37 KiB
37 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_fillBufferAligned.kd | 0 | 0 | 0 | 196041 | 196041 | 33554432 | 256 | 0 | 0 | 4 | 32 | 4160 | 0x0 | 0x7f3782804280 | 17144954536400 | 17144954560091 | 17144954799771 | 17144954888700 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 196041 | 196041 | 32768 | 256 | 0 | 0 | 12 | 24 | 13888 | 0x0 | 0x7f3782823f80 | 17144959659018 | 17144959674163 | 17144959687443 | 17144959705747 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 5 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 14336 | 0x7f37857eb380 | 0x7f3782823fc0 | 17144959710157 | 17144959760403 | 17144959853043 | 17144959855213 |
| 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 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15040 | 0x7f37857eb200 | 0x7f3782824000 | 17144959876742 | 17144959886483 | 17144960065202 | 17144960067367 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 11 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15488 | 0x7f37857eb080 | 0x7f3782824040 | 17144960080697 | 17144960088882 | 17144960267282 | 17144960269271 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 14 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 15936 | 0x7f3783149f00 | 0x7f3782824080 | 17144960283431 | 17144960292082 | 17144960385362 | 17144960387198 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 17 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 16384 | 0x7f3783149d80 | 0x7f37828240c0 | 17144960403148 | 17144960411122 | 17144960503122 | 17144960505155 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 20 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 17088 | 0x7f3783149c00 | 0x7f3782824100 | 17144960532044 | 17144960542482 | 17144960634961 | 17144960636921 |
| 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 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 16 | 24 | 17792 | 0x7f3783149a80 | 0x7f3782824140 | 17144960663411 | 17144960673201 | 17144960852881 | 17144960854605 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 26 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 16 | 24 | 18496 | 0x7f3783149900 | 0x7f3782824180 | 17144960870795 | 17144960878961 | 17144961059921 | 17144961061850 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 29 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19200 | 0x7f3783149780 | 0x7f37828241c0 | 17144961084659 | 17144961094961 | 17144961188721 | 17144961190756 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 32 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19904 | 0x7f3783149600 | 0x7f3782824200 | 17144961214355 | 17144961224721 | 17144961318161 | 17144961320172 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 35 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 20608 | 0x7f37857eb480 | 0x7f3782824240 | 17144961343852 | 17144961370320 | 17144961464080 | 17144961466158 |
| 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 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 16 | 24 | 21312 | 0x7f37857eb300 | 0x7f3782824280 | 17144961484848 | 17144961494320 | 17144961673520 | 17144961675453 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 41 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22016 | 0x7f37857eb180 | 0x7f37828242c0 | 17144961689022 | 17144961698800 | 17144961878480 | 17144961880447 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 44 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22720 | 0x7f37857eb000 | 0x7f3782824300 | 17144961905186 | 17144961915280 | 17144962008560 | 17144962010533 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 47 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 23424 | 0x7f3783149e80 | 0x7f3782824340 | 17144962034283 | 17144962043760 | 17144962137199 | 17144962139160 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 50 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 24128 | 0x7f3783149d00 | 0x7f3782824380 | 17144962162029 | 17144962172399 | 17144962265199 | 17144962267256 |
| 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 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 16 | 24 | 24832 | 0x7f3783149b80 | 0x7f37828243c0 | 17144962291485 | 17144962301839 | 17144962480559 | 17144962482540 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 56 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 16 | 24 | 25536 | 0x7f3783149a00 | 0x7f3782824400 | 17144962499930 | 17144962539119 | 17144962718639 | 17144962720734 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 59 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26240 | 0x7f3783149880 | 0x7f3782824440 | 17144962738633 | 17144962768559 | 17144962861678 | 17144962863720 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 62 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26944 | 0x7f3783149700 | 0x7f3782824480 | 17144962878489 | 17144962887278 | 17144962980238 | 17144962982086 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 65 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 27648 | 0x7f37857eb580 | 0x7f37828244c0 | 17144963003696 | 17144963014318 | 17144963107118 | 17144963109083 |
