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 | 161495 | 161495 | 33554432 | 256 | 0 | 0 | 4 | 32 | 4160 | 0x0 | 0x7fac9be04280 | 16491695695851 | 16491695721721 | 16491695960599 | 16491696073827 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 161495 | 161495 | 32768 | 256 | 0 | 0 | 12 | 24 | 13888 | 0x0 | 0x7fac9be23f80 | 16491700762811 | 16491700778153 | 16491700791273 | 16491700809859 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 5 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 14336 | 0x7facba5de380 | 0x7fac9be23fc0 | 16491700814069 | 16491700861193 | 16491700953512 | 16491700955214 |
| 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 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15040 | 0x7facba5de200 | 0x7fac9be24000 | 16491700976853 | 16491700986951 | 16491701165350 | 16491701167146 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 11 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15488 | 0x7facba5de080 | 0x7fac9be24040 | 16491701182425 | 16491701190950 | 16491701369988 | 16491701371578 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 14 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 15936 | 0x7facac6cdf00 | 0x7fac9be24080 | 16491701385898 | 16491701394308 | 16491701487747 | 16491701489394 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 17 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 16384 | 0x7facac6cdd80 | 0x7fac9be240c0 | 16491701504653 | 16491701512867 | 16491701604866 | 16491701606520 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 20 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 17088 | 0x7facac6cdc00 | 0x7fac9be24100 | 16491701634858 | 16491701645665 | 16491701737985 | 16491701739485 |
| 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 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 16 | 24 | 17792 | 0x7facac6cda80 | 0x7fac9be24140 | 16491701765524 | 16491701775584 | 16491701954783 | 16491701956346 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 26 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 16 | 24 | 18496 | 0x7facac6cd900 | 0x7fac9be24180 | 16491701973616 | 16491701993182 | 16491702172541 | 16491702174498 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 29 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19200 | 0x7facac6cd780 | 0x7fac9be241c0 | 16491702192258 | 16491702201180 | 16491702294300 | 16491702295864 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 32 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19904 | 0x7facac6cd600 | 0x7fac9be24200 | 16491702316063 | 16491702327099 | 16491702419898 | 16491702421569 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 35 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 20608 | 0x7facba5de480 | 0x7fac9be24240 | 16491702442418 | 16491702451898 | 16491702545977 | 16491702547704 |
| 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 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 16 | 24 | 21312 | 0x7facba5de300 | 0x7fac9be24280 | 16491702567333 | 16491702578137 | 16491702756695 | 16491702758096 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 41 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22016 | 0x7facba5de180 | 0x7fac9be242c0 | 16491702773726 | 16491702782135 | 16491702962933 | 16491702965029 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 44 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22720 | 0x7facba5de000 | 0x7fac9be24300 | 16491702979988 | 16491702988853 | 16491703082612 | 16491703084194 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 47 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 23424 | 0x7facac6cde80 | 0x7fac9be24340 | 16491703108043 | 16491703117812 | 16491703211571 | 16491703213199 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 50 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 24128 | 0x7facac6cdd00 | 0x7fac9be24380 | 16491703234928 | 16491703245491 | 16491703338930 | 16491703340604 |
| 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 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 16 | 24 | 24832 | 0x7facac6cdb80 | 0x7fac9be243c0 | 16491703356334 | 16491703364690 | 16491703544528 | 16491703546117 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 56 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 16 | 24 | 25536 | 0x7facac6cda00 | 0x7fac9be24400 | 16491703565946 | 16491703576688 | 16491703757486 | 16491703759009 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 59 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26240 | 0x7facac6cd880 | 0x7fac9be24440 | 16491703776228 | 16491703808046 | 16491703901645 | 16491703903583 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 62 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26944 | 0x7facac6cd700 | 0x7fac9be24480 | 16491703925742 | 16491703935884 | 16491704029324 | 16491704030839 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 65 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 27648 | 0x7facba5de580 | 0x7fac9be244c0 | 16491704052158 | 16491704063243 | 16491704156202 | 16491704157864 |
