38 KiB
38 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | SQ_INSTS_LDS | SQ_INST_LEVEL_LDS | SQ_ACCUM_PREV_HIRES | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBufferAligned.kd | 0 | 0 | 0 | 23312 | 23312 | 33554432 | 256 | 0 | 0 | 4 | 32 | 4160 | 0x0 | 0x7feaad204280 | 0 | 0 | 0 | 14233267445370 | 14232642250674 | 14233414720083 | 14233414811963 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 23312 | 23312 | 32768 | 256 | 0 | 0 | 12 | 24 | 13888 | 0x0 | 0x7feaad223f80 | 0 | 0 | 0 | 14233420005197 | 14233414720083 | 14233420131141 | 14233420134244 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 5 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 14336 | 0x7feab02cc380 | 0x7feaad223fc0 | 0 | 0 | 0 | 14233420170393 | 14233420131141 | 14233420457702 | 14233420460207 |
| 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 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15040 | 0x7feab02cc200 | 0x7feaad224000 | 0 | 0 | 0 | 14233420496887 | 14233420457702 | 14233420856424 | 14233420858779 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 11 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15488 | 0x7feab02cc080 | 0x7feaad224040 | 0 | 0 | 0 | 14233420890689 | 14233420856424 | 14233421251465 | 14233421253831 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 14 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 15936 | 0x7feaadc2df00 | 0x7feaad224080 | 0 | 0 | 0 | 14233421286690 | 14233421251465 | 14233421564586 | 14233421566805 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 17 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 16384 | 0x7feaadc2dd80 | 0x7feaad2240c0 | 0 | 0 | 0 | 14233421599144 | 14233421564586 | 14233421870027 | 14233421872388 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 20 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 17088 | 0x7feaadc2dc00 | 0x7feaad224100 | 0 | 0 | 0 | 14233421915368 | 14233421870027 | 14233422173548 | 14233422175942 |
| 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 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 16 | 24 | 17792 | 0x7feaadc2da80 | 0x7feaad224140 | 0 | 0 | 0 | 14233422206112 | 14233422173548 | 14233422575630 | 14233422577884 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 26 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 16 | 24 | 18496 | 0x7feaadc2d900 | 0x7feaad224180 | 0 | 0 | 0 | 14233422608323 | 14233422575630 | 14233422967471 | 14233422969786 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 29 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19200 | 0x7feaadc2d780 | 0x7feaad2241c0 | 0 | 0 | 0 | 14233422999415 | 14233422967471 | 14233423285712 | 14233423288309 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 32 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19904 | 0x7feaadc2d600 | 0x7feaad224200 | 0 | 0 | 0 | 14233423319219 | 14233423285712 | 14233423589073 | 14233423591443 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 35 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 20608 | 0x7feab02cc480 | 0x7feaad224240 | 0 | 0 | 0 | 14233423630112 | 14233423589073 | 14233423895954 | 14233423898357 |
| 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 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 16 | 24 | 21312 | 0x7feab02cc300 | 0x7feaad224280 | 0 | 0 | 0 | 14233423928926 | 14233423895954 | 14233424285235 | 14233424287569 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 41 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22016 | 0x7feab02cc180 | 0x7feaad2242c0 | 0 | 0 | 0 | 14233424318808 | 14233424285235 | 14233424675157 | 14233424677491 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 44 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22720 | 0x7feab02cc000 | 0x7feaad224300 | 0 | 0 | 0 | 14233424708090 | 14233424675157 | 14233424974838 | 14233424977245 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 47 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 23424 | 0x7feaadc2de80 | 0x7feaad224340 | 0 | 0 | 0 | 14233425007194 | 14233424974838 | 14233425275319 | 14233425277809 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 50 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 24128 | 0x7feaadc2dd00 | 0x7feaad224380 | 0 | 0 | 0 | 14233425314958 | 14233425275319 | 14233425575160 | 14233425577492 |
| 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 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 16 | 24 | 24832 | 0x7feaadc2db80 | 0x7feaad2243c0 | 0 | 0 | 0 | 14233425607532 | 14233425575160 | 14233425963801 | 14233425966164 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 56 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 16 | 24 | 25536 | 0x7feaadc2da00 | 0x7feaad224400 | 0 | 0 | 0 | 14233425997074 | 14233425963801 | 14233426380923 | 14233426383696 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 59 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26240 | 0x7feaadc2d880 | 0x7feaad224440 | 0 | 0 | 0 | 14233426414205 | 14233426380923 | 14233426696924 | 14233426699540 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 62 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26944 | 0x7feaadc2d700 | 0x7feaad224480 | 0 | 0 | 0 | 14233426729259 | 14233426696924 | 14233427001565 | 14233427003913 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 65 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 27648 | 0x7feab02cc580 | 0x7feaad2244c0 | 0 | 0 | 0 | 14233427040503 | 14233427001565 | 14233427285246 | 14233427286918 |
