46 KiB
46 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | GRBM_COUNT | GRBM_GUI_ACTIVE | SQ_WAVES | SQ_IFETCH | SQ_IFETCH_LEVEL | SQ_ACCUM_PREV_HIRES | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBuffer.kd | 0 | 0 | 0 | 851446 | 851451 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7f57d7204180 | 502017 | 502017 | 524288 | 6291456 | 791691 | 101396696 | 12074888626877398 | 12074888876000832 | 12074888876323390 | 12074888876416213 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 851446 | 851451 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7f57d7235100 | 27806 | 27806 | 512 | 8192 | 9394 | 1198836 | 12074888891216898 | 12074888891548393 | 12074888891555113 | 12074888891564213 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7f5907505900 | 0x7f57d7235140 | 216862 | 216862 | 65536 | 917504 | 139878 | 17901600 | 12074888891674198 | 12074888891859432 | 12074888891991591 | 12074888891995104 |
| 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 | 6 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7f5907505800 | 0x7f57d7235180 | 400582 | 400582 | 65536 | 1245184 | 183863 | 23460024 | 12074888892097605 | 12074888892289670 | 12074888892544868 | 12074888892593396 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7f5907505700 | 0x7f57d72351c0 | 400438 | 400438 | 65536 | 983040 | 137294 | 17507448 | 12074888892669447 | 12074888892850147 | 12074888893104706 | 12074888893151513 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7f5907505600 | 0x7f57d7235200 | 216742 | 216742 | 65536 | 1048576 | 157728 | 20202892 | 12074888893233876 | 12074888893416864 | 12074888893549663 | 12074888893552588 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7f5907505500 | 0x7f57d7235240 | 226558 | 226558 | 65536 | 983040 | 148040 | 18899188 | 12074888893635202 | 12074888893815102 | 12074888893953661 | 12074888893956599 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7f5907505400 | 0x7f57d7235280 | 220142 | 220142 | 65536 | 1048576 | 146551 | 18777020 | 12074888894070230 | 12074888894246940 | 12074888894380219 | 12074888894383182 |
| 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 | 16 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7f5907505300 | 0x7f57d72352c0 | 401302 | 401302 | 65536 | 1572864 | 226601 | 28881052 | 12074888894456689 | 12074888894633498 | 12074888894888857 | 12074888894933945 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7f5907505a00 | 0x7f57d7235300 | 403470 | 403470 | 65536 | 1179648 | 158793 | 20339796 | 12074888894968399 | 12074888895171575 | 12074888895428534 | 12074888895473989 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7f5907505900 | 0x7f57d7235340 | 213430 | 213430 | 65536 | 1114112 | 179324 | 22948528 | 12074888895512611 | 12074888895692853 | 12074888895822612 | 12074888895825592 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7f5907505800 | 0x7f57d7235380 | 226694 | 226694 | 65536 | 1114112 | 157495 | 20177632 | 12074888895899630 | 12074888896074931 | 12074888896214130 | 12074888896217260 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7f5907505700 | 0x7f57d72353c0 | 215718 | 215718 | 65536 | 1179648 | 171749 | 21887008 | 12074888896303400 | 12074888896482449 | 12074888896614128 | 12074888896617083 |
| 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 | 26 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7f5907505600 | 0x7f57d7235400 | 456814 | 456814 | 65536 | 1835008 | 266449 | 34156184 | 12074888896691021 | 12074888896864847 | 12074888897158445 | 12074888897203623 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7f5907505500 | 0x7f57d7235440 | 398870 | 398870 | 65536 | 1310720 | 178023 | 22735096 | 12074888897242756 | 12074888897440524 | 12074888897693643 | 12074888897738427 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7f5907505400 | 0x7f57d7235480 | 212310 | 212310 | 65536 | 1245184 | 176829 | 22678076 | 12074888897773613 | 12074888897958441 | 12074888898088201 | 12074888898091493 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7f5907505300 | 0x7f57d72354c0 | 214806 | 214806 | 65536 | 1310720 | 186800 | 23885540 | 12074888898165932 | 12074888898341799 | 12074888898472679 | 12074888898475687 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7f5907505a00 | 0x7f57d7235500 | 218190 | 218190 | 65536 | 1310720 | 180272 | 23009816 | 12074888898564001 | 12074888898739078 | 12074888898872677 | 12074888898875651 |
