39 KiB
39 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBuffer.kd | 0 | 0 | 0 | 785581 | 785586 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7f9e50404180 | 12073812903887663 | 12073812903928197 | 12073812904253634 | 12073812904368346 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 785581 | 785586 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7f9e50435100 | 12073812919274588 | 12073812919377104 | 12073812919384144 | 12073812919389572 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7f9f5c0e3900 | 0x7f9e50435140 | 12073812919433553 | 12073812919446544 | 12073812919580302 | 12073812919583672 |
| 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 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7f9f5c0e3800 | 0x7f9e50435180 | 12073812919623937 | 12073812919640942 | 12073812919885100 | 12073812919985088 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7f9f5c0e3700 | 0x7f9e504351c0 | 12073812920013181 | 12073812920026379 | 12073812920273096 | 12073812920374141 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7f9f5c0e3600 | 0x7f9e50435200 | 12073812920399428 | 12073812920411495 | 12073812920537094 | 12073812920539729 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7f9f5c0e3500 | 0x7f9e50435240 | 12073812920566839 | 12073812920578374 | 12073812920703653 | 12073812920706539 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7f9f5c0e3400 | 0x7f9e50435280 | 12073812920753887 | 12073812920766212 | 12073812920890211 | 12073812920893176 |
| 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 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7f9f5c0e3300 | 0x7f9e504352c0 | 12073812920919094 | 12073812920930851 | 12073812921177409 | 12073812921280696 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7f9f5c0e3a00 | 0x7f9e50435300 | 12073812921301915 | 12073812921312928 | 12073812921556285 | 12073812921655823 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7f9f5c0e3900 | 0x7f9e50435340 | 12073812921677924 | 12073812921690364 | 12073812921815163 | 12073812921818225 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7f9f5c0e3800 | 0x7f9e50435380 | 12073812921845576 | 12073812921856923 | 12073812921981722 | 12073812921984754 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7f9f5c0e3700 | 0x7f9e504353c0 | 12073812922035809 | 12073812922048281 | 12073812922173400 | 12073812922176110 |
| 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 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7f9f5c0e3600 | 0x7f9e50435400 | 12073812922203160 | 12073812922214520 | 12073812922463158 | 12073812922537902 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7f9f5c0e3500 | 0x7f9e50435440 | 12073812922562799 | 12073812922574997 | 12073812922820115 | 12073812922919632 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7f9f5c0e3400 | 0x7f9e50435480 | 12073812922944358 | 12073812922955474 | 12073812923080272 | 12073812923083416 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7f9f5c0e3300 | 0x7f9e504354c0 | 12073812923109294 | 12073812923120592 | 12073812923245711 | 12073812923248433 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7f9f5c0e3a00 | 0x7f9e50435500 | 12073812923285832 | 12073812923297231 | 12073812923422030 | 12073812923424951 |
| 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 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7f9f5c0e3900 | 0x7f9e50435540 | 12073812923451019 | 12073812923462349 | 12073812923707307 | 12073812923754283 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7f9f5c0e3800 | 0x7f9e50435580 | 12073812923775412 | 12073812923787626 | 12073812924032264 | 12073812924102941 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7f9f5c0e3700 | 0x7f9e504355c0 | 12073812924123780 | 12073812924135143 | 12073812924259142 | 12073812924261525 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7f9f5c0e3600 | 0x7f9e50435600 | 12073812924288215 | 12073812924299942 | 12073812924424741 | 12073812924427464 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7f9f5c0e3500 | 0x7f9e50435640 | 12073812924462108 | 12073812924475621 | 12073812924599939 | 12073812924602960 |
| 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 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7f9f5c0e3400 | 0x7f9e50435680 | 12073812924629860 | 12073812924643139 | 12073812924887777 | 12073812924931551 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7f9f5c0e3300 | 0x7f9e504356c0 | 12073812924953792 | 12073812924967136 | 12073812925210814 | 12073812925282813 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7f9f5c0e3a00 | 0x7f9e50435700 | 12073812925305095 | 12073812925318333 | 12073812925442652 | 12073812925445025 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7f9f5c0e3900 | 0x7f9e50435740 | 12073812925471694 | 12073812925483292 | 12073812925608251 | 12073812925610853 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7f9f5c0e3800 | 0x7f9e50435780 | 12073812925646950 | 12073812925658970 | 12073812925783289 | 12073812925785698 |
