39 KiB
39 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBuffer.kd | 0 | 0 | 0 | 856550 | 856555 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7fa7c2a04180 | 12074986772983985 | 12074986773041058 | 12074986773364415 | 12074986773464237 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 856550 | 856555 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7fa7c2a35100 | 12074986787949045 | 12074986788051185 | 12074986788058225 | 12074986788064139 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7fa8ce69a900 | 0x7fa7c2a35140 | 12074986788108862 | 12074986788122704 | 12074986788249903 | 12074986788253321 |
| 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 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7fa8ce69a800 | 0x7fa7c2a35180 | 12074986788296551 | 12074986788308463 | 12074986788551821 | 12074986788642534 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7fa8ce69a700 | 0x7fa7c2a351c0 | 12074986788668753 | 12074986788681100 | 12074986788928298 | 12074986789021619 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7fa8ce69a600 | 0x7fa7c2a35200 | 12074986789051544 | 12074986789063337 | 12074986789189256 | 12074986789192687 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7fa8ce69a500 | 0x7fa7c2a35240 | 12074986789220659 | 12074986789232456 | 12074986789357415 | 12074986789360659 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7fa8ce69a400 | 0x7fa7c2a35280 | 12074986789414018 | 12074986789426055 | 12074986789550374 | 12074986789553437 |
| 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 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7fa8ce69a300 | 0x7fa7c2a352c0 | 12074986789580066 | 12074986789591813 | 12074986789873091 | 12074986789964250 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7fa8ce69aa00 | 0x7fa7c2a35300 | 12074986789989638 | 12074986790002370 | 12074986790245248 | 12074986790339648 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7fa8ce69a900 | 0x7fa7c2a35340 | 12074986790362440 | 12074986790374847 | 12074986790499647 | 12074986790502841 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7fa8ce69a800 | 0x7fa7c2a35380 | 12074986790528569 | 12074986790540286 | 12074986790665245 | 12074986790668309 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7fa8ce69a700 | 0x7fa7c2a353c0 | 12074986790706620 | 12074986790718205 | 12074986790843324 | 12074986790846119 |
| 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 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7fa8ce69a600 | 0x7fa7c2a35400 | 12074986790872538 | 12074986790884764 | 12074986791133722 | 12074986791226717 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7fa8ce69a500 | 0x7fa7c2a35440 | 12074986791254408 | 12074986791266201 | 12074986791548759 | 12074986791613886 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7fa8ce69a400 | 0x7fa7c2a35480 | 12074986791639323 | 12074986791651318 | 12074986791775637 | 12074986791779013 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7fa8ce69a300 | 0x7fa7c2a354c0 | 12074986791806023 | 12074986791818197 | 12074986791943476 | 12074986791946354 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7fa8ce69aa00 | 0x7fa7c2a35500 | 12074986791983774 | 12074986791995315 | 12074986792119794 | 12074986792123012 |
| 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 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7fa8ce69a900 | 0x7fa7c2a35540 | 12074986792150524 | 12074986792163314 | 12074986792411952 | 12074986792478042 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7fa8ce69a800 | 0x7fa7c2a35580 | 12074986792500794 | 12074986792513712 | 12074986792757550 | 12074986792821030 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7fa8ce69a700 | 0x7fa7c2a355c0 | 12074986792843040 | 12074986792855949 | 12074986792980908 | 12074986792983832 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7fa8ce69a600 | 0x7fa7c2a35600 | 12074986793017124 | 12074986793029708 | 12074986793154667 | 12074986793157505 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7fa8ce69a500 | 0x7fa7c2a35640 | 12074986793200114 | 12074986793213706 | 12074986793337865 | 12074986793340906 |
| 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 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7fa8ce69a400 | 0x7fa7c2a35680 | 12074986793372514 | 12074986793386025 | 12074986793632903 | 12074986793700955 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7fa8ce69a300 | 0x7fa7c2a356c0 | 12074986793726913 | 12074986793740742 | 12074986793986981 | 12074986794079749 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7fa8ce69aa00 | 0x7fa7c2a35700 | 12074986794102261 | 12074986794113700 | 12074986794237859 | 12074986794241189 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7fa8ce69a900 | 0x7fa7c2a35740 | 12074986794267808 | 12074986794280258 | 12074986794405377 | 12074986794408279 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7fa8ce69a800 | 0x7fa7c2a35780 | 12074986794445278 | 12074986794461057 | 12074986794585376 | 12074986794588554 |
