39 KiB
39 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBuffer.kd | 0 | 0 | 0 | 873448 | 873453 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7f47ac404180 | 12075402664803599 | 12075402664851029 | 12075402665174706 | 12075402665287268 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 873448 | 873453 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7f47ac435100 | 12075402679814105 | 12075402679915257 | 12075402679922137 | 12075402679928087 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7f48b80c6900 | 0x7f47ac435140 | 12075402679968402 | 12075402679981496 | 12075402680111895 | 12075402680115946 |
| 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 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7f48b80c6800 | 0x7f47ac435180 | 12075402680160700 | 12075402680178455 | 12075402680426452 | 12075402680525748 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7f48b80c6700 | 0x7f47ac4351c0 | 12075402680550975 | 12075402680563091 | 12075402680807249 | 12075402680904141 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7f48b80c6600 | 0x7f47ac435200 | 12075402680928306 | 12075402680940048 | 12075402681065007 | 12075402681068777 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7f48b80c6500 | 0x7f47ac435240 | 12075402681094215 | 12075402681106287 | 12075402681231725 | 12075402681235016 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7f48b80c6400 | 0x7f47ac435280 | 12075402681288636 | 12075402681300365 | 12075402681424844 | 12075402681428005 |
| 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 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7f48b80c6300 | 0x7f47ac4352c0 | 12075402681453953 | 12075402681465483 | 12075402681712681 | 12075402681810546 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7f48b80c6a00 | 0x7f47ac435300 | 12075402681830463 | 12075402681845000 | 12075402682088038 | 12075402682189520 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7f48b80c6900 | 0x7f47ac435340 | 12075402682210329 | 12075402682222597 | 12075402682347396 | 12075402682350830 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7f48b80c6800 | 0x7f47ac435380 | 12075402682376518 | 12075402682388195 | 12075402682513794 | 12075402682517169 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7f48b80c6700 | 0x7f47ac4353c0 | 12075402682553667 | 12075402682564834 | 12075402682688993 | 12075402682692294 |
| 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 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7f48b80c6600 | 0x7f47ac435400 | 12075402682717441 | 12075402682729792 | 12075402682980510 | 12075402683059317 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7f48b80c6500 | 0x7f47ac435440 | 12075402683081257 | 12075402683092829 | 12075402683336507 | 12075402683433833 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7f48b80c6400 | 0x7f47ac435480 | 12075402683453189 | 12075402683464186 | 12075402683588985 | 12075402683592317 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7f48b80c6300 | 0x7f47ac4354c0 | 12075402683617043 | 12075402683628665 | 12075402683753623 | 12075402683757183 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7f48b80c6a00 | 0x7f47ac435500 | 12075402683792439 | 12075402683804183 | 12075402683928662 | 12075402683931838 |
| 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 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7f48b80c6900 | 0x7f47ac435540 | 12075402683956804 | 12075402683968662 | 12075402684214739 | 12075402684316593 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7f48b80c6800 | 0x7f47ac435580 | 12075402684336580 | 12075402684348818 | 12075402684593296 | 12075402684662807 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7f48b80c6700 | 0x7f47ac4355c0 | 12075402684682673 | 12075402684694095 | 12075402684819214 | 12075402684822343 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7f48b80c6600 | 0x7f47ac435600 | 12075402684848672 | 12075402684860174 | 12075402684985613 | 12075402684988983 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7f48b80c6500 | 0x7f47ac435640 | 12075402685031301 | 12075402685042732 | 12075402685166731 | 12075402685169999 |
| 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 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7f48b80c6400 | 0x7f47ac435680 | 12075402685195386 | 12075402685207371 | 12075402685453769 | 12075402685497017 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7f48b80c6300 | 0x7f47ac4356c0 | 12075402685517054 | 12075402685528968 | 12075402685776966 | 12075402685842940 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7f48b80c6a00 | 0x7f47ac435700 | 12075402685864079 | 12075402685875205 | 12075402685999524 | 12075402686005432 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7f48b80c6900 | 0x7f47ac435740 | 12075402686028895 | 12075402686040483 | 12075402686165602 | 12075402686168815 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7f48b80c6800 | 0x7f47ac435780 | 12075402686203911 | 12075402686216482 | 12075402686340641 | 12075402686343730 |
