41 KiB
41 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | SQ_INSTS_SMEM | SQ_INST_LEVEL_SMEM | SQ_ACCUM_PREV_HIRES | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBufferAligned.kd | 0 | 0 | 0 | 199978 | 199978 | 33554432 | 256 | 0 | 0 | 4 | 32 | 4160 | 0x0 | 0x7fe1d2a04280 | 3670016 | 3040452 | 340321896 | 17229574411755 | 17224026851585 | 17229723837237 | 17229723948727 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 199978 | 199978 | 32768 | 256 | 0 | 0 | 12 | 24 | 13888 | 0x0 | 0x7fe1d2a23f80 | 512 | 97598 | 10948992 | 17229729109777 | 17229723837237 | 17229729235641 | 17229729240263 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 5 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 14336 | 0x7fe1d5a50380 | 0x7fe1d2a23fc0 | 65536 | 619714 | 69394784 | 17229729274252 | 17229729235641 | 17229729595641 | 17229729597774 |
| 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 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15040 | 0x7fe1d5a50200 | 0x7fe1d2a24000 | 65536 | 650318 | 72879808 | 17229729633863 | 17229729595641 | 17229729997881 | 17229729999983 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 11 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15488 | 0x7fe1d5a50080 | 0x7fe1d2a24040 | 65536 | 660540 | 73841616 | 17229730033752 | 17229729997881 | 17229730405402 | 17229730407522 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 14 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 15936 | 0x7fe1d32edf00 | 0x7fe1d2a24080 | 65536 | 651524 | 72958416 | 17229730439761 | 17229730405402 | 17229730712282 | 17229730714413 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 17 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 16384 | 0x7fe1d32edd80 | 0x7fe1d2a240c0 | 65536 | 621762 | 69629072 | 17229730746023 | 17229730712282 | 17229731016282 | 17229731018485 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 20 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 17088 | 0x7fe1d32edc00 | 0x7fe1d2a24100 | 131072 | 658036 | 73785048 | 17229731061514 | 17229731016282 | 17229731318682 | 17229731320617 |
| 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 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 16 | 24 | 17792 | 0x7fe1d32eda80 | 0x7fe1d2a24140 | 131072 | 692714 | 77624960 | 17229731352936 | 17229731318682 | 17229731705403 | 17229731707457 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 26 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 16 | 24 | 18496 | 0x7fe1d32ed900 | 0x7fe1d2a24180 | 65536 | 657794 | 73816888 | 17229731738516 | 17229731705403 | 17229732092283 | 17229732094766 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 29 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19200 | 0x7fe1d32ed780 | 0x7fe1d2a241c0 | 131072 | 696868 | 78111816 | 17229732125465 | 17229732092283 | 17229732405083 | 17229732407348 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 32 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19904 | 0x7fe1d32ed600 | 0x7fe1d2a24200 | 131072 | 688984 | 77089720 | 17229732439337 | 17229732405083 | 17229732705243 | 17229732707560 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 35 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 20608 | 0x7fe1d5a50480 | 0x7fe1d2a24240 | 131072 | 697572 | 78205352 | 17229732747848 | 17229732705243 | 17229733005084 | 17229733007491 |
| 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 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 16 | 24 | 21312 | 0x7fe1d5a50300 | 0x7fe1d2a24280 | 131072 | 699686 | 78315120 | 17229733039281 | 17229733005084 | 17229733392284 | 17229733394351 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 41 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22016 | 0x7fe1d5a50180 | 0x7fe1d2a242c0 | 65536 | 661136 | 74060040 | 17229733425900 | 17229733392284 | 17229733781084 | 17229733783221 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 44 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22720 | 0x7fe1d5a50000 | 0x7fe1d2a24300 | 131072 | 692774 | 77575808 | 17229733814700 | 17229733781084 | 17229734081405 | 17229734103252 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 47 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 23424 | 0x7fe1d32ede80 | 0x7fe1d2a24340 | 131072 | 696002 | 77982304 | 17229734116062 | 17229734081405 | 17229734400765 | 17229734403004 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 50 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 24128 | 0x7fe1d32edd00 | 0x7fe1d2a24380 | 131072 | 694870 | 77780424 | 17229734442153 | 17229734400765 | 17229734703485 | 17229734705525 |
| 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 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 16 | 24 | 24832 | 0x7fe1d32edb80 | 0x7fe1d2a243c0 | 131072 | 693142 | 77612224 | 17229734737245 | 17229734703485 | 17229735078845 | 17229735080325 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 56 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 16 | 24 | 25536 | 0x7fe1d32eda00 | 0x7fe1d2a24400 | 65536 | 632122 | 70739888 | 17229735111904 | 17229735078845 | 17229735442526 | 17229735444085 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 59 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26240 | 0x7fe1d32ed880 | 0x7fe1d2a24440 | 131072 | 696514 | 78115888 | 17229735474235 | 17229735442526 | 17229735713406 | 17229735714958 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 62 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26944 | 0x7fe1d32ed700 | 0x7fe1d2a24480 | 131072 | 697122 | 78073464 | 17229735745907 | 17229735713406 | 17229735988926 | 17229735990371 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 65 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 27648 | 0x7fe1d5a50580 | 0x7fe1d2a244c0 | 131072 | 656260 | 73458768 | 17229736028670 | 17229735988926 | 17229736267966 | 17229736269463 |
