40 KiB
40 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | SQ_INSTS_LDS | SQ_INST_LEVEL_LDS | SQ_ACCUM_PREV_HIRES | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBuffer.kd | 0 | 0 | 0 | 880769 | 880774 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7f7857204180 | 0 | 0 | 0 | 12075539223562575 | 12075539467660681 | 12075539467987880 | 12075539468097332 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 880769 | 880774 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7f7857235100 | 0 | 0 | 0 | 12075539482817159 | 12075539483127613 | 12075539483134333 | 12075539483143365 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7f79873eb900 | 0x7f7857235140 | 0 | 0 | 0 | 12075539483206322 | 12075539483420572 | 12075539483552891 | 12075539483556633 |
| 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 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7f79873eb800 | 0x7f7857235180 | 0 | 0 | 0 | 12075539483626673 | 12075539483798650 | 12075539484054809 | 12075539484123967 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7f79873eb700 | 0x7f78572351c0 | 0 | 0 | 0 | 12075539484154865 | 12075539484339768 | 12075539484594327 | 12075539484660885 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7f79873eb600 | 0x7f7857235200 | 0 | 0 | 0 | 12075539484685140 | 12075539484869685 | 12075539485003765 | 12075539485009242 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7f79873eb500 | 0x7f7857235240 | 0 | 0 | 0 | 12075539485057753 | 12075539485224724 | 12075539485356563 | 12075539485359924 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7f79873eb400 | 0x7f7857235280 | 0 | 0 | 0 | 12075539485437679 | 12075539485610802 | 12075539485742002 | 12075539485745300 |
| 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 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7f79873eb300 | 0x7f78572352c0 | 0 | 0 | 0 | 12075539485795353 | 12075539485972241 | 12075539486225999 | 12075539486268733 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7f79873eba00 | 0x7f7857235300 | 0 | 0 | 0 | 12075539486293469 | 12075539486478318 | 12075539486738477 | 12075539486780144 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7f79873eb900 | 0x7f7857235340 | 0 | 0 | 0 | 12075539486802615 | 12075539486993036 | 12075539487126635 | 12075539487130395 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7f79873eb800 | 0x7f7857235380 | 0 | 0 | 0 | 12075539487180668 | 12075539487352554 | 12075539487483754 | 12075539487487228 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7f79873eb700 | 0x7f78572353c0 | 0 | 0 | 0 | 12075539487548462 | 12075539487709833 | 12075539487840712 | 12075539487844061 |
| 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 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7f79873eb600 | 0x7f7857235400 | 0 | 0 | 0 | 12075539487892521 | 12075539488066951 | 12075539488325830 | 12075539488393582 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7f79873eb500 | 0x7f7857235440 | 0 | 0 | 0 | 12075539488420662 | 12075539488600069 | 12075539488852388 | 12075539488919039 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7f79873eb400 | 0x7f7857235480 | 0 | 0 | 0 | 12075539488945257 | 12075539489131907 | 12075539489266306 | 12075539489269861 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7f79873eb300 | 0x7f78572354c0 | 0 | 0 | 0 | 12075539489320144 | 12075539489485505 | 12075539489618625 | 12075539489622085 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7f79873eba00 | 0x7f7857235500 | 0 | 0 | 0 | 12075539489683039 | 12075539489841824 | 12075539489975423 | 12075539489978748 |
| 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 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7f79873eb900 | 0x7f7857235540 | 0 | 0 | 0 | 12075539490033089 | 12075539490208542 | 12075539490466301 | 12075539490534130 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7f79873eb800 | 0x7f7857235580 | 0 | 0 | 0 | 12075539490557894 | 12075539490743580 | 12075539490998299 | 12075539491041103 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7f79873eb700 | 0x7f78572355c0 | 0 | 0 | 0 | 12075539491064256 | 12075539491249337 | 12075539491383097 | 12075539491386424 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7f79873eb600 | 0x7f7857235600 | 0 | 0 | 0 | 12075539491435475 | 12075539491599576 | 12075539491736055 | 12075539491739440 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7f79873eb500 | 0x7f7857235640 | 0 | 0 | 0 | 12075539491802357 | 12075539491966134 | 12075539492100214 | 12075539492104078 |
