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 | 149854 | 149854 | 33554432 | 256 | 0 | 0 | 4 | 32 | 4160 | 0x0 | 0x7fc5e4404280 | 16183289169342 | 16183289197144 | 16183289434105 | 16183289492135 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 149854 | 149854 | 32768 | 256 | 0 | 0 | 12 | 24 | 13888 | 0x0 | 0x7fc5e4423f80 | 16183294346368 | 16183294361816 | 16183294370297 | 16183294394017 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 5 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 14336 | 0x7fc5febd0380 | 0x7fc5e4423fc0 | 16183294400107 | 16183294445977 | 16183294537978 | 16183294540374 |
| 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 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15040 | 0x7fc5febd0200 | 0x7fc5e4424000 | 16183294567223 | 16183294576538 | 16183294755419 | 16183294757959 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 11 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15488 | 0x7fc5febd0080 | 0x7fc5e4424040 | 16183294775609 | 16183294784219 | 16183294963260 | 16183294965885 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 14 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 15936 | 0x7fc5f4ccdf00 | 0x7fc5e4424080 | 16183294983494 | 16183294991261 | 16183295083741 | 16183295086132 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 17 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 16384 | 0x7fc5f4ccdd80 | 0x7fc5e44240c0 | 16183295105311 | 16183295115901 | 16183295207742 | 16183295209999 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 20 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 17088 | 0x7fc5f4ccdc00 | 0x7fc5e4424100 | 16183295245008 | 16183295255742 | 16183295347263 | 16183295349506 |
| 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 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 16 | 24 | 17792 | 0x7fc5f4ccda80 | 0x7fc5e4424140 | 16183295368366 | 16183295379423 | 16183295559584 | 16183295561941 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 26 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 16 | 24 | 18496 | 0x7fc5f4ccd900 | 0x7fc5e4424180 | 16183295580241 | 16183295588705 | 16183295770946 | 16183295773187 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 29 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19200 | 0x7fc5f4ccd780 | 0x7fc5e44241c0 | 16183295791276 | 16183295799906 | 16183295892547 | 16183295895084 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 32 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19904 | 0x7fc5f4ccd600 | 0x7fc5e4424200 | 16183295913644 | 16183295924707 | 16183296016547 | 16183296018781 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 35 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 20608 | 0x7fc5febd0480 | 0x7fc5e4424240 | 16183296045971 | 16183296056228 | 16183296148548 | 16183296150638 |
| 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 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 16 | 24 | 21312 | 0x7fc5febd0300 | 0x7fc5e4424280 | 16183296170498 | 16183296180708 | 16183296360390 | 16183296362764 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 41 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22016 | 0x7fc5febd0180 | 0x7fc5e44242c0 | 16183296381833 | 16183296392550 | 16183296574151 | 16183296576399 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 44 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22720 | 0x7fc5febd0000 | 0x7fc5e4424300 | 16183296596898 | 16183296606951 | 16183296699272 | 16183296701596 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 47 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 23424 | 0x7fc5f4ccde80 | 0x7fc5e4424340 | 16183296721366 | 16183296731272 | 16183296823113 | 16183296825313 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 50 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 24128 | 0x7fc5f4ccdd00 | 0x7fc5e4424380 | 16183296849613 | 16183296859753 | 16183296952073 | 16183296954310 |
| 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 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 16 | 24 | 24832 | 0x7fc5f4ccdb80 | 0x7fc5e44243c0 | 16183296973330 | 16183296984554 | 16183297164235 | 16183297166586 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 56 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 16 | 24 | 25536 | 0x7fc5f4ccda00 | 0x7fc5e4424400 | 16183297184735 | 16183297193355 | 16183297373836 | 16183297376141 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 59 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26240 | 0x7fc5f4ccd880 | 0x7fc5e4424440 | 16183297394561 | 16183297403116 | 16183297495437 | 16183297497798 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 62 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26944 | 0x7fc5f4ccd700 | 0x7fc5e4424480 | 16183297516848 | 16183297527597 | 16183297619278 | 16183297621576 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 65 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 27648 | 0x7fc5febd0580 | 0x7fc5e44244c0 | 16183297647525 | 16183297657998 | 16183297749679 | 16183297751973 |