| 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 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 16 | 24 | 28608 | 0x7fe1d5a50400 | 0x7fe1d2a24500 | 131072 | 694092 | 77729424 | 17229736300782 | 17229736267966 | 17229736628127 | 17229736629553 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 71 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 16 | 24 | 29312 | 0x7fe1d5a50280 | 0x7fe1d2a24540 | 65536 | 653480 | 73120032 | 17229736661042 | 17229736628127 | 17229736987807 | 17229736989253 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 74 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 30016 | 0x7fe1d5a50100 | 0x7fe1d2a24580 | 131072 | 651654 | 72963520 | 17229737021073 | 17229736987807 | 17229737259327 | 17229737260826 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 77 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 8 | 24 | 30976 | 0x7fe1d32edf80 | 0x7fe1d2a245c0 | 131072 | 676638 | 75862016 | 17229737292915 | 17229737259327 | 17229737536287 | 17229737537729 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 80 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 31680 | 0x7fe1d32ede00 | 0x7fe1d2a24600 | 131072 | 697408 | 78157968 | 17229737575827 | 17229737536287 | 17229737809728 | 17229737811211 |
| 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 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 16 | 24 | 32640 | 0x7fe1d32edc80 | 0x7fe1d2a24640 | 131072 | 651490 | 72953896 | 17229737842360 | 17229737809728 | 17229738171808 | 17229738173581 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 86 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 33600 | 0x7fe1d32edb00 | 0x7fe1d2a24680 | 65536 | 647570 | 72530616 | 17229738204170 | 17229738171808 | 17229738538688 | 17229738540131 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 89 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 34560 | 0x7fe1d32ed980 | 0x7fe1d2a246c0 | 131072 | 695336 | 77882328 | 17229738570871 | 17229738538688 | 17229738812928 | 17229738814384 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 92 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 8 | 24 | 35520 | 0x7fe1d32ed800 | 0x7fe1d2a24700 | 131072 | 692392 | 77567480 | 17229738845563 | 17229738812928 | 17229739087329 | 17229739088797 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 95 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 36224 | 0x7fe1d32ed680 | 0x7fe1d2a24740 | 131072 | 686996 | 77028992 | 17229739127145 | 17229739087329 | 17229739365409 | 17229739366779 |
| 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 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 37184 | 0x7fe1d5a50500 | 0x7fe1d2a24780 | 131072 | 650852 | 72891072 | 17229739397518 | 17229739365409 | 17229739726209 | 17229739727719 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 101 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 38144 | 0x7fe1d5a50380 | 0x7fe1d2a247c0 | 65536 | 652532 | 73094752 | 17229739759308 | 17229739726209 | 17229740085089 | 17229740086490 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 104 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 39104 | 0x7fe1d5a50200 | 0x7fe1d2a24800 | 131072 | 688218 | 77136928 | 17229740117329 | 17229740085089 | 17229740358210 | 17229740359662 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 107 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 8 | 24 | 40320 | 0x7fe1d5a50080 | 0x7fe1d2a24840 | 131072 | 689854 | 77240728 | 17229740391301 | 17229740358210 | 17229740630690 | 17229740632135 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 110 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 41280 | 0x7fe1d32edf00 | 0x7fe1d2a24880 | 131072 | 698612 | 78183104 | 17229740670384 | 17229740630690 | 17229740907970 | 17229740909567 |
| 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 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 42240 | 0x7fe1d32edd80 | 0x7fe1d2a248c0 | 131072 | 688732 | 77205936 | 17229740939887 | 17229740907970 | 17229741283490 | 17229741285027 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 116 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 43200 | 0x7fe1d32edc00 | 0x7fe1d2a24900 | 65536 | 643360 | 72084848 | 17229741316056 | 17229741283490 | 17229741644931 | 17229741646397 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 119 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 8 | 24 | 44160 | 0x7fe1d32eda80 | 0x7fe1d2a24940 | 131072 | 694312 | 77835328 | 17229741677187 | 17229741644931 | 17229741917571 | 17229741919010 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 122 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 45376 | 0x7fe1d32ed900 | 0x7fe1d2a24980 | 131072 | 690512 | 77344248 | 17229741949439 | 17229741917571 | 17229742203331 | 17229742204862 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 125 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 46336 | 0x7fe1d32ed780 | 0x7fe1d2a249c0 | 131072 | 694344 | 77807592 | 17229742242981 | 17229742203331 | 17229742487171 | 17229742488715 |
