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 | 181366 | 181366 | 33554432 | 256 | 0 | 0 | 4 | 32 | 4160 | 0x0 | 0x7f33a6c04280 | 3670016 | 3019484 | 338020728 | 16904335818371 | 16891058910669 | 16904484999882 | 16904485116821 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 181366 | 181366 | 32768 | 256 | 0 | 0 | 12 | 24 | 13888 | 0x0 | 0x7f33a6c23f80 | 512 | 101100 | 11349552 | 16904490248777 | 16904484999882 | 16904490374105 | 16904490378944 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 5 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 14336 | 0x7f33a9bc8380 | 0x7f33a6c23fc0 | 65536 | 666782 | 74629024 | 16904490412293 | 16904490374105 | 16904490739224 | 16904490741593 |
| 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 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15040 | 0x7f33a9bc8200 | 0x7f33a6c24000 | 65536 | 653188 | 73326160 | 16904490778192 | 16904490739224 | 16904491140823 | 16904491143281 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 11 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15488 | 0x7f33a9bc8080 | 0x7f33a6c24040 | 65536 | 683186 | 76613392 | 16904491176430 | 16904491140823 | 16904491535222 | 16904491537359 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 14 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 15936 | 0x7f33a7527f00 | 0x7f33a6c24080 | 65536 | 663390 | 74385432 | 16904491568898 | 16904491535222 | 16904491832021 | 16904491834280 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 17 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 16384 | 0x7f33a7527d80 | 0x7f33a6c240c0 | 65536 | 624616 | 69958088 | 16904491866519 | 16904491832021 | 16904492130100 | 16904492132331 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 20 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 17088 | 0x7f33a7527c00 | 0x7f33a6c24100 | 131072 | 657876 | 73617368 | 16904492176250 | 16904492130100 | 16904492433939 | 16904492436242 |
| 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 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 16 | 24 | 17792 | 0x7f33a7527a80 | 0x7f33a6c24140 | 131072 | 696086 | 78101552 | 16904492467801 | 16904492433939 | 16904492820658 | 16904492822730 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 26 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 16 | 24 | 18496 | 0x7f33a7527900 | 0x7f33a6c24180 | 65536 | 656176 | 73466512 | 16904492853979 | 16904492820658 | 16904493206897 | 16904493208999 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 29 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19200 | 0x7f33a7527780 | 0x7f33a6c241c0 | 131072 | 702108 | 78638064 | 16904493238438 | 16904493206897 | 16904493518736 | 16904493520919 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 32 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19904 | 0x7f33a7527600 | 0x7f33a6c24200 | 131072 | 697504 | 78008632 | 16904493553108 | 16904493518736 | 16904493815215 | 16904493817510 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 35 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 20608 | 0x7f33a9bc8480 | 0x7f33a6c24240 | 131072 | 697208 | 78059536 | 16904493857329 | 16904493815215 | 16904494112815 | 16904494115291 |
| 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 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 16 | 24 | 21312 | 0x7f33a9bc8300 | 0x7f33a6c24280 | 131072 | 739946 | 82923944 | 16904494148100 | 16904494112815 | 16904494519213 | 16904494521399 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 41 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22016 | 0x7f33a9bc8180 | 0x7f33a6c242c0 | 65536 | 657832 | 73615264 | 16904494553048 | 16904494519213 | 16904494908012 | 16904494909528 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 44 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22720 | 0x7f33a9bc8000 | 0x7f33a6c24300 | 131072 | 698700 | 78298432 | 16904494941347 | 16904494908012 | 16904495177932 | 16904495179540 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 47 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 23424 | 0x7f33a7527e80 | 0x7f33a6c24340 | 131072 | 693960 | 77734320 | 16904495210499 | 16904495177932 | 16904495446411 | 16904495447922 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 50 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 24128 | 0x7f33a7527d00 | 0x7f33a6c24380 | 131072 | 690242 | 77283560 | 16904495486240 | 16904495446411 | 16904495719690 | 16904495721233 |
| 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 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 16 | 24 | 24832 | 0x7f33a7527b80 | 0x7f33a6c243c0 | 131072 | 714750 | 80020688 | 16904495753453 | 16904495719690 | 16904496076329 | 16904496077803 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 56 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 16 | 24 | 25536 | 0x7f33a7527a00 | 0x7f33a6c24400 | 65536 | 621118 | 69572280 | 16904496108702 | 16904496076329 | 16904496436808 | 16904496438432 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 59 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26240 | 0x7f33a7527880 | 0x7f33a6c24440 | 131072 | 700468 | 78409440 | 16904496469301 | 16904496436808 | 16904496705767 | 16904496707584 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 62 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26944 | 0x7f33a7527700 | 0x7f33a6c24480 | 131072 | 698480 | 78145872 | 16904496737683 | 16904496705767 | 16904496975206 | 16904496976936 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 65 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 27648 | 0x7f33a9bc8580 | 0x7f33a6c244c0 | 131072 | 656448 | 73511416 | 16904497015155 | 16904496975206 | 16904497247526 | 16904497249148 |