| 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 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 16 | 24 | 28608 | 0x7facba5de400 | 0x7fac9be24500 | 16491704175733 | 16491704184362 | 16491704363721 | 16491704365356 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 71 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 16 | 24 | 29312 | 0x7facba5de280 | 0x7fac9be24540 | 16491704381425 | 16491704390600 | 16491704572839 | 16491704574058 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 74 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 30016 | 0x7facba5de100 | 0x7fac9be24580 | 16491704588888 | 16491704597318 | 16491704689638 | 16491704690714 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 77 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 8 | 24 | 30976 | 0x7facac6cdf80 | 0x7fac9be245c0 | 16491704706453 | 16491704714437 | 16491704806597 | 16491704807779 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 80 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 31680 | 0x7facac6cde00 | 0x7fac9be24600 | 16491704829379 | 16491704840356 | 16491704933955 | 16491704935055 |
| 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 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 16 | 24 | 32640 | 0x7facac6cdc80 | 0x7fac9be24640 | 16491704949804 | 16491704958435 | 16491705139393 | 16491705140357 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 86 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 33600 | 0x7facac6cdb00 | 0x7fac9be24680 | 16491705154926 | 16491705162913 | 16491705343392 | 16491705344549 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 89 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 34560 | 0x7facac6cd980 | 0x7fac9be246c0 | 16491705358819 | 16491705366911 | 16491705459871 | 16491705460885 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 92 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 8 | 24 | 35520 | 0x7facac6cd800 | 0x7fac9be24700 | 16491705474584 | 16491705482910 | 16491705576669 | 16491705577780 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 95 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 36224 | 0x7facac6cd680 | 0x7fac9be24740 | 16491705598800 | 16491705608669 | 16491705702588 | 16491705703716 |
| 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 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 37184 | 0x7facba5de500 | 0x7fac9be24780 | 16491705719765 | 16491705728028 | 16491705908186 | 16491705909288 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 101 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 38144 | 0x7facba5de380 | 0x7fac9be247c0 | 16491705923458 | 16491705932346 | 16491706112505 | 16491706113680 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 104 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 39104 | 0x7facba5de200 | 0x7fac9be24800 | 16491706130090 | 16491706138744 | 16491706232663 | 16491706233736 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 107 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 8 | 24 | 40320 | 0x7facba5de080 | 0x7fac9be24840 | 16491706248015 | 16491706256023 | 16491706350582 | 16491706351581 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 110 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 41280 | 0x7facac6cdf00 | 0x7fac9be24880 | 16491706370631 | 16491706383382 | 16491706476181 | 16491706477217 |
| 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 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 42240 | 0x7facac6cdd80 | 0x7fac9be248c0 | 16491706493226 | 16491706501301 | 16491706679699 | 16491706680729 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 116 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 43200 | 0x7facac6cdc00 | 0x7fac9be24900 | 16491706694639 | 16491706702579 | 16491706882897 | 16491706884051 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 119 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 8 | 24 | 44160 | 0x7facac6cda80 | 0x7fac9be24940 | 16491706898181 | 16491706906737 | 16491707001296 | 16491707002347 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 122 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 45376 | 0x7facac6cd900 | 0x7fac9be24980 | 16491707016507 | 16491707024656 | 16491707118415 | 16491707119423 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 125 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 46336 | 0x7facac6cd780 | 0x7fac9be249c0 | 16491707138912 | 16491707150415 | 16491707244654 | 16491707245678 |
| 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 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 47552 | 0x7facac6cd600 | 0x7fac9be24a00 | 16491707259877 | 16491707268654 | 16491707448972 | 16491707449870 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 131 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 48512 | 0x7facba5de480 | 0x7fac9be24a40 | 16491707463490 | 16491707472012 | 16491707653130 | 16491707654223 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 134 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 8 | 24 | 49472 | 0x7facba5de300 | 0x7fac9be24a80 | 16491707667662 | 16491707676650 | 16491707769929 | 16491707771008 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 137 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 50688 | 0x7facba5de180 | 0x7fac9be24ac0 | 16491707785068 | 16491707794569 | 16491707887688 | 16491707888754 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 140 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 51648 | 0x7facba5de000 | 0x7fac9be24b00 | 16491707909933 | 16491707920968 | 16491708012487 | 16491708013659 |
