40 KiB
40 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | SQ_INSTS_LDS | SQ_INST_LEVEL_LDS | SQ_ACCUM_PREV_HIRES | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBuffer.kd | 0 | 0 | 0 | 896318 | 896323 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7f4214204180 | 0 | 0 | 0 | 12075848456376772 | 12075848700835421 | 12075848701157819 | 12075848701272961 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 896318 | 896323 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7f4214235100 | 0 | 0 | 0 | 12075848716121136 | 12075848716425626 | 12075848716432345 | 12075848716441912 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7f431ff59900 | 0x7f4214235140 | 0 | 0 | 0 | 12075848716497545 | 12075848716720824 | 12075848716854103 | 12075848716856793 |
| 5 | 3 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 6 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7f431ff59800 | 0x7f4214235180 | 0 | 0 | 0 | 12075848716924839 | 12075848717106102 | 12075848717359381 | 12075848717433144 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7f431ff59700 | 0x7f42142351c0 | 0 | 0 | 0 | 12075848717466596 | 12075848717652180 | 12075848717908178 | 12075848717978968 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7f431ff59600 | 0x7f4214235200 | 0 | 0 | 0 | 12075848718013853 | 12075848718198097 | 12075848718329296 | 12075848718332065 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7f431ff59500 | 0x7f4214235240 | 0 | 0 | 0 | 12075848718380004 | 12075848718557135 | 12075848718687855 | 12075848718690581 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7f431ff59400 | 0x7f4214235280 | 0 | 0 | 0 | 12075848718763446 | 12075848718932334 | 12075848719063373 | 12075848719066259 |
| 10 | 8 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 16 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7f431ff59300 | 0x7f42142352c0 | 0 | 0 | 0 | 12075848719114629 | 12075848719293292 | 12075848719548811 | 12075848719592197 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7f431ff59a00 | 0x7f4214235300 | 0 | 0 | 0 | 12075848719619648 | 12075848719800489 | 12075848720051848 | 12075848720095251 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7f431ff59900 | 0x7f4214235340 | 0 | 0 | 0 | 12075848720118775 | 12075848720320007 | 12075848720448646 | 12075848720451233 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7f431ff59800 | 0x7f4214235380 | 0 | 0 | 0 | 12075848720498250 | 12075848720679525 | 12075848720816485 | 12075848720819017 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7f431ff59700 | 0x7f42142353c0 | 0 | 0 | 0 | 12075848720879359 | 12075848721054564 | 12075848721188803 | 12075848721191739 |
| 15 | 13 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 26 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7f431ff59600 | 0x7f4214235400 | 0 | 0 | 0 | 12075848721238787 | 12075848721416642 | 12075848721674401 | 12075848721743665 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7f431ff59500 | 0x7f4214235440 | 0 | 0 | 0 | 12075848721771226 | 12075848721951039 | 12075848722207358 | 12075848722277727 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7f431ff59400 | 0x7f4214235480 | 0 | 0 | 0 | 12075848722305479 | 12075848722490717 | 12075848722621756 | 12075848722624612 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7f431ff59300 | 0x7f42142354c0 | 0 | 0 | 0 | 12075848722672832 | 12075848722844635 | 12075848722980634 | 12075848722983529 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7f431ff59a00 | 0x7f4214235500 | 0 | 0 | 0 | 12075848723048520 | 12075848723220313 | 12075848723353113 | 12075848723355971 |
| 20 | 18 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 36 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7f431ff59900 | 0x7f4214235540 | 0 | 0 | 0 | 12075848723407357 | 12075848723574552 | 12075848723824310 | 12075848723868815 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7f431ff59800 | 0x7f4214235580 | 0 | 0 | 0 | 12075848723892308 | 12075848724088309 | 12075848724341588 | 12075848724385775 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7f431ff59700 | 0x7f42142355c0 | 0 | 0 | 0 | 12075848724408157 | 12075848724595987 | 12075848724727506 | 12075848724729995 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7f431ff59600 | 0x7f4214235600 | 0 | 0 | 0 | 12075848724777263 | 12075848724943345 | 12075848725081264 | 12075848725083883 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7f431ff59500 | 0x7f4214235640 | 0 | 0 | 0 | 12075848725146679 | 12075848725318223 | 12075848725447023 | 12075848725449843 |