| 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 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7f9f5c0e3700 | 0x7f9e504357c0 | 12073812925811596 | 12073812925823449 | 12073812926070487 | 12073812926142060 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7f9f5c0e3600 | 0x7f9e50435800 | 12073812926165754 | 12073812926177046 | 12073812926425044 | 12073812926474799 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7f9f5c0e3500 | 0x7f9e50435840 | 12073812926497671 | 12073812926509683 | 12073812926634322 | 12073812926636639 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7f9f5c0e3400 | 0x7f9e50435880 | 12073812926662788 | 12073812926674002 | 12073812926799601 | 12073812926802297 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7f9f5c0e3300 | 0x7f9e504358c0 | 12073812926839136 | 12073812926854000 | 12073812926978799 | 12073812926981631 |
| 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 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7f9f5c0e3a00 | 0x7f9e50435900 | 12073812927014221 | 12073812927026319 | 12073812927274957 | 12073812927331270 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7f9f5c0e3900 | 0x7f9e50435940 | 12073812927352370 | 12073812927363916 | 12073812927608394 | 12073812927663167 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7f9f5c0e3800 | 0x7f9e50435980 | 12073812927684938 | 12073812927696233 | 12073812927821672 | 12073812927824216 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7f9f5c0e3700 | 0x7f9e504359c0 | 12073812927848922 | 12073812927860232 | 12073812927985990 | 12073812927988712 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7f9f5c0e3600 | 0x7f9e50435a00 | 12073812928031692 | 12073812928043910 | 12073812928167909 | 12073812928171001 |
| 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 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7f9f5c0e3500 | 0x7f9e50435a40 | 12073812928197019 | 12073812928208709 | 12073812928462786 | 12073812928494372 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7f9f5c0e3400 | 0x7f9e50435a80 | 12073812928515521 | 12073812928528706 | 12073812928772064 | 12073812928825998 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7f9f5c0e3300 | 0x7f9e50435ac0 | 12073812928848510 | 12073812928862143 | 12073812928987102 | 12073812928989712 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7f9f5c0e3a00 | 0x7f9e50435b00 | 12073812929023215 | 12073812929035742 | 12073812929162780 | 12073812929165439 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7f9f5c0e3900 | 0x7f9e50435b40 | 12073812929201316 | 12073812929215420 | 12073812929340219 | 12073812929343019 |
| 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 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7f9f5c0e3800 | 0x7f9e50435b80 | 12073812929368266 | 12073812929381019 | 12073812929637496 | 12073812929660389 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7f9f5c0e3700 | 0x7f9e50435bc0 | 12073812929683562 | 12073812929694776 | 12073812929938134 | 12073812929986675 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7f9f5c0e3600 | 0x7f9e50435c00 | 12073812930014767 | 12073812930026453 | 12073812930150932 | 12073812930153475 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7f9f5c0e3500 | 0x7f9e50435c40 | 12073812930180786 | 12073812930192372 | 12073812930319411 | 12073812930322098 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7f9f5c0e3400 | 0x7f9e50435c80 | 12073812930359418 | 12073812930372690 | 12073812930497649 | 12073812930500039 |
| 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 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7f9f5c0e3300 | 0x7f9e50435cc0 | 12073812930525617 | 12073812930539089 | 12073812930793966 | 12073812930817780 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7f9f5c0e3a00 | 0x7f9e50435d00 | 12073812930840842 | 12073812930853486 | 12073812931103724 | 12073812931153363 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7f9f5c0e3900 | 0x7f9e50435d40 | 12073812931175605 | 12073812931188523 | 12073812931313962 | 12073812931316406 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7f9f5c0e3800 | 0x7f9e50435d80 | 12073812931343126 | 12073812931356522 | 12073812931484361 | 12073812931486853 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7f9f5c0e3700 | 0x7f9e50435dc0 | 12073812931522920 | 12073812931535400 | 12073812931660359 | 12073812931662740 |
