38 KiB
38 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | SQ_INSTS_LDS | SQ_INST_LEVEL_LDS | SQ_ACCUM_PREV_HIRES | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBufferAligned.kd | 0 | 0 | 0 | 202048 | 202048 | 33554432 | 256 | 0 | 0 | 4 | 32 | 4160 | 0x0 | 0x7ff18ec04280 | 0 | 0 | 0 | 17249839171366 | 17249136551505 | 17249986734818 | 17249986848227 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 202048 | 202048 | 32768 | 256 | 0 | 0 | 12 | 24 | 13888 | 0x0 | 0x7ff18ec23f80 | 0 | 0 | 0 | 17249992035347 | 17249986734818 | 17249992162336 | 17249992165533 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 5 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 14336 | 0x7ff191cc5380 | 0x7ff18ec23fc0 | 0 | 0 | 0 | 17249992202162 | 17249992162336 | 17249992490176 | 17249992492374 |
| 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 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15040 | 0x7ff191cc5200 | 0x7ff18ec24000 | 0 | 0 | 0 | 17249992529443 | 17249992490176 | 17249992890816 | 17249992893283 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 11 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15488 | 0x7ff191cc5080 | 0x7ff18ec24040 | 0 | 0 | 0 | 17249992925242 | 17249992890816 | 17249993283296 | 17249993285693 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 14 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 15936 | 0x7ff18f697f00 | 0x7ff18ec24080 | 0 | 0 | 0 | 17249993318942 | 17249993283296 | 17249993592096 | 17249993594354 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 17 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 16384 | 0x7ff18f697d80 | 0x7ff18ec240c0 | 0 | 0 | 0 | 17249993626764 | 17249993592096 | 17249993899296 | 17249993901626 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 20 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 17088 | 0x7ff18f697c00 | 0x7ff18ec24100 | 0 | 0 | 0 | 17249993945465 | 17249993899296 | 17249994219616 | 17249994222037 |
| 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 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 16 | 24 | 17792 | 0x7ff18f697a80 | 0x7ff18ec24140 | 0 | 0 | 0 | 17249994253437 | 17249994219616 | 17249994622656 | 17249994624857 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 26 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 16 | 24 | 18496 | 0x7ff18f697900 | 0x7ff18ec24180 | 0 | 0 | 0 | 17249994656146 | 17249994622656 | 17249995018016 | 17249995020296 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 29 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19200 | 0x7ff18f697780 | 0x7ff18ec241c0 | 0 | 0 | 0 | 17249995050875 | 17249995018016 | 17249995336416 | 17249995338617 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 32 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19904 | 0x7ff18f697600 | 0x7ff18ec24200 | 0 | 0 | 0 | 17249995371007 | 17249995336416 | 17249995641696 | 17249995643839 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 35 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 20608 | 0x7ff191cc5480 | 0x7ff18ec24240 | 0 | 0 | 0 | 17249995684388 | 17249995641696 | 17249995948896 | 17249995951081 |
| 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 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 16 | 24 | 21312 | 0x7ff191cc5300 | 0x7ff18ec24280 | 0 | 0 | 0 | 17249995984580 | 17249995948896 | 17249996340096 | 17249996342321 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 41 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22016 | 0x7ff191cc5180 | 0x7ff18ec242c0 | 0 | 0 | 0 | 17249996375400 | 17249996340096 | 17249996730176 | 17249996732560 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 44 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22720 | 0x7ff191cc5000 | 0x7ff18ec24300 | 0 | 0 | 0 | 17249996765329 | 17249996730176 | 17249997031296 | 17249997033652 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 47 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 23424 | 0x7ff18f697e80 | 0x7ff18ec24340 | 0 | 0 | 0 | 17249997066421 | 17249997031296 | 17249997337696 | 17249997339894 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 50 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 24128 | 0x7ff18f697d00 | 0x7ff18ec24380 | 0 | 0 | 0 | 17249997378473 | 17249997337696 | 17249997638976 | 17249997641146 |
| 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 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 16 | 24 | 24832 | 0x7ff18f697b80 | 0x7ff18ec243c0 | 0 | 0 | 0 | 17249997672505 | 17249997638976 | 17249998031456 | 17249998033625 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 56 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 16 | 24 | 25536 | 0x7ff18f697a00 | 0x7ff18ec24400 | 0 | 0 | 0 | 17249998065784 | 17249998031456 | 17249998447456 | 17249998450024 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 59 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26240 | 0x7ff18f697880 | 0x7ff18ec24440 | 0 | 0 | 0 | 17249998484223 | 17249998447456 | 17249998752096 | 17249998753776 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 62 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26944 | 0x7ff18f697700 | 0x7ff18ec24480 | 0 | 0 | 0 | 17249998785525 | 17249998752096 | 17249999030976 | 17249999032658 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 65 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 27648 | 0x7ff191cc5580 | 0x7ff18ec244c0 | 0 | 0 | 0 | 17249999072127 | 17249999030976 | 17249999307936 | 17249999309711 |
