54 KiB
54 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | SQ_CYCLES | SQ_BUSY_CYCLES | SQ_BUSY_CU_CYCLES | SQ_WAVES | SQ_WAVE_CYCLES | GRBM_COUNT | GRBM_GUI_ACTIVE | TD_TD_BUSY_sum | TD_TC_STALL_sum | TD_COALESCABLE_WAVEFRONT_sum | TD_LOAD_WAVEFRONT_sum | TD_ATOMIC_WAVEFRONT_sum | TD_STORE_WAVEFRONT_sum | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBuffer.kd | 0 | 0 | 0 | 860709 | 860715 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7f588cc04180 | 4038864 | 3835198 | 57371238 | 524288 | 367403680 | 504857 | 504857 | 55595309 | 54413933 | 1048576 | 1048576 | 0 | 1048576 | 12075089892782251 | 12075093208489155 | 12075093208815232 | 12075090134629592 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 860709 | 860715 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7f588cc35100 | 218424 | 73402 | 1035867 | 512 | 1105318 | 27302 | 27302 | 592232 | 571748 | 4096 | 4096 | 0 | 0 | 12075090149202244 | 12075093223931152 | 12075093223937872 | 12075090149710528 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7f59987a3900 | 0x7f588cc35140 | 1790312 | 1602551 | 23768599 | 65536 | 142188998 | 223788 | 223788 | 23284372 | 21124335 | 524288 | 524288 | 0 | 0 | 12075090149874072 | 12075093224005071 | 12075093224143150 | 12075090150529119 |
| 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 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7f59987a3800 | 0x7f588cc35180 | 3129192 | 2949587 | 43974220 | 65536 | 244296485 | 391148 | 391148 | 43477976 | 35084146 | 0 | 524288 | 0 | 0 | 12075090150784985 | 12075093224210190 | 12075093224457388 | 12075090151470689 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7f59987a3700 | 0x7f588cc351c0 | 3282880 | 3115344 | 46363930 | 65536 | 293327799 | 410359 | 410359 | 46003328 | 37610898 | 0 | 524288 | 0 | 0 | 12075090151637359 | 12075093224593867 | 12075093224841225 | 12075090152343501 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7f59987a3600 | 0x7f588cc35200 | 1720768 | 1560404 | 23076825 | 65536 | 149647913 | 215095 | 215095 | 22566152 | 20402359 | 524288 | 524288 | 0 | 0 | 12075090152511003 | 12075093224975944 | 12075093225101543 | 12075090153009299 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7f59987a3500 | 0x7f588cc35240 | 1735128 | 1575640 | 23320023 | 65536 | 147189490 | 216890 | 216890 | 22859796 | 20693632 | 524288 | 524288 | 0 | 0 | 12075090153244355 | 12075093225147302 | 12075093225272901 | 12075090153743503 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7f59987a3400 | 0x7f588cc35280 | 1698432 | 1545179 | 22887283 | 65536 | 162234843 | 212303 | 212303 | 22465420 | 20292312 | 524288 | 524288 | 0 | 0 | 12075090154017252 | 12075093225347461 | 12075093225472100 | 12075090154514686 |
| 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 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7f59987a3300 | 0x7f588cc352c0 | 3211096 | 3045914 | 45460045 | 65536 | 275989559 | 401386 | 401386 | 44913812 | 36518629 | 0 | 524288 | 0 | 0 | 12075090154750855 | 12075093225516099 | 12075093225764257 | 12075090155473237 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7f59987a3a00 | 0x7f588cc35300 | 3220208 | 3057169 | 45618706 | 65536 | 233722964 | 402525 | 402525 | 45256264 | 36862769 | 0 | 524288 | 0 | 0 | 12075090155633064 | 12075093225892576 | 12075093226137054 | 12075090156323247 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7f59987a3900 | 0x7f588cc35340 | 1732264 | 1569321 | 23230867 | 65536 | 162792510 | 216532 | 216532 | 22740276 | 20571336 | 524288 | 524288 | 0 | 0 | 12075090156481441 | 12075093226267773 | 12075093226392572 | 12075090156994515 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7f59987a3800 | 0x7f588cc35380 | 1714800 | 1558592 | 23054762 | 65536 | 146142875 | 214349 | 214349 | 22524712 | 20353840 | 524288 | 524288 | 0 | 0 | 12075090157225995 | 12075093226434332 | 12075093226559131 | 12075090157706818 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7f59987a3700 | 0x7f588cc353c0 | 1725096 | 1553081 | 23056049 | 65536 | 162441693 | 215636 | 215636 | 22585040 | 20417671 | 524288 | 524288 | 0 | 0 | 12075090157958426 | 12075093226615291 | 12075093226740250 | 12075090158464296 |
| 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 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7f59987a3600 | 0x7f588cc35400 | 3078184 | 2917749 | 43551845 | 65536 | 348975247 | 384772 | 384772 | 43039092 | 34646605 | 0 | 524288 | 0 | 0 | 12075090158696638 | 12075093226783449 | 12075093227027767 | 12075090159380990 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7f59987a3500 | 0x7f588cc35440 | 3137088 | 2973692 | 44392997 | 65536 | 356686497 | 392135 | 392135 | 44013392 | 35620836 | 0 | 524288 | 0 | 0 | 12075090159548321 | 12075093227158486 | 12075093227402804 | 12075090160242220 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7f59987a3400 | 0x7f588cc35480 | 1716160 | 1557164 | 23047502 | 65536 | 166333299 | 214519 | 214519 | 22531048 | 20362067 | 524288 | 524288 | 0 | 0 | 12075090160404271 | 12075093227506324 | 12075093227631603 | 12075090160927494 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7f59987a3300 | 0x7f588cc354c0 | 1734232 | 1566152 | 23265348 | 65536 | 156393952 | 216778 | 216778 | 22749188 | 20587633 | 524288 | 524288 | 0 | 0 | 12075090161159375 | 12075093227674162 | 12075093227799121 | 12075090161676145 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7f59987a3a00 | 0x7f588cc35500 | 1711280 | 1551696 | 22990509 | 65536 | 162759011 | 213909 | 213909 | 22533360 | 20361295 | 524288 | 524288 | 0 | 0 | 12075090161924987 | 12075093227852561 | 12075093227976720 | 12075090162428673 |