| 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 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 52864 | 0x7facac6cde80 | 0x7fac9be24b40 | 16491708029368 | 16491708037607 | 16491708216485 | 16491708217631 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 146 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 54080 | 0x7facac6cdd00 | 0x7fac9be24b80 | 16491708231321 | 16491708240325 | 16491708420803 | 16491708421894 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 149 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 8 | 24 | 55296 | 0x7facac6cdb80 | 0x7fac9be24bc0 | 16491708436013 | 16491708445123 | 16491708539202 | 16491708540329 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 152 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 56768 | 0x7facac6cda00 | 0x7fac9be24c00 | 16491708554389 | 16491708562882 | 16491708659041 | 16491708660065 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 155 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 57728 | 0x7facac6cd880 | 0x7fac9be24c40 | 16491708679834 | 16491708690881 | 16491708785440 | 16491708786500 |
| 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 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 58944 | 0x7facac6cd700 | 0x7fac9be24c80 | 16491708801150 | 16491708809280 | 16491708988638 | 16491708989752 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 161 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 60160 | 0x7facba5de580 | 0x7fac9be24cc0 | 16491709003732 | 16491709011998 | 16491709192796 | 16491709193745 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 164 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 8 | 24 | 61376 | 0x7facba5de400 | 0x7fac9be24d00 | 16491709207834 | 16491709216156 | 16491709311515 | 16491709312650 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 167 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 62848 | 0x7facba5de280 | 0x7fac9be24d40 | 16491709327730 | 16491709336475 | 16491709436314 | 16491709437326 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 170 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 63808 | 0x7facba5de100 | 0x7fac9be24d80 | 16491709458155 | 16491709469114 | 16491709562073 | 16491709563191 |
| 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 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 65024 | 0x7facac6cdf80 | 0x7fac9be24dc0 | 16491709588540 | 16491709599513 | 16491709779351 | 16491709780503 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 176 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 66240 | 0x7facac6cde00 | 0x7fac9be24e00 | 16491709795892 | 16491709804151 | 16491709985749 | 16491709986775 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 179 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 8 | 24 | 67456 | 0x7facac6cdc80 | 0x7fac9be24e40 | 16491710000935 | 16491710009429 | 16491710103988 | 16491710104911 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 182 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 68928 | 0x7facac6cdb00 | 0x7fac9be24e80 | 16491710120020 | 16491710128308 | 16491710232467 | 16491710233686 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 185 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 70144 | 0x7facac6cd980 | 0x7fac9be24ec0 | 16491710254295 | 16491710265267 | 16491710358066 | 16491710359141 |
| 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 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 71616 | 0x7facac6cd800 | 0x7fac9be24f00 | 16491710373651 | 16491710381905 | 16491710561104 | 16491710562173 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 191 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 72832 | 0x7facac6cd680 | 0x7fac9be24f40 | 16491710576983 | 16491710585744 | 16491710766062 | 16491710767186 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 194 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 8 | 24 | 74048 | 0x7facba5de500 | 0x7fac9be24f80 | 16491710782125 | 16491710790222 | 16491710883821 | 16491710884971 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 197 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 75776 | 0x7facba5de380 | 0x7fac9be24fc0 | 16491710899821 | 16491710908141 | 16491711015180 | 16491711016276 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 200 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 76992 | 0x7facba5de200 | 0x7fac9be25000 | 16491711036856 | 16491711047819 | 16491711142538 | 16491711143682 |
| 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 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 78464 | 0x7facba5de080 | 0x7fac9be25040 | 16491711158611 | 16491711166698 | 16491711346057 | 16491711347204 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 206 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 79936 | 0x7facac6cdf00 | 0x7fac9be25080 | 16491711361383 | 16491711370056 | 16491711549095 | 16491711550146 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 209 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 8 | 24 | 81408 | 0x7facac6cdd80 | 0x7fac9be250c0 | 16491711563996 | 16491711572935 | 16491711668614 | 16491711669702 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 212 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 83136 | 0x7facac6cdc00 | 0x7fac9be25100 | 16491711683091 | 16491711691173 | 16491711806372 | 16491711807397 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 215 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 84352 | 0x7facac6cda80 | 0x7fac9be25140 | 16491711843135 | 16491711852772 | 16491711947491 | 16491711948461 |