| 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 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 16 | 24 | 28608 | 0x7ff191cc5400 | 0x7ff18ec24500 | 0 | 0 | 0 | 17249999342300 | 17249999307936 | 17249999674816 | 17249999676431 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 71 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 16 | 24 | 29312 | 0x7ff191cc5280 | 0x7ff18ec24540 | 0 | 0 | 0 | 17249999709210 | 17249999674816 | 17250000041376 | 17250000043121 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 74 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 30016 | 0x7ff191cc5100 | 0x7ff18ec24580 | 0 | 0 | 0 | 17250000075610 | 17250000041376 | 17250000318336 | 17250000320053 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 77 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 8 | 24 | 30976 | 0x7ff18f697f80 | 0x7ff18ec245c0 | 0 | 0 | 0 | 17250000352962 | 17250000318336 | 17250000600416 | 17250000602016 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 80 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 31680 | 0x7ff18f697e00 | 0x7ff18ec24600 | 0 | 0 | 0 | 17250000641455 | 17250000600416 | 17250000878336 | 17250000879978 |
| 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 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 16 | 24 | 32640 | 0x7ff18f697c80 | 0x7ff18ec24640 | 0 | 0 | 0 | 17250000911847 | 17250000878336 | 17250001241376 | 17250001243018 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 86 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 33600 | 0x7ff18f697b00 | 0x7ff18ec24680 | 0 | 0 | 0 | 17250001275378 | 17250001241376 | 17250001608096 | 17250001609689 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 89 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 34560 | 0x7ff18f697980 | 0x7ff18ec246c0 | 0 | 0 | 0 | 17250001641878 | 17250001608096 | 17250001890816 | 17250001892581 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 92 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 8 | 24 | 35520 | 0x7ff18f697800 | 0x7ff18ec24700 | 0 | 0 | 0 | 17250001924570 | 17250001890816 | 17250002170176 | 17250002171953 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 95 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 36224 | 0x7ff18f697680 | 0x7ff18ec24740 | 0 | 0 | 0 | 17250002211702 | 17250002170176 | 17250002451776 | 17250002453386 |
| 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 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 37184 | 0x7ff191cc5500 | 0x7ff18ec24780 | 0 | 0 | 0 | 17250002485335 | 17250002451776 | 17250002819296 | 17250002821006 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 101 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 38144 | 0x7ff191cc5380 | 0x7ff18ec247c0 | 0 | 0 | 0 | 17250002853395 | 17250002819296 | 17250003191616 | 17250003193166 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 104 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 39104 | 0x7ff191cc5200 | 0x7ff18ec24800 | 0 | 0 | 0 | 17250003225635 | 17250003191616 | 17250003470016 | 17250003471708 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 107 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 8 | 24 | 40320 | 0x7ff191cc5080 | 0x7ff18ec24840 | 0 | 0 | 0 | 17250003504508 | 17250003470016 | 17250003748416 | 17250003750151 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 110 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 41280 | 0x7ff18f697f00 | 0x7ff18ec24880 | 0 | 0 | 0 | 17250003790240 | 17250003748416 | 17250004027616 | 17250004029204 |
| 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 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 42240 | 0x7ff18f697d80 | 0x7ff18ec248c0 | 0 | 0 | 0 | 17250004060783 | 17250004027616 | 17250004393376 | 17250004395214 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 116 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 43200 | 0x7ff18f697c00 | 0x7ff18ec24900 | 0 | 0 | 0 | 17250004427603 | 17250004393376 | 17250004762656 | 17250004764364 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 119 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 8 | 24 | 44160 | 0x7ff18f697a80 | 0x7ff18ec24940 | 0 | 0 | 0 | 17250004795883 | 17250004762656 | 17250005042335 | 17250005043946 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 122 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 45376 | 0x7ff18f697900 | 0x7ff18ec24980 | 0 | 0 | 0 | 17250005076675 | 17250005042335 | 17250005337855 | 17250005339478 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 125 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 46336 | 0x7ff18f697780 | 0x7ff18ec249c0 | 0 | 0 | 0 | 17250005378017 | 17250005337855 | 17250005618335 | 17250005620071 |
