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 | 163806 | 163806 | 33554432 | 256 | 0 | 0 | 4 | 32 | 4160 | 0x0 | 0x7f6951404280 | 16560615136465 | 16560615162516 | 16560615404114 | 16560615491373 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 163806 | 163806 | 32768 | 256 | 0 | 0 | 12 | 24 | 13888 | 0x0 | 0x7f6951423f80 | 16560620221963 | 16560620237679 | 16560620251119 | 16560620269262 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 5 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 14336 | 0x7f6954367380 | 0x7f6951423fc0 | 16560620274852 | 16560620321359 | 16560620413838 | 16560620415986 |
| 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 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15040 | 0x7f6954367200 | 0x7f6951424000 | 16560620437236 | 16560620446958 | 16560620626637 | 16560620628739 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 11 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15488 | 0x7f6954367080 | 0x7f6951424040 | 16560620643598 | 16560620651916 | 16560620832555 | 16560620834672 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 14 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 15936 | 0x7f6951d09f00 | 0x7f6951424080 | 16560620848771 | 16560620857195 | 16560620950794 | 16560620952997 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 17 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 16384 | 0x7f6951d09d80 | 0x7f69514240c0 | 16560620968247 | 16560620976394 | 16560621068394 | 16560621070413 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 20 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 17088 | 0x7f6951d09c00 | 0x7f6951424100 | 16560621097862 | 16560621108713 | 16560621200553 | 16560621202408 |
| 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 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 16 | 24 | 17792 | 0x7f6951d09a80 | 0x7f6951424140 | 16560621217028 | 16560621225672 | 16560621405031 | 16560621406991 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 26 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 16 | 24 | 18496 | 0x7f6951d09900 | 0x7f6951424180 | 16560621432230 | 16560621442631 | 16560621621670 | 16560621623573 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 29 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19200 | 0x7f6951d09780 | 0x7f69514241c0 | 16560621641823 | 16560621659909 | 16560621753989 | 16560621755859 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 32 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19904 | 0x7f6951d09600 | 0x7f6951424200 | 16560621772738 | 16560621782149 | 16560621875268 | 16560621877124 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 35 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 20608 | 0x7f6954367480 | 0x7f6951424240 | 16560621900363 | 16560621919588 | 16560622013667 | 16560622015749 |
| 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 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 16 | 24 | 21312 | 0x7f6954367300 | 0x7f6951424280 | 16560622036849 | 16560622046147 | 16560622225346 | 16560622227172 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 41 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22016 | 0x7f6954367180 | 0x7f69514242c0 | 16560622243361 | 16560622252385 | 16560622433024 | 16560622435024 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 44 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22720 | 0x7f6954367000 | 0x7f6951424300 | 16560622449714 | 16560622459264 | 16560622552543 | 16560622554400 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 47 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 23424 | 0x7f6951d09e80 | 0x7f6951424340 | 16560622575269 | 16560622584383 | 16560622677182 | 16560622679046 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 50 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 24128 | 0x7f6951d09d00 | 0x7f6951424380 | 16560622700535 | 16560622710782 | 16560622803421 | 16560622805311 |
| 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 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 16 | 24 | 24832 | 0x7f6951d09b80 | 0x7f69514243c0 | 16560622823220 | 16560622832221 | 16560623011580 | 16560623013504 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 56 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 16 | 24 | 25536 | 0x7f6951d09a00 | 0x7f6951424400 | 16560623032253 | 16560623041340 | 16560623221019 | 16560623223196 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 59 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26240 | 0x7f6951d09880 | 0x7f6951424440 | 16560623236706 | 16560623246138 | 16560623340218 | 16560623342202 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 62 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26944 | 0x7f6951d09700 | 0x7f6951424480 | 16560623359311 | 16560623368378 | 16560623461337 | 16560623463277 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 65 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 27648 | 0x7f6954367580 | 0x7f69514244c0 | 16560623483617 | 16560623494137 | 16560623586776 | 16560623588683 |