| 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 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 85824 | 0x7facac6cd900 | 0x7fac9be25180 | 16491711963951 | 16491711972291 | 16491712151809 | 16491712152814 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 221 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 87296 | 0x7facac6cd780 | 0x7fac9be251c0 | 16491712168493 | 16491712176769 | 16491712357247 | 16491712358286 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 224 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 88768 | 0x7facac6cd600 | 0x7fac9be25200 | 16491712372216 | 16491712380607 | 16491712474846 | 16491712475912 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 227 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 90752 | 0x7facba5de480 | 0x7fac9be25240 | 16491712492641 | 16491712501566 | 16491712622525 | 16491712623586 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 230 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 91968 | 0x7facba5de300 | 0x7fac9be25280 | 16491712644645 | 16491712655645 | 16491712749724 | 16491712750791 |
| 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 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 93440 | 0x7facba5de180 | 0x7fac9be252c0 | 16491712765041 | 16491712773244 | 16491712953082 | 16491712954234 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 236 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 94912 | 0x7facba5de000 | 0x7fac9be25300 | 16491712968443 | 16491712976442 | 16491713156120 | 16491713157086 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 239 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 96384 | 0x7facac6cde80 | 0x7fac9be25340 | 16491713172615 | 16491713181240 | 16491713276599 | 16491713277612 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 242 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 98368 | 0x7facac6cdd00 | 0x7fac9be25380 | 16491713293581 | 16491713301559 | 16491713428598 | 16491713429716 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 245 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 99584 | 0x7facac6cdb80 | 0x7fac9be253c0 | 16491713451185 | 16491713462197 | 16491713556756 | 16491713557871 |
| 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 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 101312 | 0x7facac6cda00 | 0x7fac9be25400 | 16491713573970 | 16491713581876 | 16491713761074 | 16491713762113 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 251 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 102784 | 0x7facac6cd880 | 0x7fac9be25440 | 16491713778003 | 16491713785874 | 16491713964593 | 16491713965686 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 254 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 104256 | 0x7facac6cd700 | 0x7fac9be25480 | 16491713980355 | 16491713988272 | 16491714082192 | 16491714083241 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 257 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 106240 | 0x7facba5de580 | 0x7fac9be254c0 | 16491714097981 | 16491714106191 | 16491714236750 | 16491714237925 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 260 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 107712 | 0x7facba5de400 | 0x7fac9be25500 | 16491714257695 | 16491714268910 | 16491714361869 | 16491714362951 |
| 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 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 16 | 24 | 109440 | 0x7facba5de280 | 0x7fac9be25540 | 16491714379490 | 16491714388269 | 16491714567467 | 16491714568553 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 266 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 16 | 24 | 111168 | 0x7facba5de100 | 0x7fac9be25580 | 16491714583633 | 16491714591787 | 16491714770505 | 16491714771615 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 269 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 8 | 24 | 112896 | 0x7facac6cdf80 | 0x7fac9be255c0 | 16491714786475 | 16491714794505 | 16491714889544 | 16491714890611 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 272 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 115136 | 0x7facac6cde00 | 0x7fac9be25600 | 16491714904110 | 16491714912264 | 16491715050663 | 16491715051735 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 275 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 116608 | 0x7facac6cdc80 | 0x7fac9be25640 | 16491715072694 | 16491715083782 | 16491715178662 | 16491715179790 |
| 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 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 16 | 24 | 118336 | 0x7facac6cdb00 | 0x7fac9be25680 | 16491715194010 | 16491715202181 | 16491715380900 | 16491715381983 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 281 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 16 | 24 | 120064 | 0x7facac6cd980 | 0x7fac9be256c0 | 16491715395562 | 16491715404419 | 16491715585538 | 16491715586655 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 284 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 121792 | 0x7facac6cd800 | 0x7fac9be25700 | 16491715600424 | 16491715609218 | 16491715706017 | 16491715707040 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 287 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 124032 | 0x7facac6cd680 | 0x7fac9be25740 | 16491715721870 | 16491715730176 | 16491715876255 | 16491715877204 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 290 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 125504 | 0x7facba5de500 | 0x7fac9be25780 | 16491715897823 | 16491715908575 | 16491716005054 | 16491716006109 |
