989e29cf81
Signed-off-by: Jose Santos <josantos@login1.hpcfund>
37 KiB
37 KiB
| 1 | Dispatch_ID | Kernel_Name | GPU_ID | queue-id | queue-index | pid | tid | grd | Workgroup_Size | LDS_Per_Workgroup | scr | vgpr | SGPR | fbar | sig | obj | DispatchNs | Start_Timestamp | End_Timestamp | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBufferAligned.kd | 0 | 0 | 0 | 152884 | 152884 | 33554432 | 256 | 0 | 0 | 4 | 32 | 4160 | 0x0 | 0x7faac0204280 | 16263272597989 | 16263272627979 | 16263272865101 | 16263272975281 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 152884 | 152884 | 32768 | 256 | 0 | 0 | 12 | 24 | 13888 | 0x0 | 0x7faac0223f80 | 16263277872962 | 16263277888332 | 16263277896172 | 16263277919581 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 5 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 14336 | 0x7faac3119380 | 0x7faac0223fc0 | 16263277920561 | 16263277967853 | 16263278060333 | 16263278062978 |
| 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 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15040 | 0x7faac3119200 | 0x7faac0224000 | 16263278099207 | 16263278108814 | 16263278289295 | 16263278291913 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 11 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15488 | 0x7faac3119080 | 0x7faac0224040 | 16263278308003 | 16263278316495 | 16263278497296 | 16263278499739 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 14 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 15936 | 0x7faac097df00 | 0x7faac0224080 | 16263278514638 | 16263278522736 | 16263278615377 | 16263278617976 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 17 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 16384 | 0x7faac097dd80 | 0x7faac02240c0 | 16263278634226 | 16263278642097 | 16263278733618 | 16263278736163 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 20 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 17088 | 0x7faac097dc00 | 0x7faac0224100 | 16263278767013 | 16263278777458 | 16263278869138 | 16263278871470 |
| 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 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 16 | 24 | 17792 | 0x7faac097da80 | 0x7faac0224140 | 16263278888470 | 16263278896979 | 16263279076820 | 16263279079266 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 26 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 16 | 24 | 18496 | 0x7faac097d900 | 0x7faac0224180 | 16263279098395 | 16263279108980 | 16263279288821 | 16263279291081 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 29 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19200 | 0x7faac097d780 | 0x7faac02241c0 | 16263279309931 | 16263279321941 | 16263279414102 | 16263279416518 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 32 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19904 | 0x7faac097d600 | 0x7faac0224200 | 16263279442658 | 16263279453302 | 16263279545303 | 16263279547566 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 35 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 20608 | 0x7faac3119480 | 0x7faac0224240 | 16263279570725 | 16263279579383 | 16263279670904 | 16263279673373 |
| 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 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 16 | 24 | 21312 | 0x7faac3119300 | 0x7faac0224280 | 16263279697192 | 16263279707064 | 16263279888185 | 16263279890568 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 41 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22016 | 0x7faac3119180 | 0x7faac02242c0 | 16263279908208 | 16263279928345 | 16263280107066 | 16263280109543 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 44 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22720 | 0x7faac3119000 | 0x7faac0224300 | 16263280126893 | 16263280135707 | 16263280228027 | 16263280230650 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 47 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 23424 | 0x7faac097de80 | 0x7faac0224340 | 16263280249380 | 16263280259067 | 16263280350748 | 16263280353398 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 50 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 24128 | 0x7faac097dd00 | 0x7faac0224380 | 16263280374607 | 16263280384988 | 16263280476669 | 16263280478935 |
| 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 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 16 | 24 | 24832 | 0x7faac097db80 | 0x7faac02243c0 | 16263280496925 | 16263280505309 | 16263280685630 | 16263280688000 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 56 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 16 | 24 | 25536 | 0x7faac097da00 | 0x7faac0224400 | 16263280706340 | 16263280735070 | 16263280913952 | 16263280916295 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 59 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26240 | 0x7faac097d880 | 0x7faac0224440 | 16263280934315 | 16263280960032 | 16263281052513 | 16263281055162 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 62 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26944 | 0x7faac097d700 | 0x7faac0224480 | 16263281072362 | 16263281080993 | 16263281172833 | 16263281174710 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 65 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 27648 | 0x7faac3119580 | 0x7faac02244c0 | 16263281196439 | 16263281206914 | 16263281297954 | 16263281299837 |
