43 KiB
43 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | SQ_INSTS_VMEM | SQ_INST_LEVEL_VMEM | SQ_ACCUM_PREV_HIRES | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBuffer.kd | 0 | 0 | 0 | 875584 | 875589 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7f5b04404180 | 1048576 | 11071116 | 1417193120 | 12075444941615500 | 12075445186250006 | 12075445186573684 | 12075445186682496 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 875584 | 875589 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7f5b04435100 | 4096 | 123364 | 15785988 | 12075445201347390 | 12075445201650930 | 12075445201656850 | 12075445201668637 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7f5c0ff99900 | 0x7f5b04435140 | 524288 | 12242043 | 1566904348 | 12075445201720614 | 12075445201935569 | 12075445202067728 | 12075445202071947 |
| 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 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7f5c0ff99800 | 0x7f5b04435180 | 524288 | 13183125 | 1687425876 | 12075445202143941 | 12075445202318287 | 12075445202568046 | 12075445202636566 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7f5c0ff99700 | 0x7f5b044351c0 | 524288 | 14292621 | 1829451176 | 12075445202672393 | 12075445202860364 | 12075445203109963 | 12075445203179696 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7f5c0ff99600 | 0x7f5b04435200 | 524288 | 12654083 | 1619686504 | 12075445203211415 | 12075445203389962 | 12075445203521641 | 12075445203525238 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7f5c0ff99500 | 0x7f5b04435240 | 524288 | 12138351 | 1553685552 | 12075445203574539 | 12075445203746600 | 12075445203879719 | 12075445203883243 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7f5c0ff99400 | 0x7f5b04435280 | 524288 | 12026446 | 1539375992 | 12075445203962671 | 12075445204133638 | 12075445204267237 | 12075445204271114 |
| 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 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7f5c0ff99300 | 0x7f5b044352c0 | 524288 | 13644148 | 1746442344 | 12075445204320105 | 12075445204495076 | 12075445204748035 | 12075445204788996 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7f5c0ff99a00 | 0x7f5b04435300 | 524288 | 14230216 | 1821424660 | 12075445204814634 | 12075445204993314 | 12075445205241153 | 12075445205281692 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7f5c0ff99900 | 0x7f5b04435340 | 524288 | 12238749 | 1566570668 | 12075445205306138 | 12075445205499231 | 12075445205630751 | 12075445205634347 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7f5c0ff99800 | 0x7f5b04435380 | 524288 | 11196438 | 1433217468 | 12075445205685092 | 12075445205856510 | 12075445205993309 | 12075445205996811 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7f5c0ff99700 | 0x7f5b044353c0 | 524288 | 12212793 | 1563160156 | 12075445206059277 | 12075445206223708 | 12075445206355227 | 12075445206358804 |
| 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 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7f5c0ff99600 | 0x7f5b04435400 | 524288 | 12806611 | 1639211192 | 12075445206409598 | 12075445206574746 | 12075445206832825 | 12075445206898998 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7f5c0ff99500 | 0x7f5b04435440 | 524288 | 12870479 | 1647431124 | 12075445206923924 | 12075445207113943 | 12075445207371862 | 12075445207440494 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7f5c0ff99400 | 0x7f5b04435480 | 524288 | 12542658 | 1605428292 | 12075445207459650 | 12075445207649141 | 12075445207779220 | 12075445207782961 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7f5c0ff99300 | 0x7f5b044354c0 | 524288 | 11511646 | 1473430776 | 12075445207827193 | 12075445207998579 | 12075445208134579 | 12075445208138331 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7f5c0ff99a00 | 0x7f5b04435500 | 524288 | 12096847 | 1548388212 | 12075445208198823 | 12075445208362257 | 12075445208493777 | 12075445208497398 |
