48 KiB
48 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 | CPC_ME1_BUSY_FOR_PACKET_DECODE | SQ_CYCLES | SQ_WAVES | SQ_WAVE_CYCLES | SQ_BUSY_CYCLES | SQ_LEVEL_WAVES | SQ_ACCUM_PREV_HIRES | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBufferAligned.kd | 0 | 0 | 0 | 194332 | 194332 | 33554432 | 256 | 0 | 0 | 4 | 32 | 4160 | 0x0 | 0x7fc390804280 | 381340 | 381340 | 8834 | 3050728 | 524288 | 239605293 | 2963625 | 0 | 974680612 | 17125775589873 | 17125068730776 | 17125923761092 | 17125923874631 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 194332 | 194332 | 32768 | 256 | 0 | 0 | 12 | 24 | 13888 | 0x0 | 0x7fc390823f80 | 33330 | 33330 | 29863 | 266648 | 512 | 1782276 | 165375 | 0 | 7142768 | 17125929027678 | 17125923761092 | 17125929167969 | 17125929172374 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 5 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 14336 | 0x7fc3937bf380 | 0x7fc390823fc0 | 164235 | 164235 | 13939 | 1313888 | 65536 | 80435930 | 1212523 | 0 | 323471456 | 17125929215982 | 17125929167969 | 17125929561249 | 17125929563653 |
| 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 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15040 | 0x7fc3937bf200 | 0x7fc390824000 | 308131 | 308131 | 23902 | 2465056 | 65536 | 227437416 | 2366838 | 0 | 911476300 | 17125929609812 | 17125929561249 | 17125929990209 | 17125929992501 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 11 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15488 | 0x7fc3937bf080 | 0x7fc390824040 | 308793 | 308793 | 22768 | 2470352 | 65536 | 216744840 | 2370791 | 0 | 868707944 | 17125930034760 | 17125929990209 | 17125930430529 | 17125930432689 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 14 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 15936 | 0x7fc391191f00 | 0x7fc390824080 | 164121 | 164121 | 12907 | 1312976 | 65536 | 74948047 | 1209804 | 0 | 301522696 | 17125930474637 | 17125930430529 | 17125930767649 | 17125930769699 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 17 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 16384 | 0x7fc391191d80 | 0x7fc3908240c0 | 163653 | 163653 | 14159 | 1309232 | 65536 | 87523164 | 1210978 | 0 | 351821424 | 17125930809898 | 17125930767649 | 17125931104768 | 17125931106810 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 20 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 17088 | 0x7fc391191c00 | 0x7fc390824100 | 161993 | 161993 | 15516 | 1295952 | 65536 | 107050772 | 1199194 | 0 | 429930144 | 17125931161218 | 17125931104768 | 17125931432928 | 17125931435011 |
| 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 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 16 | 24 | 17792 | 0x7fc391191a80 | 0x7fc390824140 | 309379 | 309379 | 23110 | 2475040 | 65536 | 226969388 | 2375242 | 0 | 909605148 | 17125931475590 | 17125931432928 | 17125931867168 | 17125931869529 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 26 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 16 | 24 | 18496 | 0x7fc391191900 | 0x7fc390824180 | 308213 | 308213 | 21076 | 2465712 | 65536 | 219158231 | 2363892 | 0 | 878361696 | 17125931910417 | 17125931867168 | 17125932287808 | 17125932289937 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 29 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19200 | 0x7fc391191780 | 0x7fc3908241c0 | 165589 | 165589 | 15469 | 1324720 | 65536 | 99060101 | 1220646 | 0 | 397967520 | 17125932330036 | 17125932287808 | 17125932619968 | 17125932622018 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 32 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19904 | 0x7fc391191600 | 0x7fc390824200 | 164530 | 164530 | 15270 | 1316248 | 65536 | 93524503 | 1211989 | 0 | 375828948 | 17125932662227 | 17125932619968 | 17125932951008 | 17125932953168 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 35 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 20608 | 0x7fc3937bf480 | 0x7fc390824240 | 164499 | 164499 | 14944 | 1316000 | 65536 | 98827527 | 1210804 | 0 | 397034036 | 17125933006067 | 17125932951008 | 17125933285248 | 17125933287399 |
| 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 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 16 | 24 | 21312 | 0x7fc3937bf300 | 0x7fc390824280 | 310836 | 310836 | 24318 | 2486696 | 65536 | 229061745 | 2386426 | 0 | 917975492 | 17125933328958 | 17125933285248 | 17125933704608 | 17125933706877 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 41 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22016 | 0x7fc3937bf180 | 0x7fc3908242c0 | 307384 | 307384 | 21652 | 2459080 | 65536 | 221046444 | 2355255 | 0 | 885912352 | 17125933749066 | 17125933704608 | 17125934123648 | 17125934125886 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 44 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22720 | 0x7fc3937bf000 | 0x7fc390824300 | 164050 | 164050 | 14759 | 1312408 | 65536 | 87719575 | 1210641 | 0 | 352612320 | 17125934167545 | 17125934123648 | 17125934476447 | 17125934478806 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 47 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 23424 | 0x7fc391191e80 | 0x7fc390824340 | 163416 | 163416 | 15017 | 1307336 | 65536 | 107836475 | 1209452 | 0 | 433070936 | 17125934518745 | 17125934476447 | 17125934793247 | 17125934794997 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 50 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 24128 | 0x7fc391191d00 | 0x7fc390824380 | 163126 | 163126 | 14876 | 1305016 | 65536 | 94493731 | 1199380 | 0 | 379697316 | 17125934843466 | 17125934793247 | 17125935096927 | 17125935098389 |
| 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 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 16 | 24 | 24832 | 0x7fc391191b80 | 0x7fc3908243c0 | 308927 | 308927 | 24223 | 2471424 | 65536 | 231630167 | 2371682 | 0 | 928248524 | 17125935142518 | 17125935096927 | 17125935487647 | 17125935489378 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 56 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 16 | 24 | 25536 | 0x7fc391191a00 | 0x7fc390824400 | 306834 | 306834 | 21355 | 2454680 | 65536 | 219380053 | 2353205 | 0 | 879250036 | 17125935530957 | 17125935487647 | 17125935878687 | 17125935880237 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 59 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26240 | 0x7fc391191880 | 0x7fc390824440 | 162388 | 162388 | 14532 | 1299112 | 65536 | 96771330 | 1201417 | 0 | 388810844 | 17125935922306 | 17125935878687 | 17125936179487 | 17125936180989 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 62 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26944 | 0x7fc391191700 | 0x7fc390824480 | 162986 | 162986 | 14023 | 1303896 | 65536 | 87946997 | 1203291 | 0 | 353516344 | 17125936223208 | 17125936179487 | 17125936481727 | 17125936483371 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 65 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 27648 | 0x7fc3937bf580 | 0x7fc3908244c0 | 162540 | 162540 | 14469 | 1300328 | 65536 | 101334829 | 1202343 | 0 | 407070776 | 17125936531719 | 17125936481727 | 17125936787647 | 17125936789212 |
