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 | 186167 | 186167 | 33554432 | 256 | 0 | 0 | 4 | 32 | 4160 | 0x0 | 0x7f4df6404280 | 16974017017829 | 16974017042861 | 16974017282380 | 16974017371119 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 186167 | 186167 | 32768 | 256 | 0 | 0 | 12 | 24 | 13888 | 0x0 | 0x7f4df6423f80 | 16974022044663 | 16974022060764 | 16974022074684 | 16974022101802 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 5 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 14336 | 0x7f4df94f8380 | 0x7f4df6423fc0 | 16974022218628 | 16974022228923 | 16974022321243 | 16974022323445 |
| 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 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15040 | 0x7f4df94f8200 | 0x7f4df6424000 | 16974022343794 | 16974022353883 | 16974022532442 | 16974022534659 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 11 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15488 | 0x7f4df94f8080 | 0x7f4df6424040 | 16974022549638 | 16974022558362 | 16974022736762 | 16974022738803 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 14 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 15936 | 0x7f4df6ec9f00 | 0x7f4df6424080 | 16974022754482 | 16974022763322 | 16974022857081 | 16974022859169 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 17 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 16384 | 0x7f4df6ec9d80 | 0x7f4df64240c0 | 16974022874149 | 16974022882041 | 16974022974041 | 16974022976086 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 20 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 17088 | 0x7f4df6ec9c00 | 0x7f4df6424100 | 16974023005005 | 16974023015321 | 16974023107480 | 16974023109462 |
| 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 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 16 | 24 | 17792 | 0x7f4df6ec9a80 | 0x7f4df6424140 | 16974023129432 | 16974023139640 | 16974023319160 | 16974023321136 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 26 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 16 | 24 | 18496 | 0x7f4df6ec9900 | 0x7f4df6424180 | 16974023341245 | 16974023362200 | 16974023541559 | 16974023543889 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 29 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19200 | 0x7f4df6ec9780 | 0x7f4df64241c0 | 16974023563109 | 16974023573559 | 16974023666999 | 16974023668916 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 32 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19904 | 0x7f4df6ec9600 | 0x7f4df6424200 | 16974023688965 | 16974023699479 | 16974023793078 | 16974023795112 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 35 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 20608 | 0x7f4df94f8480 | 0x7f4df6424240 | 16974023819101 | 16974023838518 | 16974023931958 | 16974023934068 |
| 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 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 16 | 24 | 21312 | 0x7f4df94f8300 | 0x7f4df6424280 | 16974023954257 | 16974023964438 | 16974024143797 | 16974024145792 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 41 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22016 | 0x7f4df94f8180 | 0x7f4df64242c0 | 16974024160721 | 16974024170997 | 16974024351797 | 16974024353956 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 44 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22720 | 0x7f4df94f8000 | 0x7f4df6424300 | 16974024367285 | 16974024376597 | 16974024470356 | 16974024472392 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 47 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 23424 | 0x7f4df6ec9e80 | 0x7f4df6424340 | 16974024491172 | 16974024502196 | 16974024595156 | 16974024597249 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 50 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 24128 | 0x7f4df6ec9d00 | 0x7f4df6424380 | 16974024620918 | 16974024631156 | 16974024724115 | 16974024726115 |
| 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 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 16 | 24 | 24832 | 0x7f4df6ec9b80 | 0x7f4df64243c0 | 16974024744824 | 16974024753875 | 16974024933075 | 16974024935279 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 56 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 16 | 24 | 25536 | 0x7f4df6ec9a00 | 0x7f4df6424400 | 16974024954058 | 16974024964595 | 16974025144594 | 16974025146733 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 59 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26240 | 0x7f4df6ec9880 | 0x7f4df6424440 | 16974025165582 | 16974025176594 | 16974025270994 | 16974025273169 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 62 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26944 | 0x7f4df6ec9700 | 0x7f4df6424480 | 16974025292788 | 16974025323634 | 16974025416913 | 16974025419205 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 65 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 27648 | 0x7f4df94f8580 | 0x7f4df64244c0 | 16974025442014 | 16974025452433 | 16974025544593 | 16974025546611 |