| 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 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7f59987a3900 | 0x7f588cc35540 | 3220632 | 3046449 | 45377862 | 65536 | 251478761 | 402578 | 402578 | 44826468 | 36433345 | 0 | 524288 | 0 | 0 | 12075090162665714 | 12075093228022959 | 12075093228267438 | 12075090163369802 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7f59987a3800 | 0x7f588cc35580 | 3218136 | 3043794 | 45343636 | 65536 | 254429525 | 402266 | 402266 | 44969124 | 36576582 | 0 | 524288 | 0 | 0 | 12075090163533717 | 12075093228372877 | 12075093228618795 | 12075090164234048 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7f59987a3700 | 0x7f588cc355c0 | 1659880 | 1494709 | 22202825 | 65536 | 159652050 | 207484 | 207484 | 21718244 | 19542391 | 524288 | 524288 | 0 | 0 | 12075090164399165 | 12075093228717034 | 12075093228841833 | 12075090164892793 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7f59987a3600 | 0x7f588cc35600 | 1696704 | 1537408 | 22786417 | 65536 | 151420152 | 212087 | 212087 | 22198712 | 20030228 | 524288 | 524288 | 0 | 0 | 12075090165133049 | 12075093228883913 | 12075093229009672 | 12075090165655069 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7f59987a3500 | 0x7f588cc35640 | 1660696 | 1498088 | 22282560 | 65536 | 165066931 | 207586 | 207586 | 21818744 | 19646242 | 524288 | 524288 | 0 | 0 | 12075090165900014 | 12075093229063271 | 12075093229187110 | 12075090166390506 |
| 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 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7f59987a3400 | 0x7f588cc35680 | 3149992 | 2960786 | 44110518 | 65536 | 319775004 | 393748 | 393748 | 43585448 | 35192817 | 0 | 524288 | 0 | 0 | 12075090166621465 | 12075093229230470 | 12075093229481828 | 12075090167312269 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7f59987a3300 | 0x7f588cc356c0 | 3146456 | 2957738 | 44128878 | 65536 | 320653194 | 393306 | 393306 | 43721392 | 35328521 | 0 | 524288 | 0 | 0 | 12075090167473829 | 12075093229558307 | 12075093229801025 | 12075090168191403 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7f59987a3a00 | 0x7f588cc35700 | 1655552 | 1503491 | 22259976 | 65536 | 166951989 | 206943 | 206943 | 21800892 | 19624055 | 524288 | 524288 | 0 | 0 | 12075090168358984 | 12075093229899745 | 12075093230024064 | 12075090168853523 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7f59987a3900 | 0x7f588cc35740 | 1709160 | 1545988 | 22895973 | 65536 | 168367196 | 213644 | 213644 | 22297624 | 20131938 | 524288 | 524288 | 0 | 0 | 12075090169085414 | 12075093230067103 | 12075093230192062 | 12075090169614367 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7f59987a3800 | 0x7f588cc35780 | 1669032 | 1513912 | 22415028 | 65536 | 163068381 | 208628 | 208628 | 21914044 | 19735352 | 524288 | 524288 | 0 | 0 | 12075090169851287 | 12075093230244862 | 12075093230369661 | 12075090170386722 |
| 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 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7f59987a3700 | 0x7f588cc357c0 | 3102144 | 2917048 | 43448968 | 65536 | 288873949 | 387767 | 387767 | 42906264 | 34513335 | 0 | 524288 | 0 | 0 | 12075090170612592 | 12075093230412061 | 12075093230698938 | 12075090171317001 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7f59987a3600 | 0x7f588cc35800 | 3199384 | 3031673 | 45210261 | 65536 | 299371608 | 399922 | 399922 | 44782080 | 36389164 | 0 | 524288 | 0 | 0 | 12075090171492167 | 12075093230802297 | 12075093231048856 | 12075090172176468 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7f59987a3500 | 0x7f588cc35840 | 1728896 | 1562577 | 23137919 | 65536 | 161040347 | 216111 | 216111 | 22674284 | 20509363 | 524288 | 524288 | 0 | 0 | 12075090172341234 | 12075093231132855 | 12075093231257174 | 12075090172870839 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7f59987a3400 | 0x7f588cc35880 | 1680896 | 1517928 | 22409041 | 65536 | 159783295 | 210111 | 210111 | 21774992 | 19599109 | 524288 | 524288 | 0 | 0 | 12075090173104232 | 12075093231298294 | 12075093231424533 | 12075090173631412 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7f59987a3300 | 0x7f588cc358c0 | 1698968 | 1542530 | 22834767 | 65536 | 155453276 | 212370 | 212370 | 22363048 | 20198662 | 524288 | 524288 | 0 | 0 | 12075090173870236 | 12075093231477012 | 12075093231601491 | 12075090174396835 |
| 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 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7f59987a3a00 | 0x7f588cc35900 | 3154408 | 2975311 | 44343052 | 65536 | 301316229 | 394300 | 394300 | 43793692 | 35396615 | 0 | 524288 | 0 | 0 | 12075090174625099 | 12075093231641651 | 12075093231886769 | 12075090175328235 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7f59987a3900 | 0x7f588cc35940 | 3173848 | 3006575 | 44766734 | 65536 | 294865205 | 396730 | 396730 | 44370620 | 35978106 | 0 | 524288 | 0 | 0 | 12075090175489896 | 12075093231944208 | 12075093232188527 | 12075090176223559 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7f59987a3800 | 0x7f588cc35980 | 1743424 | 1590755 | 23546248 | 65536 | 157187288 | 217927 | 217927 | 23063632 | 20902546 | 524288 | 524288 | 0 | 0 | 12075090176384418 | 12075093232274126 | 12075093232399245 | 12075090176927007 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7f59987a3700 | 0x7f588cc359c0 | 1746200 | 1584903 | 23442390 | 65536 | 159646049 | 218274 | 218274 | 22815316 | 20651730 | 524288 | 524288 | 0 | 0 | 12075090177157435 | 12075093232441005 | 12075093232566284 | 12075090177671290 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7f59987a3600 | 0x7f588cc35a00 | 1741544 | 1562035 | 23130828 | 65536 | 164044352 | 217692 | 217692 | 22633816 | 20468699 | 524288 | 524288 | 0 | 0 | 12075090177913610 | 12075093232618123 | 12075093232742922 | 12075090178411666 |
| 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 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7f59987a3500 | 0x7f588cc35a40 | 3223464 | 3043601 | 45267568 | 65536 | 260425546 | 402932 | 402932 | 44689016 | 36294457 | 0 | 524288 | 0 | 0 | 12075090178638808 | 12075093232785802 | 12075093233037960 | 12075090179383882 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7f59987a3400 | 0x7f588cc35a80 | 3127296 | 2954472 | 44027634 | 65536 | 312490012 | 390911 | 390911 | 43600076 | 35207622 | 0 | 524288 | 0 | 0 | 12075090179547627 | 12075093233104679 | 12075093233350917 | 12075090180248910 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7f59987a3300 | 0x7f588cc35ac0 | 1657408 | 1492575 | 22157404 | 65536 | 157815171 | 207175 | 207175 | 21635100 | 19460442 | 524288 | 524288 | 0 | 0 | 12075090180412564 | 12075093233417317 | 12075093233542276 | 12075090180911702 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7f59987a3a00 | 0x7f588cc35b00 | 1737624 | 1569956 | 23051617 | 65536 | 161107796 | 217202 | 217202 | 22230536 | 20053401 | 524288 | 524288 | 0 | 0 | 12075090181144624 | 12075093233585315 | 12075093233711074 | 12075090181653380 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7f59987a3900 | 0x7f588cc35b40 | 1708224 | 1545893 | 22817398 | 65536 | 161300074 | 213527 | 213527 | 22292760 | 20122013 | 524288 | 524288 | 0 | 0 | 12075090181890771 | 12075093233763714 | 12075093233888833 | 12075090182426987 |
