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 | 129459 | 129459 | 33554432 | 256 | 0 | 0 | 4 | 32 | 4160 | 0x0 | 0x7fec4ac04280 | 15733876934024 | 15733876958945 | 15733877198786 | 15733877280556 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 129459 | 129459 | 32768 | 256 | 0 | 0 | 12 | 24 | 13888 | 0x0 | 0x7fec4ac23f80 | 15733881995950 | 15733882011284 | 15733882024564 | 15733882042619 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 5 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 14336 | 0x7fec552ba380 | 0x7fec4ac23fc0 | 15733882047019 | 15733882103285 | 15733882196085 | 15733882198235 |
| 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 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15040 | 0x7fec552ba200 | 0x7fec4ac24000 | 15733882220505 | 15733882230645 | 15733882409366 | 15733882411261 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 11 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15488 | 0x7fec552ba080 | 0x7fec4ac24040 | 15733882426480 | 15733882434326 | 15733882616247 | 15733882618256 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 14 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 15936 | 0x7fec4b36bf00 | 0x7fec4ac24080 | 15733882632486 | 15733882640567 | 15733882734327 | 15733882736413 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 17 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 16384 | 0x7fec4b36bd80 | 0x7fec4ac240c0 | 15733882752673 | 15733882760567 | 15733882852567 | 15733882854411 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 20 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 17088 | 0x7fec4b36bc00 | 0x7fec4ac24100 | 15733882881680 | 15733882892248 | 15733882984408 | 15733882986268 |
| 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 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 16 | 24 | 17792 | 0x7fec4b36ba80 | 0x7fec4ac24140 | 15733883013617 | 15733883023288 | 15733883202009 | 15733883203833 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 26 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 16 | 24 | 18496 | 0x7fec4b36b900 | 0x7fec4ac24180 | 15733883227992 | 15733883242169 | 15733883422010 | 15733883424118 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 29 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19200 | 0x7fec4b36b780 | 0x7fec4ac241c0 | 15733883441498 | 15733883450330 | 15733883543610 | 15733883545445 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 32 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19904 | 0x7fec4b36b600 | 0x7fec4ac24200 | 15733883563465 | 15733883586490 | 15733883679771 | 15733883681752 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 35 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 20608 | 0x7fec552ba480 | 0x7fec4ac24240 | 15733883702832 | 15733883713051 | 15733883806491 | 15733883808329 |
| 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 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 16 | 24 | 21312 | 0x7fec552ba300 | 0x7fec4ac24280 | 15733883827149 | 15733883836891 | 15733884016732 | 15733884018855 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 41 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22016 | 0x7fec552ba180 | 0x7fec4ac242c0 | 15733884033754 | 15733884042812 | 15733884222973 | 15733884224820 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 44 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22720 | 0x7fec552ba000 | 0x7fec4ac24300 | 15733884239060 | 15733884247773 | 15733884341533 | 15733884343367 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 47 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 23424 | 0x7fec4b36be80 | 0x7fec4ac24340 | 15733884362797 | 15733884385534 | 15733884479454 | 15733884481474 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 50 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 24128 | 0x7fec4b36bd00 | 0x7fec4ac24380 | 15733884502644 | 15733884512894 | 15733884606174 | 15733884607891 |
| 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 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 16 | 24 | 24832 | 0x7fec4b36bb80 | 0x7fec4ac243c0 | 15733884626551 | 15733884634815 | 15733884813535 | 15733884815537 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 56 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 16 | 24 | 25536 | 0x7fec4b36ba00 | 0x7fec4ac24400 | 15733884833066 | 15733884841055 | 15733885021376 | 15733885023232 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 59 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26240 | 0x7fec4b36b880 | 0x7fec4ac24440 | 15733885042482 | 15733885051296 | 15733885145377 | 15733885147199 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 62 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26944 | 0x7fec4b36b700 | 0x7fec4ac24480 | 15733885166349 | 15733885175457 | 15733885269217 | 15733885271127 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 65 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 27648 | 0x7fec552ba580 | 0x7fec4ac244c0 | 15733885292706 | 15733885302977 | 15733885394658 | 15733885396534 |