| 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 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 16 | 24 | 28608 | 0x7faac3119400 | 0x7faac0224500 | 16263281315497 | 16263281322914 | 16263281502115 | 16263281503832 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 71 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 16 | 24 | 29312 | 0x7faac3119280 | 0x7faac0224540 | 16263281520122 | 16263281527716 | 16263281707877 | 16263281709888 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 74 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 30016 | 0x7faac3119100 | 0x7faac0224580 | 16263281724228 | 16263281732037 | 16263281823717 | 16263281825555 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 77 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 8 | 24 | 30976 | 0x7faac097df80 | 0x7faac02245c0 | 16263281841015 | 16263281848678 | 16263281939878 | 16263281941703 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 80 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 31680 | 0x7faac097de00 | 0x7faac0224600 | 16263281961672 | 16263281972198 | 16263282064359 | 16263282066050 |
| 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 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 16 | 24 | 32640 | 0x7faac097dc80 | 0x7faac0224640 | 16263282088180 | 16263282098599 | 16263282277960 | 16263282280025 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 86 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 33600 | 0x7faac097db00 | 0x7faac0224680 | 16263282295595 | 16263282303241 | 16263282483402 | 16263282485301 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 89 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 34560 | 0x7faac097d980 | 0x7faac02246c0 | 16263282500380 | 16263282508362 | 16263282600843 | 16263282602748 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 92 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 8 | 24 | 35520 | 0x7faac097d800 | 0x7faac0224700 | 16263282616998 | 16263282624843 | 16263282717003 | 16263282719056 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 95 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 36224 | 0x7faac097d680 | 0x7faac0224740 | 16263282740795 | 16263282750123 | 16263282842444 | 16263282844413 |
| 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 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 37184 | 0x7faac3119500 | 0x7faac0224780 | 16263282858992 | 16263282866764 | 16263283045325 | 16263283047438 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 101 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 38144 | 0x7faac3119380 | 0x7faac02247c0 | 16263283061268 | 16263283069486 | 16263283249327 | 16263283251344 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 104 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 39104 | 0x7faac3119200 | 0x7faac0224800 | 16263283266163 | 16263283274127 | 16263283366607 | 16263283368641 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 107 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 8 | 24 | 40320 | 0x7faac3119080 | 0x7faac0224840 | 16263283382791 | 16263283390288 | 16263283482288 | 16263283484279 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 110 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 41280 | 0x7faac097df00 | 0x7faac0224880 | 16263283504408 | 16263283514768 | 16263283606609 | 16263283608336 |
| 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 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 42240 | 0x7faac097dd80 | 0x7faac02248c0 | 16263283623516 | 16263283631249 | 16263283811730 | 16263283813591 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 116 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 43200 | 0x7faac097dc00 | 0x7faac0224900 | 16263283828841 | 16263283836530 | 16263284017812 | 16263284019797 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 119 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 8 | 24 | 44160 | 0x7faac097da80 | 0x7faac0224940 | 16263284035456 | 16263284044052 | 16263284136212 | 16263284138214 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 122 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 45376 | 0x7faac097d900 | 0x7faac0224980 | 16263284154384 | 16263284161813 | 16263284255253 | 16263284257002 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 125 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 46336 | 0x7faac097d780 | 0x7faac02249c0 | 16263284278271 | 16263284288853 | 16263284380854 | 16263284382659 |
| 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 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 47552 | 0x7faac097d600 | 0x7faac0224a00 | 16263284398498 | 16263284405974 | 16263284585655 | 16263284587364 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 131 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 48512 | 0x7faac3119480 | 0x7faac0224a40 | 16263284602544 | 16263284609975 | 16263284789177 | 16263284790880 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 134 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 8 | 24 | 49472 | 0x7faac3119300 | 0x7faac0224a80 | 16263284805489 | 16263284813017 | 16263284904697 | 16263284906507 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 137 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 50688 | 0x7faac3119180 | 0x7faac0224ac0 | 16263284921387 | 16263284929497 | 16263285021978 | 16263285023685 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 140 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 51648 | 0x7faac3119000 | 0x7faac0224b00 | 16263285044934 | 16263285055738 | 16263285146779 | 16263285148622 |