| 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 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 16 | 24 | 28608 | 0x7fc3937bf400 | 0x7fc390824500 | 305040 | 305040 | 23727 | 2440328 | 65536 | 212012863 | 2335008 | 0 | 849781028 | 17125936833541 | 17125936787647 | 17125937178207 | 17125937179881 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 71 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 16 | 24 | 29312 | 0x7fc3937bf280 | 0x7fc390824540 | 306762 | 306762 | 20940 | 2454104 | 65536 | 213531613 | 2349729 | 0 | 855855464 | 17125937222860 | 17125937178207 | 17125937572127 | 17125937573840 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 74 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 30016 | 0x7fc3937bf100 | 0x7fc390824580 | 161204 | 161204 | 14493 | 1289640 | 65536 | 102213692 | 1192834 | 0 | 410585580 | 17125937616529 | 17125937572127 | 17125937873246 | 17125937874992 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 77 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 8 | 24 | 30976 | 0x7fc391191f80 | 0x7fc3908245c0 | 162220 | 162220 | 14832 | 1297768 | 65536 | 97504893 | 1195937 | 0 | 391745700 | 17125937916841 | 17125937873246 | 17125938175966 | 17125938177844 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 80 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 31680 | 0x7fc391191e00 | 0x7fc390824600 | 162405 | 162405 | 14302 | 1299248 | 65536 | 94799236 | 1198245 | 0 | 380922652 | 17125938227472 | 17125938175966 | 17125938494686 | 17125938496215 |
| 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 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 16 | 24 | 32640 | 0x7fc391191c80 | 0x7fc390824640 | 304323 | 304323 | 22745 | 2434592 | 65536 | 222967499 | 2331339 | 0 | 893604940 | 17125938538624 | 17125938494686 | 17125938889246 | 17125938890794 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 86 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 33600 | 0x7fc391191b00 | 0x7fc390824680 | 306200 | 306200 | 22685 | 2449608 | 65536 | 220414519 | 2347657 | 0 | 883385616 | 17125938932973 | 17125938889246 | 17125939280766 | 17125939282393 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 89 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 34560 | 0x7fc391191980 | 0x7fc3908246c0 | 162903 | 162903 | 15160 | 1303232 | 65536 | 103007433 | 1203470 | 0 | 413755668 | 17125939323452 | 17125939280766 | 17125939600286 | 17125939601934 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 92 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 8 | 24 | 35520 | 0x7fc391191800 | 0x7fc390824700 | 163228 | 163228 | 14832 | 1305832 | 65536 | 99974425 | 1207029 | 0 | 401620384 | 17125939643953 | 17125939600286 | 17125939903646 | 17125939905345 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 95 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 36224 | 0x7fc391191680 | 0x7fc390824740 | 161812 | 161812 | 15003 | 1294504 | 65536 | 97962593 | 1191034 | 0 | 393574488 | 17125939952934 | 17125939903646 | 17125940211166 | 17125940212717 |
| 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 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 37184 | 0x7fc3937bf500 | 0x7fc390824780 | 301681 | 301681 | 22799 | 2413456 | 65536 | 223274986 | 2312497 | 0 | 894831272 | 17125940259326 | 17125940211166 | 17125940614686 | 17125940616466 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 101 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 38144 | 0x7fc3937bf380 | 0x7fc3908247c0 | 304538 | 304538 | 22597 | 2436312 | 65536 | 216073126 | 2337039 | 0 | 866022032 | 17125940656805 | 17125940614686 | 17125941003646 | 17125941005375 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 104 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 39104 | 0x7fc3937bf200 | 0x7fc390824800 | 161786 | 161786 | 14113 | 1294296 | 65536 | 92586509 | 1195169 | 0 | 372078912 | 17125941046174 | 17125941003646 | 17125941308606 | 17125941310296 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 107 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 8 | 24 | 40320 | 0x7fc3937bf080 | 0x7fc390824840 | 163212 | 163212 | 15036 | 1305704 | 65536 | 92823918 | 1201226 | 0 | 373023960 | 17125941352135 | 17125941308606 | 17125941614685 | 17125941616178 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 110 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 41280 | 0x7fc391191f00 | 0x7fc390824880 | 162423 | 162423 | 14766 | 1299392 | 65536 | 103426478 | 1199927 | 0 | 415425584 | 17125941664966 | 17125941614685 | 17125941923165 | 17125941924729 |
| 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 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 42240 | 0x7fc391191d80 | 0x7fc3908248c0 | 306696 | 306696 | 23919 | 2453576 | 65536 | 230067969 | 2352565 | 0 | 922000636 | 17125941966148 | 17125941923165 | 17125942324285 | 17125942325908 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 116 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 43200 | 0x7fc391191c00 | 0x7fc390824900 | 306657 | 306657 | 23888 | 2453264 | 65536 | 223055758 | 2346706 | 0 | 893957276 | 17125942366157 | 17125942324285 | 17125942717725 | 17125942719407 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 119 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 8 | 24 | 44160 | 0x7fc391191a80 | 0x7fc390824940 | 161982 | 161982 | 14717 | 1295864 | 65536 | 99154839 | 1196939 | 0 | 398341852 | 17125942759796 | 17125942717725 | 17125943019965 | 17125943021609 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 122 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 45376 | 0x7fc391191900 | 0x7fc390824980 | 161590 | 161590 | 15041 | 1292728 | 65536 | 90767813 | 1188799 | 0 | 364798140 | 17125943062998 | 17125943019965 | 17125943324925 | 17125943326470 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 125 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 46336 | 0x7fc391191780 | 0x7fc3908249c0 | 161434 | 161434 | 13907 | 1291480 | 65536 | 97340952 | 1194568 | 0 | 391087672 | 17125943374659 | 17125943324925 | 17125943632605 | 17125943634112 |