| 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 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 127488 | 0x7facba5de380 | 0x7fac9be257c0 | 16491716019779 | 16491716028094 | 16491716209052 | 16491716210031 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 296 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 129216 | 0x7facba5de200 | 0x7fac9be25800 | 16491716224321 | 16491716232412 | 16491716414330 | 16491716415394 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 299 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 130944 | 0x7facba5de080 | 0x7fac9be25840 | 16491716428913 | 16491716438170 | 16491716537689 | 16491716538779 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 302 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 133440 | 0x7facac6cdf00 | 0x7fac9be25880 | 16491716552069 | 16491716560569 | 16491716715927 | 16491716716952 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 305 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 134912 | 0x7facac6cdd80 | 0x7fac9be258c0 | 16491716736822 | 16491716748887 | 16491716844086 | 16491716845148 |
| 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 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 136896 | 0x7facac6cdc00 | 0x7fac9be25900 | 16491716859967 | 16491716868246 | 16491717046964 | 16491717048010 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 311 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 138880 | 0x7facac6cda80 | 0x7fac9be25940 | 16491717062729 | 16491717071444 | 16491717253043 | 16491717254022 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 314 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 140864 | 0x7facac6cd900 | 0x7fac9be25980 | 16491717268682 | 16491717277522 | 16491717382801 | 16491717383887 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 317 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 143616 | 0x7facac6cd780 | 0x7fac9be259c0 | 16491717397777 | 16491717406161 | 16491717576080 | 16491717577090 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 320 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 145344 | 0x7facac6cd600 | 0x7fac9be25a00 | 16491717598369 | 16491717609039 | 16491717705358 | 16491717706375 |
| 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 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 147584 | 0x7facba5de480 | 0x7fac9be25a40 | 16491717722055 | 16491717730318 | 16491717910636 | 16491717911618 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 326 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 149568 | 0x7facba5de300 | 0x7fac9be25a80 | 16491717925577 | 16491717934316 | 16491718116395 | 16491718117550 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 329 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 151552 | 0x7facba5de180 | 0x7fac9be25ac0 | 16491718131689 | 16491718139754 | 16491718249993 | 16491718250955 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 332 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 154304 | 0x7facba5de000 | 0x7fac9be25b00 | 16491718264864 | 16491718272873 | 16491718453992 | 16491718455317 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 335 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 156288 | 0x7facac6cde80 | 0x7fac9be25b40 | 16491718475617 | 16491718485991 | 16491718586790 | 16491718587942 |
| 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 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 158784 | 0x7facac6cdd00 | 0x7fac9be25b80 | 16491718603012 | 16491718610950 | 16491718796228 | 16491718797305 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 341 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 161024 | 0x7facac6cdb80 | 0x7fac9be25bc0 | 16491718810204 | 16491718818468 | 16491719004386 | 16491719005467 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 344 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 163264 | 0x7facac6cda00 | 0x7fac9be25c00 | 16491719023856 | 16491719032066 | 16491719154305 | 16491719155381 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 347 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 166528 | 0x7facac6cd880 | 0x7fac9be25c40 | 16491719170881 | 16491719178945 | 16491719385823 | 16491719406452 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 350 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 168512 | 0x7facac6cd700 | 0x7fac9be25c80 | 16491719421991 | 16491719433183 | 16491719543742 | 16491719544877 |