| 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 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 52864 | 0x7faac097de80 | 0x7faac0224b40 | 16263285164361 | 16263285171739 | 16263285351420 | 16263285353107 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 146 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 54080 | 0x7faac097dd00 | 0x7faac0224b80 | 16263285367387 | 16263285375420 | 16263285557182 | 16263285558893 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 149 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 8 | 24 | 55296 | 0x7faac097db80 | 0x7faac0224bc0 | 16263285573242 | 16263285581022 | 16263285674622 | 16263285676290 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 152 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 56768 | 0x7faac097da00 | 0x7faac0224c00 | 16263285693020 | 16263285700862 | 16263285794463 | 16263285796297 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 155 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 57728 | 0x7faac097d880 | 0x7faac0224c40 | 16263285818007 | 16263285828703 | 16263285920544 | 16263285922355 |
| 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 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 58944 | 0x7faac097d700 | 0x7faac0224c80 | 16263285938084 | 16263285945664 | 16263286124545 | 16263286126450 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 161 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 60160 | 0x7faac3119580 | 0x7faac0224cc0 | 16263286141580 | 16263286149505 | 16263286329667 | 16263286331356 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 164 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 8 | 24 | 61376 | 0x7faac3119400 | 0x7faac0224d00 | 16263286345095 | 16263286352867 | 16263286445827 | 16263286447593 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 167 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 62848 | 0x7faac3119280 | 0x7faac0224d40 | 16263286463133 | 16263286471267 | 16263286568228 | 16263286569990 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 170 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 63808 | 0x7faac3119100 | 0x7faac0224d80 | 16263286589910 | 16263286600388 | 16263286692549 | 16263286694378 |
| 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 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 65024 | 0x7faac097df80 | 0x7faac0224dc0 | 16263286711437 | 16263286720229 | 16263286899270 | 16263286901043 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 176 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 66240 | 0x7faac097de00 | 0x7faac0224e00 | 16263286915873 | 16263286923910 | 16263287102631 | 16263287104439 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 179 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 8 | 24 | 67456 | 0x7faac097dc80 | 0x7faac0224e40 | 16263287119158 | 16263287126952 | 16263287219752 | 16263287221516 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 182 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 68928 | 0x7faac097db00 | 0x7faac0224e80 | 16263287235996 | 16263287243592 | 16263287345673 | 16263287347443 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 185 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 70144 | 0x7faac097d980 | 0x7faac0224ec0 | 16263287368363 | 16263287378953 | 16263287470954 | 16263287472770 |
| 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 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 71616 | 0x7faac097d800 | 0x7faac0224f00 | 16263287488020 | 16263287495754 | 16263287676235 | 16263287678046 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 191 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 72832 | 0x7faac097d680 | 0x7faac0224f40 | 16263287693286 | 16263287701675 | 16263287881997 | 16263287883671 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 194 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 8 | 24 | 74048 | 0x7faac3119500 | 0x7faac0224f80 | 16263287898561 | 16263287906157 | 16263287998477 | 16263288000239 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 197 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 75776 | 0x7faac3119380 | 0x7faac0224fc0 | 16263288014938 | 16263288022477 | 16263288128398 | 16263288130046 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 200 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 76992 | 0x7faac3119200 | 0x7faac0225000 | 16263288150886 | 16263288161518 | 16263288253999 | 16263288255703 |
| 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 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 78464 | 0x7faac3119080 | 0x7faac0225040 | 16263288270403 | 16263288278159 | 16263288458480 | 16263288460149 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 206 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 79936 | 0x7faac097df00 | 0x7faac0225080 | 16263288474808 | 16263288483120 | 16263288661842 | 16263288663524 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 209 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 8 | 24 | 81408 | 0x7faac097dd80 | 0x7faac02250c0 | 16263288680054 | 16263288688882 | 16263288782162 | 16263288783862 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 212 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 83136 | 0x7faac097dc00 | 0x7faac0225100 | 16263288799871 | 16263288807282 | 16263288918963 | 16263288920699 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 215 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 84352 | 0x7faac097da80 | 0x7faac0225140 | 16263288959448 | 16263288969044 | 16263289062004 | 16263289064075 |