| 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 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 16 | 24 | 28608 | 0x7f6954367400 | 0x7f6951424500 | 16560623612432 | 16560623622936 | 16560623801815 | 16560623803765 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 71 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 16 | 24 | 29312 | 0x7f6954367280 | 0x7f6951424540 | 16560623818425 | 16560623827414 | 16560624007733 | 16560624009708 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 74 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 30016 | 0x7f6954367100 | 0x7f6951424580 | 16560624025967 | 16560624056373 | 16560624148692 | 16560624150723 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 77 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 8 | 24 | 30976 | 0x7f6951d09f80 | 0x7f69514245c0 | 16560624166802 | 16560624176372 | 16560624268371 | 16560624270349 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 80 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 31680 | 0x7f6951d09e00 | 0x7f6951424600 | 16560624291358 | 16560624301811 | 16560624394130 | 16560624396014 |
| 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 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 16 | 24 | 32640 | 0x7f6951d09c80 | 0x7f6951424640 | 16560624416713 | 16560624433010 | 16560624612529 | 16560624614066 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 86 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 33600 | 0x7f6951d09b00 | 0x7f6951424680 | 16560624629976 | 16560624637809 | 16560624819087 | 16560624820599 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 89 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 34560 | 0x7f6951d09980 | 0x7f69514246c0 | 16560624837348 | 16560624845967 | 16560624940687 | 16560624942034 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 92 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 8 | 24 | 35520 | 0x7f6951d09800 | 0x7f6951424700 | 16560624955874 | 16560624964206 | 16560625058446 | 16560625059910 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 95 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 36224 | 0x7f6951d09680 | 0x7f6951424740 | 16560625081129 | 16560625090926 | 16560625184525 | 16560625186036 |
| 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 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 37184 | 0x7f6954367500 | 0x7f6951424780 | 16560625200785 | 16560625209805 | 16560625390283 | 16560625391688 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 101 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 38144 | 0x7f6954367380 | 0x7f69514247c0 | 16560625408388 | 16560625416363 | 16560625596042 | 16560625597491 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 104 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 39104 | 0x7f6954367200 | 0x7f6951424800 | 16560625612730 | 16560625620682 | 16560625713481 | 16560625714887 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 107 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 8 | 24 | 40320 | 0x7f6954367080 | 0x7f6951424840 | 16560625729776 | 16560625739081 | 16560625832200 | 16560625833602 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 110 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 41280 | 0x7f6951d09f00 | 0x7f6951424880 | 16560625855352 | 16560625866120 | 16560625959559 | 16560625961128 |
| 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 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 42240 | 0x7f6951d09d80 | 0x7f69514248c0 | 16560625976197 | 16560625984519 | 16560626164678 | 16560626166341 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 116 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 43200 | 0x7f6951d09c00 | 0x7f6951424900 | 16560626185190 | 16560626192998 | 16560626373157 | 16560626374943 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 119 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 8 | 24 | 44160 | 0x7f6951d09a80 | 0x7f6951424940 | 16560626389403 | 16560626398436 | 16560626492836 | 16560626494399 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 122 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 45376 | 0x7f6951d09900 | 0x7f6951424980 | 16560626508658 | 16560626516836 | 16560626611395 | 16560626612835 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 125 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 46336 | 0x7f6951d09780 | 0x7f69514249c0 | 16560626632464 | 16560626643555 | 16560626736834 | 16560626738450 |
| 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 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 47552 | 0x7f6951d09600 | 0x7f6951424a00 | 16560626753670 | 16560626761954 | 16560626941633 | 16560626943033 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 131 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 48512 | 0x7f6954367480 | 0x7f6951424a40 | 16560626958752 | 16560626966912 | 16560627148991 | 16560627150535 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 134 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 8 | 24 | 49472 | 0x7f6954367300 | 0x7f6951424a80 | 16560627165285 | 16560627173951 | 16560627266750 | 16560627268131 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 137 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 50688 | 0x7f6954367180 | 0x7f6951424ac0 | 16560627283121 | 16560627291870 | 16560627385150 | 16560627386537 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 140 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 51648 | 0x7f6954367000 | 0x7f6951424b00 | 16560627407926 | 16560627418429 | 16560627510109 | 16560627511543 |
