44 KiB
44 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | GRBM_COUNT | GRBM_GUI_ACTIVE | SQ_WAVES | SQ_IFETCH | SQ_IFETCH_LEVEL | SQ_ACCUM_PREV_HIRES | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBufferAligned.kd | 0 | 0 | 0 | 21628 | 21628 | 33554432 | 256 | 0 | 0 | 4 | 32 | 4160 | 0x0 | 0x7fb388204280 | 386456 | 386456 | 524288 | 4718592 | 682294 | 76313024 | 14214950724382 | 14214326191617 | 14215097854019 | 14215097943239 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 21628 | 21628 | 32768 | 256 | 0 | 0 | 12 | 24 | 13888 | 0x0 | 0x7fb388223f80 | 34296 | 34296 | 512 | 8192 | 7593 | 846628 | 14215103103013 | 14215097854019 | 14215103238826 | 14215103243910 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 5 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 14336 | 0x7fb3a6bcd380 | 0x7fb388223fc0 | 165334 | 165334 | 65536 | 917504 | 140628 | 15755044 | 14215103282580 | 14215103238826 | 14215103620427 | 14215103623193 |
| 5 | 3 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 8 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15040 | 0x7fb3a6bcd200 | 0x7fb388224000 | 309586 | 309586 | 65536 | 1114112 | 167319 | 18771692 | 14215103663022 | 14215103620427 | 14215104033707 | 14215104036434 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 11 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15488 | 0x7fb3a6bcd080 | 0x7fb388224040 | 310584 | 310584 | 65536 | 917504 | 140083 | 15672232 | 14215104070553 | 14215104033707 | 14215104437548 | 14215104440156 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 14 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 15936 | 0x7fb3a452df00 | 0x7fb388224080 | 165951 | 165951 | 65536 | 1048576 | 158775 | 17777204 | 14215104475935 | 14215104437548 | 14215104751628 | 14215104754079 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 17 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 16384 | 0x7fb3a452dd80 | 0x7fb3882240c0 | 165430 | 165430 | 65536 | 983040 | 148612 | 16691092 | 14215104789569 | 14215104751628 | 14215105068269 | 14215105070953 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 20 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 17088 | 0x7fb3a452dc00 | 0x7fb388224100 | 162894 | 162894 | 65536 | 1114112 | 163039 | 18248364 | 14215105117962 | 14215105068269 | 14215105379469 | 14215105381957 |
| 10 | 8 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 23 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 16 | 24 | 17792 | 0x7fb3a452da80 | 0x7fb388224140 | 309744 | 309744 | 65536 | 1310720 | 195850 | 21885884 | 14215105417296 | 14215105379469 | 14215105778670 | 14215105781348 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 26 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 16 | 24 | 18496 | 0x7fb3a452d900 | 0x7fb388224180 | 310937 | 310937 | 65536 | 1179648 | 178192 | 19956608 | 14215105814628 | 14215105778670 | 14215106192591 | 14215106195330 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 29 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19200 | 0x7fb3a452d780 | 0x7fb3882241c0 | 164650 | 164650 | 65536 | 1245184 | 190540 | 21453144 | 14215106230779 | 14215106192591 | 14215106514511 | 14215106516923 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 32 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19904 | 0x7fb3a452d600 | 0x7fb388224200 | 164581 | 164581 | 65536 | 1245184 | 186808 | 20924128 | 14215106552473 | 14215106514511 | 14215106827151 | 14215106829637 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 35 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 20608 | 0x7fb3a6bcd480 | 0x7fb388224240 | 163641 | 163641 | 65536 | 1245184 | 188820 | 21150744 | 14215106873446 | 14215106827151 | 14215107140592 | 14215107143200 |
| 15 | 13 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 38 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 16 | 24 | 21312 | 0x7fb3a6bcd300 | 0x7fb388224280 | 310703 | 310703 | 65536 | 1441792 | 216721 | 24236460 | 14215107179880 | 14215107140592 | 14215107538512 | 14215107540532 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 41 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22016 | 0x7fb3a6bcd180 | 0x7fb3882242c0 | 308655 | 308655 | 65536 | 1310720 | 198962 | 22223428 | 14215107575482 | 14215107538512 | 14215107910833 | 14215107912825 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 44 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22720 | 0x7fb3a6bcd000 | 0x7fb388224300 | 165143 | 165143 | 65536 | 1376256 | 206542 | 23134528 | 14215107947604 | 14215107910833 | 14215108193553 | 14215108195319 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 47 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 23424 | 0x7fb3a452de80 | 0x7fb388224340 | 164145 | 164145 | 65536 | 1441792 | 217542 | 24343488 | 14215108230368 | 14215108193553 | 14215108481394 | 14215108483323 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 50 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 24128 | 0x7fb3a452dd00 | 0x7fb388224380 | 163835 | 163835 | 65536 | 1310720 | 195950 | 21895500 | 14215108525012 | 14215108481394 | 14215108788114 | 14215108790087 |
| 20 | 18 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 53 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 16 | 24 | 24832 | 0x7fb3a452db80 | 0x7fb3882243c0 | 310507 | 310507 | 65536 | 1572864 | 234367 | 26279312 | 14215108826616 | 14215108788114 | 14215109164915 | 14215109166829 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 56 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 16 | 24 | 25536 | 0x7fb3a452da00 | 0x7fb388224400 | 306015 | 306015 | 65536 | 1441792 | 208796 | 23355844 | 14215109201528 | 14215109164915 | 14215109540755 | 14215109542501 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 59 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26240 | 0x7fb3a452d880 | 0x7fb388224440 | 163647 | 163647 | 65536 | 1507328 | 226059 | 25280752 | 14215109577081 | 14215109540755 | 14215109827636 | 14215109829525 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 62 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26944 | 0x7fb3a452d700 | 0x7fb388224480 | 163581 | 163581 | 65536 | 1638400 | 243183 | 27237796 | 14215109864755 | 14215109827636 | 14215110112596 | 14215110114499 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 65 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 27648 | 0x7fb3a6bcd580 | 0x7fb3882244c0 | 162443 | 162443 | 65536 | 1441792 | 215406 | 24188908 | 14215110157179 | 14215110112596 | 14215110410197 | 14215110412043 |
