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 | 179735 | 179735 | 33554432 | 256 | 0 | 0 | 4 | 32 | 4160 | 0x0 | 0x7f657d204280 | 16860531235832 | 16860531261993 | 16860531499752 | 16860531588771 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 179735 | 179735 | 32768 | 256 | 0 | 0 | 12 | 24 | 13888 | 0x0 | 0x7f657d223f80 | 16860536306988 | 16860536322773 | 16860536336053 | 16860536353576 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 5 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 14336 | 0x7f65802d0380 | 0x7f657d223fc0 | 16860536359256 | 16860536405493 | 16860536497973 | 16860536500272 |
| 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 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15040 | 0x7f65802d0200 | 0x7f657d224000 | 16860536522261 | 16860536532533 | 16860536713012 | 16860536715175 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 11 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15488 | 0x7f65802d0080 | 0x7f657d224040 | 16860536730065 | 16860536738292 | 16860536916371 | 16860536918359 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 14 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 15936 | 0x7f657dc31f00 | 0x7f657d224080 | 16860536933059 | 16860536941491 | 16860537035571 | 16860537037765 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 17 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 16384 | 0x7f657dc31d80 | 0x7f657d2240c0 | 16860537053695 | 16860537061651 | 16860537153490 | 16860537155522 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 20 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 17088 | 0x7f657dc31c00 | 0x7f657d224100 | 16860537182701 | 16860537193650 | 16860537285970 | 16860537288028 |
| 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 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 16 | 24 | 17792 | 0x7f657dc31a80 | 0x7f657d224140 | 16860537306357 | 16860537314770 | 16860537494449 | 16860537496462 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 26 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 16 | 24 | 18496 | 0x7f657dc31900 | 0x7f657d224180 | 16860537515961 | 16860537526449 | 16860537706928 | 16860537709235 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 29 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19200 | 0x7f657dc31780 | 0x7f657d2241c0 | 16860537726805 | 16860537735088 | 16860537828688 | 16860537830901 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 32 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19904 | 0x7f657dc31600 | 0x7f657d224200 | 16860537850161 | 16860537867408 | 16860537960688 | 16860537962857 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 35 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 20608 | 0x7f65802d0480 | 0x7f657d224240 | 16860537985517 | 16860537994767 | 16860538087247 | 16860538089324 |
| 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 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 16 | 24 | 21312 | 0x7f65802d0300 | 0x7f657d224280 | 16860538108913 | 16860538119407 | 16860538298446 | 16860538300467 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 41 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22016 | 0x7f65802d0180 | 0x7f657d2242c0 | 16860538316037 | 16860538325486 | 16860538505966 | 16860538508051 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 44 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22720 | 0x7f65802d0000 | 0x7f657d224300 | 16860538531320 | 16860538541805 | 16860538635245 | 16860538637247 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 47 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 23424 | 0x7f657dc31e80 | 0x7f657d224340 | 16860538661656 | 16860538671405 | 16860538764525 | 16860538766603 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 50 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 24128 | 0x7f657dc31d00 | 0x7f657d224380 | 16860538788372 | 16860538798924 | 16860538892364 | 16860538894489 |
| 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 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 16 | 24 | 24832 | 0x7f657dc31b80 | 0x7f657d2243c0 | 16860538913878 | 16860538924204 | 16860539102923 | 16860539104903 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 56 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 16 | 24 | 25536 | 0x7f657dc31a00 | 0x7f657d224400 | 16860539121782 | 16860539135723 | 16860539317003 | 16860539319136 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 59 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26240 | 0x7f657dc31880 | 0x7f657d224440 | 16860539339515 | 16860539349323 | 16860539442922 | 16860539444952 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 62 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26944 | 0x7f657dc31700 | 0x7f657d224480 | 16860539466012 | 16860539476362 | 16860539569802 | 16860539571838 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 65 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 27648 | 0x7f65802d0580 | 0x7f657d2244c0 | 16860539593208 | 16860539603402 | 16860539695561 | 16860539697604 |
