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 | 845736 | 845741 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7fa5f2c04180 | 12074712949765672 | 12074712949814439 | 12074712950139236 | 12074712950247648 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 845736 | 845741 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7fa5f2c35100 | 12074712964863469 | 12074712964969515 | 12074712964975915 | 12074712964981519 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7fa722cfe900 | 0x7fa5f2c35140 | 12074712965035800 | 12074712965051114 | 12074712965185353 | 12074712965188564 |
| 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 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7fa722cfe800 | 0x7fa5f2c35180 | 12074712965234078 | 12074712965248233 | 12074712965494791 | 12074712965586213 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7fa722cfe700 | 0x7fa5f2c351c0 | 12074712965613764 | 12074712965625830 | 12074712965868868 | 12074712965959667 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7fa722cfe600 | 0x7fa5f2c35200 | 12074712965986486 | 12074712965998467 | 12074712966123586 | 12074712966127098 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7fa722cfe500 | 0x7fa5f2c35240 | 12074712966157063 | 12074712966177345 | 12074712966301664 | 12074712966304678 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7fa722cfe400 | 0x7fa5f2c35280 | 12074712966362074 | 12074712966378304 | 12074712966502463 | 12074712966505281 |
| 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 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7fa722cfe300 | 0x7fa5f2c352c0 | 12074712966533283 | 12074712966547742 | 12074712966801340 | 12074712966893181 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7fa722cfea00 | 0x7fa5f2c35300 | 12074712966915663 | 12074712966927579 | 12074712967177817 | 12074712967269831 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7fa722cfe900 | 0x7fa5f2c35340 | 12074712967297723 | 12074712967309496 | 12074712967433655 | 12074712967437072 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7fa722cfe800 | 0x7fa5f2c35380 | 12074712967468711 | 12074712967480695 | 12074712967605174 | 12074712967608090 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7fa722cfe700 | 0x7fa5f2c353c0 | 12074712967646481 | 12074712967658293 | 12074712967782932 | 12074712967785830 |
| 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 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7fa722cfe600 | 0x7fa5f2c35400 | 12074712967813752 | 12074712967825172 | 12074712968075730 | 12074712968172008 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7fa722cfe500 | 0x7fa5f2c35440 | 12074712968198407 | 12074712968210289 | 12074712968455247 | 12074712968520576 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7fa722cfe400 | 0x7fa5f2c35480 | 12074712968547937 | 12074712968560206 | 12074712968685325 | 12074712968688368 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7fa722cfe300 | 0x7fa5f2c354c0 | 12074712968715889 | 12074712968727404 | 12074712968852363 | 12074712968855147 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7fa722cfea00 | 0x7fa5f2c35500 | 12074712968893318 | 12074712968905803 | 12074712969029962 | 12074712969032988 |
| 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 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7fa722cfe900 | 0x7fa5f2c35540 | 12074712969063495 | 12074712969078922 | 12074712969330440 | 12074712969394329 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7fa722cfe800 | 0x7fa5f2c35580 | 12074712969416070 | 12074712969429799 | 12074712969674597 | 12074712969738639 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7fa722cfe700 | 0x7fa5f2c355c0 | 12074712969762403 | 12074712969775716 | 12074712969900195 | 12074712969903345 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7fa722cfe600 | 0x7fa5f2c35600 | 12074712969930255 | 12074712969942915 | 12074712970067714 | 12074712970070696 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7fa722cfe500 | 0x7fa5f2c35640 | 12074712970109478 | 12074712970124033 | 12074712970248672 | 12074712970251813 |
| 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 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7fa722cfe400 | 0x7fa5f2c35680 | 12074712970279254 | 12074712970294592 | 12074712970542590 | 12074712970606382 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7fa722cfe300 | 0x7fa5f2c356c0 | 12074712970628002 | 12074712970640669 | 12074712970887067 | 12074712970951493 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7fa722cfea00 | 0x7fa5f2c35700 | 12074712970975197 | 12074712970988026 | 12074712971112025 | 12074712971115668 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7fa722cfe900 | 0x7fa5f2c35740 | 12074712971144051 | 12074712971157145 | 12074712971282264 | 12074712971285143 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7fa722cfe800 | 0x7fa5f2c35780 | 12074712971322232 | 12074712971335223 | 12074712971459222 | 12074712971462182 |
