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 | 875773 | 875778 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7efd0fa04180 | 0 | 0 | 0 | 12075446198050940 | 12075446442424062 | 12075446442747100 | 12075446442857662 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 875773 | 875778 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7efd0fa35100 | 0 | 0 | 0 | 12075446457398255 | 12075446457697741 | 12075446457704301 | 12075446457709524 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7efe3faf3900 | 0x7efd0fa35140 | 0 | 0 | 0 | 12075446457773643 | 12075446457993100 | 12075446458130539 | 12075446458134884 |
| 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 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7efe3faf3800 | 0x7efd0fa35180 | 0 | 0 | 0 | 12075446458208241 | 12075446458381098 | 12075446458632776 | 12075446458701497 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7efe3faf3700 | 0x7efd0fa351c0 | 0 | 0 | 0 | 12075446458730321 | 12075446458919815 | 12075446459173893 | 12075446459243465 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7efe3faf3600 | 0x7efd0fa35200 | 0 | 0 | 0 | 12075446459272058 | 12075446459455172 | 12075446459593571 | 12075446459597212 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7efe3faf3500 | 0x7efd0fa35240 | 0 | 0 | 0 | 12075446459647926 | 12075446459808450 | 12075446459945409 | 12075446459949016 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7efe3faf3400 | 0x7efd0fa35280 | 0 | 0 | 0 | 12075446460032160 | 12075446460196768 | 12075446460329407 | 12075446460333300 |
| 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 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7efe3faf3300 | 0x7efd0fa352c0 | 0 | 0 | 0 | 12075446460377302 | 12075446460556926 | 12075446460814845 | 12075446460856252 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7efe3faf3a00 | 0x7efd0fa35300 | 0 | 0 | 0 | 12075446460882020 | 12075446461068764 | 12075446461327482 | 12075446461369135 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7efe3faf3900 | 0x7efd0fa35340 | 0 | 0 | 0 | 12075446461396947 | 12075446461589241 | 12075446461722680 | 12075446461726479 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7efe3faf3800 | 0x7efd0fa35380 | 0 | 0 | 0 | 12075446461775320 | 12075446461950039 | 12075446462088598 | 12075446462092439 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7efe3faf3700 | 0x7efd0fa353c0 | 0 | 0 | 0 | 12075446462156067 | 12075446462321557 | 12075446462456596 | 12075446462460273 |
| 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 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7efe3faf3600 | 0x7efd0fa35400 | 0 | 0 | 0 | 12075446462509094 | 12075446462673075 | 12075446462927634 | 12075446462994105 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7efe3faf3500 | 0x7efd0fa35440 | 0 | 0 | 0 | 12075446463023369 | 12075446463205232 | 12075446463460111 | 12075446463528929 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7efe3faf3400 | 0x7efd0fa35480 | 0 | 0 | 0 | 12075446463551541 | 12075446463734190 | 12075446463867149 | 12075446463870784 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7efe3faf3300 | 0x7efd0fa354c0 | 0 | 0 | 0 | 12075446463919925 | 12075446464101068 | 12075446464238667 | 12075446464242735 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7efe3faf3a00 | 0x7efd0fa35500 | 0 | 0 | 0 | 12075446464307376 | 12075446464468906 | 12075446464599785 | 12075446464603576 |
| 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 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7efe3faf3900 | 0x7efd0fa35540 | 0 | 0 | 0 | 12075446464653188 | 12075446464825544 | 12075446465078663 | 12075446465147166 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7efe3faf3800 | 0x7efd0fa35580 | 0 | 0 | 0 | 12075446465171031 | 12075446465359301 | 12075446465611300 | 12075446465653627 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7efe3faf3700 | 0x7efd0fa355c0 | 0 | 0 | 0 | 12075446465676841 | 12075446465857699 | 12075446465988258 | 12075446465992006 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7efe3faf3600 | 0x7efd0fa35600 | 0 | 0 | 0 | 12075446466043853 | 12075446466209217 | 12075446466344896 | 12075446466348850 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7efe3faf3500 | 0x7efd0fa35640 | 0 | 0 | 0 | 12075446466410013 | 12075446466573055 | 12075446466704574 | 12075446466708428 |