| 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 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7f59987a3800 | 0x7f588cc35b80 | 3264872 | 3083317 | 45839250 | 65536 | 282003431 | 408108 | 408108 | 45261240 | 36865024 | 0 | 524288 | 0 | 0 | 12075090182655182 | 12075093233930273 | 12075093234184671 | 12075090183370841 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7f59987a3700 | 0x7f588cc35bc0 | 3188928 | 3022349 | 45136673 | 65536 | 265580559 | 398615 | 398615 | 44706572 | 36314013 | 0 | 524288 | 0 | 0 | 12075090183535247 | 12075093234248190 | 12075093234493788 | 12075090184267167 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7f59987a3600 | 0x7f588cc35c00 | 1683200 | 1526334 | 22569912 | 65536 | 162775190 | 210399 | 210399 | 22053488 | 19883193 | 524288 | 524288 | 0 | 0 | 12075090184422225 | 12075093234554588 | 12075093234678747 | 12075090184964172 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7f59987a3500 | 0x7f588cc35c40 | 1751128 | 1584429 | 23262235 | 65536 | 165514455 | 218890 | 218890 | 22377756 | 20202166 | 524288 | 524288 | 0 | 0 | 12075090185193589 | 12075093234721626 | 12075093234848665 | 12075090185720047 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7f59987a3400 | 0x7f588cc35c80 | 1673192 | 1512002 | 22409084 | 65536 | 161589533 | 209148 | 209148 | 21865224 | 19694132 | 524288 | 524288 | 0 | 0 | 12075090185959432 | 12075093234902905 | 12075093235027864 | 12075090186464020 |
| 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 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7f59987a3300 | 0x7f588cc35cc0 | 3191360 | 3022851 | 44928613 | 65536 | 320230553 | 398919 | 398919 | 44367588 | 35971478 | 0 | 524288 | 0 | 0 | 12075090186711059 | 12075093235071224 | 12075093235329142 | 12075090187407603 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7f59987a3a00 | 0x7f588cc35d00 | 3103720 | 2938206 | 43761449 | 65536 | 295983158 | 387964 | 387964 | 43314732 | 34918270 | 0 | 524288 | 0 | 0 | 12075090187569484 | 12075093235385301 | 12075093235633299 | 12075090188301054 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7f59987a3900 | 0x7f588cc35d40 | 1710616 | 1552315 | 22944351 | 65536 | 161036036 | 213826 | 213826 | 22381776 | 20217298 | 524288 | 524288 | 0 | 0 | 12075090188460831 | 12075093235690099 | 12075093235814578 | 12075090188991366 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7f59987a3800 | 0x7f588cc35d80 | 1804416 | 1643679 | 24123698 | 65536 | 179358305 | 225551 | 225551 | 23022920 | 20850262 | 524288 | 524288 | 0 | 0 | 12075090189220252 | 12075093235855698 | 12075093235983856 | 12075090189738345 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7f59987a3700 | 0x7f588cc35dc0 | 1690240 | 1529303 | 22623440 | 65536 | 167222899 | 211279 | 211279 | 22062972 | 19887008 | 524288 | 524288 | 0 | 0 | 12075090189978070 | 12075093236041776 | 12075093236166415 | 12075090190509418 |
| 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 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7f59987a3600 | 0x7f588cc35e00 | 3211304 | 3054006 | 45423665 | 65536 | 338851236 | 401412 | 401412 | 44761756 | 36366522 | 0 | 524288 | 0 | 0 | 12075090190741379 | 12075093236209295 | 12075093236467213 | 12075090191450336 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7f59987a3500 | 0x7f588cc35e40 | 3139376 | 2984920 | 44525025 | 65536 | 259810264 | 392421 | 392421 | 44068596 | 35667706 | 0 | 524288 | 0 | 0 | 12075090191611806 | 12075093236520652 | 12075093236767530 | 12075090192318670 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7f59987a3400 | 0x7f588cc35e80 | 1785792 | 1620131 | 23982123 | 65536 | 161540335 | 223223 | 223223 | 23430148 | 21270108 | 524288 | 524288 | 0 | 0 | 12075090192481152 | 12075093236825930 | 12075093236951049 | 12075090193011808 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7f59987a3300 | 0x7f588cc35ec0 | 1831384 | 1657404 | 24245393 | 65536 | 181398032 | 228922 | 228922 | 22288044 | 20088521 | 524288 | 524288 | 0 | 0 | 12075090193236656 | 12075093236993449 | 12075093237122727 | 12075090193774255 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7f59987a3a00 | 0x7f588cc35f00 | 1682560 | 1525309 | 22551448 | 65536 | 164631930 | 210319 | 210319 | 22036600 | 19859552 | 524288 | 524288 | 0 | 0 | 12075090193980688 | 12075093237177607 | 12075093237303206 | 12075090194537714 |
| 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 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7f59987a3900 | 0x7f588cc35f40 | 3254808 | 3090003 | 45947536 | 65536 | 358859196 | 406850 | 406850 | 45295928 | 36900711 | 0 | 524288 | 0 | 0 | 12075090194762962 | 12075093237344326 | 12075093237600324 | 12075090195474444 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7f59987a3800 | 0x7f588cc35f80 | 3131136 | 2963920 | 44131821 | 65536 | 281808427 | 391391 | 391391 | 43669076 | 35276447 | 0 | 524288 | 0 | 0 | 12075090195641034 | 12075093237655683 | 12075093237899841 | 12075090196336607 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7f59987a3700 | 0x7f588cc35fc0 | 1716352 | 1560379 | 23106671 | 65536 | 164516277 | 214543 | 214543 | 22596440 | 20427477 | 524288 | 524288 | 0 | 0 | 12075090196501483 | 12075093237960641 | 12075093238085600 | 12075090197013955 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7f59987a3600 | 0x7f588cc36000 | 1793856 | 1626304 | 23983850 | 65536 | 185045554 | 224231 | 224231 | 20002852 | 17732267 | 524288 | 524288 | 0 | 0 | 12075090197243442 | 12075093238128480 | 12075093238267198 | 12075090197756535 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7f59987a3500 | 0x7f588cc36040 | 1731224 | 1564799 | 23130758 | 65536 | 169180862 | 216402 | 216402 | 22568340 | 20393991 | 524288 | 524288 | 0 | 0 | 12075090197987605 | 12075093238322238 | 12075093238446397 | 12075090198498234 |