| 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 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7fa722cfe700 | 0x7fa5f2c357c0 | 12074712971489573 | 12074712971503862 | 12074712971756660 | 12074712971804208 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7fa722cfe600 | 0x7fa5f2c35800 | 12074712971824466 | 12074712971840659 | 12074712972090097 | 12074712972164287 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7fa722cfe500 | 0x7fa5f2c35840 | 12074712972185997 | 12074712972197456 | 12074712972321455 | 12074712972324855 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7fa722cfe400 | 0x7fa5f2c35880 | 12074712972352166 | 12074712972363855 | 12074712972489134 | 12074712972492116 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7fa722cfe300 | 0x7fa5f2c358c0 | 12074712972529315 | 12074712972543693 | 12074712972668812 | 12074712972671800 |
| 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 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7fa722cfea00 | 0x7fa5f2c35900 | 12074712972698490 | 12074712972711852 | 12074712972958250 | 12074712973013435 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7fa722cfe900 | 0x7fa5f2c35940 | 12074712973036788 | 12074712973054089 | 12074712973298247 | 12074712973350702 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7fa722cfe800 | 0x7fa5f2c35980 | 12074712973372052 | 12074712973384007 | 12074712973509286 | 12074712973512472 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7fa722cfe700 | 0x7fa5f2c359c0 | 12074712973539793 | 12074712973551045 | 12074712973676484 | 12074712973679653 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7fa722cfe600 | 0x7fa5f2c35a00 | 12074712973715139 | 12074712973728964 | 12074712973853283 | 12074712973856201 |
| 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 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7fa722cfe500 | 0x7fa5f2c35a40 | 12074712973881889 | 12074712973895362 | 12074712974140960 | 12074712974172289 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7fa722cfe400 | 0x7fa5f2c35a80 | 12074712974195311 | 12074712974211360 | 12074712974492958 | 12074712974519544 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7fa722cfe300 | 0x7fa5f2c35ac0 | 12074712974544981 | 12074712974559197 | 12074712974684476 | 12074712974687817 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7fa722cfea00 | 0x7fa5f2c35b00 | 12074712974714045 | 12074712974725916 | 12074712974851835 | 12074712974854807 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7fa722cfe900 | 0x7fa5f2c35b40 | 12074712974892557 | 12074712974906394 | 12074712975031353 | 12074712975034631 |
| 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 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7fa722cfe800 | 0x7fa5f2c35b80 | 12074712975061962 | 12074712975073753 | 12074712975328791 | 12074712975349937 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7fa722cfe700 | 0x7fa5f2c35bc0 | 12074712975371106 | 12074712975383830 | 12074712975627348 | 12074712975652379 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7fa722cfe600 | 0x7fa5f2c35c00 | 12074712975672246 | 12074712975685428 | 12074712975809267 | 12074712975812236 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7fa722cfe500 | 0x7fa5f2c35c40 | 12074712975840048 | 12074712975852627 | 12074712975978546 | 12074712975981521 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7fa722cfe400 | 0x7fa5f2c35c80 | 12074712976025633 | 12074712976038705 | 12074712976163984 | 12074712976167116 |
| 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 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7fa722cfe300 | 0x7fa5f2c35cc0 | 12074712976195749 | 12074712976209104 | 12074712976470542 | 12074712976495306 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7fa722cfea00 | 0x7fa5f2c35d00 | 12074712976516134 | 12074712976528941 | 12074712976774219 | 12074712976799050 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7fa722cfe900 | 0x7fa5f2c35d40 | 12074712976821502 | 12074712976834699 | 12074712976959818 | 12074712976962764 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7fa722cfe800 | 0x7fa5f2c35d80 | 12074712976989534 | 12074712977002697 | 12074712977130696 | 12074712977134093 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7fa722cfe700 | 0x7fa5f2c35dc0 | 12074712977172975 | 12074712977187016 | 12074712977312135 | 12074712977315059 |
| 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 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7fa722cfe600 | 0x7fa5f2c35e00 | 12074712977341598 | 12074712977354854 | 12074712977607012 | 12074712977623863 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7fa722cfe500 | 0x7fa5f2c35e40 | 12074712977649210 | 12074712977662532 | 12074712977908290 | 12074712977929030 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7fa722cfe400 | 0x7fa5f2c35e80 | 12074712977954397 | 12074712977967329 | 12074712978092928 | 12074712978096231 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7fa722cfe300 | 0x7fa5f2c35ec0 | 12074712978123852 | 12074712978136928 | 12074712978265247 | 12074712978268621 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7fa722cfea00 | 0x7fa5f2c35f00 | 12074712978306592 | 12074712978322847 | 12074712978447486 | 12074712978450689 |