| 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 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7efe3faf3400 | 0x7efd0fa35680 | 0 | 0 | 0 | 12075446466759372 | 12075446466922493 | 12075446467184572 | 12075446467253801 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7efe3faf3300 | 0x7efd0fa356c0 | 0 | 0 | 0 | 12075446467281653 | 12075446467470330 | 12075446467726649 | 12075446467793514 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7efe3faf3a00 | 0x7efd0fa35700 | 0 | 0 | 0 | 12075446467820154 | 12075446467998967 | 12075446468126967 | 12075446468131002 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7efe3faf3900 | 0x7efd0fa35740 | 0 | 0 | 0 | 12075446468179111 | 12075446468351446 | 12075446468485205 | 12075446468489047 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7efe3faf3800 | 0x7efd0fa35780 | 0 | 0 | 0 | 12075446468551142 | 12075446468714324 | 12075446468848083 | 12075446468851851 |
| 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 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7efe3faf3700 | 0x7efd0fa357c0 | 0 | 0 | 0 | 12075446468899871 | 12075446469080882 | 12075446469341041 | 12075446469408346 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7efe3faf3600 | 0x7efd0fa35800 | 0 | 0 | 0 | 12075446469431819 | 12075446469618959 | 12075446469875118 | 12075446469943089 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7efe3faf3500 | 0x7efd0fa35840 | 0 | 0 | 0 | 12075446469967104 | 12075446470164076 | 12075446470295596 | 12075446470299532 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7efe3faf3400 | 0x7efd0fa35880 | 0 | 0 | 0 | 12075446470343724 | 12075446470517674 | 12075446470653674 | 12075446470657577 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7efe3faf3300 | 0x7efd0fa358c0 | 0 | 0 | 0 | 12075446470720594 | 12075446470883432 | 12075446471015912 | 12075446471019720 |
| 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 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7efe3faf3a00 | 0x7efd0fa35900 | 0 | 0 | 0 | 12075446471064634 | 12075446471238791 | 12075446471500549 | 12075446471568400 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7efe3faf3900 | 0x7efd0fa35940 | 0 | 0 | 0 | 12075446471595180 | 12075446471772548 | 12075446472031906 | 12075446472074851 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7efe3faf3800 | 0x7efd0fa35980 | 0 | 0 | 0 | 12075446472099136 | 12075446472287265 | 12075446472423424 | 12075446472427186 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7efe3faf3700 | 0x7efd0fa359c0 | 0 | 0 | 0 | 12075446472476608 | 12075446472641183 | 12075446472778463 | 12075446472782476 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7efe3faf3600 | 0x7efd0fa35a00 | 0 | 0 | 0 | 12075446472843500 | 12075446473006301 | 12075446473135741 | 12075446473139860 |
| 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 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7efe3faf3500 | 0x7efd0fa35a40 | 0 | 0 | 0 | 12075446473191436 | 12075446473366620 | 12075446473628858 | 12075446473696906 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7efe3faf3400 | 0x7efd0fa35a80 | 0 | 0 | 0 | 12075446473720680 | 12075446473901497 | 12075446474158295 | 12075446474228083 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7efe3faf3300 | 0x7efd0fa35ac0 | 0 | 0 | 0 | 12075446474251837 | 12075446474439414 | 12075446474568053 | 12075446474572052 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7efe3faf3a00 | 0x7efd0fa35b00 | 0 | 0 | 0 | 12075446474623628 | 12075446474786292 | 12075446474927891 | 12075446474931650 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7efe3faf3900 | 0x7efd0fa35b40 | 0 | 0 | 0 | 12075446474992894 | 12075446475165650 | 12075446475297649 | 12075446475301548 |
| 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 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7efe3faf3800 | 0x7efd0fa35b80 | 0 | 0 | 0 | 12075446475350779 | 12075446475514448 | 12075446475784527 | 12075446475827155 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7efe3faf3700 | 0x7efd0fa35bc0 | 0 | 0 | 0 | 12075446475849777 | 12075446476037006 | 12075446476298284 | 12075446476365786 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7efe3faf3600 | 0x7efd0fa35c00 | 0 | 0 | 0 | 12075446476389409 | 12075446476567883 | 12075446476696682 | 12075446476700437 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7efe3faf3500 | 0x7efd0fa35c40 | 0 | 0 | 0 | 12075446476749268 | 12075446476918441 | 12075446477063720 | 12075446477067900 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7efe3faf3400 | 0x7efd0fa35c80 | 0 | 0 | 0 | 12075446477129785 | 12075446477291559 | 12075446477422438 | 12075446477426337 |