| 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 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 47552 | 0x7fe1d32ed600 | 0x7fe1d2a24a00 | 131072 | 699456 | 78338704 | 17229742520354 | 17229742487171 | 17229742848132 | 17229742849545 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 131 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 48512 | 0x7fe1d5a50480 | 0x7fe1d2a24a40 | 65536 | 655170 | 73448704 | 17229742881104 | 17229742848132 | 17229743205252 | 17229743206795 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 134 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 8 | 24 | 49472 | 0x7fe1d5a50300 | 0x7fe1d2a24a80 | 131072 | 657420 | 73669896 | 17229743238224 | 17229743205252 | 17229743478372 | 17229743479828 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 137 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 50688 | 0x7fe1d5a50180 | 0x7fe1d2a24ac0 | 131072 | 655534 | 73262024 | 17229743511727 | 17229743478372 | 17229743749092 | 17229743750621 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 140 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 51648 | 0x7fe1d5a50000 | 0x7fe1d2a24b00 | 131072 | 653462 | 73291488 | 17229743789280 | 17229743749092 | 17229744033732 | 17229744035243 |
| 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 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 52864 | 0x7fe1d32ede80 | 0x7fe1d2a24b40 | 131072 | 701236 | 78512344 | 17229744067372 | 17229744033732 | 17229744392773 | 17229744394223 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 146 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 54080 | 0x7fe1d32edd00 | 0x7fe1d2a24b80 | 65536 | 651740 | 72963632 | 17229744425492 | 17229744392773 | 17229744750853 | 17229744752374 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 149 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 8 | 24 | 55296 | 0x7fe1d32edb80 | 0x7fe1d2a24bc0 | 131072 | 690970 | 77444424 | 17229744783923 | 17229744750853 | 17229745023333 | 17229745024756 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 152 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 56768 | 0x7fe1d32eda00 | 0x7fe1d2a24c00 | 131072 | 691894 | 77577944 | 17229745055765 | 17229745023333 | 17229745297893 | 17229745299439 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 155 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 57728 | 0x7fe1d32ed880 | 0x7fe1d2a24c40 | 131072 | 690332 | 77267912 | 17229745337298 | 17229745297893 | 17229745570854 | 17229745572301 |
| 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 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 58944 | 0x7fe1d32ed700 | 0x7fe1d2a24c80 | 131072 | 650030 | 72785448 | 17229745603361 | 17229745570854 | 17229745930054 | 17229745931472 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 161 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 60160 | 0x7fe1d5a50580 | 0x7fe1d2a24cc0 | 65536 | 648214 | 72658440 | 17229745962451 | 17229745930054 | 17229746297734 | 17229746299172 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 164 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 8 | 24 | 61376 | 0x7fe1d5a50400 | 0x7fe1d2a24d00 | 131072 | 694088 | 77665712 | 17229746330791 | 17229746297734 | 17229746577095 | 17229746578664 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 167 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 62848 | 0x7fe1d5a50280 | 0x7fe1d2a24d40 | 131072 | 697236 | 78081184 | 17229746610213 | 17229746577095 | 17229746857575 | 17229746859106 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 170 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 63808 | 0x7fe1d5a50100 | 0x7fe1d2a24d80 | 131072 | 691432 | 77482472 | 17229746898285 | 17229746857575 | 17229747131335 | 17229747132849 |
| 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 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 65024 | 0x7fe1d32edf80 | 0x7fe1d2a24dc0 | 131072 | 647160 | 72396728 | 17229747164348 | 17229747131335 | 17229747487815 | 17229747489279 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 176 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 66240 | 0x7fe1d32ede00 | 0x7fe1d2a24e00 | 65536 | 622286 | 69678184 | 17229747520279 | 17229747487815 | 17229747845416 | 17229747846890 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 179 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 8 | 24 | 67456 | 0x7fe1d32edc80 | 0x7fe1d2a24e40 | 131072 | 695708 | 77973768 | 17229747877299 | 17229747845416 | 17229748117896 | 17229748119392 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 182 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 68928 | 0x7fe1d32edb00 | 0x7fe1d2a24e80 | 131072 | 692924 | 77692848 | 17229748150211 | 17229748117896 | 17229748399336 | 17229748400855 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 185 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 70144 | 0x7fe1d32ed980 | 0x7fe1d2a24ec0 | 131072 | 654402 | 73185312 | 17229748438944 | 17229748399336 | 17229748673896 | 17229748675347 |