| 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 | 36 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7f5907505900 | 0x7f57d7235540 | 404374 | 404374 | 65536 | 2097152 | 286650 | 36661500 | 12074888898948245 | 12074888899128356 | 12074888899386594 | 12074888899432095 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7f5907505800 | 0x7f57d7235580 | 393694 | 393694 | 65536 | 1441792 | 195675 | 25120580 | 12074888899469775 | 12074888899646113 | 12074888899897472 | 12074888899941962 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7f5907505700 | 0x7f57d72355c0 | 216686 | 216686 | 65536 | 1376256 | 196425 | 25150948 | 12074888899977118 | 12074888900169630 | 12074888900301790 | 12074888900305057 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7f5907505600 | 0x7f57d7235600 | 216678 | 216678 | 65536 | 1507328 | 211442 | 27019848 | 12074888900376179 | 12074888900554108 | 12074888900686908 | 12074888900689962 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7f5907505500 | 0x7f57d7235640 | 214686 | 214686 | 65536 | 1441792 | 199334 | 25480000 | 12074888900777936 | 12074888900949787 | 12074888901080506 | 12074888901083794 |
| 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 | 46 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7f5907505400 | 0x7f57d7235680 | 400462 | 400462 | 65536 | 2359296 | 322898 | 41262920 | 12074888901154626 | 12074888901330585 | 12074888901587223 | 12074888901631221 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7f5907505300 | 0x7f57d72356c0 | 405486 | 405486 | 65536 | 1572864 | 212951 | 27174392 | 12074888901668270 | 12074888901852662 | 12074888902111221 | 12074888902156938 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7f5907505a00 | 0x7f57d7235700 | 217702 | 217702 | 65536 | 1507328 | 204156 | 26170576 | 12074888902191212 | 12074888902384019 | 12074888902517459 | 12074888902520514 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7f5907505900 | 0x7f57d7235740 | 221062 | 221062 | 65536 | 1703936 | 232487 | 29848552 | 12074888902593199 | 12074888902764177 | 12074888902899697 | 12074888902902754 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7f5907505800 | 0x7f57d7235780 | 213550 | 213550 | 65536 | 1572864 | 225294 | 28819856 | 12074888902987121 | 12074888903166415 | 12074888903297295 | 12074888903300283 |
| 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 | 56 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7f5907505700 | 0x7f57d72357c0 | 400118 | 400118 | 65536 | 2621440 | 355439 | 45418788 | 12074888903376164 | 12074888903549134 | 12074888903805132 | 12074888903849975 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7f5907505600 | 0x7f57d7235800 | 394526 | 394526 | 65536 | 1703936 | 233040 | 29814288 | 12074888903885681 | 12074888904068491 | 12074888904320650 | 12074888904366675 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7f5907505500 | 0x7f57d7235840 | 214590 | 214590 | 65536 | 1638400 | 227151 | 29049592 | 12074888904401109 | 12074888904589128 | 12074888904720008 | 12074888904722987 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7f5907505400 | 0x7f57d7235880 | 221966 | 221966 | 65536 | 1900544 | 267838 | 34231792 | 12074888904797285 | 12074888904970727 | 12074888905107526 | 12074888905110798 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7f5907505300 | 0x7f57d72358c0 | 219518 | 219518 | 65536 | 1703936 | 230697 | 29582108 | 12074888905200234 | 12074888905375685 | 12074888905508484 | 12074888905511512 |
| 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 | 66 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7f5907505a00 | 0x7f57d7235900 | 404382 | 404382 | 65536 | 2883584 | 393559 | 50398116 | 12074888905584378 | 12074888905756643 | 12074888906016321 | 12074888906061545 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7f5907505900 | 0x7f57d7235940 | 401998 | 401998 | 65536 | 1835008 | 244295 | 31332428 | 12074888906100357 | 12074888906291360 | 12074888906548319 | 12074888906591920 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7f5907505800 | 0x7f57d7235980 | 218734 | 218734 | 65536 | 1769472 | 276585 | 35426276 | 12074888906628598 | 12074888906806557 | 12074888906940957 | 12074888906944105 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7f5907505700 | 0x7f57d72359c0 | 218742 | 218742 | 65536 | 2097152 | 308374 | 39323900 | 12074888907020286 | 12074888907193275 | 12074888907327675 | 12074888907330673 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7f5907505600 | 0x7f57d7235a00 | 217734 | 217734 | 65536 | 1835008 | 248202 | 31773324 | 12074888907419168 | 12074888907591034 | 12074888907724633 | 12074888907727541 |
| 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 | 76 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7f5907505500 | 0x7f57d7235a40 | 401966 | 401966 | 65536 | 3145728 | 416703 | 53480124 | 12074888907798753 | 12074888907971192 | 12074888908228790 | 12074888908276160 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7f5907505400 | 0x7f57d7235a80 | 396094 | 396094 | 65536 | 1966080 | 263104 | 33575180 | 12074888908310935 | 12074888908496949 | 12074888908751028 | 12074888908794063 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7f5907505300 | 0x7f57d7235ac0 | 212606 | 212606 | 65536 | 1900544 | 282432 | 36173560 | 12074888908833656 | 12074888909012786 | 12074888909142866 | 12074888909146217 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7f5907505a00 | 0x7f57d7235b00 | 223390 | 223390 | 65536 | 2293760 | 309601 | 39837468 | 12074888909219613 | 12074888909393745 | 12074888909532144 | 12074888909535430 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7f5907505900 | 0x7f57d7235b40 | 218606 | 218606 | 65536 | 1966080 | 302285 | 38777772 | 12074888909621440 | 12074888909793903 | 12074888909927662 | 12074888909930855 |