| 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 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7fa722cfe900 | 0x7fa5f2c35f40 | 12074712978478100 | 12074712978491645 | 12074712978742843 | 12074712978763130 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7fa722cfe800 | 0x7fa5f2c35f80 | 12074712978784981 | 12074712978798203 | 12074712979044921 | 12074712979069860 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7fa722cfe700 | 0x7fa5f2c35fc0 | 12074712979091691 | 12074712979104920 | 12074712979229559 | 12074712979232733 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7fa722cfe600 | 0x7fa5f2c36000 | 12074712979260504 | 12074712979273399 | 12074712979409878 | 12074712979412958 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7fa722cfe500 | 0x7fa5f2c36040 | 12074712979452872 | 12074712979466357 | 12074712979591636 | 12074712979594876 |
| 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 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7fa722cfe400 | 0x7fa5f2c36080 | 12074712979622096 | 12074712979635956 | 12074712979892274 | 12074712979909150 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7fa722cfe300 | 0x7fa5f2c360c0 | 12074712979937573 | 12074712979950833 | 12074712980197871 | 12074712980222993 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7fa722cfea00 | 0x7fa5f2c36100 | 12074712980244233 | 12074712980257071 | 12074712980381550 | 12074712980384744 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7fa722cfe900 | 0x7fa5f2c36140 | 12074712980412615 | 12074712980425709 | 12074712980568428 | 12074712980571390 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7fa722cfe800 | 0x7fa5f2c36180 | 12074712980609401 | 12074712980622348 | 12074712980747147 | 12074712980750113 |
| 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 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7fa722cfe700 | 0x7fa5f2c361c0 | 12074712980777383 | 12074712980792106 | 12074712981047304 | 12074712981069396 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7fa722cfe600 | 0x7fa5f2c36200 | 12074712981090706 | 12074712981104104 | 12074712981351622 | 12074712981375535 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7fa722cfe500 | 0x7fa5f2c36240 | 12074712981400902 | 12074712981414341 | 12074712981539300 | 12074712981542525 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7fa722cfe400 | 0x7fa5f2c36280 | 12074712981568774 | 12074712981582180 | 12074712981731619 | 12074712981734933 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7fa722cfe300 | 0x7fa5f2c362c0 | 12074712981791849 | 12074712981805218 | 12074712981931617 | 12074712981934854 |
| 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 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7fa722cfea00 | 0x7fa5f2c36300 | 12074712981961684 | 12074712981974977 | 12074712982228575 | 12074712982256091 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7fa722cfe900 | 0x7fa5f2c36340 | 12074712982276960 | 12074712982290174 | 12074712982539612 | 12074712982564364 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7fa722cfe800 | 0x7fa5f2c36380 | 12074712982586014 | 12074712982598972 | 12074712982724411 | 12074712982727487 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7fa722cfe700 | 0x7fa5f2c363c0 | 12074712982754297 | 12074712982767290 | 12074712982924089 | 12074712982927229 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7fa722cfe600 | 0x7fa5f2c36400 | 12074712982966361 | 12074712982979929 | 12074712983104888 | 12074712983108165 |
| 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 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7fa722cfe500 | 0x7fa5f2c36440 | 12074712983136077 | 12074712983149207 | 12074712983414165 | 12074712983435132 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7fa722cfe400 | 0x7fa5f2c36480 | 12074712983458155 | 12074712983470805 | 12074712983715283 | 12074712983735881 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7fa722cfe300 | 0x7fa5f2c364c0 | 12074712983756480 | 12074712983769362 | 12074712983896081 | 12074712983899115 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7fa722cfea00 | 0x7fa5f2c36500 | 12074712983927267 | 12074712983939921 | 12074712984104400 | 12074712984108073 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7fa722cfe900 | 0x7fa5f2c36540 | 12074712984146104 | 12074712984159599 | 12074712984285198 | 12074712984288238 |