| 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 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 16 | 24 | 28608 | 0x7f37857eb400 | 0x7f3782824500 | 17144963131172 | 17144963141358 | 17144963320398 | 17144963321897 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 71 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 16 | 24 | 29312 | 0x7f37857eb280 | 0x7f3782824540 | 17144963340776 | 17144963349998 | 17144963530157 | 17144963531491 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 74 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 30016 | 0x7f37857eb100 | 0x7f3782824580 | 17144963547121 | 17144963555117 | 17144963647277 | 17144963648778 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 77 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 8 | 24 | 30976 | 0x7f3783149f80 | 0x7f37828245c0 | 17144963663847 | 17144963671757 | 17144963763757 | 17144963765235 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 80 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 31680 | 0x7f3783149e00 | 0x7f3782824600 | 17144963785524 | 17144963796077 | 17144963888077 | 17144963889611 |
| 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 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 16 | 24 | 32640 | 0x7f3783149c80 | 0x7f3782824640 | 17144963904541 | 17144963913357 | 17144964092237 | 17144964093816 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 86 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 33600 | 0x7f3783149b00 | 0x7f3782824680 | 17144964108605 | 17144964116557 | 17144964297196 | 17144964298610 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 89 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 34560 | 0x7f3783149980 | 0x7f37828246c0 | 17144964314519 | 17144964322316 | 17144964416396 | 17144964417807 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 92 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 8 | 24 | 35520 | 0x7f3783149800 | 0x7f3782824700 | 17144964432816 | 17144964440876 | 17144964534636 | 17144964536113 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 95 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 36224 | 0x7f3783149680 | 0x7f3782824740 | 17144964557723 | 17144964566956 | 17144964660716 | 17144964662020 |
| 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 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 37184 | 0x7f37857eb500 | 0x7f3782824780 | 17144964676939 | 17144964684716 | 17144964864716 | 17144964866134 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 101 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 38144 | 0x7f37857eb380 | 0x7f37828247c0 | 17144964881654 | 17144964890956 | 17144965072235 | 17144965073558 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 104 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 39104 | 0x7f37857eb200 | 0x7f3782824800 | 17144965088788 | 17144965097515 | 17144965190795 | 17144965192275 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 107 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 8 | 24 | 40320 | 0x7f37857eb080 | 0x7f3782824840 | 17144965207485 | 17144965215275 | 17144965309515 | 17144965310982 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 110 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 41280 | 0x7f3783149f00 | 0x7f3782824880 | 17144965332501 | 17144965343275 | 17144965436555 | 17144965438008 |
| 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 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 42240 | 0x7f3783149d80 | 0x7f37828248c0 | 17144965452828 | 17144965460715 | 17144965640234 | 17144965641643 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 116 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 43200 | 0x7f3783149c00 | 0x7f3782824900 | 17144965656192 | 17144965664554 | 17144965845834 | 17144965847297 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 119 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 8 | 24 | 44160 | 0x7f3783149a80 | 0x7f3782824940 | 17144965862527 | 17144965873194 | 17144965966634 | 17144965968074 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 122 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 45376 | 0x7f3783149900 | 0x7f3782824980 | 17144965982583 | 17144965990634 | 17144966085674 | 17144966087260 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 125 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 46336 | 0x7f3783149780 | 0x7f37828249c0 | 17144966109360 | 17144966119914 | 17144966212714 | 17144966214267 |
| 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 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 47552 | 0x7f3783149600 | 0x7f3782824a00 | 17144966228587 | 17144966237034 | 17144966415593 | 17144966417021 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 131 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 48512 | 0x7f37857eb480 | 0x7f3782824a40 | 17144966432321 | 17144966439753 | 17144966620713 | 17144966622166 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 134 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 8 | 24 | 49472 | 0x7f37857eb300 | 0x7f3782824a80 | 17144966638025 | 17144966646633 | 17144966739433 | 17144966740862 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 137 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 50688 | 0x7f37857eb180 | 0x7f3782824ac0 | 17144966756532 | 17144966764713 | 17144966858153 | 17144966859609 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 140 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 51648 | 0x7f37857eb000 | 0x7f3782824b00 | 17144966881448 | 17144966891913 | 17144966984233 | 17144966985836 |