| 25 | 23 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 46 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7f431ff59400 | 0x7f4214235680 | 0 | 0 | 0 | 12075848725497521 | 12075848725671982 | 12075848725922860 | 12075848725992612 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7f431ff59300 | 0x7f42142356c0 | 0 | 0 | 0 | 12075848726026124 | 12075848726207019 | 12075848726458378 | 12075848726528768 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7f431ff59a00 | 0x7f4214235700 | 0 | 0 | 0 | 12075848726555798 | 12075848726732937 | 12075848726865096 | 12075848726867708 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7f431ff59900 | 0x7f4214235740 | 0 | 0 | 0 | 12075848726914885 | 12075848727095175 | 12075848727229254 | 12075848727232055 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7f431ff59800 | 0x7f4214235780 | 0 | 0 | 0 | 12075848727292357 | 12075848727462373 | 12075848727590853 | 12075848727593627 |
| 30 | 28 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 56 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7f431ff59700 | 0x7f42142357c0 | 0 | 0 | 0 | 12075848727642137 | 12075848727808451 | 12075848728060930 | 12075848728130986 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7f431ff59600 | 0x7f4214235800 | 0 | 0 | 0 | 12075848728155832 | 12075848728346049 | 12075848728595648 | 12075848728665669 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7f431ff59500 | 0x7f4214235840 | 0 | 0 | 0 | 12075848728692128 | 12075848728875806 | 12075848729005886 | 12075848729009017 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7f431ff59400 | 0x7f4214235880 | 0 | 0 | 0 | 12075848729057888 | 12075848729235485 | 12075848729371164 | 12075848729374006 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7f431ff59300 | 0x7f42142358c0 | 0 | 0 | 0 | 12075848729434518 | 12075848729599323 | 12075848729727322 | 12075848729730047 |
| 35 | 33 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 66 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7f431ff59a00 | 0x7f4214235900 | 0 | 0 | 0 | 12075848729776734 | 12075848729948761 | 12075848730199160 | 12075848730269259 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7f431ff59900 | 0x7f4214235940 | 0 | 0 | 0 | 12075848730296640 | 12075848730480119 | 12075848730731638 | 12075848730801619 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7f431ff59800 | 0x7f4214235980 | 0 | 0 | 0 | 12075848730827587 | 12075848731008276 | 12075848731145396 | 12075848731148654 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7f431ff59700 | 0x7f42142359c0 | 0 | 0 | 0 | 12075848731199598 | 12075848731366355 | 12075848731505394 | 12075848731508232 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7f431ff59600 | 0x7f4214235a00 | 0 | 0 | 0 | 12075848731569255 | 12075848731734673 | 12075848731867792 | 12075848731870716 |
| 40 | 38 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 76 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7f431ff59500 | 0x7f4214235a40 | 0 | 0 | 0 | 12075848731919867 | 12075848732101711 | 12075848732361710 | 12075848732431718 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7f431ff59400 | 0x7f4214235a80 | 0 | 0 | 0 | 12075848732456084 | 12075848732643469 | 12075848732902507 | 12075848732972082 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7f431ff59300 | 0x7f4214235ac0 | 0 | 0 | 0 | 12075848732999383 | 12075848733189706 | 12075848733325865 | 12075848733328916 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7f431ff59a00 | 0x7f4214235b00 | 0 | 0 | 0 | 12075848733378418 | 12075848733541864 | 12075848733678344 | 12075848733680990 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7f431ff59900 | 0x7f4214235b40 | 0 | 0 | 0 | 12075848733741633 | 12075848733906823 | 12075848734033542 | 12075848734036411 |
| 45 | 43 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 86 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7f431ff59800 | 0x7f4214235b80 | 0 | 0 | 0 | 12075848734085422 | 12075848734257381 | 12075848734519460 | 12075848734589478 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7f431ff59700 | 0x7f4214235bc0 | 0 | 0 | 0 | 12075848734614876 | 12075848734798978 | 12075848735056097 | 12075848735127087 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7f431ff59600 | 0x7f4214235c00 | 0 | 0 | 0 | 12075848735151242 | 12075848735333536 | 12075848735464415 | 12075848735467350 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7f431ff59500 | 0x7f4214235c40 | 0 | 0 | 0 | 12075848735516030 | 12075848735687774 | 12075848735825373 | 12075848735828200 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7f431ff59400 | 0x7f4214235c80 | 0 | 0 | 0 | 12075848735889795 | 12075848736072412 | 12075848736203772 | 12075848736206484 |