| 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 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7fa722cfe800 | 0x7fa5f2c36580 | 12074712984315288 | 12074712984327278 | 12074712984581836 | 12074712984602792 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7fa722cfe700 | 0x7fa5f2c365c0 | 12074712984625795 | 12074712984638635 | 12074712984882793 | 12074712984907348 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7fa722cfe600 | 0x7fa5f2c36600 | 12074712984932335 | 12074712984945353 | 12074712985070152 | 12074712985073517 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7fa722cfe500 | 0x7fa5f2c36640 | 12074712985099165 | 12074712985111911 | 12074712985284550 | 12074712985287665 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7fa722cfe400 | 0x7fa5f2c36680 | 12074712985326878 | 12074712985340710 | 12074712985467269 | 12074712985470535 |
| 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 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7fa722cfe300 | 0x7fa5f2c366c0 | 12074712985497826 | 12074712985511108 | 12074712985766466 | 12074712985783767 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7fa722cfea00 | 0x7fa5f2c36700 | 12074712985809124 | 12074712985821826 | 12074712986065984 | 12074712986095947 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7fa722cfe900 | 0x7fa5f2c36740 | 12074712986116656 | 12074712986129663 | 12074712986255262 | 12074712986258449 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7fa722cfe800 | 0x7fa5f2c36780 | 12074712986286501 | 12074712986299102 | 12074712986481180 | 12074712986484359 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7fa722cfe700 | 0x7fa5f2c367c0 | 12074712986524153 | 12074712986537980 | 12074712986664059 | 12074712986667038 |
| 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 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7fa722cfe600 | 0x7fa5f2c36800 | 12074712986693738 | 12074712986706938 | 12074712986969816 | 12074712986990319 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7fa722cfe500 | 0x7fa5f2c36840 | 12074712987015215 | 12074712987028216 | 12074712987274774 | 12074712987299544 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7fa722cfe400 | 0x7fa5f2c36880 | 12074712987321775 | 12074712987334453 | 12074712987460212 | 12074712987463278 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7fa722cfe300 | 0x7fa5f2c368c0 | 12074712987489978 | 12074712987502932 | 12074712987693970 | 12074712987697053 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7fa722cfea00 | 0x7fa5f2c36900 | 12074712987734713 | 12074712987747890 | 12074712987874929 | 12074712987878059 |
| 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 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7fa722cfe900 | 0x7fa5f2c36940 | 12074712987904648 | 12074712987917489 | 12074712988199246 | 12074712988225945 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7fa722cfe800 | 0x7fa5f2c36980 | 12074712988246484 | 12074712988259406 | 12074712988505964 | 12074712988530151 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7fa722cfe700 | 0x7fa5f2c369c0 | 12074712988553835 | 12074712988567083 | 12074712988692522 | 12074712988695588 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7fa722cfe600 | 0x7fa5f2c36a00 | 12074712988723650 | 12074712988736362 | 12074712988945160 | 12074712988965660 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7fa722cfe500 | 0x7fa5f2c36a40 | 12074712988997058 | 12074712989014760 | 12074712989141959 | 12074712989145384 |
| 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 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7fa722cfe400 | 0x7fa5f2c36a80 | 12074712989172024 | 12074712989185318 | 12074712989491556 | 12074712989515231 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7fa722cfe300 | 0x7fa5f2c36ac0 | 12074712989535860 | 12074712989548515 | 12074712989794273 | 12074712989818365 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7fa722cfea00 | 0x7fa5f2c36b00 | 12074712989840736 | 12074712989853953 | 12074712989980352 | 12074712989983442 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7fa722cfe900 | 0x7fa5f2c36b40 | 12074712990016723 | 12074712990029471 | 12074712990256350 | 12074712990280113 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7fa722cfe800 | 0x7fa5f2c36b80 | 12074712990315198 | 12074712990328509 | 12074712990455548 | 12074712990458655 |
| 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 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7fa722cfe700 | 0x7fa5f2c36bc0 | 12074712990485965 | 12074712990499388 | 12074712990828185 | 12074712990848830 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7fa722cfe600 | 0x7fa5f2c36c00 | 12074712990869759 | 12074712990882745 | 12074712991129783 | 12074712991150681 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7fa722cfe500 | 0x7fa5f2c36c40 | 12074712991171800 | 12074712991184502 | 12074712991313301 | 12074712991316659 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7fa722cfe400 | 0x7fa5f2c36c80 | 12074712991343910 | 12074712991356661 | 12074712991600499 | 12074712991624762 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7fa722cfe300 | 0x7fa5f2c36cc0 | 12074712991657052 | 12074712991670258 | 12074712991799377 | 12074712991802572 |
