | 131072 | 1047426 | 117140904 | 16791035825003 | 16791035739006 | 16791037657398 | 16791037723934 |
| 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 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 331968 | 0x7f091a6f6200 | 0x7f090be26800 | 131072 | 1049296 | 117342328 | 16791037735193 | 16791037657398 | 16791039628429 | 16791039698502 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 491 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 12 | 24 | 334720 | 0x7f091a6f6080 | 0x7f090be26840 | 65536 | 675246 | 75515880 | 16791039710241 | 16791039628429 | 16791041609701 | 16791041674830 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 494 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 8 | 24 | 337472 | 0x7f09180c9f00 | 0x7f090be26880 | 131072 | 1052700 | 117742976 | 16791041686939 | 16791041609701 | 16791043537533 | 16791043613869 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 497 | 174935 | 174935 | 4194304 | 256 | 0 | 0 | 8 | 24 | 0 | 0x7f09180c9d80 | 0x7f090be268c0 | 131072 | 1051736 | 117758016 | 16791043625578 | 16791043537533 | 16791047155758 | 16791047229565 |