| 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 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 16 | 24 | 28608 | 0x7feab02cc400 | 0x7feaad224500 | 0 | 0 | 0 | 14233427318107 | 14233427285246 | 14233427648287 | 14233427650120 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 71 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 16 | 24 | 29312 | 0x7feab02cc280 | 0x7feaad224540 | 0 | 0 | 0 | 14233427681020 | 14233427648287 | 14233428011168 | 14233428012883 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 74 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 30016 | 0x7feab02cc100 | 0x7feaad224580 | 0 | 0 | 0 | 14233428043812 | 14233428011168 | 14233428287009 | 14233428288867 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 77 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 8 | 24 | 30976 | 0x7feaadc2df80 | 0x7feaad2245c0 | 0 | 0 | 0 | 14233428319397 | 14233428287009 | 14233428560610 | 14233428562472 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 80 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 31680 | 0x7feaadc2de00 | 0x7feaad224600 | 0 | 0 | 0 | 14233428600031 | 14233428560610 | 14233428842051 | 14233428843896 |
| 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 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 16 | 24 | 32640 | 0x7feaadc2dc80 | 0x7feaad224640 | 0 | 0 | 0 | 14233428873915 | 14233428842051 | 14233429203013 | 14233429204659 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 86 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 33600 | 0x7feaadc2db00 | 0x7feaad224680 | 0 | 0 | 0 | 14233429235038 | 14233429203013 | 14233429564614 | 14233429566341 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 89 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 34560 | 0x7feaadc2d980 | 0x7feaad2246c0 | 0 | 0 | 0 | 14233429596271 | 14233429564614 | 14233429845575 | 14233429847386 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 92 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 8 | 24 | 35520 | 0x7feaadc2d800 | 0x7feaad224700 | 0 | 0 | 0 | 14233429877675 | 14233429845575 | 14233430121096 | 14233430123470 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 95 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 36224 | 0x7feaadc2d680 | 0x7feaad224740 | 0 | 0 | 0 | 14233430160139 | 14233430121096 | 14233430404617 | 14233430406334 |
| 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 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 37184 | 0x7feab02cc500 | 0x7feaad224780 | 0 | 0 | 0 | 14233430436303 | 14233430404617 | 14233430766218 | 14233430768047 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 101 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 38144 | 0x7feab02cc380 | 0x7feaad2247c0 | 0 | 0 | 0 | 14233430798606 | 14233430766218 | 14233431131339 | 14233431133039 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 104 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 39104 | 0x7feab02cc200 | 0x7feaad224800 | 0 | 0 | 0 | 14233431163269 | 14233431131339 | 14233431406380 | 14233431408094 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 107 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 8 | 24 | 40320 | 0x7feab02cc080 | 0x7feaad224840 | 0 | 0 | 0 | 14233431438753 | 14233431406380 | 14233431682701 | 14233431684448 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 110 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 41280 | 0x7feaadc2df00 | 0x7feaad224880 | 0 | 0 | 0 | 14233431722517 | 14233431682701 | 14233431963822 | 14233431965572 |
| 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 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 42240 | 0x7feaadc2dd80 | 0x7feaad2248c0 | 0 | 0 | 0 | 14233431995522 | 14233431963822 | 14233432326543 | 14233432328225 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 116 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 43200 | 0x7feaadc2dc00 | 0x7feaad224900 | 0 | 0 | 0 | 14233432358114 | 14233432326543 | 14233432692785 | 14233432694617 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 119 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 8 | 24 | 44160 | 0x7feaadc2da80 | 0x7feaad224940 | 0 | 0 | 0 | 14233432724767 | 14233432692785 | 14233432969426 | 14233432971242 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 122 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 45376 | 0x7feaadc2d900 | 0x7feaad224980 | 0 | 0 | 0 | 14233433001511 | 14233432969426 | 14233433252147 | 14233433253926 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 125 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 46336 | 0x7feaadc2d780 | 0x7feaad2249c0 | 0 | 0 | 0 | 14233433290845 | 14233433252147 | 14233433529268 | 14233433530860 |