| 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 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7fa722cfea00 | 0x7fa5f2c36d00 | 12074712991829472 | 12074712991842577 | 12074712992217774 | 12074712992245315 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7fa722cfe900 | 0x7fa5f2c36d40 | 12074712992266544 | 12074712992279533 | 12074712992535531 | 12074712992559799 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7fa722cfe800 | 0x7fa5f2c36d80 | 12074712992583784 | 12074712992596971 | 12074712992726570 | 12074712992729705 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7fa722cfe700 | 0x7fa5f2c36dc0 | 12074712992755914 | 12074712992768809 | 12074712993047207 | 12074712993072262 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7fa722cfe600 | 0x7fa5f2c36e00 | 12074712993104231 | 12074712993118246 | 12074712993253285 | 12074712993256484 |
| 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 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7fa722cfe500 | 0x7fa5f2c36e40 | 12074712993282993 | 12074712993295845 | 12074712993718722 | 12074712993742698 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7fa722cfe400 | 0x7fa5f2c36e80 | 12074712993764769 | 12074712993777441 | 12074712994032799 | 12074712994057202 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7fa722cfe300 | 0x7fa5f2c36ec0 | 12074712994078622 | 12074712994091518 | 12074712994227357 | 12074712994230644 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7fa722cfea00 | 0x7fa5f2c36f00 | 12074712994256432 | 12074712994269437 | 12074712994582235 | 12074712994603848 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7fa722cfe900 | 0x7fa5f2c36f40 | 12074712994638893 | 12074712994652474 | 12074712994803673 | 12074712994806805 |
| 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 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7fa722cfe800 | 0x7fa5f2c36f80 | 12074712994833505 | 12074712994846552 | 12074712995363028 | 12074712995393936 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7fa722cfe700 | 0x7fa5f2c36fc0 | 12074712995415506 | 12074712995427988 | 12074712995725905 | 12074712995750238 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7fa722cfe600 | 0x7fa5f2c37000 | 12074712995772129 | 12074712995785105 | 12074712995938383 | 12074712995941494 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7fa722cfe500 | 0x7fa5f2c37040 | 12074712995967382 | 12074712995980463 | 12074712996365260 | 12074712996392853 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7fa722cfe400 | 0x7fa5f2c37080 | 12074712996425583 | 12074712996438699 | 12074712996614538 | 12074712996617710 |
| 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 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7fa722cfe300 | 0x7fa5f2c370c0 | 12074712996644510 | 12074712996657738 | 12074712997267173 | 12074712997291302 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7fa722cfea00 | 0x7fa5f2c37100 | 12074712997313273 | 12074712997325732 | 12074712997653090 | 12074712997677239 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7fa722cfe900 | 0x7fa5f2c37140 | 12074712997700132 | 12074712997713089 | 12074712997892288 | 12074712997895555 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7fa722cfe800 | 0x7fa5f2c37180 | 12074712997921583 | 12074712997934207 | 12074712998389724 | 12074712998419609 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7fa722cfe700 | 0x7fa5f2c371c0 | 12074712998453682 | 12074712998466683 | 12074712998665721 | 12074712998689330 |
| 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 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7fa722cfe600 | 0x7fa5f2c37200 | 12074712998709107 | 12074712998722201 | 12074712999432275 | 12074712999457187 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7fa722cfe500 | 0x7fa5f2c37240 | 12074712999480951 | 12074712999493715 | 12074712999892111 | 12074712999916741 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7fa722cfe400 | 0x7fa5f2c37280 | 12074712999937440 | 12074712999950031 | 12074713000152909 | 12074713000182335 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7fa722cfe300 | 0x7fa5f2c372c0 | 12074713000205057 | 12074713000217869 | 12074713000742664 | 12074713000768204 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7fa722cfea00 | 0x7fa5f2c37300 | 12074713000802678 | 12074713000815944 | 12074713001039142 | 12074713001063843 |