| 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 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 47552 | 0x7fc391191600 | 0x7fc390824a00 | 303827 | 303827 | 22496 | 2430624 | 65536 | 212619403 | 2325201 | 0 | 852208080 | 17125943675690 | 17125943632605 | 17125944020925 | 17125944022421 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 131 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 48512 | 0x7fc3937bf480 | 0x7fc390824a40 | 302160 | 302160 | 21331 | 2417288 | 65536 | 210469971 | 2312130 | 0 | 843607472 | 17125944064130 | 17125944020925 | 17125944409565 | 17125944411080 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 134 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 8 | 24 | 49472 | 0x7fc3937bf300 | 0x7fc390824a80 | 161138 | 161138 | 14536 | 1289112 | 65536 | 95012236 | 1189673 | 0 | 381777500 | 17125944452269 | 17125944409565 | 17125944711645 | 17125944713342 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 137 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 50688 | 0x7fc3937bf180 | 0x7fc390824ac0 | 161463 | 161463 | 15753 | 1291712 | 65536 | 96357214 | 1188044 | 0 | 387161624 | 17125944754970 | 17125944711645 | 17125945014684 | 17125945016153 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 140 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 51648 | 0x7fc3937bf000 | 0x7fc390824b00 | 160809 | 160809 | 14396 | 1286480 | 65536 | 89934062 | 1185460 | 0 | 361472420 | 17125945065262 | 17125945014684 | 17125945321404 | 17125945322955 |
| 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 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 52864 | 0x7fc391191e80 | 0x7fc390824b40 | 305128 | 305128 | 24280 | 2441032 | 65536 | 224386657 | 2336721 | 0 | 899274428 | 17125945368753 | 17125945321404 | 17125945723324 | 17125945724983 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 146 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 54080 | 0x7fc391191d00 | 0x7fc390824b80 | 300035 | 300035 | 19869 | 2400288 | 65536 | 205814889 | 2294941 | 0 | 824988636 | 17125945768172 | 17125945723324 | 17125946120604 | 17125946122272 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 149 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 8 | 24 | 55296 | 0x7fc391191b80 | 0x7fc390824bc0 | 162731 | 162731 | 14902 | 1301856 | 65536 | 101275591 | 1199291 | 0 | 406823596 | 17125946163161 | 17125946120604 | 17125946427804 | 17125946429384 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 152 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 56768 | 0x7fc391191a00 | 0x7fc390824c00 | 162961 | 162961 | 15439 | 1303696 | 65536 | 102842047 | 1205134 | 0 | 413102288 | 17125946470083 | 17125946427804 | 17125946737084 | 17125946738755 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 155 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 57728 | 0x7fc391191880 | 0x7fc390824c40 | 162067 | 162067 | 14843 | 1296544 | 65536 | 95279405 | 1195877 | 0 | 382844056 | 17125946786664 | 17125946737084 | 17125947042844 | 17125947044367 |
| 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 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 58944 | 0x7fc391191700 | 0x7fc390824c80 | 303593 | 303593 | 22974 | 2428752 | 65536 | 223988210 | 2325002 | 0 | 897686072 | 17125947091505 | 17125947042844 | 17125947440124 | 17125947441686 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 161 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 60160 | 0x7fc3937bf580 | 0x7fc390824cc0 | 300307 | 300307 | 20864 | 2402464 | 65536 | 215170018 | 2299894 | 0 | 862408044 | 17125947485814 | 17125947440124 | 17125947834204 | 17125947835665 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 164 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 8 | 24 | 61376 | 0x7fc3937bf400 | 0x7fc390824d00 | 162327 | 162327 | 14427 | 1298624 | 65536 | 93983382 | 1201659 | 0 | 377667932 | 17125947878863 | 17125947834204 | 17125948140284 | 17125948141916 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 167 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 62848 | 0x7fc3937bf280 | 0x7fc390824d40 | 168017 | 168017 | 16192 | 1344144 | 65536 | 107028236 | 1242516 | 0 | 429847472 | 17125948184265 | 17125948140284 | 17125948453883 | 17125948455277 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 170 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 63808 | 0x7fc3937bf100 | 0x7fc390824d80 | 160632 | 160632 | 14497 | 1285064 | 65536 | 95352726 | 1187612 | 0 | 383132992 | 17125948505186 | 17125948453883 | 17125948753563 | 17125948755269 |
| 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 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 65024 | 0x7fc391191f80 | 0x7fc390824dc0 | 301754 | 301754 | 23428 | 2414040 | 65536 | 222043648 | 2310314 | 0 | 889909532 | 17125948800848 | 17125948753563 | 17125949148283 | 17125949149788 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 176 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 66240 | 0x7fc391191e00 | 0x7fc390824e00 | 300309 | 300309 | 21642 | 2402480 | 65536 | 214077053 | 2298861 | 0 | 858039388 | 17125949192447 | 17125949148283 | 17125949535643 | 17125949537277 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 179 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 8 | 24 | 67456 | 0x7fc391191c80 | 0x7fc390824e40 | 162610 | 162610 | 14505 | 1300888 | 65536 | 93481998 | 1199654 | 0 | 375653152 | 17125949577756 | 17125949535643 | 17125949838043 | 17125949839789 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 182 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 68928 | 0x7fc391191b00 | 0x7fc390824e80 | 175643 | 175643 | 16360 | 1405152 | 65536 | 106267614 | 1304364 | 0 | 426810160 | 17125949882718 | 17125949838043 | 17125950153083 | 17125950154680 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 185 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 70144 | 0x7fc391191980 | 0x7fc390824ec0 | 160606 | 160606 | 15049 | 1284856 | 65536 | 93761457 | 1184291 | 0 | 376780548 | 17125950203859 | 17125950153083 | 17125950463803 | 17125950465371 |