| 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 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7f59987a3400 | 0x7f588cc36080 | 3248128 | 3069245 | 45604057 | 65536 | 312680614 | 406015 | 406015 | 44958924 | 36561488 | 0 | 524288 | 0 | 0 | 12075090198725446 | 12075093238487517 | 12075093238749755 | 12075090199426088 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7f59987a3300 | 0x7f588cc360c0 | 3129128 | 2963499 | 44228044 | 65536 | 293211678 | 391140 | 391140 | 43794760 | 35401935 | 0 | 524288 | 0 | 0 | 12075090199587718 | 12075093238803034 | 12075093239049432 | 12075090200286818 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7f59987a3a00 | 0x7f588cc36100 | 1731584 | 1572471 | 23266205 | 65536 | 164897928 | 216447 | 216447 | 22718024 | 20552659 | 524288 | 524288 | 0 | 0 | 12075090200422971 | 12075093239110712 | 12075093239235831 | 12075090200975698 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7f59987a3900 | 0x7f588cc36140 | 1840472 | 1677050 | 24878234 | 65536 | 195917069 | 230058 | 230058 | 19041136 | 16715834 | 524288 | 524288 | 0 | 0 | 12075090201209011 | 12075093239277910 | 12075093239419509 | 12075090201731783 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7f59987a3800 | 0x7f588cc36180 | 1661440 | 1506433 | 22361507 | 65536 | 166922630 | 207679 | 207679 | 21763088 | 19594782 | 524288 | 524288 | 0 | 0 | 12075090201969575 | 12075093239472309 | 12075093239597748 | 12075090202470255 |
| 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 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7f59987a3700 | 0x7f588cc361c0 | 3222872 | 3030337 | 45042498 | 65536 | 298953761 | 402858 | 402858 | 44319056 | 35910543 | 0 | 524288 | 0 | 0 | 12075090202695614 | 12075093239639988 | 12075093239892466 | 12075090203420611 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7f59987a3600 | 0x7f588cc36200 | 3179544 | 2995773 | 44654123 | 65536 | 245711520 | 397442 | 397442 | 44156452 | 35763419 | 0 | 524288 | 0 | 0 | 12075090203580228 | 12075093239950385 | 12075093240197583 | 12075090204309974 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7f59987a3500 | 0x7f588cc36240 | 1751408 | 1595060 | 23521484 | 65536 | 168753094 | 218925 | 218925 | 22972984 | 20808920 | 524288 | 524288 | 0 | 0 | 12075090204470683 | 12075093240260463 | 12075093240386222 | 12075090204995027 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7f59987a3400 | 0x7f588cc36280 | 1916824 | 1759295 | 26056501 | 65536 | 209057190 | 239602 | 239602 | 18050144 | 15700032 | 524288 | 524288 | 0 | 0 | 12075090205223281 | 12075093240427821 | 12075093240576940 | 12075090205748127 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7f59987a3300 | 0x7f588cc362c0 | 1693504 | 1534629 | 22628051 | 65536 | 167824993 | 211687 | 211687 | 22058472 | 19891070 | 524288 | 524288 | 0 | 0 | 12075090205998512 | 12075093240646220 | 12075093240771979 | 12075090206512106 |
| 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 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7f59987a3a00 | 0x7f588cc36300 | 3256432 | 3068569 | 45452580 | 65536 | 268030568 | 407053 | 407053 | 44643508 | 36221749 | 0 | 524288 | 0 | 0 | 12075090206739779 | 12075093240813898 | 12075093241068456 | 12075090207478773 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7f59987a3900 | 0x7f588cc36340 | 3084608 | 2926025 | 43671179 | 65536 | 351334653 | 385575 | 385575 | 43180640 | 34788041 | 0 | 524288 | 0 | 0 | 12075090207646214 | 12075093241129736 | 12075093241376294 | 12075090208343289 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7f59987a3800 | 0x7f588cc36380 | 1653720 | 1495134 | 22160668 | 65536 | 162655604 | 206714 | 206714 | 21567616 | 19392827 | 524288 | 524288 | 0 | 0 | 12075090208506924 | 12075093241435493 | 12075093241561252 | 12075090209033763 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7f59987a3700 | 0x7f588cc363c0 | 2012864 | 1851818 | 27494622 | 65536 | 221232484 | 251607 | 251607 | 16407032 | 13969322 | 524288 | 524288 | 0 | 0 | 12075090209263369 | 12075093241603652 | 12075093241761251 | 12075090209825364 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7f59987a3600 | 0x7f588cc36400 | 1710888 | 1527177 | 22560446 | 65536 | 155651778 | 213860 | 213860 | 21950172 | 19779824 | 524288 | 524288 | 0 | 0 | 12075090210065640 | 12075093241815650 | 12075093241941249 | 12075090210571891 |
| 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 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7f59987a3500 | 0x7f588cc36440 | 3246528 | 3071243 | 45452574 | 65536 | 298953310 | 405815 | 405815 | 44564768 | 36144636 | 0 | 524288 | 0 | 0 | 12075090210803311 | 12075093241982849 | 12075093242242207 | 12075090211501659 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7f59987a3400 | 0x7f588cc36480 | 3154648 | 2984874 | 44396457 | 65536 | 329460026 | 394330 | 394330 | 43902384 | 35509141 | 0 | 524288 | 0 | 0 | 12075090211660554 | 12075093242303007 | 12075093242549405 | 12075090212380041 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7f59987a3300 | 0x7f588cc364c0 | 1759784 | 1592339 | 23465274 | 65536 | 167509200 | 219972 | 219972 | 22887548 | 20726232 | 524288 | 524288 | 0 | 0 | 12075090212541421 | 12075093242607804 | 12075093242734203 | 12075090213081625 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7f59987a3a00 | 0x7f588cc36500 | 2099928 | 1942390 | 28885887 | 65536 | 233098792 | 262490 | 262490 | 16178584 | 13733755 | 524288 | 524288 | 0 | 0 | 12075090213308396 | 12075093242774683 | 12075093242941561 | 12075090213860863 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7f59987a3900 | 0x7f588cc36540 | 1746392 | 1584596 | 23366408 | 65536 | 164904720 | 218298 | 218298 | 22701352 | 20535881 | 524288 | 524288 | 0 | 0 | 12075090214071835 | 12075093242993081 | 12075093243119160 | 12075090214616958 |