| 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 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 16 | 24 | 28608 | 0x7f65802d0400 | 0x7f657d224500 | 16860539715444 | 16860539744841 | 16860539925320 | 16860539927667 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 71 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 16 | 24 | 29312 | 0x7f65802d0280 | 0x7f657d224540 | 16860539941847 | 16860539959560 | 16860540138920 | 16860540141011 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 74 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 30016 | 0x7f65802d0100 | 0x7f657d224580 | 16860540158550 | 16860540183879 | 16860540276199 | 16860540278297 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 77 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 8 | 24 | 30976 | 0x7f657dc31f80 | 0x7f657d2245c0 | 16860540297676 | 16860540308199 | 16860540400039 | 16860540402163 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 80 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 31680 | 0x7f657dc31e00 | 0x7f657d224600 | 16860540424022 | 16860540433959 | 16860540527078 | 16860540529059 |
| 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 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 16 | 24 | 32640 | 0x7f657dc31c80 | 0x7f657d224640 | 16860540545919 | 16860540555558 | 16860540735558 | 16860540737143 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 86 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 33600 | 0x7f657dc31b00 | 0x7f657d224680 | 16860540751662 | 16860540759877 | 16860540940357 | 16860540941877 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 89 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 34560 | 0x7f657dc31980 | 0x7f657d2246c0 | 16860540956116 | 16860540964357 | 16860541057156 | 16860541058813 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 92 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 8 | 24 | 35520 | 0x7f657dc31800 | 0x7f657d224700 | 16860541075242 | 16860541083236 | 16860541177156 | 16860541178649 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 95 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 36224 | 0x7f657dc31680 | 0x7f657d224740 | 16860541200419 | 16860541209796 | 16860541302595 | 16860541304215 |
| 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 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 37184 | 0x7f65802d0500 | 0x7f657d224780 | 16860541318685 | 16860541326595 | 16860541507235 | 16860541508719 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 101 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 38144 | 0x7f65802d0380 | 0x7f657d2247c0 | 16860541524649 | 16860541533795 | 16860541714434 | 16860541715933 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 104 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 39104 | 0x7f65802d0200 | 0x7f657d224800 | 16860541732242 | 16860541740354 | 16860541833954 | 16860541835649 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 107 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 8 | 24 | 40320 | 0x7f65802d0080 | 0x7f657d224840 | 16860541851059 | 16860541859073 | 16860541953153 | 16860541954676 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 110 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 41280 | 0x7f657dc31f00 | 0x7f657d224880 | 16860541976285 | 16860541986273 | 16860542079713 | 16860542081272 |
| 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 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 42240 | 0x7f657dc31d80 | 0x7f657d2248c0 | 16860542097101 | 16860542105473 | 16860542283872 | 16860542285455 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 116 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 43200 | 0x7f657dc31c00 | 0x7f657d224900 | 16860542301395 | 16860542309632 | 16860542490271 | 16860542491789 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 119 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 8 | 24 | 44160 | 0x7f657dc31a80 | 0x7f657d224940 | 16860542509009 | 16860542517311 | 16860542610591 | 16860542612106 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 122 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 45376 | 0x7f657dc31900 | 0x7f657d224980 | 16860542626435 | 16860542634751 | 16860542728990 | 16860542730532 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 125 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 46336 | 0x7f657dc31780 | 0x7f657d2249c0 | 16860542750181 | 16860542760830 | 16860542854910 | 16860542856378 |
| 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 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 47552 | 0x7f657dc31600 | 0x7f657d224a00 | 16860542871038 | 16860542879070 | 16860543058749 | 16860543060272 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 131 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 48512 | 0x7f65802d0480 | 0x7f657d224a40 | 16860543074571 | 16860543082909 | 16860543261948 | 16860543263606 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 134 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 8 | 24 | 49472 | 0x7f65802d0300 | 0x7f657d224a80 | 16860543277775 | 16860543285948 | 16860543378588 | 16860543380052 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 137 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 50688 | 0x7f65802d0180 | 0x7f657d224ac0 | 16860543396882 | 16860543405148 | 16860543498428 | 16860543499998 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 140 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 51648 | 0x7f65802d0000 | 0x7f657d224b00 | 16860543521778 | 16860543532507 | 16860543624507 | 16860543626115 |