| 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 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 16 | 24 | 28608 | 0x7fec552ba400 | 0x7fec4ac24500 | 15733885413263 | 15733885440098 | 15733885619458 | 15733885621349 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 71 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 16 | 24 | 29312 | 0x7fec552ba280 | 0x7fec4ac24540 | 15733885636068 | 15733885652899 | 15733885832739 | 15733885834194 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 74 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 30016 | 0x7fec552ba100 | 0x7fec4ac24580 | 15733885849034 | 15733885857059 | 15733885949220 | 15733885950591 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 77 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 8 | 24 | 30976 | 0x7fec4b36bf80 | 0x7fec4ac245c0 | 15733885965271 | 15733885973380 | 15733886064740 | 15733886066169 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 80 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 31680 | 0x7fec4b36be00 | 0x7fec4ac24600 | 15733886093468 | 15733886103780 | 15733886197701 | 15733886199056 |
| 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 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 16 | 24 | 32640 | 0x7fec4b36bc80 | 0x7fec4ac24640 | 15733886213526 | 15733886222021 | 15733886400901 | 15733886402221 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 86 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 33600 | 0x7fec4b36bb00 | 0x7fec4ac24680 | 15733886415661 | 15733886423622 | 15733886605062 | 15733886606547 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 89 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 34560 | 0x7fec4b36b980 | 0x7fec4ac246c0 | 15733886620686 | 15733886628422 | 15733886721223 | 15733886722694 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 92 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 8 | 24 | 35520 | 0x7fec4b36b800 | 0x7fec4ac24700 | 15733886736954 | 15733886744903 | 15733886838663 | 15733886840261 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 95 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 36224 | 0x7fec4b36b680 | 0x7fec4ac24740 | 15733886860841 | 15733886870983 | 15733886963624 | 15733886964909 |
| 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 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 37184 | 0x7fec552ba500 | 0x7fec4ac24780 | 15733886979468 | 15733886987304 | 15733887167625 | 15733887169044 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 101 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 38144 | 0x7fec552ba380 | 0x7fec4ac247c0 | 15733887183324 | 15733887191785 | 15733887371945 | 15733887373509 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 104 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 39104 | 0x7fec552ba200 | 0x7fec4ac24800 | 15733887387469 | 15733887395465 | 15733887489066 | 15733887490537 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 107 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 8 | 24 | 40320 | 0x7fec552ba080 | 0x7fec4ac24840 | 15733887505636 | 15733887513706 | 15733887608746 | 15733887609984 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 110 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 41280 | 0x7fec4b36bf00 | 0x7fec4ac24880 | 15733887629744 | 15733887640586 | 15733887734027 | 15733887735361 |
| 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 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 42240 | 0x7fec4b36bd80 | 0x7fec4ac248c0 | 15733887753051 | 15733887768107 | 15733887948428 | 15733887949796 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 116 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 43200 | 0x7fec4b36bc00 | 0x7fec4ac24900 | 15733887963606 | 15733887971788 | 15733888153068 | 15733888154492 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 119 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 8 | 24 | 44160 | 0x7fec4b36ba80 | 0x7fec4ac24940 | 15733888169482 | 15733888178668 | 15733888272269 | 15733888273709 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 122 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 45376 | 0x7fec4b36b900 | 0x7fec4ac24980 | 15733888287379 | 15733888295309 | 15733888389869 | 15733888391097 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 125 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 46336 | 0x7fec4b36b780 | 0x7fec4ac249c0 | 15733888410626 | 15733888422989 | 15733888516110 | 15733888517474 |
| 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 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 47552 | 0x7fec4b36b600 | 0x7fec4ac24a00 | 15733888532183 | 15733888539950 | 15733888719471 | 15733888720729 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 131 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 48512 | 0x7fec552ba480 | 0x7fec4ac24a40 | 15733888734689 | 15733888742671 | 15733888923951 | 15733888925295 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 134 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 8 | 24 | 49472 | 0x7fec552ba300 | 0x7fec4ac24a80 | 15733888938734 | 15733888947152 | 15733889039472 | 15733889040822 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 137 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 50688 | 0x7fec552ba180 | 0x7fec4ac24ac0 | 15733889056592 | 15733889069872 | 15733889163792 | 15733889165109 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 140 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 51648 | 0x7fec552ba000 | 0x7fec4ac24b00 | 15733889185119 | 15733889195633 | 15733889287473 | 15733889288886 |
