37 KiB
37 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBufferAligned.kd | 0 | 0 | 0 | 141143 | 141143 | 33554432 | 256 | 0 | 0 | 4 | 32 | 4160 | 0x0 | 0x7f4378404280 | 15948461762825 | 15948461788706 | 15948462027747 | 15948462150707 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 141143 | 141143 | 32768 | 256 | 0 | 0 | 12 | 24 | 13888 | 0x0 | 0x7f4378423f80 | 15948466853362 | 15948466868890 | 15948466882330 | 15948466899001 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 5 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 14336 | 0x7f437b4e8380 | 0x7f4378423fc0 | 15948466903361 | 15948466952090 | 15948467044891 | 15948467046497 |
| 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 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15040 | 0x7f437b4e8200 | 0x7f4378424000 | 15948467068347 | 15948467078491 | 15948467257212 | 15948467258903 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 11 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15488 | 0x7f437b4e8080 | 0x7f4378424040 | 15948467273562 | 15948467282332 | 15948467461533 | 15948467463158 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 14 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 15936 | 0x7f4378e47f00 | 0x7f4378424080 | 15948467477118 | 15948467485693 | 15948467579773 | 15948467581605 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 17 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 16384 | 0x7f4378e47d80 | 0x7f43784240c0 | 15948467596915 | 15948467605534 | 15948467697534 | 15948467699243 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 20 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 17088 | 0x7f4378e47c00 | 0x7f4378424100 | 15948467726332 | 15948467737214 | 15948467829695 | 15948467831270 |
| 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 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 16 | 24 | 17792 | 0x7f4378e47a80 | 0x7f4378424140 | 15948467850689 | 15948467861535 | 15948468041216 | 15948468042745 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 26 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 16 | 24 | 18496 | 0x7f4378e47900 | 0x7f4378424180 | 15948468061855 | 15948468082016 | 15948468261537 | 15948468263170 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 29 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19200 | 0x7f4378e47780 | 0x7f43784241c0 | 15948468277460 | 15948468286497 | 15948468379777 | 15948468381548 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 32 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19904 | 0x7f4378e47600 | 0x7f4378424200 | 15948468400847 | 15948468411778 | 15948468505378 | 15948468506905 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 35 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 20608 | 0x7f437b4e8480 | 0x7f4378424240 | 15948468527294 | 15948468537698 | 15948468630979 | 15948468632452 |
| 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 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 16 | 24 | 21312 | 0x7f437b4e8300 | 0x7f4378424280 | 15948468656251 | 15948468666979 | 15948468845860 | 15948468847407 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 41 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22016 | 0x7f437b4e8180 | 0x7f43784242c0 | 15948468864537 | 15948468878180 | 15948469057541 | 15948469059182 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 44 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22720 | 0x7f437b4e8000 | 0x7f4378424300 | 15948469077102 | 15948469086181 | 15948469180421 | 15948469182100 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 47 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 23424 | 0x7f4378e47e80 | 0x7f4378424340 | 15948469196909 | 15948469207142 | 15948469300102 | 15948469301647 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 50 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 24128 | 0x7f4378e47d00 | 0x7f4378424380 | 15948469322617 | 15948469333382 | 15948469426503 | 15948469428134 |
| 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 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 16 | 24 | 24832 | 0x7f4378e47b80 | 0x7f43784243c0 | 15948469450064 | 15948469459943 | 15948469640104 | 15948469641839 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 56 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 16 | 24 | 25536 | 0x7f4378e47a00 | 0x7f4378424400 | 15948469656569 | 15948469666344 | 15948469847625 | 15948469849085 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 59 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26240 | 0x7f4378e47880 | 0x7f4378424440 | 15948469865504 | 15948469874505 | 15948469967785 | 15948469969432 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 62 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26944 | 0x7f4378e47700 | 0x7f4378424480 | 15948469991472 | 15948470001545 | 15948470094826 | 15948470096529 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 65 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 27648 | 0x7f437b4e8580 | 0x7f43784244c0 | 15948470119469 | 15948470130026 | 15948470222667 | 15948470224196 |