| 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 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7f9f5c0e3600 | 0x7f9e50435e00 | 12073812931688488 | 12073812931701479 | 12073812931957957 | 12073812931979388 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7f9f5c0e3500 | 0x7f9e50435e40 | 12073812932006939 | 12073812932020516 | 12073812932265314 | 12073812932293823 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7f9f5c0e3400 | 0x7f9e50435e80 | 12073812932317877 | 12073812932331233 | 12073812932456832 | 12073812932459561 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7f9f5c0e3300 | 0x7f9e50435ec0 | 12073812932485799 | 12073812932498432 | 12073812932628031 | 12073812932630458 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7f9f5c0e3a00 | 0x7f9e50435f00 | 12073812932666756 | 12073812932680030 | 12073812932805469 | 12073812932808198 |
| 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 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7f9f5c0e3900 | 0x7f9e50435f40 | 12073812932833726 | 12073812932845949 | 12073812933102267 | 12073812933129305 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7f9f5c0e3800 | 0x7f9e50435f80 | 12073812933151607 | 12073812933163226 | 12073812933408024 | 12073812933433631 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7f9f5c0e3700 | 0x7f9e50435fc0 | 12073812933456333 | 12073812933467704 | 12073812933592823 | 12073812933595281 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7f9f5c0e3600 | 0x7f9e50436000 | 12073812933621279 | 12073812933635222 | 12073812933772821 | 12073812933775596 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7f9f5c0e3500 | 0x7f9e50436040 | 12073812933812845 | 12073812933825461 | 12073812933951219 | 12073812933953677 |
| 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 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7f9f5c0e3400 | 0x7f9e50436080 | 12073812933980036 | 12073812933993139 | 12073812934259217 | 12073812934285354 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7f9f5c0e3300 | 0x7f9e504360c0 | 12073812934306403 | 12073812934319536 | 12073812934566574 | 12073812934590851 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7f9f5c0e3a00 | 0x7f9e50436100 | 12073812934612141 | 12073812934623534 | 12073812934748013 | 12073812934750568 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7f9f5c0e3900 | 0x7f9e50436140 | 12073812934776747 | 12073812934788172 | 12073812934928651 | 12073812934931204 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7f9f5c0e3800 | 0x7f9e50436180 | 12073812934967441 | 12073812934978891 | 12073812935103850 | 12073812935106800 |
| 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 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7f9f5c0e3700 | 0x7f9e504361c0 | 12073812935132789 | 12073812935144169 | 12073812935394887 | 12073812935421175 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7f9f5c0e3600 | 0x7f9e50436200 | 12073812935441532 | 12073812935454727 | 12073812935697605 | 12073812935722004 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7f9f5c0e3500 | 0x7f9e50436240 | 12073812935744415 | 12073812935757284 | 12073812935883043 | 12073812935885568 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7f9f5c0e3400 | 0x7f9e50436280 | 12073812935911025 | 12073812935924003 | 12073812936073441 | 12073812936076402 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7f9f5c0e3300 | 0x7f9e504362c0 | 12073812936129831 | 12073812936142401 | 12073812936267360 | 12073812936270242 |
| 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 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7f9f5c0e3a00 | 0x7f9e50436300 | 12073812936295149 | 12073812936307679 | 12073812936560477 | 12073812936582332 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7f9f5c0e3900 | 0x7f9e50436340 | 12073812936602901 | 12073812936615517 | 12073812936860795 | 12073812936880897 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7f9f5c0e3800 | 0x7f9e50436380 | 12073812936902758 | 12073812936915514 | 12073812937041273 | 12073812937044361 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7f9f5c0e3700 | 0x7f9e504363c0 | 12073812937071011 | 12073812937082393 | 12073812937239671 | 12073812937242469 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7f9f5c0e3600 | 0x7f9e50436400 | 12073812937279518 | 12073812937294551 | 12073812937419670 | 12073812937422263 |
| 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 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7f9f5c0e3500 | 0x7f9e50436440 | 12073812937448863 | 12073812937461589 | 12073812937719347 | 12073812937740054 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7f9f5c0e3400 | 0x7f9e50436480 | 12073812937762886 | 12073812937775827 | 12073812938026705 | 12073812938060149 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7f9f5c0e3300 | 0x7f9e504364c0 | 12073812938080757 | 12073812938093104 | 12073812938218703 | 12073812938221288 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7f9f5c0e3a00 | 0x7f9e50436500 | 12073812938246976 | 12073812938259183 | 12073812938424941 | 12073812938427481 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7f9f5c0e3900 | 0x7f9e50436540 | 12073812938461975 | 12073812938474061 | 12073812938599980 | 12073812938602507 |