| 25 | 23 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 68 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 16 | 24 | 28608 | 0x7fb3a6bcd400 | 0x7fb388224500 | 307405 | 307405 | 65536 | 1703936 | 251430 | 28220112 | 14215110448413 | 14215110410197 | 14215110779957 | 14215110781856 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 71 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 16 | 24 | 29312 | 0x7fb3a6bcd280 | 0x7fb388224540 | 304969 | 304969 | 65536 | 1572864 | 234692 | 26194172 | 14215110817355 | 14215110779957 | 14215111151958 | 14215111153818 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 74 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 30016 | 0x7fb3a6bcd100 | 0x7fb388224580 | 162433 | 162433 | 65536 | 1638400 | 246718 | 27640452 | 14215111189277 | 14215111151958 | 14215111439958 | 14215111441912 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 77 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 8 | 24 | 30976 | 0x7fb3a452df80 | 0x7fb3882245c0 | 162308 | 162308 | 65536 | 1835008 | 282353 | 31569516 | 14215111478022 | 14215111439958 | 14215111726199 | 14215111728166 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 80 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 31680 | 0x7fb3a452de00 | 0x7fb388224600 | 163377 | 163377 | 65536 | 1507328 | 225655 | 25218620 | 14215111770086 | 14215111726199 | 14215112017879 | 14215112019760 |
| 30 | 28 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 83 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 16 | 24 | 32640 | 0x7fb3a452dc80 | 0x7fb388224640 | 305569 | 305569 | 65536 | 1835008 | 272522 | 30459116 | 14215112055600 | 14215112017879 | 14215112387960 | 14215112389893 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 86 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 33600 | 0x7fb3a452db00 | 0x7fb388224680 | 306311 | 306311 | 65536 | 1703936 | 250258 | 28020952 | 14215112424712 | 14215112387960 | 14215112758040 | 14215112760005 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 89 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 34560 | 0x7fb3a452d980 | 0x7fb3882246c0 | 163400 | 163400 | 65536 | 1769472 | 274783 | 30809876 | 14215112794545 | 14215112758040 | 14215113044280 | 14215113046069 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 92 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 8 | 24 | 35520 | 0x7fb3a452d800 | 0x7fb388224700 | 163389 | 163389 | 65536 | 2031616 | 303729 | 33879984 | 14215113081849 | 14215113044280 | 14215113328921 | 14215113330744 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 95 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 36224 | 0x7fb3a452d680 | 0x7fb388224740 | 163522 | 163522 | 65536 | 1638400 | 244707 | 27396992 | 14215113373063 | 14215113328921 | 14215113618841 | 14215113620628 |
| 35 | 33 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 98 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 37184 | 0x7fb3a6bcd500 | 0x7fb388224780 | 305255 | 305255 | 65536 | 1966080 | 286949 | 32265720 | 14215113655307 | 14215113618841 | 14215113995162 | 14215113997100 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 101 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 38144 | 0x7fb3a6bcd380 | 0x7fb3882247c0 | 306624 | 306624 | 65536 | 1835008 | 274135 | 30574248 | 14215114032939 | 14215113995162 | 14215114381402 | 14215114383362 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 104 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 39104 | 0x7fb3a6bcd200 | 0x7fb388224800 | 163143 | 163143 | 65536 | 1900544 | 282499 | 31577064 | 14215114418521 | 14215114381402 | 14215114666843 | 14215114668626 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 107 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 8 | 24 | 40320 | 0x7fb3a6bcd080 | 0x7fb388224840 | 163358 | 163358 | 65536 | 2228224 | 327906 | 36723572 | 14215114704535 | 14215114666843 | 14215114957243 | 14215114959200 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 110 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 41280 | 0x7fb3a452df00 | 0x7fb388224880 | 162917 | 162917 | 65536 | 1703936 | 256223 | 28662332 | 14215115001389 | 14215114957243 | 14215115249564 | 14215115251434 |
| 40 | 38 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 113 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 42240 | 0x7fb3a452dd80 | 0x7fb3882248c0 | 306644 | 306644 | 65536 | 2097152 | 327472 | 36732992 | 14215115288164 | 14215115249564 | 14215115625724 | 14215115627577 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 116 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 43200 | 0x7fb3a452dc00 | 0x7fb388224900 | 306516 | 306516 | 65536 | 1966080 | 283439 | 31732212 | 14215115662106 | 14215115625724 | 14215116001725 | 14215116003459 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 119 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 8 | 24 | 44160 | 0x7fb3a452da80 | 0x7fb388224940 | 162700 | 162700 | 65536 | 2031616 | 303642 | 34002532 | 14215116038528 | 14215116001725 | 14215116286205 | 14215116287983 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 122 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 45376 | 0x7fb3a452d900 | 0x7fb388224980 | 163574 | 163574 | 65536 | 2424832 | 362502 | 40574392 | 14215116323073 | 14215116286205 | 14215116577086 | 14215116578897 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 125 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 46336 | 0x7fb3a452d780 | 0x7fb3882249c0 | 163046 | 163046 | 65536 | 1835008 | 271916 | 30586284 | 14215116620167 | 14215116577086 | 14215116865726 | 14215116867531 |