| 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 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 16 | 24 | 28608 | 0x7fc5febd0400 | 0x7fc5e4424500 | 16183297771332 | 16183297781839 | 16183297962800 | 16183297965168 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 71 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 16 | 24 | 29312 | 0x7fc5febd0280 | 0x7fc5e4424540 | 16183297985938 | 16183297995280 | 16183298174961 | 16183298177803 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 74 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 30016 | 0x7fc5febd0100 | 0x7fc5e4424580 | 16183298197433 | 16183298207282 | 16183298299442 | 16183298301761 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 77 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 8 | 24 | 30976 | 0x7fc5f4ccdf80 | 0x7fc5e44245c0 | 16183298319790 | 16183298327922 | 16183298419443 | 16183298421878 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 80 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 31680 | 0x7fc5f4ccde00 | 0x7fc5e4424600 | 16183298447447 | 16183298458003 | 16183298549844 | 16183298552025 |
| 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 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 16 | 24 | 32640 | 0x7fc5f4ccdc80 | 0x7fc5e4424640 | 16183298571675 | 16183298582164 | 16183298761525 | 16183298763650 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 86 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 33600 | 0x7fc5f4ccdb00 | 0x7fc5e4424680 | 16183298782160 | 16183298794166 | 16183298972887 | 16183298975276 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 89 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 34560 | 0x7fc5f4ccd980 | 0x7fc5e44246c0 | 16183298992915 | 16183299001207 | 16183299093527 | 16183299095233 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 92 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 8 | 24 | 35520 | 0x7fc5f4ccd800 | 0x7fc5e4424700 | 16183299112863 | 16183299120728 | 16183299214008 | 16183299215810 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 95 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 36224 | 0x7fc5f4ccd680 | 0x7fc5e4424740 | 16183299240810 | 16183299250169 | 16183299342489 | 16183299344308 |
| 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 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 37184 | 0x7fc5febd0500 | 0x7fc5e4424780 | 16183299362247 | 16183299370169 | 16183299549850 | 16183299551543 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 101 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 38144 | 0x7fc5febd0380 | 0x7fc5e44247c0 | 16183299569643 | 16183299578331 | 16183299756732 | 16183299758648 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 104 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 39104 | 0x7fc5febd0200 | 0x7fc5e4424800 | 16183299776028 | 16183299784092 | 16183299876413 | 16183299878226 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 107 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 8 | 24 | 40320 | 0x7fc5febd0080 | 0x7fc5e4424840 | 16183299897155 | 16183299909693 | 16183300002973 | 16183300004683 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 110 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 41280 | 0x7fc5f4ccdf00 | 0x7fc5e4424880 | 16183300029132 | 16183300039774 | 16183300132734 | 16183300134420 |
| 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 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 42240 | 0x7fc5f4ccdd80 | 0x7fc5e44248c0 | 16183300154120 | 16183300165375 | 16183300344896 | 16183300346655 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 116 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 43200 | 0x7fc5f4ccdc00 | 0x7fc5e4424900 | 16183300366345 | 16183300377536 | 16183300557857 | 16183300559561 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 119 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 8 | 24 | 44160 | 0x7fc5f4ccda80 | 0x7fc5e4424940 | 16183300578930 | 16183300587457 | 16183300679778 | 16183300681408 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 122 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 45376 | 0x7fc5f4ccd900 | 0x7fc5e4424980 | 16183300699937 | 16183300707778 | 16183300801059 | 16183300802755 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 125 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 46336 | 0x7fc5f4ccd780 | 0x7fc5e44249c0 | 16183300828165 | 16183300838179 | 16183300930340 | 16183300931962 |
| 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 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 47552 | 0x7fc5f4ccd600 | 0x7fc5e4424a00 | 16183300951582 | 16183300962500 | 16183301141541 | 16183301143188 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 131 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 48512 | 0x7fc5febd0480 | 0x7fc5e4424a40 | 16183301162347 | 16183301173701 | 16183301353542 | 16183301355133 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 134 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 8 | 24 | 49472 | 0x7fc5febd0300 | 0x7fc5e4424a80 | 16183301373303 | 16183301381383 | 16183301473863 | 16183301475590 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 137 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 50688 | 0x7fc5febd0180 | 0x7fc5e4424ac0 | 16183301494520 | 16183301505863 | 16183301598184 | 16183301599887 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 140 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 51648 | 0x7fc5febd0000 | 0x7fc5e4424b00 | 16183301624567 | 16183301635144 | 16183301726825 | 16183301728555 |