| 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 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7efe3faf3300 | 0x7efd0fa35cc0 | 0 | 0 | 0 | 12075446477475939 | 12075446477647557 | 12075446477915556 | 12075446477983011 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7efe3faf3a00 | 0x7efd0fa35d00 | 0 | 0 | 0 | 12075446478013187 | 12075446478196994 | 12075446478452193 | 12075446478522624 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7efe3faf3900 | 0x7efd0fa35d40 | 0 | 0 | 0 | 12075446478545647 | 12075446478728672 | 12075446478858431 | 12075446478862175 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7efe3faf3800 | 0x7efd0fa35d80 | 0 | 0 | 0 | 12075446478910906 | 12075446479086910 | 12075446479229949 | 12075446479233866 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7efe3faf3700 | 0x7efd0fa35dc0 | 0 | 0 | 0 | 12075446479294749 | 12075446479457948 | 12075446479591867 | 12075446479595598 |
| 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 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7efe3faf3600 | 0x7efd0fa35e00 | 0 | 0 | 0 | 12075446479637466 | 12075446479813146 | 12075446480079865 | 12075446480147644 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7efe3faf3500 | 0x7efd0fa35e40 | 0 | 0 | 0 | 12075446480171919 | 12075446480353463 | 12075446480609302 | 12075446480675365 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7efe3faf3400 | 0x7efd0fa35e80 | 0 | 0 | 0 | 12075446480700872 | 12075446480876340 | 12075446481008500 | 12075446481012351 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7efe3faf3300 | 0x7efd0fa35ec0 | 0 | 0 | 0 | 12075446481063356 | 12075446481230579 | 12075446481369298 | 12075446481373172 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7efe3faf3a00 | 0x7efd0fa35f00 | 0 | 0 | 0 | 12075446481433824 | 12075446481596177 | 12075446481733456 | 12075446481737258 |
| 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 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7efe3faf3900 | 0x7efd0fa35f40 | 0 | 0 | 0 | 12075446481784917 | 12075446481957775 | 12075446482220333 | 12075446482289464 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7efe3faf3800 | 0x7efd0fa35f80 | 0 | 0 | 0 | 12075446482314050 | 12075446482494252 | 12075446482757611 | 12075446482824138 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7efe3faf3700 | 0x7efd0fa35fc0 | 0 | 0 | 0 | 12075446482842342 | 12075446483032489 | 12075446483166888 | 12075446483170893 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7efe3faf3600 | 0x7efd0fa36000 | 0 | 0 | 0 | 12075446483221006 | 12075446483394247 | 12075446483532167 | 12075446483535941 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7efe3faf3500 | 0x7efd0fa36040 | 0 | 0 | 0 | 12075446483597576 | 12075446483759045 | 12075446483894885 | 12075446483898745 |
| 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 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7efe3faf3400 | 0x7efd0fa36080 | 0 | 0 | 0 | 12075446483947245 | 12075446484120003 | 12075446484392962 | 12075446484442656 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7efe3faf3300 | 0x7efd0fa360c0 | 0 | 0 | 0 | 12075446484467222 | 12075446484649441 | 12075446484902239 | 12075446484924762 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7efe3faf3a00 | 0x7efd0fa36100 | 0 | 0 | 0 | 12075446484967532 | 12075446485133918 | 12075446485267678 | 12075446485271517 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7efe3faf3900 | 0x7efd0fa36140 | 0 | 0 | 0 | 12075446485324395 | 12075446485494876 | 12075446485638556 | 12075446485642346 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7efe3faf3800 | 0x7efd0fa36180 | 0 | 0 | 0 | 12075446485703760 | 12075446485865274 | 12075446486002074 | 12075446486007023 |
| 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 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7efe3faf3700 | 0x7efd0fa361c0 | 0 | 0 | 0 | 12075446486055734 | 12075446486227513 | 12075446486498871 | 12075446486548690 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7efe3faf3600 | 0x7efd0fa36200 | 0 | 0 | 0 | 12075446486574668 | 12075446486749270 | 12075446487004468 | 12075446487053398 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7efe3faf3500 | 0x7efd0fa36240 | 0 | 0 | 0 | 12075446487077513 | 12075446487262547 | 12075446487398226 | 12075446487402086 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7efe3faf3400 | 0x7efd0fa36280 | 0 | 0 | 0 | 12075446487455926 | 12075446487616785 | 12075446487767504 | 12075446487771252 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7efe3faf3300 | 0x7efd0fa362c0 | 0 | 0 | 0 | 12075446487853785 | 12075446488021583 | 12075446488160142 | 12075446488164132 |