| 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 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7f79873eb400 | 0x7f7857235680 | 0 | 0 | 0 | 12075539492153580 | 12075539492324693 | 12075539492579252 | 12075539492647588 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7f79873eb300 | 0x7f78572356c0 | 0 | 0 | 0 | 12075539492673957 | 12075539492851250 | 12075539493105649 | 12075539493173005 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7f79873eba00 | 0x7f7857235700 | 0 | 0 | 0 | 12075539493199734 | 12075539493377648 | 12075539493510128 | 12075539493513567 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7f79873eb900 | 0x7f7857235740 | 0 | 0 | 0 | 12075539493562889 | 12075539493732047 | 12075539493865486 | 12075539493868577 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7f79873eb800 | 0x7f7857235780 | 0 | 0 | 0 | 12075539493930081 | 12075539494095405 | 12075539494228204 | 12075539494231912 |
| 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 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7f79873eb700 | 0x7f78572357c0 | 0 | 0 | 0 | 12075539494281264 | 12075539494451084 | 12075539494702602 | 12075539494744225 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7f79873eb600 | 0x7f7857235800 | 0 | 0 | 0 | 12075539494769221 | 12075539494954281 | 12075539495206280 | 12075539495274149 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7f79873eb500 | 0x7f7857235840 | 0 | 0 | 0 | 12075539495298044 | 12075539495479559 | 12075539495607878 | 12075539495611066 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7f79873eb400 | 0x7f7857235880 | 0 | 0 | 0 | 12075539495662842 | 12075539495822598 | 12075539495961317 | 12075539495964663 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7f79873eb300 | 0x7f78572358c0 | 0 | 0 | 0 | 12075539496032348 | 12075539496193476 | 12075539496326275 | 12075539496330022 |
| 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 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7f79873eba00 | 0x7f7857235900 | 0 | 0 | 0 | 12075539496378802 | 12075539496547874 | 12075539496807393 | 12075539496875045 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7f79873eb900 | 0x7f7857235940 | 0 | 0 | 0 | 12075539496898468 | 12075539497082592 | 12075539497337311 | 12075539497405470 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7f79873eb800 | 0x7f7857235980 | 0 | 0 | 0 | 12075539497434264 | 12075539497612830 | 12075539497751389 | 12075539497754820 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7f79873eb700 | 0x7f78572359c0 | 0 | 0 | 0 | 12075539497807898 | 12075539497977948 | 12075539498112828 | 12075539498116271 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7f79873eb600 | 0x7f7857235a00 | 0 | 0 | 0 | 12075539498178417 | 12075539498342587 | 12075539498473306 | 12075539498476481 |
| 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 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7f79873eb500 | 0x7f7857235a40 | 0 | 0 | 0 | 12075539498525652 | 12075539498699225 | 12075539498960504 | 12075539499010363 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7f79873eb400 | 0x7f7857235a80 | 0 | 0 | 0 | 12075539499033075 | 12075539499214743 | 12075539499470102 | 12075539499511534 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7f79873eb300 | 0x7f7857235ac0 | 0 | 0 | 0 | 12075539499539286 | 12075539499712021 | 12075539499848980 | 12075539499852388 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7f79873eba00 | 0x7f7857235b00 | 0 | 0 | 0 | 12075539499906458 | 12075539500072019 | 12075539500204338 | 12075539500208149 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7f79873eb900 | 0x7f7857235b40 | 0 | 0 | 0 | 12075539500273510 | 12075539500437457 | 12075539500566897 | 12075539500570292 |
| 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 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7f79873eb800 | 0x7f7857235b80 | 0 | 0 | 0 | 12075539500620866 | 12075539500788496 | 12075539501056495 | 12075539501124823 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7f79873eb700 | 0x7f7857235bc0 | 0 | 0 | 0 | 12075539501155389 | 12075539501332173 | 12075539501592172 | 12075539501660468 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7f79873eb600 | 0x7f7857235c00 | 0 | 0 | 0 | 12075539501683411 | 12075539501862571 | 12075539501993771 | 12075539501997394 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7f79873eb500 | 0x7f7857235c40 | 0 | 0 | 0 | 12075539502049461 | 12075539502212170 | 12075539502347689 | 12075539502351242 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7f79873eb400 | 0x7f7857235c80 | 0 | 0 | 0 | 12075539502412546 | 12075539502573288 | 12075539502702248 | 12075539502705681 |