| 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 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 52864 | 0x7fec4b36be80 | 0x7fec4ac24b40 | 15733889304286 | 15733889312593 | 15733889492434 | 15733889493802 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 146 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 54080 | 0x7fec4b36bd00 | 0x7fec4ac24b80 | 15733889508441 | 15733889516914 | 15733889698194 | 15733889699507 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 149 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 8 | 24 | 55296 | 0x7fec4b36bb80 | 0x7fec4ac24bc0 | 15733889713367 | 15733889722195 | 15733889816595 | 15733889817974 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 152 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 56768 | 0x7fec4b36ba00 | 0x7fec4ac24c00 | 15733889831774 | 15733889839955 | 15733889935955 | 15733889937332 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 155 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 57728 | 0x7fec4b36b880 | 0x7fec4ac24c40 | 15733889957441 | 15733889967956 | 15733890062196 | 15733890063539 |
| 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 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 58944 | 0x7fec4b36b700 | 0x7fec4ac24c80 | 15733890086628 | 15733890097556 | 15733890277077 | 15733890278584 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 161 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 60160 | 0x7fec552ba580 | 0x7fec4ac24cc0 | 15733890293054 | 15733890301077 | 15733890483318 | 15733890484539 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 164 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 8 | 24 | 61376 | 0x7fec552ba400 | 0x7fec4ac24d00 | 15733890498669 | 15733890506838 | 15733890601238 | 15733890602687 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 167 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 62848 | 0x7fec552ba280 | 0x7fec4ac24d40 | 15733890619796 | 15733890627638 | 15733890726679 | 15733890728054 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 170 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 63808 | 0x7fec552ba100 | 0x7fec4ac24d80 | 15733890750183 | 15733890761079 | 15733890854199 | 15733890855541 |
| 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 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 65024 | 0x7fec4b36bf80 | 0x7fec4ac24dc0 | 15733890882001 | 15733890892599 | 15733891072920 | 15733891074406 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 176 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 66240 | 0x7fec4b36be00 | 0x7fec4ac24e00 | 15733891089426 | 15733891097720 | 15733891278201 | 15733891279512 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 179 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 8 | 24 | 67456 | 0x7fec4b36bc80 | 0x7fec4ac24e40 | 15733891296371 | 15733891303641 | 15733891399001 | 15733891400329 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 182 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 68928 | 0x7fec4b36bb00 | 0x7fec4ac24e80 | 15733891416958 | 15733891424921 | 15733891529562 | 15733891531156 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 185 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 70144 | 0x7fec4b36b980 | 0x7fec4ac24ec0 | 15733891552805 | 15733891563322 | 15733891656122 | 15733891657493 |
| 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 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 71616 | 0x7fec4b36b800 | 0x7fec4ac24f00 | 15733891673323 | 15733891681402 | 15733891861563 | 15733891862908 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 191 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 72832 | 0x7fec4b36b680 | 0x7fec4ac24f40 | 15733891876868 | 15733891885563 | 15733892065564 | 15733892066954 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 194 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 8 | 24 | 74048 | 0x7fec552ba500 | 0x7fec4ac24f80 | 15733892081004 | 15733892089564 | 15733892183164 | 15733892184551 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 197 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 75776 | 0x7fec552ba380 | 0x7fec4ac24fc0 | 15733892198421 | 15733892206364 | 15733892313085 | 15733892314448 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 200 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 76992 | 0x7fec552ba200 | 0x7fec4ac25000 | 15733892336058 | 15733892346685 | 15733892440765 | 15733892442155 |
| 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 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 78464 | 0x7fec552ba080 | 0x7fec4ac25040 | 15733892459495 | 15733892467325 | 15733892646686 | 15733892648201 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 206 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 79936 | 0x7fec4b36bf00 | 0x7fec4ac25080 | 15733892662720 | 15733892671166 | 15733892851807 | 15733892853206 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 209 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 8 | 24 | 81408 | 0x7fec4b36bd80 | 0x7fec4ac250c0 | 15733892867576 | 15733892876447 | 15733892971167 | 15733892972493 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 212 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 83136 | 0x7fec4b36bc00 | 0x7fec4ac25100 | 15733892986333 | 15733892994207 | 15733893109088 | 15733893110550 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 215 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 84352 | 0x7fec4b36ba80 | 0x7fec4ac25140 | 15733893143620 | 15733893153248 | 15733893247488 | 15733893248887 |