| 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 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 52864 | 0x7f3783149e80 | 0x7f3782824b40 | 17144967003925 | 17144967011593 | 17144967189992 | 17144967191520 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 146 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 54080 | 0x7f3783149d00 | 0x7f3782824b80 | 17144967206089 | 17144967215272 | 17144967393832 | 17144967395234 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 149 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 8 | 24 | 55296 | 0x7f3783149b80 | 0x7f3782824bc0 | 17144967409354 | 17144967417672 | 17144967511592 | 17144967513111 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 152 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 56768 | 0x7f3783149a00 | 0x7f3782824c00 | 17144967527871 | 17144967535752 | 17144967631112 | 17144967632498 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 155 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 57728 | 0x7f3783149880 | 0x7f3782824c40 | 17144967652687 | 17144967663272 | 17144967756392 | 17144967757794 |
| 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 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 58944 | 0x7f3783149700 | 0x7f3782824c80 | 17144967772784 | 17144967780712 | 17144967959271 | 17144967960679 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 161 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 60160 | 0x7f37857eb580 | 0x7f3782824cc0 | 17144967975768 | 17144967983751 | 17144968165831 | 17144968167253 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 164 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 8 | 24 | 61376 | 0x7f37857eb400 | 0x7f3782824d00 | 17144968181502 | 17144968190151 | 17144968284871 | 17144968286310 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 167 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 62848 | 0x7f37857eb280 | 0x7f3782824d40 | 17144968301709 | 17144968309831 | 17144968409511 | 17144968410966 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 170 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 63808 | 0x7f37857eb100 | 0x7f3782824d80 | 17144968431436 | 17144968441831 | 17144968535910 | 17144968537263 |
| 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 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 65024 | 0x7f3783149f80 | 0x7f3782824dc0 | 17144968553112 | 17144968561830 | 17144968741350 | 17144968742857 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 176 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 66240 | 0x7f3783149e00 | 0x7f3782824e00 | 17144968757117 | 17144968765350 | 17144968945510 | 17144968946831 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 179 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 8 | 24 | 67456 | 0x7f3783149c80 | 0x7f3782824e40 | 17144968961131 | 17144968969510 | 17144969064710 | 17144969066108 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 182 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 68928 | 0x7f3783149b00 | 0x7f3782824e80 | 17144969079508 | 17144969087430 | 17144969192390 | 17144969193974 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 185 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 70144 | 0x7f3783149980 | 0x7f3782824ec0 | 17144969215434 | 17144969225829 | 17144969318469 | 17144969319861 |
| 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 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 71616 | 0x7f3783149800 | 0x7f3782824f00 | 17144969334011 | 17144969342309 | 17144969522309 | 17144969523775 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 191 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 72832 | 0x7f3783149680 | 0x7f3782824f40 | 17144969539395 | 17144969548869 | 17144969730629 | 17144969732210 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 194 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 8 | 24 | 74048 | 0x7f37857eb500 | 0x7f3782824f80 | 17144969746069 | 17144969754469 | 17144969847749 | 17144969849226 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 197 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 75776 | 0x7f37857eb380 | 0x7f3782824fc0 | 17144969863916 | 17144969872389 | 17144969979268 | 17144969980803 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 200 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 76992 | 0x7f37857eb200 | 0x7f3782825000 | 17144970000262 | 17144970011268 | 17144970105348 | 17144970106729 |
| 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 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 78464 | 0x7f37857eb080 | 0x7f3782825040 | 17144970122519 | 17144970131428 | 17144970310468 | 17144970311814 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 206 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 79936 | 0x7f3783149f00 | 0x7f3782825080 | 17144970326983 | 17144970334948 | 17144970513988 | 17144970515458 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 209 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 8 | 24 | 81408 | 0x7f3783149d80 | 0x7f37828250c0 | 17144970529868 | 17144970538788 | 17144970634468 | 17144970635855 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 212 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 83136 | 0x7f3783149c00 | 0x7f3782825100 | 17144970649924 | 17144970658307 | 17144970772707 | 17144970774051 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 215 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 84352 | 0x7f3783149a80 | 0x7f3782825140 | 17144970808180 | 17144970817667 | 17144970911587 | 17144970912977 |