| 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 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7f79873eb300 | 0x7f7857235cc0 | 0 | 0 | 0 | 12075539502753850 | 12075539502926727 | 12075539503195365 | 12075539503264229 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7f79873eba00 | 0x7f7857235d00 | 0 | 0 | 0 | 12075539503289215 | 12075539503467844 | 12075539503718563 | 12075539503785668 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7f79873eb900 | 0x7f7857235d40 | 0 | 0 | 0 | 12075539503808390 | 12075539503987522 | 12075539504121121 | 12075539504124868 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7f79873eb800 | 0x7f7857235d80 | 0 | 0 | 0 | 12075539504174691 | 12075539504338880 | 12075539504480480 | 12075539504483895 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7f79873eb700 | 0x7f7857235dc0 | 0 | 0 | 0 | 12075539504544037 | 12075539504703839 | 12075539504833918 | 12075539504837152 |
| 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 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7f79873eb600 | 0x7f7857235e00 | 0 | 0 | 0 | 12075539504885882 | 12075539505052317 | 12075539505325756 | 12075539505393315 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7f79873eb500 | 0x7f7857235e40 | 0 | 0 | 0 | 12075539505417661 | 12075539505596635 | 12075539505848474 | 12075539505889999 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7f79873eb400 | 0x7f7857235e80 | 0 | 0 | 0 | 12075539505917339 | 12075539506097113 | 12075539506229272 | 12075539506232675 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7f79873eb300 | 0x7f7857235ec0 | 0 | 0 | 0 | 12075539506285554 | 12075539506444951 | 12075539506581751 | 12075539506585271 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7f79873eba00 | 0x7f7857235f00 | 0 | 0 | 0 | 12075539506647977 | 12075539506807030 | 12075539506939829 | 12075539506943096 |
| 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 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7f79873eb900 | 0x7f7857235f40 | 0 | 0 | 0 | 12075539506991475 | 12075539507171188 | 12075539507437267 | 12075539507506122 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7f79873eb800 | 0x7f7857235f80 | 0 | 0 | 0 | 12075539507531379 | 12075539507708146 | 12075539507973105 | 12075539508042168 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7f79873eb700 | 0x7f7857235fc0 | 0 | 0 | 0 | 12075539508072635 | 12075539508250703 | 12075539508381743 | 12075539508385106 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7f79873eb600 | 0x7f7857236000 | 0 | 0 | 0 | 12075539508434367 | 12075539508595502 | 12075539508735181 | 12075539508738562 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7f79873eb500 | 0x7f7857236040 | 0 | 0 | 0 | 12075539508800157 | 12075539508956780 | 12075539509089260 | 12075539509092981 |
| 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 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7f79873eb400 | 0x7f7857236080 | 0 | 0 | 0 | 12075539509142794 | 12075539509310699 | 12075539509576778 | 12075539509626503 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7f79873eb300 | 0x7f78572360c0 | 0 | 0 | 0 | 12075539509650207 | 12075539509825096 | 12075539510082535 | 12075539510130179 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7f79873eba00 | 0x7f7857236100 | 0 | 0 | 0 | 12075539510156548 | 12075539510331494 | 12075539510463654 | 12075539510466824 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7f79873eb900 | 0x7f7857236140 | 0 | 0 | 0 | 12075539510516617 | 12075539510685733 | 12075539510831972 | 12075539510835189 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7f79873eb800 | 0x7f7857236180 | 0 | 0 | 0 | 12075539510896292 | 12075539511070851 | 12075539511210850 | 12075539511214965 |
| 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 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7f79873eb700 | 0x7f78572361c0 | 0 | 0 | 0 | 12075539511264587 | 12075539511429089 | 12075539511697728 | 12075539511745370 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7f79873eb600 | 0x7f7857236200 | 0 | 0 | 0 | 12075539511770497 | 12075539511944927 | 12075539512201566 | 12075539512251942 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7f79873eb500 | 0x7f7857236240 | 0 | 0 | 0 | 12075539512279774 | 12075539512456925 | 12075539512588924 | 12075539512592535 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7f79873eb400 | 0x7f7857236280 | 0 | 0 | 0 | 12075539512641065 | 12075539512806523 | 12075539512957723 | 12075539512961280 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7f79873eb300 | 0x7f78572362c0 | 0 | 0 | 0 | 12075539513045727 | 12075539513207162 | 12075539513342041 | 12075539513345735 |