| 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 | 86 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7f5907505800 | 0x7f57d7235b80 | 415270 | 415270 | 65536 | 3407872 | 456135 | 58472540 | 12074888910007678 | 12074888910181101 | 12074888910448299 | 12074888910494012 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7f5907505700 | 0x7f57d7235bc0 | 397166 | 397166 | 65536 | 2097152 | 278236 | 35623212 | 12074888910529638 | 12074888910710538 | 12074888910964457 | 12074888911019027 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7f5907505600 | 0x7f57d7235c00 | 218918 | 218918 | 65536 | 2031616 | 286718 | 36701428 | 12074888911054894 | 12074888911245095 | 12074888911379495 | 12074888911382874 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7f5907505500 | 0x7f57d7235c40 | 222278 | 222278 | 65536 | 2490368 | 345037 | 44150696 | 12074888911457432 | 12074888911630213 | 12074888911767173 | 12074888911770304 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7f5907505400 | 0x7f57d7235c80 | 224654 | 224654 | 65536 | 2097152 | 326627 | 41796696 | 12074888911858558 | 12074888912033091 | 12074888912171491 | 12074888912174986 |
| 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 | 96 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7f5907505300 | 0x7f57d7235cc0 | 423766 | 423766 | 65536 | 3670016 | 501314 | 64215320 | 12074888912253391 | 12074888912426849 | 12074888912699168 | 12074888912744414 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7f5907505a00 | 0x7f57d7235d00 | 391206 | 391206 | 65536 | 2228224 | 311630 | 39784640 | 12074888912782775 | 12074888912955647 | 12074888913206686 | 12074888913252147 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7f5907505900 | 0x7f57d7235d40 | 218734 | 218734 | 65536 | 2162688 | 310544 | 39784240 | 12074888913288745 | 12074888913474204 | 12074888913608284 | 12074888913611335 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7f5907505800 | 0x7f57d7235d80 | 231806 | 231806 | 65536 | 2686976 | 383475 | 48963064 | 12074888913680814 | 12074888913852762 | 12074888913996762 | 12074888913999847 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7f5907505700 | 0x7f57d7235dc0 | 225638 | 225638 | 65536 | 2228224 | 313140 | 40013364 | 12074888914088742 | 12074888914261240 | 12074888914399800 | 12074888914402866 |
| 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 | 106 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7f5907505600 | 0x7f57d7235e00 | 410246 | 410246 | 65536 | 3932160 | 520554 | 66676008 | 12074888914477014 | 12074888914646998 | 12074888914911637 | 12074888914956445 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7f5907505500 | 0x7f57d7235e40 | 395758 | 395758 | 65536 | 2359296 | 310390 | 39789524 | 12074888914990869 | 12074888915185236 | 12074888915438514 | 12074888915482412 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7f5907505400 | 0x7f57d7235e80 | 280518 | 280518 | 65536 | 2293760 | 322126 | 41271432 | 12074888915519852 | 12074888915700753 | 12074888915876592 | 12074888915879580 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7f5907505300 | 0x7f57d7235ec0 | 224630 | 224630 | 65536 | 2883584 | 402843 | 51223660 | 12074888915954209 | 12074888916134831 | 12074888916273230 | 12074888916276618 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7f5907505a00 | 0x7f57d7235f00 | 216406 | 216406 | 65536 | 2359296 | 316455 | 40438780 | 12074888916361556 | 12074888916531789 | 12074888916664908 | 12074888916668015 |
| 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 | 116 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7f5907505900 | 0x7f57d7235f40 | 415766 | 415766 | 65536 | 4194304 | 582048 | 74647896 | 12074888916741261 | 12074888916913867 | 12074888917180426 | 12074888917226413 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7f5907505800 | 0x7f57d7235f80 | 399294 | 399294 | 65536 | 2490368 | 326718 | 41862580 | 12074888917263592 | 12074888917446985 | 12074888917703143 | 12074888917747682 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7f5907505700 | 0x7f57d7235fc0 | 217670 | 217670 | 65536 | 2424832 | 340448 | 43605056 | 12074888917781515 | 12074888917964102 | 12074888918097381 | 12074888918100818 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7f5907505600 | 0x7f57d7236000 | 224998 | 224998 | 65536 | 3080192 | 505443 | 64770092 | 12074888918174084 | 12074888918346980 | 12074888918486819 | 12074888918489931 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7f5907505500 | 0x7f57d7236040 | 225918 | 225918 | 65536 | 2490368 | 400091 | 51229872 | 12074888918575710 | 12074888918746338 | 12074888918884737 | 12074888918887800 |