| 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 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7fa722cfe900 | 0x7fa5f2c37340 | 12074713001085363 | 12074713001098502 | 12074713001896095 | 12074713001919653 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7fa722cfe800 | 0x7fa5f2c37380 | 12074713001939400 | 12074713001951775 | 12074713002372091 | 12074713002396540 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7fa722cfe700 | 0x7fa5f2c373c0 | 12074713002418550 | 12074713002430971 | 12074713002656569 | 12074713002680567 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7fa722cfe600 | 0x7fa5f2c37400 | 12074713002701807 | 12074713002714328 | 12074713003323924 | 12074713003348919 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7fa722cfe500 | 0x7fa5f2c37440 | 12074713003380949 | 12074713003393843 | 12074713003662961 | 12074713003687108 |
| 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 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7fa722cfe400 | 0x7fa5f2c37480 | 12074713003707275 | 12074713003720720 | 12074713004705352 | 12074713004730557 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7fa722cfe300 | 0x7fa5f2c374c0 | 12074713004751165 | 12074713004763752 | 12074713005277668 | 12074713005304433 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7fa722cfea00 | 0x7fa5f2c37500 | 12074713005329791 | 12074713005342947 | 12074713005614785 | 12074713005639326 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7fa722cfe900 | 0x7fa5f2c37540 | 12074713005660936 | 12074713005673824 | 12074713006415898 | 12074713006441957 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7fa722cfe800 | 0x7fa5f2c37580 | 12074713006475830 | 12074713006489018 | 12074713006803735 | 12074713006828065 |
| 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 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7fa722cfe700 | 0x7fa5f2c375c0 | 12074713006848813 | 12074713006861975 | 12074713008033965 | 12074713008064883 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7fa722cfe600 | 0x7fa5f2c37600 | 12074713008087175 | 12074713008099725 | 12074713008708520 | 12074713008733466 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7fa722cfe500 | 0x7fa5f2c37640 | 12074713008755146 | 12074713008767399 | 12074713009086597 | 12074713009113242 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7fa722cfe400 | 0x7fa5f2c37680 | 12074713009134942 | 12074713009147876 | 12074713010025629 | 12074713010051976 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7fa722cfe300 | 0x7fa5f2c376c0 | 12074713010086721 | 12074713010099549 | 12074713010511065 | 12074713010538079 |
| 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 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7fa722cfea00 | 0x7fa5f2c37700 | 12074713010563437 | 12074713010576825 | 12074713012127052 | 12074713012195029 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7fa722cfe900 | 0x7fa5f2c37740 | 12074713012216950 | 12074713012230702 | 12074713013028457 | 12074713013082228 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7fa722cfe800 | 0x7fa5f2c37780 | 12074713013102275 | 12074713013115495 | 12074713013530372 | 12074713013598387 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7fa722cfe700 | 0x7fa5f2c377c0 | 12074713013621550 | 12074713013635012 | 12074713014794204 | 12074713014861594 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7fa722cfe600 | 0x7fa5f2c37800 | 12074713014894255 | 12074713014908123 | 12074713015693397 | 12074713015763671 |
| 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 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7fa722cfe500 | 0x7fa5f2c37840 | 12074713015787585 | 12074713015801236 | 12074713018852895 | 12074713018920567 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7fa722cfe400 | 0x7fa5f2c37880 | 12074713018943791 | 12074713018956894 | 12074713020499124 | 12074713020570664 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7fa722cfe300 | 0x7fa5f2c378c0 | 12074713020595380 | 12074713020609523 | 12074713021398957 | 12074713021466829 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7fa722cfea00 | 0x7fa5f2c37900 | 12074713021490974 | 12074713021503597 | 12074713023784861 | 12074713023852483 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7fa722cfe900 | 0x7fa5f2c37940 | 12074713023886025 | 12074713023900700 | 12074713025435729 | 12074713025506456 |
| 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 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7fa722cfe800 | 0x7fa5f2c37980 | 12074713025531373 | 12074713025543408 | 12074713031598886 | 12074713031666634 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7fa722cfe700 | 0x7fa5f2c379c0 | 12074713031690488 | 12074713031701765 | 12074713034744624 | 12074713034813041 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7fa722cfe600 | 0x7fa5f2c37a00 | 12074713034834431 | 12074713034846543 | 12074713036384933 | 12074713036458038 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 845736 | 845741 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7fa722cfe500 | 0x7fa5f2c37a40 | 12074713036481332 | 12074713036493092 | 12074713041019940 | 12074713041088874 |