| 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 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7efe3faf3a00 | 0x7efd0fa36300 | 0 | 0 | 0 | 12075446488213584 | 12075446488383981 | 12075446488655980 | 12075446488678729 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7efe3faf3900 | 0x7efd0fa36340 | 0 | 0 | 0 | 12075446488716429 | 12075446488874059 | 12075446489131017 | 12075446489180712 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7efe3faf3800 | 0x7efd0fa36380 | 0 | 0 | 0 | 12075446489197673 | 12075446489389736 | 12075446489521255 | 12075446489525172 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7efe3faf3700 | 0x7efd0fa363c0 | 0 | 0 | 0 | 12075446489577459 | 12075446489737894 | 12075446489894853 | 12075446489898576 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7efe3faf3600 | 0x7efd0fa36400 | 0 | 0 | 0 | 12075446489959910 | 12075446490125732 | 12075446490259812 | 12075446490263784 |
| 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 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7efe3faf3500 | 0x7efd0fa36440 | 0 | 0 | 0 | 12075446490307375 | 12075446490481570 | 12075446490747169 | 12075446490795122 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7efe3faf3400 | 0x7efd0fa36480 | 0 | 0 | 0 | 12075446490825508 | 12075446491027328 | 12075446491288126 | 12075446491337650 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7efe3faf3300 | 0x7efd0fa364c0 | 0 | 0 | 0 | 12075446491362076 | 12075446491543325 | 12075446491683964 | 12075446491687891 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7efe3faf3a00 | 0x7efd0fa36500 | 0 | 0 | 0 | 12075446491735980 | 12075446491901083 | 12075446492066522 | 12075446492070602 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7efe3faf3900 | 0x7efd0fa36540 | 0 | 0 | 0 | 12075446492133329 | 12075446492297881 | 12075446492433080 | 12075446492437023 |
| 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 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7efe3faf3800 | 0x7efd0fa36580 | 0 | 0 | 0 | 12075446492480003 | 12075446492655959 | 12075446492924278 | 12075446492946791 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7efe3faf3700 | 0x7efd0fa365c0 | 0 | 0 | 0 | 12075446492988278 | 12075446493155476 | 12075446493409235 | 12075446493458872 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7efe3faf3600 | 0x7efd0fa36600 | 0 | 0 | 0 | 12075446493475894 | 12075446493667154 | 12075446493805553 | 12075446493809664 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7efe3faf3500 | 0x7efd0fa36640 | 0 | 0 | 0 | 12075446493860389 | 12075446494029392 | 12075446494202671 | 12075446494206842 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7efe3faf3400 | 0x7efd0fa36680 | 0 | 0 | 0 | 12075446494268557 | 12075446494431790 | 12075446494568749 | 12075446494572833 |
| 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 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7efe3faf3300 | 0x7efd0fa366c0 | 0 | 0 | 0 | 12075446494622264 | 12075446494792748 | 12075446495053867 | 12075446495103849 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7efe3faf3a00 | 0x7efd0fa36700 | 0 | 0 | 0 | 12075446495132012 | 12075446495309545 | 12075446495572264 | 12075446495619608 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7efe3faf3900 | 0x7efd0fa36740 | 0 | 0 | 0 | 12075446495644614 | 12075446495823303 | 12075446495962342 | 12075446495966393 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7efe3faf3800 | 0x7efd0fa36780 | 0 | 0 | 0 | 12075446496020723 | 12075446496196901 | 12075446496379940 | 12075446496383948 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7efe3faf3700 | 0x7efd0fa367c0 | 0 | 0 | 0 | 12075446496445663 | 12075446496606818 | 12075446496748898 | 12075446496752744 |
| 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 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7efe3faf3600 | 0x7efd0fa36800 | 0 | 0 | 0 | 12075446496802076 | 12075446496969057 | 12075446497236735 | 12075446497286856 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7efe3faf3500 | 0x7efd0fa36840 | 0 | 0 | 0 | 12075446497311793 | 12075446497495294 | 12075446497753052 | 12075446497800551 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7efe3faf3400 | 0x7efd0fa36880 | 0 | 0 | 0 | 12075446497823013 | 12075446498009691 | 12075446498149690 | 12075446498153848 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7efe3faf3300 | 0x7efd0fa368c0 | 0 | 0 | 0 | 12075446498198050 | 12075446498381689 | 12075446498574648 | 12075446498622869 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7efe3faf3a00 | 0x7efd0fa36900 | 0 | 0 | 0 | 12075446498658415 | 12075446498818807 | 12075446498958326 | 12075446498962460 |