| 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 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 47552 | 0x7feaadc2d600 | 0x7feaad224a00 | 0 | 0 | 0 | 14233433561019 | 14233433529268 | 14233433892949 | 14233433894783 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 131 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 48512 | 0x7feab02cc480 | 0x7feaad224a40 | 0 | 0 | 0 | 14233433925722 | 14233433892949 | 14233434254070 | 14233434256265 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 134 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 8 | 24 | 49472 | 0x7feab02cc300 | 0x7feaad224a80 | 0 | 0 | 0 | 14233434289094 | 14233434254070 | 14233434535511 | 14233434537299 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 137 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 50688 | 0x7feab02cc180 | 0x7feaad224ac0 | 0 | 0 | 0 | 14233434569329 | 14233434535511 | 14233434813272 | 14233434815114 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 140 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 51648 | 0x7feab02cc000 | 0x7feaad224b00 | 0 | 0 | 0 | 14233434852653 | 14233434813272 | 14233435095513 | 14233435097278 |
| 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 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 52864 | 0x7feaadc2de80 | 0x7feaad224b40 | 0 | 0 | 0 | 14233435128857 | 14233435095513 | 14233435462714 | 14233435464310 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 146 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 54080 | 0x7feaadc2dd00 | 0x7feaad224b80 | 0 | 0 | 0 | 14233435495090 | 14233435462714 | 14233435832796 | 14233435834573 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 149 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 8 | 24 | 55296 | 0x7feaadc2db80 | 0x7feaad224bc0 | 0 | 0 | 0 | 14233435865052 | 14233435832796 | 14233436110557 | 14233436112327 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 152 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 56768 | 0x7feaadc2da00 | 0x7feaad224c00 | 0 | 0 | 0 | 14233436143696 | 14233436110557 | 14233436389438 | 14233436391251 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 155 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 57728 | 0x7feaadc2d880 | 0x7feaad224c40 | 0 | 0 | 0 | 14233436428661 | 14233436389438 | 14233436669279 | 14233436671076 |
| 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 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 58944 | 0x7feaadc2d700 | 0x7feaad224c80 | 0 | 0 | 0 | 14233436700925 | 14233436669279 | 14233437031360 | 14233437033268 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 161 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 60160 | 0x7feab02cc580 | 0x7feaad224cc0 | 0 | 0 | 0 | 14233437064018 | 14233437031360 | 14233437391361 | 14233437393101 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 164 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 8 | 24 | 61376 | 0x7feab02cc400 | 0x7feaad224d00 | 0 | 0 | 0 | 14233437423310 | 14233437391361 | 14233437665282 | 14233437667055 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 167 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 62848 | 0x7feab02cc280 | 0x7feaad224d40 | 0 | 0 | 0 | 14233437697565 | 14233437665282 | 14233437945923 | 14233437947589 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 170 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 63808 | 0x7feab02cc100 | 0x7feaad224d80 | 0 | 0 | 0 | 14233437986729 | 14233437945923 | 14233438231844 | 14233438233684 |
| 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 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 65024 | 0x7feaadc2df80 | 0x7feaad224dc0 | 0 | 0 | 0 | 14233438265143 | 14233438231844 | 14233438593605 | 14233438595416 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 176 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 66240 | 0x7feaadc2de00 | 0x7feaad224e00 | 0 | 0 | 0 | 14233438625786 | 14233438593605 | 14233438957767 | 14233438959409 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 179 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 8 | 24 | 67456 | 0x7feaadc2dc80 | 0x7feaad224e40 | 0 | 0 | 0 | 14233438990108 | 14233438957767 | 14233439232328 | 14233439234113 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 182 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 68928 | 0x7feaadc2db00 | 0x7feaad224e80 | 0 | 0 | 0 | 14233439264822 | 14233439232328 | 14233439518409 | 14233439520147 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 185 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 70144 | 0x7feaadc2d980 | 0x7feaad224ec0 | 0 | 0 | 0 | 14233439558486 | 14233439518409 | 14233439797769 | 14233439799622 |