| 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 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7f5c0ff99900 | 0x7f5b04435540 | 524288 | 14058725 | 1799446648 | 12075445208550427 | 12075445208711696 | 12075445208962095 | 12075445209028996 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7f5c0ff99800 | 0x7f5b04435580 | 524288 | 13992064 | 1790891848 | 12075445209052630 | 12075445209241293 | 12075445209490412 | 12075445209557448 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7f5c0ff99700 | 0x7f5b044355c0 | 524288 | 12651846 | 1619469300 | 12075445209581062 | 12075445209764651 | 12075445209894250 | 12075445209897971 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7f5c0ff99600 | 0x7f5b04435600 | 524288 | 12665739 | 1621263040 | 12075445209948485 | 12075445210112169 | 12075445210242408 | 12075445210246309 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7f5c0ff99500 | 0x7f5b04435640 | 524288 | 11973210 | 1532517196 | 12075445210307673 | 12075445210470727 | 12075445210602887 | 12075445210606518 |
| 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 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7f5c0ff99400 | 0x7f5b04435680 | 524288 | 12547634 | 1606099412 | 12075445210655038 | 12075445210817926 | 12075445211076484 | 12075445211144378 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7f5c0ff99300 | 0x7f5b044356c0 | 524288 | 13992156 | 1790918172 | 12075445211168502 | 12075445211349763 | 12075445211599682 | 12075445211665997 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7f5c0ff99a00 | 0x7f5b04435700 | 524288 | 13332673 | 1706605508 | 12075445211691725 | 12075445211869280 | 12075445211997120 | 12075445212003434 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7f5c0ff99900 | 0x7f5b04435740 | 524288 | 12764778 | 1633878816 | 12075445212050993 | 12075445212215679 | 12075445212346238 | 12075445212349968 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7f5c0ff99800 | 0x7f5b04435780 | 524288 | 12607970 | 1613758848 | 12075445212409759 | 12075445212575357 | 12075445212705596 | 12075445212709316 |
| 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 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7f5c0ff99700 | 0x7f5b044357c0 | 524288 | 13333275 | 1706575464 | 12075445212756844 | 12075445212937115 | 12075445213192954 | 12075445213234592 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7f5c0ff99600 | 0x7f5b04435800 | 524288 | 14024869 | 1795170708 | 12075445213257895 | 12075445213442073 | 12075445213692952 | 12075445213733499 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7f5c0ff99500 | 0x7f5b04435840 | 524288 | 11231225 | 1437609372 | 12075445213755901 | 12075445213935510 | 12075445214071350 | 12075445214075255 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7f5c0ff99400 | 0x7f5b04435880 | 524288 | 12122996 | 1551760532 | 12075445214123775 | 12075445214291349 | 12075445214424788 | 12075445214428431 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7f5c0ff99300 | 0x7f5b044358c0 | 524288 | 12724140 | 1628670748 | 12075445214489394 | 12075445214651187 | 12075445214780466 | 12075445214784262 |
| 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 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7f5c0ff99a00 | 0x7f5b04435900 | 524288 | 14274589 | 1827055720 | 12075445214832552 | 12075445215000465 | 12075445215255344 | 12075445215324426 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7f5c0ff99900 | 0x7f5b04435940 | 524288 | 13994868 | 1791327560 | 12075445215348972 | 12075445215531983 | 12075445215786701 | 12075445215853018 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7f5c0ff99800 | 0x7f5b04435980 | 524288 | 11888702 | 1521665824 | 12075445215878235 | 12075445216061900 | 12075445216240619 | 12075445216244456 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7f5c0ff99700 | 0x7f5b044359c0 | 524288 | 12808125 | 1639389912 | 12075445216294379 | 12075445216467658 | 12075445216597898 | 12075445216601399 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7f5c0ff99600 | 0x7f5b04435a00 | 524288 | 13160617 | 1684520140 | 12075445216662363 | 12075445216824776 | 12075445216952936 | 12075445216956780 |
| 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 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7f5c0ff99500 | 0x7f5b04435a40 | 524288 | 11970878 | 1532248272 | 12075445217011101 | 12075445217175815 | 12075445217433253 | 12075445217499478 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7f5c0ff99400 | 0x7f5b04435a80 | 524288 | 13277269 | 1699524588 | 12075445217521429 | 12075445217702212 | 12075445217989571 | 12075445218032008 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7f5c0ff99300 | 0x7f5b04435ac0 | 524288 | 12711504 | 1627092880 | 12075445218054339 | 12075445218236610 | 12075445218367009 | 12075445218370717 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7f5c0ff99a00 | 0x7f5b04435b00 | 524288 | 11298077 | 1446136748 | 12075445218422383 | 12075445218584768 | 12075445218721887 | 12075445218725587 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7f5c0ff99900 | 0x7f5b04435b40 | 524288 | 11770214 | 1506548124 | 12075445218785218 | 12075445218944286 | 12075445219077566 | 12075445219081308 |