| 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 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 71616 | 0x7fe1d32ed800 | 0x7fe1d2a24f00 | 131072 | 703178 | 78741424 | 17229748706376 | 17229748673896 | 17229749034696 | 17229749036317 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 191 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 72832 | 0x7fe1d32ed680 | 0x7fe1d2a24f40 | 65536 | 658376 | 73762752 | 17229749067076 | 17229749034696 | 17229749395497 | 17229749396898 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 194 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 8 | 24 | 74048 | 0x7fe1d5a50500 | 0x7fe1d2a24f80 | 131072 | 654188 | 73164320 | 17229749427517 | 17229749395497 | 17229749672617 | 17229749674240 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 197 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 75776 | 0x7fe1d5a50380 | 0x7fe1d2a24fc0 | 131072 | 651998 | 73052896 | 17229749704559 | 17229749672617 | 17229749960617 | 17229749962062 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 200 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 76992 | 0x7fe1d5a50200 | 0x7fe1d2a25000 | 131072 | 693448 | 77708360 | 17229750000561 | 17229749960617 | 17229750248297 | 17229750250064 |
| 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 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 78464 | 0x7fe1d5a50080 | 0x7fe1d2a25040 | 131072 | 698358 | 78132256 | 17229750280964 | 17229750248297 | 17229750610698 | 17229750612285 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 206 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 79936 | 0x7fe1d32edf00 | 0x7fe1d2a25080 | 65536 | 656022 | 73489312 | 17229750644654 | 17229750610698 | 17229750969258 | 17229750970705 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 209 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 8 | 24 | 81408 | 0x7fe1d32edd80 | 0x7fe1d2a250c0 | 131072 | 687656 | 77075208 | 17229751001264 | 17229750969258 | 17229751241418 | 17229751242788 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 212 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 83136 | 0x7fe1d32edc00 | 0x7fe1d2a25100 | 131072 | 694816 | 77855688 | 17229751273967 | 17229751241418 | 17229751536618 | 17229751538090 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 215 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 84352 | 0x7fe1d32eda80 | 0x7fe1d2a25140 | 131072 | 723126 | 80993576 | 17229751588728 | 17229751536618 | 17229751815979 | 17229751817492 |
| 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 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 85824 | 0x7fe1d32ed900 | 0x7fe1d2a25180 | 131072 | 695490 | 77934520 | 17229751847561 | 17229751815979 | 17229752179179 | 17229752180572 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 221 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 87296 | 0x7fe1d32ed780 | 0x7fe1d2a251c0 | 65536 | 665304 | 74530984 | 17229752211071 | 17229752179179 | 17229752545099 | 17229752546532 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 224 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 88768 | 0x7fe1d32ed600 | 0x7fe1d2a25200 | 131072 | 690002 | 77289808 | 17229752577211 | 17229752545099 | 17229752817419 | 17229752818915 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 227 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 90752 | 0x7fe1d5a50480 | 0x7fe1d2a25240 | 131072 | 690972 | 77398064 | 17229752849594 | 17229752817419 | 17229753116460 | 17229753117937 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 230 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 91968 | 0x7fe1d5a50300 | 0x7fe1d2a25280 | 131072 | 693782 | 77700432 | 17229753155996 | 17229753116460 | 17229753389900 | 17229753391319 |
| 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 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 93440 | 0x7fe1d5a50180 | 0x7fe1d2a252c0 | 131072 | 680758 | 76218616 | 17229753421929 | 17229753389900 | 17229753751180 | 17229753752650 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 236 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 94912 | 0x7fe1d5a50000 | 0x7fe1d2a25300 | 65536 | 658788 | 73721336 | 17229753785469 | 17229753751180 | 17229754117581 | 17229754119130 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 239 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 96384 | 0x7fe1d32ede80 | 0x7fe1d2a25340 | 131072 | 691942 | 77554056 | 17229754150369 | 17229754117581 | 17229754396941 | 17229754398312 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 242 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 98368 | 0x7fe1d32edd00 | 0x7fe1d2a25380 | 131072 | 688758 | 77187880 | 17229754428951 | 17229754396941 | 17229754705101 | 17229754706604 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 245 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 99584 | 0x7fe1d32edb80 | 0x7fe1d2a253c0 | 131072 | 691104 | 77372464 | 17229754744113 | 17229754705101 | 17229754981261 | 17229754982856 |