| 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 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 52864 | 0x7f6951d09e80 | 0x7f6951424b40 | 16560627528792 | 16560627536348 | 16560627715547 | 16560627716955 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 146 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 54080 | 0x7f6951d09d00 | 0x7f6951424b80 | 16560627733025 | 16560627742107 | 16560627922906 | 16560627924228 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 149 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 8 | 24 | 55296 | 0x7f6951d09b80 | 0x7f6951424bc0 | 16560627939107 | 16560627947546 | 16560628041945 | 16560628043454 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 152 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 56768 | 0x7f6951d09a00 | 0x7f6951424c00 | 16560628058363 | 16560628067545 | 16560628162584 | 16560628163979 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 155 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 57728 | 0x7f6951d09880 | 0x7f6951424c40 | 16560628183919 | 16560628194424 | 16560628287703 | 16560628289135 |
| 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 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 58944 | 0x7f6951d09700 | 0x7f6951424c80 | 16560628305784 | 16560628314103 | 16560628493782 | 16560628495207 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 161 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 60160 | 0x7f6954367580 | 0x7f6951424cc0 | 16560628510517 | 16560628518582 | 16560628699060 | 16560628700350 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 164 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 8 | 24 | 61376 | 0x7f6954367400 | 0x7f6951424d00 | 16560628715220 | 16560628724340 | 16560628818100 | 16560628819536 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 167 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 62848 | 0x7f6954367280 | 0x7f6951424d40 | 16560628836895 | 16560628844979 | 16560628944179 | 16560628945711 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 170 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 63808 | 0x7f6954367100 | 0x7f6951424d80 | 16560628966501 | 16560628977138 | 16560629071218 | 16560629072627 |
| 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 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 65024 | 0x7f6951d09f80 | 0x7f6951424dc0 | 16560629089926 | 16560629100018 | 16560629278576 | 16560629279979 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 176 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 66240 | 0x7f6951d09e00 | 0x7f6951424e00 | 16560629296059 | 16560629305136 | 16560629484335 | 16560629485792 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 179 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 8 | 24 | 67456 | 0x7f6951d09c80 | 0x7f6951424e40 | 16560629499682 | 16560629508655 | 16560629602574 | 16560629603928 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 182 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 68928 | 0x7f6951d09b00 | 0x7f6951424e80 | 16560629620067 | 16560629628494 | 16560629732333 | 16560629733803 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 185 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 70144 | 0x7f6951d09980 | 0x7f6951424ec0 | 16560629755332 | 16560629765773 | 16560629858892 | 16560629860289 |
| 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 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 71616 | 0x7f6951d09800 | 0x7f6951424f00 | 16560629874338 | 16560629882572 | 16560630062571 | 16560630064111 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 191 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 72832 | 0x7f6951d09680 | 0x7f6951424f40 | 16560630111560 | 16560630120650 | 16560630300809 | 16560630302273 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 194 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 8 | 24 | 74048 | 0x7f6954367500 | 0x7f6951424f80 | 16560630317252 | 16560630325929 | 16560630419848 | 16560630421349 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 197 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 75776 | 0x7f6954367380 | 0x7f6951424fc0 | 16560630437678 | 16560630445288 | 16560630552807 | 16560630554394 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 200 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 76992 | 0x7f6954367200 | 0x7f6951425000 | 16560630575073 | 16560630585927 | 16560630679847 | 16560630681289 |
| 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 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 78464 | 0x7f6954367080 | 0x7f6951425040 | 16560630695989 | 16560630704006 | 16560630884805 | 16560630886162 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 206 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 79936 | 0x7f6951d09f00 | 0x7f6951425080 | 16560630900681 | 16560630909125 | 16560631089604 | 16560631091055 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 209 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 8 | 24 | 81408 | 0x7f6951d09d80 | 0x7f69514250c0 | 16560631105054 | 16560631114564 | 16560631210243 | 16560631211560 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 212 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 83136 | 0x7f6951d09c00 | 0x7f6951425100 | 16560631226260 | 16560631234883 | 16560631350722 | 16560631352225 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 215 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 84352 | 0x7f6951d09a80 | 0x7f6951425140 | 16560631388164 | 16560631397602 | 16560631492161 | 16560631493620 |