| 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 | 126 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7f5907505400 | 0x7f57d7236080 | 422630 | 422630 | 65536 | 4456448 | 601327 | 76826904 | 12074888918958832 | 12074888919136736 | 12074888919409375 | 12074888919453782 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7f5907505300 | 0x7f57d72360c0 | 402070 | 402070 | 65536 | 2621440 | 351017 | 45012632 | 12074888919490460 | 12074888919677533 | 12074888919935452 | 12074888919979289 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7f5907505a00 | 0x7f57d7236100 | 216254 | 216254 | 65536 | 2555904 | 370340 | 47464440 | 12074888920018331 | 12074888920206171 | 12074888920339290 | 12074888920342694 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7f5907505900 | 0x7f57d7236140 | 234838 | 234838 | 65536 | 3276800 | 484204 | 61637112 | 12074888920416832 | 12074888920587609 | 12074888920733048 | 12074888920736065 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7f5907505800 | 0x7f57d7236180 | 214718 | 214718 | 65536 | 2621440 | 376639 | 48264828 | 12074888920821674 | 12074888920991447 | 12074888921123766 | 12074888921127382 |
| 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 | 136 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7f5907505700 | 0x7f57d72361c0 | 414230 | 414230 | 65536 | 4718592 | 641204 | 82023744 | 12074888921200679 | 12074888921372405 | 12074888921639604 | 12074888921684478 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7f5907505600 | 0x7f57d7236200 | 394574 | 394574 | 65536 | 2752512 | 373150 | 47964376 | 12074888921717639 | 12074888921901202 | 12074888922155121 | 12074888922201218 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7f5907505500 | 0x7f57d7236240 | 218918 | 218918 | 65536 | 2686976 | 375161 | 48121336 | 12074888922236554 | 12074888922423760 | 12074888922557839 | 12074888922561077 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7f5907505400 | 0x7f57d7236280 | 243110 | 243110 | 65536 | 3473408 | 518513 | 66351928 | 12074888922633361 | 12074888922804238 | 12074888922955917 | 12074888922958926 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7f5907505300 | 0x7f57d72362c0 | 216830 | 216830 | 65536 | 2752512 | 394401 | 50430892 | 12074888923074501 | 12074888923249196 | 12074888923382315 | 12074888923385449 |
| 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 | 146 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7f5907505a00 | 0x7f57d7236300 | 416470 | 416470 | 65536 | 4980736 | 665626 | 85131076 | 12074888923455739 | 12074888923626474 | 12074888923896392 | 12074888923941262 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7f5907505900 | 0x7f57d7236340 | 399950 | 399950 | 65536 | 2883584 | 395763 | 50410868 | 12074888923977008 | 12074888924165031 | 12074888924422470 | 12074888924469243 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7f5907505800 | 0x7f57d7236380 | 223166 | 223166 | 65536 | 2818048 | 435550 | 55826480 | 12074888924503496 | 12074888924690788 | 12074888924828548 | 12074888924831766 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7f5907505700 | 0x7f57d72363c0 | 253142 | 253142 | 65536 | 3670016 | 552795 | 70615936 | 12074888924904602 | 12074888925085987 | 12074888925244066 | 12074888925247188 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7f5907505600 | 0x7f57d7236400 | 222822 | 222822 | 65536 | 2883584 | 461222 | 59166340 | 12074888925331816 | 12074888925504544 | 12074888925642144 | 12074888925645308 |
| 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 | 156 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7f5907505500 | 0x7f57d7236440 | 412398 | 412398 | 65536 | 5177344 | 680264 | 86771676 | 12074888925717623 | 12074888925888543 | 12074888926155261 | 12074888926200791 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7f5907505400 | 0x7f57d7236480 | 397158 | 397158 | 65536 | 3014656 | 403196 | 51595700 | 12074888926235816 | 12074888926420380 | 12074888926676859 | 12074888926720737 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7f5907505300 | 0x7f57d72364c0 | 217518 | 217518 | 65536 | 2949120 | 405680 | 51895584 | 12074888926752496 | 12074888926940857 | 12074888927074457 | 12074888927077670 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7f5907505a00 | 0x7f57d7236500 | 264654 | 264654 | 65536 | 3866624 | 573686 | 73928344 | 12074888927156236 | 12074888927328215 | 12074888927494455 | 12074888927497651 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7f5907505900 | 0x7f57d7236540 | 219054 | 219054 | 65536 | 3014656 | 404315 | 51751784 | 12074888927578421 | 12074888927750773 | 12074888927885333 | 12074888927888507 |