| 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 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 16 | 24 | 28608 | 0x7f437b4e8400 | 0x7f4378424500 | 15948470244186 | 15948470254507 | 15948470432908 | 15948470434622 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 71 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 16 | 24 | 29312 | 0x7f437b4e8280 | 0x7f4378424540 | 15948470448611 | 15948470466668 | 15948470646349 | 15948470648087 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 74 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 30016 | 0x7f437b4e8100 | 0x7f4378424580 | 15948470666537 | 15948470675309 | 15948470767949 | 15948470769394 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 77 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 8 | 24 | 30976 | 0x7f4378e47f80 | 0x7f43784245c0 | 15948470783364 | 15948470792429 | 15948470884270 | 15948470885842 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 80 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 31680 | 0x7f4378e47e00 | 0x7f4378424600 | 15948470906271 | 15948470917230 | 15948471010510 | 15948471011949 |
| 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 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 16 | 24 | 32640 | 0x7f4378e47c80 | 0x7f4378424640 | 15948471029159 | 15948471038191 | 15948471219472 | 15948471220924 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 86 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 33600 | 0x7f4378e47b00 | 0x7f4378424680 | 15948471238164 | 15948471251312 | 15948471431473 | 15948471433270 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 89 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 34560 | 0x7f4378e47980 | 0x7f43784246c0 | 15948471449259 | 15948471458673 | 15948471552113 | 15948471553647 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 92 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 8 | 24 | 35520 | 0x7f4378e47800 | 0x7f4378424700 | 15948471572517 | 15948471584433 | 15948471678194 | 15948471679974 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 95 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 36224 | 0x7f4378e47680 | 0x7f4378424740 | 15948471702004 | 15948471711474 | 15948471805074 | 15948471806711 |
| 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 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 37184 | 0x7f437b4e8500 | 0x7f4378424780 | 15948471829781 | 15948471840595 | 15948472021236 | 15948472022887 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 101 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 38144 | 0x7f437b4e8380 | 0x7f43784247c0 | 15948472046416 | 15948472057236 | 15948472238517 | 15948472240162 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 104 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 39104 | 0x7f437b4e8200 | 0x7f4378424800 | 15948472253791 | 15948472263157 | 15948472356597 | 15948472358099 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 107 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 8 | 24 | 40320 | 0x7f437b4e8080 | 0x7f4378424840 | 15948472377599 | 15948472388917 | 15948472483638 | 15948472485136 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 110 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 41280 | 0x7f4378e47f00 | 0x7f4378424880 | 15948472506426 | 15948472517878 | 15948472611318 | 15948472612893 |
| 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 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 42240 | 0x7f4378e47d80 | 0x7f43784248c0 | 15948472636663 | 15948472647159 | 15948472826520 | 15948472828099 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 116 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 43200 | 0x7f4378e47c00 | 0x7f4378424900 | 15948472847918 | 15948472858360 | 15948473036441 | 15948473037964 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 119 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 8 | 24 | 44160 | 0x7f4378e47a80 | 0x7f4378424940 | 15948473059014 | 15948473068921 | 15948473162521 | 15948473164041 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 122 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 45376 | 0x7f4378e47900 | 0x7f4378424980 | 15948473186261 | 15948473197081 | 15948473292442 | 15948473293868 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 125 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 46336 | 0x7f4378e47780 | 0x7f43784249c0 | 15948473315748 | 15948473326522 | 15948473420122 | 15948473421626 |
| 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 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 47552 | 0x7f4378e47600 | 0x7f4378424a00 | 15948473447435 | 15948473458203 | 15948473637084 | 15948473638541 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 131 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 48512 | 0x7f437b4e8480 | 0x7f4378424a40 | 15948473655200 | 15948473683484 | 15948473862845 | 15948473864326 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 134 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 8 | 24 | 49472 | 0x7f437b4e8300 | 0x7f4378424a80 | 15948473882475 | 15948473891805 | 15948473984605 | 15948473986193 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 137 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 50688 | 0x7f437b4e8180 | 0x7f4378424ac0 | 15948473998983 | 15948474023805 | 15948474117406 | 15948474118450 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 140 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 51648 | 0x7f437b4e8000 | 0x7f4378424b00 | 15948474140990 | 15948474152286 | 15948474244127 | 15948474245137 |