| 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 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 85824 | 0x7f6951d09900 | 0x7f6951425180 | 16560631509710 | 16560631517761 | 16560631698719 | 16560631700073 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 221 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 87296 | 0x7f6951d09780 | 0x7f69514251c0 | 16560631716782 | 16560631725599 | 16560631906558 | 16560631908045 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 224 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 88768 | 0x7f6951d09600 | 0x7f6951425200 | 16560631922725 | 16560631931838 | 16560632027837 | 16560632029131 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 227 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 90752 | 0x7f6954367480 | 0x7f6951425240 | 16560632043990 | 16560632053757 | 16560632175356 | 16560632176806 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 230 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 91968 | 0x7f6954367300 | 0x7f6951425280 | 16560632196875 | 16560632207356 | 16560632301115 | 16560632302611 |
| 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 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 93440 | 0x7f6954367180 | 0x7f69514252c0 | 16560632317131 | 16560632324955 | 16560632503674 | 16560632504964 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 236 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 94912 | 0x7f6954367000 | 0x7f6951425300 | 16560632519073 | 16560632527194 | 16560632707192 | 16560632708627 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 239 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 96384 | 0x7f6951d09e80 | 0x7f6951425340 | 16560632723146 | 16560632731672 | 16560632827672 | 16560632829172 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 242 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 98368 | 0x7f6951d09d00 | 0x7f6951425380 | 16560632844742 | 16560632853111 | 16560632979191 | 16560632980587 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 245 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 99584 | 0x7f6951d09b80 | 0x7f69514253c0 | 16560633001166 | 16560633011670 | 16560633105750 | 16560633107182 |
| 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 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 101312 | 0x7f6951d09a00 | 0x7f6951425400 | 16560633126702 | 16560633138549 | 16560633317428 | 16560633318875 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 251 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 102784 | 0x7f6951d09880 | 0x7f6951425440 | 16560633333894 | 16560633343188 | 16560633522227 | 16560633523677 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 254 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 104256 | 0x7f6951d09700 | 0x7f6951425480 | 16560633537887 | 16560633547187 | 16560633641746 | 16560633643383 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 257 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 106240 | 0x7f6954367580 | 0x7f69514254c0 | 16560633657633 | 16560633665906 | 16560633796465 | 16560633797808 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 260 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 107712 | 0x7f6954367400 | 0x7f6951425500 | 16560633819247 | 16560633830065 | 16560633923504 | 16560633924943 |
| 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 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 16 | 24 | 109440 | 0x7f6954367280 | 0x7f6951425540 | 16560633942592 | 16560633951024 | 16560634130542 | 16560634131976 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 266 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 16 | 24 | 111168 | 0x7f6954367100 | 0x7f6951425580 | 16560634147285 | 16560634155022 | 16560634334221 | 16560634335738 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 269 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 8 | 24 | 112896 | 0x7f6951d09f80 | 0x7f69514255c0 | 16560634351018 | 16560634359501 | 16560634455340 | 16560634456694 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 272 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 115136 | 0x7f6951d09e00 | 0x7f6951425600 | 16560634472713 | 16560634481420 | 16560634620139 | 16560634621508 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 275 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 116608 | 0x7f6951d09c80 | 0x7f6951425640 | 16560634641687 | 16560634652299 | 16560634747338 | 16560634748773 |
| 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 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 16 | 24 | 118336 | 0x7f6951d09b00 | 0x7f6951425680 | 16560634763613 | 16560634771658 | 16560634952457 | 16560634953946 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 281 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 16 | 24 | 120064 | 0x7f6951d09980 | 0x7f69514256c0 | 16560634968016 | 16560634976777 | 16560635155815 | 16560635157369 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 284 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 121792 | 0x7f6951d09800 | 0x7f6951425700 | 16560635171788 | 16560635179815 | 16560635276934 | 16560635278354 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 287 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 124032 | 0x7f6951d09680 | 0x7f6951425740 | 16560635293844 | 16560635301574 | 16560635447013 | 16560635448608 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 290 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 125504 | 0x7f6954367500 | 0x7f6951425780 | 16560635468688 | 16560635479173 | 16560635575332 | 16560635576724 |