| 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 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 47552 | 0x7ff18f697600 | 0x7ff18ec24a00 | 0 | 0 | 0 | 17250005651960 | 17250005618335 | 17250005981375 | 17250005982891 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 131 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 48512 | 0x7ff191cc5480 | 0x7ff18ec24a40 | 0 | 0 | 0 | 17250006015180 | 17250005981375 | 17250006356095 | 17250006357801 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 134 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 8 | 24 | 49472 | 0x7ff191cc5300 | 0x7ff18ec24a80 | 0 | 0 | 0 | 17250006390150 | 17250006356095 | 17250006636415 | 17250006638083 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 137 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 50688 | 0x7ff191cc5180 | 0x7ff18ec24ac0 | 0 | 0 | 0 | 17250006670163 | 17250006636415 | 17250006915295 | 17250006916826 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 140 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 51648 | 0x7ff191cc5000 | 0x7ff18ec24b00 | 0 | 0 | 0 | 17250006956305 | 17250006915295 | 17250007192095 | 17250007193868 |
| 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 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 52864 | 0x7ff18f697e80 | 0x7ff18ec24b40 | 0 | 0 | 0 | 17250007225608 | 17250007192095 | 17250007560255 | 17250007561868 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 146 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 54080 | 0x7ff18f697d00 | 0x7ff18ec24b80 | 0 | 0 | 0 | 17250007593328 | 17250007560255 | 17250007930335 | 17250007931788 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 149 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 8 | 24 | 55296 | 0x7ff18f697b80 | 0x7ff18ec24bc0 | 0 | 0 | 0 | 17250007962958 | 17250007930335 | 17250008210175 | 17250008211931 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 152 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 56768 | 0x7ff18f697a00 | 0x7ff18ec24c00 | 0 | 0 | 0 | 17250008243900 | 17250008210175 | 17250008490175 | 17250008491643 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 155 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 57728 | 0x7ff18f697880 | 0x7ff18ec24c40 | 0 | 0 | 0 | 17250008529862 | 17250008490175 | 17250008767295 | 17250008768846 |
| 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 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 58944 | 0x7ff18f697700 | 0x7ff18ec24c80 | 0 | 0 | 0 | 17250008801015 | 17250008767295 | 17250009133535 | 17250009135316 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 161 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 60160 | 0x7ff191cc5580 | 0x7ff18ec24cc0 | 0 | 0 | 0 | 17250009167525 | 17250009133535 | 17250009497215 | 17250009498826 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 164 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 8 | 24 | 61376 | 0x7ff191cc5400 | 0x7ff18ec24d00 | 0 | 0 | 0 | 17250009530285 | 17250009497215 | 17250009774495 | 17250009776119 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 167 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 62848 | 0x7ff191cc5280 | 0x7ff18ec24d40 | 0 | 0 | 0 | 17250009807728 | 17250009774495 | 17250010056095 | 17250010057781 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 170 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 63808 | 0x7ff191cc5100 | 0x7ff18ec24d80 | 0 | 0 | 0 | 17250010101420 | 17250010056095 | 17250010349855 | 17250010351743 |
| 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 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 65024 | 0x7ff18f697f80 | 0x7ff18ec24dc0 | 0 | 0 | 0 | 17250010383852 | 17250010349855 | 17250010719135 | 17250010720863 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 176 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 66240 | 0x7ff18f697e00 | 0x7ff18ec24e00 | 0 | 0 | 0 | 17250010753092 | 17250010719135 | 17250011085695 | 17250011087233 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 179 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 8 | 24 | 67456 | 0x7ff18f697c80 | 0x7ff18ec24e40 | 0 | 0 | 0 | 17250011118952 | 17250011085695 | 17250011364895 | 17250011366506 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 182 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 68928 | 0x7ff18f697b00 | 0x7ff18ec24e80 | 0 | 0 | 0 | 17250011399495 | 17250011364895 | 17250011654815 | 17250011656398 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 185 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 70144 | 0x7ff18f697980 | 0x7ff18ec24ec0 | 0 | 0 | 0 | 17250011696437 | 17250011654815 | 17250011933375 | 17250011934980 |