| 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 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 52864 | 0x7fc5f4ccde80 | 0x7fc5e4424b40 | 16183301748224 | 16183301756425 | 16183301934186 | 16183301935870 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 146 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 54080 | 0x7fc5f4ccdd00 | 0x7fc5e4424b80 | 16183301953930 | 16183301961546 | 16183302140427 | 16183302142175 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 149 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 8 | 24 | 55296 | 0x7fc5f4ccdb80 | 0x7fc5e4424bc0 | 16183302159905 | 16183302167948 | 16183302261068 | 16183302262883 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 152 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 56768 | 0x7fc5f4ccda00 | 0x7fc5e4424c00 | 16183302279882 | 16183302287628 | 16183302381069 | 16183302382790 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 155 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 57728 | 0x7fc5f4ccd880 | 0x7fc5e4424c40 | 16183302408460 | 16183302419149 | 16183302511790 | 16183302513557 |
| 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 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 58944 | 0x7fc5f4ccd700 | 0x7fc5e4424c80 | 16183302532967 | 16183302543790 | 16183302724111 | 16183302725813 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 161 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 60160 | 0x7fc5febd0580 | 0x7fc5e4424cc0 | 16183302745682 | 16183302756752 | 16183302936273 | 16183302937998 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 164 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 8 | 24 | 61376 | 0x7fc5febd0400 | 0x7fc5e4424d00 | 16183302956197 | 16183302963953 | 16183303057074 | 16183303058685 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 167 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 62848 | 0x7fc5febd0280 | 0x7fc5e4424d40 | 16183303079245 | 16183303089234 | 16183303187314 | 16183303189042 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 170 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 63808 | 0x7fc5febd0100 | 0x7fc5e4424d80 | 16183303214102 | 16183303224755 | 16183303317555 | 16183303319129 |
| 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 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 65024 | 0x7fc5f4ccdf80 | 0x7fc5e4424dc0 | 16183303338889 | 16183303349555 | 16183303529397 | 16183303531195 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 176 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 66240 | 0x7fc5f4ccde00 | 0x7fc5e4424e00 | 16183303549884 | 16183303562197 | 16183303741558 | 16183303743250 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 179 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 8 | 24 | 67456 | 0x7fc5f4ccdc80 | 0x7fc5e4424e40 | 16183303762210 | 16183303770038 | 16183303862999 | 16183303864767 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 182 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 68928 | 0x7fc5f4ccdb00 | 0x7fc5e4424e80 | 16183303883437 | 16183303891319 | 16183303993720 | 16183303995324 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 185 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 70144 | 0x7fc5f4ccd980 | 0x7fc5e4424ec0 | 16183304019644 | 16183304030200 | 16183304122520 | 16183304124212 |
| 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 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 71616 | 0x7fc5f4ccd800 | 0x7fc5e4424f00 | 16183304142911 | 16183304150841 | 16183304331162 | 16183304332807 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 191 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 72832 | 0x7fc5f4ccd680 | 0x7fc5e4424f40 | 16183304352436 | 16183304361082 | 16183304540443 | 16183304542132 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 194 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 8 | 24 | 74048 | 0x7fc5febd0500 | 0x7fc5e4424f80 | 16183304560872 | 16183304568763 | 16183304661884 | 16183304663470 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 197 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 75776 | 0x7fc5febd0380 | 0x7fc5e4424fc0 | 16183304681489 | 16183304689244 | 16183304795165 | 16183304796857 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 200 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 76992 | 0x7fc5febd0200 | 0x7fc5e4425000 | 16183304821926 | 16183304832445 | 16183304925246 | 16183304926874 |
| 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 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 78464 | 0x7fc5febd0080 | 0x7fc5e4425040 | 16183304946073 | 16183304957406 | 16183305138847 | 16183305140509 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 206 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 79936 | 0x7fc5f4ccdf00 | 0x7fc5e4425080 | 16183305158799 | 16183305166687 | 16183305346689 | 16183305348344 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 209 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 8 | 24 | 81408 | 0x7fc5f4ccdd80 | 0x7fc5e44250c0 | 16183305366454 | 16183305375009 | 16183305468289 | 16183305469892 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 212 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 83136 | 0x7fc5f4ccdc00 | 0x7fc5e4425100 | 16183305489021 | 16183305501250 | 16183305613570 | 16183305615308 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 215 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 84352 | 0x7fc5f4ccda80 | 0x7fc5e4425140 | 16183305654038 | 16183305663491 | 16183305755971 | 16183305757705 |