| 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 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7f59987a3800 | 0x7f588cc36580 | 3214296 | 3041119 | 45074905 | 65536 | 316387909 | 401786 | 401786 | 44000068 | 35566139 | 0 | 524288 | 0 | 0 | 12075090214842457 | 12075093243161080 | 12075093243418998 | 12075090215557035 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7f59987a3700 | 0x7f588cc365c0 | 3186456 | 3006254 | 44730606 | 65536 | 226702702 | 398306 | 398306 | 44179908 | 35783708 | 0 | 524288 | 0 | 0 | 12075090215722623 | 12075093243477877 | 12075093243727635 | 12075090216451387 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7f59987a3600 | 0x7f588cc36600 | 1732912 | 1570186 | 23213660 | 65536 | 172586408 | 216613 | 216613 | 22574276 | 20407666 | 524288 | 524288 | 0 | 0 | 12075090216611946 | 12075093243791155 | 12075093243915954 | 12075090217138745 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7f59987a3500 | 0x7f588cc36640 | 2200704 | 2041732 | 30342367 | 65536 | 244161529 | 275087 | 275087 | 15388204 | 12883862 | 524288 | 524288 | 0 | 0 | 12075090217370976 | 12075093243957873 | 12075093244130352 | 12075090217920417 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7f59987a3400 | 0x7f588cc36680 | 1740272 | 1582652 | 23298477 | 65536 | 165794687 | 217533 | 217533 | 22700348 | 20531664 | 524288 | 524288 | 0 | 0 | 12075090218165222 | 12075093244183952 | 12075093244309711 | 12075090218662306 |
| 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 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7f59987a3300 | 0x7f588cc366c0 | 3170456 | 2979230 | 44284222 | 65536 | 323993715 | 396306 | 396306 | 43041108 | 34589893 | 0 | 524288 | 0 | 0 | 12075090218893285 | 12075093244353070 | 12075093244604428 | 12075090219627069 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7f59987a3a00 | 0x7f588cc36700 | 3167128 | 2995740 | 44652512 | 65536 | 273994271 | 395890 | 395890 | 43977696 | 35572087 | 0 | 524288 | 0 | 0 | 12075090219794199 | 12075093244659948 | 12075093244911146 | 12075090220504169 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7f59987a3900 | 0x7f588cc36740 | 1761920 | 1605482 | 23658966 | 65536 | 168361860 | 220239 | 220239 | 23054928 | 20889549 | 524288 | 524288 | 0 | 0 | 12075090220662453 | 12075093244969865 | 12075093245094984 | 12075090221197317 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7f59987a3800 | 0x7f588cc36780 | 2298944 | 2147450 | 31866234 | 65536 | 258731515 | 287367 | 287367 | 15282128 | 12756486 | 524288 | 524288 | 0 | 0 | 12075090221422686 | 12075093245137224 | 12075093245319783 | 12075090221988788 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7f59987a3700 | 0x7f588cc367c0 | 1783280 | 1623644 | 23977583 | 65536 | 168081674 | 222909 | 222909 | 23126920 | 20954881 | 524288 | 524288 | 0 | 0 | 12075090222228213 | 12075093245374662 | 12075093245500421 | 12075090222733502 |
| 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 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7f59987a3600 | 0x7f588cc36800 | 3272320 | 3113278 | 46401800 | 65536 | 379860854 | 409039 | 409039 | 45875536 | 37448510 | 0 | 524288 | 0 | 0 | 12075090222952960 | 12075093245542181 | 12075093245806659 | 12075090223703775 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7f59987a3500 | 0x7f588cc36840 | 3241880 | 3054234 | 45427684 | 65536 | 270747181 | 405234 | 405234 | 44884072 | 36489951 | 0 | 524288 | 0 | 0 | 12075090223865195 | 12075093245862978 | 12075093246108096 | 12075090224600912 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7f59987a3400 | 0x7f588cc36880 | 1762200 | 1598669 | 23530434 | 65536 | 173160453 | 220274 | 220274 | 22919260 | 20752611 | 524288 | 524288 | 0 | 0 | 12075090224763715 | 12075093246167136 | 12075093246293215 | 12075090225290584 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7f59987a3300 | 0x7f588cc368c0 | 2416576 | 2253297 | 33503874 | 65536 | 272785098 | 302071 | 302071 | 15674964 | 13164050 | 524288 | 524288 | 0 | 0 | 12075090225519189 | 12075093246334975 | 12075093246525533 | 12075090226113082 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7f59987a3a00 | 0x7f588cc36900 | 1778088 | 1594453 | 23504845 | 65536 | 173725751 | 222260 | 222260 | 22655592 | 20485717 | 524288 | 524288 | 0 | 0 | 12075090226351766 | 12075093246577693 | 12075093246704412 | 12075090226856384 |
| 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 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7f59987a3900 | 0x7f588cc36940 | 3479320 | 3316647 | 49367276 | 65536 | 403374027 | 434914 | 434914 | 48769692 | 40305450 | 0 | 524288 | 0 | 0 | 12075090227064060 | 12075093246746011 | 12075093247027769 | 12075090227824032 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7f59987a3800 | 0x7f588cc36980 | 3162456 | 2982407 | 44392033 | 65536 | 261122683 | 395306 | 395306 | 43777836 | 35376490 | 0 | 524288 | 0 | 0 | 12075090227981444 | 12075093247087929 | 12075093247334167 | 12075090228698457 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7f59987a3700 | 0x7f588cc369c0 | 1699288 | 1521023 | 22507267 | 65536 | 168205907 | 212410 | 212410 | 21788508 | 19616538 | 524288 | 524288 | 0 | 0 | 12075090228861129 | 12075093247395446 | 12075093247521685 | 12075090229398568 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7f59987a3600 | 0x7f588cc36a00 | 2628376 | 2467365 | 36696267 | 65536 | 298975670 | 328546 | 328546 | 16008788 | 13499163 | 524288 | 524288 | 0 | 0 | 12075090229625019 | 12075093247562965 | 12075093247771923 | 12075090230289534 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7f59987a3500 | 0x7f588cc36a40 | 1806696 | 1628628 | 23911597 | 65536 | 172964370 | 225836 | 225836 | 22902864 | 20732188 | 524288 | 524288 | 0 | 0 | 12075090230464499 | 12075093247840563 | 12075093247968562 | 12075090230975358 |