| 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 | 166 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7f5907505800 | 0x7f57d7236580 | 419710 | 419710 | 65536 | 5439488 | 739915 | 94097156 | 12074888927960511 | 12074888928140691 | 12074888928413170 | 12074888928440292 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7f5907505700 | 0x7f57d72365c0 | 401302 | 401302 | 65536 | 3145728 | 433583 | 55613340 | 12074888928492069 | 12074888928661169 | 12074888928919567 | 12074888928943327 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7f5907505600 | 0x7f57d7236600 | 224166 | 224166 | 65536 | 3080192 | 460855 | 59049700 | 12074888928997277 | 12074888929177166 | 12074888929316045 | 12074888929319566 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7f5907505500 | 0x7f57d7236640 | 277342 | 277342 | 65536 | 4063232 | 569142 | 72932964 | 12074888929392492 | 12074888929573964 | 12074888929748203 | 12074888929751659 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7f5907505400 | 0x7f57d7236680 | 217086 | 217086 | 65536 | 3145728 | 423988 | 54423576 | 12074888929831007 | 12074888930004042 | 12074888930137481 | 12074888930141824 |
| 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 | 176 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7f5907505300 | 0x7f57d72366c0 | 406022 | 406022 | 65536 | 5701632 | 772125 | 98734244 | 12074888930212626 | 12074888930391240 | 12074888930653799 | 12074888930681317 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7f5907505a00 | 0x7f57d7236700 | 407958 | 407958 | 65536 | 3276800 | 434230 | 55631764 | 12074888930740237 | 12074888930918918 | 12074888931182756 | 12074888931210440 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7f5907505900 | 0x7f57d7236740 | 227326 | 227326 | 65536 | 3211264 | 480762 | 61547668 | 12074888931265553 | 12074888931438115 | 12074888931578114 | 12074888931581229 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7f5907505800 | 0x7f57d7236780 | 288446 | 288446 | 65536 | 4259840 | 586744 | 75087404 | 12074888931650849 | 12074888931823393 | 12074888932006592 | 12074888932009666 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7f5907505700 | 0x7f57d72367c0 | 228774 | 228774 | 65536 | 3276800 | 513733 | 65784444 | 12074888932095495 | 12074888932269631 | 12074888932410910 | 12074888932414578 |
| 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 | 186 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7f5907505600 | 0x7f57d7236800 | 460342 | 460342 | 65536 | 7733248 | 989005 | 126401488 | 12074888932483917 | 12074888932656669 | 12074888932956507 | 12074888932982333 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7f5907505500 | 0x7f57d7236840 | 396462 | 396462 | 65536 | 3407872 | 451852 | 57949744 | 12074888933044479 | 12074888933219226 | 12074888933474265 | 12074888933501468 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7f5907505400 | 0x7f57d7236880 | 216134 | 216134 | 65536 | 3342336 | 500928 | 64122364 | 12074888933552583 | 12074888933720664 | 12074888933852823 | 12074888933856047 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7f5907505300 | 0x7f57d72368c0 | 303142 | 303142 | 65536 | 4456448 | 679985 | 87247412 | 12074888933929904 | 12074888934117302 | 12074888934309621 | 12074888934335077 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7f5907505a00 | 0x7f57d7236900 | 225398 | 225398 | 65536 | 3538944 | 530488 | 67881876 | 12074888934403554 | 12074888934575379 | 12074888934714899 | 12074888934718139 |
| 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 | 196 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7f5907505900 | 0x7f57d7236940 | 435494 | 435494 | 65536 | 8978432 | 1128638 | 144515684 | 12074888934786196 | 12074888934956977 | 12074888935240816 | 12074888935269063 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7f5907505800 | 0x7f57d7236980 | 407022 | 407022 | 65536 | 3670016 | 546040 | 70006276 | 12074888935322172 | 12074888935504655 | 12074888935767693 | 12074888935791704 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7f5907505700 | 0x7f57d72369c0 | 218646 | 218646 | 65536 | 3604480 | 498450 | 63767860 | 12074888935849181 | 12074888936031852 | 12074888936166411 | 12074888936170268 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7f5907505600 | 0x7f57d7236a00 | 329934 | 329934 | 65536 | 4849664 | 717326 | 91872920 | 12074888936243614 | 12074888936417450 | 12074888936627689 | 12074888936652744 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7f5907505500 | 0x7f57d7236a40 | 223182 | 223182 | 65536 | 3801088 | 593569 | 75888696 | 12074888936722003 | 12074888936894088 | 12074888937031527 | 12074888937034894 |