| 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 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 71616 | 0x7feaadc2d800 | 0x7feaad224f00 | 0 | 0 | 0 | 14233439830891 | 14233439797769 | 14233440159691 | 14233440161344 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 191 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 72832 | 0x7feaadc2d680 | 0x7feaad224f40 | 0 | 0 | 0 | 14233440191803 | 14233440159691 | 14233440520012 | 14233440521747 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 194 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 8 | 24 | 74048 | 0x7feab02cc500 | 0x7feaad224f80 | 0 | 0 | 0 | 14233440551436 | 14233440520012 | 14233440796013 | 14233440797631 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 197 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 75776 | 0x7feab02cc380 | 0x7feaad224fc0 | 0 | 0 | 0 | 14233440828030 | 14233440796013 | 14233441086414 | 14233441088135 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 200 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 76992 | 0x7feab02cc200 | 0x7feaad225000 | 0 | 0 | 0 | 14233441126174 | 14233441086414 | 14233441360815 | 14233441362879 |
| 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 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 78464 | 0x7feab02cc080 | 0x7feaad225040 | 0 | 0 | 0 | 14233441393179 | 14233441360815 | 14233441729296 | 14233441731092 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 206 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 79936 | 0x7feaadc2df00 | 0x7feaad225080 | 0 | 0 | 0 | 14233441762021 | 14233441729296 | 14233442092177 | 14233442094074 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 209 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 8 | 24 | 81408 | 0x7feaadc2dd80 | 0x7feaad2250c0 | 0 | 0 | 0 | 14233442125424 | 14233442092177 | 14233442373618 | 14233442375189 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 212 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 83136 | 0x7feaadc2dc00 | 0x7feaad225100 | 0 | 0 | 0 | 14233442405728 | 14233442373618 | 14233442674739 | 14233442676383 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 215 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 84352 | 0x7feaadc2da80 | 0x7feaad225140 | 0 | 0 | 0 | 14233442726481 | 14233442674739 | 14233442953460 | 14233442955367 |
| 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 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 85824 | 0x7feaadc2d900 | 0x7feaad225180 | 0 | 0 | 0 | 14233442984776 | 14233442953460 | 14233443332822 | 14233443334669 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 221 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 87296 | 0x7feaadc2d780 | 0x7feaad2251c0 | 0 | 0 | 0 | 14233443364808 | 14233443332822 | 14233443695543 | 14233443697302 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 224 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 88768 | 0x7feaadc2d600 | 0x7feaad225200 | 0 | 0 | 0 | 14233443727311 | 14233443695543 | 14233443972504 | 14233443974196 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 227 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 90752 | 0x7feab02cc480 | 0x7feaad225240 | 0 | 0 | 0 | 14233444004855 | 14233443972504 | 14233444276345 | 14233444278130 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 230 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 91968 | 0x7feab02cc300 | 0x7feaad225280 | 0 | 0 | 0 | 14233444315879 | 14233444276345 | 14233444558106 | 14233444559894 |
| 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 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 93440 | 0x7feab02cc180 | 0x7feaad2252c0 | 0 | 0 | 0 | 14233444589663 | 14233444558106 | 14233444928987 | 14233444930706 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 236 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 94912 | 0x7feab02cc000 | 0x7feaad225300 | 0 | 0 | 0 | 14233444961856 | 14233444928987 | 14233445291709 | 14233445293369 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 239 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 96384 | 0x7feaadc2de80 | 0x7feaad225340 | 0 | 0 | 0 | 14233445323508 | 14233445291709 | 14233445568350 | 14233445570033 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 242 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 98368 | 0x7feaadc2dd00 | 0x7feaad225380 | 0 | 0 | 0 | 14233445600663 | 14233445568350 | 14233445878431 | 14233445880167 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 245 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 99584 | 0x7feaadc2db80 | 0x7feaad2253c0 | 0 | 0 | 0 | 14233445917346 | 14233445878431 | 14233446154272 | 14233446156111 |