| 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 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7f5c0ff99800 | 0x7f5b04435b80 | 524288 | 11918525 | 1525557520 | 12075445219124548 | 12075445219299164 | 12075445219564123 | 12075445219631781 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7f5c0ff99700 | 0x7f5b04435bc0 | 524288 | 13102832 | 1677129636 | 12075445219654573 | 12075445219833882 | 12075445220091001 | 12075445220157238 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7f5c0ff99600 | 0x7f5b04435c00 | 524288 | 11227652 | 1437124688 | 12075445220178016 | 12075445220368119 | 12075445220503959 | 12075445220507499 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7f5c0ff99500 | 0x7f5b04435c40 | 524288 | 11497745 | 1471741912 | 12075445220557411 | 12075445220725558 | 12075445220861717 | 12075445220865464 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7f5c0ff99400 | 0x7f5b04435c80 | 524288 | 12683526 | 1623464924 | 12075445220924153 | 12075445221090836 | 12075445221220275 | 12075445221224231 |
| 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 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7f5c0ff99300 | 0x7f5b04435cc0 | 524288 | 13710500 | 1754912492 | 12075445221273252 | 12075445221445074 | 12075445221710673 | 12075445221752592 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7f5c0ff99a00 | 0x7f5b04435d00 | 524288 | 14223021 | 1820563356 | 12075445221777499 | 12075445221952752 | 12075445222208270 | 12075445222276376 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7f5c0ff99900 | 0x7f5b04435d40 | 524288 | 11821414 | 1513095896 | 12075445222299008 | 12075445222484269 | 12075445222616748 | 12075445222620505 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7f5c0ff99800 | 0x7f5b04435d80 | 524288 | 10631555 | 1360867520 | 12075445222668294 | 12075445222833707 | 12075445222970347 | 12075445222974133 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7f5c0ff99700 | 0x7f5b04435dc0 | 524288 | 12428129 | 1590845084 | 12075445223039945 | 12075445223202986 | 12075445223333705 | 12075445223337518 |
| 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 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7f5c0ff99600 | 0x7f5b04435e00 | 524288 | 12046177 | 1541928264 | 12075445223386058 | 12075445223553384 | 12075445223818023 | 12075445223884915 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7f5c0ff99500 | 0x7f5b04435e40 | 524288 | 14182319 | 1815374704 | 12075445223902187 | 12075445224097221 | 12075445224346660 | 12075445224413969 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7f5c0ff99400 | 0x7f5b04435e80 | 524288 | 11674883 | 1494391608 | 12075445224436961 | 12075445224615939 | 12075445224750338 | 12075445224754161 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7f5c0ff99300 | 0x7f5b04435ec0 | 524288 | 9221224 | 1180235804 | 12075445224803943 | 12075445224971937 | 12075445225114176 | 12075445225118097 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7f5c0ff99a00 | 0x7f5b04435f00 | 524288 | 12504674 | 1600631052 | 12075445225180353 | 12075445225343295 | 12075445225473695 | 12075445225477625 |
| 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 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7f5c0ff99900 | 0x7f5b04435f40 | 524288 | 11703016 | 1497972176 | 12075445225525334 | 12075445225694973 | 12075445225955772 | 12075445226022668 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7f5c0ff99800 | 0x7f5b04435f80 | 524288 | 12256949 | 1568842132 | 12075445226045811 | 12075445226228091 | 12075445226482970 | 12075445226549988 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7f5c0ff99700 | 0x7f5b04435fc0 | 524288 | 10848266 | 1388542760 | 12075445226575546 | 12075445226748728 | 12075445226885848 | 12075445226889639 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7f5c0ff99600 | 0x7f5b04436000 | 524288 | 8358145 | 1069805872 | 12075445226938080 | 12075445227112887 | 12075445227251446 | 12075445227255259 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7f5c0ff99500 | 0x7f5b04436040 | 524288 | 12555089 | 1607106480 | 12075445227316543 | 12075445227477525 | 12075445227607924 | 12075445227611772 |