| 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 | 206 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7f5907505400 | 0x7f57d7236a80 | 473454 | 473454 | 65536 | 14548992 | 1826612 | 233815444 | 12074888937103612 | 12074888937276166 | 12074888937585604 | 12074888937609973 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7f5907505300 | 0x7f57d7236ac0 | 404086 | 404086 | 65536 | 3932160 | 518190 | 66275488 | 12074888937666298 | 12074888937835043 | 12074888938095842 | 12074888938121534 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7f5907505a00 | 0x7f57d7236b00 | 227918 | 227918 | 65536 | 3866624 | 562763 | 72073732 | 12074888938175614 | 12074888938348481 | 12074888938490240 | 12074888938493505 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7f5907505900 | 0x7f57d7236b40 | 358094 | 358094 | 65536 | 5242880 | 785774 | 100553612 | 12074888938560880 | 12074888938731263 | 12074888938959262 | 12074888938987423 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7f5907505800 | 0x7f57d7236b80 | 231358 | 231358 | 65536 | 4063232 | 634330 | 81155284 | 12074888939058876 | 12074888939232219 | 12074888939376219 | 12074888939378900 |
| 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 | 216 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7f5907505700 | 0x7f57d7236bc0 | 504854 | 504854 | 65536 | 10027008 | 1260041 | 161406892 | 12074888939449231 | 12074888939624058 | 12074888939953497 | 12074888939975820 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7f5907505600 | 0x7f57d7236c00 | 402022 | 402022 | 65536 | 4194304 | 588781 | 75233456 | 12074888940037645 | 12074888940212215 | 12074888940472534 | 12074888940497379 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7f5907505500 | 0x7f57d7236c40 | 222886 | 222886 | 65536 | 4128768 | 611725 | 78249072 | 12074888940549957 | 12074888940718613 | 12074888940856373 | 12074888940858961 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7f5907505400 | 0x7f57d7236c80 | 380598 | 380598 | 65536 | 5636096 | 771938 | 98403304 | 12074888940926647 | 12074888941109332 | 12074888941353971 | 12074888941378807 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7f5907505300 | 0x7f57d7236cc0 | 224726 | 224726 | 65536 | 4587520 | 673102 | 86169924 | 12074888941447124 | 12074888941621010 | 12074888941759729 | 12074888941762220 |
| 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 | 226 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7f5907505a00 | 0x7f57d7236d00 | 575102 | 575102 | 65536 | 11075584 | 1392964 | 178314572 | 12074888941832270 | 12074888942003728 | 12074888942380687 | 12074888942405044 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7f5907505900 | 0x7f57d7236d40 | 414974 | 414974 | 65536 | 4718592 | 629775 | 80821052 | 12074888942459856 | 12074888942630606 | 12074888942899244 | 12074888942921604 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7f5907505800 | 0x7f57d7236d80 | 227150 | 227150 | 65536 | 4653056 | 684262 | 87597456 | 12074888942974653 | 12074888943152203 | 12074888943293483 | 12074888943296230 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7f5907505700 | 0x7f57d7236dc0 | 434790 | 434790 | 65536 | 6422528 | 908770 | 116569984 | 12074888943363636 | 12074888943535562 | 12074888943815561 | 12074888943838348 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7f5907505600 | 0x7f57d7236e00 | 222790 | 222790 | 65536 | 5111808 | 803928 | 102931532 | 12074888943905933 | 12074888944090760 | 12074888944229319 | 12074888944232250 |
| 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 | 236 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7f5907505500 | 0x7f57d7236e40 | 644374 | 644374 | 65536 | 15007744 | 1887291 | 241448868 | 12074888944302340 | 12074888944477638 | 12074888944900836 | 12074888944924877 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7f5907505400 | 0x7f57d7236e80 | 405638 | 405638 | 65536 | 5242880 | 789428 | 101121016 | 12074888944981252 | 12074888945162435 | 12074888945425954 | 12074888945451496 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7f5907505300 | 0x7f57d7236ec0 | 226750 | 226750 | 65536 | 5177344 | 853625 | 109364740 | 12074888945503502 | 12074888945671553 | 12074888945812033 | 12074888945814650 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7f5907505a00 | 0x7f57d7236f00 | 488758 | 488758 | 65536 | 7208960 | 1047404 | 134914984 | 12074888945882997 | 12074888946057312 | 12074888946373150 | 12074888946398866 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7f5907505900 | 0x7f57d7236f40 | 243798 | 243798 | 65536 | 6160384 | 926082 | 118548656 | 12074888946465821 | 12074888946641149 | 12074888946793788 | 12074888946796595 |
| 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 | 246 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7f5907505800 | 0x7f57d7236f80 | 784726 | 784726 | 65536 | 17104896 | 2147176 | 274700516 | 12074888946865093 | 12074888947040827 | 12074888947558905 | 12074888947583728 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7f5907505700 | 0x7f57d7236fc0 | 462942 | 462942 | 65536 | 6291456 | 921311 | 117861964 | 12074888947637278 | 12074888947807384 | 12074888948109303 | 12074888948135934 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7f5907505600 | 0x7f57d7237000 | 246702 | 246702 | 65536 | 6225920 | 902641 | 115517268 | 12074888948186087 | 12074888948356182 | 12074888948511221 | 12074888948514087 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7f5907505500 | 0x7f57d7237040 | 594726 | 594726 | 65536 | 8781824 | 1254655 | 161103304 | 12074888948587584 | 12074888948761140 | 12074888949147699 | 12074888949173603 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7f5907505400 | 0x7f57d7237080 | 280110 | 280110 | 65536 | 7208960 | 1129602 | 144640472 | 12074888949246468 | 12074888949425298 | 12074888949603057 | 12074888949605686 |