| 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 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 101312 | 0x7feaadc2da00 | 0x7feaad225400 | 0 | 0 | 0 | 14233446187151 | 14233446154272 | 14233446524513 | 14233446526294 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 251 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 102784 | 0x7feaadc2d880 | 0x7feaad225440 | 0 | 0 | 0 | 14233446557063 | 14233446524513 | 14233446890114 | 14233446891806 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 254 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 104256 | 0x7feaadc2d700 | 0x7feaad225480 | 0 | 0 | 0 | 14233446921856 | 14233446890114 | 14233447168355 | 14233447170031 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 257 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 106240 | 0x7feab02cc580 | 0x7feaad2254c0 | 0 | 0 | 0 | 14233447201160 | 14233447168355 | 14233447483876 | 14233447485654 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 260 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 107712 | 0x7feab02cc400 | 0x7feaad225500 | 0 | 0 | 0 | 14233447523703 | 14233447483876 | 14233447767077 | 14233447768788 |
| 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 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 16 | 24 | 109440 | 0x7feab02cc280 | 0x7feaad225540 | 0 | 0 | 0 | 14233447799068 | 14233447767077 | 14233448129318 | 14233448131041 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 266 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 16 | 24 | 111168 | 0x7feab02cc100 | 0x7feaad225580 | 0 | 0 | 0 | 14233448162510 | 14233448129318 | 14233448492840 | 14233448494564 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 269 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 8 | 24 | 112896 | 0x7feaadc2df80 | 0x7feaad2255c0 | 0 | 0 | 0 | 14233448525723 | 14233448492840 | 14233448770761 | 14233448772508 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 272 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 115136 | 0x7feaadc2de00 | 0x7feaad225600 | 0 | 0 | 0 | 14233448802977 | 14233448770761 | 14233449094122 | 14233449095861 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 275 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 116608 | 0x7feaadc2dc80 | 0x7feaad225640 | 0 | 0 | 0 | 14233449134021 | 14233449094122 | 14233449371403 | 14233449373236 |
| 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 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 16 | 24 | 118336 | 0x7feaadc2db00 | 0x7feaad225680 | 0 | 0 | 0 | 14233449403215 | 14233449371403 | 14233449734924 | 14233449736448 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 281 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 16 | 24 | 120064 | 0x7feaadc2d980 | 0x7feaad2256c0 | 0 | 0 | 0 | 14233449766678 | 14233449734924 | 14233450097485 | 14233450099711 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 284 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 121792 | 0x7feaadc2d800 | 0x7feaad225700 | 0 | 0 | 0 | 14233450130280 | 14233450097485 | 14233450380526 | 14233450382345 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 287 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 124032 | 0x7feaadc2d680 | 0x7feaad225740 | 0 | 0 | 0 | 14233450412745 | 14233450380526 | 14233450705647 | 14233450707309 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 290 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 125504 | 0x7feab02cc500 | 0x7feaad225780 | 0 | 0 | 0 | 14233450745438 | 14233450705647 | 14233450994128 | 14233450995963 |
| 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 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 127488 | 0x7feab02cc380 | 0x7feaad2257c0 | 0 | 0 | 0 | 14233451026382 | 14233450994128 | 14233451358450 | 14233451360065 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 296 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 129216 | 0x7feab02cc200 | 0x7feaad225800 | 0 | 0 | 0 | 14233451391134 | 14233451358450 | 14233451720851 | 14233451722708 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 299 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 130944 | 0x7feab02cc080 | 0x7feaad225840 | 0 | 0 | 0 | 14233451753607 | 14233451720851 | 14233452002932 | 14233452004642 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 302 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 133440 | 0x7feaadc2df00 | 0x7feaad225880 | 0 | 0 | 0 | 14233452035761 | 14233452002932 | 14233452342773 | 14233452344565 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 305 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 134912 | 0x7feaadc2dd80 | 0x7feaad2258c0 | 0 | 0 | 0 | 14233452382714 | 14233452342773 | 14233452620214 | 14233452621959 |