| 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 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7f5c0ff99400 | 0x7f5b04436080 | 524288 | 13283158 | 1700239664 | 12075445227660422 | 12075445227833043 | 12075445228096082 | 12075445228144872 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7f5c0ff99300 | 0x7f5b044360c0 | 524288 | 13975311 | 1788823100 | 12075445228168927 | 12075445228349521 | 12075445228605039 | 12075445228653498 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7f5c0ff99a00 | 0x7f5b04436100 | 524288 | 12521954 | 1602911716 | 12075445228674987 | 12075445228853358 | 12075445228983758 | 12075445228987478 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7f5c0ff99900 | 0x7f5b04436140 | 524288 | 7338430 | 939378364 | 12075445229035578 | 12075445229205036 | 12075445229348716 | 12075445229352386 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7f5c0ff99800 | 0x7f5b04436180 | 524288 | 13103930 | 1677280960 | 12075445229412468 | 12075445229572555 | 12075445229701034 | 12075445229704761 |
| 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 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7f5c0ff99700 | 0x7f5b044361c0 | 524288 | 13078984 | 1674076120 | 12075445229751568 | 12075445229919113 | 12075445230179112 | 12075445230228164 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7f5c0ff99600 | 0x7f5b04436200 | 524288 | 12224011 | 1564617820 | 12075445230251077 | 12075445230433031 | 12075445230689349 | 12075445230710681 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7f5c0ff99500 | 0x7f5b04436240 | 524288 | 12215939 | 1563623704 | 12075445230753330 | 12075445230915108 | 12075445231047268 | 12075445231051244 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7f5c0ff99400 | 0x7f5b04436280 | 524288 | 5922621 | 758076584 | 12075445231104402 | 12075445231266946 | 12075445231417826 | 12075445231421622 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7f5c0ff99300 | 0x7f5b044362c0 | 524288 | 11164844 | 1429179100 | 12075445231502222 | 12075445231660225 | 12075445231796224 | 12075445231800105 |
| 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 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7f5c0ff99a00 | 0x7f5b04436300 | 524288 | 11072665 | 1417259344 | 12075445231848085 | 12075445232022623 | 12075445232285182 | 12075445232333847 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7f5c0ff99900 | 0x7f5b04436340 | 524288 | 12738660 | 1630486656 | 12075445232357511 | 12075445232535580 | 12075445232792699 | 12075445232840970 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7f5c0ff99800 | 0x7f5b04436380 | 524288 | 11560016 | 1479703688 | 12075445232862931 | 12075445233047418 | 12075445233181177 | 12075445233184959 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7f5c0ff99700 | 0x7f5b044363c0 | 524288 | 4403880 | 563730884 | 12075445233233499 | 12075445233401656 | 12075445233559095 | 12075445233563032 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7f5c0ff99600 | 0x7f5b04436400 | 524288 | 11403545 | 1459526868 | 12075445233623755 | 12075445233782934 | 12075445233917174 | 12075445233920927 |
| 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 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7f5c0ff99500 | 0x7f5b04436440 | 524288 | 10889606 | 1393855452 | 12075445233967964 | 12075445234141813 | 12075445234408531 | 12075445234431035 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7f5c0ff99400 | 0x7f5b04436480 | 524288 | 14102128 | 1805005956 | 12075445234473213 | 12075445234638130 | 12075445234888049 | 12075445234934741 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7f5c0ff99300 | 0x7f5b044364c0 | 524288 | 11285718 | 1444601164 | 12075445234956411 | 12075445235142128 | 12075445235278127 | 12075445235282217 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7f5c0ff99a00 | 0x7f5b04436500 | 524288 | 4342187 | 555764628 | 12075445235332240 | 12075445235503246 | 12075445235669965 | 12075445235673684 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7f5c0ff99900 | 0x7f5b04436540 | 524288 | 11433598 | 1463470524 | 12075445235733866 | 12075445235895564 | 12075445236030603 | 12075445236034635 |