| 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 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 85824 | 0x7fc5f4ccd900 | 0x7fc5e4425180 | 16183305775505 | 16183305783491 | 16183305963813 | 16183305965761 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 221 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 87296 | 0x7fc5f4ccd780 | 0x7fc5e44251c0 | 16183305984850 | 16183305995973 | 16183306176294 | 16183306178286 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 224 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 88768 | 0x7fc5f4ccd600 | 0x7fc5e4425200 | 16183306198466 | 16183306208934 | 16183306302215 | 16183306304003 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 227 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 90752 | 0x7fc5febd0480 | 0x7fc5e4425240 | 16183306321573 | 16183306330055 | 16183306448136 | 16183306450020 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 230 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 91968 | 0x7fc5febd0300 | 0x7fc5e4425280 | 16183306475129 | 16183306485736 | 16183306578217 | 16183306579827 |
| 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 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 93440 | 0x7fc5febd0180 | 0x7fc5e44252c0 | 16183306598267 | 16183306606057 | 16183306786378 | 16183306788203 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 236 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 94912 | 0x7fc5febd0000 | 0x7fc5e4425300 | 16183306807462 | 16183306818378 | 16183306996779 | 16183306998588 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 239 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 96384 | 0x7fc5f4ccde80 | 0x7fc5e4425340 | 16183307017968 | 16183307025900 | 16183307119500 | 16183307121335 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 242 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 98368 | 0x7fc5f4ccdd00 | 0x7fc5e4425380 | 16183307139065 | 16183307146700 | 16183307270381 | 16183307272152 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 245 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 99584 | 0x7fc5f4ccdb80 | 0x7fc5e44253c0 | 16183307296071 | 16183307306701 | 16183307399502 | 16183307401219 |
| 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 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 101312 | 0x7fc5f4ccda00 | 0x7fc5e4425400 | 16183307419819 | 16183307427822 | 16183307607663 | 16183307609424 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 251 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 102784 | 0x7fc5f4ccd880 | 0x7fc5e4425440 | 16183307626074 | 16183307634064 | 16183307815025 | 16183307816740 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 254 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 104256 | 0x7fc5f4ccd700 | 0x7fc5e4425480 | 16183307834280 | 16183307842065 | 16183307935666 | 16183307937487 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 257 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 106240 | 0x7fc5febd0580 | 0x7fc5e44254c0 | 16183307955407 | 16183307963186 | 16183308092147 | 16183308093824 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 260 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 107712 | 0x7fc5febd0400 | 0x7fc5e4425500 | 16183308118433 | 16183308128787 | 16183308221107 | 16183308222811 |
| 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 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 16 | 24 | 109440 | 0x7fc5febd0280 | 0x7fc5e4425540 | 16183308243391 | 16183308253268 | 16183308431509 | 16183308433116 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 266 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 16 | 24 | 111168 | 0x7fc5febd0100 | 0x7fc5e4425580 | 16183308451826 | 16183308459829 | 16183308638550 | 16183308640292 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 269 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 8 | 24 | 112896 | 0x7fc5f4ccdf80 | 0x7fc5e44255c0 | 16183308659231 | 16183308667190 | 16183308761111 | 16183308762749 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 272 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 115136 | 0x7fc5f4ccde00 | 0x7fc5e4425600 | 16183308780949 | 16183308789111 | 16183308925112 | 16183308926736 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 275 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 116608 | 0x7fc5f4ccdc80 | 0x7fc5e4425640 | 16183308950775 | 16183308961432 | 16183309054713 | 16183309056473 |
| 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 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 16 | 24 | 118336 | 0x7fc5f4ccdb00 | 0x7fc5e4425680 | 16183309074912 | 16183309083193 | 16183309262394 | 16183309264108 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 281 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 16 | 24 | 120064 | 0x7fc5f4ccd980 | 0x7fc5e44256c0 | 16183309283388 | 16183309294554 | 16183309473276 | 16183309474983 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 284 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 121792 | 0x7fc5f4ccd800 | 0x7fc5e4425700 | 16183309493853 | 16183309505276 | 16183309600316 | 16183309602011 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 287 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 124032 | 0x7fc5f4ccd680 | 0x7fc5e4425740 | 16183309622470 | 16183309632317 | 16183309774718 | 16183309776577 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 290 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 125504 | 0x7fc5febd0500 | 0x7fc5e4425780 | 16183309800176 | 16183309811038 | 16183309904958 | 16183309906704 |