| 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 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 16 | 24 | 28608 | 0x7f33a9bc8400 | 0x7f33a6c24500 | 131072 | 693044 | 77668840 | 16904497281247 | 16904497247526 | 16904497608005 | 16904497609637 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 71 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 16 | 24 | 29312 | 0x7f33a9bc8280 | 0x7f33a6c24540 | 65536 | 665924 | 74453184 | 16904497641066 | 16904497608005 | 16904497971204 | 16904497972936 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 74 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 30016 | 0x7f33a9bc8100 | 0x7f33a6c24580 | 131072 | 658360 | 73775544 | 16904498004185 | 16904497971204 | 16904498250563 | 16904498252188 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 77 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 8 | 24 | 30976 | 0x7f33a7527f80 | 0x7f33a6c245c0 | 131072 | 660900 | 74084232 | 16904498284407 | 16904498250563 | 16904498522722 | 16904498524480 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 80 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 31680 | 0x7f33a7527e00 | 0x7f33a6c24600 | 131072 | 689184 | 77117056 | 16904498563069 | 16904498522722 | 16904498792001 | 16904498793542 |
| 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 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 16 | 24 | 32640 | 0x7f33a7527c80 | 0x7f33a6c24640 | 131072 | 661564 | 73963720 | 16904498823801 | 16904498792001 | 16904499146880 | 16904499148511 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 86 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 33600 | 0x7f33a7527b00 | 0x7f33a6c24680 | 65536 | 660418 | 73806048 | 16904499179110 | 16904499146880 | 16904499506399 | 16904499507940 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 89 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 34560 | 0x7f33a7527980 | 0x7f33a6c246c0 | 131072 | 693234 | 77642864 | 16904499538559 | 16904499506399 | 16904499778878 | 16904499780582 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 92 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 8 | 24 | 35520 | 0x7f33a7527800 | 0x7f33a6c24700 | 131072 | 698054 | 78161960 | 16904499811161 | 16904499778878 | 16904500047198 | 16904500048684 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 95 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 36224 | 0x7f33a7527680 | 0x7f33a6c24740 | 131072 | 695748 | 77961720 | 16904500086633 | 16904500047198 | 16904500316477 | 16904500318246 |
| 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 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 37184 | 0x7f33a9bc8500 | 0x7f33a6c24780 | 131072 | 659844 | 73926872 | 16904500348595 | 16904500316477 | 16904500671996 | 16904500673605 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 101 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 38144 | 0x7f33a9bc8380 | 0x7f33a6c247c0 | 65536 | 665830 | 74521664 | 16904500704894 | 16904500671996 | 16904501028315 | 16904501029895 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 104 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 39104 | 0x7f33a9bc8200 | 0x7f33a6c24800 | 131072 | 699598 | 78445056 | 16904501061194 | 16904501028315 | 16904501303354 | 16904501304926 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 107 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 8 | 24 | 40320 | 0x7f33a9bc8080 | 0x7f33a6c24840 | 131072 | 696378 | 77889744 | 16904501336265 | 16904501303354 | 16904501577433 | 16904501579028 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 110 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 41280 | 0x7f33a7527f00 | 0x7f33a6c24880 | 131072 | 730088 | 81728056 | 16904501617497 | 16904501577433 | 16904501853912 | 16904501855470 |
| 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 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 42240 | 0x7f33a7527d80 | 0x7f33a6c248c0 | 131072 | 692642 | 77566632 | 16904501885789 | 16904501853912 | 16904502215991 | 16904502217759 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 116 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 43200 | 0x7f33a7527c00 | 0x7f33a6c24900 | 65536 | 619214 | 69437520 | 16904502249288 | 16904502215991 | 16904502579510 | 16904502581078 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 119 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 8 | 24 | 44160 | 0x7f33a7527a80 | 0x7f33a6c24940 | 131072 | 697000 | 78165360 | 16904502611017 | 16904502579510 | 16904502848789 | 16904502850390 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 122 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 45376 | 0x7f33a7527900 | 0x7f33a6c24980 | 131072 | 693876 | 77779712 | 16904502881079 | 16904502848789 | 16904503123189 | 16904503124882 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 125 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 46336 | 0x7f33a7527780 | 0x7f33a6c249c0 | 131072 | 692562 | 77641464 | 16904503163311 | 16904503123189 | 16904503392628 | 16904503394254 |