| 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 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7f48b80c6700 | 0x7f47ac4357c0 | 12075402686367935 | 12075402686379841 | 12075402686631678 | 12075402686655630 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7f48b80c6600 | 0x7f47ac435800 | 12075402686675076 | 12075402686686238 | 12075402686929916 | 12075402686951330 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7f48b80c6500 | 0x7f47ac435840 | 12075402686970996 | 12075402686983515 | 12075402687107994 | 12075402687111808 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7f48b80c6400 | 0x7f47ac435880 | 12075402687138097 | 12075402687150394 | 12075402687276313 | 12075402687279590 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7f48b80c6300 | 0x7f47ac4358c0 | 12075402687315446 | 12075402687329112 | 12075402687454231 | 12075402687457420 |
| 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 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7f48b80c6a00 | 0x7f47ac435900 | 12075402687482256 | 12075402687495191 | 12075402687742069 | 12075402687819723 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7f48b80c6900 | 0x7f47ac435940 | 12075402687839210 | 12075402687858868 | 12075402688103985 | 12075402688185273 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7f48b80c6800 | 0x7f47ac435980 | 12075402688205070 | 12075402688215985 | 12075402688340783 | 12075402688344318 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7f48b80c6700 | 0x7f47ac4359c0 | 12075402688368123 | 12075402688379183 | 12075402688504462 | 12075402688507973 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7f48b80c6600 | 0x7f47ac435a00 | 12075402688541054 | 12075402688552622 | 12075402688676780 | 12075402688680012 |
| 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 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7f48b80c6500 | 0x7f47ac435a40 | 12075402688704358 | 12075402688716460 | 12075402688961578 | 12075402689019964 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7f48b80c6400 | 0x7f47ac435a80 | 12075402689040192 | 12075402689051177 | 12075402689294375 | 12075402689372179 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7f48b80c6300 | 0x7f47ac435ac0 | 12075402689392146 | 12075402689403974 | 12075402689529093 | 12075402689532417 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7f48b80c6a00 | 0x7f47ac435b00 | 12075402689557533 | 12075402689569093 | 12075402689695332 | 12075402689698625 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7f48b80c6900 | 0x7f47ac435b40 | 12075402689737257 | 12075402689750211 | 12075402689875330 | 12075402689878420 |
| 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 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7f48b80c6800 | 0x7f47ac435b80 | 12075402689902835 | 12075402689914530 | 12075402690165408 | 12075402690217971 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7f48b80c6700 | 0x7f47ac435bc0 | 12075402690237537 | 12075402690248767 | 12075402690496445 | 12075402690523709 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7f48b80c6600 | 0x7f47ac435c00 | 12075402690543135 | 12075402690554364 | 12075402690678683 | 12075402690681843 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7f48b80c6500 | 0x7f47ac435c40 | 12075402690708442 | 12075402690719323 | 12075402690845882 | 12075402690849013 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7f48b80c6400 | 0x7f47ac435c80 | 12075402690885491 | 12075402690897561 | 12075402691022040 | 12075402691025591 |
| 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 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7f48b80c6300 | 0x7f47ac435cc0 | 12075402691052251 | 12075402691063640 | 12075402691318037 | 12075402691343322 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7f48b80c6a00 | 0x7f47ac435d00 | 12075402691362969 | 12075402691374037 | 12075402691621715 | 12075402691647457 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7f48b80c6900 | 0x7f47ac435d40 | 12075402691668256 | 12075402691681074 | 12075402691805873 | 12075402691808947 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7f48b80c6800 | 0x7f47ac435d80 | 12075402691833904 | 12075402691845393 | 12075402691973872 | 12075402691976980 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7f48b80c6700 | 0x7f47ac435dc0 | 12075402692017335 | 12075402692030511 | 12075402692155630 | 12075402692158768 |