| 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 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7f9f5c0e3800 | 0x7f9e50436580 | 12073812938628555 | 12073812938640139 | 12073812938894377 | 12073812938919466 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7f9f5c0e3700 | 0x7f9e504365c0 | 12073812938939583 | 12073812938952297 | 12073812939199975 | 12073812939230253 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7f9f5c0e3600 | 0x7f9e50436600 | 12073812939251443 | 12073812939264614 | 12073812939389893 | 12073812939392415 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7f9f5c0e3500 | 0x7f9e50436640 | 12073812939418443 | 12073812939431173 | 12073812939603651 | 12073812939606242 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7f9f5c0e3400 | 0x7f9e50436680 | 12073812939642559 | 12073812939655171 | 12073812939781890 | 12073812939784493 |
| 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 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7f9f5c0e3300 | 0x7f9e504366c0 | 12073812939810501 | 12073812939823489 | 12073812940078687 | 12073812940107503 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7f9f5c0e3a00 | 0x7f9e50436700 | 12073812940127591 | 12073812940139007 | 12073812940420764 | 12073812940446383 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7f9f5c0e3900 | 0x7f9e50436740 | 12073812940466050 | 12073812940477724 | 12073812940603483 | 12073812940606431 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7f9f5c0e3800 | 0x7f9e50436780 | 12073812940632579 | 12073812940646202 | 12073812940828601 | 12073812940831118 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7f9f5c0e3700 | 0x7f9e504367c0 | 12073812940867355 | 12073812940879960 | 12073812941005399 | 12073812941008638 |
| 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 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7f9f5c0e3600 | 0x7f9e50436800 | 12073812941035869 | 12073812941048279 | 12073812941312277 | 12073812941341026 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7f9f5c0e3500 | 0x7f9e50436840 | 12073812941361323 | 12073812941374036 | 12073812941620434 | 12073812941644390 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7f9f5c0e3400 | 0x7f9e50436880 | 12073812941663926 | 12073812941677073 | 12073812941802672 | 12073812941805289 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7f9f5c0e3300 | 0x7f9e504368c0 | 12073812941831227 | 12073812941844272 | 12073812942035150 | 12073812942038322 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7f9f5c0e3a00 | 0x7f9e50436900 | 12073812942074188 | 12073812942087470 | 12073812942213549 | 12073812942216042 |
| 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 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7f9f5c0e3900 | 0x7f9e50436940 | 12073812942241138 | 12073812942253708 | 12073812942535786 | 12073812942556985 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7f9f5c0e3800 | 0x7f9e50436980 | 12073812942576832 | 12073812942589706 | 12073812942839783 | 12073812942863405 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7f9f5c0e3700 | 0x7f9e504369c0 | 12073812942885716 | 12073812942899623 | 12073812943025542 | 12073812943028402 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7f9f5c0e3600 | 0x7f9e50436a00 | 12073812943054260 | 12073812943066822 | 12073812943276580 | 12073812943300988 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7f9f5c0e3500 | 0x7f9e50436a40 | 12073812943331675 | 12073812943344739 | 12073812943471618 | 12073812943474190 |
| 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 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7f9f5c0e3400 | 0x7f9e50436a80 | 12073812943500549 | 12073812943513858 | 12073812943850815 | 12073812943871258 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7f9f5c0e3300 | 0x7f9e50436ac0 | 12073812943892578 | 12073812943905054 | 12073812944157212 | 12073812944186554 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7f9f5c0e3a00 | 0x7f9e50436b00 | 12073812944207333 | 12073812944220892 | 12073812944347451 | 12073812944350028 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7f9f5c0e3900 | 0x7f9e50436b40 | 12073812944375986 | 12073812944387290 | 12073812944614648 | 12073812944637873 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7f9f5c0e3800 | 0x7f9e50436b80 | 12073812944672166 | 12073812944684888 | 12073812944811447 | 12073812944813970 |
| 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 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7f9f5c0e3700 | 0x7f9e50436bc0 | 12073812944839067 | 12073812944851766 | 12073812945180403 | 12073812945205998 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7f9f5c0e3600 | 0x7f9e50436c00 | 12073812945228170 | 12073812945240723 | 12073812945493361 | 12073812945516756 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7f9f5c0e3500 | 0x7f9e50436c40 | 12073812945540039 | 12073812945553360 | 12073812945682479 | 12073812945685059 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7f9f5c0e3400 | 0x7f9e50436c80 | 12073812945709684 | 12073812945722319 | 12073812945966157 | 12073812945986439 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7f9f5c0e3300 | 0x7f9e50436cc0 | 12073812946026293 | 12073812946039436 | 12073812946168235 | 12073812946171112 |