| 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 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7f79873eba00 | 0x7f7857236300 | 0 | 0 | 0 | 12075539513394074 | 12075539513564440 | 12075539513833559 | 12075539513856223 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7f79873eb900 | 0x7f7857236340 | 0 | 0 | 0 | 12075539513898802 | 12075539514066998 | 12075539514318997 | 12075539514368235 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7f79873eb800 | 0x7f7857236380 | 0 | 0 | 0 | 12075539514393913 | 12075539514574836 | 12075539514714515 | 12075539514717644 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7f79873eb700 | 0x7f78572363c0 | 0 | 0 | 0 | 12075539514771134 | 12075539514927954 | 12075539515085393 | 12075539515089325 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7f79873eb600 | 0x7f7857236400 | 0 | 0 | 0 | 12075539515155959 | 12075539515318672 | 12075539515453072 | 12075539515456668 |
| 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 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7f79873eb500 | 0x7f7857236440 | 0 | 0 | 0 | 12075539515505619 | 12075539515673871 | 12075539515940110 | 12075539515987705 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7f79873eb400 | 0x7f7857236480 | 0 | 0 | 0 | 12075539516020075 | 12075539516193549 | 12075539516450188 | 12075539516499366 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7f79873eb300 | 0x7f78572364c0 | 0 | 0 | 0 | 12075539516525995 | 12075539516698826 | 12075539516830506 | 12075539516834028 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7f79873eba00 | 0x7f7857236500 | 0 | 0 | 0 | 12075539516887677 | 12075539517050825 | 12075539517216904 | 12075539517220636 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7f79873eb900 | 0x7f7857236540 | 0 | 0 | 0 | 12075539517286178 | 12075539517445703 | 12075539517581543 | 12075539517584993 |
| 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 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7f79873eb800 | 0x7f7857236580 | 0 | 0 | 0 | 12075539517634756 | 12075539517822982 | 12075539518091460 | 12075539518139794 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7f79873eb700 | 0x7f78572365c0 | 0 | 0 | 0 | 12075539518164500 | 12075539518345059 | 12075539518605858 | 12075539518651255 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7f79873eb600 | 0x7f7857236600 | 0 | 0 | 0 | 12075539518676983 | 12075539518854977 | 12075539518986496 | 12075539518989724 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7f79873eb500 | 0x7f7857236640 | 0 | 0 | 0 | 12075539519041280 | 12075539519209696 | 12075539519383295 | 12075539519386982 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7f79873eb400 | 0x7f7857236680 | 0 | 0 | 0 | 12075539519447585 | 12075539519604734 | 12075539519737373 | 12075539519740820 |
| 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 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7f79873eb300 | 0x7f78572366c0 | 0 | 0 | 0 | 12075539519792936 | 12075539519951452 | 12075539520212411 | 12075539520260135 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7f79873eba00 | 0x7f7857236700 | 0 | 0 | 0 | 12075539520283969 | 12075539520461050 | 12075539520719929 | 12075539520767658 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7f79873eb900 | 0x7f7857236740 | 0 | 0 | 0 | 12075539520792705 | 12075539520965048 | 12075539521099767 | 12075539521103993 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7f79873eb800 | 0x7f7857236780 | 0 | 0 | 0 | 12075539521152483 | 12075539521321366 | 12075539521503925 | 12075539521507393 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7f79873eb700 | 0x7f78572367c0 | 0 | 0 | 0 | 12075539521570239 | 12075539521728085 | 12075539521869844 | 12075539521873373 |