| 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 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 85824 | 0x7fec4b36b900 | 0x7fec4ac25180 | 15733893265587 | 15733893273249 | 15733893452769 | 15733893454483 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 221 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 87296 | 0x7fec4b36b780 | 0x7fec4ac251c0 | 15733893470312 | 15733893478209 | 15733893657410 | 15733893658838 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 224 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 88768 | 0x7fec4b36b600 | 0x7fec4ac25200 | 15733893673588 | 15733893682210 | 15733893777411 | 15733893778685 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 227 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 90752 | 0x7fec552ba480 | 0x7fec4ac25240 | 15733893792745 | 15733893802051 | 15733893922691 | 15733893924022 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 230 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 91968 | 0x7fec552ba300 | 0x7fec4ac25280 | 15733893943482 | 15733893955491 | 15733894049252 | 15733894050629 |
| 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 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 93440 | 0x7fec552ba180 | 0x7fec4ac252c0 | 15733894065839 | 15733894073572 | 15733894252932 | 15733894254285 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 236 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 94912 | 0x7fec552ba000 | 0x7fec4ac25300 | 15733894268994 | 15733894276773 | 15733894456453 | 15733894458040 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 239 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 96384 | 0x7fec4b36be80 | 0x7fec4ac25340 | 15733894473760 | 15733894481733 | 15733894576454 | 15733894578017 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 242 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 98368 | 0x7fec4b36bd00 | 0x7fec4ac25380 | 15733894592947 | 15733894600614 | 15733894727654 | 15733894729074 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 245 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 99584 | 0x7fec4b36bb80 | 0x7fec4ac253c0 | 15733894749914 | 15733894760134 | 15733894855175 | 15733894856721 |
| 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 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 101312 | 0x7fec4b36ba00 | 0x7fec4ac25400 | 15733894871551 | 15733894879495 | 15733895058056 | 15733895059547 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 251 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 102784 | 0x7fec4b36b880 | 0x7fec4ac25440 | 15733895073846 | 15733895081736 | 15733895261256 | 15733895262712 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 254 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 104256 | 0x7fec4b36b700 | 0x7fec4ac25480 | 15733895277222 | 15733895285097 | 15733895378537 | 15733895380119 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 257 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 106240 | 0x7fec552ba580 | 0x7fec4ac254c0 | 15733895397049 | 15733895405737 | 15733895536298 | 15733895537676 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 260 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 107712 | 0x7fec552ba400 | 0x7fec4ac25500 | 15733895557706 | 15733895568298 | 15733895661578 | 15733895663013 |
| 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 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 16 | 24 | 109440 | 0x7fec552ba280 | 0x7fec4ac25540 | 15733895680713 | 15733895696298 | 15733895875179 | 15733895876628 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 266 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 16 | 24 | 111168 | 0x7fec552ba100 | 0x7fec4ac25580 | 15733895890278 | 15733895898539 | 15733896077900 | 15733896079164 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 269 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 8 | 24 | 112896 | 0x7fec4b36bf80 | 0x7fec4ac255c0 | 15733896093194 | 15733896101580 | 15733896196780 | 15733896198131 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 272 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 115136 | 0x7fec4b36be00 | 0x7fec4ac25600 | 15733896211621 | 15733896219980 | 15733896358061 | 15733896359288 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 275 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 116608 | 0x7fec4b36bc80 | 0x7fec4ac25640 | 15733896381007 | 15733896391501 | 15733896486381 | 15733896487795 |
| 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 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 16 | 24 | 118336 | 0x7fec4b36bb00 | 0x7fec4ac25680 | 15733896502924 | 15733896510701 | 15733896689742 | 15733896691200 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 281 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 16 | 24 | 120064 | 0x7fec4b36b980 | 0x7fec4ac256c0 | 15733896705990 | 15733896715022 | 15733896894543 | 15733896895806 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 284 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 121792 | 0x7fec4b36b800 | 0x7fec4ac25700 | 15733896910125 | 15733896918703 | 15733897015503 | 15733897016953 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 287 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 124032 | 0x7fec4b36b680 | 0x7fec4ac25740 | 15733897031713 | 15733897040303 | 15733897186544 | 15733897187919 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 290 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 125504 | 0x7fec552ba500 | 0x7fec4ac25780 | 15733897207739 | 15733897219024 | 15733897313905 | 15733897315216 |