| 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 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7f9f5c0e3a00 | 0x7f9e50436d00 | 12073812946197441 | 12073812946210155 | 12073812946585031 | 12073812946609567 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7f9f5c0e3900 | 0x7f9e50436d40 | 12073812946630726 | 12073812946643591 | 12073812946894949 | 12073812946918461 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7f9f5c0e3800 | 0x7f9e50436d80 | 12073812946941143 | 12073812946954148 | 12073812947083587 | 12073812947086453 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7f9f5c0e3700 | 0x7f9e50436dc0 | 12073812947111710 | 12073812947122627 | 12073812947400544 | 12073812947429971 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7f9f5c0e3600 | 0x7f9e50436e00 | 12073812947460468 | 12073812947473824 | 12073812947609183 | 12073812947611739 |
| 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 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7f9f5c0e3500 | 0x7f9e50436e40 | 12073812947636405 | 12073812947648542 | 12073812948071419 | 12073812948101439 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7f9f5c0e3400 | 0x7f9e50436e80 | 12073812948123540 | 12073812948136218 | 12073812948392056 | 12073812948420482 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7f9f5c0e3300 | 0x7f9e50436ec0 | 12073812948443084 | 12073812948455575 | 12073812948591574 | 12073812948594145 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7f9f5c0e3a00 | 0x7f9e50436f00 | 12073812948619843 | 12073812948632054 | 12073812948975571 | 12073812949008655 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7f9f5c0e3900 | 0x7f9e50436f40 | 12073812949042578 | 12073812949055410 | 12073812949207409 | 12073812949210691 |
| 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 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7f9f5c0e3800 | 0x7f9e50436f80 | 12073812949236058 | 12073812949249489 | 12073812949764844 | 12073812949789416 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7f9f5c0e3700 | 0x7f9e50436fc0 | 12073812949810495 | 12073812949821804 | 12073812950118921 | 12073812950149435 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7f9f5c0e3600 | 0x7f9e50437000 | 12073812950167489 | 12073812950180041 | 12073812950333479 | 12073812950336022 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7f9f5c0e3500 | 0x7f9e50437040 | 12073812950362221 | 12073812950375079 | 12073812950759876 | 12073812950789324 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7f9f5c0e3400 | 0x7f9e50437080 | 12073812950821835 | 12073812950835075 | 12073812951010914 | 12073812951013922 |
| 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 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7f9f5c0e3300 | 0x7f9e504370c0 | 12073812951040261 | 12073812951051713 | 12073812951660988 | 12073812951693985 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7f9f5c0e3a00 | 0x7f9e50437100 | 12073812951715215 | 12073812951727067 | 12073812952051545 | 12073812952081956 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7f9f5c0e3900 | 0x7f9e50437140 | 12073812952105781 | 12073812952117304 | 12073812952296183 | 12073812952298799 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7f9f5c0e3800 | 0x7f9e50437180 | 12073812952325068 | 12073812952335862 | 12073812952790738 | 12073812952819016 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7f9f5c0e3700 | 0x7f9e504371c0 | 12073812952851857 | 12073812952864818 | 12073812953063696 | 12073812953094418 |
| 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 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7f9f5c0e3600 | 0x7f9e50437200 | 12073812953115307 | 12073812953128175 | 12073812953830729 | 12073812953859420 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7f9f5c0e3500 | 0x7f9e50437240 | 12073812953882673 | 12073812953895529 | 12073812954268006 | 12073812954301862 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7f9f5c0e3400 | 0x7f9e50437280 | 12073812954325245 | 12073812954338085 | 12073812954540643 | 12073812954568688 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7f9f5c0e3300 | 0x7f9e504372c0 | 12073812954588905 | 12073812954601603 | 12073812955126558 | 12073812955157602 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7f9f5c0e3a00 | 0x7f9e50437300 | 12073812955191125 | 12073812955204958 | 12073812955428156 | 12073812955456538 |