| 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 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 136896 | 0x7feaadc2dc00 | 0x7feaad225900 | 0 | 0 | 0 | 14233452652439 | 14233452620214 | 14233452979255 | 14233452980992 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 311 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 138880 | 0x7feaadc2da80 | 0x7feaad225940 | 0 | 0 | 0 | 14233453012381 | 14233452979255 | 14233453343577 | 14233453345344 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 314 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 140864 | 0x7feaadc2d900 | 0x7feaad225980 | 0 | 0 | 0 | 14233453375354 | 14233453343577 | 14233453632378 | 14233453634069 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 317 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 143616 | 0x7feaadc2d780 | 0x7feaad2259c0 | 0 | 0 | 0 | 14233453664188 | 14233453632378 | 14233453988379 | 14233453990181 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 320 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 145344 | 0x7feaadc2d600 | 0x7feaad225a00 | 0 | 0 | 0 | 14233454028830 | 14233453988379 | 14233454286620 | 14233454288385 |
| 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 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 147584 | 0x7feab02cc480 | 0x7feaad225a40 | 0 | 0 | 0 | 14233454319164 | 14233454286620 | 14233454651741 | 14233454653528 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 326 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 149568 | 0x7feab02cc300 | 0x7feaad225a80 | 0 | 0 | 0 | 14233454684917 | 14233454651741 | 14233455012862 | 14233455014770 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 329 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 151552 | 0x7feab02cc180 | 0x7feaad225ac0 | 0 | 0 | 0 | 14233455044840 | 14233455012862 | 14233455305183 | 14233455306924 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 332 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 154304 | 0x7feab02cc000 | 0x7feaad225b00 | 0 | 0 | 0 | 14233455337854 | 14233455305183 | 14233455669185 | 14233455670897 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 335 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 156288 | 0x7feaadc2de80 | 0x7feaad225b40 | 0 | 0 | 0 | 14233455709236 | 14233455669185 | 14233455955586 | 14233455957361 |
| 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 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 158784 | 0x7feaadc2dd00 | 0x7feaad225b80 | 0 | 0 | 0 | 14233455987750 | 14233455955586 | 14233456322307 | 14233456323913 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 341 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 161024 | 0x7feaadc2db80 | 0x7feaad225bc0 | 0 | 0 | 0 | 14233456354343 | 14233456322307 | 14233456689188 | 14233456690896 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 344 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 163264 | 0x7feaadc2da00 | 0x7feaad225c00 | 0 | 0 | 0 | 14233456721275 | 14233456689188 | 14233456993669 | 14233456995330 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 347 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 166528 | 0x7feaadc2d880 | 0x7feaad225c40 | 0 | 0 | 0 | 14233457026159 | 14233456993669 | 14233457390311 | 14233457410191 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 350 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 168512 | 0x7feaadc2d700 | 0x7feaad225c80 | 0 | 0 | 0 | 14233457430501 | 14233457390311 | 14233457698152 | 14233457699785 |
| 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 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 171264 | 0x7feab02cc580 | 0x7feaad225cc0 | 0 | 0 | 0 | 14233457729945 | 14233457698152 | 14233458061833 | 14233458063448 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 356 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 173760 | 0x7feab02cc400 | 0x7feaad225d00 | 0 | 0 | 0 | 14233458098077 | 14233458061833 | 14233458435754 | 14233458437450 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 359 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 176256 | 0x7feab02cc280 | 0x7feaad225d40 | 0 | 0 | 0 | 14233458468409 | 14233458435754 | 14233458753355 | 14233458755023 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 362 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 179776 | 0x7feab02cc100 | 0x7feaad225d80 | 0 | 0 | 0 | 14233458786103 | 14233458753355 | 14233459167117 | 14233459213014 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 365 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 182272 | 0x7feaadc2df80 | 0x7feaad225dc0 | 0 | 0 | 0 | 14233459232034 | 14233459167117 | 14233459516238 | 14233459517918 |