| 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 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 47552 | 0x7f33a7527600 | 0x7f33a6c24a00 | 131072 | 694616 | 77768104 | 16904503424793 | 16904503392628 | 16904503747507 | 16904503749123 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 131 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 48512 | 0x7f33a9bc8480 | 0x7f33a6c24a40 | 65536 | 661252 | 74052864 | 16904503780602 | 16904503747507 | 16904504107026 | 16904504108652 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 134 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 8 | 24 | 49472 | 0x7f33a9bc8300 | 0x7f33a6c24a80 | 131072 | 668264 | 74888800 | 16904504139162 | 16904504107026 | 16904504378225 | 16904504379884 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 137 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 50688 | 0x7f33a9bc8180 | 0x7f33a6c24ac0 | 131072 | 695312 | 77868008 | 16904504410843 | 16904504378225 | 16904504648464 | 16904504650006 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 140 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 51648 | 0x7f33a9bc8000 | 0x7f33a6c24b00 | 131072 | 655878 | 73448136 | 16904504688485 | 16904504648464 | 16904504924304 | 16904504925898 |
| 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 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 52864 | 0x7f33a7527e80 | 0x7f33a6c24b40 | 131072 | 697932 | 77963568 | 16904504956407 | 16904504924304 | 16904505282862 | 16904505284557 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 146 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 54080 | 0x7f33a7527d00 | 0x7f33a6c24b80 | 65536 | 659836 | 73941960 | 16904505315416 | 16904505282862 | 16904505636781 | 16904505638587 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 149 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 8 | 24 | 55296 | 0x7f33a7527b80 | 0x7f33a6c24bc0 | 131072 | 691918 | 77477600 | 16904505669076 | 16904505636781 | 16904505906541 | 16904505908119 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 152 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 56768 | 0x7f33a7527a00 | 0x7f33a6c24c00 | 131072 | 696476 | 77979360 | 16904505939058 | 16904505906541 | 16904506180300 | 16904506181861 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 155 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 57728 | 0x7f33a7527880 | 0x7f33a6c24c40 | 131072 | 698060 | 78221280 | 16904506220599 | 16904506180300 | 16904506454219 | 16904506455902 |
| 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 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 58944 | 0x7f33a7527700 | 0x7f33a6c24c80 | 131072 | 660212 | 73891296 | 16904506487091 | 16904506454219 | 16904506808298 | 16904506809912 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 161 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 60160 | 0x7f33a9bc8580 | 0x7f33a6c24cc0 | 65536 | 666688 | 74572440 | 16904506840051 | 16904506808298 | 16904507161737 | 16904507163311 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 164 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 8 | 24 | 61376 | 0x7f33a9bc8400 | 0x7f33a6c24d00 | 131072 | 697330 | 78183120 | 16904507194430 | 16904507161737 | 16904507446536 | 16904507448123 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 167 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 62848 | 0x7f33a9bc8280 | 0x7f33a6c24d40 | 131072 | 693342 | 77623720 | 16904507479472 | 16904507446536 | 16904507730855 | 16904507732704 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 170 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 63808 | 0x7f33a9bc8100 | 0x7f33a6c24d80 | 131072 | 709512 | 79633112 | 16904507771633 | 16904507730855 | 16904508008615 | 16904508010376 |
| 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 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 65024 | 0x7f33a7527f80 | 0x7f33a6c24dc0 | 131072 | 658500 | 73854440 | 16904508042395 | 16904508008615 | 16904508362214 | 16904508363785 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 176 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 66240 | 0x7f33a7527e00 | 0x7f33a6c24e00 | 65536 | 624912 | 69981368 | 16904508394684 | 16904508362214 | 16904508715653 | 16904508717484 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 179 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 8 | 24 | 67456 | 0x7f33a7527c80 | 0x7f33a6c24e40 | 131072 | 695462 | 77944584 | 16904508748134 | 16904508715653 | 16904508987332 | 16904508989046 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 182 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 68928 | 0x7f33a7527b00 | 0x7f33a6c24e80 | 131072 | 703908 | 78799656 | 16904509019075 | 16904508987332 | 16904509264931 | 16904509266408 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 185 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 70144 | 0x7f33a7527980 | 0x7f33a6c24ec0 | 131072 | 650494 | 72948680 | 16904509304137 | 16904509264931 | 16904509539650 | 16904509541250 |