| 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 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 52864 | 0x7f4378e47e80 | 0x7f4378424b40 | 15948474260397 | 15948474268607 | 15948474448448 | 15948474449453 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 146 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 54080 | 0x7f4378e47d00 | 0x7f4378424b80 | 15948474464192 | 15948474472448 | 15948474652769 | 15948474653698 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 149 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 8 | 24 | 55296 | 0x7f4378e47b80 | 0x7f4378424bc0 | 15948474670648 | 15948474678689 | 15948474773089 | 15948474774115 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 152 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 56768 | 0x7f4378e47a00 | 0x7f4378424c00 | 15948474789745 | 15948474798209 | 15948474893410 | 15948474894763 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 155 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 57728 | 0x7f4378e47880 | 0x7f4378424c40 | 15948474919172 | 15948474930210 | 15948475024930 | 15948475025950 |
| 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 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 58944 | 0x7f4378e47700 | 0x7f4378424c80 | 15948475042459 | 15948475050851 | 15948475230691 | 15948475231675 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 161 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 60160 | 0x7f437b4e8580 | 0x7f4378424cc0 | 15948475246615 | 15948475255172 | 15948475435972 | 15948475436911 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 164 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 8 | 24 | 61376 | 0x7f437b4e8400 | 0x7f4378424d00 | 15948475450970 | 15948475459013 | 15948475554053 | 15948475555088 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 167 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 62848 | 0x7f437b4e8280 | 0x7f4378424d40 | 15948475570188 | 15948475579173 | 15948475678854 | 15948475679955 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 170 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 63808 | 0x7f437b4e8100 | 0x7f4378424d80 | 15948475700985 | 15948475712134 | 15948475806054 | 15948475807082 |
| 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 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 65024 | 0x7f4378e47f80 | 0x7f4378424dc0 | 15948475823562 | 15948475832614 | 15948476012615 | 15948476013628 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 176 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 66240 | 0x7f4378e47e00 | 0x7f4378424e00 | 15948476028887 | 15948476038055 | 15948476218376 | 15948476219423 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 179 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 8 | 24 | 67456 | 0x7f4378e47c80 | 0x7f4378424e40 | 15948476234073 | 15948476242696 | 15948476337097 | 15948476338080 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 182 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 68928 | 0x7f4378e47b00 | 0x7f4378424e80 | 15948476354590 | 15948476362857 | 15948476467178 | 15948476468328 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 185 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 70144 | 0x7f4378e47980 | 0x7f4378424ec0 | 15948476490187 | 15948476501578 | 15948476594538 | 15948476595555 |
| 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 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 71616 | 0x7f4378e47800 | 0x7f4378424f00 | 15948476611444 | 15948476620298 | 15948476800299 | 15948476801370 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 191 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 72832 | 0x7f4378e47680 | 0x7f4378424f40 | 15948476817080 | 15948476825579 | 15948477006220 | 15948477007336 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 194 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 8 | 24 | 74048 | 0x7f437b4e8500 | 0x7f4378424f80 | 15948477022175 | 15948477030540 | 15948477124461 | 15948477125413 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 197 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 75776 | 0x7f437b4e8380 | 0x7f4378424fc0 | 15948477140113 | 15948477148621 | 15948477255181 | 15948477256300 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 200 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 76992 | 0x7f437b4e8200 | 0x7f4378425000 | 15948477278319 | 15948477289902 | 15948477384622 | 15948477385567 |
| 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 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 78464 | 0x7f437b4e8080 | 0x7f4378425040 | 15948477402067 | 15948477410382 | 15948477589263 | 15948477590273 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 206 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 79936 | 0x7f4378e47f00 | 0x7f4378425080 | 15948477605732 | 15948477614063 | 15948477793104 | 15948477794238 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 209 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 8 | 24 | 81408 | 0x7f4378e47d80 | 0x7f43784250c0 | 15948477810298 | 15948477818864 | 15948477913425 | 15948477914465 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 212 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 83136 | 0x7f4378e47c00 | 0x7f4378425100 | 15948477930325 | 15948477938705 | 15948478052945 | 15948478054012 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 215 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 84352 | 0x7f4378e47a80 | 0x7f4378425140 | 15948478099841 | 15948478109906 | 15948478203666 | 15948478205069 |