| 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 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7f48b80c6600 | 0x7f47ac435e00 | 12075402692184465 | 12075402692196910 | 12075402692451468 | 12075402692473522 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7f48b80c6500 | 0x7f47ac435e40 | 12075402692492297 | 12075402692505227 | 12075402692752905 | 12075402692774492 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7f48b80c6400 | 0x7f47ac435e80 | 12075402692795861 | 12075402692808264 | 12075402692932903 | 12075402692936202 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7f48b80c6300 | 0x7f47ac435ec0 | 12075402692959546 | 12075402692970663 | 12075402693099142 | 12075402693102411 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7f48b80c6a00 | 0x7f47ac435f00 | 12075402693138468 | 12075402693149861 | 12075402693275300 | 12075402693278579 |
| 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 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7f48b80c6900 | 0x7f47ac435f40 | 12075402693298586 | 12075402693309860 | 12075402693561058 | 12075402693585559 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7f48b80c6800 | 0x7f47ac435f80 | 12075402693604745 | 12075402693615937 | 12075402693860895 | 12075402693885617 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7f48b80c6700 | 0x7f47ac435fc0 | 12075402693906375 | 12075402693917695 | 12075402694042974 | 12075402694046506 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7f48b80c6600 | 0x7f47ac436000 | 12075402694072985 | 12075402694084093 | 12075402694219772 | 12075402694222984 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7f48b80c6500 | 0x7f47ac436040 | 12075402694258440 | 12075402694269692 | 12075402694394811 | 12075402694398069 |
| 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 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7f48b80c6400 | 0x7f47ac436080 | 12075402694421883 | 12075402694433530 | 12075402694693048 | 12075402694717783 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7f48b80c6300 | 0x7f47ac4360c0 | 12075402694737560 | 12075402694750328 | 12075402694995765 | 12075402695023612 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7f48b80c6a00 | 0x7f47ac436100 | 12075402695043549 | 12075402695055765 | 12075402695179924 | 12075402695183358 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7f48b80c6900 | 0x7f47ac436140 | 12075402695207533 | 12075402695219923 | 12075402695362002 | 12075402695365116 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7f48b80c6800 | 0x7f47ac436180 | 12075402695398929 | 12075402695411122 | 12075402695536081 | 12075402695539330 |
| 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 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7f48b80c6700 | 0x7f47ac4361c0 | 12075402695562373 | 12075402695573680 | 12075402695841678 | 12075402695867089 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7f48b80c6600 | 0x7f47ac436200 | 12075402695886125 | 12075402695897518 | 12075402696141515 | 12075402696173419 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7f48b80c6500 | 0x7f47ac436240 | 12075402696194478 | 12075402696205835 | 12075402696331274 | 12075402696334418 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7f48b80c6400 | 0x7f47ac436280 | 12075402696358863 | 12075402696369993 | 12075402696520392 | 12075402696523489 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7f48b80c6300 | 0x7f47ac4362c0 | 12075402696577099 | 12075402696589031 | 12075402696714470 | 12075402696717800 |
| 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 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7f48b80c6a00 | 0x7f47ac436300 | 12075402696742757 | 12075402696754630 | 12075402697008068 | 12075402697036392 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7f48b80c6900 | 0x7f47ac436340 | 12075402697056460 | 12075402697069187 | 12075402697314465 | 12075402697342231 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7f48b80c6800 | 0x7f47ac436380 | 12075402697361977 | 12075402697374305 | 12075402697499744 | 12075402697502889 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7f48b80c6700 | 0x7f47ac4363c0 | 12075402697528597 | 12075402697541023 | 12075402697698782 | 12075402697701879 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7f48b80c6600 | 0x7f47ac436400 | 12075402697737225 | 12075402697749821 | 12075402697875100 | 12075402697877976 |
| 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 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7f48b80c6500 | 0x7f47ac436440 | 12075402697903564 | 12075402697915900 | 12075402698169978 | 12075402698203020 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7f48b80c6400 | 0x7f47ac436480 | 12075402698218359 | 12075402698232217 | 12075402698482135 | 12075402698506965 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7f48b80c6300 | 0x7f47ac4364c0 | 12075402698526852 | 12075402698539414 | 12075402698665493 | 12075402698668806 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7f48b80c6a00 | 0x7f47ac436500 | 12075402698693662 | 12075402698705813 | 12075402698871092 | 12075402698874328 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7f48b80c6900 | 0x7f47ac436540 | 12075402698908892 | 12075402698921331 | 12075402699046770 | 12075402699049954 |