| 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 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 85824 | 0x7f3783149900 | 0x7f3782825180 | 17144970928427 | 17144970936227 | 17144971116867 | 17144971118231 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 221 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 87296 | 0x7f3783149780 | 0x7f37828251c0 | 17144971133161 | 17144971141667 | 17144971322467 | 17144971323936 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 224 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 88768 | 0x7f3783149600 | 0x7f3782825200 | 17144971338785 | 17144971347587 | 17144971442946 | 17144971444412 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 227 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 90752 | 0x7f37857eb480 | 0x7f3782825240 | 17144971458522 | 17144971467426 | 17144971588226 | 17144971589698 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 230 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 91968 | 0x7f37857eb300 | 0x7f3782825280 | 17144971609848 | 17144971620226 | 17144971714146 | 17144971715605 |
| 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 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 93440 | 0x7f37857eb180 | 0x7f37828252c0 | 17144971730554 | 17144971738466 | 17144971917346 | 17144971918729 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 236 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 94912 | 0x7f37857eb000 | 0x7f3782825300 | 17144971933029 | 17144971941666 | 17144972121185 | 17144972122724 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 239 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 96384 | 0x7f3783149e80 | 0x7f3782825340 | 17144972137683 | 17144972147265 | 17144972241825 | 17144972243390 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 242 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 98368 | 0x7f3783149d00 | 0x7f3782825380 | 17144972260380 | 17144972268065 | 17144972394145 | 17144972395516 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 245 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 99584 | 0x7f3783149b80 | 0x7f37828253c0 | 17144972417106 | 17144972427745 | 17144972522945 | 17144972524383 |
| 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 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 101312 | 0x7f3783149a00 | 0x7f3782825400 | 17144972540812 | 17144972548705 | 17144972729185 | 17144972730657 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 251 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 102784 | 0x7f3783149880 | 0x7f3782825440 | 17144972745417 | 17144972754305 | 17144972934624 | 17144972935991 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 254 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 104256 | 0x7f3783149700 | 0x7f3782825480 | 17144972949771 | 17144972957824 | 17144973052064 | 17144973053568 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 257 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 106240 | 0x7f37857eb580 | 0x7f37828254c0 | 17144973070308 | 17144973078304 | 17144973209184 | 17144973210644 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 260 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 107712 | 0x7f37857eb400 | 0x7f3782825500 | 17144973232423 | 17144973242944 | 17144973335904 | 17144973337330 |
| 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 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 16 | 24 | 109440 | 0x7f37857eb280 | 0x7f3782825540 | 17144973352840 | 17144973361024 | 17144973540703 | 17144973542115 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 266 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 16 | 24 | 111168 | 0x7f37857eb100 | 0x7f3782825580 | 17144973556634 | 17144973565503 | 17144973745983 | 17144973747369 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 269 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 8 | 24 | 112896 | 0x7f3783149f80 | 0x7f37828255c0 | 17144973761009 | 17144973769183 | 17144973865023 | 17144973866656 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 272 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 115136 | 0x7f3783149e00 | 0x7f3782825600 | 17144973882935 | 17144973890783 | 17144974029663 | 17144974031091 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 275 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 116608 | 0x7f3783149c80 | 0x7f3782825640 | 17144974052171 | 17144974062783 | 17144974157503 | 17144974158858 |
| 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 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 16 | 24 | 118336 | 0x7f3783149b00 | 0x7f3782825680 | 17144974174497 | 17144974182783 | 17144974363262 | 17144974364922 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 281 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 16 | 24 | 120064 | 0x7f3783149980 | 0x7f37828256c0 | 17144974379152 | 17144974388062 | 17144974566782 | 17144974568376 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 284 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 121792 | 0x7f3783149800 | 0x7f3782825700 | 17144974582716 | 17144974590622 | 17144974688542 | 17144974690183 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 287 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 124032 | 0x7f3783149680 | 0x7f3782825740 | 17144974705813 | 17144974713662 | 17144974858622 | 17144974860158 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 290 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 125504 | 0x7f37857eb500 | 0x7f3782825780 | 17144974880628 | 17144974891102 | 17144974985821 | 17144974987415 |