| 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 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 171264 | 0x7facba5de580 | 0x7fac9be25cc0 | 16491719560356 | 16491719569341 | 16491719750940 | 16491719752029 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 356 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 173760 | 0x7facba5de400 | 0x7fac9be25d00 | 16491719765558 | 16491719773979 | 16491719961338 | 16491719962341 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 359 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 176256 | 0x7facba5de280 | 0x7fac9be25d40 | 16491719977100 | 16491719985817 | 16491720120216 | 16491720121355 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 362 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 179776 | 0x7facba5de100 | 0x7fac9be25d80 | 16491720134605 | 16491720142936 | 16491720375414 | 16491720394535 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 365 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 182272 | 0x7facac6cdf80 | 0x7fac9be25dc0 | 16491720408734 | 16491720419894 | 16491720546452 | 16491720547499 |
| 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 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 185536 | 0x7facac6cde00 | 0x7fac9be25e00 | 16491720561819 | 16491720570292 | 16491720761330 | 16491720762321 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 371 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 188544 | 0x7facac6cdc80 | 0x7fac9be25e40 | 16491720775631 | 16491720784370 | 16491720977488 | 16491720978523 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 374 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 191552 | 0x7facac6cdb00 | 0x7fac9be25e80 | 16491720992243 | 16491721000688 | 16491721160687 | 16491721161776 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 377 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 195840 | 0x7facac6cd980 | 0x7fac9be25ec0 | 16491721176036 | 16491721184207 | 16491721468044 | 16491721483854 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 380 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 198592 | 0x7facac6cd800 | 0x7fac9be25f00 | 16491721498564 | 16491721509484 | 16491721659722 | 16491721660888 |
| 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 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 202368 | 0x7facac6cd680 | 0x7fac9be25f40 | 16491721678437 | 16491721686122 | 16491721894440 | 16491721910108 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 386 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 205888 | 0x7facba5de500 | 0x7fac9be25f80 | 16491721917948 | 16491721928520 | 16491722138598 | 16491722152009 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 389 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 209408 | 0x7facba5de380 | 0x7fac9be25fc0 | 16491722160279 | 16491722170597 | 16491722356516 | 16491722357791 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 392 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 214464 | 0x7facba5de200 | 0x7fac9be26000 | 16491722372401 | 16491722380356 | 16491722714912 | 16491722758916 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 395 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 217728 | 0x7facba5de080 | 0x7fac9be26040 | 16491722774476 | 16491722785152 | 16491722952510 | 16491722953579 |
| 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 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 222016 | 0x7facac6cdf00 | 0x7fac9be26080 | 16491722968439 | 16491722976670 | 16491723203548 | 16491723246418 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 401 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 226048 | 0x7facac6cdd80 | 0x7fac9be260c0 | 16491723253528 | 16491723264347 | 16491723495065 | 16491723537557 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 404 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 230080 | 0x7facac6cdc00 | 0x7fac9be26100 | 16491723545587 | 16491723556345 | 16491723768023 | 16491723807447 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 407 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 235904 | 0x7facac6cda80 | 0x7fac9be26140 | 16491723815997 | 16491723825622 | 16491724211059 | 16491724250430 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 410 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 239424 | 0x7facac6cd900 | 0x7fac9be26180 | 16491724265480 | 16491724277298 | 16491724464656 | 16491724465762 |
| 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 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 244224 | 0x7facac6cd780 | 0x7fac9be261c0 | 16491724480262 | 16491724488336 | 16491724738894 | 16491724782010 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 416 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 248768 | 0x7facac6cd600 | 0x7fac9be26200 | 16491724790620 | 16491724800973 | 16491725047051 | 16491725087919 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 419 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 253312 | 0x7facba5de480 | 0x7fac9be26240 | 16491725095869 | 16491725106571 | 16491725343368 | 16491725384438 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 422 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 8 | 24 | 255552 | 0x7facba5de300 | 0x7fac9be26280 | 16491725392338 | 16491725402888 | 16491725856484 | 16491725897549 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 425 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 259840 | 0x7facba5de180 | 0x7fac9be262c0 | 16491725912788 | 16491725923523 | 16491726149601 | 16491726191678 |