| 45 | 43 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 128 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 47552 | 0x7fb3a452d600 | 0x7fb388224a00 | 306234 | 306234 | 65536 | 2228224 | 328184 | 36686716 | 14215116905141 | 14215116865726 | 14215117238527 | 14215117240354 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 131 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 48512 | 0x7fb3a6bcd480 | 0x7fb388224a40 | 301873 | 301873 | 65536 | 2097152 | 308935 | 34567828 | 14215117275593 | 14215117238527 | 14215117610687 | 14215117612616 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 134 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 8 | 24 | 49472 | 0x7fb3a6bcd300 | 0x7fb388224a80 | 160784 | 160784 | 65536 | 2162688 | 318244 | 35656940 | 14215117647436 | 14215117610687 | 14215117896128 | 14215117897991 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 137 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 50688 | 0x7fb3a6bcd180 | 0x7fb388224ac0 | 161814 | 161814 | 65536 | 2621440 | 388431 | 43514360 | 14215117933320 | 14215117896128 | 14215118186848 | 14215118188705 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 140 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 51648 | 0x7fb3a6bcd000 | 0x7fb388224b00 | 160816 | 160816 | 65536 | 1966080 | 298814 | 33466540 | 14215118231144 | 14215118186848 | 14215118480928 | 14215118482809 |
| 50 | 48 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 143 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 52864 | 0x7fb3a452de80 | 0x7fb388224b40 | 304857 | 304857 | 65536 | 2359296 | 397974 | 44551316 | 14215118519698 | 14215118480928 | 14215118852769 | 14215118854911 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 146 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 54080 | 0x7fb3a452dd00 | 0x7fb388224b80 | 301890 | 301890 | 65536 | 2228224 | 329721 | 36894144 | 14215118888530 | 14215118852769 | 14215119230849 | 14215119232683 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 149 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 8 | 24 | 55296 | 0x7fb3a452db80 | 0x7fb388224bc0 | 163297 | 163297 | 65536 | 2293760 | 346273 | 38802992 | 14215119268262 | 14215119230849 | 14215119522690 | 14215119524517 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 152 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 56768 | 0x7fb3a452da00 | 0x7fb388224c00 | 163548 | 163548 | 65536 | 2752512 | 413971 | 46280568 | 14215119560026 | 14215119522690 | 14215119809730 | 14215119811611 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 155 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 57728 | 0x7fb3a452d880 | 0x7fb388224c40 | 161778 | 161778 | 65536 | 2031616 | 305504 | 34200544 | 14215119853330 | 14215119809730 | 14215120099971 | 14215120101785 |
| 55 | 53 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 158 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 58944 | 0x7fb3a452d700 | 0x7fb388224c80 | 302160 | 302160 | 65536 | 2490368 | 364870 | 40851976 | 14215120137775 | 14215120099971 | 14215120470371 | 14215120472248 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 161 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 60160 | 0x7fb3a6bcd580 | 0x7fb388224cc0 | 301987 | 301987 | 65536 | 2359296 | 352155 | 39506240 | 14215120507627 | 14215120470371 | 14215120840932 | 14215120842880 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 164 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 8 | 24 | 61376 | 0x7fb3a6bcd400 | 0x7fb388224d00 | 163736 | 163736 | 65536 | 2424832 | 357944 | 40111004 | 14215120878159 | 14215120840932 | 14215121128772 | 14215121130544 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 167 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 62848 | 0x7fb3a6bcd280 | 0x7fb388224d40 | 168683 | 168683 | 65536 | 2949120 | 439104 | 49213644 | 14215121165764 | 14215121128772 | 14215121421733 | 14215121423708 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 170 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 63808 | 0x7fb3a6bcd100 | 0x7fb388224d80 | 162904 | 162904 | 65536 | 2162688 | 338978 | 37938564 | 14215121466047 | 14215121421733 | 14215121713413 | 14215121715372 |
| 60 | 58 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 173 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 65024 | 0x7fb3a452df80 | 0x7fb388224dc0 | 300000 | 300000 | 65536 | 2621440 | 395026 | 44229860 | 14215121749972 | 14215121713413 | 14215122089254 | 14215122091205 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 176 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 66240 | 0x7fb3a452de00 | 0x7fb388224e00 | 303069 | 303069 | 65536 | 2490368 | 359608 | 40302212 | 14215122127204 | 14215122089254 | 14215122472294 | 14215122474247 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 179 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 8 | 24 | 67456 | 0x7fb3a452dc80 | 0x7fb388224e40 | 163658 | 163658 | 65536 | 2555904 | 377766 | 42376116 | 14215122509226 | 14215122472294 | 14215122767015 | 14215122768961 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 182 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 68928 | 0x7fb3a452db00 | 0x7fb388224e80 | 177806 | 177806 | 65536 | 3145728 | 463642 | 51966032 | 14215122803620 | 14215122767015 | 14215123064615 | 14215123066585 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 185 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 70144 | 0x7fb3a452d980 | 0x7fb388224ec0 | 160836 | 160836 | 65536 | 2228224 | 328922 | 36878152 | 14215123108054 | 14215123064615 | 14215123357255 | 14215123359089 |