| 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 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 127488 | 0x7f6954367380 | 0x7f69514257c0 | 16560635592863 | 16560635600932 | 16560635784771 | 16560635786316 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 296 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 129216 | 0x7f6954367200 | 0x7f6951425800 | 16560635800946 | 16560635808771 | 16560635988930 | 16560635990429 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 299 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 130944 | 0x7f6954367080 | 0x7f6951425840 | 16560636005218 | 16560636013889 | 16560636113569 | 16560636115034 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 302 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 133440 | 0x7f6951d09f00 | 0x7f6951425880 | 16560636128874 | 16560636136929 | 16560636292127 | 16560636293618 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 305 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 134912 | 0x7f6951d09d80 | 0x7f69514258c0 | 16560636313487 | 16560636324287 | 16560636419487 | 16560636420913 |
| 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 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 136896 | 0x7f6951d09c00 | 0x7f6951425900 | 16560636435543 | 16560636443646 | 16560636622525 | 16560636623946 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 311 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 138880 | 0x7f6951d09a80 | 0x7f6951425940 | 16560636638496 | 16560636647005 | 16560636827644 | 16560636829099 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 314 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 140864 | 0x7f6951d09900 | 0x7f6951425980 | 16560636842448 | 16560636850684 | 16560636957883 | 16560636959264 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 317 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 143616 | 0x7f6951d09780 | 0x7f69514259c0 | 16560636973724 | 16560636983003 | 16560637153401 | 16560637154787 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 320 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 145344 | 0x7f6951d09600 | 0x7f6951425a00 | 16560637175706 | 16560637186041 | 16560637281241 | 16560637282713 |
| 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 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 147584 | 0x7f6954367480 | 0x7f6951425a40 | 16560637299572 | 16560637307480 | 16560637487639 | 16560637489545 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 326 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 149568 | 0x7f6954367300 | 0x7f6951425a80 | 16560637503835 | 16560637512599 | 16560637692438 | 16560637693858 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 329 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 151552 | 0x7f6954367180 | 0x7f6951425ac0 | 16560637707497 | 16560637716277 | 16560637826677 | 16560637828143 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 332 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 154304 | 0x7f6954367000 | 0x7f6951425b00 | 16560637841913 | 16560637850677 | 16560638031635 | 16560638033076 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 335 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 156288 | 0x7f6951d09e80 | 0x7f6951425b40 | 16560638054135 | 16560638063475 | 16560638165074 | 16560638166771 |
| 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 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 158784 | 0x7f6951d09d00 | 0x7f6951425b80 | 16560638182520 | 16560638190674 | 16560638376433 | 16560638378023 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 341 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 161024 | 0x7f6951d09b80 | 0x7f6951425bc0 | 16560638392323 | 16560638400113 | 16560638586031 | 16560638587466 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 344 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 163264 | 0x7f6951d09a00 | 0x7f6951425c00 | 16560638602175 | 16560638610511 | 16560638733230 | 16560638734781 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 347 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 166528 | 0x7f6951d09880 | 0x7f6951425c40 | 16560638749170 | 16560638757230 | 16560638963789 | 16560639008371 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 350 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 168512 | 0x7f6951d09700 | 0x7f6951425c80 | 16560639024640 | 16560639035148 | 16560639146028 | 16560639147406 |