| 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 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 85824 | 0x7f4378e47900 | 0x7f4378425180 | 15948478222588 | 15948478231186 | 15948478411027 | 15948478412174 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 221 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 87296 | 0x7f4378e47780 | 0x7f43784251c0 | 15948478426414 | 15948478434547 | 15948478613428 | 15948478614540 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 224 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 88768 | 0x7f4378e47600 | 0x7f4378425200 | 15948478632109 | 15948478640468 | 15948478735669 | 15948478736677 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 227 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 90752 | 0x7f437b4e8480 | 0x7f4378425240 | 15948478752507 | 15948478761589 | 15948478882070 | 15948478883044 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 230 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 91968 | 0x7f437b4e8300 | 0x7f4378425280 | 15948478902593 | 15948478914550 | 15948479008310 | 15948479009411 |
| 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 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 93440 | 0x7f437b4e8180 | 0x7f43784252c0 | 15948479024361 | 15948479032470 | 15948479212151 | 15948479213286 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 236 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 94912 | 0x7f437b4e8000 | 0x7f4378425300 | 15948479228486 | 15948479236631 | 15948479417112 | 15948479418252 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 239 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 96384 | 0x7f4378e47e80 | 0x7f4378425340 | 15948479433572 | 15948479442392 | 15948479538393 | 15948479539489 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 242 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 98368 | 0x7f4378e47d00 | 0x7f4378425380 | 15948479556029 | 15948479563833 | 15948479689914 | 15948479690866 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 245 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 99584 | 0x7f4378e47b80 | 0x7f43784253c0 | 15948479712045 | 15948479723354 | 15948479818554 | 15948479819643 |
| 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 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 101312 | 0x7f4378e47a00 | 0x7f4378425400 | 15948479835093 | 15948479843514 | 15948480023835 | 15948480024818 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 251 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 102784 | 0x7f4378e47880 | 0x7f4378425440 | 15948480039808 | 15948480048475 | 15948480230076 | 15948480231114 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 254 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 104256 | 0x7f4378e47700 | 0x7f4378425480 | 15948480247174 | 15948480255516 | 15948480349757 | 15948480350841 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 257 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 106240 | 0x7f437b4e8580 | 0x7f43784254c0 | 15948480366901 | 15948480375357 | 15948480505598 | 15948480506638 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 260 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 107712 | 0x7f437b4e8400 | 0x7f4378425500 | 15948480528447 | 15948480539358 | 15948480632318 | 15948480633425 |
| 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 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 16 | 24 | 109440 | 0x7f437b4e8280 | 0x7f4378425540 | 15948480650475 | 15948480658878 | 15948480838079 | 15948480839170 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 266 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 16 | 24 | 111168 | 0x7f437b4e8100 | 0x7f4378425580 | 15948480854800 | 15948480863999 | 15948481045120 | 15948481046156 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 269 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 8 | 24 | 112896 | 0x7f4378e47f80 | 0x7f43784255c0 | 15948481060655 | 15948481069440 | 15948481165601 | 15948481166683 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 272 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 115136 | 0x7f4378e47e00 | 0x7f4378425600 | 15948481182633 | 15948481191041 | 15948481330402 | 15948481331399 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 275 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 116608 | 0x7f4378e47c80 | 0x7f4378425640 | 15948481352809 | 15948481363842 | 15948481458242 | 15948481459287 |
| 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 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 16 | 24 | 118336 | 0x7f4378e47b00 | 0x7f4378425680 | 15948481475826 | 15948481484162 | 15948481663363 | 15948481664482 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 281 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 16 | 24 | 120064 | 0x7f4378e47980 | 0x7f43784256c0 | 15948481680532 | 15948481689444 | 15948481868644 | 15948481869638 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 284 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 121792 | 0x7f4378e47800 | 0x7f4378425700 | 15948481884877 | 15948481893765 | 15948481990405 | 15948481991545 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 287 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 124032 | 0x7f4378e47680 | 0x7f4378425740 | 15948482006365 | 15948482015365 | 15948482161446 | 15948482162621 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 290 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 125504 | 0x7f437b4e8500 | 0x7f4378425780 | 15948482183311 | 15948482194086 | 15948482289606 | 15948482290738 |