| 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 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 127488 | 0x7f37857eb380 | 0x7f37828257c0 | 17144975001864 | 17144975009821 | 17144975191101 | 17144975192879 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 296 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 129216 | 0x7f37857eb200 | 0x7f3782825800 | 17144975206879 | 17144975214941 | 17144975395901 | 17144975397563 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 299 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 130944 | 0x7f37857eb080 | 0x7f3782825840 | 17144975411093 | 17144975419901 | 17144975519741 | 17144975521130 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 302 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 133440 | 0x7f3783149f00 | 0x7f3782825880 | 17144975535510 | 17144975544061 | 17144975699900 | 17144975701375 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 305 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 134912 | 0x7f3783149d80 | 0x7f37828258c0 | 17144975720974 | 17144975732380 | 17144975827900 | 17144975829231 |
| 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 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 136896 | 0x7f3783149c00 | 0x7f3782825900 | 17144975846061 | 17144975853820 | 17144976033020 | 17144976034576 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 311 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 138880 | 0x7f3783149a80 | 0x7f3782825940 | 17144976050095 | 17144976058780 | 17144976239100 | 17144976240680 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 314 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 140864 | 0x7f3783149900 | 0x7f3782825980 | 17144976255190 | 17144976263580 | 17144976371100 | 17144976372576 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 317 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 143616 | 0x7f3783149780 | 0x7f37828259c0 | 17144976386926 | 17144976396059 | 17144976567899 | 17144976569341 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 320 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 145344 | 0x7f3783149600 | 0x7f3782825a00 | 17144976589270 | 17144976600059 | 17144976695739 | 17144976697097 |
| 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 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 147584 | 0x7f37857eb480 | 0x7f3782825a40 | 17144976712147 | 17144976720219 | 17144976902139 | 17144976903512 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 326 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 149568 | 0x7f37857eb300 | 0x7f3782825a80 | 17144976918101 | 17144976926619 | 17144977108699 | 17144977110116 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 329 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 151552 | 0x7f37857eb180 | 0x7f3782825ac0 | 17144977124876 | 17144977133178 | 17144977243898 | 17144977245312 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 332 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 154304 | 0x7f37857eb000 | 0x7f3782825b00 | 17144977260102 | 17144977268538 | 17144977449658 | 17144977451117 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 335 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 156288 | 0x7f3783149e80 | 0x7f3782825b40 | 17144977473046 | 17144977482298 | 17144977583578 | 17144977585133 |
| 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 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 158784 | 0x7f3783149d00 | 0x7f3782825b80 | 17144977602982 | 17144977611258 | 17144977798298 | 17144977799717 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 341 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 161024 | 0x7f3783149b80 | 0x7f3782825bc0 | 17144977816046 | 17144977823898 | 17144978009177 | 17144978010601 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 344 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 163264 | 0x7f3783149a00 | 0x7f3782825c00 | 17144978027801 | 17144978036217 | 17144978159097 | 17144978160687 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 347 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 166528 | 0x7f3783149880 | 0x7f3782825c40 | 17144978174566 | 17144978182457 | 17144978389177 | 17144978433629 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 350 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 168512 | 0x7f3783149700 | 0x7f3782825c80 | 17144978448969 | 17144978459577 | 17144978570456 | 17144978571975 |