| 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 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 171264 | 0x7f6954367580 | 0x7f6951425cc0 | 16560639164285 | 16560639173227 | 16560639356266 | 16560639357918 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 356 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 173760 | 0x7f6954367400 | 0x7f6951425d00 | 16560639372818 | 16560639381066 | 16560639568745 | 16560639570281 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 359 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 176256 | 0x7f6954367280 | 0x7f6951425d40 | 16560639584490 | 16560639592424 | 16560639726983 | 16560639728395 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 362 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 179776 | 0x7f6954367100 | 0x7f6951425d80 | 16560639743815 | 16560639752103 | 16560639984102 | 16560640027444 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 365 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 182272 | 0x7f6951d09f80 | 0x7f6951425dc0 | 16560640042804 | 16560640053381 | 16560640180100 | 16560640181529 |
| 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 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 185536 | 0x7f6951d09e00 | 0x7f6951425e00 | 16560640196828 | 16560640204580 | 16560640395459 | 16560640396981 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 371 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 188544 | 0x7f6951d09c80 | 0x7f6951425e40 | 16560640411651 | 16560640420259 | 16560640613857 | 16560640615443 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 374 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 191552 | 0x7f6951d09b00 | 0x7f6951425e80 | 16560640630153 | 16560640637857 | 16560640797856 | 16560640799267 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 377 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 195840 | 0x7f6951d09980 | 0x7f6951425ec0 | 16560640813846 | 16560640821856 | 16560641106014 | 16560641127655 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 380 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 198592 | 0x7f6951d09800 | 0x7f6951425f00 | 16560641143185 | 16560641154014 | 16560641303612 | 16560641304999 |
| 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 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 202368 | 0x7f6951d09680 | 0x7f6951425f40 | 16560641322828 | 16560641330812 | 16560641540891 | 16560641559840 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 386 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 205888 | 0x7f6954367500 | 0x7f6951425f80 | 16560641567879 | 16560641578171 | 16560641787289 | 16560641806601 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 389 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 209408 | 0x7f6954367380 | 0x7f6951425fc0 | 16560641814811 | 16560641824729 | 16560642010968 | 16560642012314 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 392 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 214464 | 0x7f6954367200 | 0x7f6951426000 | 16560642027663 | 16560642035607 | 16560642370165 | 16560642413169 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 395 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 217728 | 0x7f6954367080 | 0x7f6951426040 | 16560642429919 | 16560642440245 | 16560642607763 | 16560642609222 |
| 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 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 222016 | 0x7f6951d09f00 | 0x7f6951426080 | 16560642623902 | 16560642631923 | 16560642862322 | 16560642902122 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 401 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 226048 | 0x7f6951d09d80 | 0x7f69514260c0 | 16560642910101 | 16560642920241 | 16560643150160 | 16560643189971 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 404 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 230080 | 0x7f6951d09c00 | 0x7f6951426100 | 16560643201011 | 16560643211279 | 16560643422478 | 16560643462312 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 407 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 235904 | 0x7f6951d09a80 | 0x7f6951426140 | 16560643471831 | 16560643480717 | 16560643866635 | 16560643906556 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 410 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 239424 | 0x7f6951d09900 | 0x7f6951426180 | 16560643923185 | 16560643933194 | 16560644120713 | 16560644122238 |
| 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 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 244224 | 0x7f6951d09780 | 0x7f69514261c0 | 16560644137467 | 16560644145353 | 16560644395751 | 16560644438837 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 416 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 248768 | 0x7f6951d09600 | 0x7f6951426200 | 16560644447026 | 16560644457350 | 16560644705829 | 16560644748986 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 419 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 253312 | 0x7f6954367480 | 0x7f6951426240 | 16560644757735 | 16560644767908 | 16560645005347 | 16560645023566 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 422 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 8 | 24 | 255552 | 0x7f6954367300 | 0x7f6951426280 | 16560645031965 | 16560645041986 | 16560645496543 | 16560645512008 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 425 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 259840 | 0x7f6954367180 | 0x7f69514262c0 | 16560645528818 | 16560645539423 | 16560645765021 | 16560645781049 |