| 65 | 63 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 188 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 71616 | 0x7fb3a452d800 | 0x7fb388224f00 | 301674 | 301674 | 65536 | 2752512 | 408095 | 45747336 | 14215123395288 | 14215123357255 | 14215123728936 | 14215123730741 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 191 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 72832 | 0x7fb3a452d680 | 0x7fb388224f40 | 302940 | 302940 | 65536 | 2621440 | 389433 | 43715848 | 14215123765730 | 14215123728936 | 14215124103337 | 14215124105193 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 194 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 8 | 24 | 74048 | 0x7fb3a6bcd500 | 0x7fb388224f80 | 162958 | 162958 | 65536 | 2686976 | 403393 | 45267036 | 14215124139403 | 14215124103337 | 14215124389097 | 14215124390927 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 197 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 75776 | 0x7fb3a6bcd380 | 0x7fb388224fc0 | 182448 | 182448 | 65536 | 3342336 | 497131 | 55648364 | 14215124425917 | 14215124389097 | 14215124695177 | 14215124697131 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 200 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 76992 | 0x7fb3a6bcd200 | 0x7fb388225000 | 162628 | 162628 | 65536 | 2359296 | 350854 | 39341196 | 14215124750430 | 14215124695177 | 14215124981738 | 14215124983485 |
| 70 | 68 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 203 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 78464 | 0x7fb3a6bcd080 | 0x7fb388225040 | 302088 | 302088 | 65536 | 2883584 | 432874 | 48431532 | 14215125021155 | 14215124981738 | 14215125357098 | 14215125358968 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 206 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 79936 | 0x7fb3a452df00 | 0x7fb388225080 | 299794 | 299794 | 65536 | 2686976 | 399680 | 44851596 | 14215125394497 | 14215125357098 | 14215125727339 | 14215125729260 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 209 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 8 | 24 | 81408 | 0x7fb3a452dd80 | 0x7fb3882250c0 | 162632 | 162632 | 65536 | 2818048 | 421752 | 47176424 | 14215125762619 | 14215125727339 | 14215126014699 | 14215126016594 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 212 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 83136 | 0x7fb3a452dc00 | 0x7fb388225100 | 190882 | 190882 | 65536 | 3538944 | 526100 | 58891396 | 14215126052603 | 14215126014699 | 14215126330540 | 14215126332798 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 215 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 84352 | 0x7fb3a452da80 | 0x7fb388225140 | 162054 | 162054 | 65536 | 2424832 | 360973 | 40389556 | 14215126374677 | 14215126330540 | 14215126618540 | 14215126620542 |
| 75 | 73 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 218 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 85824 | 0x7fb3a452d900 | 0x7fb388225180 | 305428 | 305428 | 65536 | 3014656 | 454544 | 50811252 | 14215126657961 | 14215126618540 | 14215126991501 | 14215126993284 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 221 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 87296 | 0x7fb3a452d780 | 0x7fb3882251c0 | 297795 | 297795 | 65536 | 2818048 | 417042 | 46806344 | 14215127028603 | 14215126991501 | 14215127369741 | 14215127371616 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 224 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 88768 | 0x7fb3a452d600 | 0x7fb388225200 | 163892 | 163892 | 65536 | 2949120 | 438222 | 49071800 | 14215127406176 | 14215127369741 | 14215127654862 | 14215127656860 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 227 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 90752 | 0x7fb3a6bcd480 | 0x7fb388225240 | 201630 | 201630 | 65536 | 3735552 | 556986 | 62343496 | 14215127692120 | 14215127654862 | 14215127965582 | 14215127967444 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 230 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 91968 | 0x7fb3a6bcd300 | 0x7fb388225280 | 162086 | 162086 | 65536 | 2555904 | 385290 | 43117436 | 14215128009803 | 14215127965582 | 14215128255183 | 14215128256978 |
| 80 | 78 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 233 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 93440 | 0x7fb3a6bcd180 | 0x7fb3882252c0 | 300864 | 300864 | 65536 | 3145728 | 467107 | 52354248 | 14215128292687 | 14215128255183 | 14215128626223 | 14215128628031 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 236 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 94912 | 0x7fb3a6bcd000 | 0x7fb388225300 | 300508 | 300508 | 65536 | 2949120 | 432329 | 48427872 | 14215128663670 | 14215128626223 | 14215128997584 | 14215128999453 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 239 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 96384 | 0x7fb3a452de80 | 0x7fb388225340 | 162730 | 162730 | 65536 | 3080192 | 458830 | 51438760 | 14215129033852 | 14215128997584 | 14215129286384 | 14215129288447 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 242 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 98368 | 0x7fb3a452dd00 | 0x7fb388225380 | 211852 | 211852 | 65536 | 3932160 | 605678 | 67786040 | 14215129323576 | 14215129286384 | 14215129603825 | 14215129605701 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 245 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 99584 | 0x7fb3a452db80 | 0x7fb3882253c0 | 162008 | 162008 | 65536 | 2621440 | 391398 | 43799324 | 14215129647500 | 14215129603825 | 14215129894385 | 14215129896225 |