| 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 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 71616 | 0x7f33a7527800 | 0x7f33a6c24f00 | 131072 | 709056 | 79484584 | 16904509572729 | 16904509539650 | 16904509896609 | 16904509898249 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 191 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 72832 | 0x7f33a7527680 | 0x7f33a6c24f40 | 65536 | 658654 | 73801248 | 16904509928738 | 16904509896609 | 16904510253408 | 16904510255028 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 194 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 8 | 24 | 74048 | 0x7f33a9bc8500 | 0x7f33a6c24f80 | 131072 | 664426 | 74448536 | 16904510286297 | 16904510253408 | 16904510532447 | 16904510534090 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 197 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 75776 | 0x7f33a9bc8380 | 0x7f33a6c24fc0 | 131072 | 693572 | 77666992 | 16904510565139 | 16904510532447 | 16904510815967 | 16904510817592 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 200 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 76992 | 0x7f33a9bc8200 | 0x7f33a6c25000 | 131072 | 697120 | 78062664 | 16904510855570 | 16904510815967 | 16904511091646 | 16904511093313 |
| 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 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 78464 | 0x7f33a9bc8080 | 0x7f33a6c25040 | 131072 | 701566 | 78474760 | 16904511124402 | 16904511091646 | 16904511445565 | 16904511447173 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 206 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 79936 | 0x7f33a7527f00 | 0x7f33a6c25080 | 65536 | 658004 | 73944544 | 16904511479322 | 16904511445565 | 16904511801724 | 16904511803362 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 209 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 8 | 24 | 81408 | 0x7f33a7527d80 | 0x7f33a6c250c0 | 131072 | 695488 | 77826184 | 16904511834251 | 16904511801724 | 16904512072603 | 16904512074344 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 212 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 83136 | 0x7f33a7527c00 | 0x7f33a6c25100 | 131072 | 693400 | 77655272 | 16904512104723 | 16904512072603 | 16904512360922 | 16904512362695 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 215 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 84352 | 0x7f33a7527a80 | 0x7f33a6c25140 | 131072 | 689810 | 77244992 | 16904512412484 | 16904512360922 | 16904512637881 | 16904512639597 |
| 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 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 85824 | 0x7f33a7527900 | 0x7f33a6c25180 | 131072 | 697334 | 78214936 | 16904512669766 | 16904512637881 | 16904513005240 | 16904513006856 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 221 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 87296 | 0x7f33a7527780 | 0x7f33a6c251c0 | 65536 | 711296 | 79665728 | 16904513037945 | 16904513005240 | 16904513369079 | 16904513370765 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 224 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 88768 | 0x7f33a7527600 | 0x7f33a6c25200 | 131072 | 688446 | 77148272 | 16904513400994 | 16904513369079 | 16904513640118 | 16904513641727 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 227 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 90752 | 0x7f33a9bc8480 | 0x7f33a6c25240 | 131072 | 692672 | 77556016 | 16904513672016 | 16904513640118 | 16904513933718 | 16904513935408 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 230 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 91968 | 0x7f33a9bc8300 | 0x7f33a6c25280 | 131072 | 694530 | 77955144 | 16904513972987 | 16904513933718 | 16904514214357 | 16904514216020 |
| 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 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 93440 | 0x7f33a9bc8180 | 0x7f33a6c252c0 | 131072 | 700616 | 78443600 | 16904514247259 | 16904514214357 | 16904514576276 | 16904514577839 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 236 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 94912 | 0x7f33a9bc8000 | 0x7f33a6c25300 | 65536 | 667822 | 74833536 | 16904514609708 | 16904514576276 | 16904514933715 | 16904514935448 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 239 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 96384 | 0x7f33a7527e80 | 0x7f33a6c25340 | 131072 | 689572 | 77307936 | 16904514966478 | 16904514933715 | 16904515206034 | 16904515207580 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 242 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 98368 | 0x7f33a7527d00 | 0x7f33a6c25380 | 131072 | 692116 | 77543104 | 16904515238049 | 16904515206034 | 16904515506513 | 16904515508111 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 245 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 99584 | 0x7f33a7527b80 | 0x7f33a6c253c0 | 131072 | 693438 | 77637552 | 16904515545900 | 16904515506513 | 16904515778192 | 16904515779843 |