| 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 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7fa8ce69a700 | 0x7fa7c2a357c0 | 12074986794615835 | 12074986794627776 | 12074986794873534 | 12074986794939937 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7fa8ce69a600 | 0x7fa7c2a35800 | 12074986794961527 | 12074986794973853 | 12074986795221211 | 12074986795295568 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7fa8ce69a500 | 0x7fa7c2a35840 | 12074986795317830 | 12074986795330491 | 12074986795454650 | 12074986795457840 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7fa8ce69a400 | 0x7fa7c2a35880 | 12074986795484479 | 12074986795495929 | 12074986795621528 | 12074986795624489 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7fa8ce69a300 | 0x7fa7c2a358c0 | 12074986795660266 | 12074986795671928 | 12074986795796407 | 12074986795799234 |
| 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 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7fa8ce69aa00 | 0x7fa7c2a35900 | 12074986795825433 | 12074986795837527 | 12074986796085525 | 12074986796141119 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7fa8ce69a900 | 0x7fa7c2a35940 | 12074986796163601 | 12074986796178164 | 12074986796423122 | 12074986796474749 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7fa8ce69a800 | 0x7fa7c2a35980 | 12074986796495458 | 12074986796508882 | 12074986796633681 | 12074986796637111 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7fa8ce69a700 | 0x7fa7c2a359c0 | 12074986796663350 | 12074986796674641 | 12074986796800080 | 12074986796803340 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7fa8ce69a600 | 0x7fa7c2a35a00 | 12074986796837974 | 12074986796851279 | 12074986796975598 | 12074986796978646 |
| 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 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7fa8ce69a500 | 0x7fa7c2a35a40 | 12074986797010014 | 12074986797024558 | 12074986797272716 | 12074986797294663 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7fa8ce69a400 | 0x7fa7c2a35a80 | 12074986797315512 | 12074986797328076 | 12074986797573034 | 12074986797594090 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7fa8ce69a300 | 0x7fa7c2a35ac0 | 12074986797617844 | 12074986797631273 | 12074986797756552 | 12074986797759367 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7fa8ce69aa00 | 0x7fa7c2a35b00 | 12074986797785295 | 12074986797797192 | 12074986797923591 | 12074986797926457 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7fa8ce69a900 | 0x7fa7c2a35b40 | 12074986797962955 | 12074986797975751 | 12074986798101190 | 12074986798104398 |
| 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 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7fa8ce69a800 | 0x7fa7c2a35b80 | 12074986798131047 | 12074986798144870 | 12074986798402628 | 12074986798423090 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7fa8ce69a700 | 0x7fa7c2a35bc0 | 12074986798444700 | 12074986798457507 | 12074986798702785 | 12074986798724420 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7fa8ce69a600 | 0x7fa7c2a35c00 | 12074986798744167 | 12074986798757185 | 12074986798882144 | 12074986798885089 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7fa8ce69a500 | 0x7fa7c2a35c40 | 12074986798912129 | 12074986798924544 | 12074986799050943 | 12074986799054163 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7fa8ce69a400 | 0x7fa7c2a35c80 | 12074986799093847 | 12074986799106622 | 12074986799231741 | 12074986799234769 |
| 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 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7fa8ce69a300 | 0x7fa7c2a35cc0 | 12074986799262240 | 12074986799277021 | 12074986799536859 | 12074986799557058 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7fa8ce69aa00 | 0x7fa7c2a35d00 | 12074986799578227 | 12074986799590779 | 12074986799873497 | 12074986799893984 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7fa8ce69a900 | 0x7fa7c2a35d40 | 12074986799916636 | 12074986799929176 | 12074986800053815 | 12074986800057257 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7fa8ce69a800 | 0x7fa7c2a35d80 | 12074986800084357 | 12074986800096535 | 12074986800224854 | 12074986800227914 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7fa8ce69a700 | 0x7fa7c2a35dc0 | 12074986800265584 | 12074986800277974 | 12074986800403413 | 12074986800406326 |