| 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 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 16 | 24 | 28608 | 0x7f4df94f8400 | 0x7f4df6424500 | 16974025564800 | 16974025574033 | 16974025754512 | 16974025756645 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 71 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 16 | 24 | 29312 | 0x7f4df94f8280 | 0x7f4df6424540 | 16974025771254 | 16974025779952 | 16974025962672 | 16974025964729 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 74 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 30016 | 0x7f4df94f8100 | 0x7f4df6424580 | 16974025983588 | 16974025994511 | 16974026086991 | 16974026089335 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 77 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 8 | 24 | 30976 | 0x7f4df6ec9f80 | 0x7f4df64245c0 | 16974026104355 | 16974026113871 | 16974026206351 | 16974026208412 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 80 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 31680 | 0x7f4df6ec9e00 | 0x7f4df6424600 | 16974026229931 | 16974026240591 | 16974026333390 | 16974026335468 |
| 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 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 16 | 24 | 32640 | 0x7f4df6ec9c80 | 0x7f4df6424640 | 16974026352637 | 16974026361550 | 16974026540910 | 16974026542472 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 86 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 33600 | 0x7f4df6ec9b00 | 0x7f4df6424680 | 16974026556682 | 16974026565070 | 16974026745709 | 16974026747266 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 89 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 34560 | 0x7f4df6ec9980 | 0x7f4df64246c0 | 16974026762126 | 16974026770189 | 16974026863469 | 16974026865113 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 92 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 8 | 24 | 35520 | 0x7f4df6ec9800 | 0x7f4df6424700 | 16974026879342 | 16974026887469 | 16974026981228 | 16974026982869 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 95 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 36224 | 0x7f4df6ec9680 | 0x7f4df6424740 | 16974027003928 | 16974027013388 | 16974027107308 | 16974027108915 |
| 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 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 37184 | 0x7f4df94f8500 | 0x7f4df6424780 | 16974027122775 | 16974027130828 | 16974027310027 | 16974027311800 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 101 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 38144 | 0x7f4df94f8380 | 0x7f4df64247c0 | 16974027326369 | 16974027335307 | 16974027517547 | 16974027519253 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 104 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 39104 | 0x7f4df94f8200 | 0x7f4df6424800 | 16974027533623 | 16974027541547 | 16974027635146 | 16974027636890 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 107 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 8 | 24 | 40320 | 0x7f4df94f8080 | 0x7f4df6424840 | 16974027651020 | 16974027659626 | 16974027753866 | 16974027755527 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 110 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 41280 | 0x7f4df6ec9f00 | 0x7f4df6424880 | 16974027780356 | 16974027791626 | 16974027884425 | 16974027886063 |
| 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 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 42240 | 0x7f4df6ec9d80 | 0x7f4df64248c0 | 16974027900512 | 16974027908745 | 16974028086825 | 16974028088357 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 116 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 43200 | 0x7f4df6ec9c00 | 0x7f4df6424900 | 16974028106466 | 16974028114505 | 16974028294504 | 16974028296251 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 119 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 8 | 24 | 44160 | 0x7f4df6ec9a80 | 0x7f4df6424940 | 16974028313680 | 16974028322344 | 16974028415944 | 16974028417507 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 122 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 45376 | 0x7f4df6ec9900 | 0x7f4df6424980 | 16974028431007 | 16974028438984 | 16974028533703 | 16974028535284 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 125 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 46336 | 0x7f4df6ec9780 | 0x7f4df64249c0 | 16974028557943 | 16974028568423 | 16974028662343 | 16974028663840 |
| 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 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 47552 | 0x7f4df6ec9600 | 0x7f4df6424a00 | 16974028680150 | 16974028688263 | 16974028867302 | 16974028868804 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 131 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 48512 | 0x7f4df94f8480 | 0x7f4df6424a40 | 16974028883654 | 16974028892262 | 16974029071622 | 16974029073258 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 134 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 8 | 24 | 49472 | 0x7f4df94f8300 | 0x7f4df6424a80 | 16974029087598 | 16974029095782 | 16974029188421 | 16974029190035 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 137 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 50688 | 0x7f4df94f8180 | 0x7f4df6424ac0 | 16974029203984 | 16974029212901 | 16974029306341 | 16974029307871 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 140 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 51648 | 0x7f4df94f8000 | 0x7f4df6424b00 | 16974029329241 | 16974029339781 | 16974029431621 | 16974029433218 |