| 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 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 127488 | 0x7fec552ba380 | 0x7fec4ac257c0 | 15733897332276 | 15733897339825 | 15733897519185 | 15733897520682 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 296 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 129216 | 0x7fec552ba200 | 0x7fec4ac25800 | 15733897537831 | 15733897545745 | 15733897726706 | 15733897728137 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 299 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 130944 | 0x7fec552ba080 | 0x7fec4ac25840 | 15733897745217 | 15733897752946 | 15733897853747 | 15733897855034 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 302 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 133440 | 0x7fec4b36bf00 | 0x7fec4ac25880 | 15733897868704 | 15733897877107 | 15733898032467 | 15733898033940 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 305 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 134912 | 0x7fec4b36bd80 | 0x7fec4ac258c0 | 15733898054270 | 15733898064947 | 15733898159828 | 15733898161307 |
| 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 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 136896 | 0x7fec4b36bc00 | 0x7fec4ac25900 | 15733898175547 | 15733898183828 | 15733898362869 | 15733898364363 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 311 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 138880 | 0x7fec4b36ba80 | 0x7fec4ac25940 | 15733898379422 | 15733898387509 | 15733898567669 | 15733898569108 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 314 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 140864 | 0x7fec4b36b900 | 0x7fec4ac25980 | 15733898583738 | 15733898591350 | 15733898698230 | 15733898699665 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 317 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 143616 | 0x7fec4b36b780 | 0x7fec4ac259c0 | 15733898713855 | 15733898722070 | 15733898892311 | 15733898893791 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 320 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 145344 | 0x7fec4b36b600 | 0x7fec4ac25a00 | 15733898919250 | 15733898930071 | 15733899026711 | 15733899028098 |
| 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 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 147584 | 0x7fec552ba480 | 0x7fec4ac25a40 | 15733899043927 | 15733899051671 | 15733899233112 | 15733899234563 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 326 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 149568 | 0x7fec552ba300 | 0x7fec4ac25a80 | 15733899248773 | 15733899256312 | 15733899438233 | 15733899439789 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 329 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 151552 | 0x7fec552ba180 | 0x7fec4ac25ac0 | 15733899453688 | 15733899461593 | 15733899573273 | 15733899574706 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 332 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 154304 | 0x7fec552ba000 | 0x7fec4ac25b00 | 15733899588825 | 15733899596474 | 15733899777434 | 15733899778881 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 335 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 156288 | 0x7fec4b36be80 | 0x7fec4ac25b40 | 15733899799470 | 15733899808954 | 15733899909915 | 15733899911348 |
| 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 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 158784 | 0x7fec4b36bd00 | 0x7fec4ac25b80 | 15733899926618 | 15733899934395 | 15733900118556 | 15733900120023 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 341 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 161024 | 0x7fec4b36bb80 | 0x7fec4ac25bc0 | 15733900134423 | 15733900142396 | 15733900329276 | 15733900330799 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 344 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 163264 | 0x7fec4b36ba00 | 0x7fec4ac25c00 | 15733900345058 | 15733900353117 | 15733900475357 | 15733900476835 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 347 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 166528 | 0x7fec4b36b880 | 0x7fec4ac25c40 | 15733900491075 | 15733900499357 | 15733900705598 | 15733900749909 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 350 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 168512 | 0x7fec4b36b700 | 0x7fec4ac25c80 | 15733900765349 | 15733900776318 | 15733900886719 | 15733900888156 |