| 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 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7f59987a3400 | 0x7f588cc36a80 | 3767984 | 3606249 | 53702110 | 65536 | 438407223 | 470997 | 470997 | 52722824 | 44157987 | 0 | 524288 | 0 | 0 | 12075090231199935 | 12075093248015281 | 12075093248321519 | 12075090231970457 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7f59987a3300 | 0x7f588cc36ac0 | 3235200 | 3038706 | 45150162 | 65536 | 268913766 | 404399 | 404399 | 44534640 | 36133574 | 0 | 524288 | 0 | 0 | 12075090232138730 | 12075093248383278 | 12075093248630316 | 12075090232829955 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7f59987a3a00 | 0x7f588cc36b00 | 1786736 | 1628797 | 23935311 | 65536 | 178359764 | 223341 | 223341 | 23194224 | 21030805 | 524288 | 524288 | 0 | 0 | 12075090232963343 | 12075093248687116 | 12075093248814635 | 12075090233542118 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7f59987a3900 | 0x7f588cc36b40 | 2846360 | 2683510 | 39855302 | 65536 | 325594419 | 355794 | 355794 | 16675272 | 14144873 | 524288 | 524288 | 0 | 0 | 12075090233766345 | 12075093248856235 | 12075093249084233 | 12075090234451819 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7f59987a3800 | 0x7f588cc36b80 | 1786496 | 1618315 | 23797163 | 65536 | 173103456 | 223311 | 223311 | 22822300 | 20644787 | 524288 | 524288 | 0 | 0 | 12075090234625121 | 12075093249160552 | 12075093249287591 | 12075090235136782 |
| 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 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7f59987a3700 | 0x7f588cc36bc0 | 4054696 | 3860911 | 57514203 | 65536 | 470412500 | 506836 | 506836 | 56404692 | 47778685 | 0 | 524288 | 0 | 0 | 12075090235360908 | 12075093249328231 | 12075093249656868 | 12075090236160053 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7f59987a3600 | 0x7f588cc36c00 | 3641728 | 3007767 | 44683103 | 65536 | 294419675 | 455215 | 455215 | 44078188 | 35682359 | 0 | 524288 | 0 | 0 | 12075090236326422 | 12075093249710308 | 12075093249957026 | 12075090237079572 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7f59987a3500 | 0x7f588cc36c40 | 1809088 | 1627453 | 23958636 | 65536 | 178319603 | 226135 | 226135 | 22916076 | 20746474 | 524288 | 524288 | 0 | 0 | 12075090237246242 | 12075093250018466 | 12075093250148384 | 12075090237779964 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7f59987a3400 | 0x7f588cc36c80 | 3037504 | 2880721 | 42819756 | 65536 | 350910252 | 379687 | 379687 | 15366512 | 12846999 | 524288 | 524288 | 0 | 0 | 12075090238016583 | 12075093250189184 | 12075093250432862 | 12075090238717606 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7f59987a3300 | 0x7f588cc36cc0 | 1824024 | 1652937 | 24217400 | 65536 | 181374482 | 228002 | 228002 | 23002736 | 20821950 | 524288 | 524288 | 0 | 0 | 12075090238859530 | 12075093250504222 | 12075093250633341 | 12075090239424279 |
| 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 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7f59987a3a00 | 0x7f588cc36d00 | 4588720 | 4422690 | 65904710 | 65536 | 541129345 | 573589 | 573589 | 63970292 | 55106838 | 0 | 524288 | 0 | 0 | 12075090239652904 | 12075093250673180 | 12075093251048057 | 12075090240482265 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7f59987a3900 | 0x7f588cc36d40 | 3249448 | 3053373 | 45386206 | 65536 | 292518969 | 406180 | 406180 | 44337152 | 35921048 | 0 | 524288 | 0 | 0 | 12075090240640209 | 12075093251109977 | 12075093251363575 | 12075090241368072 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7f59987a3800 | 0x7f588cc36d80 | 1776664 | 1602515 | 23491250 | 65536 | 180141469 | 222082 | 222082 | 22367728 | 20187258 | 524288 | 524288 | 0 | 0 | 12075090241526897 | 12075093251425334 | 12075093251555093 | 12075090242053816 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7f59987a3700 | 0x7f588cc36dc0 | 3836184 | 3305012 | 49172657 | 65536 | 402076077 | 479522 | 479522 | 16182632 | 13607283 | 524288 | 524288 | 0 | 0 | 12075090242279866 | 12075093251596373 | 12075093251874611 | 12075090243068572 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7f59987a3600 | 0x7f588cc36e00 | 1823088 | 1651273 | 24429649 | 65536 | 188785478 | 227885 | 227885 | 22180072 | 19966068 | 524288 | 524288 | 0 | 0 | 12075090243249448 | 12075093251941490 | 12075093252076689 | 12075090243764014 |
| 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 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7f59987a3500 | 0x7f588cc36e40 | 5166872 | 4999768 | 74529042 | 65536 | 609663569 | 645858 | 645858 | 69935356 | 60726137 | 0 | 524288 | 0 | 0 | 12075090243993651 | 12075093252117809 | 12075093252539886 | 12075090244890037 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7f59987a3400 | 0x7f588cc36e80 | 3241704 | 3060250 | 45407062 | 65536 | 283895324 | 405212 | 405212 | 43190108 | 34728969 | 0 | 524288 | 0 | 0 | 12075090245058379 | 12075093252600045 | 12075093252855083 | 12075090245792013 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7f59987a3300 | 0x7f588cc36ec0 | 1790360 | 1616984 | 23803096 | 65536 | 179833928 | 223794 | 223794 | 21317404 | 19062491 | 524288 | 524288 | 0 | 0 | 12075090245925751 | 12075093252915403 | 12075093253050122 | 12075090246488126 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7f59987a3a00 | 0x7f588cc36f00 | 3887872 | 3729487 | 55519468 | 65536 | 453701444 | 485983 | 485983 | 15697264 | 13182371 | 524288 | 524288 | 0 | 0 | 12075090246712513 | 12075093253092681 | 12075093253406919 | 12075090247503473 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7f59987a3900 | 0x7f588cc36f40 | 1934616 | 1775176 | 26411364 | 65536 | 213685190 | 241826 | 241826 | 21571812 | 19018419 | 524288 | 524288 | 0 | 0 | 12075090247675703 | 12075093253479558 | 12075093253631397 | 12075090248203244 |