| 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 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 71616 | 0x7ff18f697800 | 0x7ff18ec24f00 | 0 | 0 | 0 | 17250011966369 | 17250011933375 | 17250012302175 | 17250012303850 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 191 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 72832 | 0x7ff18f697680 | 0x7ff18ec24f40 | 0 | 0 | 0 | 17250012335749 | 17250012302175 | 17250012672255 | 17250012673930 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 194 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 8 | 24 | 74048 | 0x7ff191cc5500 | 0x7ff18ec24f80 | 0 | 0 | 0 | 17250012706059 | 17250012672255 | 17250012951775 | 17250012953383 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 197 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 75776 | 0x7ff191cc5380 | 0x7ff18ec24fc0 | 0 | 0 | 0 | 17250012985682 | 17250012951775 | 17250013246175 | 17250013247735 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 200 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 76992 | 0x7ff191cc5200 | 0x7ff18ec25000 | 0 | 0 | 0 | 17250013287404 | 17250013246175 | 17250013525855 | 17250013527607 |
| 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 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 78464 | 0x7ff191cc5080 | 0x7ff18ec25040 | 0 | 0 | 0 | 17250013559916 | 17250013525855 | 17250013894495 | 17250013896277 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 206 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 79936 | 0x7ff18f697f00 | 0x7ff18ec25080 | 0 | 0 | 0 | 17250013928766 | 17250013894495 | 17250014259935 | 17250014261747 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 209 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 8 | 24 | 81408 | 0x7ff18f697d80 | 0x7ff18ec250c0 | 0 | 0 | 0 | 17250014294877 | 17250014259935 | 17250014546815 | 17250014548540 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 212 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 83136 | 0x7ff18f697c00 | 0x7ff18ec25100 | 0 | 0 | 0 | 17250014579829 | 17250014546815 | 17250014845535 | 17250014847142 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 215 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 84352 | 0x7ff18f697a80 | 0x7ff18ec25140 | 0 | 0 | 0 | 17250014896760 | 17250014845535 | 17250015126495 | 17250015128384 |
| 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 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 85824 | 0x7ff18f697900 | 0x7ff18ec25180 | 0 | 0 | 0 | 17250015159803 | 17250015126495 | 17250015490655 | 17250015492484 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 221 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 87296 | 0x7ff18f697780 | 0x7ff18ec251c0 | 0 | 0 | 0 | 17250015524194 | 17250015490655 | 17250015853535 | 17250015855125 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 224 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 88768 | 0x7ff18f697600 | 0x7ff18ec25200 | 0 | 0 | 0 | 17250015886674 | 17250015853535 | 17250016132735 | 17250016134397 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 227 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 90752 | 0x7ff191cc5480 | 0x7ff18ec25240 | 0 | 0 | 0 | 17250016166106 | 17250016132735 | 17250016434495 | 17250016436389 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 230 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 91968 | 0x7ff191cc5300 | 0x7ff18ec25280 | 0 | 0 | 0 | 17250016474598 | 17250016434495 | 17250016717855 | 17250016719451 |
| 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 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 93440 | 0x7ff191cc5180 | 0x7ff18ec252c0 | 0 | 0 | 0 | 17250016750651 | 17250016717855 | 17250017083295 | 17250017084962 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 236 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 94912 | 0x7ff191cc5000 | 0x7ff18ec25300 | 0 | 0 | 0 | 17250017116261 | 17250017083295 | 17250017446015 | 17250017447732 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 239 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 96384 | 0x7ff18f697e80 | 0x7ff18ec25340 | 0 | 0 | 0 | 17250017478501 | 17250017446015 | 17250017726655 | 17250017728224 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 242 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 98368 | 0x7ff18f697d00 | 0x7ff18ec25380 | 0 | 0 | 0 | 17250017759794 | 17250017726655 | 17250018036255 | 17250018037846 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 245 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 99584 | 0x7ff18f697b80 | 0x7ff18ec253c0 | 0 | 0 | 0 | 17250018084125 | 17250018036255 | 17250018316575 | 17250018318209 |