| 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 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 71616 | 0x7fc391191800 | 0x7fc390824f00 | 302425 | 302425 | 22949 | 2419408 | 65536 | 222010511 | 2321865 | 0 | 889769940 | 17125950506350 | 17125950463803 | 17125950854363 | 17125950856031 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 191 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 72832 | 0x7fc391191680 | 0x7fc390824f40 | 301255 | 301255 | 22834 | 2410048 | 65536 | 223263724 | 2313901 | 0 | 894782660 | 17125950897290 | 17125950854363 | 17125951242843 | 17125951244370 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 194 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 8 | 24 | 74048 | 0x7fc3937bf500 | 0x7fc390824f80 | 160243 | 160243 | 14783 | 1281952 | 65536 | 91212878 | 1183471 | 0 | 366587204 | 17125951284919 | 17125951242843 | 17125951545883 | 17125951547452 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 197 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 75776 | 0x7fc3937bf380 | 0x7fc390824fc0 | 181828 | 181828 | 17113 | 1454632 | 65536 | 110009581 | 1350382 | 0 | 441783620 | 17125951588810 | 17125951545883 | 17125951863962 | 17125951865453 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 200 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 76992 | 0x7fc3937bf200 | 0x7fc390825000 | 160943 | 160943 | 14923 | 1287552 | 65536 | 92883392 | 1188959 | 0 | 373263336 | 17125951925371 | 17125951863962 | 17125952169722 | 17125952171474 |
| 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 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 78464 | 0x7fc3937bf080 | 0x7fc390825040 | 301048 | 301048 | 23187 | 2408392 | 65536 | 214263265 | 2307682 | 0 | 858784376 | 17125952213353 | 17125952169722 | 17125952560122 | 17125952561673 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 206 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 79936 | 0x7fc391191f00 | 0x7fc390825080 | 299641 | 299641 | 22262 | 2397136 | 65536 | 219242148 | 2298804 | 0 | 878698364 | 17125952603162 | 17125952560122 | 17125952952762 | 17125952954283 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 209 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 8 | 24 | 81408 | 0x7fc391191d80 | 0x7fc3908250c0 | 162570 | 162570 | 15174 | 1300568 | 65536 | 95859485 | 1198280 | 0 | 385159664 | 17125952994671 | 17125952952762 | 17125953254522 | 17125953256254 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 212 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 83136 | 0x7fc391191c00 | 0x7fc390825100 | 191402 | 191402 | 17856 | 1531224 | 65536 | 118790047 | 1425666 | 0 | 476899756 | 17125953296813 | 17125953254522 | 17125953576762 | 17125953578345 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 215 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 84352 | 0x7fc391191a80 | 0x7fc390825140 | 160494 | 160494 | 14549 | 1283960 | 65536 | 94232346 | 1186075 | 0 | 378661148 | 17125953626704 | 17125953576762 | 17125953891482 | 17125953893137 |
| 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 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 85824 | 0x7fc391191900 | 0x7fc390825180 | 300925 | 300925 | 22918 | 2407408 | 65536 | 223069482 | 2310429 | 0 | 894014084 | 17125953934685 | 17125953891482 | 17125954294202 | 17125954295915 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 221 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 87296 | 0x7fc391191780 | 0x7fc3908251c0 | 299793 | 299793 | 22663 | 2398352 | 65536 | 217660320 | 2299933 | 0 | 872370088 | 17125954336574 | 17125954294202 | 17125954687642 | 17125954689374 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 224 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 88768 | 0x7fc391191600 | 0x7fc390825200 | 161824 | 161824 | 15743 | 1294600 | 65536 | 98147038 | 1187529 | 0 | 394314932 | 17125954728963 | 17125954687642 | 17125954988762 | 17125954990226 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 227 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 90752 | 0x7fc3937bf480 | 0x7fc390825240 | 201973 | 201973 | 18490 | 1615792 | 65536 | 121216894 | 1501665 | 0 | 486615296 | 17125955030625 | 17125954988762 | 17125955321241 | 17125955323097 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 230 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 91968 | 0x7fc3937bf300 | 0x7fc390825280 | 161198 | 161198 | 14588 | 1289592 | 65536 | 93067314 | 1189405 | 0 | 373995792 | 17125955372125 | 17125955321241 | 17125955624441 | 17125955625958 |
| 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 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 93440 | 0x7fc3937bf180 | 0x7fc3908252c0 | 302414 | 302414 | 24188 | 2419320 | 65536 | 220333872 | 2314085 | 0 | 883068520 | 17125955667477 | 17125955624441 | 17125956014521 | 17125956016077 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 236 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 94912 | 0x7fc3937bf000 | 0x7fc390825300 | 299438 | 299438 | 21013 | 2395512 | 65536 | 208037140 | 2292007 | 0 | 833881536 | 17125956059466 | 17125956014521 | 17125956404121 | 17125956405567 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 239 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 96384 | 0x7fc391191e80 | 0x7fc390825340 | 161383 | 161383 | 15156 | 1291072 | 65536 | 97792491 | 1191414 | 0 | 392899980 | 17125956446855 | 17125956404121 | 17125956707961 | 17125956709468 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 242 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 98368 | 0x7fc391191d00 | 0x7fc390825380 | 210364 | 210364 | 19104 | 1682920 | 65536 | 134280356 | 1572768 | 0 | 538861792 | 17125956750817 | 17125956707961 | 17125957041881 | 17125957043659 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 245 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 99584 | 0x7fc391191b80 | 0x7fc3908253c0 | 161084 | 161084 | 15170 | 1288680 | 65536 | 92485444 | 1186314 | 0 | 371671020 | 17125957091508 | 17125957041881 | 17125957351001 | 17125957352470 |