| 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 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7fa8ce69a600 | 0x7fa7c2a35e00 | 12074986800432464 | 12074986800444532 | 12074986800702610 | 12074986800719167 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7fa8ce69a500 | 0x7fa7c2a35e40 | 12074986800744304 | 12074986800757650 | 12074986801005968 | 12074986801030676 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7fa8ce69a400 | 0x7fa7c2a35e80 | 12074986801055031 | 12074986801067728 | 12074986801193167 | 12074986801196204 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7fa8ce69a300 | 0x7fa7c2a35ec0 | 12074986801223184 | 12074986801234927 | 12074986801362766 | 12074986801365839 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7fa8ce69aa00 | 0x7fa7c2a35f00 | 12074986801403038 | 12074986801415885 | 12074986801540524 | 12074986801543529 |
| 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 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7fa8ce69a900 | 0x7fa7c2a35f40 | 12074986801569608 | 12074986801581804 | 12074986801837962 | 12074986801862532 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7fa8ce69a800 | 0x7fa7c2a35f80 | 12074986801883521 | 12074986801896522 | 12074986802142920 | 12074986802167439 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7fa8ce69a700 | 0x7fa7c2a35fc0 | 12074986802190612 | 12074986802203399 | 12074986802328998 | 12074986802331944 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7fa8ce69a600 | 0x7fa7c2a36000 | 12074986802359265 | 12074986802372358 | 12074986802509317 | 12074986802512360 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7fa8ce69a500 | 0x7fa7c2a36040 | 12074986802552184 | 12074986802564517 | 12074986802689316 | 12074986802692344 |
| 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 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7fa8ce69a400 | 0x7fa7c2a36080 | 12074986802718433 | 12074986802730115 | 12074986802984193 | 12074986803007570 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7fa8ce69a300 | 0x7fa7c2a360c0 | 12074986803033648 | 12074986803047713 | 12074986803292191 | 12074986803316564 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7fa8ce69aa00 | 0x7fa7c2a36100 | 12074986803337192 | 12074986803349951 | 12074986803474910 | 12074986803478014 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7fa8ce69a900 | 0x7fa7c2a36140 | 12074986803505395 | 12074986803517949 | 12074986803660188 | 12074986803663178 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7fa8ce69a800 | 0x7fa7c2a36180 | 12074986803700257 | 12074986803712188 | 12074986803837307 | 12074986803840508 |
| 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 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7fa8ce69a700 | 0x7fa7c2a361c0 | 12074986803867167 | 12074986803880667 | 12074986804131865 | 12074986804154772 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7fa8ce69a600 | 0x7fa7c2a36200 | 12074986804177394 | 12074986804194424 | 12074986804443383 | 12074986804465780 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7fa8ce69a500 | 0x7fa7c2a36240 | 12074986804490466 | 12074986804503222 | 12074986804628821 | 12074986804631788 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7fa8ce69a400 | 0x7fa7c2a36280 | 12074986804658167 | 12074986804670421 | 12074986804820340 | 12074986804823354 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7fa8ce69a300 | 0x7fa7c2a362c0 | 12074986804879168 | 12074986804890739 | 12074986805015858 | 12074986805019078 |
| 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 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7fa8ce69aa00 | 0x7fa7c2a36300 | 12074986805047310 | 12074986805060178 | 12074986805320816 | 12074986805341247 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7fa8ce69a900 | 0x7fa7c2a36340 | 12074986805362015 | 12074986805374256 | 12074986805620494 | 12074986805640813 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7fa8ce69a800 | 0x7fa7c2a36380 | 12074986805663415 | 12074986805676013 | 12074986805801452 | 12074986805804738 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7fa8ce69a700 | 0x7fa7c2a363c0 | 12074986805831408 | 12074986805845292 | 12074986806002251 | 12074986806006102 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7fa8ce69a600 | 0x7fa7c2a36400 | 12074986806048050 | 12074986806059371 | 12074986806184810 | 12074986806187990 |
| 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 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7fa8ce69a500 | 0x7fa7c2a36440 | 12074986806216343 | 12074986806228809 | 12074986806488967 | 12074986806509247 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7fa8ce69a400 | 0x7fa7c2a36480 | 12074986806530507 | 12074986806542087 | 12074986806785925 | 12074986806806249 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7fa8ce69a300 | 0x7fa7c2a364c0 | 12074986806828340 | 12074986806839685 | 12074986806965284 | 12074986806968310 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7fa8ce69aa00 | 0x7fa7c2a36500 | 12074986806994469 | 12074986807005924 | 12074986807170402 | 12074986807173712 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7fa8ce69a900 | 0x7fa7c2a36540 | 12074986807213105 | 12074986807227042 | 12074986807352321 | 12074986807355310 |