| 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 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7f48b80c6800 | 0x7f47ac436580 | 12075402699076093 | 12075402699088210 | 12075402699340367 | 12075402699363928 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7f48b80c6700 | 0x7f47ac4365c0 | 12075402699384055 | 12075402699395247 | 12075402699646765 | 12075402699669716 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7f48b80c6600 | 0x7f47ac436600 | 12075402699689944 | 12075402699702444 | 12075402699827723 | 12075402699830906 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7f48b80c6500 | 0x7f47ac436640 | 12075402699853638 | 12075402699866763 | 12075402700039561 | 12075402700043110 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7f48b80c6400 | 0x7f47ac436680 | 12075402700077895 | 12075402700090601 | 12075402700215560 | 12075402700218827 |
| 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 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7f48b80c6300 | 0x7f47ac4366c0 | 12075402700243583 | 12075402700256039 | 12075402700510757 | 12075402700534073 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7f48b80c6a00 | 0x7f47ac436700 | 12075402700552427 | 12075402700565157 | 12075402700810115 | 12075402700833249 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7f48b80c6900 | 0x7f47ac436740 | 12075402700853115 | 12075402700865474 | 12075402700991713 | 12075402700994849 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7f48b80c6800 | 0x7f47ac436780 | 12075402701023622 | 12075402701035713 | 12075402701218271 | 12075402701221680 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7f48b80c6700 | 0x7f47ac4367c0 | 12075402701257056 | 12075402701269471 | 12075402701396190 | 12075402701399321 |
| 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 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7f48b80c6600 | 0x7f47ac436800 | 12075402701424668 | 12075402701437309 | 12075402701702267 | 12075402701722261 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7f48b80c6500 | 0x7f47ac436840 | 12075402701741176 | 12075402701753946 | 12075402702000824 | 12075402702028290 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7f48b80c6400 | 0x7f47ac436880 | 12075402702047946 | 12075402702060984 | 12075402702186903 | 12075402702190070 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7f48b80c6300 | 0x7f47ac4368c0 | 12075402702214926 | 12075402702227222 | 12075402702418421 | 12075402702421791 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7f48b80c6a00 | 0x7f47ac436900 | 12075402702455584 | 12075402702468500 | 12075402702595059 | 12075402702598509 |
| 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 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7f48b80c6900 | 0x7f47ac436940 | 12075402702622634 | 12075402702635379 | 12075402702917296 | 12075402702941176 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7f48b80c6800 | 0x7f47ac436980 | 12075402702959180 | 12075402702971696 | 12075402703222894 | 12075402703250611 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7f48b80c6700 | 0x7f47ac4369c0 | 12075402703270598 | 12075402703283053 | 12075402703408172 | 12075402703411560 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7f48b80c6600 | 0x7f47ac436a00 | 12075402703435565 | 12075402703447692 | 12075402703656810 | 12075402703676974 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7f48b80c6500 | 0x7f47ac436a40 | 12075402703704815 | 12075402703718089 | 12075402703845288 | 12075402703848653 |
| 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 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7f48b80c6400 | 0x7f47ac436a80 | 12075402703872427 | 12075402703885608 | 12075402704191845 | 12075402704216967 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7f48b80c6300 | 0x7f47ac436ac0 | 12075402704235742 | 12075402704248325 | 12075402704495523 | 12075402704519610 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7f48b80c6a00 | 0x7f47ac436b00 | 12075402704538655 | 12075402704551042 | 12075402704679681 | 12075402704683103 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7f48b80c6900 | 0x7f47ac436b40 | 12075402704708210 | 12075402704720801 | 12075402704947679 | 12075402704971339 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7f48b80c6800 | 0x7f47ac436b80 | 12075402705005182 | 12075402705017598 | 12075402705144317 | 12075402705147847 |
| 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 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7f48b80c6700 | 0x7f47ac436bc0 | 12075402705171191 | 12075402705182397 | 12075402705510234 | 12075402705534395 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7f48b80c6600 | 0x7f47ac436c00 | 12075402705553190 | 12075402705565593 | 12075402705813591 | 12075402705837579 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7f48b80c6500 | 0x7f47ac436c40 | 12075402705857426 | 12075402705870391 | 12075402705999829 | 12075402706005611 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7f48b80c6400 | 0x7f47ac436c80 | 12075402706030988 | 12075402706043029 | 12075402706287187 | 12075402706307302 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7f48b80c6300 | 0x7f47ac436cc0 | 12075402706336306 | 12075402706349906 | 12075402706478225 | 12075402706481566 |