| 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 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7f5c0ff99800 | 0x7f5b04436580 | 524288 | 10220070 | 1308170012 | 12075445236087433 | 12075445236248842 | 12075445236509801 | 12075445236557687 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7f5c0ff99700 | 0x7f5b044365c0 | 524288 | 13620211 | 1743396756 | 12075445236583064 | 12075445236760360 | 12075445237014919 | 12075445237062746 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7f5c0ff99600 | 0x7f5b04436600 | 524288 | 11426388 | 1462545268 | 12075445237086360 | 12075445237268197 | 12075445237403397 | 12075445237407236 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7f5c0ff99500 | 0x7f5b04436640 | 524288 | 3618133 | 463115928 | 12075445237456137 | 12075445237624036 | 12075445237798115 | 12075445237801819 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7f5c0ff99400 | 0x7f5b04436680 | 524288 | 12479411 | 1597291180 | 12075445237860929 | 12075445238027554 | 12075445238159713 | 12075445238164173 |
| 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 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7f5c0ff99300 | 0x7f5b044366c0 | 524288 | 8847721 | 1132535452 | 12075445238212312 | 12075445238382432 | 12075445238642271 | 12075445238666166 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7f5c0ff99a00 | 0x7f5b04436700 | 524288 | 13526668 | 1731376616 | 12075445238710418 | 12075445238873470 | 12075445239128188 | 12075445239155455 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7f5c0ff99900 | 0x7f5b04436740 | 524288 | 11802974 | 1510743924 | 12075445239195469 | 12075445239354107 | 12075445239488187 | 12075445239492040 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7f5c0ff99800 | 0x7f5b04436780 | 524288 | 3551472 | 454581244 | 12075445239539639 | 12075445239707066 | 12075445239890105 | 12075445239894008 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7f5c0ff99700 | 0x7f5b044367c0 | 524288 | 10943653 | 1400798980 | 12075445239954049 | 12075445240121944 | 12075445240260663 | 12075445240264676 |
| 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 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7f5c0ff99600 | 0x7f5b04436800 | 524288 | 4181116 | 535160240 | 12075445240314950 | 12075445240483542 | 12075445240749301 | 12075445240773552 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7f5c0ff99500 | 0x7f5b04436840 | 524288 | 13714222 | 1755350080 | 12075445240816492 | 12075445240973139 | 12075445241231698 | 12075445241257431 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7f5c0ff99400 | 0x7f5b04436880 | 524288 | 11106078 | 1421589164 | 12075445241300161 | 12075445241459537 | 12075445241594736 | 12075445241598746 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7f5c0ff99300 | 0x7f5b044368c0 | 524288 | 3493856 | 447255800 | 12075445241646845 | 12075445241814895 | 12075445242006254 | 12075445242010180 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7f5c0ff99a00 | 0x7f5b04436900 | 524288 | 10991023 | 1406834800 | 12075445242090009 | 12075445242254093 | 12075445242390893 | 12075445242394755 |
| 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 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7f5c0ff99900 | 0x7f5b04436940 | 524288 | 2931427 | 375168692 | 12075445242442183 | 12075445242616651 | 12075445242899850 | 12075445242924640 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7f5c0ff99800 | 0x7f5b04436980 | 524288 | 13844168 | 1772022460 | 12075445242966728 | 12075445243131849 | 12075445243385128 | 12075445243412757 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7f5c0ff99700 | 0x7f5b044369c0 | 524288 | 11153081 | 1427539868 | 12075445243451749 | 12075445243610087 | 12075445243745926 | 12075445243749833 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7f5c0ff99600 | 0x7f5b04436a00 | 524288 | 3506965 | 448747744 | 12075445243801509 | 12075445243962405 | 12075445244172964 | 12075445244198637 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7f5c0ff99500 | 0x7f5b04436a40 | 524288 | 10612791 | 1358456088 | 12075445244252958 | 12075445244415523 | 12075445244554722 | 12075445244558707 |