| 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 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 101312 | 0x7fc391191a00 | 0x7fc390825400 | 297326 | 297326 | 22402 | 2378616 | 65536 | 217258070 | 2277071 | 0 | 870770568 | 17125957393529 | 17125957351001 | 17125957744121 | 17125957745739 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 251 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 102784 | 0x7fc391191880 | 0x7fc390825440 | 298532 | 298532 | 22122 | 2388264 | 65536 | 212131684 | 2280139 | 0 | 850257416 | 17125957788308 | 17125957744121 | 17125958133561 | 17125958134998 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 254 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 104256 | 0x7fc391191700 | 0x7fc390825480 | 160022 | 160022 | 14919 | 1280184 | 65536 | 98996138 | 1182306 | 0 | 397726880 | 17125958176547 | 17125958133561 | 17125958439961 | 17125958441360 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 257 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 106240 | 0x7fc3937bf580 | 0x7fc3908254c0 | 219118 | 219118 | 18931 | 1752952 | 65536 | 142587045 | 1649553 | 0 | 572096756 | 17125958482599 | 17125958439961 | 17125958782520 | 17125958784130 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 260 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 107712 | 0x7fc3937bf400 | 0x7fc390825500 | 160024 | 160024 | 14741 | 1280200 | 65536 | 96199805 | 1180542 | 0 | 386536840 | 17125958833209 | 17125958782520 | 17125959094040 | 17125959095542 |
| 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 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 16 | 24 | 109440 | 0x7fc3937bf280 | 0x7fc390825540 | 297104 | 297104 | 21107 | 2376840 | 65536 | 210107478 | 2274308 | 0 | 842162740 | 17125959139321 | 17125959094040 | 17125959483960 | 17125959485431 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 266 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 16 | 24 | 111168 | 0x7fc3937bf100 | 0x7fc390825580 | 298133 | 298133 | 20839 | 2385072 | 65536 | 202645784 | 2279286 | 0 | 812315004 | 17125959526800 | 17125959483960 | 17125959875000 | 17125959876570 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 269 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 8 | 24 | 112896 | 0x7fc391191f80 | 0x7fc3908255c0 | 163249 | 163249 | 14999 | 1306000 | 65536 | 103606309 | 1205097 | 0 | 416163452 | 17125959917049 | 17125959875000 | 17125960187960 | 17125960189521 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 272 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 115136 | 0x7fc391191e00 | 0x7fc390825600 | 228489 | 228489 | 19493 | 1827920 | 65536 | 154009180 | 1720796 | 0 | 617780180 | 17125960230690 | 17125960187960 | 17125960538520 | 17125960540092 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 275 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 116608 | 0x7fc391191c80 | 0x7fc390825640 | 159865 | 159865 | 15059 | 1278928 | 65536 | 96911884 | 1179856 | 0 | 389371540 | 17125960587660 | 17125960538520 | 17125960855160 | 17125960856753 |
| 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 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 16 | 24 | 118336 | 0x7fc391191b00 | 0x7fc390825680 | 296591 | 296591 | 21118 | 2372736 | 65536 | 213293260 | 2272586 | 0 | 854907004 | 17125960898152 | 17125960855160 | 17125961245080 | 17125961246612 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 281 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 16 | 24 | 120064 | 0x7fc391191980 | 0x7fc3908256c0 | 300603 | 300603 | 22458 | 2404832 | 65536 | 213646337 | 2301096 | 0 | 856316140 | 17125961289191 | 17125961245080 | 17125961637720 | 17125961639441 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 284 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 121792 | 0x7fc391191800 | 0x7fc390825700 | 162585 | 162585 | 15341 | 1300688 | 65536 | 101856514 | 1202977 | 0 | 409157968 | 17125961680040 | 17125961637720 | 17125961943640 | 17125961945182 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 287 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 124032 | 0x7fc391191680 | 0x7fc390825740 | 239943 | 239943 | 20012 | 1919552 | 65536 | 147416214 | 1808980 | 0 | 591414424 | 17125961985341 | 17125961943640 | 17125962311479 | 17125962313262 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 290 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 125504 | 0x7fc3937bf500 | 0x7fc390825780 | 161840 | 161840 | 16339 | 1294728 | 65536 | 97731961 | 1188624 | 0 | 392654660 | 17125962362501 | 17125962311479 | 17125962618839 | 17125962620484 |
| 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 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 127488 | 0x7fc3937bf380 | 0x7fc3908257c0 | 297462 | 297462 | 19328 | 2379704 | 65536 | 193198544 | 2280617 | 0 | 774529324 | 17125962666292 | 17125962618839 | 17125963012599 | 17125963014153 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 296 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 129216 | 0x7fc3937bf200 | 0x7fc390825800 | 296150 | 296150 | 20372 | 2369208 | 65536 | 204684431 | 2265713 | 0 | 820471588 | 17125963056132 | 17125963012599 | 17125963401239 | 17125963402762 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 299 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 130944 | 0x7fc3937bf080 | 0x7fc390825840 | 170340 | 170340 | 16426 | 1362728 | 65536 | 100255485 | 1261215 | 0 | 402765012 | 17125963443791 | 17125963401239 | 17125963711479 | 17125963713043 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 302 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 133440 | 0x7fc391191f00 | 0x7fc390825880 | 258402 | 258402 | 20745 | 2067224 | 65536 | 168118060 | 1957558 | 0 | 674219584 | 17125963754262 | 17125963711479 | 17125964074999 | 17125964076583 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 305 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 134912 | 0x7fc391191d80 | 0x7fc3908258c0 | 160600 | 160600 | 15502 | 1284808 | 65536 | 97762268 | 1182505 | 0 | 392778028 | 17125964125922 | 17125964074999 | 17125964377879 | 17125964379345 |