| 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 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 127488 | 0x7f437b4e8380 | 0x7f43784257c0 | 15948482306128 | 15948482314247 | 15948482493928 | 15948482495324 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 296 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 129216 | 0x7f437b4e8200 | 0x7f4378425800 | 15948482510143 | 15948482518248 | 15948482698249 | 15948482699429 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 299 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 130944 | 0x7f437b4e8080 | 0x7f4378425840 | 15948482714309 | 15948482723049 | 15948482824009 | 15948482825386 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 302 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 133440 | 0x7f4378e47f00 | 0x7f4378425880 | 15948482840116 | 15948482848329 | 15948483003690 | 15948483005052 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 305 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 134912 | 0x7f4378e47d80 | 0x7f43784258c0 | 15948483026272 | 15948483037450 | 15948483132491 | 15948483133739 |
| 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 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 136896 | 0x7f4378e47c00 | 0x7f4378425900 | 15948483149319 | 15948483157611 | 15948483336332 | 15948483337755 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 311 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 138880 | 0x7f4378e47a80 | 0x7f4378425940 | 15948483353214 | 15948483361932 | 15948483541453 | 15948483542540 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 314 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 140864 | 0x7f4378e47900 | 0x7f4378425980 | 15948483557280 | 15948483565293 | 15948483672333 | 15948483673487 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 317 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 143616 | 0x7f4378e47780 | 0x7f43784259c0 | 15948483687367 | 15948483695693 | 15948483866094 | 15948483867303 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 320 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 145344 | 0x7f4378e47600 | 0x7f4378425a00 | 15948483886543 | 15948483898094 | 15948483994095 | 15948483995250 |
| 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 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 147584 | 0x7f437b4e8480 | 0x7f4378425a40 | 15948484010450 | 15948484018575 | 15948484200496 | 15948484201685 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 326 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 149568 | 0x7f437b4e8300 | 0x7f4378425a80 | 15948484215665 | 15948484223696 | 15948484406897 | 15948484408021 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 329 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 151552 | 0x7f437b4e8180 | 0x7f4378425ac0 | 15948484422991 | 15948484431377 | 15948484543058 | 15948484543978 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 332 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 154304 | 0x7f437b4e8000 | 0x7f4378425b00 | 15948484558678 | 15948484567378 | 15948484748499 | 15948484749633 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 335 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 156288 | 0x7f4378e47e80 | 0x7f4378425b40 | 15948484772023 | 15948484782099 | 15948484884019 | 15948484885100 |
| 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 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 158784 | 0x7f4378e47d00 | 0x7f4378425b80 | 15948484899970 | 15948484908659 | 15948485094900 | 15948485095836 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 341 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 161024 | 0x7f4378e47b80 | 0x7f4378425bc0 | 15948485110275 | 15948485118581 | 15948485302261 | 15948485303371 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 344 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 163264 | 0x7f4378e47a00 | 0x7f4378425c00 | 15948485319091 | 15948485327702 | 15948485449622 | 15948485450718 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 347 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 166528 | 0x7f4378e47880 | 0x7f4378425c40 | 15948485466147 | 15948485475222 | 15948485681623 | 15948485703112 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 350 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 168512 | 0x7f4378e47700 | 0x7f4378425c80 | 15948485718972 | 15948485729624 | 15948485840344 | 15948485841469 |