| 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 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7f79873eb600 | 0x7f7857236800 | 0 | 0 | 0 | 12075539521921893 | 12075539522094483 | 12075539522395282 | 12075539522445206 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7f79873eb500 | 0x7f7857236840 | 0 | 0 | 0 | 12075539522470553 | 12075539522652720 | 12075539522905359 | 12075539522952278 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7f79873eb400 | 0x7f7857236880 | 0 | 0 | 0 | 12075539522974820 | 12075539523159118 | 12075539523297198 | 12075539523300806 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7f79873eb300 | 0x7f78572368c0 | 0 | 0 | 0 | 12075539523350668 | 12075539523510797 | 12075539523703116 | 12075539523750291 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7f79873eba00 | 0x7f7857236900 | 0 | 0 | 0 | 12075539523788642 | 12075539523948395 | 12075539524087754 | 12075539524091425 |
| 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 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7f79873eb900 | 0x7f7857236940 | 0 | 0 | 0 | 12075539524139925 | 12075539524310313 | 12075539524594632 | 12075539524640896 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7f79873eb800 | 0x7f7857236980 | 0 | 0 | 0 | 12075539524666233 | 12075539524840711 | 12075539525098310 | 12075539525148670 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7f79873eb700 | 0x7f78572369c0 | 0 | 0 | 0 | 12075539525175780 | 12075539525350789 | 12075539525486948 | 12075539525490375 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7f79873eb600 | 0x7f7857236a00 | 0 | 0 | 0 | 12075539525538685 | 12075539525702787 | 12075539525914146 | 12075539525960408 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7f79873eb500 | 0x7f7857236a40 | 0 | 0 | 0 | 12075539525999401 | 12075539526167265 | 12075539526303585 | 12075539526307163 |
| 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 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7f79873eb400 | 0x7f7857236a80 | 0 | 0 | 0 | 12075539526356885 | 12075539526526144 | 12075539526833982 | 12075539526881120 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7f79873eb300 | 0x7f7857236ac0 | 0 | 0 | 0 | 12075539526904403 | 12075539527090141 | 12075539527347420 | 12075539527396848 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7f79873eba00 | 0x7f7857236b00 | 0 | 0 | 0 | 12075539527420021 | 12075539527598299 | 12075539527735258 | 12075539527738914 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7f79873eb900 | 0x7f7857236b40 | 0 | 0 | 0 | 12075539527787674 | 12075539527956537 | 12075539528186136 | 12075539528208527 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7f79873eb800 | 0x7f7857236b80 | 0 | 0 | 0 | 12075539528266134 | 12075539528427575 | 12075539528565975 | 12075539528569227 |
| 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 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7f79873eb700 | 0x7f7857236bc0 | 0 | 0 | 0 | 12075539528617527 | 12075539528784534 | 12075539529114292 | 12075539529164223 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7f79873eb600 | 0x7f7857236c00 | 0 | 0 | 0 | 12075539529191193 | 12075539529366131 | 12075539529629650 | 12075539529678078 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7f79873eb500 | 0x7f7857236c40 | 0 | 0 | 0 | 12075539529704517 | 12075539529875729 | 12075539530013808 | 12075539530017579 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7f79873eb400 | 0x7f7857236c80 | 0 | 0 | 0 | 12075539530069124 | 12075539530229487 | 12075539530475086 | 12075539530521896 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7f79873eb300 | 0x7f7857236cc0 | 0 | 0 | 0 | 12075539530558003 | 12075539530726519 | 12075539530866519 | 12075539530873609 |
| 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 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7f79873eba00 | 0x7f7857236d00 | 0 | 0 | 0 | 12075539530921849 | 12075539531086517 | 12075539531463315 | 12075539531511765 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7f79873eb900 | 0x7f7857236d40 | 0 | 0 | 0 | 12075539531540649 | 12075539531715314 | 12075539531984753 | 12075539532031972 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7f79873eb800 | 0x7f7857236d80 | 0 | 0 | 0 | 12075539532058772 | 12075539532233232 | 12075539532376272 | 12075539532379127 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7f79873eb700 | 0x7f7857236dc0 | 0 | 0 | 0 | 12075539532429240 | 12075539532590671 | 12075539532869870 | 12075539532917047 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7f79873eb600 | 0x7f7857236e00 | 0 | 0 | 0 | 12075539532957292 | 12075539533121549 | 12075539533259948 | 12075539533263401 |