| 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 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 136896 | 0x7fc391191c00 | 0x7fc390825900 | 296344 | 296344 | 20731 | 2370760 | 65536 | 210234393 | 2269243 | 0 | 842695500 | 17125964421384 | 17125964377879 | 17125964773879 | 17125964775394 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 311 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 138880 | 0x7fc391191a80 | 0x7fc390825940 | 294600 | 294600 | 21010 | 2356808 | 65536 | 204491045 | 2252118 | 0 | 819707808 | 17125964817253 | 17125964773879 | 17125965163639 | 17125965165183 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 314 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 140864 | 0x7fc391191900 | 0x7fc390825980 | 178542 | 178542 | 16440 | 1428344 | 65536 | 100907687 | 1321976 | 0 | 405381440 | 17125965205652 | 17125965163639 | 17125965480119 | 17125965481634 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 317 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 143616 | 0x7fc391191780 | 0x7fc3908259c0 | 280086 | 280086 | 22645 | 2240696 | 65536 | 191879761 | 2129699 | 0 | 769267016 | 17125965522483 | 17125965480119 | 17125965858358 | 17125965859914 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 320 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 145344 | 0x7fc391191600 | 0x7fc390825a00 | 160202 | 160202 | 15488 | 1281624 | 65536 | 100939918 | 1181745 | 0 | 405493660 | 17125965908123 | 17125965858358 | 17125966168278 | 17125966169895 |
| 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 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 147584 | 0x7fc3937bf480 | 0x7fc390825a40 | 295760 | 295760 | 21317 | 2366088 | 65536 | 211572263 | 2264263 | 0 | 848021580 | 17125966212864 | 17125966168278 | 17125966568918 | 17125966570384 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 326 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 149568 | 0x7fc3937bf300 | 0x7fc390825a80 | 293482 | 293482 | 20989 | 2347864 | 65536 | 210482097 | 2244928 | 0 | 843665740 | 17125966615463 | 17125966568918 | 17125966965878 | 17125966967353 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 329 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 151552 | 0x7fc3937bf180 | 0x7fc390825ac0 | 185492 | 185492 | 17267 | 1483944 | 65536 | 117858655 | 1380288 | 0 | 473176200 | 17125967007372 | 17125966965878 | 17125967290678 | 17125967292154 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 332 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 154304 | 0x7fc3937bf000 | 0x7fc390825b00 | 298558 | 298558 | 23197 | 2388472 | 65536 | 209366990 | 2282139 | 0 | 839216360 | 17125967333953 | 17125967290678 | 17125967680598 | 17125967682163 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 335 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 156288 | 0x7fc391191e80 | 0x7fc390825b40 | 170260 | 170260 | 16604 | 1362088 | 65536 | 106332798 | 1262552 | 0 | 427072424 | 17125967731402 | 17125967680598 | 17125967992438 | 17125967994055 |
| 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 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 158784 | 0x7fc391191d00 | 0x7fc390825b80 | 297942 | 297942 | 18149 | 2383544 | 65536 | 167488464 | 2258643 | 0 | 671700096 | 17125968036043 | 17125967992438 | 17125968390198 | 17125968391804 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 341 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 161024 | 0x7fc391191b80 | 0x7fc390825bc0 | 296398 | 296398 | 19203 | 2371192 | 65536 | 190134047 | 2258794 | 0 | 762288584 | 17125968433612 | 17125968390198 | 17125968783478 | 17125968785163 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 344 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 163264 | 0x7fc391191a00 | 0x7fc390825c00 | 205786 | 205786 | 18458 | 1646296 | 65536 | 129516748 | 1535560 | 0 | 519821588 | 17125968825861 | 17125968783478 | 17125969115958 | 17125969117423 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 347 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 166528 | 0x7fc391191880 | 0x7fc390825c40 | 339418 | 339418 | 25367 | 2715352 | 65536 | 240243535 | 2605951 | 0 | 962722508 | 17125969158032 | 17125969115958 | 17125969533077 | 17125969552721 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 350 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 168512 | 0x7fc391191700 | 0x7fc390825c80 | 184069 | 184069 | 17114 | 1472560 | 65536 | 105638320 | 1362405 | 0 | 424296676 | 17125969585390 | 17125969533077 | 17125969872277 | 17125969873792 |
| 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 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 171264 | 0x7fc3937bf580 | 0x7fc390825cc0 | 294168 | 294168 | 19782 | 2353352 | 65536 | 196244315 | 2247462 | 0 | 786741992 | 17125969914331 | 17125969872277 | 17125970265237 | 17125970266861 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 356 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 173760 | 0x7fc3937bf400 | 0x7fc390825d00 | 295818 | 295818 | 19904 | 2366552 | 65536 | 182868151 | 2260153 | 0 | 733221976 | 17125970309420 | 17125970265237 | 17125970661877 | 17125970663460 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 359 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 176256 | 0x7fc3937bf280 | 0x7fc390825d40 | 224364 | 224364 | 19332 | 1794920 | 65536 | 150850721 | 1690013 | 0 | 605151024 | 17125970704579 | 17125970661877 | 17125971008597 | 17125971010291 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 362 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 179776 | 0x7fc3937bf100 | 0x7fc390825d80 | 380912 | 380912 | 27477 | 3047304 | 65536 | 266784723 | 2929563 | 0 | 1068898900 | 17125971051029 | 17125971008597 | 17125971453717 | 17125971475768 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 365 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 182272 | 0x7fc391191f80 | 0x7fc390825dc0 | 211269 | 211269 | 18554 | 1690160 | 65536 | 131995943 | 1583293 | 0 | 529738944 | 17125971503527 | 17125971453717 | 17125971799477 | 17125971801419 |
| 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 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 185536 | 0x7fc391191e00 | 0x7fc390825e00 | 305368 | 305368 | 22829 | 2442952 | 65536 | 188865369 | 2320780 | 0 | 757215228 | 17125971842717 | 17125971799477 | 17125972203637 | 17125972223407 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 371 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 188544 | 0x7fc391191c80 | 0x7fc390825e40 | 304878 | 304878 | 22876 | 2439032 | 65536 | 165207637 | 2308200 | 0 | 662584640 | 17125972245726 | 17125972203637 | 17125972611797 | 17125972613426 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 374 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 191552 | 0x7fc391191b00 | 0x7fc390825e80 | 264638 | 264638 | 21240 | 2117112 | 65536 | 188403136 | 2013214 | 0 | 755365800 | 17125972653475 | 17125972611797 | 17125972981716 | 17125972983276 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 377 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 195840 | 0x7fc391191980 | 0x7fc390825ec0 | 461565 | 461565 | 31962 | 3692528 | 65536 | 345443894 | 3577931 | 0 | 1383536616 | 17125973024475 | 17125972981716 | 17125973477876 | 17125973495181 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 380 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 198592 | 0x7fc391191800 | 0x7fc390825f00 | 244408 | 244408 | 20647 | 1955272 | 65536 | 156781362 | 1845676 | 0 | 628886524 | 17125973528540 | 17125973477876 | 17125973842836 | 17125973844452 |