| 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 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 101312 | 0x7fe1d32eda00 | 0x7fe1d2a25400 | 131072 | 649638 | 72733736 | 17229755013586 | 17229754981261 | 17229755348461 | 17229755349957 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 251 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 102784 | 0x7fe1d32ed880 | 0x7fe1d2a25440 | 65536 | 657900 | 73651048 | 17229755380396 | 17229755348461 | 17229755711502 | 17229755713037 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 254 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 104256 | 0x7fe1d32ed700 | 0x7fe1d2a25480 | 131072 | 703028 | 78742840 | 17229755743076 | 17229755711502 | 17229755987502 | 17229755988979 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 257 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 106240 | 0x7fe1d5a50580 | 0x7fe1d2a254c0 | 131072 | 653618 | 73344056 | 17229756019558 | 17229755987502 | 17229756298382 | 17229756299841 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 260 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 107712 | 0x7fe1d5a50400 | 0x7fe1d2a25500 | 131072 | 642784 | 71979936 | 17229756337770 | 17229756298382 | 17229756577262 | 17229756578843 |
| 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 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 16 | 24 | 109440 | 0x7fe1d5a50280 | 0x7fe1d2a25540 | 131072 | 711360 | 79613480 | 17229756610223 | 17229756577262 | 17229756935823 | 17229756937314 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 266 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 16 | 24 | 111168 | 0x7fe1d5a50100 | 0x7fe1d2a25580 | 65536 | 648064 | 72613816 | 17229756968403 | 17229756935823 | 17229757294703 | 17229757296194 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 269 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 8 | 24 | 112896 | 0x7fe1d32edf80 | 0x7fe1d2a255c0 | 131072 | 695014 | 77748400 | 17229757326353 | 17229757294703 | 17229757569903 | 17229757571307 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 272 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 115136 | 0x7fe1d32ede00 | 0x7fe1d2a25600 | 131072 | 686958 | 77029112 | 17229757601606 | 17229757569903 | 17229757889104 | 17229757890628 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 275 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 116608 | 0x7fe1d32edc80 | 0x7fe1d2a25640 | 131072 | 692630 | 77680104 | 17229757928397 | 17229757889104 | 17229758166704 | 17229758168340 |
| 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 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 16 | 24 | 118336 | 0x7fe1d32edb00 | 0x7fe1d2a25680 | 131072 | 694774 | 77900120 | 17229758198560 | 17229758166704 | 17229758539504 | 17229758541150 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 281 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 16 | 24 | 120064 | 0x7fe1d32ed980 | 0x7fe1d2a256c0 | 65536 | 648832 | 72663616 | 17229758571899 | 17229758539504 | 17229758897104 | 17229758898601 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 284 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 121792 | 0x7fe1d32ed800 | 0x7fe1d2a25700 | 131072 | 699648 | 78385872 | 17229758929200 | 17229758897104 | 17229759172305 | 17229759173773 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 287 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 124032 | 0x7fe1d32ed680 | 0x7fe1d2a25740 | 131072 | 688894 | 77158496 | 17229759204292 | 17229759172305 | 17229759493265 | 17229759494544 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 290 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 125504 | 0x7fe1d5a50500 | 0x7fe1d2a25780 | 131072 | 702652 | 78755024 | 17229759532313 | 17229759493265 | 17229759764625 | 17229759766167 |
| 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 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 127488 | 0x7fe1d5a50380 | 0x7fe1d2a257c0 | 131072 | 693964 | 77733776 | 17229759797796 | 17229759764625 | 17229760121425 | 17229760122967 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 296 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 129216 | 0x7fe1d5a50200 | 0x7fe1d2a25800 | 65536 | 662076 | 74109832 | 17229760154256 | 17229760121425 | 17229760479986 | 17229760481618 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 299 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 130944 | 0x7fe1d5a50080 | 0x7fe1d2a25840 | 131072 | 648944 | 72639784 | 17229760513127 | 17229760479986 | 17229760758226 | 17229760759580 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 302 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 133440 | 0x7fe1d32edf00 | 0x7fe1d2a25880 | 131072 | 655580 | 73383176 | 17229760790439 | 17229760758226 | 17229761090866 | 17229761092411 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 305 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 134912 | 0x7fe1d32edd80 | 0x7fe1d2a258c0 | 131072 | 1029228 | 115501488 | 17229761131190 | 17229761090866 | 17229761370866 | 17229761372383 |