| 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 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7f79873eb500 | 0x7f7857236e40 | 0 | 0 | 0 | 12075539533312953 | 12075539533480587 | 12075539533904426 | 12075539533950698 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7f79873eb400 | 0x7f7857236e80 | 0 | 0 | 0 | 12075539533978189 | 12075539534161065 | 12075539534426984 | 12075539534474862 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7f79873eb300 | 0x7f7857236ec0 | 0 | 0 | 0 | 12075539534498787 | 12075539534677223 | 12075539534817702 | 12075539534820915 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7f79873eba00 | 0x7f7857236f00 | 0 | 0 | 0 | 12075539534870027 | 12075539535033701 | 12075539535350180 | 12075539535398749 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7f79873eb900 | 0x7f7857236f40 | 0 | 0 | 0 | 12075539535436169 | 12075539535600899 | 12075539535753539 | 12075539535756895 |
| 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 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7f79873eb800 | 0x7f7857236f80 | 0 | 0 | 0 | 12075539535805996 | 12075539535972098 | 12075539536491136 | 12075539536537596 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7f79873eb700 | 0x7f7857236fc0 | 0 | 0 | 0 | 12075539536561700 | 12075539536742335 | 12075539537041054 | 12075539537088419 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7f79873eb600 | 0x7f7857237000 | 0 | 0 | 0 | 12075539537111993 | 12075539537296253 | 12075539537451612 | 12075539537454790 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7f79873eb500 | 0x7f7857237040 | 0 | 0 | 0 | 12075539537504282 | 12075539537665051 | 12075539538050970 | 12075539538099007 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7f79873eb400 | 0x7f7857237080 | 0 | 0 | 0 | 12075539538143560 | 12075539538307609 | 12075539538484568 | 12075539538487660 |
| 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 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7f79873eb300 | 0x7f78572370c0 | 0 | 0 | 0 | 12075539538538404 | 12075539538696407 | 12075539539306645 | 12075539539354300 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7f79873eba00 | 0x7f7857237100 | 0 | 0 | 0 | 12075539539378766 | 12075539539562804 | 12075539539891603 | 12075539539938807 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7f79873eb900 | 0x7f7857237140 | 0 | 0 | 0 | 12075539539965556 | 12075539540151122 | 12075539540331281 | 12075539540334712 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7f79873eb800 | 0x7f7857237180 | 0 | 0 | 0 | 12075539540385276 | 12075539540554000 | 12075539541010638 | 12075539541060421 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7f79873eb700 | 0x7f78572371c0 | 0 | 0 | 0 | 12075539541100195 | 12075539541262317 | 12075539541462957 | 12075539541508925 |
| 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 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7f79873eb600 | 0x7f7857237200 | 0 | 0 | 0 | 12075539541534663 | 12075539541710796 | 12075539542421353 | 12075539542469199 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7f79873eb500 | 0x7f7857237240 | 0 | 0 | 0 | 12075539542494015 | 12075539542674792 | 12075539543046790 | 12075539543095062 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7f79873eb400 | 0x7f7857237280 | 0 | 0 | 0 | 12075539543124377 | 12075539543302309 | 12075539543505509 | 12075539543552102 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7f79873eb300 | 0x7f78572372c0 | 0 | 0 | 0 | 12075539543578301 | 12075539543750628 | 12075539544277026 | 12075539544328775 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7f79873eba00 | 0x7f7857237300 | 0 | 0 | 0 | 12075539544376284 | 12075539544551105 | 12075539544810304 | 12075539544857798 |
| 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 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7f79873eb900 | 0x7f7857237340 | 0 | 0 | 0 | 12075539544883747 | 12075539545063103 | 12075539545862780 | 12075539545913871 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7f79873eb800 | 0x7f7857237380 | 0 | 0 | 0 | 12075539545944147 | 12075539546122139 | 12075539546543257 | 12075539546591270 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7f79873eb700 | 0x7f78572373c0 | 0 | 0 | 0 | 12075539546614834 | 12075539546803416 | 12075539547030615 | 12075539547079798 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7f79873eb600 | 0x7f7857237400 | 0 | 0 | 0 | 12075539547110735 | 12075539547288534 | 12075539547885972 | 12075539547952069 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7f79873eb500 | 0x7f7857237440 | 0 | 0 | 0 | 12075539547990951 | 12075539548157011 | 12075539548427090 | 12075539548494076 |