| 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 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 101312 | 0x7f33a7527a00 | 0x7f33a6c25400 | 131072 | 660494 | 74002352 | 16904515809942 | 16904515778192 | 16904516141871 | 16904516143592 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 251 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 102784 | 0x7f33a7527880 | 0x7f33a6c25440 | 65536 | 665072 | 74474624 | 16904516174771 | 16904516141871 | 16904516499470 | 16904516501041 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 254 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 104256 | 0x7f33a7527700 | 0x7f33a6c25480 | 131072 | 656256 | 73487264 | 16904516531781 | 16904516499470 | 16904516768749 | 16904516770693 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 257 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 106240 | 0x7f33a9bc8580 | 0x7f33a6c254c0 | 131072 | 648000 | 72575192 | 16904516800852 | 16904516768749 | 16904517074349 | 16904517075934 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 260 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 107712 | 0x7f33a9bc8400 | 0x7f33a6c25500 | 131072 | 651288 | 72953664 | 16904517114913 | 16904517074349 | 16904517347788 | 16904517349326 |
| 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 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 16 | 24 | 109440 | 0x7f33a9bc8280 | 0x7f33a6c25540 | 131072 | 739258 | 82813288 | 16904517380205 | 16904517347788 | 16904517707307 | 16904517708925 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 266 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 16 | 24 | 111168 | 0x7f33a9bc8100 | 0x7f33a6c25580 | 65536 | 656992 | 73656624 | 16904517739834 | 16904517707307 | 16904518062186 | 16904518063965 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 269 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 8 | 24 | 112896 | 0x7f33a7527f80 | 0x7f33a6c255c0 | 131072 | 691664 | 77494272 | 16904518095124 | 16904518062186 | 16904518339465 | 16904518341106 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 272 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 115136 | 0x7f33a7527e00 | 0x7f33a6c25600 | 131072 | 694142 | 77795816 | 16904518371625 | 16904518339465 | 16904518651304 | 16904518652937 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 275 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 116608 | 0x7f33a7527c80 | 0x7f33a6c25640 | 131072 | 692938 | 77663600 | 16904518690306 | 16904518651304 | 16904518926663 | 16904518928279 |
| 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 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 16 | 24 | 118336 | 0x7f33a7527b00 | 0x7f33a6c25680 | 131072 | 692394 | 77781440 | 16904518958118 | 16904518926663 | 16904519289062 | 16904519290758 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 281 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 16 | 24 | 120064 | 0x7f33a7527980 | 0x7f33a6c256c0 | 65536 | 662148 | 74207440 | 16904519320947 | 16904519289062 | 16904519644581 | 16904519646187 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 284 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 121792 | 0x7f33a7527800 | 0x7f33a6c25700 | 131072 | 707772 | 79284984 | 16904519677166 | 16904519644581 | 16904519920420 | 16904519922369 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 287 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 124032 | 0x7f33a7527680 | 0x7f33a6c25740 | 131072 | 696666 | 77997296 | 16904519952468 | 16904519920420 | 16904520240739 | 16904520242360 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 290 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 125504 | 0x7f33a9bc8500 | 0x7f33a6c25780 | 131072 | 696208 | 77923320 | 16904520280658 | 16904520240739 | 16904520520739 | 16904520522441 |
| 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 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 127488 | 0x7f33a9bc8380 | 0x7f33a6c257c0 | 131072 | 693066 | 77759728 | 16904520553040 | 16904520520739 | 16904520883298 | 16904520884890 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 296 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 129216 | 0x7f33a9bc8200 | 0x7f33a6c25800 | 65536 | 661956 | 74170984 | 16904520915669 | 16904520883298 | 16904521239297 | 16904521240980 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 299 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 130944 | 0x7f33a9bc8080 | 0x7f33a6c25840 | 131072 | 646626 | 72451080 | 16904521271769 | 16904521239297 | 16904521514016 | 16904521515671 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 302 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 133440 | 0x7f33a7527f00 | 0x7f33a6c25880 | 131072 | 658194 | 73641696 | 16904521546601 | 16904521514016 | 16904521844575 | 16904521846202 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 305 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 134912 | 0x7f33a7527d80 | 0x7f33a6c258c0 | 131072 | 1038986 | 116157440 | 16904521884560 | 16904521844575 | 16904522124094 | 16904522126243 |