| 50 | 48 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 96 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7f431ff59300 | 0x7f4214235cc0 | 0 | 0 | 0 | 12075848736255264 | 12075848736431291 | 12075848736693369 | 12075848736763569 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7f431ff59a00 | 0x7f4214235d00 | 0 | 0 | 0 | 12075848736787784 | 12075848736969208 | 12075848737222167 | 12075848737293013 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7f431ff59900 | 0x7f4214235d40 | 0 | 0 | 0 | 12075848737319913 | 12075848737499765 | 12075848737630325 | 12075848737633175 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7f431ff59800 | 0x7f4214235d80 | 0 | 0 | 0 | 12075848737683378 | 12075848737850004 | 12075848737991923 | 12075848737994647 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7f431ff59700 | 0x7f4214235dc0 | 0 | 0 | 0 | 12075848738056942 | 12075848738222482 | 12075848738353361 | 12075848738356068 |
| 55 | 53 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 106 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7f431ff59600 | 0x7f4214235e00 | 0 | 0 | 0 | 12075848738404458 | 12075848738569040 | 12075848738873519 | 12075848738916841 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7f431ff59500 | 0x7f4214235e40 | 0 | 0 | 0 | 12075848738943320 | 12075848739135918 | 12075848739391596 | 12075848739461813 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7f431ff59400 | 0x7f4214235e80 | 0 | 0 | 0 | 12075848739490797 | 12075848739666475 | 12075848739799915 | 12075848739802967 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7f431ff59300 | 0x7f4214235ec0 | 0 | 0 | 0 | 12075848739850826 | 12075848740027433 | 12075848740168393 | 12075848740171232 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7f431ff59a00 | 0x7f4214235f00 | 0 | 0 | 0 | 12075848740232967 | 12075848740399432 | 12075848740535911 | 12075848740538675 |
| 60 | 58 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 116 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7f431ff59900 | 0x7f4214235f40 | 0 | 0 | 0 | 12075848740586393 | 12075848740759590 | 12075848741021349 | 12075848741091472 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7f431ff59800 | 0x7f4214235f80 | 0 | 0 | 0 | 12075848741116779 | 12075848741300547 | 12075848741549826 | 12075848741619463 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7f431ff59700 | 0x7f4214235fc0 | 0 | 0 | 0 | 12075848741645482 | 12075848741834465 | 12075848741965504 | 12075848741968281 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7f431ff59600 | 0x7f4214236000 | 0 | 0 | 0 | 12075848742024827 | 12075848742199743 | 12075848742339102 | 12075848742341986 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7f431ff59500 | 0x7f4214236040 | 0 | 0 | 0 | 12075848742404192 | 12075848742567581 | 12075848742697821 | 12075848742700593 |
| 65 | 63 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 126 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7f431ff59400 | 0x7f4214236080 | 0 | 0 | 0 | 12075848742751928 | 12075848742916220 | 12075848743175418 | 12075848743247349 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7f431ff59300 | 0x7f42142360c0 | 0 | 0 | 0 | 12075848743272265 | 12075848743455737 | 12075848743704536 | 12075848743774498 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7f431ff59a00 | 0x7f4214236100 | 0 | 0 | 0 | 12075848743801278 | 12075848743979575 | 12075848744118134 | 12075848744121323 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7f431ff59900 | 0x7f4214236140 | 0 | 0 | 0 | 12075848744172278 | 12075848744349493 | 12075848744493012 | 12075848744496099 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7f431ff59800 | 0x7f4214236180 | 0 | 0 | 0 | 12075848744557143 | 12075848744718611 | 12075848744854131 | 12075848744856810 |
| 70 | 68 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 136 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7f431ff59700 | 0x7f42142361c0 | 0 | 0 | 0 | 12075848744905881 | 12075848745081649 | 12075848745344208 | 12075848745396723 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7f431ff59600 | 0x7f4214236200 | 0 | 0 | 0 | 12075848745423122 | 12075848745604207 | 12075848745861326 | 12075848745911089 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7f431ff59500 | 0x7f4214236240 | 0 | 0 | 0 | 12075848745940824 | 12075848746125164 | 12075848746253484 | 12075848746256591 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7f431ff59400 | 0x7f4214236280 | 0 | 0 | 0 | 12075848746305392 | 12075848746474763 | 12075848746626442 | 12075848746629214 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7f431ff59300 | 0x7f42142362c0 | 0 | 0 | 0 | 12075848746708842 | 12075848746875081 | 12075848747010440 | 12075848747013608 |