| 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 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 185536 | 0x7feaadc2de00 | 0x7feaad225e00 | 0 | 0 | 0 | 14233459548847 | 14233459516238 | 14233459886639 | 14233459908790 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 371 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 188544 | 0x7feaadc2dc80 | 0x7feaad225e40 | 0 | 0 | 0 | 14233459921330 | 14233459886639 | 14233460275761 | 14233460295962 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 374 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 191552 | 0x7feaadc2db00 | 0x7feaad225e80 | 0 | 0 | 0 | 14233460308662 | 14233460275761 | 14233460625522 | 14233460627245 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 377 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 195840 | 0x7feaadc2d980 | 0x7feaad225ec0 | 0 | 0 | 0 | 14233460657304 | 14233460625522 | 14233461094964 | 14233461114115 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 380 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 198592 | 0x7feaadc2d800 | 0x7feaad225f00 | 0 | 0 | 0 | 14233461134755 | 14233461094964 | 14233461431445 | 14233461433119 |
| 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 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 202368 | 0x7feaadc2d680 | 0x7feaad225f40 | 0 | 0 | 0 | 14233461463298 | 14233461431445 | 14233461822006 | 14233461839190 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 386 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 205888 | 0x7feab02cc500 | 0x7feaad225f80 | 0 | 0 | 0 | 14233461855290 | 14233461822006 | 14233462216088 | 14233462233472 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 389 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 209408 | 0x7feab02cc380 | 0x7feaad225fc0 | 0 | 0 | 0 | 14233462249712 | 14233462216088 | 14233462594009 | 14233462595915 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 392 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 214464 | 0x7feab02cc200 | 0x7feaad226000 | 0 | 0 | 0 | 14233462627054 | 14233462594009 | 14233463110491 | 14233463152243 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 395 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 217728 | 0x7feab02cc080 | 0x7feaad226040 | 0 | 0 | 0 | 14233463170953 | 14233463110491 | 14233463491452 | 14233463493146 |
| 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 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 222016 | 0x7feaadc2df00 | 0x7feaad226080 | 0 | 0 | 0 | 14233463524596 | 14233463491452 | 14233463908253 | 14233463926637 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 401 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 226048 | 0x7feaadc2dd80 | 0x7feaad2260c0 | 0 | 0 | 0 | 14233463941087 | 14233463908253 | 14233464331295 | 14233464349839 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 404 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 230080 | 0x7feaadc2dc00 | 0x7feaad226100 | 0 | 0 | 0 | 14233464363598 | 14233464331295 | 14233464739136 | 14233464756360 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 407 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 235904 | 0x7feaadc2da80 | 0x7feaad226140 | 0 | 0 | 0 | 14233464771430 | 14233464739136 | 14233465312578 | 14233465331119 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 410 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 239424 | 0x7feaadc2d900 | 0x7feaad226180 | 0 | 0 | 0 | 14233465353198 | 14233465312578 | 14233465694340 | 14233465696101 |
| 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 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 244224 | 0x7feaadc2d780 | 0x7feaad2261c0 | 0 | 0 | 0 | 14233465726231 | 14233465694340 | 14233466131461 | 14233466177341 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 416 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 248768 | 0x7feaadc2d600 | 0x7feaad226200 | 0 | 0 | 0 | 14233466189441 | 14233466131461 | 14233466599623 | 14233466618062 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 419 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 253312 | 0x7feab02cc480 | 0x7feaad226240 | 0 | 0 | 0 | 14233466632202 | 14233466599623 | 14233467024744 | 14233467042344 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 422 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 8 | 24 | 255552 | 0x7feab02cc300 | 0x7feaad226280 | 0 | 0 | 0 | 14233467057943 | 14233467024744 | 14233467663626 | 14233467682271 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 425 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 259840 | 0x7feab02cc180 | 0x7feaad2262c0 | 0 | 0 | 0 | 14233467704010 | 14233467663626 | 14233468079148 | 14233468096662 |
| 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 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 265664 | 0x7feab02cc000 | 0x7feaad226300 | 0 | 0 | 0 | 14233468111662 | 14233468079148 | 14233468575310 | 14233468593292 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 431 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 271232 | 0x7feaadc2de80 | 0x7feaad226340 | 0 | 0 | 0 | 14233468608182 | 14233468575310 | 14233469069871 | 14233469087242 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 434 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 8 | 24 | 273216 | 0x7feaadc2dd00 | 0x7feaad226380 | 0 | 0 | 0 | 14233469101202 | 14233469069871 | 14233469560753 | 14233469579252 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 437 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 8 | 24 | 275712 | 0x7feaadc2db80 | 0x7feaad2263c0 | 0 | 0 | 0 | 14233469593052 | 14233469560753 | 14233470307796 | 14233470327147 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 440 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 280768 | 0x7feaadc2da00 | 0x7feaad226400 | 0 | 0 | 0 | 14233470347876 | 14233470307796 | 14233470766357 | 14233470808957 |