| 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 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 52864 | 0x7f4df6ec9e80 | 0x7f4df6424b40 | 16974029450627 | 16974029458661 | 16974029638020 | 16974029639542 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 146 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 54080 | 0x7f4df6ec9d00 | 0x7f4df6424b80 | 16974029655941 | 16974029663620 | 16974029845059 | 16974029846536 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 149 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 8 | 24 | 55296 | 0x7f4df6ec9b80 | 0x7f4df6424bc0 | 16974029862905 | 16974029871139 | 16974029965859 | 16974029967482 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 152 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 56768 | 0x7f4df6ec9a00 | 0x7f4df6424c00 | 16974029983132 | 16974029991139 | 16974030087299 | 16974030088908 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 155 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 57728 | 0x7f4df6ec9880 | 0x7f4df6424c40 | 16974030110108 | 16974030120098 | 16974030213698 | 16974030215335 |
| 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 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 58944 | 0x7f4df6ec9700 | 0x7f4df6424c80 | 16974030231314 | 16974030239618 | 16974030418498 | 16974030420039 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 161 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 60160 | 0x7f4df94f8580 | 0x7f4df6424cc0 | 16974030435328 | 16974030443617 | 16974030623137 | 16974030624813 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 164 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 8 | 24 | 61376 | 0x7f4df94f8400 | 0x7f4df6424d00 | 16974030640312 | 16974030648097 | 16974030743457 | 16974030744959 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 167 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 62848 | 0x7f4df94f8280 | 0x7f4df6424d40 | 16974030760299 | 16974030768096 | 16974030867936 | 16974030869486 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 170 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 63808 | 0x7f4df94f8100 | 0x7f4df6424d80 | 16974030889355 | 16974030899776 | 16974030993536 | 16974030995282 |
| 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 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 65024 | 0x7f4df6ec9f80 | 0x7f4df6424dc0 | 16974031012941 | 16974031022656 | 16974031201055 | 16974031202656 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 176 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 66240 | 0x7f4df6ec9e00 | 0x7f4df6424e00 | 16974031219145 | 16974031227295 | 16974031406654 | 16974031408300 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 179 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 8 | 24 | 67456 | 0x7f4df6ec9c80 | 0x7f4df6424e40 | 16974031424139 | 16974031432894 | 16974031527454 | 16974031529096 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 182 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 68928 | 0x7f4df6ec9b00 | 0x7f4df6424e80 | 16974031543996 | 16974031552574 | 16974031656094 | 16974031657603 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 185 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 70144 | 0x7f4df6ec9980 | 0x7f4df6424ec0 | 16974031678362 | 16974031688254 | 16974031781213 | 16974031782749 |
| 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 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 71616 | 0x7f4df6ec9800 | 0x7f4df6424f00 | 16974031798939 | 16974031807293 | 16974031986973 | 16974031988613 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 191 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 72832 | 0x7f4df6ec9680 | 0x7f4df6424f40 | 16974032005433 | 16974032014173 | 16974032196092 | 16974032197737 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 194 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 8 | 24 | 74048 | 0x7f4df94f8500 | 0x7f4df6424f80 | 16974032213116 | 16974032221692 | 16974032315772 | 16974032317383 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 197 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 75776 | 0x7f4df94f8380 | 0x7f4df6424fc0 | 16974032332973 | 16974032341372 | 16974032447611 | 16974032449200 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 200 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 76992 | 0x7f4df94f8200 | 0x7f4df6425000 | 16974032470889 | 16974032481531 | 16974032575931 | 16974032577546 |
| 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 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 78464 | 0x7f4df94f8080 | 0x7f4df6425040 | 16974032593525 | 16974032601691 | 16974032780410 | 16974032781930 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 206 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 79936 | 0x7f4df6ec9f00 | 0x7f4df6425080 | 16974032796419 | 16974032805210 | 16974032983609 | 16974032985254 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 209 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 8 | 24 | 81408 | 0x7f4df6ec9d80 | 0x7f4df64250c0 | 16974032999674 | 16974033008729 | 16974033103449 | 16974033105100 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 212 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 83136 | 0x7f4df6ec9c00 | 0x7f4df6425100 | 16974033119430 | 16974033127609 | 16974033243129 | 16974033244616 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 215 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 84352 | 0x7f4df6ec9a80 | 0x7f4df6425140 | 16974033279835 | 16974033289369 | 16974033384088 | 16974033385582 |