| 75 | 73 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 146 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7f431ff59a00 | 0x7f4214236300 | 0 | 0 | 0 | 12075848747064142 | 12075848747230439 | 12075848747495398 | 12075848747547500 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7f431ff59900 | 0x7f4214236340 | 0 | 0 | 0 | 12075848747574671 | 12075848747752997 | 12075848748005636 | 12075848748056536 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7f431ff59800 | 0x7f4214236380 | 0 | 0 | 0 | 12075848748082675 | 12075848748267234 | 12075848748396354 | 12075848748399153 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7f431ff59700 | 0x7f42142363c0 | 0 | 0 | 0 | 12075848748447984 | 12075848748612513 | 12075848748770432 | 12075848748773348 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7f431ff59600 | 0x7f4214236400 | 0 | 0 | 0 | 12075848748834743 | 12075848748997951 | 12075848749130430 | 12075848749133648 |
| 80 | 78 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 156 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7f431ff59500 | 0x7f4214236440 | 0 | 0 | 0 | 12075848749182499 | 12075848749355869 | 12075848749616348 | 12075848749644828 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7f431ff59400 | 0x7f4214236480 | 0 | 0 | 0 | 12075848749684682 | 12075848749846107 | 12075848750103546 | 12075848750130340 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7f431ff59300 | 0x7f42142364c0 | 0 | 0 | 0 | 12075848750173511 | 12075848750337144 | 12075848750475064 | 12075848750478007 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7f431ff59a00 | 0x7f4214236500 | 0 | 0 | 0 | 12075848750526176 | 12075848750699703 | 12075848750865302 | 12075848750868162 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7f431ff59900 | 0x7f4214236540 | 0 | 0 | 0 | 12075848750929886 | 12075848751098581 | 12075848751230900 | 12075848751234142 |
| 85 | 83 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 166 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7f431ff59800 | 0x7f4214236580 | 0 | 0 | 0 | 12075848751281229 | 12075848751451219 | 12075848751713298 | 12075848751736105 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7f431ff59700 | 0x7f42142365c0 | 0 | 0 | 0 | 12075848751778023 | 12075848751940657 | 12075848752192976 | 12075848752220435 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7f431ff59600 | 0x7f4214236600 | 0 | 0 | 0 | 12075848752264507 | 12075848752431535 | 12075848752565454 | 12075848752568752 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7f431ff59500 | 0x7f4214236640 | 0 | 0 | 0 | 12075848752617002 | 12075848752788173 | 12075848752962252 | 12075848752965139 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7f431ff59400 | 0x7f4214236680 | 0 | 0 | 0 | 12075848753034608 | 12075848753197931 | 12075848753326730 | 12075848753329576 |
| 90 | 88 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 176 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7f431ff59300 | 0x7f42142366c0 | 0 | 0 | 0 | 12075848753382524 | 12075848753545609 | 12075848753803688 | 12075848753829786 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7f431ff59a00 | 0x7f4214236700 | 0 | 0 | 0 | 12075848753877564 | 12075848754050087 | 12075848754304486 | 12075848754333802 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7f431ff59900 | 0x7f4214236740 | 0 | 0 | 0 | 12075848754372815 | 12075848754536645 | 12075848754674724 | 12075848754677651 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7f431ff59800 | 0x7f4214236780 | 0 | 0 | 0 | 12075848754723937 | 12075848754897763 | 12075848755081602 | 12075848755084998 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7f431ff59700 | 0x7f42142367c0 | 0 | 0 | 0 | 12075848755146853 | 12075848755315361 | 12075848755452640 | 12075848755455447 |