| 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 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 136896 | 0x7fe1d32edc00 | 0x7fe1d2a25900 | 131072 | 658768 | 73737024 | 17229761402583 | 17229761370866 | 17229761733427 | 17229761735133 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 311 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 138880 | 0x7fe1d32eda80 | 0x7fe1d2a25940 | 65536 | 656608 | 73354024 | 17229761765903 | 17229761733427 | 17229762091347 | 17229762093114 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 314 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 140864 | 0x7fe1d32ed900 | 0x7fe1d2a25980 | 131072 | 699878 | 78359344 | 17229762123673 | 17229762091347 | 17229762381267 | 17229762382796 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 317 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 143616 | 0x7fe1d32ed780 | 0x7fe1d2a259c0 | 131072 | 692510 | 77546800 | 17229762412755 | 17229762381267 | 17229762728307 | 17229762729827 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 320 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 145344 | 0x7fe1d32ed600 | 0x7fe1d2a25a00 | 131072 | 1031390 | 115541096 | 17229762768226 | 17229762728307 | 17229763002868 | 17229763004429 |
| 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 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 147584 | 0x7fe1d5a50480 | 0x7fe1d2a25a40 | 131072 | 689014 | 77238960 | 17229763034908 | 17229763002868 | 17229763366388 | 17229763367859 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 326 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 149568 | 0x7fe1d5a50300 | 0x7fe1d2a25a80 | 65536 | 647862 | 72664936 | 17229763399298 | 17229763366388 | 17229763727508 | 17229763729040 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 329 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 151552 | 0x7fe1d5a50180 | 0x7fe1d2a25ac0 | 131072 | 677972 | 75915208 | 17229763759869 | 17229763727508 | 17229764018068 | 17229764019522 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 332 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 154304 | 0x7fe1d5a50000 | 0x7fe1d2a25b00 | 131072 | 655158 | 73297080 | 17229764050841 | 17229764018068 | 17229764385269 | 17229764386732 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 335 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 156288 | 0x7fe1d32ede80 | 0x7fe1d2a25b40 | 131072 | 979438 | 109780136 | 17229764425461 | 17229764385269 | 17229764667829 | 17229764669154 |
| 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 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 158784 | 0x7fe1d32edd00 | 0x7fe1d2a25b80 | 131072 | 749656 | 83895672 | 17229764699523 | 17229764667829 | 17229765031509 | 17229765033024 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 341 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 161024 | 0x7fe1d32edb80 | 0x7fe1d2a25bc0 | 65536 | 655836 | 73380776 | 17229765063114 | 17229765031509 | 17229765395029 | 17229765396425 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 344 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 163264 | 0x7fe1d32eda00 | 0x7fe1d2a25c00 | 131072 | 654092 | 73285872 | 17229765426734 | 17229765395029 | 17229765695830 | 17229765697276 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 347 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 166528 | 0x7fe1d32ed880 | 0x7fe1d2a25c40 | 131072 | 653258 | 73084176 | 17229765727446 | 17229765695830 | 17229766083030 | 17229766106585 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 350 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 168512 | 0x7fe1d32ed700 | 0x7fe1d2a25c80 | 131072 | 1029692 | 115221856 | 17229766125805 | 17229766083030 | 17229766389110 | 17229766390578 |
| 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 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 171264 | 0x7fe1d5a50580 | 0x7fe1d2a25cc0 | 131072 | 657502 | 73618456 | 17229766420967 | 17229766389110 | 17229766752471 | 17229766753848 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 356 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 173760 | 0x7fe1d5a50400 | 0x7fe1d2a25d00 | 65536 | 660430 | 73873128 | 17229766784717 | 17229766752471 | 17229767121431 | 17229767122838 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 359 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 176256 | 0x7fe1d5a50280 | 0x7fe1d2a25d40 | 131072 | 674432 | 75572384 | 17229767153587 | 17229767121431 | 17229767444471 | 17229767445949 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 362 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 179776 | 0x7fe1d5a50100 | 0x7fe1d2a25d80 | 131072 | 673906 | 75441072 | 17229767476208 | 17229767444471 | 17229767861431 | 17229767881467 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 365 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 182272 | 0x7fe1d32edf80 | 0x7fe1d2a25dc0 | 131072 | 981800 | 109942344 | 17229767901777 | 17229767861431 | 17229768177272 | 17229768178769 |
| 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 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 185536 | 0x7fe1d32ede00 | 0x7fe1d2a25e00 | 131072 | 690758 | 77372432 | 17229768210099 | 17229768177272 | 17229768550712 | 17229768570789 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 371 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 188544 | 0x7fe1d32edc80 | 0x7fe1d2a25e40 | 65536 | 659946 | 73901008 | 17229768583418 | 17229768550712 | 17229768932632 | 17229768949579 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 374 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 191552 | 0x7fe1d32edb00 | 0x7fe1d2a25e80 | 131072 | 658782 | 73851224 | 17229768965188 | 17229768932632 | 17229769278873 | 17229769280260 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 377 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 195840 | 0x7fe1d32ed980 | 0x7fe1d2a25ec0 | 131072 | 647704 | 72567408 | 17229769310839 | 17229769278873 | 17229769742073 | 17229769759407 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 380 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 198592 | 0x7fe1d32ed800 | 0x7fe1d2a25f00 | 131072 | 1028044 | 115064712 | 17229769784646 | 17229769742073 | 17229770080313 | 17229770081958 |