| 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 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7efe3faf3900 | 0x7efd0fa36940 | 0 | 0 | 0 | 12075446499017312 | 12075446499177845 | 12075446499462484 | 12075446499485883 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7efe3faf3800 | 0x7efd0fa36980 | 0 | 0 | 0 | 12075446499527941 | 12075446499685362 | 12075446499944241 | 12075446499992405 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7efe3faf3700 | 0x7efd0fa369c0 | 0 | 0 | 0 | 12075446500020427 | 12075446500202000 | 12075446500341679 | 12075446500345811 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7efe3faf3600 | 0x7efd0fa36a00 | 0 | 0 | 0 | 12075446500395985 | 12075446500561038 | 12075446500772557 | 12075446500820604 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7efe3faf3500 | 0x7efd0fa36a40 | 0 | 0 | 0 | 12075446500856701 | 12075446501023595 | 12075446501161835 | 12075446501166156 |
| 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 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7efe3faf3400 | 0x7efd0fa36a80 | 0 | 0 | 0 | 12075446501215397 | 12075446501387434 | 12075446501694792 | 12075446501743409 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7efe3faf3300 | 0x7efd0fa36ac0 | 0 | 0 | 0 | 12075446501765680 | 12075446501944711 | 12075446502202469 | 12075446502254168 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7efe3faf3a00 | 0x7efd0fa36b00 | 0 | 0 | 0 | 12075446502273694 | 12075446502458148 | 12075446502592707 | 12075446502596935 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7efe3faf3900 | 0x7efd0fa36b40 | 0 | 0 | 0 | 12075446502650154 | 12075446502812226 | 12075446503039745 | 12075446503090492 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7efe3faf3800 | 0x7efd0fa36b80 | 0 | 0 | 0 | 12075446503125798 | 12075446503289504 | 12075446503428543 | 12075446503432848 |
| 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 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7efe3faf3700 | 0x7efd0fa36bc0 | 0 | 0 | 0 | 12075446503482591 | 12075446503654142 | 12075446504013340 | 12075446504042001 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7efe3faf3600 | 0x7efd0fa36c00 | 0 | 0 | 0 | 12075446504085572 | 12075446504247579 | 12075446504510457 | 12075446504558280 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7efe3faf3500 | 0x7efd0fa36c40 | 0 | 0 | 0 | 12075446504579850 | 12075446504764216 | 12075446504904375 | 12075446504908471 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7efe3faf3400 | 0x7efd0fa36c80 | 0 | 0 | 0 | 12075446504957322 | 12075446505136674 | 12075446505382753 | 12075446505437163 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7efe3faf3300 | 0x7efd0fa36cc0 | 0 | 0 | 0 | 12075446505471487 | 12075446505645791 | 12075446505786430 | 12075446505789859 |
| 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 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7efe3faf3a00 | 0x7efd0fa36d00 | 0 | 0 | 0 | 12075446505839291 | 12075446506008029 | 12075446506384507 | 12075446506434898 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7efe3faf3900 | 0x7efd0fa36d40 | 0 | 0 | 0 | 12075446506457900 | 12075446506637946 | 12075446506908345 | 12075446506954584 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7efe3faf3800 | 0x7efd0fa36d80 | 0 | 0 | 0 | 12075446506976534 | 12075446507162104 | 12075446507303223 | 12075446507306808 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7efe3faf3700 | 0x7efd0fa36dc0 | 0 | 0 | 0 | 12075446507358755 | 12075446507521462 | 12075446507801461 | 12075446507848785 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7efe3faf3600 | 0x7efd0fa36e00 | 0 | 0 | 0 | 12075446507887497 | 12075446508056660 | 12075446508195859 | 12075446508199617 |