| 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 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 136896 | 0x7f33a7527c00 | 0x7f33a6c25900 | 131072 | 658368 | 73799440 | 16904522156742 | 16904522124094 | 16904522485853 | 16904522487532 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 311 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 138880 | 0x7f33a7527a80 | 0x7f33a6c25940 | 65536 | 652416 | 73186408 | 16904522517782 | 16904522485853 | 16904522842652 | 16904522844342 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 314 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 140864 | 0x7f33a7527900 | 0x7f33a6c25980 | 131072 | 691986 | 77517936 | 16904522874781 | 16904522842652 | 16904523125371 | 16904523127073 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 317 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 143616 | 0x7f33a7527780 | 0x7f33a6c259c0 | 131072 | 700312 | 78505096 | 16904523157022 | 16904523125371 | 16904523469690 | 16904523471183 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 320 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 145344 | 0x7f33a7527600 | 0x7f33a6c25a00 | 131072 | 1031800 | 115747872 | 16904523509862 | 16904523469690 | 16904523740249 | 16904523742035 |
| 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 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 147584 | 0x7f33a9bc8480 | 0x7f33a6c25a40 | 131072 | 694900 | 77757744 | 16904523772494 | 16904523740249 | 16904524097368 | 16904524099054 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 326 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 149568 | 0x7f33a9bc8300 | 0x7f33a6c25a80 | 65536 | 665394 | 74603808 | 16904524129793 | 16904524097368 | 16904524453527 | 16904524454963 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 329 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 151552 | 0x7f33a9bc8180 | 0x7f33a6c25ac0 | 131072 | 648112 | 72575064 | 16904524486172 | 16904524453527 | 16904524740886 | 16904524742375 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 332 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 154304 | 0x7f33a9bc8000 | 0x7f33a6c25b00 | 131072 | 654930 | 73377184 | 16904524773794 | 16904524740886 | 16904525102325 | 16904525103934 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 335 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 156288 | 0x7f33a7527e80 | 0x7f33a6c25b40 | 131072 | 977186 | 109347832 | 16904525142663 | 16904525102325 | 16904525382805 | 16904525384435 |
| 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 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 158784 | 0x7f33a7527d00 | 0x7f33a6c25b80 | 131072 | 733442 | 82190064 | 16904525416474 | 16904525382805 | 16904525745524 | 16904525747095 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 341 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 161024 | 0x7f33a7527b80 | 0x7f33a6c25bc0 | 65536 | 673644 | 75551792 | 16904525777484 | 16904525745524 | 16904526102963 | 16904526104634 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 344 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 163264 | 0x7f33a7527a00 | 0x7f33a6c25c00 | 131072 | 655072 | 73479048 | 16904526135373 | 16904526102963 | 16904526404082 | 16904526405585 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 347 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 166528 | 0x7f33a7527880 | 0x7f33a6c25c40 | 131072 | 670352 | 75122112 | 16904526436274 | 16904526404082 | 16904526787921 | 16904526811283 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 350 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 168512 | 0x7f33a7527700 | 0x7f33a6c25c80 | 131072 | 1030582 | 115410560 | 16904526829812 | 16904526787921 | 16904527085840 | 16904527087384 |
| 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 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 171264 | 0x7f33a9bc8580 | 0x7f33a6c25cc0 | 131072 | 662110 | 74147272 | 16904527117883 | 16904527085840 | 16904527442479 | 16904527444004 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 356 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 173760 | 0x7f33a9bc8400 | 0x7f33a6c25d00 | 65536 | 699604 | 78353760 | 16904527475173 | 16904527442479 | 16904527801198 | 16904527802733 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 359 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 176256 | 0x7f33a9bc8280 | 0x7f33a6c25d40 | 131072 | 659098 | 73886320 | 16904527833602 | 16904527801198 | 16904528117997 | 16904528119663 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 362 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 179776 | 0x7f33a9bc8100 | 0x7f33a6c25d80 | 131072 | 657224 | 73554824 | 16904528150442 | 16904528117997 | 16904528528716 | 16904528549040 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 365 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 182272 | 0x7f33a7527f80 | 0x7f33a6c25dc0 | 131072 | 973732 | 109180976 | 16904528568560 | 16904528528716 | 16904528841835 | 16904528843452 |
| 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 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 185536 | 0x7f33a7527e00 | 0x7f33a6c25e00 | 131072 | 692344 | 77487840 | 16904528875861 | 16904528841835 | 16904529210794 | 16904529229840 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 371 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 188544 | 0x7f33a7527c80 | 0x7f33a6c25e40 | 65536 | 655268 | 73367152 | 16904529243390 | 16904529210794 | 16904529588073 | 16904529589419 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 374 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 191552 | 0x7f33a7527b00 | 0x7f33a6c25e80 | 131072 | 658230 | 73680088 | 16904529620048 | 16904529588073 | 16904529930952 | 16904529932559 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 377 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 195840 | 0x7f33a7527980 | 0x7f33a6c25ec0 | 131072 | 706916 | 79229816 | 16904529963278 | 16904529930952 | 16904530414150 | 16904530437844 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 380 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 198592 | 0x7f33a7527800 | 0x7f33a6c25f00 | 131072 | 1029088 | 115410600 | 16904530457123 | 16904530414150 | 16904530761669 | 16904530763244 |