| 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 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 52864 | 0x7f657dc31e80 | 0x7f657d224b40 | 16860543642664 | 16860543650427 | 16860543829146 | 16860543830668 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 146 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 54080 | 0x7f657dc31d00 | 0x7f657d224b80 | 16860543845078 | 16860543853626 | 16860544033466 | 16860544034992 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 149 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 8 | 24 | 55296 | 0x7f657dc31b80 | 0x7f657d224bc0 | 16860544050642 | 16860544059546 | 16860544153785 | 16860544155408 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 152 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 56768 | 0x7f657dc31a00 | 0x7f657d224c00 | 16860544170638 | 16860544178585 | 16860544274745 | 16860544276235 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 155 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 57728 | 0x7f657dc31880 | 0x7f657d224c40 | 16860544297554 | 16860544308345 | 16860544402104 | 16860544403661 |
| 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 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 58944 | 0x7f657dc31700 | 0x7f657d224c80 | 16860544418650 | 16860544426904 | 16860544606104 | 16860544607655 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 161 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 60160 | 0x7f65802d0580 | 0x7f657d224cc0 | 16860544621364 | 16860544629783 | 16860544810263 | 16860544811798 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 164 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 8 | 24 | 61376 | 0x7f65802d0400 | 0x7f657d224d00 | 16860544825228 | 16860544833783 | 16860544928022 | 16860544929585 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 167 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 62848 | 0x7f65802d0280 | 0x7f657d224d40 | 16860544945634 | 16860544953302 | 16860545052342 | 16860545053941 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 170 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 63808 | 0x7f65802d0100 | 0x7f657d224d80 | 16860545074560 | 16860545084822 | 16860545178901 | 16860545180517 |
| 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 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 65024 | 0x7f657dc31f80 | 0x7f657d224dc0 | 16860545195317 | 16860545204501 | 16860545383221 | 16860545384811 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 176 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 66240 | 0x7f657dc31e00 | 0x7f657d224e00 | 16860545398860 | 16860545407701 | 16860545587860 | 16860545589455 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 179 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 8 | 24 | 67456 | 0x7f657dc31c80 | 0x7f657d224e40 | 16860545604824 | 16860545612980 | 16860545708340 | 16860545709841 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 182 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 68928 | 0x7f657dc31b00 | 0x7f657d224e80 | 16860545726460 | 16860545734739 | 16860545839379 | 16860545841077 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 185 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 70144 | 0x7f657dc31980 | 0x7f657d224ec0 | 16860545862166 | 16860545873139 | 16860545966099 | 16860545967943 |
| 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 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 71616 | 0x7f657dc31800 | 0x7f657d224f00 | 16860545983303 | 16860545991219 | 16860546171378 | 16860546172887 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 191 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 72832 | 0x7f657dc31680 | 0x7f657d224f40 | 16860546189526 | 16860546197938 | 16860546379857 | 16860546381590 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 194 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 8 | 24 | 74048 | 0x7f65802d0500 | 0x7f657d224f80 | 16860546395790 | 16860546404017 | 16860546497137 | 16860546498797 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 197 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 75776 | 0x7f65802d0380 | 0x7f657d224fc0 | 16860546513116 | 16860546521137 | 16860546627696 | 16860546629453 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 200 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 76992 | 0x7f65802d0200 | 0x7f657d225000 | 16860546651102 | 16860546661776 | 16860546755856 | 16860546757439 |
| 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 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 78464 | 0x7f65802d0080 | 0x7f657d225040 | 16860546772739 | 16860546780816 | 16860546960175 | 16860546961883 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 206 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 79936 | 0x7f657dc31f00 | 0x7f657d225080 | 16860546977412 | 16860546985295 | 16860547164174 | 16860547165917 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 209 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 8 | 24 | 81408 | 0x7f657dc31d80 | 0x7f657d2250c0 | 16860547180456 | 16860547189134 | 16860547283694 | 16860547285333 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 212 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 83136 | 0x7f657dc31c00 | 0x7f657d225100 | 16860547300032 | 16860547308174 | 16860547424013 | 16860547425869 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 215 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 84352 | 0x7f657dc31a80 | 0x7f657d225140 | 16860547459928 | 16860547469613 | 16860547563693 | 16860547565294 |