| 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 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 85824 | 0x7faac097d900 | 0x7faac0225180 | 16263289079375 | 16263289087444 | 16263289267925 | 16263289269731 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 221 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 87296 | 0x7faac097d780 | 0x7faac02251c0 | 16263289284681 | 16263289292726 | 16263289472567 | 16263289474276 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 224 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 88768 | 0x7faac097d600 | 0x7faac0225200 | 16263289489276 | 16263289497207 | 16263289590648 | 16263289592314 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 227 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 90752 | 0x7faac3119480 | 0x7faac0225240 | 16263289607063 | 16263289615928 | 16263289734008 | 16263289735811 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 230 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 91968 | 0x7faac3119300 | 0x7faac0225280 | 16263289756510 | 16263289766969 | 16263289859129 | 16263289860838 |
| 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 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 93440 | 0x7faac3119180 | 0x7faac02252c0 | 16263289875368 | 16263289883289 | 16263290063131 | 16263290064913 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 236 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 94912 | 0x7faac3119000 | 0x7faac0225300 | 16263290092643 | 16263290102971 | 16263290283132 | 16263290285159 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 239 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 96384 | 0x7faac097de80 | 0x7faac0225340 | 16263290300998 | 16263290309372 | 16263290403453 | 16263290405486 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 242 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 98368 | 0x7faac097dd00 | 0x7faac0225380 | 16263290420645 | 16263290428253 | 16263290551774 | 16263290553663 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 245 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 99584 | 0x7faac097db80 | 0x7faac02253c0 | 16263290574182 | 16263290584574 | 16263290677375 | 16263290679420 |
| 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 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 101312 | 0x7faac097da00 | 0x7faac0225400 | 16263290695089 | 16263290702975 | 16263290880416 | 16263290882315 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 251 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 102784 | 0x7faac097d880 | 0x7faac0225440 | 16263290897405 | 16263290905376 | 16263291083777 | 16263291085741 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 254 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 104256 | 0x7faac097d700 | 0x7faac0225480 | 16263291100400 | 16263291108257 | 16263291201218 | 16263291203208 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 257 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 106240 | 0x7faac3119580 | 0x7faac02254c0 | 16263291218018 | 16263291225858 | 16263291354819 | 16263291356795 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 260 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 107712 | 0x7faac3119400 | 0x7faac0225500 | 16263291376764 | 16263291387299 | 16263291479460 | 16263291481452 |
| 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 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 16 | 24 | 109440 | 0x7faac3119280 | 0x7faac0225540 | 16263291497012 | 16263291505220 | 16263291684261 | 16263291686157 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 266 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 16 | 24 | 111168 | 0x7faac3119100 | 0x7faac0225580 | 16263291700967 | 16263291708581 | 16263291888742 | 16263291890673 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 269 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 8 | 24 | 112896 | 0x7faac097df80 | 0x7faac02255c0 | 16263291905333 | 16263291913062 | 16263292006983 | 16263292008870 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 272 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 115136 | 0x7faac097de00 | 0x7faac0225600 | 16263292023540 | 16263292031303 | 16263292167464 | 16263292169167 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 275 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 116608 | 0x7faac097dc80 | 0x7faac0225640 | 16263292189986 | 16263292200424 | 16263292294025 | 16263292295644 |