| 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 | 256 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7f5907505300 | 0x7f57d72370c0 | 943390 | 943390 | 65536 | 19202048 | 2406884 | 308186200 | 12074888949674193 | 12074888949846416 | 12074888950468653 | 12074888950495629 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7f5907505a00 | 0x7f57d7237100 | 500950 | 500950 | 65536 | 7340032 | 1030443 | 131850348 | 12074888950547105 | 12074888950718092 | 12074888951045611 | 12074888951070939 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7f5907505900 | 0x7f57d7237140 | 283014 | 283014 | 65536 | 7274496 | 1028495 | 131587296 | 12074888951130509 | 12074888951302410 | 12074888951482089 | 12074888951484768 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7f5907505800 | 0x7f57d7237180 | 698262 | 698262 | 65536 | 10354688 | 1474316 | 188806760 | 12074888951554978 | 12074888951725288 | 12074888952181286 | 12074888952208192 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7f5907505700 | 0x7f57d72371c0 | 314134 | 314134 | 65536 | 8257536 | 1256557 | 160815212 | 12074888952279695 | 12074888952452645 | 12074888952653604 | 12074888952677234 |
| 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 | 266 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7f5907505600 | 0x7f57d7237200 | 1076190 | 1076190 | 65536 | 21299200 | 2676712 | 342604912 | 12074888952738978 | 12074888952913763 | 12074888953624320 | 12074888953650342 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7f5907505500 | 0x7f57d7237240 | 567686 | 567686 | 65536 | 8388608 | 1133506 | 145439160 | 12074888953708440 | 12074888953884479 | 12074888954256798 | 12074888954283859 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7f5907505400 | 0x7f57d7237280 | 317862 | 317862 | 65536 | 8323072 | 1254433 | 160518856 | 12074888954334924 | 12074888954505917 | 12074888954709596 | 12074888954733485 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7f5907505300 | 0x7f57d72372c0 | 803358 | 803358 | 65536 | 11927552 | 1641542 | 210367012 | 12074888954790461 | 12074888954962875 | 12074888955489273 | 12074888955514496 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7f5907505a00 | 0x7f57d7237300 | 349966 | 349966 | 65536 | 9306112 | 1431682 | 183285256 | 12074888955583985 | 12074888955759992 | 12074888955984791 | 12074888956017611 |
| 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 | 276 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7f5907505900 | 0x7f57d7237340 | 1206814 | 1206814 | 65536 | 29163520 | 3652415 | 467442716 | 12074888956076050 | 12074888956248790 | 12074888957047986 | 12074888957094482 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7f5907505800 | 0x7f57d7237380 | 636030 | 636030 | 65536 | 9437184 | 1284489 | 164851412 | 12074888957131040 | 12074888957317265 | 12074888957736944 | 12074888957779976 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7f5907505700 | 0x7f57d72373c0 | 352582 | 352582 | 65536 | 9371648 | 1353487 | 173339132 | 12074888957812938 | 12074888957997423 | 12074888958223182 | 12074888958269246 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7f5907505600 | 0x7f57d7237400 | 909790 | 909790 | 65536 | 13500416 | 1909461 | 245551060 | 12074888958305172 | 12074888958489101 | 12074888959087178 | 12074888959133682 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7f5907505500 | 0x7f57d7237440 | 417294 | 417294 | 65536 | 11403264 | 1705338 | 218360456 | 12074888959178175 | 12074888959355337 | 12074888959624776 | 12074888959668426 |
| 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 | 286 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7f5907505400 | 0x7f57d7237480 | 1486934 | 1486934 | 65536 | 33357824 | 4177740 | 534652068 | 12074888959702459 | 12074888959895815 | 12074888960882051 | 12074888960928207 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7f5907505300 | 0x7f57d72374c0 | 779454 | 779454 | 65536 | 11534336 | 1591372 | 203426964 | 12074888960965797 | 12074888961153090 | 12074888961668767 | 12074888961713086 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7f5907505a00 | 0x7f57d7237500 | 423942 | 423942 | 65536 | 11534336 | 1819915 | 232982024 | 12074888961750485 | 12074888961928766 | 12074888962202845 | 12074888962248250 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7f5907505900 | 0x7f57d7237540 | 1126774 | 1126774 | 65536 | 19267584 | 2420661 | 310285972 | 12074888962287844 | 12074888962465404 | 12074888963204281 | 12074888963249982 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7f5907505800 | 0x7f57d7237580 | 489614 | 489614 | 65536 | 13500416 | 2139642 | 273892892 | 12074888963301978 | 12074888963477720 | 12074888963794999 | 12074888963839908 |