| 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 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 85824 | 0x7f4df6ec9900 | 0x7f4df6425180 | 16974033399552 | 16974033407768 | 16974033586488 | 16974033588046 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 221 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 87296 | 0x7f4df6ec9780 | 0x7f4df64251c0 | 16974033604826 | 16974033612408 | 16974033791767 | 16974033793380 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 224 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 88768 | 0x7f4df6ec9600 | 0x7f4df6425200 | 16974033809430 | 16974033818647 | 16974033913367 | 16974033914957 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 227 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 90752 | 0x7f4df94f8480 | 0x7f4df6425240 | 16974033929576 | 16974033938326 | 16974034059926 | 16974034061393 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 230 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 91968 | 0x7f4df94f8300 | 0x7f4df6425280 | 16974034091422 | 16974034101846 | 16974034195766 | 16974034197759 |
| 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 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 93440 | 0x7f4df94f8180 | 0x7f4df64252c0 | 16974034216688 | 16974034228406 | 16974034409845 | 16974034411652 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 236 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 94912 | 0x7f4df94f8000 | 0x7f4df6425300 | 16974034426842 | 16974034434965 | 16974034615284 | 16974034617016 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 239 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 96384 | 0x7f4df6ec9e80 | 0x7f4df6425340 | 16974034632416 | 16974034640564 | 16974034736084 | 16974034737733 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 242 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 98368 | 0x7f4df6ec9d00 | 0x7f4df6425380 | 16974034752512 | 16974034761044 | 16974034888244 | 16974034890018 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 245 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 99584 | 0x7f4df6ec9b80 | 0x7f4df64253c0 | 16974034911828 | 16974034922003 | 16974035016403 | 16974035017975 |
| 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 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 101312 | 0x7f4df6ec9a00 | 0x7f4df6425400 | 16974035036974 | 16974035044723 | 16974035224562 | 16974035226449 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 251 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 102784 | 0x7f4df6ec9880 | 0x7f4df6425440 | 16974035240678 | 16974035248882 | 16974035430322 | 16974035432033 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 254 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 104256 | 0x7f4df6ec9700 | 0x7f4df6425480 | 16974035447262 | 16974035455282 | 16974035549841 | 16974035551509 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 257 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 106240 | 0x7f4df94f8580 | 0x7f4df64254c0 | 16974035566369 | 16974035574481 | 16974035705361 | 16974035706895 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 260 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 107712 | 0x7f4df94f8400 | 0x7f4df6425500 | 16974035726494 | 16974035737201 | 16974035830801 | 16974035832421 |
| 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 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 16 | 24 | 109440 | 0x7f4df94f8280 | 0x7f4df6425540 | 16974035848410 | 16974035857040 | 16974036035440 | 16974036037105 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 266 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 16 | 24 | 111168 | 0x7f4df94f8100 | 0x7f4df6425580 | 16974036052114 | 16974036059920 | 16974036240239 | 16974036241929 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 269 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 8 | 24 | 112896 | 0x7f4df6ec9f80 | 0x7f4df64255c0 | 16974036255438 | 16974036263439 | 16974036358639 | 16974036360335 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 272 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 115136 | 0x7f4df6ec9e00 | 0x7f4df6425600 | 16974036374395 | 16974036382479 | 16974036522478 | 16974036524131 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 275 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 116608 | 0x7f4df6ec9c80 | 0x7f4df6425640 | 16974036545140 | 16974036556078 | 16974036650638 | 16974036652247 |
| 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 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 16 | 24 | 118336 | 0x7f4df6ec9b00 | 0x7f4df6425680 | 16974036668766 | 16974036676878 | 16974036856077 | 16974036857611 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 281 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 16 | 24 | 120064 | 0x7f4df6ec9980 | 0x7f4df64256c0 | 16974036871481 | 16974036880237 | 16974037059917 | 16974037061575 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 284 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 121792 | 0x7f4df6ec9800 | 0x7f4df6425700 | 16974037076135 | 16974037083917 | 16974037180076 | 16974037181621 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 287 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 124032 | 0x7f4df6ec9680 | 0x7f4df6425740 | 16974037197621 | 16974037205676 | 16974037351276 | 16974037352896 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 290 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 125504 | 0x7f4df94f8500 | 0x7f4df6425780 | 16974037372356 | 16974037383276 | 16974037478475 | 16974037480063 |