| 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 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 202368 | 0x7f33a7527680 | 0x7f33a6c25f40 | 131072 | 978350 | 109832424 | 16904530793983 | 16904530761669 | 16904531148068 | 16904531170232 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 386 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 205888 | 0x7f33a9bc8500 | 0x7f33a6c25f80 | 65536 | 661988 | 74080832 | 16904531180892 | 16904531148068 | 16904531545507 | 16904531563100 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 389 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 209408 | 0x7f33a9bc8380 | 0x7f33a6c25fc0 | 131072 | 652302 | 73057304 | 16904531578090 | 16904531545507 | 16904531913346 | 16904531914900 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 392 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 214464 | 0x7f33a9bc8200 | 0x7f33a6c26000 | 131072 | 654720 | 73348632 | 16904531945779 | 16904531913346 | 16904532423904 | 16904532442394 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 395 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 217728 | 0x7f33a9bc8080 | 0x7f33a6c26040 | 131072 | 1042434 | 116791312 | 16904532464653 | 16904532423904 | 16904532780383 | 16904532782014 |
| 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 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 222016 | 0x7f33a7527f00 | 0x7f33a6c26080 | 131072 | 1020884 | 114596344 | 16904532813963 | 16904532780383 | 16904533186462 | 16904533204301 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 401 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 226048 | 0x7f33a7527d80 | 0x7f33a6c260c0 | 65536 | 675424 | 75767608 | 16904533218721 | 16904533186462 | 16904533596701 | 16904533613819 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 404 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 230080 | 0x7f33a7527c00 | 0x7f33a6c26100 | 131072 | 666644 | 74721032 | 16904533628439 | 16904533596701 | 16904533988060 | 16904534005027 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 407 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 235904 | 0x7f33a7527a80 | 0x7f33a6c26140 | 131072 | 671904 | 75166672 | 16904534020807 | 16904533988060 | 16904534562298 | 16904534581820 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 410 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 239424 | 0x7f33a7527900 | 0x7f33a6c26180 | 131072 | 1032228 | 115607880 | 16904534602629 | 16904534562298 | 16904534934457 | 16904534936089 |
| 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 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 244224 | 0x7f33a7527780 | 0x7f33a6c261c0 | 131072 | 982454 | 109560904 | 16904534966308 | 16904534934457 | 16904535365656 | 16904535384016 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 416 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 248768 | 0x7f33a7527600 | 0x7f33a6c26200 | 65536 | 652728 | 73191544 | 16904535398246 | 16904535365656 | 16904535799255 | 16904535816253 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 419 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 253312 | 0x7f33a9bc8480 | 0x7f33a6c26240 | 131072 | 668370 | 74904760 | 16904535832113 | 16904535799255 | 16904536218773 | 16904536236290 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 422 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 8 | 24 | 255552 | 0x7f33a9bc8300 | 0x7f33a6c26280 | 131072 | 1027554 | 115093368 | 16904536251540 | 16904536218773 | 16904536852052 | 16904536871431 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 425 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 259840 | 0x7f33a9bc8180 | 0x7f33a6c262c0 | 131072 | 1064090 | 119320136 | 16904536892851 | 16904536852052 | 16904537262770 | 16904537280399 |
| 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 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 265664 | 0x7f33a9bc8000 | 0x7f33a6c26300 | 131072 | 991684 | 110787344 | 16904537297899 | 16904537262770 | 16904537744369 | 16904537761965 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 431 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 271232 | 0x7f33a7527e80 | 0x7f33a6c26340 | 65536 | 653686 | 73315376 | 16904537777094 | 16904537744369 | 16904538224848 | 16904538246030 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 434 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 8 | 24 | 273216 | 0x7f33a7527d00 | 0x7f33a6c26380 | 131072 | 983194 | 110284192 | 16904538257960 | 16904538224848 | 16904538712366 | 16904538754885 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 437 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 8 | 24 | 275712 | 0x7f33a7527b80 | 0x7f33a6c263c0 | 131072 | 1035616 | 115847984 | 16904538765495 | 16904538712366 | 16904539476684 | 16904539519232 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 440 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 280768 | 0x7f33a7527a00 | 0x7f33a6c26400 | 131072 | 978178 | 109456952 | 16904539538072 | 16904539476684 | 16904539955723 | 16904539998208 |