| 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 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7f59987a3800 | 0x7f588cc36f80 | 6266032 | 6105528 | 91111730 | 65536 | 748545459 | 783253 | 783253 | 81968128 | 72128102 | 0 | 524288 | 0 | 0 | 12075090248428562 | 12075093253672997 | 12075093254187713 | 12075090249403635 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7f59987a3700 | 0x7f588cc36fc0 | 3705064 | 3495643 | 51724567 | 65536 | 381769484 | 463132 | 463132 | 40591404 | 31922489 | 0 | 524288 | 0 | 0 | 12075090249567830 | 12075093254248832 | 12075093254545150 | 12075090250323614 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7f59987a3600 | 0x7f588cc37000 | 1955624 | 1801294 | 26796426 | 65536 | 217156204 | 244452 | 244452 | 21741632 | 19135372 | 524288 | 524288 | 0 | 0 | 12075090250487439 | 12075093254605309 | 12075093254759868 | 12075090251031961 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7f59987a3500 | 0x7f588cc37040 | 4741528 | 4579936 | 68284600 | 65536 | 560897563 | 592690 | 592690 | 16213008 | 13670243 | 524288 | 524288 | 0 | 0 | 12075090251261567 | 12075093254800828 | 12075093255184505 | 12075090252110405 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7f59987a3400 | 0x7f588cc37080 | 2220120 | 2069900 | 30794992 | 65536 | 250330267 | 277514 | 277514 | 21990696 | 19306401 | 524288 | 524288 | 0 | 0 | 12075090252286302 | 12075093255256184 | 12075093255468822 | 12075090252822358 |
| 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 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7f59987a3300 | 0x7f588cc370c0 | 7400240 | 7231054 | 107869309 | 65536 | 888885065 | 925029 | 925029 | 90241568 | 79668058 | 0 | 524288 | 0 | 0 | 12075090253054349 | 12075093255529782 | 12075093256139537 | 12075090254133324 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7f59987a3a00 | 0x7f588cc37100 | 3997312 | 3827917 | 56953386 | 65536 | 451286852 | 499663 | 499663 | 35151388 | 26208536 | 0 | 524288 | 0 | 0 | 12075090254298601 | 12075093256200177 | 12075093256525614 | 12075090255094640 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7f59987a3900 | 0x7f588cc37140 | 2256216 | 2090864 | 31111512 | 65536 | 253417839 | 282026 | 282026 | 21556332 | 18907266 | 524288 | 524288 | 0 | 0 | 12075090255257223 | 12075093256588174 | 12075093256766252 | 12075090255832943 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7f59987a3800 | 0x7f588cc37180 | 5585664 | 5426009 | 80952199 | 65536 | 665839664 | 698207 | 698207 | 16291028 | 13775417 | 524288 | 524288 | 0 | 0 | 12075090256035118 | 12075093256807052 | 12075093257261448 | 12075090256985354 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7f59987a3700 | 0x7f588cc371c0 | 2505256 | 2345235 | 34868367 | 65536 | 284407963 | 313156 | 313156 | 21387944 | 18652423 | 524288 | 524288 | 0 | 0 | 12075090257164958 | 12075093257341288 | 12075093257540966 | 12075090257794989 |
| 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 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7f59987a3600 | 0x7f588cc37200 | 8513560 | 8358317 | 124673346 | 65536 | 1027550982 | 1064194 | 1064194 | 95709096 | 84749318 | 0 | 524288 | 0 | 0 | 12075090257952341 | 12075093257600326 | 12075093258303200 | 12075090259142132 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7f59987a3500 | 0x7f588cc37240 | 4552408 | 4362607 | 65009192 | 65536 | 512442172 | 569050 | 569050 | 33034028 | 24030902 | 0 | 524288 | 0 | 0 | 12075090259309654 | 12075093258367519 | 12075093258739837 | 12075090260130128 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7f59987a3400 | 0x7f588cc37280 | 2531432 | 2376459 | 35360314 | 65536 | 288557921 | 316428 | 316428 | 21843792 | 19133731 | 524288 | 524288 | 0 | 0 | 12075090260292991 | 12075093258801276 | 12075093259003514 | 12075090260921389 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7f59987a3300 | 0x7f588cc372c0 | 6426112 | 6265142 | 93417467 | 65536 | 769117522 | 803263 | 803263 | 17981944 | 15508010 | 524288 | 524288 | 0 | 0 | 12075090261083971 | 12075093259063994 | 12075093259588470 | 12075090262098957 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7f59987a3a00 | 0x7f588cc37300 | 2790936 | 2637333 | 39268727 | 65536 | 321332223 | 348866 | 348866 | 19994464 | 17313260 | 524288 | 524288 | 0 | 0 | 12075090262288169 | 12075093259661589 | 12075093259885427 | 12075090262954517 |
| 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 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7f59987a3900 | 0x7f588cc37340 | 9648640 | 9483907 | 141598331 | 65536 | 1168194097 | 1206079 | 1206079 | 104691912 | 93184081 | 0 | 524288 | 0 | 0 | 12075090263117490 | 12075093259945267 | 12075093260742701 | 12075090264361231 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7f59987a3800 | 0x7f588cc37380 | 5106352 | 4945553 | 73667758 | 65536 | 601636633 | 638293 | 638293 | 35071548 | 26020458 | 0 | 524288 | 0 | 0 | 12075090264527250 | 12075093260804460 | 12075093261223337 | 12075090265394692 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7f59987a3700 | 0x7f588cc373c0 | 2813312 | 2653623 | 39525461 | 65536 | 322633634 | 351663 | 351663 | 20352632 | 17667752 | 524288 | 524288 | 0 | 0 | 12075090265556733 | 12075093261286536 | 12075093261511655 | 12075090266250743 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7f59987a3600 | 0x7f588cc37400 | 7268120 | 7111114 | 106149348 | 65536 | 871423289 | 908514 | 908514 | 17547820 | 15044113 | 524288 | 524288 | 0 | 0 | 12075090266384431 | 12075093261574694 | 12075093262171009 | 12075090267455582 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7f59987a3500 | 0x7f588cc37440 | 3331264 | 3170213 | 47120985 | 65536 | 385810837 | 416407 | 416407 | 16897768 | 14339171 | 524288 | 524288 | 0 | 0 | 12075090267599439 | 12075093262243969 | 12075093262514367 | 12075090268329075 |
| 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 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7f59987a3400 | 0x7f588cc37480 | 11889944 | 11733047 | 175205333 | 65536 | 1446248815 | 1486242 | 1486242 | 107841672 | 95871976 | 0 | 524288 | 0 | 0 | 12075090268462473 | 12075093262575166 | 12075093263559638 | 12075090269909342 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7f59987a3300 | 0x7f588cc374c0 | 6214824 | 6051278 | 90250931 | 65536 | 741181811 | 776852 | 776852 | 30039828 | 21088141 | 0 | 524288 | 0 | 0 | 12075090270068528 | 12075093263620438 | 12075093264133714 | 12075090271049240 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7f59987a3a00 | 0x7f588cc37500 | 3364912 | 3208514 | 47745558 | 65536 | 390972328 | 420613 | 420613 | 16784204 | 14225301 | 524288 | 524288 | 0 | 0 | 12075090271204198 | 12075093264199953 | 12075093264502991 | 12075090271951487 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7f59987a3900 | 0x7f588cc37540 | 9007384 | 8846550 | 132071646 | 65536 | 1089830712 | 1125922 | 1125922 | 101006028 | 96067040 | 524288 | 524288 | 0 | 0 | 12075090272116053 | 12075093264562030 | 12075093265299305 | 12075090273333325 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7f59987a3800 | 0x7f588cc37580 | 3925544 | 3747012 | 55753450 | 65536 | 457378451 | 490692 | 490692 | 16997360 | 14429729 | 524288 | 524288 | 0 | 0 | 12075090273506627 | 12075093265369384 | 12075093265685222 | 12075090274250960 |