| 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 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7efe3faf3500 | 0x7efd0fa36e40 | 0 | 0 | 0 | 12075446508241525 | 12075446508417458 | 12075446508866096 | 12075446508916530 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7efe3faf3400 | 0x7efd0fa36e80 | 0 | 0 | 0 | 12075446508942207 | 12075446509132655 | 12075446509396814 | 12075446509446425 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7efe3faf3300 | 0x7efd0fa36ec0 | 0 | 0 | 0 | 12075446509472874 | 12075446509651053 | 12075446509791212 | 12075446509794742 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7efe3faf3a00 | 0x7efd0fa36f00 | 0 | 0 | 0 | 12075446509844454 | 12075446510010411 | 12075446510327210 | 12075446510377765 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7efe3faf3900 | 0x7efd0fa36f40 | 0 | 0 | 0 | 12075446510413702 | 12075446510585449 | 12075446510737448 | 12075446510740950 |
| 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 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7efe3faf3800 | 0x7efd0fa36f80 | 0 | 0 | 0 | 12075446510790593 | 12075446510958247 | 12075446511476325 | 12075446511526210 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7efe3faf3700 | 0x7efd0fa36fc0 | 0 | 0 | 0 | 12075446511553450 | 12075446511730404 | 12075446512031202 | 12075446512079638 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7efe3faf3600 | 0x7efd0fa37000 | 0 | 0 | 0 | 12075446512103302 | 12075446512291201 | 12075446512447200 | 12075446512450708 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7efe3faf3500 | 0x7efd0fa37040 | 0 | 0 | 0 | 12075446512499208 | 12075446512667359 | 12075446513054398 | 12075446513077042 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7efe3faf3400 | 0x7efd0fa37080 | 0 | 0 | 0 | 12075446513142013 | 12075446513306557 | 12075446513483036 | 12075446513486563 |
| 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 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7efe3faf3300 | 0x7efd0fa370c0 | 0 | 0 | 0 | 12075446513536285 | 12075446513698235 | 12075446514309912 | 12075446514359165 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7efe3faf3a00 | 0x7efd0fa37100 | 0 | 0 | 0 | 12075446514385233 | 12075446514570391 | 12075446514899510 | 12075446514949842 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7efe3faf3900 | 0x7efd0fa37140 | 0 | 0 | 0 | 12075446514981201 | 12075446515160308 | 12075446515339668 | 12075446515343985 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7efe3faf3800 | 0x7efd0fa37180 | 0 | 0 | 0 | 12075446515394859 | 12075446515573907 | 12075446516031025 | 12075446516081275 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7efe3faf3700 | 0x7efd0fa371c0 | 0 | 0 | 0 | 12075446516118444 | 12075446516279823 | 12075446516479343 | 12075446516527625 |
| 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 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7efe3faf3600 | 0x7efd0fa37200 | 0 | 0 | 0 | 12075446516557921 | 12075446516731021 | 12075446517434858 | 12075446517485405 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7efe3faf3500 | 0x7efd0fa37240 | 0 | 0 | 0 | 12075446517515140 | 12075446517688297 | 12075446518060616 | 12075446518111709 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7efe3faf3400 | 0x7efd0fa37280 | 0 | 0 | 0 | 12075446518142315 | 12075446518322854 | 12075446518525894 | 12075446518575040 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7efe3faf3300 | 0x7efd0fa372c0 | 0 | 0 | 0 | 12075446518603763 | 12075446518781572 | 12075446519308130 | 12075446519359788 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7efe3faf3a00 | 0x7efd0fa37300 | 0 | 0 | 0 | 12075446519396627 | 12075446519559489 | 12075446519784608 | 12075446519831916 |
| 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 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7efe3faf3900 | 0x7efd0fa37340 | 0 | 0 | 0 | 12075446519849999 | 12075446520061567 | 12075446520861243 | 12075446520912834 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7efe3faf3800 | 0x7efd0fa37380 | 0 | 0 | 0 | 12075446520938041 | 12075446521124922 | 12075446521546520 | 12075446521596755 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7efe3faf3700 | 0x7efd0fa373c0 | 0 | 0 | 0 | 12075446521621010 | 12075446521802519 | 12075446522030358 | 12075446522081536 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7efe3faf3600 | 0x7efd0fa37400 | 0 | 0 | 0 | 12075446522109368 | 12075446522287957 | 12075446522885714 | 12075446522954719 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7efe3faf3500 | 0x7efd0fa37440 | 0 | 0 | 0 | 12075446522992880 | 12075446523166193 | 12075446523435632 | 12075446523505302 |