| 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 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 171264 | 0x7f37857eb580 | 0x7f3782825cc0 | 17144978587725 | 17144978596376 | 17144978779256 | 17144978780770 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 356 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 173760 | 0x7f37857eb400 | 0x7f3782825d00 | 17144978794949 | 17144978802616 | 17144978990616 | 17144978992164 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 359 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 176256 | 0x7f37857eb280 | 0x7f3782825d40 | 17144979007663 | 17144979016376 | 17144979150936 | 17144979152349 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 362 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 179776 | 0x7f37857eb100 | 0x7f3782825d80 | 17144979166349 | 17144979175096 | 17144979407095 | 17144979428152 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 365 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 182272 | 0x7f3783149f80 | 0x7f3782825dc0 | 17144979442981 | 17144979453815 | 17144979580535 | 17144979581958 |
| 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 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 185536 | 0x7f3783149e00 | 0x7f3782825e00 | 17144979597587 | 17144979605335 | 17144979795895 | 17144979797222 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 371 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 188544 | 0x7f3783149c80 | 0x7f3782825e40 | 17144979813981 | 17144979822455 | 17144980015734 | 17144980017195 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 374 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 191552 | 0x7f3783149b00 | 0x7f3782825e80 | 17144980033545 | 17144980041814 | 17144980202294 | 17144980203730 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 377 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 195840 | 0x7f3783149980 | 0x7f3782825ec0 | 17144980218960 | 17144980226614 | 17144980509974 | 17144980557371 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 380 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 198592 | 0x7f3783149800 | 0x7f3782825f00 | 17144980573480 | 17144980583894 | 17144980733333 | 17144980734786 |
| 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 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 202368 | 0x7f3783149680 | 0x7f3782825f40 | 17144980751045 | 17144980759093 | 17144980967093 | 17144981012698 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 386 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 205888 | 0x7f37857eb500 | 0x7f3782825f80 | 17144981020588 | 17144981030773 | 17144981237333 | 17144981280941 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 389 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 209408 | 0x7f37857eb380 | 0x7f3782825fc0 | 17144981289520 | 17144981299413 | 17144981485012 | 17144981486555 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 392 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 214464 | 0x7f37857eb200 | 0x7f3782826000 | 17144981500574 | 17144981509332 | 17144981843572 | 17144981860134 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 395 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 217728 | 0x7f37857eb080 | 0x7f3782826040 | 17144981875814 | 17144981886132 | 17144982053652 | 17144982054989 |
| 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 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 222016 | 0x7f3783149f00 | 0x7f3782826080 | 17144982070149 | 17144982078132 | 17144982308691 | 17144982350081 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 401 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 226048 | 0x7f3783149d80 | 0x7f37828260c0 | 17144982359281 | 17144982369331 | 17144982597491 | 17144982637943 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 404 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 230080 | 0x7f3783149c00 | 0x7f3782826100 | 17144982652193 | 17144982661491 | 17144982872850 | 17144982916505 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 407 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 235904 | 0x7f3783149a80 | 0x7f3782826140 | 17144982926545 | 17144982936050 | 17144983321330 | 17144983340184 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 410 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 239424 | 0x7f3783149900 | 0x7f3782826180 | 17144983357433 | 17144983367250 | 17144983554610 | 17144983556028 |
| 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 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 244224 | 0x7f3783149780 | 0x7f37828261c0 | 17144983571407 | 17144983579249 | 17144983829489 | 17144983847919 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 416 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 248768 | 0x7f3783149600 | 0x7f3782826200 | 17144983856319 | 17144983866449 | 17144984113969 | 17144984132222 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 419 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 253312 | 0x7f37857eb480 | 0x7f3782826240 | 17144984140931 | 17144984150929 | 17144984388048 | 17144984406354 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 422 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 8 | 24 | 255552 | 0x7f37857eb300 | 0x7f3782826280 | 17144984415324 | 17144984425488 | 17144984880208 | 17144984896660 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 425 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 259840 | 0x7f37857eb180 | 0x7f37828262c0 | 17144984913010 | 17144984923728 | 17144985148367 | 17144985164033 |