| 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 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7f48b80c6a00 | 0x7f47ac436d00 | 12075402706506262 | 12075402706518865 | 12075402706894542 | 12075402706918007 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7f48b80c6900 | 0x7f47ac436d40 | 12075402706938204 | 12075402706950861 | 12075402707208779 | 12075402707237280 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7f48b80c6800 | 0x7f47ac436d80 | 12075402707260423 | 12075402707273578 | 12075402707403497 | 12075402707406915 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7f48b80c6700 | 0x7f47ac436dc0 | 12075402707431732 | 12075402707443337 | 12075402707722214 | 12075402707742399 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7f48b80c6600 | 0x7f47ac436e00 | 12075402707776362 | 12075402707788454 | 12075402707924773 | 12075402707928094 |
| 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 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7f48b80c6500 | 0x7f47ac436e40 | 12075402707952179 | 12075402707963492 | 12075402708386529 | 12075402708411012 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7f48b80c6400 | 0x7f47ac436e80 | 12075402708430748 | 12075402708441728 | 12075402708697086 | 12075402708724524 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7f48b80c6300 | 0x7f47ac436ec0 | 12075402708744551 | 12075402708757085 | 12075402708893564 | 12075402708896975 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7f48b80c6a00 | 0x7f47ac436f00 | 12075402708922111 | 12075402708934204 | 12075402709279161 | 12075402709310153 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7f48b80c6900 | 0x7f47ac436f40 | 12075402709341791 | 12075402709356280 | 12075402709507959 | 12075402709511968 |
| 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 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7f48b80c6800 | 0x7f47ac436f80 | 12075402709536433 | 12075402709548918 | 12075402710066034 | 12075402710094781 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7f48b80c6700 | 0x7f47ac436fc0 | 12075402710115159 | 12075402710128593 | 12075402710426991 | 12075402710453858 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7f48b80c6600 | 0x7f47ac437000 | 12075402710474206 | 12075402710486670 | 12075402710639949 | 12075402710643591 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7f48b80c6500 | 0x7f47ac437040 | 12075402710668026 | 12075402710680269 | 12075402711066025 | 12075402711094639 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7f48b80c6400 | 0x7f47ac437080 | 12075402711125176 | 12075402711138825 | 12075402711314023 | 12075402711317724 |
| 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 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7f48b80c6300 | 0x7f47ac4370c0 | 12075402711341588 | 12075402711354503 | 12075402711965857 | 12075402711990854 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7f48b80c6a00 | 0x7f47ac437100 | 12075402712014769 | 12075402712027617 | 12075402712356254 | 12075402712386610 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7f48b80c6900 | 0x7f47ac437140 | 12075402712414041 | 12075402712426813 | 12075402712605052 | 12075402712608613 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7f48b80c6800 | 0x7f47ac437180 | 12075402712627898 | 12075402712639611 | 12075402713094968 | 12075402713119943 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7f48b80c6700 | 0x7f47ac4371c0 | 12075402713154176 | 12075402713167287 | 12075402713366805 | 12075402713390125 |
| 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 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7f48b80c6600 | 0x7f47ac437200 | 12075402713409781 | 12075402713422325 | 12075402714125519 | 12075402714155567 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7f48b80c6500 | 0x7f47ac437240 | 12075402714180163 | 12075402714192558 | 12075402714564715 | 12075402714592279 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7f48b80c6400 | 0x7f47ac437280 | 12075402714613629 | 12075402714626154 | 12075402714828712 | 12075402714855719 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7f48b80c6300 | 0x7f47ac4372c0 | 12075402714874654 | 12075402714886792 | 12075402715412867 | 12075402715447068 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7f48b80c6a00 | 0x7f47ac437300 | 12075402715480490 | 12075402715493187 | 12075402715717345 | 12075402715744220 |