| 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 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 85824 | 0x7f657dc31900 | 0x7f657d225180 | 16860547580644 | 16860547588493 | 16860547768652 | 16860547770188 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 221 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 87296 | 0x7f657dc31780 | 0x7f657d2251c0 | 16860547784648 | 16860547792332 | 16860547973771 | 16860547975372 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 224 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 88768 | 0x7f657dc31600 | 0x7f657d225200 | 16860547990081 | 16860547998251 | 16860548093131 | 16860548094928 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 227 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 90752 | 0x7f65802d0480 | 0x7f657d225240 | 16860548110848 | 16860548119211 | 16860548239530 | 16860548241244 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 230 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 91968 | 0x7f65802d0300 | 0x7f657d225280 | 16860548263473 | 16860548274090 | 16860548368010 | 16860548369690 |
| 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 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 93440 | 0x7f65802d0180 | 0x7f657d2252c0 | 16860548386949 | 16860548394890 | 16860548574889 | 16860548576424 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 236 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 94912 | 0x7f65802d0000 | 0x7f657d225300 | 16860548590493 | 16860548599049 | 16860548778568 | 16860548780207 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 239 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 96384 | 0x7f657dc31e80 | 0x7f657d225340 | 16860548794517 | 16860548802888 | 16860548897928 | 16860548899534 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 242 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 98368 | 0x7f657dc31d00 | 0x7f657d225380 | 16860548914883 | 16860548922888 | 16860549049288 | 16860549050759 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 245 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 99584 | 0x7f657dc31b80 | 0x7f657d2253c0 | 16860549071298 | 16860549081607 | 16860549176167 | 16860549177755 |
| 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 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 101312 | 0x7f657dc31a00 | 0x7f657d225400 | 16860549194285 | 16860549202247 | 16860549382566 | 16860549384179 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 251 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 102784 | 0x7f657dc31880 | 0x7f657d225440 | 16860549399868 | 16860549408326 | 16860549587846 | 16860549589363 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 254 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 104256 | 0x7f657dc31700 | 0x7f657d225480 | 16860549604332 | 16860549612325 | 16860549706405 | 16860549707939 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 257 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 106240 | 0x7f65802d0580 | 0x7f657d2254c0 | 16860549724258 | 16860549732805 | 16860549863365 | 16860549864844 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 260 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 107712 | 0x7f65802d0400 | 0x7f657d225500 | 16860549884474 | 16860549895204 | 16860549988804 | 16860549990300 |
| 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 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 16 | 24 | 109440 | 0x7f65802d0280 | 0x7f657d225540 | 16860550006810 | 16860550015204 | 16860550194723 | 16860550196294 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 266 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 16 | 24 | 111168 | 0x7f65802d0100 | 0x7f657d225580 | 16860550212214 | 16860550220483 | 16860550399843 | 16860550401498 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 269 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 8 | 24 | 112896 | 0x7f657dc31f80 | 0x7f657d2255c0 | 16860550416007 | 16860550423843 | 16860550519202 | 16860550520904 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 272 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 115136 | 0x7f657dc31e00 | 0x7f657d225600 | 16860550535644 | 16860550543842 | 16860550682722 | 16860550684409 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 275 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 116608 | 0x7f657dc31c80 | 0x7f657d225640 | 16860550705129 | 16860550715842 | 16860550809601 | 16860550811555 |
| 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 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 16 | 24 | 118336 | 0x7f657dc31b00 | 0x7f657d225680 | 16860550825655 | 16860550833761 | 16860551012960 | 16860551014639 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 281 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 16 | 24 | 120064 | 0x7f657dc31980 | 0x7f657d2256c0 | 16860551029369 | 16860551037760 | 16860551217760 | 16860551219403 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 284 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 121792 | 0x7f657dc31800 | 0x7f657d225700 | 16860551233862 | 16860551241760 | 16860551339519 | 16860551341189 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 287 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 124032 | 0x7f657dc31680 | 0x7f657d225740 | 16860551357099 | 16860551365119 | 16860551511199 | 16860551512794 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 290 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 125504 | 0x7f65802d0500 | 0x7f657d225780 | 16860551532683 | 16860551543039 | 16860551637598 | 16860551639330 |