| 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 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 287616 | 0x7feaadc2d880 | 0x7feaad226440 | 0 | 0 | 0 | 14233470819737 | 14233470766357 | 14233471333399 | 14233471350926 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 446 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 294208 | 0x7feaadc2d700 | 0x7feaad226480 | 0 | 0 | 0 | 14233471365416 | 14233471333399 | 14233471868921 | 14233471887845 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 449 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 8 | 24 | 296960 | 0x7feab02cc580 | 0x7feaad2264c0 | 0 | 0 | 0 | 14233471901225 | 14233471868921 | 14233472404283 | 14233472422084 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 452 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 8 | 24 | 299968 | 0x7feab02cc400 | 0x7feaad226500 | 0 | 0 | 0 | 14233472437394 | 14233472404283 | 14233473249246 | 14233473267807 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 455 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 8 | 24 | 302720 | 0x7feab02cc280 | 0x7feaad226540 | 0 | 0 | 0 | 14233473289196 | 14233473249246 | 14233473883488 | 14233473902464 |
| 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 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 305472 | 0x7feab02cc100 | 0x7feaad226580 | 0 | 0 | 0 | 14233473916863 | 14233473883488 | 14233474534370 | 14233474552820 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 461 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 308224 | 0x7feaadc2df80 | 0x7feaad2265c0 | 0 | 0 | 0 | 14233474567160 | 14233474534370 | 14233475193253 | 14233475211887 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 464 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 8 | 24 | 310976 | 0x7feaadc2de00 | 0x7feaad226600 | 0 | 0 | 0 | 14233475225526 | 14233475193253 | 14233475832295 | 14233475849944 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 467 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 8 | 24 | 313216 | 0x7feaadc2dc80 | 0x7feaad226640 | 0 | 0 | 0 | 14233475865193 | 14233475832295 | 14233476889419 | 14233476907822 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 470 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 8 | 24 | 315968 | 0x7feaadc2db00 | 0x7feaad226680 | 0 | 0 | 0 | 14233476929252 | 14233476889138 | 14233477931541 | 14233477952551 |
| 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 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 318720 | 0x7feaadc2d980 | 0x7feaad2266c0 | 0 | 0 | 0 | 14233477964060 | 14233477931541 | 14233479018904 | 14233479058748 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 476 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 321472 | 0x7feaadc2d800 | 0x7feaad226700 | 0 | 0 | 0 | 14233479070998 | 14233479018904 | 14233480133947 | 14233480153395 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 479 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 8 | 24 | 324224 | 0x7feaadc2d680 | 0x7feaad226740 | 0 | 0 | 0 | 14233480166975 | 14233480133947 | 14233481196030 | 14233481214424 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 482 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 8 | 24 | 326464 | 0x7feab02cc500 | 0x7feaad226780 | 0 | 0 | 0 | 14233481228723 | 14233481196030 | 14233483095556 | 14233483117895 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 485 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 8 | 24 | 329216 | 0x7feab02cc380 | 0x7feaad2267c0 | 0 | 0 | 0 | 14233483137164 | 14233483095556 | 14233484974761 | 14233485044285 |
| 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 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 331968 | 0x7feab02cc200 | 0x7feaad226800 | 0 | 0 | 0 | 14233485055575 | 14233484974761 | 14233486959567 | 14233487032815 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 491 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 334720 | 0x7feab02cc080 | 0x7feaad226840 | 0 | 0 | 0 | 14233487044904 | 14233486959567 | 14233488951733 | 14233488996525 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 494 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 8 | 24 | 337472 | 0x7feaadc2df00 | 0x7feaad226880 | 0 | 0 | 0 | 14233489007984 | 14233488951733 | 14233490857818 | 14233490929365 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 497 | 23312 | 23312 | 4194304 | 256 | 0 | 0 | 8 | 24 | 0 | 0x7feaadc2dd80 | 0x7feaad2268c0 | 0 | 0 | 0 | 14233490941095 | 14233490857818 | 14233494479429 | 14233494551231 |