| 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 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 127488 | 0x7fc5febd0380 | 0x7fc5e44257c0 | 16183309925964 | 16183309937279 | 16183310115200 | 16183310117239 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 296 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 129216 | 0x7fc5febd0200 | 0x7fc5e4425800 | 16183310135489 | 16183310143360 | 16183310322081 | 16183310323775 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 299 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 130944 | 0x7fc5febd0080 | 0x7fc5e4425840 | 16183310343044 | 16183310354081 | 16183310453442 | 16183310455362 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 302 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 133440 | 0x7fc5f4ccdf00 | 0x7fc5e4425880 | 16183310474951 | 16183310485602 | 16183310639043 | 16183310640668 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 305 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 134912 | 0x7fc5f4ccdd80 | 0x7fc5e44258c0 | 16183310666757 | 16183310677123 | 16183310770724 | 16183310772395 |
| 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 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 136896 | 0x7fc5f4ccdc00 | 0x7fc5e4425900 | 16183310791334 | 16183310803364 | 16183310982085 | 16183310983840 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 311 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 138880 | 0x7fc5f4ccda80 | 0x7fc5e4425940 | 16183311003660 | 16183311013766 | 16183311193767 | 16183311195415 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 314 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 140864 | 0x7fc5f4ccd900 | 0x7fc5e4425980 | 16183311214565 | 16183311225767 | 16183311330408 | 16183311332022 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 317 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 143616 | 0x7fc5f4ccd780 | 0x7fc5e44259c0 | 16183311350502 | 16183311358728 | 16183311525769 | 16183311527558 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 320 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 145344 | 0x7fc5f4ccd600 | 0x7fc5e4425a00 | 16183311552687 | 16183311563209 | 16183311656970 | 16183311658605 |
| 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 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 147584 | 0x7fc5febd0480 | 0x7fc5e4425a40 | 16183311679465 | 16183311689610 | 16183311868651 | 16183311870280 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 326 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 149568 | 0x7fc5febd0300 | 0x7fc5e4425a80 | 16183311888740 | 16183311896651 | 16183312076013 | 16183312077666 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 329 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 151552 | 0x7fc5febd0180 | 0x7fc5e4425ac0 | 16183312095385 | 16183312103213 | 16183312212014 | 16183312213713 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 332 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 154304 | 0x7fc5febd0000 | 0x7fc5e4425b00 | 16183312234072 | 16183312244174 | 16183312423055 | 16183312424778 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 335 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 156288 | 0x7fc5f4ccde80 | 0x7fc5e4425b40 | 16183312451228 | 16183312460815 | 16183312560976 | 16183312562685 |
| 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 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 158784 | 0x7fc5f4ccdd00 | 0x7fc5e4425b80 | 16183312581685 | 16183312589616 | 16183312771377 | 16183312772980 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 341 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 161024 | 0x7fc5f4ccdb80 | 0x7fc5e4425bc0 | 16183312791640 | 16183312799537 | 16183312982899 | 16183312984626 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 344 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 163264 | 0x7fc5f4ccda00 | 0x7fc5e4425c00 | 16183313004375 | 16183313015219 | 16183313136980 | 16183313138752 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 347 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 166528 | 0x7fc5f4ccd880 | 0x7fc5e4425c40 | 16183313157292 | 16183313165780 | 16183313370101 | 16183313386947 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 350 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 168512 | 0x7fc5f4ccd700 | 0x7fc5e4425c80 | 16183313404056 | 16183313414581 | 16183313522742 | 16183313524484 |