| 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 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 101312 | 0x7ff18f697a00 | 0x7ff18ec25400 | 0 | 0 | 0 | 17250018349828 | 17250018316575 | 17250018687295 | 17250018688969 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 251 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 102784 | 0x7ff18f697880 | 0x7ff18ec25440 | 0 | 0 | 0 | 17250018720298 | 17250018687295 | 17250019051935 | 17250019053609 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 254 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 104256 | 0x7ff18f697700 | 0x7ff18ec25480 | 0 | 0 | 0 | 17250019085488 | 17250019051935 | 17250019332415 | 17250019333961 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 257 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 106240 | 0x7ff191cc5580 | 0x7ff18ec254c0 | 0 | 0 | 0 | 17250019365160 | 17250019332415 | 17250019646975 | 17250019648723 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 260 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 107712 | 0x7ff191cc5400 | 0x7ff18ec25500 | 0 | 0 | 0 | 17250019688752 | 17250019646975 | 17250019934495 | 17250019936085 |
| 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 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 16 | 24 | 109440 | 0x7ff191cc5280 | 0x7ff18ec25540 | 0 | 0 | 0 | 17250019968774 | 17250019934495 | 17250020298655 | 17250020300345 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 266 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 16 | 24 | 111168 | 0x7ff191cc5100 | 0x7ff18ec25580 | 0 | 0 | 0 | 17250020331954 | 17250020298655 | 17250020663935 | 17250020665595 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 269 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 8 | 24 | 112896 | 0x7ff18f697f80 | 0x7ff18ec255c0 | 0 | 0 | 0 | 17250020697724 | 17250020663935 | 17250020945215 | 17250020946938 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 272 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 115136 | 0x7ff18f697e00 | 0x7ff18ec25600 | 0 | 0 | 0 | 17250020979117 | 17250020945215 | 17250021271135 | 17250021272729 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 275 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 116608 | 0x7ff18f697c80 | 0x7ff18ec25640 | 0 | 0 | 0 | 17250021311788 | 17250021271135 | 17250021549535 | 17250021551161 |
| 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 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 16 | 24 | 118336 | 0x7ff18f697b00 | 0x7ff18ec25680 | 0 | 0 | 0 | 17250021582920 | 17250021549535 | 17250021914495 | 17250021916101 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 281 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 16 | 24 | 120064 | 0x7ff18f697980 | 0x7ff18ec256c0 | 0 | 0 | 0 | 17250021947220 | 17250021914495 | 17250022285375 | 17250022287171 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 284 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 121792 | 0x7ff18f697800 | 0x7ff18ec25700 | 0 | 0 | 0 | 17250022319060 | 17250022285375 | 17250022580095 | 17250022581813 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 287 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 124032 | 0x7ff18f697680 | 0x7ff18ec25740 | 0 | 0 | 0 | 17250022614103 | 17250022580095 | 17250022913215 | 17250022914864 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 290 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 125504 | 0x7ff191cc5500 | 0x7ff18ec25780 | 0 | 0 | 0 | 17250022954783 | 17250022913215 | 17250023191614 | 17250023193277 |
| 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 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 127488 | 0x7ff191cc5380 | 0x7ff18ec257c0 | 0 | 0 | 0 | 17250023225146 | 17250023191614 | 17250023556254 | 17250023557967 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 296 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 129216 | 0x7ff191cc5200 | 0x7ff18ec25800 | 0 | 0 | 0 | 17250023589986 | 17250023556254 | 17250023921854 | 17250023923477 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 299 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 130944 | 0x7ff191cc5080 | 0x7ff18ec25840 | 0 | 0 | 0 | 17250023954797 | 17250023921854 | 17250024207294 | 17250024208840 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 302 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 133440 | 0x7ff18f697f00 | 0x7ff18ec25880 | 0 | 0 | 0 | 17250024241219 | 17250024207294 | 17250024551614 | 17250024553261 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 305 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 134912 | 0x7ff18f697d80 | 0x7ff18ec258c0 | 0 | 0 | 0 | 17250024592319 | 17250024551614 | 17250024830014 | 17250024831703 |