| 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 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7fa8ce69a800 | 0x7fa7c2a36580 | 12074986807381608 | 12074986807394881 | 12074986807648639 | 12074986807665266 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7fa8ce69a700 | 0x7fa7c2a365c0 | 12074986807694069 | 12074986807706558 | 12074986807952956 | 12074986807973037 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7fa8ce69a600 | 0x7fa7c2a36600 | 12074986807997423 | 12074986808016156 | 12074986808140795 | 12074986808144216 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7fa8ce69a500 | 0x7fa7c2a36640 | 12074986808171757 | 12074986808186875 | 12074986808359193 | 12074986808362511 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7fa8ce69a400 | 0x7fa7c2a36680 | 12074986808400482 | 12074986808413593 | 12074986808539192 | 12074986808542215 |
| 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 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7fa8ce69a300 | 0x7fa7c2a366c0 | 12074986808569746 | 12074986808583672 | 12074986808836630 | 12074986808860877 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7fa8ce69aa00 | 0x7fa7c2a36700 | 12074986808881075 | 12074986808893589 | 12074986809138228 | 12074986809158831 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7fa8ce69a900 | 0x7fa7c2a36740 | 12074986809181894 | 12074986809194867 | 12074986809320946 | 12074986809324048 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7fa8ce69a800 | 0x7fa7c2a36780 | 12074986809351008 | 12074986809363666 | 12074986809546865 | 12074986809549948 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7fa8ce69a700 | 0x7fa7c2a367c0 | 12074986809589091 | 12074986809600624 | 12074986809726223 | 12074986809729211 |
| 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 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7fa8ce69a600 | 0x7fa7c2a36800 | 12074986809756251 | 12074986809768943 | 12074986810031821 | 12074986810056930 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7fa8ce69a500 | 0x7fa7c2a36840 | 12074986810078921 | 12074986810090541 | 12074986810337739 | 12074986810361997 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7fa8ce69a400 | 0x7fa7c2a36880 | 12074986810383978 | 12074986810397098 | 12074986810523657 | 12074986810526693 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7fa8ce69a300 | 0x7fa7c2a368c0 | 12074986810553132 | 12074986810566217 | 12074986810757256 | 12074986810761930 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7fa8ce69aa00 | 0x7fa7c2a36900 | 12074986810798939 | 12074986810811975 | 12074986810938374 | 12074986810941805 |
| 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 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7fa8ce69a900 | 0x7fa7c2a36940 | 12074986810967783 | 12074986810981254 | 12074986811262852 | 12074986811287527 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7fa8ce69a800 | 0x7fa7c2a36980 | 12074986811309338 | 12074986811322051 | 12074986811569729 | 12074986811590240 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7fa8ce69a700 | 0x7fa7c2a369c0 | 12074986811613182 | 12074986811626049 | 12074986811752448 | 12074986811755547 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7fa8ce69a600 | 0x7fa7c2a36a00 | 12074986811782958 | 12074986811795968 | 12074986812005246 | 12074986812030307 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7fa8ce69a500 | 0x7fa7c2a36a40 | 12074986812063048 | 12074986812077726 | 12074986812205885 | 12074986812209090 |
| 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 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7fa8ce69a400 | 0x7fa7c2a36a80 | 12074986812235569 | 12074986812247964 | 12074986812554202 | 12074986812575010 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7fa8ce69a300 | 0x7fa7c2a36ac0 | 12074986812600247 | 12074986812611802 | 12074986812861880 | 12074986812886148 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7fa8ce69aa00 | 0x7fa7c2a36b00 | 12074986812907958 | 12074986812920599 | 12074986813048438 | 12074986813051766 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7fa8ce69a900 | 0x7fa7c2a36b40 | 12074986813078615 | 12074986813091638 | 12074986813319316 | 12074986813347225 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7fa8ce69a800 | 0x7fa7c2a36b80 | 12074986813381879 | 12074986813395156 | 12074986813521075 | 12074986813524244 |
| 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 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7fa8ce69a700 | 0x7fa7c2a36bc0 | 12074986813550583 | 12074986813563315 | 12074986813891792 | 12074986813916192 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7fa8ce69a600 | 0x7fa7c2a36c00 | 12074986813937542 | 12074986813950672 | 12074986814200430 | 12074986814225367 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7fa8ce69a500 | 0x7fa7c2a36c40 | 12074986814246736 | 12074986814258349 | 12074986814385869 | 12074986814388981 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7fa8ce69a400 | 0x7fa7c2a36c80 | 12074986814416101 | 12074986814427628 | 12074986814672106 | 12074986814694248 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7fa8ce69a300 | 0x7fa7c2a36cc0 | 12074986814727239 | 12074986814740106 | 12074986814869225 | 12074986814872289 |