| 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 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 171264 | 0x7fc5febd0580 | 0x7fc5e4425cc0 | 16183313543763 | 16183313554742 | 16183313736504 | 16183313738169 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 356 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 173760 | 0x7fc5febd0400 | 0x7fc5e4425d00 | 16183313757569 | 16183313768504 | 16183313951545 | 16183313953244 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 359 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 176256 | 0x7fc5febd0280 | 0x7fc5e4425d40 | 16183313972794 | 16183313980505 | 16183314112986 | 16183314114831 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 362 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 179776 | 0x7fc5febd0100 | 0x7fc5e4425d80 | 16183314135230 | 16183314145466 | 16183314375708 | 16183314415924 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 365 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 182272 | 0x7fc5f4ccdf80 | 0x7fc5e4425dc0 | 16183314433974 | 16183314444028 | 16183314568989 | 16183314570671 |
| 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 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 185536 | 0x7fc5f4ccde00 | 0x7fc5e4425e00 | 16183314589310 | 16183314597149 | 16183314789790 | 16183314791506 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 371 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 188544 | 0x7fc5f4ccdc80 | 0x7fc5e4425e40 | 16183314809875 | 16183314818271 | 16183315014272 | 16183315016011 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 374 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 191552 | 0x7fc5f4ccdb00 | 0x7fc5e4425e80 | 16183315033880 | 16183315042112 | 16183315200193 | 16183315201977 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 377 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 195840 | 0x7fc5f4ccd980 | 0x7fc5e4425ec0 | 16183315219926 | 16183315228033 | 16183315508675 | 16183315546459 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 380 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 198592 | 0x7fc5f4ccd800 | 0x7fc5e4425f00 | 16183315565079 | 16183315575716 | 16183315722437 | 16183315724145 |
| 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 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 202368 | 0x7fc5f4ccd680 | 0x7fc5e4425f40 | 16183315743805 | 16183315751717 | 16183315965638 | 16183316002699 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 386 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 205888 | 0x7fc5febd0500 | 0x7fc5e4425f80 | 16183316013729 | 16183316024359 | 16183316235080 | 16183316272003 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 389 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 209408 | 0x7fc5febd0380 | 0x7fc5e4425fc0 | 16183316283583 | 16183316293640 | 16183316477162 | 16183316478838 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 392 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 214464 | 0x7fc5febd0200 | 0x7fc5e4426000 | 16183316497578 | 16183316505642 | 16183316838284 | 16183316872330 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 395 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 217728 | 0x7fc5febd0080 | 0x7fc5e4426040 | 16183316890169 | 16183316900844 | 16183317065165 | 16183317066755 |
| 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 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 222016 | 0x7fc5f4ccdf00 | 0x7fc5e4426080 | 16183317087005 | 16183317097326 | 16183317327727 | 16183317338509 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 401 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 226048 | 0x7fc5f4ccdd80 | 0x7fc5e44260c0 | 16183317352459 | 16183317362607 | 16183317593009 | 16183317603263 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 404 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 230080 | 0x7fc5f4ccdc00 | 0x7fc5e4426100 | 16183317617003 | 16183317626929 | 16183317836530 | 16183317846988 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 407 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 235904 | 0x7fc5f4ccda80 | 0x7fc5e4426140 | 16183317869867 | 16183317879091 | 16183318262453 | 16183318300598 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 410 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 239424 | 0x7fc5f4ccd900 | 0x7fc5e4426180 | 16183318320087 | 16183318330454 | 16183318514615 | 16183318516393 |
| 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 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 244224 | 0x7fc5f4ccd780 | 0x7fc5e44261c0 | 16183318535623 | 16183318546775 | 16183318799417 | 16183318833416 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 416 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 248768 | 0x7fc5f4ccd600 | 0x7fc5e4426200 | 16183318846606 | 16183318857177 | 16183319103739 | 16183319140489 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 419 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 253312 | 0x7fc5febd0480 | 0x7fc5e4426240 | 16183319153569 | 16183319164059 | 16183319399421 | 16183319436063 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 422 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 8 | 24 | 255552 | 0x7fc5febd0300 | 0x7fc5e4426280 | 16183319449243 | 16183319459261 | 16183319910144 | 16183319944262 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 425 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 259840 | 0x7fc5febd0180 | 0x7fc5e44262c0 | 16183319963851 | 16183319974304 | 16183320197346 | 16183320233855 |