| 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 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 127488 | 0x7f4df94f8380 | 0x7f4df64257c0 | 16974037494812 | 16974037502475 | 16974037683915 | 16974037685437 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 296 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 129216 | 0x7f4df94f8200 | 0x7f4df6425800 | 16974037701486 | 16974037709195 | 16974037890474 | 16974037892261 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 299 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 130944 | 0x7f4df94f8080 | 0x7f4df6425840 | 16974037908940 | 16974037917674 | 16974038017834 | 16974038019387 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 302 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 133440 | 0x7f4df6ec9f00 | 0x7f4df6425880 | 16974038035017 | 16974038043754 | 16974038199273 | 16974038200922 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 305 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 134912 | 0x7f4df6ec9d80 | 0x7f4df64258c0 | 16974038222391 | 16974038232873 | 16974038327913 | 16974038329608 |
| 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 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 136896 | 0x7f4df6ec9c00 | 0x7f4df6425900 | 16974038344998 | 16974038353033 | 16974038531912 | 16974038533612 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 311 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 138880 | 0x7f4df6ec9a80 | 0x7f4df6425940 | 16974038549372 | 16974038557192 | 16974038737351 | 16974038739016 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 314 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 140864 | 0x7f4df6ec9900 | 0x7f4df6425980 | 16974038753606 | 16974038761351 | 16974038868071 | 16974038869692 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 317 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 143616 | 0x7f4df6ec9780 | 0x7f4df64259c0 | 16974038883602 | 16974038891911 | 16974039062150 | 16974039063807 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 320 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 145344 | 0x7f4df6ec9600 | 0x7f4df6425a00 | 16974039084946 | 16974039095110 | 16974039190950 | 16974039192583 |
| 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 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 147584 | 0x7f4df94f8480 | 0x7f4df6425a40 | 16974039208322 | 16974039216390 | 16974039399269 | 16974039400877 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 326 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 149568 | 0x7f4df94f8300 | 0x7f4df6425a80 | 16974039414566 | 16974039422629 | 16974039605349 | 16974039607071 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 329 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 151552 | 0x7f4df94f8180 | 0x7f4df6425ac0 | 16974039620650 | 16974039628549 | 16974039739748 | 16974039741397 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 332 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 154304 | 0x7f4df94f8000 | 0x7f4df6425b00 | 16974039755856 | 16974039763748 | 16974039945028 | 16974039946751 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 335 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 156288 | 0x7f4df6ec9e80 | 0x7f4df6425b40 | 16974039968350 | 16974039977988 | 16974040079107 | 16974040080737 |
| 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 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 158784 | 0x7f4df6ec9d00 | 0x7f4df6425b80 | 16974040095676 | 16974040103907 | 16974040290147 | 16974040291801 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 341 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 161024 | 0x7f4df6ec9b80 | 0x7f4df6425bc0 | 16974040305410 | 16974040313346 | 16974040499906 | 16974040501535 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 344 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 163264 | 0x7f4df6ec9a00 | 0x7f4df6425c00 | 16974040517284 | 16974040525186 | 16974040647905 | 16974040649660 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 347 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 166528 | 0x7f4df6ec9880 | 0x7f4df6425c40 | 16974040664020 | 16974040672065 | 16974040878785 | 16974040898563 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 350 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 168512 | 0x7f4df6ec9700 | 0x7f4df6425c80 | 16974040913853 | 16974040924865 | 16974041036224 | 16974041037769 |