| 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 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 127488 | 0x7f65802d0380 | 0x7f657d2257c0 | 16860551654310 | 16860551662078 | 16860551841277 | 16860551842974 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 296 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 129216 | 0x7f65802d0200 | 0x7f657d225800 | 16860551857043 | 16860551865117 | 16860552045117 | 16860552046778 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 299 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 130944 | 0x7f65802d0080 | 0x7f657d225840 | 16860552062047 | 16860552070877 | 16860552170716 | 16860552172364 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 302 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 133440 | 0x7f657dc31f00 | 0x7f657d225880 | 16860552186943 | 16860552195356 | 16860552350236 | 16860552351858 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 305 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 134912 | 0x7f657dc31d80 | 0x7f657d2258c0 | 16860552374168 | 16860552384635 | 16860552479515 | 16860552481094 |
| 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 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 136896 | 0x7f657dc31c00 | 0x7f657d225900 | 16860552497364 | 16860552505435 | 16860552684474 | 16860552686088 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 311 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 138880 | 0x7f657dc31a80 | 0x7f657d225940 | 16860552701198 | 16860552709594 | 16860552889274 | 16860552890932 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 314 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 140864 | 0x7f657dc31900 | 0x7f657d225980 | 16860552907481 | 16860552915354 | 16860553021273 | 16860553022728 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 317 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 143616 | 0x7f657dc31780 | 0x7f657d2259c0 | 16860553040117 | 16860553048313 | 16860553218232 | 16860553219772 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 320 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 145344 | 0x7f657dc31600 | 0x7f657d225a00 | 16860553242071 | 16860553252312 | 16860553348632 | 16860553350168 |
| 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 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 147584 | 0x7f65802d0480 | 0x7f657d225a40 | 16860553365587 | 16860553373592 | 16860553554711 | 16860553556192 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 326 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 149568 | 0x7f65802d0300 | 0x7f657d225a80 | 16860553570421 | 16860553578711 | 16860553759671 | 16860553761235 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 329 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 151552 | 0x7f65802d0180 | 0x7f657d225ac0 | 16860553775645 | 16860553784150 | 16860553894230 | 16860553895831 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 332 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 154304 | 0x7f65802d0000 | 0x7f657d225b00 | 16860553911641 | 16860553919990 | 16860554100789 | 16860554102685 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 335 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 156288 | 0x7f657dc31e80 | 0x7f657d225b40 | 16860554125124 | 16860554134709 | 16860554236949 | 16860554238431 |
| 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 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 158784 | 0x7f657dc31d00 | 0x7f657d225b80 | 16860554254520 | 16860554262869 | 16860554449108 | 16860554450604 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 341 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 161024 | 0x7f657dc31b80 | 0x7f657d225bc0 | 16860554465114 | 16860554472948 | 16860554656947 | 16860554658538 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 344 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 163264 | 0x7f657dc31a00 | 0x7f657d225c00 | 16860554673758 | 16860554681907 | 16860554803667 | 16860554805234 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 347 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 166528 | 0x7f657dc31880 | 0x7f657d225c40 | 16860554820383 | 16860554828627 | 16860555034866 | 16860555056586 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 350 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 168512 | 0x7f657dc31700 | 0x7f657d225c80 | 16860555071955 | 16860555082546 | 16860555195345 | 16860555196872 |