| 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 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 287616 | 0x7f33a7527880 | 0x7f33a6c26440 | 131072 | 1026160 | 115140256 | 16904540010047 | 16904539955723 | 16904540513161 | 16904540555881 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 446 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 294208 | 0x7f33a7527700 | 0x7f33a6c26480 | 65536 | 660084 | 73988720 | 16904540566921 | 16904540513161 | 16904541067560 | 16904541109605 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 449 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 8 | 24 | 296960 | 0x7f33a9bc8580 | 0x7f33a6c264c0 | 131072 | 978490 | 109628440 | 16904541120004 | 16904541067560 | 16904541618598 | 16904541661538 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 452 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 8 | 24 | 299968 | 0x7f33a9bc8400 | 0x7f33a6c26500 | 131072 | 1043198 | 116925616 | 16904541673078 | 16904541618598 | 16904542485795 | 16904542528512 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 455 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 8 | 24 | 302720 | 0x7f33a9bc8280 | 0x7f33a6c26540 | 131072 | 1033160 | 115734240 | 16904542547912 | 16904542485795 | 16904543144034 | 16904543186832 |
| 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 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 305472 | 0x7f33a9bc8100 | 0x7f33a6c26580 | 131072 | 1039798 | 116321488 | 16904543197392 | 16904543144034 | 16904543814592 | 16904543834433 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 461 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 308224 | 0x7f33a7527f80 | 0x7f33a6c265c0 | 65536 | 654646 | 73314120 | 16904543847353 | 16904543814592 | 16904544455390 | 16904544472834 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 464 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 8 | 24 | 310976 | 0x7f33a7527e00 | 0x7f33a6c26600 | 131072 | 1033944 | 115833872 | 16904544487483 | 16904544455390 | 16904545086268 | 16904545103965 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 467 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 8 | 24 | 313216 | 0x7f33a7527c80 | 0x7f33a6c26640 | 131072 | 1026290 | 114852248 | 16904545118574 | 16904545086268 | 16904546137465 | 16904546160293 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 470 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 8 | 24 | 315968 | 0x7f33a7527b00 | 0x7f33a6c26680 | 131072 | 1035438 | 115975304 | 16904546179763 | 16904546137465 | 16904547183382 | 16904547204672 |
| 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 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 318720 | 0x7f33a7527980 | 0x7f33a6c266c0 | 131072 | 1076516 | 120374680 | 16904547216312 | 16904547183263 | 16904548266620 | 16904548311239 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 476 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 321472 | 0x7f33a7527800 | 0x7f33a6c26700 | 65536 | 659380 | 73722856 | 16904548322209 | 16904548266620 | 16904549368215 | 16904549409116 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 479 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 8 | 24 | 324224 | 0x7f33a7527680 | 0x7f33a6c26740 | 131072 | 1031770 | 115538904 | 16904549419566 | 16904549368215 | 16904550455572 | 16904550501553 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 482 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 8 | 24 | 326464 | 0x7f33a9bc8500 | 0x7f33a6c26780 | 131072 | 1038732 | 116097064 | 16904550513923 | 16904550455572 | 16904552381806 | 16904552422856 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 485 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 8 | 24 | 329216 | 0x7f33a9bc8380 | 0x7f33a6c267c0 | 131072 | 1028620 | 115133168 | 16904552442195 | 16904552381806 | 16904554265000 | 16904554338108 |
| 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 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 331968 | 0x7f33a9bc8200 | 0x7f33a6c26800 | 131072 | 1037732 | 116140224 | 16904554349928 | 16904554265000 | 16904556248994 | 16904556317649 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 491 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 12 | 24 | 334720 | 0x7f33a9bc8080 | 0x7f33a6c26840 | 65536 | 700756 | 78487848 | 16904556328499 | 16904556248994 | 16904558215548 | 16904558285311 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 494 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 8 | 24 | 337472 | 0x7f33a7527f00 | 0x7f33a6c26880 | 131072 | 1081314 | 121114680 | 16904558297490 | 16904558215548 | 16904560153302 | 16904560222622 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 497 | 181366 | 181366 | 4194304 | 256 | 0 | 0 | 8 | 24 | 0 | 0x7f33a7527d80 | 0x7f33a6c268c0 | 131072 | 1031330 | 115586440 | 16904560233752 | 16904560153302 | 16904563758730 | 16904563835684 |