| 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 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7f5c0ff99400 | 0x7f5b04436a80 | 524288 | 2545166 | 325776348 | 12075445244607006 | 12075445244774401 | 12075445245083360 | 12075445245109120 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7f5c0ff99300 | 0x7f5b04436ac0 | 524288 | 12821199 | 1641068520 | 12075445245149585 | 12075445245310878 | 12075445245567677 | 12075445245591506 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7f5c0ff99a00 | 0x7f5b04436b00 | 524288 | 12123124 | 1551662664 | 12075445245632913 | 12075445245791836 | 12075445245924955 | 12075445245928993 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7f5c0ff99900 | 0x7f5b04436b40 | 524288 | 3413001 | 436833256 | 12075445245975480 | 12075445246161274 | 12075445246388793 | 12075445246415327 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7f5c0ff99800 | 0x7f5b04436b80 | 524288 | 10326131 | 1321840020 | 12075445246473976 | 12075445246636472 | 12075445246776631 | 12075445246780666 |
| 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 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7f5c0ff99700 | 0x7f5b04436bc0 | 524288 | 2446861 | 313059400 | 12075445246828866 | 12075445246998230 | 12075445247327989 | 12075445247355775 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7f5c0ff99600 | 0x7f5b04436c00 | 524288 | 12895496 | 1650586764 | 12075445247398294 | 12075445247558868 | 12075445247820626 | 12075445247843952 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7f5c0ff99500 | 0x7f5b04436c40 | 524288 | 11156533 | 1428109636 | 12075445247886872 | 12075445248053745 | 12075445248189904 | 12075445248193953 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7f5c0ff99400 | 0x7f5b04436c80 | 524288 | 3427870 | 438783100 | 12075445248241461 | 12075445248415823 | 12075445248661422 | 12075445248685436 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7f5c0ff99300 | 0x7f5b04436cc0 | 524288 | 9612210 | 1230336924 | 12075445248741480 | 12075445248905261 | 12075445249048460 | 12075445249052618 |
| 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 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7f5c0ff99a00 | 0x7f5b04436d00 | 524288 | 2395484 | 306557012 | 12075445249100738 | 12075445249273853 | 12075445249652092 | 12075445249679263 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7f5c0ff99900 | 0x7f5b04436d40 | 524288 | 13167816 | 1685407828 | 12075445249717654 | 12075445249879290 | 12075445250139289 | 12075445250165266 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7f5c0ff99800 | 0x7f5b04436d80 | 524288 | 9293134 | 1189471276 | 12075445250204659 | 12075445250366168 | 12075445250510648 | 12075445250513223 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7f5c0ff99700 | 0x7f5b04436dc0 | 524288 | 3340075 | 427518504 | 12075445250564889 | 12075445250738167 | 12075445251048566 | 12075445251072352 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7f5c0ff99600 | 0x7f5b04436e00 | 524288 | 9186430 | 1175759788 | 12075445251131973 | 12075445251297685 | 12075445251433525 | 12075445251436108 |
| 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 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7f5c0ff99500 | 0x7f5b04436e40 | 524288 | 2355509 | 301543620 | 12075445251484949 | 12075445251648404 | 12075445252074963 | 12075445252098649 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7f5c0ff99400 | 0x7f5b04436e80 | 524288 | 10248423 | 1311776948 | 12075445252140828 | 12075445252300722 | 12075445252564882 | 12075445252587107 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7f5c0ff99300 | 0x7f5b04436ec0 | 524288 | 8143353 | 1042359180 | 12075445252630217 | 12075445252791281 | 12075445252931760 | 12075445252934423 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7f5c0ff99a00 | 0x7f5b04436f00 | 524288 | 3396499 | 434713680 | 12075445252981300 | 12075445253157680 | 12075445253473039 | 12075445253498952 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7f5c0ff99900 | 0x7f5b04436f40 | 524288 | 3667657 | 469383872 | 12075445253553553 | 12075445253717518 | 12075445253870798 | 12075445253873297 |