| 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 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 202368 | 0x7fe1d32ed680 | 0x7fe1d2a25f40 | 131072 | 973238 | 108984216 | 17229770112147 | 17229770080313 | 17229770470714 | 17229770487457 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 386 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 205888 | 0x7fe1d5a50500 | 0x7fe1d2a25f80 | 65536 | 655288 | 73453328 | 17229770503197 | 17229770470714 | 17229770867834 | 17229770885196 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 389 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 209408 | 0x7fe1d5a50380 | 0x7fe1d2a25fc0 | 131072 | 667030 | 74750376 | 17229770900176 | 17229770867834 | 17229771239994 | 17229771241506 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 392 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 214464 | 0x7fe1d5a50200 | 0x7fe1d2a26000 | 131072 | 652270 | 73091720 | 17229771272126 | 17229771239994 | 17229771752635 | 17229771770542 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 395 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 217728 | 0x7fe1d5a50080 | 0x7fe1d2a26040 | 131072 | 1037286 | 115977064 | 17229771793031 | 17229771752635 | 17229772110555 | 17229772111913 |
| 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 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 222016 | 0x7fe1d32edf00 | 0x7fe1d2a26080 | 131072 | 1048210 | 117580344 | 17229772143032 | 17229772110555 | 17229772520155 | 17229772536881 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 401 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 226048 | 0x7fe1d32edd80 | 0x7fe1d2a260c0 | 65536 | 654894 | 73366432 | 17229772553831 | 17229772520155 | 17229772935195 | 17229772952460 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 404 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 230080 | 0x7fe1d32edc00 | 0x7fe1d2a26100 | 131072 | 665448 | 74556000 | 17229772967760 | 17229772935195 | 17229773332156 | 17229773349379 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 407 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 235904 | 0x7fe1d32eda80 | 0x7fe1d2a26140 | 131072 | 698602 | 78228816 | 17229773365059 | 17229773332156 | 17229773902716 | 17229773919264 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 410 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 239424 | 0x7fe1d32ed900 | 0x7fe1d2a26180 | 131072 | 1025572 | 114815784 | 17229773941983 | 17229773902716 | 17229774272957 | 17229774274564 |
| 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 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 244224 | 0x7fe1d32ed780 | 0x7fe1d2a261c0 | 131072 | 991698 | 110841088 | 17229774305373 | 17229774272957 | 17229774711837 | 17229774757221 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 416 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 248768 | 0x7fe1d32ed600 | 0x7fe1d2a26200 | 65536 | 653126 | 73159768 | 17229774768521 | 17229774711837 | 17229775173277 | 17229775214729 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 419 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 253312 | 0x7fe1d5a50480 | 0x7fe1d2a26240 | 131072 | 658424 | 73694912 | 17229775226108 | 17229775173277 | 17229775619358 | 17229775660587 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 422 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 8 | 24 | 255552 | 0x7fe1d5a50300 | 0x7fe1d2a26280 | 131072 | 1030754 | 115550160 | 17229775671386 | 17229775619358 | 17229776292158 | 17229776334988 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 425 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 259840 | 0x7fe1d5a50180 | 0x7fe1d2a262c0 | 131072 | 1020390 | 114365104 | 17229776353308 | 17229776292158 | 17229776725118 | 17229776766297 |
| 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 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 265664 | 0x7fe1d5a50000 | 0x7fe1d2a26300 | 131072 | 981720 | 109672360 | 17229776777566 | 17229776725118 | 17229777231999 | 17229777272883 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 431 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 271232 | 0x7fe1d32ede80 | 0x7fe1d2a26340 | 65536 | 655876 | 73487520 | 17229777284863 | 17229777231999 | 17229777738879 | 17229777756560 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 434 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 8 | 24 | 273216 | 0x7fe1d32edd00 | 0x7fe1d2a26380 | 131072 | 986122 | 110432168 | 17229777771220 | 17229777738879 | 17229778220800 | 17229778265086 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 437 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 8 | 24 | 275712 | 0x7fe1d32edb80 | 0x7fe1d2a263c0 | 131072 | 1020804 | 114724544 | 17229778275936 | 17229778220800 | 17229778994560 | 17229779037965 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 440 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 280768 | 0x7fe1d32eda00 | 0x7fe1d2a26400 | 131072 | 989890 | 110757368 | 17229779057215 | 17229778994560 | 17229779476801 | 17229779518252 |