| 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 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 171264 | 0x7f4df94f8580 | 0x7f4df6425cc0 | 16974041053358 | 16974041062144 | 16974041247264 | 16974041248753 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 356 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 173760 | 0x7f4df94f8400 | 0x7f4df6425d00 | 16974041263722 | 16974041271423 | 16974041458303 | 16974041459877 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 359 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 176256 | 0x7f4df94f8280 | 0x7f4df6425d40 | 16974041475916 | 16974041483743 | 16974041618302 | 16974041619912 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 362 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 179776 | 0x7f4df94f8100 | 0x7f4df6425d80 | 16974041634492 | 16974041642462 | 16974041874462 | 16974041891964 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 365 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 182272 | 0x7f4df6ec9f80 | 0x7f4df6425dc0 | 16974041908644 | 16974041919261 | 16974042046141 | 16974042047769 |
| 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 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 185536 | 0x7f4df6ec9e00 | 0x7f4df6425e00 | 16974042063859 | 16974042071421 | 16974042264060 | 16974042265673 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 371 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 188544 | 0x7f4df6ec9c80 | 0x7f4df6425e40 | 16974042281803 | 16974042290460 | 16974042484540 | 16974042486377 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 374 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 191552 | 0x7f4df6ec9b00 | 0x7f4df6425e80 | 16974042499716 | 16974042507900 | 16974042668059 | 16974042669701 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 377 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 195840 | 0x7f4df6ec9980 | 0x7f4df6425ec0 | 16974042683981 | 16974042692059 | 16974042975258 | 16974043017261 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 380 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 198592 | 0x7f4df6ec9800 | 0x7f4df6425f00 | 16974043033341 | 16974043043578 | 16974043193977 | 16974043195646 |
| 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 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 202368 | 0x7f4df6ec9680 | 0x7f4df6425f40 | 16974043211885 | 16974043219737 | 16974043427417 | 16974043465588 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 386 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 205888 | 0x7f4df94f8500 | 0x7f4df6425f80 | 16974043474068 | 16974043484057 | 16974043691416 | 16974043709021 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 389 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 209408 | 0x7f4df94f8380 | 0x7f4df6425fc0 | 16974043717311 | 16974043727096 | 16974043913015 | 16974043914565 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 392 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 214464 | 0x7f4df94f8200 | 0x7f4df6426000 | 16974043929315 | 16974043937655 | 16974044272214 | 16974044289754 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 395 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 217728 | 0x7f4df94f8080 | 0x7f4df6426040 | 16974044306324 | 16974044316854 | 16974044484853 | 16974044486418 |
| 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 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 222016 | 0x7f4df6ec9f00 | 0x7f4df6426080 | 16974044501908 | 16974044509813 | 16974044738293 | 16974044752271 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 401 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 226048 | 0x7f4df6ec9d80 | 0x7f4df64260c0 | 16974044760740 | 16974044770932 | 16974045001172 | 16974045015063 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 404 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 230080 | 0x7f4df6ec9c00 | 0x7f4df6426100 | 16974045023543 | 16974045033652 | 16974045244691 | 16974045258486 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 407 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 235904 | 0x7f4df6ec9a80 | 0x7f4df6426140 | 16974045267985 | 16974045277491 | 16974045663250 | 16974045676494 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 410 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 239424 | 0x7f4df6ec9900 | 0x7f4df6426180 | 16974045692853 | 16974045703410 | 16974045890609 | 16974045892217 |
| 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 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 244224 | 0x7f4df6ec9780 | 0x7f4df64261c0 | 16974045908377 | 16974045916369 | 16974046167088 | 16974046185729 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 416 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 248768 | 0x7f4df6ec9600 | 0x7f4df6426200 | 16974046196308 | 16974046206288 | 16974046453807 | 16974046467040 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 419 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 253312 | 0x7f4df94f8480 | 0x7f4df6426240 | 16974046477200 | 16974046487247 | 16974046724046 | 16974046737243 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 422 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 8 | 24 | 255552 | 0x7f4df94f8300 | 0x7f4df6426280 | 16974046745222 | 16974046754126 | 16974047207565 | 16974047221038 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 425 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 259840 | 0x7f4df94f8180 | 0x7f4df64262c0 | 16974047237398 | 16974047248205 | 16974047474924 | 16974047488521 |