| 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 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 16 | 24 | 118336 | 0x7faac097db00 | 0x7faac0225680 | 16263292310424 | 16263292318185 | 16263292497546 | 16263292499309 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 281 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 16 | 24 | 120064 | 0x7faac097d980 | 0x7faac02256c0 | 16263292514209 | 16263292522186 | 16263292702508 | 16263292704195 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 284 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 121792 | 0x7faac097d800 | 0x7faac0225700 | 16263292719215 | 16263292726988 | 16263292822188 | 16263292823952 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 287 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 124032 | 0x7faac097d680 | 0x7faac0225740 | 16263292839982 | 16263292847628 | 16263292989709 | 16263292991508 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 290 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 125504 | 0x7faac3119500 | 0x7faac0225780 | 16263293013608 | 16263293024110 | 16263293117390 | 16263293119176 |
| 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 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 127488 | 0x7faac3119380 | 0x7faac02257c0 | 16263293134535 | 16263293142350 | 16263293320272 | 16263293321971 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 296 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 129216 | 0x7faac3119200 | 0x7faac0225800 | 16263293337051 | 16263293344752 | 16263293523793 | 16263293525447 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 299 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 130944 | 0x7faac3119080 | 0x7faac0225840 | 16263293541476 | 16263293549713 | 16263293648754 | 16263293650484 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 302 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 133440 | 0x7faac097df00 | 0x7faac0225880 | 16263293666284 | 16263293674034 | 16263293827155 | 16263293828880 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 305 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 134912 | 0x7faac097dd80 | 0x7faac02258c0 | 16263293851489 | 16263293861875 | 16263293954996 | 16263293956637 |
| 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 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 136896 | 0x7faac097dc00 | 0x7faac0225900 | 16263293973277 | 16263293980916 | 16263294158997 | 16263294161073 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 311 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 138880 | 0x7faac097da80 | 0x7faac0225940 | 16263294176712 | 16263294184437 | 16263294363158 | 16263294365068 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 314 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 140864 | 0x7faac097d900 | 0x7faac0225980 | 16263294379288 | 16263294386838 | 16263294490679 | 16263294492625 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 317 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 143616 | 0x7faac097d780 | 0x7faac02259c0 | 16263294506685 | 16263294514359 | 16263294681880 | 16263294683971 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 320 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 145344 | 0x7faac097d600 | 0x7faac0225a00 | 16263294704161 | 16263294714521 | 16263294808601 | 16263294810558 |
| 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 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 147584 | 0x7faac3119480 | 0x7faac0225a40 | 16263294825278 | 16263294832761 | 16263295011802 | 16263295013824 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 326 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 149568 | 0x7faac3119300 | 0x7faac0225a80 | 16263295027794 | 16263295035483 | 16263295215164 | 16263295217179 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 329 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 151552 | 0x7faac3119180 | 0x7faac0225ac0 | 16263295231479 | 16263295239324 | 16263295347965 | 16263295349826 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 332 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 154304 | 0x7faac3119000 | 0x7faac0225b00 | 16263295364496 | 16263295372285 | 16263295551166 | 16263295552872 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 335 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 156288 | 0x7faac097de80 | 0x7faac0225b40 | 16263295574011 | 16263295583486 | 16263295683647 | 16263295685649 |
| 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 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 158784 | 0x7faac097dd00 | 0x7faac0225b80 | 16263295702329 | 16263295709887 | 16263295891968 | 16263295893954 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 341 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 161024 | 0x7faac097db80 | 0x7faac0225bc0 | 16263295908064 | 16263295915968 | 16263296099489 | 16263296101630 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 344 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 163264 | 0x7faac097da00 | 0x7faac0225c00 | 16263296115580 | 16263296123650 | 16263296244610 | 16263296246687 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 347 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 166528 | 0x7faac097d880 | 0x7faac0225c40 | 16263296261296 | 16263296269091 | 16263296472932 | 16263296516871 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 350 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 168512 | 0x7faac097d700 | 0x7faac0225c80 | 16263296532240 | 16263296542852 | 16263296651013 | 16263296652688 |