| 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 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 136896 | 0x7ff18f697c00 | 0x7ff18ec25900 | 0 | 0 | 0 | 17250024863352 | 17250024830014 | 17250025201534 | 17250025203253 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 311 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 138880 | 0x7ff18f697a80 | 0x7ff18ec25940 | 0 | 0 | 0 | 17250025235412 | 17250025201534 | 17250025565054 | 17250025566733 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 314 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 140864 | 0x7ff18f697900 | 0x7ff18ec25980 | 0 | 0 | 0 | 17250025597652 | 17250025565054 | 17250025855294 | 17250025856936 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 317 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 143616 | 0x7ff18f697780 | 0x7ff18ec259c0 | 0 | 0 | 0 | 17250025887595 | 17250025855294 | 17250026214494 | 17250026216556 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 320 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 145344 | 0x7ff18f697600 | 0x7ff18ec25a00 | 0 | 0 | 0 | 17250026256775 | 17250026214494 | 17250026506334 | 17250026507828 |
| 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 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 147584 | 0x7ff191cc5480 | 0x7ff18ec25a40 | 0 | 0 | 0 | 17250026539807 | 17250026506334 | 17250026873214 | 17250026874788 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 326 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 149568 | 0x7ff191cc5300 | 0x7ff18ec25a80 | 0 | 0 | 0 | 17250026907227 | 17250026873214 | 17250027240094 | 17250027241838 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 329 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 151552 | 0x7ff191cc5180 | 0x7ff18ec25ac0 | 0 | 0 | 0 | 17250027273827 | 17250027240094 | 17250027535774 | 17250027537420 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 332 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 154304 | 0x7ff191cc5000 | 0x7ff18ec25b00 | 0 | 0 | 0 | 17250027569779 | 17250027535774 | 17250027901694 | 17250027903350 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 335 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 156288 | 0x7ff18f697e80 | 0x7ff18ec25b40 | 0 | 0 | 0 | 17250027941739 | 17250027901694 | 17250028187614 | 17250028189313 |
| 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 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 158784 | 0x7ff18f697d00 | 0x7ff18ec25b80 | 0 | 0 | 0 | 17250028221292 | 17250028187614 | 17250028557054 | 17250028558593 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 341 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 161024 | 0x7ff18f697b80 | 0x7ff18ec25bc0 | 0 | 0 | 0 | 17250028590722 | 17250028557054 | 17250028925854 | 17250028927573 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 344 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 163264 | 0x7ff18f697a00 | 0x7ff18ec25c00 | 0 | 0 | 0 | 17250028959012 | 17250028925854 | 17250029236574 | 17250029238184 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 347 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 166528 | 0x7ff18f697880 | 0x7ff18ec25c40 | 0 | 0 | 0 | 17250029268973 | 17250029236574 | 17250029633054 | 17250029652533 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 350 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 168512 | 0x7ff18f697700 | 0x7ff18ec25c80 | 0 | 0 | 0 | 17250029673472 | 17250029633054 | 17250029936894 | 17250029938475 |
| 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 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 171264 | 0x7ff191cc5580 | 0x7ff18ec25cc0 | 0 | 0 | 0 | 17250029970014 | 17250029936894 | 17250030314654 | 17250030316675 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 356 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 173760 | 0x7ff191cc5400 | 0x7ff18ec25d00 | 0 | 0 | 0 | 17250030349674 | 17250030314654 | 17250030686334 | 17250030687945 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 359 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 176256 | 0x7ff191cc5280 | 0x7ff18ec25d40 | 0 | 0 | 0 | 17250030719524 | 17250030686334 | 17250031006654 | 17250031008336 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 362 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 179776 | 0x7ff191cc5100 | 0x7ff18ec25d80 | 0 | 0 | 0 | 17250031039776 | 17250031006654 | 17250031422814 | 17250031467844 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 365 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 182272 | 0x7ff18f697f80 | 0x7ff18ec25dc0 | 0 | 0 | 0 | 17250031486953 | 17250031422814 | 17250031773534 | 17250031775126 |