| 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 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 265664 | 0x7f37857eb000 | 0x7f3782826300 | 17144985175333 | 17144985185807 | 17144985483727 | 17144985499024 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 431 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 271232 | 0x7f3783149e80 | 0x7f3782826340 | 17144985509373 | 17144985518447 | 17144985816526 | 17144985835054 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 434 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 8 | 24 | 273216 | 0x7f3783149d00 | 0x7f3782826380 | 17144985843984 | 17144985853966 | 17144986150766 | 17144986171715 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 437 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 8 | 24 | 275712 | 0x7f3783149b80 | 0x7f37828263c0 | 17144986181625 | 17144986191246 | 17144986749005 | 17144986764999 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 440 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 280768 | 0x7f3783149a00 | 0x7f3782826400 | 17144986782428 | 17144986792685 | 17144987056205 | 17144987074690 |
| 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 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 287616 | 0x7f3783149880 | 0x7f3782826440 | 17144987083750 | 17144987093485 | 17144987444364 | 17144987462499 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 446 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 294208 | 0x7f3783149700 | 0x7f3782826480 | 17144987470749 | 17144987486124 | 17144987836204 | 17144987854979 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 449 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 8 | 24 | 296960 | 0x7f37857eb580 | 0x7f37828264c0 | 17144987866268 | 17144987876363 | 17144988223563 | 17144988239078 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 452 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 8 | 24 | 299968 | 0x7f37857eb400 | 0x7f3782826500 | 17144988248048 | 17144988258443 | 17144988918922 | 17144988941748 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 455 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 8 | 24 | 302720 | 0x7f37857eb280 | 0x7f3782826540 | 17144988958928 | 17144988968522 | 17144989415561 | 17144989435605 |
| 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 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 305472 | 0x7f37857eb100 | 0x7f3782826580 | 17144989445454 | 17144989454761 | 17144989919561 | 17144989939001 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 461 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 308224 | 0x7f3783149f80 | 0x7f37828265c0 | 17144989950221 | 17144989965961 | 17144990428840 | 17144990475946 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 464 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 8 | 24 | 310976 | 0x7f3783149e00 | 0x7f3782826600 | 17144990485226 | 17144990495400 | 17144990946599 | 17144990993582 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 467 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 8 | 24 | 313216 | 0x7f3783149c80 | 0x7f3782826640 | 17144991002421 | 17144991012359 | 17144991882118 | 17144991926496 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 470 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 8 | 24 | 315968 | 0x7f3783149b00 | 0x7f3782826680 | 17144991943975 | 17144991954438 | 17144992808037 | 17144992828311 |
| 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 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 318720 | 0x7f3783149980 | 0x7f37828266c0 | 17144992838351 | 17144992848037 | 17144993733955 | 17144993754505 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 476 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 321472 | 0x7f3783149800 | 0x7f3782826700 | 17144993763925 | 17144993773955 | 17144994652674 | 17144994701769 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 479 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 8 | 24 | 324224 | 0x7f3783149680 | 0x7f3782826740 | 17144994711489 | 17144994738434 | 17144995597793 | 17144995619504 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 482 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 8 | 24 | 326464 | 0x7f37857eb500 | 0x7f3782826780 | 17144995629654 | 17144995640673 | 17144997338590 | 17144997387335 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 485 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 8 | 24 | 329216 | 0x7f37857eb380 | 0x7f37828267c0 | 17144997403635 | 17144997414110 | 17144999079388 | 17144999124547 |
| 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 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 331968 | 0x7f37857eb200 | 0x7f3782826800 | 17144999135977 | 17144999144828 | 17145000869785 | 17145000938287 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 491 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 12 | 24 | 334720 | 0x7f37857eb080 | 0x7f3782826840 | 17145000947177 | 17145000957145 | 17145002672343 | 17145002741977 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 494 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 8 | 24 | 337472 | 0x7f3783149f00 | 0x7f3782826880 | 17145002753117 | 17145002762263 | 17145004436660 | 17145004503678 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 497 | 196041 | 196041 | 4194304 | 256 | 0 | 0 | 8 | 24 | 0 | 0x7f3783149d80 | 0x7f37828268c0 | 17145004513518 | 17145004524980 | 17145007882896 | 17145007958173 |