| 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 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7f5c0ff99800 | 0x7f5b04436f80 | 524288 | 2344890 | 300171524 | 12075445253921507 | 12075445254096077 | 12075445254615595 | 12075445254642818 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7f5c0ff99700 | 0x7f5b04436fc0 | 524288 | 8172764 | 1046115612 | 12075445254687871 | 12075445254851115 | 12075445255148554 | 12075445255175137 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7f5c0ff99600 | 0x7f5b04437000 | 524288 | 3294382 | 421633300 | 12075445255211935 | 12075445255385033 | 12075445255539912 | 12075445255542600 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7f5c0ff99500 | 0x7f5b04437040 | 524288 | 3398762 | 434980392 | 12075445255590739 | 12075445255762472 | 12075445256147591 | 12075445256172701 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7f5c0ff99400 | 0x7f5b04437080 | 524288 | 3239560 | 414509220 | 12075445256230769 | 12075445256394310 | 12075445256571429 | 12075445256574187 |
| 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 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7f5c0ff99300 | 0x7f5b044370c0 | 524288 | 2326548 | 297677416 | 12075445256621705 | 12075445256791589 | 12075445257413347 | 12075445257440467 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7f5c0ff99a00 | 0x7f5b04437100 | 524288 | 4039513 | 517008688 | 12075445257485300 | 12075445257647586 | 12075445257975905 | 12075445257997572 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7f5c0ff99900 | 0x7f5b04437140 | 524288 | 3440034 | 440213856 | 12075445258049479 | 12075445258213984 | 12075445258392864 | 12075445258395331 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7f5c0ff99800 | 0x7f5b04437180 | 524288 | 3877876 | 496314128 | 12075445258444803 | 12075445258610143 | 12075445259066301 | 12075445259090012 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7f5c0ff99700 | 0x7f5b044371c0 | 524288 | 3211139 | 411133604 | 12075445259149693 | 12075445259313021 | 12075445259513500 | 12075445259535591 |
| 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 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7f5c0ff99600 | 0x7f5b04437200 | 524288 | 2300139 | 294338140 | 12075445259582117 | 12075445259742619 | 12075445260445337 | 12075445260468584 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7f5c0ff99500 | 0x7f5b04437240 | 524288 | 3407972 | 436170736 | 12075445260511264 | 12075445260674297 | 12075445261047415 | 12075445261071635 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7f5c0ff99400 | 0x7f5b04437280 | 524288 | 3241018 | 414773348 | 12075445261116338 | 12075445261277655 | 12075445261480694 | 12075445261503017 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7f5c0ff99300 | 0x7f5b044372c0 | 524288 | 3977252 | 509037756 | 12075445261552449 | 12075445261717973 | 12075445262244692 | 12075445262268259 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7f5c0ff99a00 | 0x7f5b04437300 | 524288 | 3213494 | 411432848 | 12075445262328842 | 12075445262492531 | 12075445262751730 | 12075445262775462 |
| 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 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7f5c0ff99900 | 0x7f5b04437340 | 524288 | 2295446 | 293812424 | 12075445262818211 | 12075445262978449 | 12075445263778127 | 12075445263805857 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7f5c0ff99800 | 0x7f5b04437380 | 524288 | 3395641 | 434604320 | 12075445263846242 | 12075445264006766 | 12075445264427725 | 12075445264452699 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7f5c0ff99700 | 0x7f5b044373c0 | 524288 | 3085451 | 395058208 | 12075445264500598 | 12075445264665804 | 12075445264892683 | 12075445264912363 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7f5c0ff99600 | 0x7f5b04437400 | 524288 | 4509141 | 577179804 | 12075445264961504 | 12075445265131563 | 12075445265728041 | 12075445265754769 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7f5c0ff99500 | 0x7f5b04437440 | 524288 | 3492513 | 446915356 | 12075445265805803 | 12075445265970280 | 12075445266240359 | 12075445266265478 |
| 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 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7f5c0ff99400 | 0x7f5b04437480 | 524288 | 2297652 | 294056448 | 12075445266307776 | 12075445266468679 | 12075445267452516 | 12075445267519318 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7f5c0ff99300 | 0x7f5b044374c0 | 524288 | 3375117 | 432074940 | 12075445267548612 | 12075445267733635 | 12075445268249153 | 12075445268316550 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7f5c0ff99a00 | 0x7f5b04437500 | 524288 | 3366253 | 430813312 | 12075445268345914 | 12075445268528992 | 12075445268801791 | 12075445268867704 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7f5c0ff99900 | 0x7f5b04437540 | 524288 | 2195601 | 280983808 | 12075445268893622 | 12075445269075071 | 12075445269813628 | 12075445269882169 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7f5c0ff99800 | 0x7f5b04437580 | 524288 | 3325965 | 425748460 | 12075445269919118 | 12075445270087067 | 12075445270404826 | 12075445270470713 |