| 95 | 93 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 186 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7f431ff59600 | 0x7f4214236800 | 0 | 0 | 0 | 12075848755501593 | 12075848755673919 | 12075848755941598 | 12075848755966847 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7f431ff59500 | 0x7f4214236840 | 0 | 0 | 0 | 12075848756015959 | 12075848756180957 | 12075848756435036 | 12075848756461947 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7f431ff59400 | 0x7f4214236880 | 0 | 0 | 0 | 12075848756503545 | 12075848756667994 | 12075848756806234 | 12075848756809233 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7f431ff59300 | 0x7f42142368c0 | 0 | 0 | 0 | 12075848756857853 | 12075848757035993 | 12075848757227352 | 12075848757255833 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7f431ff59a00 | 0x7f4214236900 | 0 | 0 | 0 | 12075848757293002 | 12075848757457591 | 12075848757599830 | 12075848757602878 |
| 100 | 98 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 196 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7f431ff59900 | 0x7f4214236940 | 0 | 0 | 0 | 12075848757657209 | 12075848757821109 | 12075848758135347 | 12075848758162408 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7f431ff59800 | 0x7f4214236980 | 0 | 0 | 0 | 12075848758213112 | 12075848758381426 | 12075848758643665 | 12075848758670933 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7f431ff59700 | 0x7f42142369c0 | 0 | 0 | 0 | 12075848758721607 | 12075848758889264 | 12075848759030383 | 12075848759033276 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7f431ff59600 | 0x7f4214236a00 | 0 | 0 | 0 | 12075848759085112 | 12075848759259182 | 12075848759468621 | 12075848759495956 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7f431ff59500 | 0x7f4214236a40 | 0 | 0 | 0 | 12075848759549125 | 12075848759716460 | 12075848759853419 | 12075848759856436 |
| 105 | 103 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 206 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7f431ff59400 | 0x7f4214236a80 | 0 | 0 | 0 | 12075848759905217 | 12075848760085738 | 12075848760392937 | 12075848760419813 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7f431ff59300 | 0x7f4214236ac0 | 0 | 0 | 0 | 12075848760461009 | 12075848760627016 | 12075848760892454 | 12075848760916997 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7f431ff59a00 | 0x7f4214236b00 | 0 | 0 | 0 | 12075848760958624 | 12075848761128293 | 12075848761261093 | 12075848761264252 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7f431ff59900 | 0x7f4214236b40 | 0 | 0 | 0 | 12075848761311580 | 12075848761481412 | 12075848761710050 | 12075848761735448 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7f431ff59800 | 0x7f4214236b80 | 0 | 0 | 0 | 12075848761791592 | 12075848761954689 | 12075848762094689 | 12075848762097882 |
| 110 | 108 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 216 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7f431ff59700 | 0x7f4214236bc0 | 0 | 0 | 0 | 12075848762145560 | 12075848762311168 | 12075848762642686 | 12075848762667610 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7f431ff59600 | 0x7f4214236c00 | 0 | 0 | 0 | 12075848762709468 | 12075848762871325 | 12075848763127804 | 12075848763157240 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7f431ff59500 | 0x7f4214236c40 | 0 | 0 | 0 | 12075848763198156 | 12075848763360923 | 12075848763503802 | 12075848763506720 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7f431ff59400 | 0x7f4214236c80 | 0 | 0 | 0 | 12075848763554739 | 12075848763726474 | 12075848763970794 | 12075848763998814 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7f431ff59300 | 0x7f4214236cc0 | 0 | 0 | 0 | 12075848764057313 | 12075848764224232 | 12075848764364551 | 12075848764366518 |
| 115 | 113 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 226 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7f431ff59a00 | 0x7f4214236d00 | 0 | 0 | 0 | 12075848764414256 | 12075848764586950 | 12075848764963749 | 12075848764988213 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7f431ff59900 | 0x7f4214236d40 | 0 | 0 | 0 | 12075848765043927 | 12075848765207588 | 12075848765469347 | 12075848765494744 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7f431ff59800 | 0x7f4214236d80 | 0 | 0 | 0 | 12075848765544377 | 12075848765709986 | 12075848765850626 | 12075848765852690 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7f431ff59700 | 0x7f4214236dc0 | 0 | 0 | 0 | 12075848765900488 | 12075848766074145 | 12075848766353824 | 12075848766382083 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7f431ff59600 | 0x7f4214236e00 | 0 | 0 | 0 | 12075848766434200 | 12075848766602303 | 12075848766740063 | 12075848766742022 |