| 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 | 296 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7f5907505700 | 0x7f57d72375c0 | 1769526 | 1769526 | 65536 | 37552128 | 4708548 | 602731776 | 12074888963873711 | 12074888964065078 | 12074888965238353 | 12074888965284212 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7f5907505600 | 0x7f57d7237600 | 921574 | 921574 | 65536 | 13631488 | 1911611 | 244214400 | 12074888965324146 | 12074888965500432 | 12074888966113069 | 12074888966158948 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7f5907505500 | 0x7f57d7237640 | 492846 | 492846 | 65536 | 13631488 | 2086011 | 267075844 | 12074888966198541 | 12074888966392428 | 12074888966712107 | 12074888966755957 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7f5907505400 | 0x7f57d7237680 | 1336910 | 1336910 | 65536 | 21692416 | 2740811 | 350861264 | 12074888966792976 | 12074888966973386 | 12074888967852902 | 12074888967899071 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7f5907505300 | 0x7f57d72376c0 | 631998 | 631998 | 65536 | 17694720 | 2749199 | 351951556 | 12074888967952160 | 12074888968133381 | 12074888968545699 | 12074888968591328 |
| 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 | 306 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7f5907505a00 | 0x7f57d7237700 | 2332342 | 2332342 | 65536 | 57475072 | 7197973 | 920769844 | 12074888968625682 | 12074888968817538 | 12074888970366972 | 12074888970411711 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7f5907505900 | 0x7f57d7237740 | 1200430 | 1200430 | 65536 | 19660800 | 2479875 | 317086968 | 12074888970450934 | 12074888970630651 | 12074888971427447 | 12074888971472522 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7f5907505800 | 0x7f57d7237780 | 640614 | 640614 | 65536 | 20381696 | 2577793 | 329853768 | 12074888971512386 | 12074888971688886 | 12074888972104725 | 12074888972149510 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7f5907505700 | 0x7f57d72377c0 | 1759806 | 1759806 | 65536 | 28704768 | 3611752 | 462594080 | 12074888972193873 | 12074888972367924 | 12074888973528719 | 12074888973574288 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7f5907505600 | 0x7f57d7237800 | 1198070 | 1198070 | 65536 | 36634624 | 4653200 | 595733552 | 12074888973626054 | 12074888973799758 | 12074888974585835 | 12074888974633156 |
| 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 | 316 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7f5907505500 | 0x7f57d7237840 | 4584790 | 4584790 | 65536 | 105840640 | 13245300 | 1694936524 | 12074888974672880 | 12074888974866473 | 12074888977918941 | 12074888977965619 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7f5907505400 | 0x7f57d7237880 | 2324838 | 2324838 | 65536 | 38535168 | 4841798 | 619350464 | 12074888978077557 | 12074888978257659 | 12074888979801013 | 12074888979848147 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7f5907505300 | 0x7f57d72378c0 | 1203310 | 1203310 | 65536 | 39124992 | 4918821 | 629565244 | 12074888979938806 | 12074888980122612 | 12074888980912209 | 12074888980958641 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7f5907505a00 | 0x7f57d7237900 | 3442886 | 3442886 | 65536 | 55771136 | 7005665 | 896322404 | 12074888981046614 | 12074888981221327 | 12074888983503398 | 12074888983553854 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7f5907505900 | 0x7f57d7237940 | 2325446 | 2325446 | 65536 | 72548352 | 9114234 | 1166608192 | 12074888983636998 | 12074888983812517 | 12074888985348670 | 12074888985396097 |
| 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 | 326 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7f5907505800 | 0x7f57d7237980 | 9087126 | 9087126 | 65536 | 210698240 | 26347058 | 3372647336 | 12074888985482338 | 12074888985665949 | 12074888991720004 | 12074888991766927 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7f5907505700 | 0x7f57d72379c0 | 4572350 | 4572350 | 65536 | 76283904 | 9557129 | 1222453272 | 12074888991845613 | 12074888992028483 | 12074888995070551 | 12074888995119968 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7f5907505600 | 0x7f57d7237a00 | 2328798 | 2328798 | 65536 | 77398016 | 9706889 | 1242593120 | 12074888995198614 | 12074888995373749 | 12074888996914223 | 12074888996960258 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 851446 | 851451 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7f5907505500 | 0x7f57d7237a40 | 6813222 | 6813222 | 65536 | 110821376 | 13879283 | 1776832124 | 12074888997047430 | 12074888997225439 | 12074889001753099 | 12074889001804089 |