| 85 | 83 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 248 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 101312 | 0x7fb3a452da00 | 0x7fb388225400 | 299326 | 299326 | 65536 | 3276800 | 493932 | 55298720 | 14215129932304 | 14215129894385 | 14215130275346 | 14215130277227 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 251 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 102784 | 0x7fb3a452d880 | 0x7fb388225440 | 301366 | 301366 | 65536 | 3080192 | 450812 | 50537068 | 14215130313926 | 14215130275346 | 14215130656146 | 14215130658049 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 254 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 104256 | 0x7fb3a452d700 | 0x7fb388225480 | 161618 | 161618 | 65536 | 3211264 | 486878 | 54566692 | 14215130692898 | 14215130656146 | 14215130941107 | 14215130943093 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 257 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 106240 | 0x7fb3a6bcd580 | 0x7fb3882254c0 | 219012 | 219012 | 65536 | 4128768 | 614508 | 68857668 | 14215130977942 | 14215130941107 | 14215131263667 | 14215131265556 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 260 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 107712 | 0x7fb3a6bcd400 | 0x7fb388225500 | 160304 | 160304 | 65536 | 2752512 | 411765 | 45977904 | 14215131307416 | 14215131263667 | 14215131552467 | 14215131554381 |
| 90 | 88 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 263 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 16 | 24 | 109440 | 0x7fb3a6bcd280 | 0x7fb388225540 | 298960 | 298960 | 65536 | 3407872 | 506186 | 56754948 | 14215131591120 | 14215131552467 | 14215131922708 | 14215131924683 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 266 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 16 | 24 | 111168 | 0x7fb3a6bcd100 | 0x7fb388225580 | 299010 | 299010 | 65536 | 3211264 | 470593 | 52734244 | 14215131960202 | 14215131922708 | 14215132291828 | 14215132293555 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 269 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 8 | 24 | 112896 | 0x7fb3a452df80 | 0x7fb3882255c0 | 161580 | 161580 | 65536 | 3276800 | 491536 | 55025260 | 14215132328285 | 14215132291828 | 14215132584149 | 14215132585989 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 272 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 115136 | 0x7fb3a452de00 | 0x7fb388225600 | 229950 | 229950 | 65536 | 4325376 | 655080 | 73329732 | 14215132621909 | 14215132584149 | 14215132911349 | 14215132913213 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 275 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 116608 | 0x7fb3a452dc80 | 0x7fb388225640 | 160790 | 160790 | 65536 | 2818048 | 423304 | 47464524 | 14215132954352 | 14215132911349 | 14215133198230 | 14215133200007 |
| 95 | 93 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 278 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 16 | 24 | 118336 | 0x7fb3a452db00 | 0x7fb388225680 | 296860 | 296860 | 65536 | 3538944 | 538372 | 60427344 | 14215133235246 | 14215133198230 | 14215133570230 | 14215133572179 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 281 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 16 | 24 | 120064 | 0x7fb3a452d980 | 0x7fb3882256c0 | 296966 | 296966 | 65536 | 3407872 | 504437 | 56500820 | 14215133607278 | 14215133570230 | 14215133942711 | 14215133944512 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 284 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 121792 | 0x7fb3a452d800 | 0x7fb388225700 | 162902 | 162902 | 65536 | 3407872 | 519339 | 58073680 | 14215133979641 | 14215133942711 | 14215134242871 | 14215134244875 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 287 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 124032 | 0x7fb3a452d680 | 0x7fb388225740 | 239450 | 239450 | 65536 | 4521984 | 679350 | 76069416 | 14215134280095 | 14215134242871 | 14215134582872 | 14215134584758 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 290 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 125504 | 0x7fb3a6bcd500 | 0x7fb388225780 | 161922 | 161922 | 65536 | 3014656 | 454097 | 50793040 | 14215134625778 | 14215134582872 | 14215134877272 | 14215134879183 |
| 100 | 98 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 293 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 127488 | 0x7fb3a6bcd380 | 0x7fb3882257c0 | 299182 | 299182 | 65536 | 3801088 | 561950 | 62937220 | 14215134913712 | 14215134877272 | 14215135252953 | 14215135254835 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 296 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 129216 | 0x7fb3a6bcd200 | 0x7fb388225800 | 298304 | 298304 | 65536 | 3670016 | 560440 | 62730508 | 14215135291804 | 14215135252953 | 14215135625593 | 14215135627587 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 299 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 130944 | 0x7fb3a6bcd080 | 0x7fb388225840 | 170118 | 170118 | 65536 | 3670016 | 559410 | 62634924 | 14215135663197 | 14215135625593 | 14215135917594 | 14215135919541 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 302 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 133440 | 0x7fb3a452df00 | 0x7fb388225880 | 259134 | 259134 | 65536 | 4915200 | 747616 | 83753076 | 14215135954791 | 14215135917594 | 14215136267354 | 14215136269274 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 305 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 134912 | 0x7fb3a452dd80 | 0x7fb3882258c0 | 162264 | 162264 | 65536 | 3145728 | 471429 | 52818356 | 14215136311693 | 14215136267354 | 14215136562075 | 14215136563888 |