| 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 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7fa8ce69aa00 | 0x7fa7c2a36d00 | 12074986814898477 | 12074986814912105 | 12074986815287622 | 12074986815308870 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7fa8ce69a900 | 0x7fa7c2a36d40 | 12074986815329959 | 12074986815342501 | 12074986815593380 | 12074986815613606 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7fa8ce69a800 | 0x7fa7c2a36d80 | 12074986815637200 | 12074986815649859 | 12074986815779458 | 12074986815782671 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7fa8ce69a700 | 0x7fa7c2a36dc0 | 12074986815809000 | 12074986815822018 | 12074986816100096 | 12074986816120819 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7fa8ce69a600 | 0x7fa7c2a36e00 | 12074986816153921 | 12074986816167135 | 12074986816302334 | 12074986816305452 |
| 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 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7fa8ce69a500 | 0x7fa7c2a36e40 | 12074986816331270 | 12074986816344894 | 12074986816767291 | 12074986816788580 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7fa8ce69a400 | 0x7fa7c2a36e80 | 12074986816810060 | 12074986816822490 | 12074986817078488 | 12074986817101992 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7fa8ce69a300 | 0x7fa7c2a36ec0 | 12074986817125125 | 12074986817138168 | 12074986817273687 | 12074986817277088 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7fa8ce69aa00 | 0x7fa7c2a36f00 | 12074986817304168 | 12074986817316087 | 12074986817629844 | 12074986817650231 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7fa8ce69a900 | 0x7fa7c2a36f40 | 12074986817684976 | 12074986817696564 | 12074986817847603 | 12074986817850804 |
| 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 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7fa8ce69a800 | 0x7fa7c2a36f80 | 12074986817878505 | 12074986817890162 | 12074986818406159 | 12074986818426874 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7fa8ce69a700 | 0x7fa7c2a36fc0 | 12074986818448715 | 12074986818461358 | 12074986818760716 | 12074986818781163 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7fa8ce69a600 | 0x7fa7c2a37000 | 12074986818802793 | 12074986818816075 | 12074986818969674 | 12074986818972789 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7fa8ce69a500 | 0x7fa7c2a37040 | 12074986818999258 | 12074986819016714 | 12074986819400711 | 12074986819421393 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7fa8ce69a400 | 0x7fa7c2a37080 | 12074986819455276 | 12074986819468231 | 12074986819644389 | 12074986819647603 |
| 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 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7fa8ce69a300 | 0x7fa7c2a370c0 | 12074986819673972 | 12074986819686949 | 12074986820296384 | 12074986820321135 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7fa8ce69aa00 | 0x7fa7c2a37100 | 12074986820343887 | 12074986820356704 | 12074986820682622 | 12074986820706741 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7fa8ce69a900 | 0x7fa7c2a37140 | 12074986820730135 | 12074986820742781 | 12074986820921340 | 12074986820924466 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7fa8ce69a800 | 0x7fa7c2a37180 | 12074986820950745 | 12074986820962299 | 12074986821416856 | 12074986821445154 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7fa8ce69a700 | 0x7fa7c2a371c0 | 12074986821478475 | 12074986821490296 | 12074986821689174 | 12074986821709214 |
| 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 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7fa8ce69a600 | 0x7fa7c2a37200 | 12074986821729492 | 12074986821741174 | 12074986822444208 | 12074986822469477 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7fa8ce69a500 | 0x7fa7c2a37240 | 12074986822493271 | 12074986822506288 | 12074986822878285 | 12074986822902963 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7fa8ce69a400 | 0x7fa7c2a37280 | 12074986822923741 | 12074986822936685 | 12074986823138923 | 12074986823167304 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7fa8ce69a300 | 0x7fa7c2a372c0 | 12074986823189886 | 12074986823205163 | 12074986823730279 | 12074986823753964 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7fa8ce69aa00 | 0x7fa7c2a37300 | 12074986823791875 | 12074986823805318 | 12074986824028517 | 12074986824049604 |