| 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 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7f5c0ff99700 | 0x7f5b044375c0 | 524288 | 2287858 | 292745268 | 12075445270493846 | 12075445270682106 | 12075445271852022 | 12075445271918474 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7f5c0ff99600 | 0x7f5b04437600 | 524288 | 3357394 | 429649500 | 12075445271948980 | 12075445272136021 | 12075445272746419 | 12075445272814399 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7f5c0ff99500 | 0x7f5b04437640 | 524288 | 3320267 | 424871480 | 12075445272837051 | 12075445273029778 | 12075445273348337 | 12075445273415896 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7f5c0ff99400 | 0x7f5b04437680 | 524288 | 2266848 | 290105472 | 12075445273439200 | 12075445273626097 | 12075445274504174 | 12075445274572286 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7f5c0ff99300 | 0x7f5b044376c0 | 524288 | 3252218 | 416227896 | 12075445274608693 | 12075445274769933 | 12075445275179852 | 12075445275249164 |
| 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 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7f5c0ff99a00 | 0x7f5b04437700 | 524288 | 2297628 | 294128872 | 12075445275281133 | 12075445275468811 | 12075445277015046 | 12075445277082761 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7f5c0ff99900 | 0x7f5b04437740 | 524288 | 2286027 | 292587052 | 12075445277114240 | 12075445277295845 | 12075445278089763 | 12075445278157509 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7f5c0ff99800 | 0x7f5b04437780 | 524288 | 2180203 | 279074964 | 12075445278186272 | 12075445278368322 | 12075445278782881 | 12075445278849054 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7f5c0ff99700 | 0x7f5b044377c0 | 524288 | 2210954 | 283032880 | 12075445278875844 | 12075445279072800 | 12075445280231676 | 12075445280300291 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7f5c0ff99600 | 0x7f5b04437800 | 524288 | 2187301 | 279992980 | 12075445280336839 | 12075445280501595 | 12075445281288313 | 12075445281355692 |
| 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 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7f5c0ff99500 | 0x7f5b04437840 | 524288 | 2698765 | 345449056 | 12075445281386660 | 12075445281569112 | 12075445284618863 | 12075445284687103 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7f5c0ff99400 | 0x7f5b04437880 | 524288 | 2333211 | 298639308 | 12075445284717310 | 12075445284898382 | 12075445286440937 | 12075445286510212 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7f5c0ff99300 | 0x7f5b044378c0 | 524288 | 2208177 | 282653904 | 12075445286534347 | 12075445286732776 | 12075445287521734 | 12075445287588736 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7f5c0ff99a00 | 0x7f5b04437900 | 524288 | 2524993 | 323176700 | 12075445287619623 | 12075445287800773 | 12075445290081886 | 12075445290150878 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7f5c0ff99900 | 0x7f5b04437940 | 524288 | 2364000 | 302446780 | 12075445290195551 | 12075445290358365 | 12075445291893880 | 12075445291961262 |
| 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 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7f5c0ff99800 | 0x7f5b04437980 | 524288 | 2924212 | 374314012 | 12075445291989956 | 12075445292178679 | 12075445298234020 | 12075445298302768 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7f5c0ff99700 | 0x7f5b044379c0 | 524288 | 3246626 | 415455476 | 12075445298332062 | 12075445298515460 | 12075445301557050 | 12075445301627707 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7f5c0ff99600 | 0x7f5b04437a00 | 524288 | 2478782 | 317190876 | 12075445301650890 | 12075445301840569 | 12075445303379765 | 12075445303449443 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 875584 | 875589 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7f5c0ff99500 | 0x7f5b04437a40 | 524288 | 2570662 | 328978280 | 12075445303480610 | 12075445303663604 | 12075445308190950 | 12075445308261676 |