| 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 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 202368 | 0x7fc391191680 | 0x7fc390825f40 | 333021 | 333021 | 22957 | 2664176 | 65536 | 204772368 | 2548690 | 0 | 820862276 | 17125973890860 | 17125973842836 | 17125974269716 | 17125974292579 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 386 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 205888 | 0x7fc3937bf500 | 0x7fc390825f80 | 330782 | 330782 | 23099 | 2646264 | 65536 | 203990127 | 2519797 | 0 | 817726788 | 17125974312969 | 17125974269716 | 17125974693396 | 17125974737397 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 389 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 209408 | 0x7fc3937bf380 | 0x7fc390825fc0 | 305049 | 305049 | 23232 | 2440400 | 65536 | 217103959 | 2337920 | 0 | 870169308 | 17125974747627 | 17125974693396 | 17125975118676 | 17125975120256 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 392 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 214464 | 0x7fc3937bf200 | 0x7fc390826000 | 541285 | 541285 | 35417 | 4330288 | 65536 | 405145736 | 4224782 | 0 | 1622344992 | 17125975162225 | 17125975118676 | 17125975663156 | 17125975680181 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 395 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 217728 | 0x7fc3937bf080 | 0x7fc390826040 | 272535 | 272535 | 21495 | 2180288 | 65536 | 174848382 | 2073731 | 0 | 701154772 | 17125975714770 | 17125975663156 | 17125976050836 | 17125976052350 |
| 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 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 222016 | 0x7fc391191f00 | 0x7fc390826080 | 364471 | 364471 | 24865 | 2915776 | 65536 | 235936850 | 2795363 | 0 | 945529876 | 17125976098529 | 17125976050836 | 17125976498035 | 17125976515067 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 401 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 226048 | 0x7fc391191d80 | 0x7fc3908260c0 | 366501 | 366501 | 28953 | 2932016 | 65536 | 259241159 | 2823404 | 0 | 1038733968 | 17125976541257 | 17125976498035 | 17125976941235 | 17125976959985 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 404 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 230080 | 0x7fc391191c00 | 0x7fc390826100 | 346645 | 346645 | 25290 | 2773168 | 65536 | 249140370 | 2665386 | 0 | 998328752 | 17125976983494 | 17125976941235 | 17125977366195 | 17125977383213 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 407 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 235904 | 0x7fc391191a80 | 0x7fc390826140 | 622867 | 622867 | 39680 | 4982944 | 65536 | 471664700 | 4871158 | 0 | 1888422832 | 17125977408832 | 17125977366195 | 17125977967475 | 17125977988206 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 410 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 239424 | 0x7fc391191900 | 0x7fc390826180 | 302629 | 302629 | 22914 | 2421040 | 65536 | 212499595 | 2315414 | 0 | 851756240 | 17125978018675 | 17125977967475 | 17125978382675 | 17125978384105 |
| 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 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 244224 | 0x7fc391191780 | 0x7fc3908261c0 | 397247 | 397247 | 26594 | 3177984 | 65536 | 273025641 | 3073080 | 0 | 1093879016 | 17125978425774 | 17125978382675 | 17125978845075 | 17125978886911 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 416 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 248768 | 0x7fc391191600 | 0x7fc390826200 | 389663 | 389663 | 27730 | 3117312 | 65536 | 287255451 | 3012386 | 0 | 1150792140 | 17125978898391 | 17125978845075 | 17125979322195 | 17125979339789 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 419 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 253312 | 0x7fc3937bf480 | 0x7fc390826240 | 387075 | 387075 | 27460 | 3096608 | 65536 | 280353620 | 2987071 | 0 | 1123181036 | 17125979364728 | 17125979322195 | 17125979770994 | 17125979788066 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 422 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 8 | 24 | 255552 | 0x7fc3937bf300 | 0x7fc390826280 | 718915 | 718915 | 44072 | 5751328 | 65536 | 535009575 | 5638400 | 0 | 2141778464 | 17125979813616 | 17125979770994 | 17125980432914 | 17125980449448 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 425 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 259840 | 0x7fc3937bf180 | 0x7fc3908262c0 | 363747 | 363747 | 26211 | 2909984 | 65536 | 261733184 | 2802808 | 0 | 1048700392 | 17125980483677 | 17125980432914 | 17125980873394 | 17125980889516 |
| 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 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 265664 | 0x7fc3937bf000 | 0x7fc390826300 | 468919 | 468919 | 31360 | 3751360 | 65536 | 355602728 | 3651396 | 0 | 1424199252 | 17125980916625 | 17125980873394 | 17125981382994 | 17125981399562 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 431 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 271232 | 0x7fc391191e80 | 0x7fc390826340 | 470476 | 470476 | 31210 | 3763816 | 65536 | 350630946 | 3663624 | 0 | 1404305744 | 17125981425131 | 17125981382994 | 17125981898034 | 17125981914868 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 434 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 8 | 24 | 273216 | 0x7fc391191d00 | 0x7fc390826380 | 482917 | 482917 | 33154 | 3863344 | 65536 | 355170706 | 3748273 | 0 | 1422422952 | 17125981939667 | 17125981898034 | 17125982411954 | 17125982430433 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 437 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 8 | 24 | 275712 | 0x7fc391191b80 | 0x7fc3908263c0 | 880512 | 880512 | 52639 | 7044104 | 65536 | 679891715 | 6929160 | 0 | 2721307320 | 17125982454563 | 17125982411954 | 17125983183794 | 17125983204022 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 440 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 280768 | 0x7fc391191a00 | 0x7fc390826400 | 425590 | 425590 | 29340 | 3404728 | 65536 | 317922931 | 3298685 | 0 | 1273462236 | 17125983234651 | 17125983183794 | 17125983663793 | 17125983680108 |