| 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 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 185536 | 0x7ff18f697e00 | 0x7ff18ec25e00 | 0 | 0 | 0 | 17250031806945 | 17250031773534 | 17250032149214 | 17250032193484 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 371 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 188544 | 0x7ff18f697c80 | 0x7ff18ec25e40 | 0 | 0 | 0 | 17250032205894 | 17250032149214 | 17250032559294 | 17250032580324 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 374 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 191552 | 0x7ff18f697b00 | 0x7ff18ec25e80 | 0 | 0 | 0 | 17250032592394 | 17250032559294 | 17250032921054 | 17250032922615 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 377 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 195840 | 0x7ff18f697980 | 0x7ff18ec25ec0 | 0 | 0 | 0 | 17250032953794 | 17250032921054 | 17250033390334 | 17250033407822 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 380 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 198592 | 0x7ff18f697800 | 0x7ff18ec25f00 | 0 | 0 | 0 | 17250033430201 | 17250033390334 | 17250033725534 | 17250033727103 |
| 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 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 202368 | 0x7ff18f697680 | 0x7ff18ec25f40 | 0 | 0 | 0 | 17250033757882 | 17250033725534 | 17250034120574 | 17250034142802 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 386 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 205888 | 0x7ff191cc5500 | 0x7ff18ec25f80 | 0 | 0 | 0 | 17250034155271 | 17250034120574 | 17250034525374 | 17250034544491 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 389 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 209408 | 0x7ff191cc5380 | 0x7ff18ec25fc0 | 0 | 0 | 0 | 17250034558791 | 17250034525374 | 17250034900734 | 17250034902381 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 392 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 214464 | 0x7ff191cc5200 | 0x7ff18ec26000 | 0 | 0 | 0 | 17250034934360 | 17250034900734 | 17250035418814 | 17250035436097 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 395 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 217728 | 0x7ff191cc5080 | 0x7ff18ec26040 | 0 | 0 | 0 | 17250035459876 | 17250035418814 | 17250035779614 | 17250035781328 |
| 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 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 222016 | 0x7ff18f697f00 | 0x7ff18ec26080 | 0 | 0 | 0 | 17250035812857 | 17250035779614 | 17250036195294 | 17250036212556 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 401 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 226048 | 0x7ff18f697d80 | 0x7ff18ec260c0 | 0 | 0 | 0 | 17250036228766 | 17250036195294 | 17250036619454 | 17250036636225 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 404 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 230080 | 0x7ff18f697c00 | 0x7ff18ec26100 | 0 | 0 | 0 | 17250036652734 | 17250036619454 | 17250037019454 | 17250037036564 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 407 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 235904 | 0x7ff18f697a80 | 0x7ff18ec26140 | 0 | 0 | 0 | 17250037053704 | 17250037019454 | 17250037591774 | 17250037608549 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 410 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 239424 | 0x7ff18f697900 | 0x7ff18ec26180 | 0 | 0 | 0 | 17250037632138 | 17250037591774 | 17250037970174 | 17250037971779 |
| 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 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 244224 | 0x7ff18f697780 | 0x7ff18ec261c0 | 0 | 0 | 0 | 17250038003048 | 17250037970174 | 17250038413854 | 17250038437536 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 416 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 248768 | 0x7ff18f697600 | 0x7ff18ec26200 | 0 | 0 | 0 | 17250038449936 | 17250038413854 | 17250038858174 | 17250038899884 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 419 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 253312 | 0x7ff191cc5480 | 0x7ff18ec26240 | 0 | 0 | 0 | 17250038912234 | 17250038858174 | 17250039306814 | 17250039348802 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 422 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 8 | 24 | 255552 | 0x7ff191cc5300 | 0x7ff18ec26280 | 0 | 0 | 0 | 17250039360151 | 17250039306814 | 17250039972254 | 17250040014014 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 425 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 259840 | 0x7ff191cc5180 | 0x7ff18ec262c0 | 0 | 0 | 0 | 17250040033743 | 17250039972254 | 17250040410174 | 17250040451192 |
| 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 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 265664 | 0x7ff191cc5000 | 0x7ff18ec26300 | 0 | 0 | 0 | 17250040463092 | 17250040410174 | 17250040921534 | 17250040939109 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 431 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 271232 | 0x7ff18f697e80 | 0x7ff18ec26340 | 0 | 0 | 0 | 17250040955688 | 17250040921534 | 17250041414493 | 17250041432345 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 434 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 8 | 24 | 273216 | 0x7ff18f697d00 | 0x7ff18ec26380 | 0 | 0 | 0 | 17250041446965 | 17250041414493 | 17250041898653 | 17250041915732 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 437 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 8 | 24 | 275712 | 0x7ff18f697b80 | 0x7ff18ec263c0 | 0 | 0 | 0 | 17250041932422 | 17250041898653 | 17250042638493 | 17250042658702 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 440 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 280768 | 0x7ff18f697a00 | 0x7ff18ec26400 | 0 | 0 | 0 | 17250042680402 | 17250042638493 | 17250043099933 | 17250043116590 |