| 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 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 171264 | 0x7f437b4e8580 | 0x7f4378425cc0 | 15948485857518 | 15948485866264 | 15948486050425 | 15948486051374 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 356 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 173760 | 0x7f437b4e8400 | 0x7f4378425d00 | 15948486066104 | 15948486074905 | 15948486262106 | 15948486263299 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 359 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 176256 | 0x7f437b4e8280 | 0x7f4378425d40 | 15948486277939 | 15948486286106 | 15948486420987 | 15948486422116 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 362 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 179776 | 0x7f437b4e8100 | 0x7f4378425d80 | 15948486436146 | 15948486444507 | 15948486676508 | 15948486721779 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 365 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 182272 | 0x7f4378e47f80 | 0x7f4378425dc0 | 15948486737609 | 15948486749949 | 15948486876989 | 15948486878026 |
| 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 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 185536 | 0x7f4378e47e00 | 0x7f4378425e00 | 15948486892886 | 15948486901149 | 15948487091070 | 15948487092191 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 371 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 188544 | 0x7f4378e47c80 | 0x7f4378425e40 | 15948487107041 | 15948487115390 | 15948487310911 | 15948487312126 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 374 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 191552 | 0x7f4378e47b00 | 0x7f4378425e80 | 15948487327826 | 15948487336672 | 15948487497152 | 15948487498182 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 377 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 195840 | 0x7f4378e47980 | 0x7f4378425ec0 | 15948487513392 | 15948487521632 | 15948487805474 | 15948487829925 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 380 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 198592 | 0x7f4378e47800 | 0x7f4378425f00 | 15948487845074 | 15948487856034 | 15948488005155 | 15948488006231 |
| 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 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 202368 | 0x7f4378e47680 | 0x7f4378425f40 | 15948488021400 | 15948488028995 | 15948488236516 | 15948488258435 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 386 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 205888 | 0x7f437b4e8500 | 0x7f4378425f80 | 15948488267215 | 15948488277796 | 15948488486277 | 15948488505090 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 389 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 209408 | 0x7f437b4e8380 | 0x7f4378425fc0 | 15948488512920 | 15948488523557 | 15948488709638 | 15948488710655 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 392 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 214464 | 0x7f437b4e8200 | 0x7f4378426000 | 15948488725005 | 15948488733798 | 15948489068200 | 15948489083667 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 395 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 217728 | 0x7f437b4e8080 | 0x7f4378426040 | 15948489099227 | 15948489110440 | 15948489278121 | 15948489279183 |
| 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 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 222016 | 0x7f4378e47f00 | 0x7f4378426080 | 15948489294022 | 15948489302441 | 15948489529482 | 15948489545037 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 401 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 226048 | 0x7f4378e47d80 | 0x7f43784260c0 | 15948489552757 | 15948489563243 | 15948489793164 | 15948489808591 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 404 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 230080 | 0x7f4378e47c00 | 0x7f4378426100 | 15948489817941 | 15948489828364 | 15948490039565 | 15948490055285 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 407 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 235904 | 0x7f4378e47a80 | 0x7f4378426140 | 15948490065625 | 15948490075245 | 15948490461487 | 15948490502775 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 410 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 239424 | 0x7f4378e47900 | 0x7f4378426180 | 15948490520425 | 15948490531247 | 15948490718128 | 15948490719091 |
| 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 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 244224 | 0x7f4378e47780 | 0x7f43784261c0 | 15948490735820 | 15948490743888 | 15948490993810 | 15948491012464 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 416 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 248768 | 0x7f4378e47600 | 0x7f4378426200 | 15948491021714 | 15948491032210 | 15948491279411 | 15948491298378 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 419 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 253312 | 0x7f437b4e8480 | 0x7f4378426240 | 15948491306397 | 15948491317011 | 15948491553812 | 15948491572401 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 422 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 8 | 24 | 255552 | 0x7f437b4e8300 | 0x7f4378426280 | 15948491581821 | 15948491592693 | 15948492045655 | 15948492064341 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 425 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 259840 | 0x7f437b4e8180 | 0x7f43784262c0 | 15948492080380 | 15948492091255 | 15948492317816 | 15948492336264 |