| 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 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 171264 | 0x7fec552ba580 | 0x7fec4ac25cc0 | 15733900903746 | 15733900912319 | 15733901095039 | 15733901096281 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 356 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 173760 | 0x7fec552ba400 | 0x7fec4ac25d00 | 15733901110101 | 15733901118240 | 15733901306080 | 15733901307477 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 359 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 176256 | 0x7fec552ba280 | 0x7fec4ac25d40 | 15733901322646 | 15733901330720 | 15733901465441 | 15733901466893 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 362 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 179776 | 0x7fec552ba100 | 0x7fec4ac25d80 | 15733901480273 | 15733901488321 | 15733901720322 | 15733901736907 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 365 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 182272 | 0x7fec4b36bf80 | 0x7fec4ac25dc0 | 15733901751377 | 15733901761922 | 15733901888483 | 15733901889913 |
| 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 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 185536 | 0x7fec4b36be00 | 0x7fec4ac25e00 | 15733901905113 | 15733901912803 | 15733902104483 | 15733902105829 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 371 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 188544 | 0x7fec4b36bc80 | 0x7fec4ac25e40 | 15733902122048 | 15733902131044 | 15733902324804 | 15733902326154 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 374 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 191552 | 0x7fec4b36bb00 | 0x7fec4ac25e80 | 15733902341263 | 15733902349764 | 15733902509925 | 15733902511389 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 377 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 195840 | 0x7fec4b36b980 | 0x7fec4ac25ec0 | 15733902527949 | 15733902535845 | 15733902819046 | 15733902835242 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 380 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 198592 | 0x7fec4b36b800 | 0x7fec4ac25f00 | 15733902851212 | 15733902861926 | 15733903011687 | 15733903013008 |
| 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 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 202368 | 0x7fec4b36b680 | 0x7fec4ac25f40 | 15733903029658 | 15733903037287 | 15733903245928 | 15733903261363 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 386 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 205888 | 0x7fec552ba500 | 0x7fec4ac25f80 | 15733903269102 | 15733903279368 | 15733903489289 | 15733903505567 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 389 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 209408 | 0x7fec552ba380 | 0x7fec4ac25fc0 | 15733903513527 | 15733903523689 | 15733903709450 | 15733903710832 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 392 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 214464 | 0x7fec552ba200 | 0x7fec4ac26000 | 15733903728082 | 15733903735690 | 15733904070091 | 15733904085834 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 395 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 217728 | 0x7fec552ba080 | 0x7fec4ac26040 | 15733904101074 | 15733904111531 | 15733904279212 | 15733904280460 |
| 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 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 222016 | 0x7fec4b36bf00 | 0x7fec4ac26080 | 15733904296389 | 15733904304012 | 15733904532013 | 15733904547594 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 401 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 226048 | 0x7fec4b36bd80 | 0x7fec4ac260c0 | 15733904555913 | 15733904566253 | 15733904795854 | 15733904810968 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 404 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 230080 | 0x7fec4b36bc00 | 0x7fec4ac26100 | 15733904822027 | 15733904832814 | 15733905043695 | 15733905059132 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 407 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 235904 | 0x7fec4b36ba80 | 0x7fec4ac26140 | 15733905069122 | 15733905078415 | 15733905463697 | 15733905479113 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 410 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 239424 | 0x7fec4b36b900 | 0x7fec4ac26180 | 15733905494282 | 15733905504977 | 15733905692018 | 15733905693428 |
| 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 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 244224 | 0x7fec4b36b780 | 0x7fec4ac261c0 | 15733905710747 | 15733905718258 | 15733905967219 | 15733905985881 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 416 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 248768 | 0x7fec4b36b600 | 0x7fec4ac26200 | 15733905994121 | 15733906004339 | 15733906251540 | 15733906267685 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 419 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 253312 | 0x7fec552ba480 | 0x7fec4ac26240 | 15733906276275 | 15733906286580 | 15733906523381 | 15733906539019 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 422 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 8 | 24 | 255552 | 0x7fec552ba300 | 0x7fec4ac26280 | 15733906549209 | 15733906559541 | 15733907012503 | 15733907028198 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 425 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 259840 | 0x7fec552ba180 | 0x7fec4ac262c0 | 15733907044518 | 15733907054743 | 15733907281144 | 15733907296852 |