| 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 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7f9f5c0e3900 | 0x7f9e50437340 | 12073812955478749 | 12073812955491835 | 12073812956289588 | 12073812956320433 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7f9f5c0e3800 | 0x7f9e50437380 | 12073812956342785 | 12073812956353908 | 12073812956775344 | 12073812956803721 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7f9f5c0e3700 | 0x7f9e504373c0 | 12073812956825702 | 12073812956838704 | 12073812957063182 | 12073812957096465 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7f9f5c0e3600 | 0x7f9e50437400 | 12073812957119288 | 12073812957132141 | 12073812957728296 | 12073812957756081 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7f9f5c0e3500 | 0x7f9e50437440 | 12073812957788622 | 12073812957799816 | 12073812958068133 | 12073812958098478 |
| 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 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7f9f5c0e3400 | 0x7f9e50437480 | 12073812958121631 | 12073812958134533 | 12073812959119644 | 12073812959150362 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7f9f5c0e3300 | 0x7f9e504374c0 | 12073812959170991 | 12073812959183964 | 12073812959698999 | 12073812959726864 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7f9f5c0e3a00 | 0x7f9e50437500 | 12073812959750678 | 12073812959763639 | 12073812960034996 | 12073812960065693 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7f9f5c0e3900 | 0x7f9e50437540 | 12073812960088506 | 12073812960101716 | 12073812960838990 | 12073812960867253 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7f9f5c0e3800 | 0x7f9e50437580 | 12073812960899393 | 12073812960912109 | 12073812961226986 | 12073812961260644 |
| 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 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7f9f5c0e3700 | 0x7f9e504375c0 | 12073812961284629 | 12073812961297546 | 12073812962468736 | 12073812962499707 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7f9f5c0e3600 | 0x7f9e50437600 | 12073812962521948 | 12073812962534335 | 12073812963145050 | 12073812963177166 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7f9f5c0e3500 | 0x7f9e50437640 | 12073812963199748 | 12073812963212409 | 12073812963531926 | 12073812963560408 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7f9f5c0e3400 | 0x7f9e50437680 | 12073812963582810 | 12073812963595606 | 12073812964472878 | 12073812964505715 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7f9f5c0e3300 | 0x7f9e504376c0 | 12073812964540038 | 12073812964553038 | 12073812964962954 | 12073812964991297 |
| 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 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7f9f5c0e3a00 | 0x7f9e50437700 | 12073812965027184 | 12073812965037834 | 12073812966588060 | 12073812966664126 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7f9f5c0e3900 | 0x7f9e50437740 | 12073812966686848 | 12073812966700363 | 12073812967494277 | 12073812967574508 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7f9f5c0e3800 | 0x7f9e50437780 | 12073812967594174 | 12073812967607395 | 12073812968021792 | 12073812968096969 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7f9f5c0e3700 | 0x7f9e504377c0 | 12073812968120632 | 12073812968133631 | 12073812969292183 | 12073812969368281 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7f9f5c0e3600 | 0x7f9e50437800 | 12073812969400501 | 12073812969412982 | 12073812970198416 | 12073812970273013 |
| 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 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7f9f5c0e3500 | 0x7f9e50437840 | 12073812970296296 | 12073812970309615 | 12073812973360632 | 12073812973436511 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7f9f5c0e3400 | 0x7f9e50437880 | 12073812973459134 | 12073812973470552 | 12073812975012300 | 12073812975087870 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7f9f5c0e3300 | 0x7f9e504378c0 | 12073812975112246 | 12073812975125579 | 12073812975914853 | 12073812975988654 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7f9f5c0e3a00 | 0x7f9e50437900 | 12073812976017277 | 12073812976030533 | 12073812978311796 | 12073812978387172 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7f9f5c0e3900 | 0x7f9e50437940 | 12073812978424712 | 12073812978437875 | 12073812979973383 | 12073812980048980 |
| 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 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7f9f5c0e3800 | 0x7f9e50437980 | 12073812980075319 | 12073812980089862 | 12073812986144217 | 12073812986219327 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7f9f5c0e3700 | 0x7f9e504379c0 | 12073812986242911 | 12073812986255576 | 12073812989297634 | 12073812989373068 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7f9f5c0e3600 | 0x7f9e50437a00 | 12073812989395570 | 12073812989409153 | 12073812990948501 | 12073812991027031 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 785581 | 785586 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7f9f5c0e3500 | 0x7f9e50437a40 | 12073812991049553 | 12073812991062901 | 12073812995589907 | 12073812995666583 |