| 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 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 287616 | 0x7fc391191880 | 0x7fc390826440 | 548172 | 548172 | 35190 | 4385384 | 65536 | 412617847 | 4279255 | 0 | 1652252348 | 17125983707318 | 17125983663793 | 17125984226993 | 17125984244043 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 446 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 294208 | 0x7fc391191700 | 0x7fc390826480 | 549602 | 549602 | 35830 | 4396824 | 65536 | 412247916 | 4291949 | 0 | 1650775496 | 17125984270902 | 17125984226993 | 17125984787473 | 17125984804197 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 449 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 8 | 24 | 296960 | 0x7fc3937bf580 | 0x7fc3908264c0 | 562958 | 562958 | 36341 | 4503672 | 65536 | 423171986 | 4392728 | 0 | 1694433528 | 17125984829746 | 17125984787473 | 17125985346353 | 17125985364322 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 452 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 8 | 24 | 299968 | 0x7fc3937bf400 | 0x7fc390826500 | 1041298 | 1041298 | 60638 | 8330392 | 65536 | 809516347 | 8217101 | 0 | 3239806896 | 17125985389461 | 17125985346353 | 17125986223953 | 17125986243617 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 455 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 8 | 24 | 302720 | 0x7fc3937bf280 | 0x7fc390826540 | 720475 | 720475 | 43960 | 5763808 | 65536 | 550162986 | 5655987 | 0 | 2202394216 | 17125986274966 | 17125986224089 | 17125986892889 | 17125986914128 |
| 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 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 305472 | 0x7fc3937bf100 | 0x7fc390826580 | 722927 | 722927 | 43813 | 5783424 | 65536 | 549539928 | 5670262 | 0 | 2199903008 | 17125986935098 | 17125986892889 | 17125987571447 | 17125987588980 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 461 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 308224 | 0x7fc391191f80 | 0x7fc3908265c0 | 721489 | 721489 | 44703 | 5771920 | 65536 | 555698876 | 5662058 | 0 | 2224535612 | 17125987614259 | 17125987571447 | 17125988251607 | 17125988267601 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 464 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 8 | 24 | 310976 | 0x7fc391191e00 | 0x7fc390826600 | 726575 | 726575 | 45063 | 5812608 | 65536 | 554449721 | 5695054 | 0 | 2219539956 | 17125988294030 | 17125988251607 | 17125988921367 | 17125988937962 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 467 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 8 | 24 | 313216 | 0x7fc391191c80 | 0x7fc390826640 | 1366521 | 1366521 | 76978 | 10932176 | 65536 | 1065157712 | 10814985 | 0 | 4262372184 | 17125988963591 | 17125988921367 | 17125990005047 | 17125990022302 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 470 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 8 | 24 | 315968 | 0x7fc391191b00 | 0x7fc390826680 | 1372153 | 1372153 | 77732 | 10977232 | 65536 | 1081382508 | 10844906 | 0 | 4327272448 | 17125990055691 | 17125990005047 | 17125991085687 | 17125991149851 |
| 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 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 318720 | 0x7fc391191980 | 0x7fc3908266c0 | 1371187 | 1371187 | 77414 | 10969504 | 65536 | 1078414736 | 10860913 | 0 | 4315399412 | 17125991161770 | 17125991085687 | 17125992225687 | 17125992287979 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 476 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 321472 | 0x7fc391191800 | 0x7fc390826700 | 1369667 | 1369667 | 76042 | 10957344 | 65536 | 1073820046 | 10845715 | 0 | 4297020948 | 17125992300199 | 17125992225687 | 17125993354167 | 17125993416398 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 479 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 8 | 24 | 324224 | 0x7fc391191680 | 0x7fc390826740 | 1375528 | 1375528 | 77740 | 11004232 | 65536 | 1086217699 | 10884916 | 0 | 4346613368 | 17125993427468 | 17125993354167 | 17125994463607 | 17125994526877 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 482 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 8 | 24 | 326464 | 0x7fc3937bf500 | 0x7fc390826780 | 2664839 | 2664839 | 142381 | 21318720 | 65536 | 2128333752 | 21194475 | 0 | 8515076912 | 17125994539037 | 17125994463607 | 17125996433207 | 17125996497602 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 485 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 8 | 24 | 329216 | 0x7fc3937bf380 | 0x7fc3908267c0 | 2667280 | 2667280 | 142689 | 21338248 | 65536 | 2130273802 | 21222305 | 0 | 8522835980 | 17125996517052 | 17125996433207 | 17125998374007 | 17125998418859 |
| 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 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 331968 | 0x7fc3937bf200 | 0x7fc390826800 | 2670375 | 2670375 | 142367 | 21363008 | 65536 | 2126282473 | 21243060 | 0 | 8506870484 | 17125998431398 | 17125998374007 | 17126000353367 | 17126000420323 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 491 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 334720 | 0x7fc3937bf080 | 0x7fc390826840 | 2667206 | 2667206 | 142259 | 21337656 | 65536 | 2129658288 | 21226684 | 0 | 8520373344 | 17126000431313 | 17126000353367 | 17126002349047 | 17126002419107 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 494 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 8 | 24 | 337472 | 0x7fc391191f00 | 0x7fc390826880 | 2673279 | 2673279 | 142440 | 21386240 | 65536 | 2132300589 | 21261596 | 0 | 8530944424 | 17126002432077 | 17126002349047 | 17126004307287 | 17126004378233 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 497 | 194332 | 194332 | 4194304 | 256 | 0 | 0 | 8 | 24 | 0 | 0x7fc391191d80 | 0x7fc3908268c0 | 5255683 | 5255683 | 273645 | 42045472 | 65536 | 4231549371 | 41928518 | 0 | 16927939052 | 17126004389442 | 17126004307287 | 17126007939287 | 17126008009862 |