| 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 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 265664 | 0x7fc5febd0000 | 0x7fc5e4426300 | 16183320246015 | 16183320256386 | 16183320555108 | 16183320591567 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 431 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 271232 | 0x7fc5f4ccde80 | 0x7fc5e4426340 | 16183320605847 | 16183320615269 | 16183320914951 | 16183320951210 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 434 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 8 | 24 | 273216 | 0x7fc5f4ccdd00 | 0x7fc5e4426380 | 16183320964029 | 16183320974311 | 16183321269193 | 16183321280182 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 437 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 8 | 24 | 275712 | 0x7fc5f4ccdb80 | 0x7fc5e44263c0 | 16183321293172 | 16183321303113 | 16183321857357 | 16183321867949 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 440 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 280768 | 0x7fc5f4ccda00 | 0x7fc5e4426400 | 16183321888729 | 16183321899117 | 16183322160719 | 16183322199742 |
| 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 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 287616 | 0x7fc5f4ccd880 | 0x7fc5e4426440 | 16183322213812 | 16183322223759 | 16183322574642 | 16183322588503 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 446 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 294208 | 0x7fc5f4ccd700 | 0x7fc5e4426480 | 16183322600253 | 16183322619922 | 16183322970164 | 16183323007734 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 449 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 8 | 24 | 296960 | 0x7fc5febd0580 | 0x7fc5e44264c0 | 16183323020614 | 16183323031285 | 16183323375927 | 16183323412115 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 452 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 8 | 24 | 299968 | 0x7fc5febd0400 | 0x7fc5e4426500 | 16183323420935 | 16183323430967 | 16183324087771 | 16183324122329 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 455 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 8 | 24 | 302720 | 0x7fc5febd0280 | 0x7fc5e4426540 | 16183324141009 | 16183324150332 | 16183324594495 | 16183324628428 |
| 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 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 305472 | 0x7fc5febd0100 | 0x7fc5e4426580 | 16183324642248 | 16183324651935 | 16183325113218 | 16183325147287 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 461 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 308224 | 0x7fc5f4ccdf80 | 0x7fc5e44265c0 | 16183325159016 | 16183325169219 | 16183325627782 | 16183325662105 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 464 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 8 | 24 | 310976 | 0x7fc5f4ccde00 | 0x7fc5e4426600 | 16183325674145 | 16183325684262 | 16183326132265 | 16183326175934 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 467 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 8 | 24 | 313216 | 0x7fc5f4ccdc80 | 0x7fc5e4426640 | 16183326186834 | 16183326196905 | 16183327062511 | 16183327106043 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 470 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 8 | 24 | 315968 | 0x7fc5f4ccdb00 | 0x7fc5e4426680 | 16183327124093 | 16183327134351 | 16183327984437 | 16183328024193 |
| 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 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 318720 | 0x7fc5f4ccd980 | 0x7fc5e44266c0 | 16183328035423 | 16183328045717 | 16183328927963 | 16183328966492 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 476 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 321472 | 0x7fc5f4ccd800 | 0x7fc5e4426700 | 16183328976832 | 16183328986524 | 16183329862209 | 16183329900751 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 479 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 8 | 24 | 324224 | 0x7fc5f4ccd680 | 0x7fc5e4426740 | 16183329911751 | 16183329937570 | 16183330793415 | 16183330834861 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 482 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 8 | 24 | 326464 | 0x7fc5febd0500 | 0x7fc5e4426780 | 16183330845750 | 16183330855336 | 16183332550067 | 16183332591002 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 485 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 8 | 24 | 329216 | 0x7fc5febd0380 | 0x7fc5e44267c0 | 16183332610161 | 16183332620147 | 16183334282878 | 16183334324923 |
| 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 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 331968 | 0x7fc5febd0200 | 0x7fc5e4426800 | 16183334335843 | 16183334345599 | 16183336066730 | 16183336110604 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 491 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 12 | 24 | 334720 | 0x7fc5febd0080 | 0x7fc5e4426840 | 16183336121344 | 16183336131370 | 16183337844182 | 16183337888465 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 494 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 8 | 24 | 337472 | 0x7fc5f4ccdf00 | 0x7fc5e4426880 | 16183337899915 | 16183337910102 | 16183339580673 | 16183339625316 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 497 | 149854 | 149854 | 4194304 | 256 | 0 | 0 | 8 | 24 | 0 | 0x7fc5f4ccdd80 | 0x7fc5e44268c0 | 16183339636776 | 16183339646914 | 16183343001656 | 16183343048840 |