| 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 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 171264 | 0x7faac3119580 | 0x7faac0225cc0 | 16263296669077 | 16263296677253 | 16263296859814 | 16263296861543 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 356 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 173760 | 0x7faac3119400 | 0x7faac0225d00 | 16263296876633 | 16263296884454 | 16263297069896 | 16263297071649 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 359 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 176256 | 0x7faac3119280 | 0x7faac0225d40 | 16263297088538 | 16263297096616 | 16263297229097 | 16263297230815 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 362 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 179776 | 0x7faac3119100 | 0x7faac0225d80 | 16263297245235 | 16263297253097 | 16263297484138 | 16263297502759 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 365 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 182272 | 0x7faac097df80 | 0x7faac0225dc0 | 16263297518019 | 16263297528779 | 16263297654059 | 16263297655756 |
| 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 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 185536 | 0x7faac097de00 | 0x7faac0225e00 | 16263297671105 | 16263297679020 | 16263297870701 | 16263297872611 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 371 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 188544 | 0x7faac097dc80 | 0x7faac0225e40 | 16263297888111 | 16263297896301 | 16263298090862 | 16263298092876 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 374 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 191552 | 0x7faac097db00 | 0x7faac0225e80 | 16263298117915 | 16263298127502 | 16263298285584 | 16263298287402 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 377 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 195840 | 0x7faac097d980 | 0x7faac0225ec0 | 16263298302601 | 16263298310224 | 16263298591345 | 16263298610025 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 380 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 198592 | 0x7faac097d800 | 0x7faac0225f00 | 16263298626034 | 16263298636626 | 16263298782227 | 16263298784021 |
| 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 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 202368 | 0x7faac097d680 | 0x7faac0225f40 | 16263298800940 | 16263298809267 | 16263299021268 | 16263299039065 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 386 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 205888 | 0x7faac3119500 | 0x7faac0225f80 | 16263299049865 | 16263299059989 | 16263299270550 | 16263299312479 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 389 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 209408 | 0x7faac3119380 | 0x7faac0225fc0 | 16263299321429 | 16263299331510 | 16263299515511 | 16263299517124 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 392 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 214464 | 0x7faac3119200 | 0x7faac0226000 | 16263299532494 | 16263299540472 | 16263299873274 | 16263299889706 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 395 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 217728 | 0x7faac3119080 | 0x7faac0226040 | 16263299906236 | 16263299916634 | 16263300080635 | 16263300082452 |
| 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 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 222016 | 0x7faac097df00 | 0x7faac0226080 | 16263300098572 | 16263300106555 | 16263300338397 | 16263300353506 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 401 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 226048 | 0x7faac097dd80 | 0x7faac02260c0 | 16263300362946 | 16263300373117 | 16263300602078 | 16263300617690 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 404 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 230080 | 0x7faac097dc00 | 0x7faac0226100 | 16263300628890 | 16263300638879 | 16263300848640 | 16263300862895 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 407 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 235904 | 0x7faac097da80 | 0x7faac0226140 | 16263300872644 | 16263300881760 | 16263301264483 | 16263301278905 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 410 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 239424 | 0x7faac097d900 | 0x7faac0226180 | 16263301295285 | 16263301305763 | 16263301489924 | 16263301491671 |
| 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 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 244224 | 0x7faac097d780 | 0x7faac02261c0 | 16263301507610 | 16263301515364 | 16263301767366 | 16263301781804 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 416 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 248768 | 0x7faac097d600 | 0x7faac0226200 | 16263301792064 | 16263301802246 | 16263302047848 | 16263302062618 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 419 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 253312 | 0x7faac3119480 | 0x7faac0226240 | 16263302072998 | 16263302087528 | 16263302322890 | 16263302363821 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 422 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 8 | 24 | 255552 | 0x7faac3119300 | 0x7faac0226280 | 16263302372911 | 16263302382090 | 16263302832013 | 16263302873210 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 425 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 259840 | 0x7faac3119180 | 0x7faac02262c0 | 16263302891600 | 16263302902253 | 16263303124655 | 16263303163404 |