| 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 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7f48b80c6900 | 0x7f47ac437340 | 12075402715763676 | 12075402715777344 | 12075402716576537 | 12075402716606102 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7f48b80c6800 | 0x7f47ac437380 | 12075402716626349 | 12075402716639417 | 12075402717059893 | 12075402717088228 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7f48b80c6700 | 0x7f47ac4373c0 | 12075402717108986 | 12075402717120372 | 12075402717345010 | 12075402717372516 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7f48b80c6600 | 0x7f47ac437400 | 12075402717393876 | 12075402717406130 | 12075402718002285 | 12075402718030669 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7f48b80c6500 | 0x7f47ac437440 | 12075402718061617 | 12075402718074444 | 12075402718342762 | 12075402718370331 |
| 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 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7f48b80c6400 | 0x7f47ac437480 | 12075402718389646 | 12075402718401321 | 12075402719386913 | 12075402719416334 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7f48b80c6300 | 0x7f47ac4374c0 | 12075402719436612 | 12075402719448032 | 12075402719961788 | 12075402719989129 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7f48b80c6a00 | 0x7f47ac437500 | 12075402720020918 | 12075402720033627 | 12075402720306265 | 12075402720333860 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7f48b80c6900 | 0x7f47ac437540 | 12075402720356852 | 12075402720369464 | 12075402721107218 | 12075402721136381 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7f48b80c6800 | 0x7f47ac437580 | 12075402721171286 | 12075402721183857 | 12075402721500334 | 12075402721527338 |
| 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 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7f48b80c6700 | 0x7f47ac4375c0 | 12075402721546824 | 12075402721559854 | 12075402722733603 | 12075402722761822 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7f48b80c6600 | 0x7f47ac437600 | 12075402722781779 | 12075402722793923 | 12075402723404318 | 12075402723433600 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7f48b80c6500 | 0x7f47ac437640 | 12075402723455000 | 12075402723467837 | 12075402723787834 | 12075402723816091 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7f48b80c6400 | 0x7f47ac437680 | 12075402723836910 | 12075402723847994 | 12075402724725746 | 12075402724761107 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7f48b80c6300 | 0x7f47ac4376c0 | 12075402724792175 | 12075402724803505 | 12075402725213902 | 12075402725243153 |
| 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 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7f48b80c6a00 | 0x7f47ac437700 | 12075402725265134 | 12075402725278381 | 12075402726830688 | 12075402726901736 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7f48b80c6900 | 0x7f47ac437740 | 12075402726923606 | 12075402726935807 | 12075402727732760 | 12075402727804373 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7f48b80c6800 | 0x7f47ac437780 | 12075402727823168 | 12075402727835230 | 12075402728249307 | 12075402728328367 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7f48b80c6700 | 0x7f47ac4377c0 | 12075402728348995 | 12075402728361785 | 12075402729520657 | 12075402729592206 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7f48b80c6600 | 0x7f47ac437800 | 12075402729623724 | 12075402729636656 | 12075402730422410 | 12075402730493270 |
| 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 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7f48b80c6500 | 0x7f47ac437840 | 12075402730515572 | 12075402730528489 | 12075402733583347 | 12075402733655227 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7f48b80c6400 | 0x7f47ac437880 | 12075402733675444 | 12075402733687826 | 12075402735231494 | 12075402735303280 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7f48b80c6300 | 0x7f47ac4378c0 | 12075402735326062 | 12075402735339814 | 12075402736129888 | 12075402736201599 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7f48b80c6a00 | 0x7f47ac437900 | 12075402736222448 | 12075402736233727 | 12075402738516430 | 12075402738587553 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7f48b80c6900 | 0x7f47ac437940 | 12075402738619402 | 12075402738632589 | 12075402740168098 | 12075402740239864 |
| 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 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7f48b80c6800 | 0x7f47ac437980 | 12075402740260753 | 12075402740273057 | 12075402746332212 | 12075402746403439 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7f48b80c6700 | 0x7f47ac4379c0 | 12075402746423767 | 12075402746436211 | 12075402749480989 | 12075402749552782 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7f48b80c6600 | 0x7f47ac437a00 | 12075402749572168 | 12075402749584988 | 12075402751124976 | 12075402751196987 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 873448 | 873453 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7f48b80c6500 | 0x7f47ac437a40 | 12075402751215772 | 12075402751228656 | 12075402755756302 | 12075402755830348 |