| 105 | 103 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 308 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 136896 | 0x7fb3a452dc00 | 0x7fb388225900 | 297244 | 297244 | 65536 | 4063232 | 605851 | 67841384 | 14215136599118 | 14215136562075 | 14215136939515 | 14215136941421 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 311 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 138880 | 0x7fb3a452da80 | 0x7fb388225940 | 298702 | 298702 | 65536 | 3932160 | 609066 | 68148880 | 14215136976350 | 14215136939515 | 14215137315036 | 14215137316973 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 314 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 140864 | 0x7fb3a452d900 | 0x7fb388225980 | 177336 | 177336 | 65536 | 3932160 | 599656 | 67042956 | 14215137351382 | 14215137315036 | 14215137613756 | 14215137615527 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 317 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 143616 | 0x7fb3a452d780 | 0x7fb3882259c0 | 281116 | 281116 | 65536 | 5308416 | 810531 | 90679524 | 14215137649816 | 14215137613756 | 14215137984157 | 14215137986119 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 320 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 145344 | 0x7fb3a452d600 | 0x7fb388225a00 | 161403 | 161403 | 65536 | 3342336 | 498530 | 55844396 | 14215138028268 | 14215137984157 | 14215138282077 | 14215138284343 |
| 110 | 108 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 323 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 147584 | 0x7fb3a6bcd480 | 0x7fb388225a40 | 295656 | 295656 | 65536 | 4325376 | 651915 | 73035088 | 14215138319702 | 14215138282077 | 14215138658398 | 14215138660186 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 326 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 149568 | 0x7fb3a6bcd300 | 0x7fb388225a80 | 296397 | 296397 | 65536 | 4194304 | 636895 | 71240248 | 14215138695165 | 14215138658398 | 14215139033278 | 14215139035028 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 329 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 151552 | 0x7fb3a6bcd180 | 0x7fb388225ac0 | 187462 | 187462 | 65536 | 4194304 | 636881 | 71369464 | 14215139069927 | 14215139033278 | 14215139339519 | 14215139341442 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 332 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 154304 | 0x7fb3a6bcd000 | 0x7fb388225b00 | 299284 | 299284 | 65536 | 5701632 | 856220 | 95917712 | 14215139376551 | 14215139339519 | 14215139713919 | 14215139715824 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 335 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 156288 | 0x7fb3a452de80 | 0x7fb388225b40 | 172588 | 172588 | 65536 | 3735552 | 566691 | 63457888 | 14215139758453 | 14215139713919 | 14215140015680 | 14215140017668 |
| 115 | 113 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 338 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 158784 | 0x7fb3a452dd00 | 0x7fb388225b80 | 296446 | 296446 | 65536 | 4849664 | 757175 | 84801412 | 14215140052577 | 14215140015680 | 14215140389920 | 14215140391820 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 341 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 161024 | 0x7fb3a452db80 | 0x7fb388225bc0 | 297536 | 297536 | 65536 | 4718592 | 747713 | 83807720 | 14215140426329 | 14215140389920 | 14215140770721 | 14215140772452 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 344 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 163264 | 0x7fb3a452da00 | 0x7fb388225c00 | 206546 | 206546 | 65536 | 4718592 | 709033 | 79430072 | 14215140806761 | 14215140770721 | 14215141087521 | 14215141089416 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 347 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 166528 | 0x7fb3a452d880 | 0x7fb388225c40 | 339786 | 339786 | 65536 | 6488064 | 972297 | 108918708 | 14215141124165 | 14215141087521 | 14215141488642 | 14215141505797 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 350 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 168512 | 0x7fb3a452d700 | 0x7fb388225c80 | 184432 | 184432 | 65536 | 4128768 | 617564 | 69122032 | 14215141532687 | 14215141488642 | 14215141802242 | 14215141804111 |
| 120 | 118 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 353 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 171264 | 0x7fb3a6bcd580 | 0x7fb388225cc0 | 298514 | 298514 | 65536 | 5373952 | 862301 | 96612968 | 14215141839700 | 14215141802242 | 14215142179843 | 14215142181933 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 356 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 173760 | 0x7fb3a6bcd400 | 0x7fb388225d00 | 296073 | 296073 | 65536 | 5242880 | 820745 | 91964688 | 14215142218543 | 14215142179843 | 14215142558563 | 14215142560466 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 359 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 176256 | 0x7fb3a6bcd280 | 0x7fb388225d40 | 225515 | 225515 | 65536 | 5242880 | 807868 | 90530300 | 14215142595425 | 14215142558563 | 14215142887204 | 14215142889109 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 362 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 179776 | 0x7fb3a6bcd100 | 0x7fb388225d80 | 380593 | 380593 | 65536 | 7274496 | 1104259 | 123783320 | 14215142924388 | 14215142887204 | 14215143311045 | 14215143356849 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 365 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 182272 | 0x7fb3a452df80 | 0x7fb388225dc0 | 211649 | 211649 | 65536 | 4915200 | 738963 | 82719360 | 14215143376409 | 14215143311045 | 14215143665925 | 14215143667653 |
| 125 | 123 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 368 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 185536 | 0x7fb3a452de00 | 0x7fb388225e00 | 304677 | 304677 | 65536 | 6422528 | 1001647 | 112287588 | 14215143704592 | 14215143665925 | 14215144045766 | 14215144047805 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 371 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 188544 | 0x7fb3a452dc80 | 0x7fb388225e40 | 310593 | 310593 | 65536 | 6291456 | 1006156 | 112700532 | 14215144082834 | 14215144045766 | 14215144430726 | 14215144476696 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 374 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 191552 | 0x7fb3a452db00 | 0x7fb388225e80 | 266577 | 266577 | 65536 | 6291456 | 956411 | 107102676 | 14215144487836 | 14215144430726 | 14215144813767 | 14215144815609 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 377 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 195840 | 0x7fb3a452d980 | 0x7fb388225ec0 | 461689 | 461689 | 65536 | 8847360 | 1343077 | 150376864 | 14215144850309 | 14215144813767 | 14215145289127 | 14215145307999 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 380 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 198592 | 0x7fb3a452d800 | 0x7fb388225f00 | 244981 | 244981 | 65536 | 5701632 | 852861 | 95559436 | 14215145333499 | 14215145289127 | 14215145638728 | 14215145640652 |