| 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 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7efe3faf3400 | 0x7efd0fa37480 | 0 | 0 | 0 | 12075446523529147 | 12075446523707151 | 12075446524692426 | 12075446524761116 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7efe3faf3300 | 0x7efd0fa374c0 | 0 | 0 | 0 | 12075446524784179 | 12075446524971145 | 12075446525503623 | 12075446525573837 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7efe3faf3a00 | 0x7efd0fa37500 | 0 | 0 | 0 | 12075446525602370 | 12075446525785221 | 12075446526057860 | 12075446526128968 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7efe3faf3900 | 0x7efd0fa37540 | 0 | 0 | 0 | 12075446526160286 | 12075446526333379 | 12075446527071776 | 12075446527139927 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7efe3faf3800 | 0x7efd0fa37580 | 0 | 0 | 0 | 12075446527179501 | 12075446527342494 | 12075446527658333 | 12075446527727329 |
| 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 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7efe3faf3700 | 0x7efd0fa375c0 | 0 | 0 | 0 | 12075446527755802 | 12075446527934972 | 12075446529105527 | 12075446529176342 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7efe3faf3600 | 0x7efd0fa37600 | 0 | 0 | 0 | 12075446529202160 | 12075446529396725 | 12075446530006163 | 12075446530075202 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7efe3faf3500 | 0x7efd0fa37640 | 0 | 0 | 0 | 12075446530104056 | 12075446530282641 | 12075446530629520 | 12075446530697038 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7efe3faf3400 | 0x7efd0fa37680 | 0 | 0 | 0 | 12075446530723968 | 12075446530900559 | 12075446531778635 | 12075446531848177 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7efe3faf3300 | 0x7efd0fa376c0 | 0 | 0 | 0 | 12075446531885446 | 12075446532056874 | 12075446532489832 | 12075446532559189 |
| 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 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7efe3faf3a00 | 0x7efd0fa37700 | 0 | 0 | 0 | 12075446532583183 | 12075446532773190 | 12075446534321184 | 12075446534390672 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7efe3faf3900 | 0x7efd0fa37740 | 0 | 0 | 0 | 12075446534422261 | 12075446534604062 | 12075446535398619 | 12075446535467013 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7efe3faf3800 | 0x7efd0fa37780 | 0 | 0 | 0 | 12075446535489234 | 12075446535675578 | 12075446536090296 | 12075446536159089 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7efe3faf3700 | 0x7efd0fa377c0 | 0 | 0 | 0 | 12075446536189575 | 12075446536367895 | 12075446537526129 | 12075446537594967 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7efe3faf3600 | 0x7efd0fa37800 | 0 | 0 | 0 | 12075446537639009 | 12075446537803728 | 12075446538590125 | 12075446538660828 |
| 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 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7efe3faf3500 | 0x7efd0fa37840 | 0 | 0 | 0 | 12075446538687778 | 12075446538868363 | 12075446541917630 | 12075446541988312 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7efe3faf3400 | 0x7efd0fa37880 | 0 | 0 | 0 | 12075446542023147 | 12075446542212349 | 12075446543754262 | 12075446543824665 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7efe3faf3300 | 0x7efd0fa378c0 | 0 | 0 | 0 | 12075446543855933 | 12075446544044981 | 12075446544834417 | 12075446544904261 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7efe3faf3a00 | 0x7efd0fa37900 | 0 | 0 | 0 | 12075446544931282 | 12075446545120496 | 12075446547402406 | 12075446547471933 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7efe3faf3900 | 0x7efd0fa37940 | 0 | 0 | 0 | 12075446547515855 | 12075446547680484 | 12075446549216638 | 12075446549284933 |
| 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 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7efe3faf3800 | 0x7efd0fa37980 | 0 | 0 | 0 | 12075446549315059 | 12075446549495676 | 12075446555549730 | 12075446555618353 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7efe3faf3700 | 0x7efd0fa379c0 | 0 | 0 | 0 | 12075446555649601 | 12075446555822528 | 12075446558864275 | 12075446558934917 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7efe3faf3600 | 0x7efd0fa37a00 | 0 | 0 | 0 | 12075446558964882 | 12075446559152274 | 12075446560690827 | 12075446560761722 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 875773 | 875778 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7efe3faf3500 | 0x7efd0fa37a40 | 0 | 0 | 0 | 12075446560791858 | 12075446560971306 | 12075446565498485 | 12075446565569106 |