| 120 | 118 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 236 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7f431ff59500 | 0x7f4214236e40 | 0 | 0 | 0 | 12075848766788369 | 12075848766959102 | 12075848767384380 | 12075848767413310 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7f431ff59400 | 0x7f4214236e80 | 0 | 0 | 0 | 12075848767454386 | 12075848767622459 | 12075848767887418 | 12075848767910484 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7f431ff59300 | 0x7f4214236ec0 | 0 | 0 | 0 | 12075848767953454 | 12075848768117658 | 12075848768256697 | 12075848768258851 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7f431ff59a00 | 0x7f4214236f00 | 0 | 0 | 0 | 12075848768307051 | 12075848768480856 | 12075848768795895 | 12075848768820064 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7f431ff59900 | 0x7f4214236f40 | 0 | 0 | 0 | 12075848768881469 | 12075848769054454 | 12075848769207094 | 12075848769209719 |
| 125 | 123 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 246 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7f431ff59800 | 0x7f4214236f80 | 0 | 0 | 0 | 12075848769257217 | 12075848769442613 | 12075848769959251 | 12075848769984939 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7f431ff59700 | 0x7f4214236fc0 | 0 | 0 | 0 | 12075848770031466 | 12075848770196850 | 12075848770497649 | 12075848770522528 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7f431ff59600 | 0x7f4214237000 | 0 | 0 | 0 | 12075848770569926 | 12075848770735728 | 12075848770889808 | 12075848770891825 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7f431ff59500 | 0x7f4214237040 | 0 | 0 | 0 | 12075848770938802 | 12075848771117967 | 12075848771504365 | 12075848771530862 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7f431ff59400 | 0x7f4214237080 | 0 | 0 | 0 | 12075848771584612 | 12075848771751564 | 12075848771926924 | 12075848771929313 |
| 130 | 128 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 256 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7f431ff59300 | 0x7f42142370c0 | 0 | 0 | 0 | 12075848771975819 | 12075848772155083 | 12075848772765321 | 12075848772791054 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7f431ff59a00 | 0x7f4214237100 | 0 | 0 | 0 | 12075848772836599 | 12075848773000040 | 12075848773328999 | 12075848773357397 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7f431ff59900 | 0x7f4214237140 | 0 | 0 | 0 | 12075848773402481 | 12075848773566278 | 12075848773746437 | 12075848773748444 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7f431ff59800 | 0x7f4214237180 | 0 | 0 | 0 | 12075848773797084 | 12075848773979236 | 12075848774435075 | 12075848774460948 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7f431ff59700 | 0x7f42142371c0 | 0 | 0 | 0 | 12075848774515740 | 12075848774684834 | 12075848774886593 | 12075848774910052 |
| 135 | 133 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 266 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7f431ff59600 | 0x7f4214237200 | 0 | 0 | 0 | 12075848774953463 | 12075848775118752 | 12075848775822270 | 12075848775851682 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7f431ff59500 | 0x7f4214237240 | 0 | 0 | 0 | 12075848775891186 | 12075848776072829 | 12075848776473147 | 12075848776498625 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7f431ff59400 | 0x7f4214237280 | 0 | 0 | 0 | 12075848776539601 | 12075848776704187 | 12075848776907066 | 12075848776926560 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7f431ff59300 | 0x7f42142372c0 | 0 | 0 | 0 | 12075848776977805 | 12075848777151705 | 12075848777678743 | 12075848777706620 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7f431ff59a00 | 0x7f4214237300 | 0 | 0 | 0 | 12075848777761702 | 12075848777928182 | 12075848778186741 | 12075848778211778 |
| 140 | 138 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 276 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7f431ff59900 | 0x7f4214237340 | 0 | 0 | 0 | 12075848778260639 | 12075848778430260 | 12075848779228977 | 12075848779256069 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7f431ff59800 | 0x7f4214237380 | 0 | 0 | 0 | 12075848779297005 | 12075848779461937 | 12075848779883055 | 12075848779908191 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7f431ff59700 | 0x7f42142373c0 | 0 | 0 | 0 | 12075848779955058 | 12075848780128174 | 12075848780354253 | 12075848780384426 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7f431ff59600 | 0x7f4214237400 | 0 | 0 | 0 | 12075848780427637 | 12075848780592812 | 12075848781202410 | 12075848781230258 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7f431ff59500 | 0x7f4214237440 | 0 | 0 | 0 | 12075848781288727 | 12075848781458569 | 12075848781729608 | 12075848781755003 |