| 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 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 287616 | 0x7fe1d32ed880 | 0x7fe1d2a26440 | 131072 | 1037604 | 115958456 | 17229779529302 | 17229779476801 | 17229780033761 | 17229780075157 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 446 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 294208 | 0x7fe1d32ed700 | 0x7fe1d2a26480 | 65536 | 691110 | 77414008 | 17229780087117 | 17229780033761 | 17229780589762 | 17229780631282 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 449 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 8 | 24 | 296960 | 0x7fe1d5a50580 | 0x7fe1d2a264c0 | 131072 | 954500 | 107156008 | 17229780642192 | 17229780589762 | 17229781143682 | 17229781184837 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 452 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 8 | 24 | 299968 | 0x7fe1d5a50400 | 0x7fe1d2a26500 | 131072 | 1035532 | 116290400 | 17229781195507 | 17229781143682 | 17229782010563 | 17229782052583 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 455 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 8 | 24 | 302720 | 0x7fe1d5a50280 | 0x7fe1d2a26540 | 131072 | 1023712 | 114670064 | 17229782071263 | 17229782010563 | 17229782673763 | 17229782717285 |
| 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 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 305472 | 0x7fe1d5a50100 | 0x7fe1d2a26580 | 131072 | 1033124 | 115602776 | 17229782727805 | 17229782673763 | 17229783348644 | 17229783389767 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 461 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 308224 | 0x7fe1d32edf80 | 0x7fe1d2a265c0 | 65536 | 657370 | 73591752 | 17229783401007 | 17229783348644 | 17229784018724 | 17229784059619 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 464 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 8 | 24 | 310976 | 0x7fe1d32ede00 | 0x7fe1d2a26600 | 131072 | 1032580 | 115708432 | 17229784070059 | 17229784018724 | 17229784680005 | 17229784720851 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 467 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 8 | 24 | 313216 | 0x7fe1d32edc80 | 0x7fe1d2a26640 | 131072 | 1031196 | 115863144 | 17229784731231 | 17229784680005 | 17229785763846 | 17229785804932 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 470 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 8 | 24 | 315968 | 0x7fe1d32edb00 | 0x7fe1d2a26680 | 131072 | 1029072 | 115054072 | 17229785826221 | 17229785763563 | 17229786832523 | 17229786881313 |
| 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 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 318720 | 0x7fe1d32ed980 | 0x7fe1d2a266c0 | 131072 | 1021276 | 114635952 | 17229786892063 | 17229786832523 | 17229787935563 | 17229787999693 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 476 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 321472 | 0x7fe1d32ed800 | 0x7fe1d2a26700 | 65536 | 644584 | 72135416 | 17229788010422 | 17229787935563 | 17229789061643 | 17229789125802 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 479 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 8 | 24 | 324224 | 0x7fe1d32ed680 | 0x7fe1d2a26740 | 131072 | 1018932 | 114366704 | 17229789136902 | 17229789061643 | 17229790164363 | 17229790229782 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 482 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 8 | 24 | 326464 | 0x7fe1d5a50500 | 0x7fe1d2a26780 | 131072 | 1015630 | 113809128 | 17229790241082 | 17229790164363 | 17229792113804 | 17229792177919 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 485 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 8 | 24 | 329216 | 0x7fe1d5a50380 | 0x7fe1d2a267c0 | 131072 | 1078016 | 120535456 | 17229792196739 | 17229792113804 | 17229794026604 | 17229794104317 |
| 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 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 331968 | 0x7fe1d5a50200 | 0x7fe1d2a26800 | 131072 | 1024624 | 114585728 | 17229794115877 | 17229794026604 | 17229796022125 | 17229796096693 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 491 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 12 | 24 | 334720 | 0x7fe1d5a50080 | 0x7fe1d2a26840 | 65536 | 655984 | 73357232 | 17229796107923 | 17229796022125 | 17229798001485 | 17229798066830 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 494 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 8 | 24 | 337472 | 0x7fe1d32edf00 | 0x7fe1d2a26880 | 131072 | 1062814 | 119048120 | 17229798084779 | 17229798001485 | 17229800099086 | 17229800169393 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 497 | 199978 | 199978 | 4194304 | 256 | 0 | 0 | 8 | 24 | 0 | 0x7fe1d32edd80 | 0x7fe1d2a268c0 | 131072 | 1025300 | 114902272 | 17229800180823 | 17229800099086 | 17229803715887 | 17229803767726 |