| 130 | 128 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 383 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 202368 | 0x7fb3a452d680 | 0x7fb388225f40 | 334275 | 334275 | 65536 | 7471104 | 1214345 | 136078436 | 14215145675352 | 14215145638728 | 14215146040968 | 14215146059884 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 386 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 205888 | 0x7fb3a6bcd500 | 0x7fb388225f80 | 329305 | 329305 | 65536 | 7340032 | 1175583 | 131588804 | 14215146084693 | 14215146040968 | 14215146450249 | 14215146499265 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 389 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 209408 | 0x7fb3a6bcd380 | 0x7fb388225fc0 | 306433 | 306433 | 65536 | 7340032 | 1132375 | 126772764 | 14215146509995 | 14215146450249 | 14215146869290 | 14215146871187 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 392 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 214464 | 0x7fb3a6bcd200 | 0x7fb388226000 | 543425 | 543425 | 65536 | 10420224 | 1590165 | 178041684 | 14215146907626 | 14215146869290 | 14215147397450 | 14215147440585 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 395 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 217728 | 0x7fb3a6bcd080 | 0x7fb388226040 | 274355 | 274355 | 65536 | 6488064 | 994111 | 111372600 | 14215147461085 | 14215147397450 | 14215147787371 | 14215147789208 |
| 135 | 133 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 398 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 222016 | 0x7fb3a452df00 | 0x7fb388226080 | 366371 | 366371 | 65536 | 8519680 | 1363542 | 152752820 | 14215147825168 | 14215147787371 | 14215148210252 | 14215148256099 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 401 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 226048 | 0x7fb3a452dd80 | 0x7fb3882260c0 | 366033 | 366033 | 65536 | 8388608 | 1321061 | 147955432 | 14215148267789 | 14215148210252 | 14215148666252 | 14215148708779 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 404 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 230080 | 0x7fb3a452dc00 | 0x7fb388226100 | 347381 | 347381 | 65536 | 8388608 | 1295203 | 144941040 | 14215148720619 | 14215148666252 | 14215149096173 | 14215149138471 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 407 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 235904 | 0x7fb3a452da80 | 0x7fb388226140 | 623762 | 623762 | 65536 | 11993088 | 1829210 | 204815088 | 14215149149630 | 14215149096173 | 14215149703694 | 14215149746338 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 410 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 239424 | 0x7fb3a452d900 | 0x7fb388226180 | 302405 | 302405 | 65536 | 7274496 | 1114985 | 124833312 | 14215149766748 | 14215149703694 | 14215150109614 | 14215150111731 |
| 140 | 138 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 413 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 244224 | 0x7fb3a452d780 | 0x7fb3882261c0 | 398592 | 398592 | 65536 | 9568256 | 1519894 | 170244104 | 14215150146620 | 14215150109614 | 14215150564335 | 14215150612850 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 416 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 248768 | 0x7fb3a452d600 | 0x7fb388226200 | 390469 | 390469 | 65536 | 9437184 | 1490798 | 167056184 | 14215150624130 | 14215150564335 | 14215151035856 | 14215151078681 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 419 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 253312 | 0x7fb3a6bcd480 | 0x7fb388226240 | 387352 | 387352 | 65536 | 9437184 | 1460005 | 163788312 | 14215151090031 | 14215151035856 | 14215151493296 | 14215151538821 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 422 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 8 | 24 | 255552 | 0x7fb3a6bcd300 | 0x7fb388226280 | 718913 | 718913 | 65536 | 16056320 | 2302660 | 258050536 | 14215151549371 | 14215151493296 | 14215152167697 | 14215152210958 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 425 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 259840 | 0x7fb3a6bcd180 | 0x7fb3882262c0 | 364836 | 364836 | 65536 | 8847360 | 1356535 | 151974892 | 14215152230777 | 14215152167697 | 14215152621298 | 14215152663438 |
| 145 | 143 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 428 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 265664 | 0x7fb3a6bcd000 | 0x7fb388226300 | 468751 | 468751 | 65536 | 11665408 | 1837201 | 205716480 | 14215152675508 | 14215152621298 | 14215153137619 | 14215153180048 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 431 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 271232 | 0x7fb3a452de80 | 0x7fb388226340 | 472638 | 472638 | 65536 | 11468800 | 1842232 | 206273736 | 14215153191608 | 14215153137619 | 14215153657780 | 14215153699737 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 434 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 8 | 24 | 273216 | 0x7fb3a452dd00 | 0x7fb388226380 | 483103 | 483103 | 65536 | 14090240 | 2019912 | 226230248 | 14215153710787 | 14215153657780 | 14215154176340 | 14215154223816 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 437 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 8 | 24 | 275712 | 0x7fb3a452db80 | 0x7fb3882263c0 | 880720 | 880720 | 65536 | 19202048 | 2758899 | 308901804 | 14215154235506 | 14215154176340 | 14215154967061 | 14215155011590 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 440 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 280768 | 0x7fb3a452da00 | 0x7fb388226400 | 426666 | 426666 | 65536 | 10420224 | 1599995 | 179226484 | 14215155032160 | 14215154967061 | 14215155452822 | 14215155495151 |