| 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 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 287616 | 0x7ff18f697880 | 0x7ff18ec26440 | 0 | 0 | 0 | 17250043133570 | 17250043099933 | 17250043638013 | 17250043655575 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 446 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 294208 | 0x7ff18f697700 | 0x7ff18ec26480 | 0 | 0 | 0 | 17250043673655 | 17250043638013 | 17250044174333 | 17250044190921 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 449 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 8 | 24 | 296960 | 0x7ff191cc5580 | 0x7ff18ec264c0 | 0 | 0 | 0 | 17250044208160 | 17250044174333 | 17250044708573 | 17250044725657 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 452 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 8 | 24 | 299968 | 0x7ff191cc5400 | 0x7ff18ec26500 | 0 | 0 | 0 | 17250044742886 | 17250044708573 | 17250045554653 | 17250045571234 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 455 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 8 | 24 | 302720 | 0x7ff191cc5280 | 0x7ff18ec26540 | 0 | 0 | 0 | 17250045596103 | 17250045554653 | 17250046189533 | 17250046207366 |
| 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 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 305472 | 0x7ff191cc5100 | 0x7ff18ec26580 | 0 | 0 | 0 | 17250046224526 | 17250046189533 | 17250046845533 | 17250046887638 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 461 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 308224 | 0x7ff18f697f80 | 0x7ff18ec265c0 | 0 | 0 | 0 | 17250046898758 | 17250046845533 | 17250047524413 | 17250047565400 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 464 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 8 | 24 | 310976 | 0x7ff18f697e00 | 0x7ff18ec26600 | 0 | 0 | 0 | 17250047576870 | 17250047524413 | 17250048188573 | 17250048229422 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 467 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 8 | 24 | 313216 | 0x7ff18f697c80 | 0x7ff18ec26640 | 0 | 0 | 0 | 17250048241772 | 17250048188573 | 17250049274973 | 17250049293424 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 470 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 8 | 24 | 315968 | 0x7ff18f697b00 | 0x7ff18ec26680 | 0 | 0 | 0 | 17250049316833 | 17250049274646 | 17250050317046 | 17250050366595 |
| 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 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 318720 | 0x7ff18f697980 | 0x7ff18ec266c0 | 0 | 0 | 0 | 17250050378434 | 17250050317046 | 17250051428724 | 17250051494854 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 476 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 321472 | 0x7ff18f697800 | 0x7ff18ec26700 | 0 | 0 | 0 | 17250051508774 | 17250051428724 | 17250052565523 | 17250052630134 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 479 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 8 | 24 | 324224 | 0x7ff18f697680 | 0x7ff18ec26740 | 0 | 0 | 0 | 17250052642423 | 17250052565523 | 17250053675442 | 17250053739184 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 482 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 8 | 24 | 326464 | 0x7ff191cc5500 | 0x7ff18ec26780 | 0 | 0 | 0 | 17250053751213 | 17250053675442 | 17250055621521 | 17250055669142 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 485 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 8 | 24 | 329216 | 0x7ff191cc5380 | 0x7ff18ec267c0 | 0 | 0 | 0 | 17250055689131 | 17250055621521 | 17250057523920 | 17250057565091 |
| 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 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 331968 | 0x7ff191cc5200 | 0x7ff18ec26800 | 0 | 0 | 0 | 17250057576921 | 17250057523920 | 17250059480878 | 17250059554457 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 491 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 12 | 24 | 334720 | 0x7ff191cc5080 | 0x7ff18ec26840 | 0 | 0 | 0 | 17250059567397 | 17250059480878 | 17250061463757 | 17250061506085 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 494 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 8 | 24 | 337472 | 0x7ff18f697f00 | 0x7ff18ec26880 | 0 | 0 | 0 | 17250061518804 | 17250061463757 | 17250063371595 | 17250063418413 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 497 | 202048 | 202048 | 4194304 | 256 | 0 | 0 | 8 | 24 | 0 | 0x7ff18f697d80 | 0x7ff18ec268c0 | 0 | 0 | 0 | 17250063432183 | 17250063371595 | 17250066969673 | 17250067038855 |