| 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 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 265664 | 0x7f6954367000 | 0x7f6951426300 | 16560645789938 | 16560645799901 | 16560646097819 | 16560646122046 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 431 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 271232 | 0x7f6951d09e80 | 0x7f6951426340 | 16560646132246 | 16560646141659 | 16560646440057 | 16560646458664 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 434 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 8 | 24 | 273216 | 0x7f6951d09d00 | 0x7f6951426380 | 16560646470524 | 16560646480696 | 16560646777974 | 16560646817831 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 437 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 8 | 24 | 275712 | 0x7f6951d09b80 | 0x7f69514263c0 | 16560646826141 | 16560646836374 | 16560647393330 | 16560647436629 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 440 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 280768 | 0x7f6951d09a00 | 0x7f6951426400 | 16560647455119 | 16560647465489 | 16560647729488 | 16560647772617 |
| 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 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 287616 | 0x7f6951d09880 | 0x7f6951426440 | 16560647780917 | 16560647791247 | 16560648141165 | 16560648184433 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 446 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 294208 | 0x7f6951d09700 | 0x7f6951426480 | 16560648192072 | 16560648210284 | 16560648561802 | 16560648604588 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 449 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 8 | 24 | 296960 | 0x7f6954367580 | 0x7f69514264c0 | 16560648614717 | 16560648624521 | 16560648972039 | 16560649015383 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 452 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 8 | 24 | 299968 | 0x7f6954367400 | 0x7f6951426500 | 16560649023723 | 16560649033639 | 16560649694114 | 16560649737237 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 455 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 8 | 24 | 302720 | 0x7f6954367280 | 0x7f6951426540 | 16560649754817 | 16560649764353 | 16560650211230 | 16560650239559 |
| 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 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 305472 | 0x7f6954367100 | 0x7f6951426580 | 16560650248689 | 16560650258270 | 16560650722747 | 16560650745281 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 461 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 308224 | 0x7f6951d09f80 | 0x7f69514265c0 | 16560650753631 | 16560650763546 | 16560651226423 | 16560651248333 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 464 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 8 | 24 | 310976 | 0x7f6951d09e00 | 0x7f6951426600 | 16560651256613 | 16560651267063 | 16560651718740 | 16560651742055 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 467 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 8 | 24 | 313216 | 0x7f6951d09c80 | 0x7f6951426640 | 16560651752115 | 16560651762260 | 16560652632493 | 16560652678012 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 470 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 8 | 24 | 315968 | 0x7f6951d09b00 | 0x7f6951426680 | 16560652694741 | 16560652705293 | 16560653559687 | 16560653601439 |
| 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 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 318720 | 0x7f6951d09980 | 0x7f69514266c0 | 16560653612918 | 16560653628807 | 16560654514560 | 16560654562024 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 476 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 321472 | 0x7f6951d09800 | 0x7f6951426700 | 16560654571214 | 16560654580960 | 16560655461114 | 16560655507911 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 479 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 8 | 24 | 324224 | 0x7f6951d09680 | 0x7f6951426740 | 16560655517830 | 16560655535033 | 16560656395507 | 16560656442657 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 482 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 8 | 24 | 326464 | 0x7f6954367500 | 0x7f6951426780 | 16560656453357 | 16560656462387 | 16560658161255 | 16560658231003 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 485 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 8 | 24 | 329216 | 0x7f6954367380 | 0x7f69514267c0 | 16560658249273 | 16560658259814 | 16560659925883 | 16560659999550 |
| 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 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 331968 | 0x7f6954367200 | 0x7f6951426800 | 16560660010980 | 16560660038042 | 16560661764270 | 16560661833084 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 491 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 12 | 24 | 334720 | 0x7f6954367080 | 0x7f6951426840 | 16560661844034 | 16560661860909 | 16560663577537 | 16560663650239 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 494 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 8 | 24 | 337472 | 0x7f6951d09f00 | 0x7f6951426880 | 16560663662969 | 16560663677696 | 16560665351925 | 16560665419186 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 497 | 163806 | 163806 | 4194304 | 256 | 0 | 0 | 8 | 24 | 0 | 0x7f6951d09d80 | 0x7f69514268c0 | 16560665428646 | 16560665439124 | 16560668797821 | 16560668875822 |