| 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 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7f79873eb400 | 0x7f7857237480 | 0 | 0 | 0 | 12075539548522028 | 12075539548693329 | 12075539549679725 | 12075539549747866 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7f79873eb300 | 0x7f78572374c0 | 0 | 0 | 0 | 12075539549778744 | 12075539549959084 | 12075539550472362 | 12075539550541491 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7f79873eba00 | 0x7f7857237500 | 0 | 0 | 0 | 12075539550570435 | 12075539550750761 | 12075539551024200 | 12075539551091213 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7f79873eb900 | 0x7f7857237540 | 0 | 0 | 0 | 12075539551127811 | 12075539551287719 | 12075539552026116 | 12075539552094187 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7f79873eb800 | 0x7f7857237580 | 0 | 0 | 0 | 12075539552139201 | 12075539552300675 | 12075539552619233 | 12075539552686598 |
| 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 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7f79873eb700 | 0x7f78572375c0 | 0 | 0 | 0 | 12075539552715612 | 12075539552893632 | 12075539554065628 | 12075539554134759 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7f79873eb600 | 0x7f7857237600 | 0 | 0 | 0 | 12075539554164044 | 12075539554350587 | 12075539554961304 | 12075539555029041 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7f79873eb500 | 0x7f7857237640 | 0 | 0 | 0 | 12075539555059077 | 12075539555240023 | 12075539555559222 | 12075539555626011 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7f79873eb400 | 0x7f7857237680 | 0 | 0 | 0 | 12075539555653181 | 12075539555826261 | 12075539556705778 | 12075539556775297 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7f79873eb300 | 0x7f78572376c0 | 0 | 0 | 0 | 12075539556817655 | 12075539556980337 | 12075539557389135 | 12075539557457184 |
| 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 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7f79873eba00 | 0x7f7857237700 | 0 | 0 | 0 | 12075539557483252 | 12075539557658574 | 12075539559210088 | 12075539559278589 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7f79873eb900 | 0x7f7857237740 | 0 | 0 | 0 | 12075539559309807 | 12075539559489767 | 12075539560285604 | 12075539560353637 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7f79873eb800 | 0x7f7857237780 | 0 | 0 | 0 | 12075539560383542 | 12075539560561763 | 12075539560977281 | 12075539561045112 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7f79873eb700 | 0x7f78572377c0 | 0 | 0 | 0 | 12075539561077151 | 12075539561251360 | 12075539562410076 | 12075539562477283 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7f79873eb600 | 0x7f7857237800 | 0 | 0 | 0 | 12075539562517278 | 12075539562679034 | 12075539563465271 | 12075539563532715 |
| 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 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7f79873eb500 | 0x7f7857237840 | 0 | 0 | 0 | 12075539563563913 | 12075539563741750 | 12075539566792139 | 12075539566860289 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7f79873eb400 | 0x7f7857237880 | 0 | 0 | 0 | 12075539566893100 | 12075539567075177 | 12075539568619492 | 12075539568689789 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7f79873eb300 | 0x7f78572378c0 | 0 | 0 | 0 | 12075539568714545 | 12075539568901090 | 12075539569690687 | 12075539569759687 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7f79873eba00 | 0x7f7857237900 | 0 | 0 | 0 | 12075539569785716 | 12075539569971486 | 12075539572253717 | 12075539572322160 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7f79873eb900 | 0x7f7857237940 | 0 | 0 | 0 | 12075539572366472 | 12075539572532596 | 12075539574068110 | 12075539574135770 |
| 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 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7f79873eb800 | 0x7f7857237980 | 0 | 0 | 0 | 12075539574166898 | 12075539574344749 | 12075539580401686 | 12075539580472397 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7f79873eb700 | 0x7f78572379c0 | 0 | 0 | 0 | 12075539580501140 | 12075539580675445 | 12075539583716553 | 12075539583787387 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7f79873eb600 | 0x7f7857237a00 | 0 | 0 | 0 | 12075539583814949 | 12075539583996872 | 12075539585535586 | 12075539585606418 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 880769 | 880774 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7f79873eb500 | 0x7f7857237a40 | 0 | 0 | 0 | 12075539585638878 | 12075539585815105 | 12075539590342447 | 12075539590414654 |