| 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 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 265664 | 0x7fec552ba000 | 0x7fec4ac26300 | 15733907306742 | 15733907316984 | 15733907615385 | 15733907631204 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 431 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 271232 | 0x7fec4b36be80 | 0x7fec4ac26340 | 15733907642914 | 15733907652185 | 15733907951386 | 15733907972777 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 434 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 8 | 24 | 273216 | 0x7fec4b36bd00 | 0x7fec4ac26380 | 15733907981737 | 15733907991547 | 15733908288028 | 15733908307159 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 437 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 8 | 24 | 275712 | 0x7fec4b36bb80 | 0x7fec4ac263c0 | 15733908318889 | 15733908329148 | 15733908885150 | 15733908900746 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 440 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 280768 | 0x7fec4b36ba00 | 0x7fec4ac26400 | 15733908916536 | 15733908927230 | 15733909191071 | 15733909209879 |
| 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 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 287616 | 0x7fec4b36b880 | 0x7fec4ac26440 | 15733909218019 | 15733909228192 | 15733909578913 | 15733909599110 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 446 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 294208 | 0x7fec4b36b700 | 0x7fec4ac26480 | 15733909609010 | 15733909618913 | 15733909969314 | 15733910014041 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 449 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 8 | 24 | 296960 | 0x7fec552ba580 | 0x7fec4ac264c0 | 15733910024621 | 15733910035075 | 15733910382276 | 15733910428242 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 452 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 8 | 24 | 299968 | 0x7fec552ba400 | 0x7fec4ac26500 | 15733910437162 | 15733910447076 | 15733911109159 | 15733911154396 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 455 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 8 | 24 | 302720 | 0x7fec552ba280 | 0x7fec4ac26540 | 15733911171125 | 15733911180679 | 15733911628361 | 15733911673714 |
| 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 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 305472 | 0x7fec552ba100 | 0x7fec4ac26580 | 15733911682804 | 15733911693161 | 15733912157163 | 15733912200282 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 461 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 308224 | 0x7fec4b36bf80 | 0x7fec4ac265c0 | 15733912208892 | 15733912219083 | 15733912680525 | 15733912724420 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 464 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 8 | 24 | 310976 | 0x7fec4b36be00 | 0x7fec4ac26600 | 15733912732480 | 15733912743085 | 15733913195407 | 15733913238559 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 467 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 8 | 24 | 313216 | 0x7fec4b36bc80 | 0x7fec4ac26640 | 15733913246988 | 15733913257167 | 15733914127091 | 15733914157048 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 470 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 8 | 24 | 315968 | 0x7fec4b36bb00 | 0x7fec4ac26680 | 15733914174008 | 15733914184371 | 15733915039254 | 15733915084637 |
| 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 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 318720 | 0x7fec4b36b980 | 0x7fec4ac266c0 | 15733915095417 | 15733915105815 | 15733915990938 | 15733916036296 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 476 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 321472 | 0x7fec4b36b800 | 0x7fec4ac26700 | 15733916046645 | 15733916057178 | 15733916937502 | 15733916981544 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 479 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 8 | 24 | 324224 | 0x7fec4b36b680 | 0x7fec4ac26740 | 15733916993934 | 15733917018942 | 15733917878786 | 15733917922363 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 482 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 8 | 24 | 326464 | 0x7fec552ba500 | 0x7fec4ac26780 | 15733917931293 | 15733917941346 | 15733919640233 | 15733919710663 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 485 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 8 | 24 | 329216 | 0x7fec552ba380 | 0x7fec4ac267c0 | 15733919728373 | 15733919738793 | 15733921403120 | 15733921471614 |
| 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 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 331968 | 0x7fec552ba200 | 0x7fec4ac26800 | 15733921481314 | 15733921490960 | 15733923217207 | 15733923287083 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 491 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 12 | 24 | 334720 | 0x7fec552ba080 | 0x7fec4ac26840 | 15733923299733 | 15733923329047 | 15733925044734 | 15733925112132 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 494 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 8 | 24 | 337472 | 0x7fec4b36bf00 | 0x7fec4ac26880 | 15733925122852 | 15733925138974 | 15733926813861 | 15733926883602 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 497 | 129459 | 129459 | 4194304 | 256 | 0 | 0 | 8 | 24 | 0 | 0x7fec4b36bd80 | 0x7fec4ac268c0 | 15733926892362 | 15733926902661 | 15733930261234 | 15733930337385 |