| 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 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7f59987a3700 | 0x7f588cc375c0 | 14138112 | 13981800 | 208775838 | 65536 | 1725068649 | 1767263 | 1767263 | 133662404 | 120263206 | 0 | 524288 | 0 | 0 | 12075090274418562 | 12075093265745861 | 12075093266916892 | 12075090276035947 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7f59987a3600 | 0x7f588cc37600 | 7337496 | 7166845 | 107040211 | 65536 | 815147783 | 917186 | 917186 | 30501696 | 21527944 | 0 | 524288 | 0 | 0 | 12075090276205132 | 12075093266978171 | 12075093267590007 | 12075090277278426 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7f59987a3500 | 0x7f588cc37640 | 3937664 | 3777089 | 56242036 | 65536 | 461123807 | 492207 | 492207 | 16717096 | 14119755 | 524288 | 524288 | 0 | 0 | 12075090277445757 | 12075093267661366 | 12075093267978483 | 12075090278214546 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7f59987a3400 | 0x7f588cc37680 | 10685672 | 10529403 | 157211753 | 65536 | 1298074668 | 1335708 | 1335708 | 107750012 | 102034544 | 524288 | 524288 | 0 | 0 | 12075090278382047 | 12075093268042163 | 12075093268919116 | 12075090279687403 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7f59987a3300 | 0x7f588cc376c0 | 5297136 | 4850442 | 72310305 | 65536 | 593369823 | 662141 | 662141 | 17050228 | 14444637 | 524288 | 524288 | 0 | 0 | 12075090279866836 | 12075093268994475 | 12075093269404072 | 12075090280727786 |
| 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 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7f59987a3a00 | 0x7f588cc37700 | 18652376 | 18499949 | 276312478 | 65536 | 2284446886 | 2331546 | 2331546 | 132113464 | 118392009 | 0 | 524288 | 0 | 0 | 12075090280891861 | 12075093269471112 | 12075093271019419 | 12075090282903890 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7f59987a3900 | 0x7f588cc37740 | 9616536 | 9442836 | 140956387 | 65536 | 1162971713 | 1202066 | 1202066 | 111579092 | 99976913 | 0 | 524288 | 0 | 0 | 12075090283071071 | 12075093271127240 | 12075093271919555 | 12075090284332195 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7f59987a3800 | 0x7f588cc37780 | 5107184 | 4954498 | 73894607 | 65536 | 607461925 | 638397 | 638397 | 68792360 | 65744450 | 524288 | 524288 | 0 | 0 | 12075090284498584 | 12075093272033953 | 12075093272447710 | 12075090285360055 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7f59987a3700 | 0x7f588cc377c0 | 14053400 | 13897632 | 207604417 | 65536 | 1713448400 | 1756674 | 1756674 | 116177024 | 109986557 | 524288 | 524288 | 0 | 0 | 12075090285524721 | 12075093272556670 | 12075093273714422 | 12075090287151364 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7f59987a3600 | 0x7f588cc37800 | 9578392 | 9422927 | 140718901 | 65536 | 1161389650 | 1197298 | 1197298 | 90857448 | 85894941 | 524288 | 524288 | 0 | 0 | 12075090287332170 | 12075093273831541 | 12075093274616816 | 12075090288551426 |
| 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 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7f59987a3500 | 0x7f588cc37840 | 36657392 | 36499285 | 545479689 | 65536 | 4514756443 | 4582173 | 4582173 | 176085972 | 160906727 | 0 | 524288 | 0 | 0 | 12075090288716292 | 12075093274726415 | 12075093277777754 | 12075090292209023 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7f59987a3400 | 0x7f588cc37880 | 18580800 | 18429513 | 275283897 | 65536 | 2276586841 | 2322599 | 2322599 | 131128296 | 117399067 | 0 | 524288 | 0 | 0 | 12075090292374170 | 12075093277882074 | 12075093279422383 | 12075090294364719 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7f59987a3300 | 0x7f588cc378c0 | 9614104 | 9452466 | 141140340 | 65536 | 1164336049 | 1201762 | 1201762 | 96806264 | 91819869 | 524288 | 524288 | 0 | 0 | 12075090294507364 | 12075093279534062 | 12075093280324137 | 12075090295771954 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7f59987a3a00 | 0x7f588cc37900 | 27538520 | 27376032 | 409017557 | 65536 | 3382677275 | 3442314 | 3442314 | 148853480 | 140651214 | 524288 | 524288 | 0 | 0 | 12075090295940968 | 12075093280428776 | 12075093282709241 | 12075090298673576 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7f59987a3900 | 0x7f588cc37940 | 18588032 | 18420705 | 275164516 | 65536 | 2275527468 | 2323503 | 2323503 | 126905604 | 120200816 | 524288 | 524288 | 0 | 0 | 12075090298852068 | 12075093282824760 | 12075093284359950 | 12075090300819805 |
| 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 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7f59987a3800 | 0x7f588cc37980 | 72681216 | 72527829 | 1084008519 | 65536 | 8976937892 | 9085151 | 9085151 | 179421376 | 164628875 | 0 | 524288 | 0 | 0 | 12075090300974763 | 12075093284470989 | 12075093290525028 | 12075090307519235 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7f59987a3700 | 0x7f588cc379c0 | 36578608 | 36409168 | 544075322 | 65536 | 4501258635 | 4572325 | 4572325 | 180249564 | 166060755 | 0 | 524288 | 0 | 0 | 12075090307682739 | 12075093290629027 | 12075093293669646 | 12075090311192331 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7f59987a3600 | 0x7f588cc37a00 | 18613336 | 18458390 | 275770447 | 65536 | 2280814009 | 2326666 | 2326666 | 125085516 | 118621326 | 524288 | 524288 | 0 | 0 | 12075090311355915 | 12075093293775406 | 12075093295313315 | 12075090313346304 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 860709 | 860715 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7f59987a3500 | 0x7f588cc37a40 | 54490264 | 54328321 | 811996880 | 65536 | 6723292986 | 6811282 | 6811282 | 146888928 | 139061056 | 524288 | 524288 | 0 | 0 | 12075090313511971 | 12075093295417315 | 12075093299942884 | 12075090318489371 |