| 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 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 171264 | 0x7f65802d0580 | 0x7f657d225cc0 | 16860555213011 | 16860555221905 | 16860555407185 | 16860555408725 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 356 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 173760 | 0x7f65802d0400 | 0x7f657d225d00 | 16860555422965 | 16860555431345 | 16860555617424 | 16860555619029 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 359 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 176256 | 0x7f65802d0280 | 0x7f657d225d40 | 16860555633828 | 16860555641744 | 16860555776303 | 16860555777894 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 362 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 179776 | 0x7f65802d0100 | 0x7f657d225d80 | 16860555792034 | 16860555800463 | 16860556032462 | 16860556053826 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 365 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 182272 | 0x7f657dc31f80 | 0x7f657d225dc0 | 16860556069265 | 16860556079982 | 16860556206542 | 16860556208181 |
| 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 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 185536 | 0x7f657dc31e00 | 0x7f657d225e00 | 16860556223800 | 16860556231982 | 16860556422381 | 16860556423934 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 371 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 188544 | 0x7f657dc31c80 | 0x7f657d225e40 | 16860556440034 | 16860556448141 | 16860556640460 | 16860556641978 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 374 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 191552 | 0x7f657dc31b00 | 0x7f657d225e80 | 16860556657537 | 16860556666060 | 16860556826379 | 16860556827862 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 377 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 195840 | 0x7f657dc31980 | 0x7f657d225ec0 | 16860556843552 | 16860556852299 | 16860557135498 | 16860557154862 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 380 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 198592 | 0x7f657dc31800 | 0x7f657d225f00 | 16860557171372 | 16860557181578 | 16860557331338 | 16860557333027 |
| 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 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 202368 | 0x7f657dc31680 | 0x7f657d225f40 | 16860557350806 | 16860557358698 | 16860557566537 | 16860557585919 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 386 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 205888 | 0x7f65802d0500 | 0x7f657d225f80 | 16860557594269 | 16860557603657 | 16860557812456 | 16860557828492 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 389 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 209408 | 0x7f65802d0380 | 0x7f657d225fc0 | 16860557848261 | 16860557858536 | 16860558043975 | 16860558045605 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 392 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 214464 | 0x7f65802d0200 | 0x7f657d226000 | 16860558063155 | 16860558071335 | 16860558405894 | 16860558424064 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 395 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 217728 | 0x7f65802d0080 | 0x7f657d226040 | 16860558441943 | 16860558452454 | 16860558621093 | 16860558622568 |
| 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 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 222016 | 0x7f657dc31f00 | 0x7f657d226080 | 16860558638477 | 16860558646853 | 16860558875332 | 16860558891319 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 401 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 226048 | 0x7f657dc31d80 | 0x7f657d2260c0 | 16860558900259 | 16860558910052 | 16860559139491 | 16860559154231 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 404 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 230080 | 0x7f657dc31c00 | 0x7f657d226100 | 16860559162891 | 16860559173091 | 16860559384610 | 16860559400244 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 407 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 235904 | 0x7f657dc31a80 | 0x7f657d226140 | 16860559410304 | 16860559419170 | 16860559804609 | 16860559820291 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 410 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 239424 | 0x7f657dc31900 | 0x7f657d226180 | 16860559836811 | 16860559847489 | 16860560033728 | 16860560035334 |
| 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 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 244224 | 0x7f657dc31780 | 0x7f657d2261c0 | 16860560050924 | 16860560058688 | 16860560309887 | 16860560325636 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 416 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 248768 | 0x7f657dc31600 | 0x7f657d226200 | 16860560333985 | 16860560343807 | 16860560592126 | 16860560608397 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 419 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 253312 | 0x7f65802d0480 | 0x7f657d226240 | 16860560620797 | 16860560631166 | 16860560867805 | 16860560883209 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 422 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 8 | 24 | 255552 | 0x7f65802d0300 | 0x7f657d226280 | 16860560894328 | 16860560904765 | 16860561358363 | 16860561374324 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 425 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 259840 | 0x7f65802d0180 | 0x7f657d2262c0 | 16860561390863 | 16860561401563 | 16860561626522 | 16860561641805 |