| 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 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 265664 | 0x7f437b4e8000 | 0x7f4378426300 | 15948492345504 | 15948492356376 | 15948492654778 | 15948492673297 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 431 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 271232 | 0x7f4378e47e80 | 0x7f4378426340 | 15948492682447 | 15948492692378 | 15948492990620 | 15948493009299 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 434 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 8 | 24 | 273216 | 0x7f4378e47d00 | 0x7f4378426380 | 15948493019279 | 15948493029660 | 15948493326621 | 15948493344212 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 437 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 8 | 24 | 275712 | 0x7f4378e47b80 | 0x7f43784263c0 | 15948493352642 | 15948493363101 | 15948493919904 | 15948493936079 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 440 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 280768 | 0x7f4378e47a00 | 0x7f4378426400 | 15948493951838 | 15948493962944 | 15948494226146 | 15948494249812 |
| 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 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 287616 | 0x7f4378e47880 | 0x7f4378426440 | 15948494258162 | 15948494268706 | 15948494619748 | 15948494641813 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 446 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 294208 | 0x7f4378e47700 | 0x7f4378426480 | 15948494650243 | 15948494661028 | 15948495010950 | 15948495033254 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 449 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 8 | 24 | 296960 | 0x7f437b4e8580 | 0x7f43784264c0 | 15948495043184 | 15948495053990 | 15948495401192 | 15948495419866 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 452 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 8 | 24 | 299968 | 0x7f437b4e8400 | 0x7f4378426500 | 15948495429636 | 15948495440232 | 15948496101035 | 15948496122530 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 455 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 8 | 24 | 302720 | 0x7f437b4e8280 | 0x7f4378426540 | 15948496138410 | 15948496148555 | 15948496595598 | 15948496617049 |
| 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 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 305472 | 0x7f437b4e8100 | 0x7f4378426580 | 15948496625539 | 15948496636078 | 15948497101680 | 15948497123348 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 461 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 308224 | 0x7f4378e47f80 | 0x7f43784265c0 | 15948497131438 | 15948497142320 | 15948497604403 | 15948497622887 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 464 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 8 | 24 | 310976 | 0x7f4378e47e00 | 0x7f4378426600 | 15948497631437 | 15948497642483 | 15948498094165 | 15948498118296 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 467 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 8 | 24 | 313216 | 0x7f4378e47c80 | 0x7f4378426640 | 15948498127196 | 15948498137365 | 15948499006969 | 15948499031166 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 470 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 8 | 24 | 315968 | 0x7f4378e47b00 | 0x7f4378426680 | 15948499049105 | 15948499059930 | 15948499913374 | 15948499934505 |
| 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 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 318720 | 0x7f4378e47980 | 0x7f43784266c0 | 15948499945925 | 15948499962494 | 15948500847779 | 15948500891584 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 476 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 321472 | 0x7f4378e47800 | 0x7f4378426700 | 15948500903304 | 15948500918979 | 15948501799303 | 15948501842973 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 479 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 8 | 24 | 324224 | 0x7f4378e47680 | 0x7f4378426740 | 15948501852782 | 15948501868744 | 15948502728588 | 15948502776332 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 482 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 8 | 24 | 326464 | 0x7f437b4e8500 | 0x7f4378426780 | 15948502785712 | 15948502796908 | 15948504496117 | 15948504542603 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 485 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 8 | 24 | 329216 | 0x7f437b4e8380 | 0x7f43784267c0 | 15948504559042 | 15948504570517 | 15948506234845 | 15948506310134 |
| 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 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 331968 | 0x7f437b4e8200 | 0x7f4378426800 | 15948506319173 | 15948506329726 | 15948508055334 | 15948508123683 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 491 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 12 | 24 | 334720 | 0x7f437b4e8080 | 0x7f4378426840 | 15948508132993 | 15948508152775 | 15948509868943 | 15948509937453 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 494 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 8 | 24 | 337472 | 0x7f4378e47f00 | 0x7f4378426880 | 15948509947532 | 15948509958064 | 15948511632632 | 15948511703793 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 497 | 141143 | 141143 | 4194304 | 256 | 0 | 0 | 8 | 24 | 0 | 0x7f4378e47d80 | 0x7f43784268c0 | 15948511713383 | 15948511736633 | 15948515092969 | 15948515169366 |