| 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 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 265664 | 0x7f4df94f8000 | 0x7f4df6426300 | 16974047498200 | 16974047507884 | 16974047806123 | 16974047819491 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 431 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 271232 | 0x7f4df6ec9e80 | 0x7f4df6426340 | 16974047832441 | 16974047842443 | 16974048141482 | 16974048158561 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 434 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 8 | 24 | 273216 | 0x7f4df6ec9d00 | 0x7f4df6426380 | 16974048168091 | 16974048177962 | 16974048474761 | 16974048491321 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 437 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 8 | 24 | 275712 | 0x7f4df6ec9b80 | 0x7f4df64263c0 | 16974048501411 | 16974048511241 | 16974049069799 | 16974049083094 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 440 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 280768 | 0x7f4df6ec9a00 | 0x7f4df6426400 | 16974049101044 | 16974049111719 | 16974049375878 | 16974049396675 |
| 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 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 287616 | 0x7f4df6ec9880 | 0x7f4df6426440 | 16974049405125 | 16974049415078 | 16974049765317 | 16974049785774 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 446 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 294208 | 0x7f4df6ec9700 | 0x7f4df6426480 | 16974049794833 | 16974049805157 | 16974050155236 | 16974050178742 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 449 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 8 | 24 | 296960 | 0x7f4df94f8580 | 0x7f4df64264c0 | 16974050192912 | 16974050202755 | 16974050549794 | 16974050572701 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 452 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 8 | 24 | 299968 | 0x7f4df94f8400 | 0x7f4df6426500 | 16974050583210 | 16974050592834 | 16974051254912 | 16974051278250 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 455 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 8 | 24 | 302720 | 0x7f4df94f8280 | 0x7f4df6426540 | 16974051295710 | 16974051305152 | 16974051752511 | 16974051772596 |
| 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 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 305472 | 0x7f4df94f8100 | 0x7f4df6426580 | 16974051784965 | 16974051794910 | 16974052260669 | 16974052280061 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 461 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 308224 | 0x7f4df6ec9f80 | 0x7f4df64265c0 | 16974052291151 | 16974052300989 | 16974052762267 | 16974052783576 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 464 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 8 | 24 | 310976 | 0x7f4df6ec9e00 | 0x7f4df6426600 | 16974052793856 | 16974052804187 | 16974053256666 | 16974053277902 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 467 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 8 | 24 | 313216 | 0x7f4df6ec9c80 | 0x7f4df6426640 | 16974053286141 | 16974053296346 | 16974054166263 | 16974054188635 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 470 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 8 | 24 | 315968 | 0x7f4df6ec9b00 | 0x7f4df6426680 | 16974054206065 | 16974054216343 | 16974055070580 | 16974055115578 |
| 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 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 318720 | 0x7f4df6ec9980 | 0x7f4df64266c0 | 16974055124678 | 16974055134900 | 16974056020017 | 16974056064010 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 476 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 321472 | 0x7f4df6ec9800 | 0x7f4df6426700 | 16974056072510 | 16974056082737 | 16974056962254 | 16974057004853 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 479 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 8 | 24 | 324224 | 0x7f4df6ec9680 | 0x7f4df6426740 | 16974057015413 | 16974057024814 | 16974057884331 | 16974057927536 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 482 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 8 | 24 | 326464 | 0x7f4df94f8500 | 0x7f4df6426780 | 16974057936256 | 16974057946411 | 16974059645606 | 16974059695034 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 485 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 8 | 24 | 329216 | 0x7f4df94f8380 | 0x7f4df64267c0 | 16974059713284 | 16974059723526 | 16974061388960 | 16974061434084 |
| 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 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 331968 | 0x7f4df94f8200 | 0x7f4df6426800 | 16974061443973 | 16974061454080 | 16974063179995 | 16974063252371 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 491 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 12 | 24 | 334720 | 0x7f4df94f8080 | 0x7f4df6426840 | 16974063263540 | 16974063273594 | 16974064989429 | 16974065056528 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 494 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 8 | 24 | 337472 | 0x7f4df6ec9f00 | 0x7f4df6426880 | 16974065073347 | 16974065082549 | 16974066757583 | 16974066828366 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 497 | 186167 | 186167 | 4194304 | 256 | 0 | 0 | 8 | 24 | 0 | 0x7f4df6ec9d80 | 0x7f4df64268c0 | 16974066837546 | 16974066847663 | 16974070205573 | 16974070253937 |