| 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 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 265664 | 0x7facba5de000 | 0x7fac9be26300 | 16491726202317 | 16491726213280 | 16491726511198 | 16491726552554 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 431 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 271232 | 0x7facac6cde80 | 0x7fac9be26340 | 16491726563724 | 16491726573277 | 16491726872954 | 16491726917380 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 434 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 8 | 24 | 273216 | 0x7facac6cdd00 | 0x7fac9be26380 | 16491726926900 | 16491726937594 | 16491727234071 | 16491727278237 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 437 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 8 | 24 | 275712 | 0x7facac6cdb80 | 0x7fac9be263c0 | 16491727286236 | 16491727296951 | 16491727855505 | 16491727897094 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 440 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 280768 | 0x7facac6cda00 | 0x7fac9be26400 | 16491727913003 | 16491727923825 | 16491728187342 | 16491728229891 |
| 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 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 287616 | 0x7facac6cd880 | 0x7fac9be26440 | 16491728237961 | 16491728248462 | 16491728599499 | 16491728645665 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 446 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 294208 | 0x7facac6cd700 | 0x7fac9be26480 | 16491728653205 | 16491728668138 | 16491729019175 | 16491729061970 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 449 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 8 | 24 | 296960 | 0x7facba5de580 | 0x7fac9be264c0 | 16491729069830 | 16491729080614 | 16491729427651 | 16491729467005 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 452 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 8 | 24 | 299968 | 0x7facba5de400 | 0x7fac9be26500 | 16491729475624 | 16491729485890 | 16491730146364 | 16491730194407 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 455 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 8 | 24 | 302720 | 0x7facba5de280 | 0x7fac9be26540 | 16491730211017 | 16491730221084 | 16491730669240 | 16491730714328 |
| 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 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 305472 | 0x7facba5de100 | 0x7fac9be26580 | 16491730721628 | 16491730732439 | 16491731198195 | 16491731241048 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 461 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 308224 | 0x7facac6cdf80 | 0x7fac9be265c0 | 16491731248568 | 16491731259314 | 16491731720590 | 16491731763608 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 464 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 8 | 24 | 310976 | 0x7facac6cde00 | 0x7fac9be26600 | 16491731771288 | 16491731782189 | 16491732234985 | 16491732277629 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 467 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 8 | 24 | 313216 | 0x7facac6cdc80 | 0x7fac9be26640 | 16491732285679 | 16491732296105 | 16491733166497 | 16491733209524 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 470 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 8 | 24 | 315968 | 0x7facac6cdb00 | 0x7fac9be26680 | 16491733225584 | 16491733236416 | 16491734091288 | 16491734118500 |
| 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 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 318720 | 0x7facac6cd980 | 0x7fac9be266c0 | 16491734128120 | 16491734138328 | 16491735023600 | 16491735068164 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 476 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 321472 | 0x7facac6cd800 | 0x7fac9be26700 | 16491735076974 | 16491735087279 | 16491735967751 | 16491736015109 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 479 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 8 | 24 | 324224 | 0x7facac6cd680 | 0x7fac9be26740 | 16491736024449 | 16491736034631 | 16491736894943 | 16491736938084 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 482 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 8 | 24 | 326464 | 0x7facba5de500 | 0x7fac9be26780 | 16491736945864 | 16491736956542 | 16491738656366 | 16491738724537 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 485 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 8 | 24 | 329216 | 0x7facba5de380 | 0x7fac9be267c0 | 16491738741487 | 16491738752046 | 16491740418430 | 16491740486931 |
| 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 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 331968 | 0x7facba5de200 | 0x7fac9be26800 | 16491740497931 | 16491740517629 | 16491742244014 | 16491742318192 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 491 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 12 | 24 | 334720 | 0x7facba5de080 | 0x7fac9be26840 | 16491742327872 | 16491742338413 | 16491744054237 | 16491744121015 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 494 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 8 | 24 | 337472 | 0x7facac6cdf00 | 0x7fac9be26880 | 16491744132074 | 16491744147036 | 16491745821901 | 16491745894138 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 497 | 161495 | 161495 | 4194304 | 256 | 0 | 0 | 8 | 24 | 0 | 0x7facac6cdd80 | 0x7fac9be268c0 | 16491745901928 | 16491745913580 | 16491749271309 | 16491749343199 |