| 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 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7fa8ce69a900 | 0x7fa7c2a37340 | 12074986824074109 | 12074986824086916 | 12074986824884030 | 12074986824904552 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7fa8ce69a800 | 0x7fa7c2a37380 | 12074986824925662 | 12074986824938110 | 12074986825357787 | 12074986825384725 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7fa8ce69a700 | 0x7fa7c2a373c0 | 12074986825407968 | 12074986825421786 | 12074986825645305 | 12074986825665937 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7fa8ce69a600 | 0x7fa7c2a37400 | 12074986825690102 | 12074986825701624 | 12074986826298260 | 12074986826319452 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7fa8ce69a500 | 0x7fa7c2a37440 | 12074986826356491 | 12074986826368499 | 12074986826637297 | 12074986826658151 |
| 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 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7fa8ce69a400 | 0x7fa7c2a37480 | 12074986826683348 | 12074986826696177 | 12074986827680329 | 12074986827702662 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7fa8ce69a300 | 0x7fa7c2a374c0 | 12074986827726707 | 12074986827738089 | 12074986828254565 | 12074986828276449 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7fa8ce69aa00 | 0x7fa7c2a37500 | 12074986828303268 | 12074986828315205 | 12074986828585923 | 12074986828606833 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7fa8ce69a900 | 0x7fa7c2a37540 | 12074986828630917 | 12074986828642242 | 12074986829379197 | 12074986829404986 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7fa8ce69a800 | 0x7fa7c2a37580 | 12074986829437626 | 12074986829450556 | 12074986829764794 | 12074986829789360 |
| 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 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7fa8ce69a700 | 0x7fa7c2a375c0 | 12074986829810339 | 12074986829823033 | 12074986830994705 | 12074986831026389 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7fa8ce69a600 | 0x7fa7c2a37600 | 12074986831050053 | 12074986831062544 | 12074986831670540 | 12074986831694340 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7fa8ce69a500 | 0x7fa7c2a37640 | 12074986831715269 | 12074986831728459 | 12074986832047817 | 12074986832074026 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7fa8ce69a400 | 0x7fa7c2a37680 | 12074986832098792 | 12074986832111976 | 12074986832989090 | 12074986833015055 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7fa8ce69a300 | 0x7fa7c2a376c0 | 12074986833050911 | 12074986833064129 | 12074986833473886 | 12074986833499375 |
| 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 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7fa8ce69aa00 | 0x7fa7c2a37700 | 12074986833520975 | 12074986833534846 | 12074986835082994 | 12074986835151525 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7fa8ce69a900 | 0x7fa7c2a37740 | 12074986835173075 | 12074986835186433 | 12074986835979708 | 12074986836051928 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7fa8ce69a800 | 0x7fa7c2a37780 | 12074986836073178 | 12074986836086106 | 12074986836499384 | 12074986836566244 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7fa8ce69a700 | 0x7fa7c2a377c0 | 12074986836589197 | 12074986836601783 | 12074986837759536 | 12074986837827328 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7fa8ce69a600 | 0x7fa7c2a37800 | 12074986837859668 | 12074986837873295 | 12074986838657610 | 12074986838728673 |
| 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 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7fa8ce69a500 | 0x7fa7c2a37840 | 12074986838752617 | 12074986838765289 | 12074986841817109 | 12074986841884908 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7fa8ce69a400 | 0x7fa7c2a37880 | 12074986841907270 | 12074986841918869 | 12074986843460939 | 12074986843532139 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7fa8ce69a300 | 0x7fa7c2a378c0 | 12074986843556294 | 12074986843568618 | 12074986844357253 | 12074986844424969 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7fa8ce69aa00 | 0x7fa7c2a37900 | 12074986844447781 | 12074986844460133 | 12074986846742198 | 12074986846810081 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7fa8ce69a900 | 0x7fa7c2a37940 | 12074986846843553 | 12074986846857397 | 12074986848392747 | 12074986848464365 |
| 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 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7fa8ce69a800 | 0x7fa7c2a37980 | 12074986848487709 | 12074986848499627 | 12074986854554308 | 12074986854622790 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7fa8ce69a700 | 0x7fa7c2a379c0 | 12074986854644781 | 12074986854657027 | 12074986857698928 | 12074986857766813 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7fa8ce69a600 | 0x7fa7c2a37a00 | 12074986857788793 | 12074986857800207 | 12074986859338117 | 12074986859406660 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 856550 | 856555 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7fa8ce69a500 | 0x7fa7c2a37a40 | 12074986859427258 | 12074986859439556 | 12074986863965447 | 12074986864033398 |