| 150 | 148 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 443 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 287616 | 0x7fb3a452d880 | 0x7fb388226440 | 549349 | 549349 | 65536 | 13762560 | 2124855 | 237972440 | 14215155506270 | 14215155452822 | 14215156020983 | 14215156063499 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 446 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 294208 | 0x7fb3a452d700 | 0x7fb388226480 | 550910 | 550910 | 65536 | 13565952 | 2145092 | 240255760 | 14215156075339 | 14215156020983 | 14215156588824 | 14215156631157 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 449 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 8 | 24 | 296960 | 0x7fb3a6bcd580 | 0x7fb3882264c0 | 562529 | 562529 | 65536 | 15466496 | 2229645 | 249696628 | 14215156642537 | 14215156588824 | 14215157160345 | 14215157203086 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 452 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 8 | 24 | 299968 | 0x7fb3a6bcd400 | 0x7fb388226500 | 1041823 | 1041823 | 65536 | 22347776 | 3212277 | 359745348 | 14215157214686 | 14215157160345 | 14215158039066 | 14215158085118 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 455 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 8 | 24 | 302720 | 0x7fb3a6bcd280 | 0x7fb388226540 | 722611 | 722611 | 65536 | 20250624 | 2908718 | 325723956 | 14215158105127 | 14215158039066 | 14215158714747 | 14215158757274 |
| 155 | 153 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 458 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 305472 | 0x7fb3a6bcd100 | 0x7fb388226580 | 723915 | 723915 | 65536 | 20447232 | 2941530 | 329259172 | 14215158768664 | 14215158714747 | 14215159398748 | 14215159443280 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 461 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 308224 | 0x7fb3a452df80 | 0x7fb3882265c0 | 720927 | 720927 | 65536 | 19595264 | 2819809 | 315762272 | 14215159454610 | 14215159398748 | 14215160104189 | 14215160124476 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 464 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 8 | 24 | 310976 | 0x7fb3a452de00 | 0x7fb388226600 | 727851 | 727851 | 65536 | 20381696 | 2927507 | 328117792 | 14215160140546 | 14215160104042 | 14215160767242 | 14215160790502 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 467 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 8 | 24 | 313216 | 0x7fb3a452dc80 | 0x7fb388226640 | 1367627 | 1367627 | 65536 | 31522816 | 4516598 | 505740804 | 14215160804042 | 14215160767242 | 14215161851083 | 14215161870240 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 470 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 8 | 24 | 315968 | 0x7fb3a452db00 | 0x7fb388226680 | 1373685 | 1373685 | 65536 | 38993920 | 5600972 | 627394832 | 14215161895530 | 14215161851083 | 14215162915724 | 14215162943718 |
| 160 | 158 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 473 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 318720 | 0x7fb3a452d980 | 0x7fb3882266c0 | 1371689 | 1371689 | 65536 | 39124992 | 5611756 | 628026528 | 14215162956158 | 14215162915724 | 14215164023405 | 14215164090415 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 476 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 321472 | 0x7fb3a452d800 | 0x7fb388226700 | 1371351 | 1371351 | 65536 | 38469632 | 5509330 | 617034512 | 14215164102135 | 14215164023405 | 14215165162767 | 14215165228301 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 479 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 8 | 24 | 324224 | 0x7fb3a452d680 | 0x7fb388226740 | 1375403 | 1375403 | 65536 | 39059456 | 5600361 | 627017248 | 14215165240901 | 14215165162767 | 14215166283408 | 14215166353648 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 482 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 8 | 24 | 326464 | 0x7fb3a6bcd500 | 0x7fb388226780 | 2665489 | 2665489 | 65536 | 60489728 | 8657149 | 969110268 | 14215166365878 | 14215166283408 | 14215168250130 | 14215168322658 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 485 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 8 | 24 | 329216 | 0x7fb3a6bcd380 | 0x7fb3882267c0 | 2668047 | 2668047 | 65536 | 77266944 | 11071122 | 1240215104 | 14215168342088 | 14215168250130 | 14215170185812 | 14215170257968 |
| 165 | 163 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 488 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 331968 | 0x7fb3a6bcd200 | 0x7fb388226800 | 2669991 | 2669991 | 65536 | 77398016 | 11073092 | 1240153972 | 14215170270618 | 14215170185812 | 14215172178135 | 14215172247277 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 491 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 12 | 24 | 334720 | 0x7fb3a6bcd080 | 0x7fb388226840 | 2669313 | 2669313 | 65536 | 76218368 | 10904971 | 1221373060 | 14215172259557 | 14215172178135 | 14215174155417 | 14215174226337 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 494 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 8 | 24 | 337472 | 0x7fb3a452df00 | 0x7fb388226880 | 2674927 | 2674927 | 65536 | 77332480 | 11078000 | 1240855628 | 14215174238627 | 14215174155417 | 14215176097979 | 14215176170547 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 497 | 21628 | 21628 | 4194304 | 256 | 0 | 0 | 8 | 24 | 0 | 0x7fb3a452dd80 | 0x7fb3882268c0 | 5255947 | 5255947 | 65536 | 120258560 | 17191418 | 1925624888 | 14215176182057 | 14215176097979 | 14215179719903 | 14215179791123 |