| 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 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 265664 | 0x7f65802d0000 | 0x7f657d226300 | 16860561650505 | 16860561660602 | 16860561959161 | 16860561974705 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 431 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 271232 | 0x7f657dc31e80 | 0x7f657d226340 | 16860561985685 | 16860561995321 | 16860562293400 | 16860562339174 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 434 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 8 | 24 | 273216 | 0x7f657dc31d00 | 0x7f657d226380 | 16860562352694 | 16860562362200 | 16860562658518 | 16860562703593 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 437 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 8 | 24 | 275712 | 0x7f657dc31b80 | 0x7f657d2263c0 | 16860562715593 | 16860562725878 | 16860563283956 | 16860563323764 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 440 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 280768 | 0x7f657dc31a00 | 0x7f657d226400 | 16860563341674 | 16860563352276 | 16860563615955 | 16860563659614 |
| 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 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 287616 | 0x7f657dc31880 | 0x7f657d226440 | 16860563668074 | 16860563678195 | 16860564028913 | 16860564072031 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 446 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 294208 | 0x7f657dc31700 | 0x7f657d226480 | 16860564080711 | 16860564091313 | 16860564442032 | 16860564484959 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 449 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 8 | 24 | 296960 | 0x7f65802d0580 | 0x7f657d2264c0 | 16860564494618 | 16860564504752 | 16860564851791 | 16860564895316 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 452 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 8 | 24 | 299968 | 0x7f65802d0400 | 0x7f657d226500 | 16860564904956 | 16860564914670 | 16860565575948 | 16860565616394 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 455 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 8 | 24 | 302720 | 0x7f65802d0280 | 0x7f657d226540 | 16860565635164 | 16860565644268 | 16860566092426 | 16860566117559 |
| 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 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 305472 | 0x7f65802d0100 | 0x7f657d226580 | 16860566126399 | 16860566135946 | 16860566600424 | 16860566645773 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 461 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 308224 | 0x7f657dc31f80 | 0x7f657d2265c0 | 16860566654232 | 16860566664424 | 16860567125702 | 16860567168827 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 464 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 8 | 24 | 310976 | 0x7f657dc31e00 | 0x7f657d226600 | 16860567177167 | 16860567187302 | 16860567639460 | 16860567683111 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 467 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 8 | 24 | 313216 | 0x7f657dc31c80 | 0x7f657d226640 | 16860567694231 | 16860567704740 | 16860568572897 | 16860568616403 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 470 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 8 | 24 | 315968 | 0x7f657dc31b00 | 0x7f657d226680 | 16860568634192 | 16860568644737 | 16860569498814 | 16860569542244 |
| 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 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 318720 | 0x7f657dc31980 | 0x7f657d2266c0 | 16860569551484 | 16860569562174 | 16860570447130 | 16860570493575 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 476 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 321472 | 0x7f657dc31800 | 0x7f657d226700 | 16860570504385 | 16860570514330 | 16860571394807 | 16860571440286 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 479 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 8 | 24 | 324224 | 0x7f657dc31680 | 0x7f657d226740 | 16860571453626 | 16860571476887 | 16860572335604 | 16860572379638 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 482 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 8 | 24 | 326464 | 0x7f65802d0500 | 0x7f657d226780 | 16860572388577 | 16860572398483 | 16860574098317 | 16860574150084 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 485 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 8 | 24 | 329216 | 0x7f65802d0380 | 0x7f657d2267c0 | 16860574167933 | 16860574178157 | 16860575843591 | 16860575912750 |
| 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 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 331968 | 0x7f65802d0200 | 0x7f657d226800 | 16860575922780 | 16860575933191 | 16860577659424 | 16860577728784 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 491 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 12 | 24 | 334720 | 0x7f65802d0080 | 0x7f657d226840 | 16860577741684 | 16860577759104 | 16860579474298 | 16860579543379 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 494 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 8 | 24 | 337472 | 0x7f657dc31f00 | 0x7f657d226880 | 16860579556289 | 16860579573657 | 16860581246611 | 16860581315766 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 497 | 179735 | 179735 | 4194304 | 256 | 0 | 0 | 8 | 24 | 0 | 0x7f657dc31d80 | 0x7f657d2268c0 | 16860581325895 | 16860581337171 | 16860584693959 | 16860584773310 |