| 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 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 265664 | 0x7faac3119000 | 0x7faac0226300 | 16263303176474 | 16263303186415 | 16263303485297 | 16263303523786 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 431 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 271232 | 0x7faac097de80 | 0x7faac0226340 | 16263303535046 | 16263303544337 | 16263303841779 | 16263303883828 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 434 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 8 | 24 | 273216 | 0x7faac097dd00 | 0x7faac0226380 | 16263303894738 | 16263303905620 | 16263304199222 | 16263304241220 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 437 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 8 | 24 | 275712 | 0x7faac097db80 | 0x7faac02263c0 | 16263304250490 | 16263304260662 | 16263304814106 | 16263304852967 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 440 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 280768 | 0x7faac097da00 | 0x7faac0226400 | 16263304869186 | 16263304879546 | 16263305141148 | 16263305182929 |
| 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 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 287616 | 0x7faac097d880 | 0x7faac0226440 | 16263305194059 | 16263305204188 | 16263305555390 | 16263305573831 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 446 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 294208 | 0x7faac097d700 | 0x7faac0226480 | 16263305585241 | 16263305600351 | 16263305950113 | 16263305968182 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 449 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 8 | 24 | 296960 | 0x7faac3119580 | 0x7faac02264c0 | 16263305978992 | 16263305989153 | 16263306333315 | 16263306374913 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 452 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 8 | 24 | 299968 | 0x7faac3119400 | 0x7faac0226500 | 16263306384723 | 16263306394276 | 16263307051240 | 16263307100027 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 455 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 8 | 24 | 302720 | 0x7faac3119280 | 0x7faac0226540 | 16263307117377 | 16263307126920 | 16263307569963 | 16263307611966 |
| 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 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 305472 | 0x7faac3119100 | 0x7faac0226580 | 16263307625645 | 16263307635884 | 16263308096687 | 16263308143924 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 461 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 308224 | 0x7faac097df80 | 0x7faac02265c0 | 16263308153784 | 16263308163727 | 16263308621330 | 16263308665482 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 464 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 8 | 24 | 310976 | 0x7faac097de00 | 0x7faac0226600 | 16263308675222 | 16263308685330 | 16263309133973 | 16263309178341 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 467 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 8 | 24 | 313216 | 0x7faac097dc80 | 0x7faac0226640 | 16263309187811 | 16263309197814 | 16263310062619 | 16263310116600 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 470 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 8 | 24 | 315968 | 0x7faac097db00 | 0x7faac0226680 | 16263310135330 | 16263310145340 | 16263310994305 | 16263311040350 |
| 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 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 318720 | 0x7faac097d980 | 0x7faac02266c0 | 16263311050970 | 16263311060706 | 16263311941671 | 16263311987789 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 476 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 321472 | 0x7faac097d800 | 0x7faac0226700 | 16263311997929 | 16263312007752 | 16263312882958 | 16263312927148 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 479 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 8 | 24 | 324224 | 0x7faac097d680 | 0x7faac0226740 | 16263312937418 | 16263312953678 | 16263313808403 | 16263313853578 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 482 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 8 | 24 | 326464 | 0x7faac3119500 | 0x7faac0226780 | 16263313863608 | 16263313873364 | 16263315566495 | 16263315640918 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 485 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 8 | 24 | 329216 | 0x7faac3119380 | 0x7faac02267c0 | 16263315658658 | 16263315668735 | 16263317329706 | 16263317397339 |
| 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 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 331968 | 0x7faac3119200 | 0x7faac0226800 | 16263317407949 | 16263317416907 | 16263319136438 | 16263319206489 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 491 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 12 | 24 | 334720 | 0x7faac3119080 | 0x7faac0226840 | 16263319216849 | 16263319226678 | 16263320937889 | 16263321003470 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 494 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 8 | 24 | 337472 | 0x7faac097df00 | 0x7faac0226880 | 16263321013760 | 16263321023330 | 16263322692301 | 16263322760701 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 497 | 152884 | 152884 | 4194304 | 256 | 0 | 0 | 8 | 24 | 0 | 0x7faac097dd80 | 0x7faac02268c0 | 16263322771491 | 16263322781101 | 16263326133923 | 16263326208215 |