| 145 | 143 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 286 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7f431ff59400 | 0x7f4214237480 | 0 | 0 | 0 | 12075848781797172 | 12075848781959528 | 12075848782944964 | 12075848783024132 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7f431ff59300 | 0x7f42142374c0 | 0 | 0 | 0 | 12075848783053497 | 12075848783239683 | 12075848783754721 | 12075848783823908 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7f431ff59a00 | 0x7f4214237500 | 0 | 0 | 0 | 12075848783852652 | 12075848784036160 | 12075848784308639 | 12075848784379090 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7f431ff59900 | 0x7f4214237540 | 0 | 0 | 0 | 12075848784406711 | 12075848784589278 | 12075848785327515 | 12075848785396892 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7f431ff59800 | 0x7f4214237580 | 0 | 0 | 0 | 12075848785434552 | 12075848785600794 | 12075848785919033 | 12075848785961952 |
| 150 | 148 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 296 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7f431ff59700 | 0x7f42142375c0 | 0 | 0 | 0 | 12075848785992599 | 12075848786184952 | 12075848787354548 | 12075848787424580 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7f431ff59600 | 0x7f4214237600 | 0 | 0 | 0 | 12075848787455838 | 12075848787643027 | 12075848788254225 | 12075848788323270 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7f431ff59500 | 0x7f4214237640 | 0 | 0 | 0 | 12075848788346624 | 12075848788540784 | 12075848788859503 | 12075848788928094 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7f431ff59400 | 0x7f4214237680 | 0 | 0 | 0 | 12075848788955515 | 12075848789146702 | 12075848790025418 | 12075848790096496 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7f431ff59300 | 0x7f42142376c0 | 0 | 0 | 0 | 12075848790138454 | 12075848790304937 | 12075848790738376 | 12075848790808138 |
| 155 | 153 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 306 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7f431ff59a00 | 0x7f4214237700 | 0 | 0 | 0 | 12075848790839737 | 12075848791022055 | 12075848792571809 | 12075848792643329 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7f431ff59900 | 0x7f4214237740 | 0 | 0 | 0 | 12075848792675188 | 12075848792859808 | 12075848793655005 | 12075848793725400 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7f431ff59800 | 0x7f4214237780 | 0 | 0 | 0 | 12075848793749535 | 12075848793933724 | 12075848794348123 | 12075848794417376 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7f431ff59700 | 0x7f42142377c0 | 0 | 0 | 0 | 12075848794443695 | 12075848794624282 | 12075848795783158 | 12075848795853334 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7f431ff59600 | 0x7f4214237800 | 0 | 0 | 0 | 12075848795892708 | 12075848796059957 | 12075848796846514 | 12075848796917693 |
| 160 | 158 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 316 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7f431ff59500 | 0x7f4214237840 | 0 | 0 | 0 | 12075848796948650 | 12075848797143313 | 12075848800194502 | 12075848800267598 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7f431ff59400 | 0x7f4214237880 | 0 | 0 | 0 | 12075848800295921 | 12075848800487140 | 12075848802029215 | 12075848802099673 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7f431ff59300 | 0x7f42142378c0 | 0 | 0 | 0 | 12075848802132684 | 12075848802314334 | 12075848803103771 | 12075848803174240 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7f431ff59a00 | 0x7f4214237900 | 0 | 0 | 0 | 12075848803201521 | 12075848803389370 | 12075848805670802 | 12075848805741221 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7f431ff59900 | 0x7f4214237940 | 0 | 0 | 0 | 12075848805786866 | 12075848805953521 | 12075848807489515 | 12075848807560782 |
| 165 | 163 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 326 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7f431ff59800 | 0x7f4214237980 | 0 | 0 | 0 | 12075848807592982 | 12075848807773674 | 12075848813827412 | 12075848813897669 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7f431ff59700 | 0x7f42142379c0 | 0 | 0 | 0 | 12075848813930590 | 12075848814121491 | 12075848817164520 | 12075848817238688 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7f431ff59600 | 0x7f4214237a00 | 0 | 0 | 0 | 12075848817267742 | 12075848817456359 | 12075848818996194 | 12075848819066535 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 896318 | 896323 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7f431ff59500 | 0x7f4214237a40 | 0 | 0 | 0 | 12075848819097954 | 12075848819283392 | 12075848823811376 | 12075848823881474 |