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 | 765125 | 765130 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7f1f67204180 | 1048576 | 11164777 | 1429239040 | 12073467472462070 | 12073467715806481 | 12073467716131280 | 12073467716223251 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 765125 | 765130 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7f1f67235100 | 4096 | 115725 | 14817852 | 12073467730930413 | 12073467731240451 | 12073467731247011 | 12073467731258703 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7f20972e5900 | 0x7f1f67235140 | 524288 | 11904931 | 1523805584 | 12073467731354080 | 12073467731525889 | 12073467731659649 | 12073467731663165 |
| 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 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7f20972e5800 | 0x7f1f67235180 | 524288 | 12792363 | 1637448276 | 12073467731756979 | 12073467731924928 | 12073467732176447 | 12073467732222715 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7f20972e5700 | 0x7f1f672351c0 | 524288 | 14131644 | 1808810664 | 12073467732291332 | 12073467732466205 | 12073467732714844 | 12073467732758280 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7f20972e5600 | 0x7f1f67235200 | 524288 | 11177346 | 1430714956 | 12073467732825345 | 12073467732991163 | 12073467733126202 | 12073467733129720 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7f20972e5500 | 0x7f1f67235240 | 524288 | 12606907 | 1613648872 | 12073467733193849 | 12073467733360601 | 12073467733491161 | 12073467733494358 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7f20972e5400 | 0x7f1f67235280 | 524288 | 11828883 | 1514165168 | 12073467733586088 | 12073467733747479 | 12073467733880919 | 12073467733884092 |
| 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 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7f20972e5300 | 0x7f1f672352c0 | 524288 | 14250642 | 1824013884 | 12073467733947660 | 12073467734120598 | 12073467734366517 | 12073467734409749 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7f20972e5a00 | 0x7f1f67235300 | 524288 | 13377886 | 1712331408 | 12073467734432662 | 12073467734620275 | 12073467734872594 | 12073467734913595 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7f20972e5900 | 0x7f1f67235340 | 524288 | 11944871 | 1528894124 | 12073467734937239 | 12073467735132433 | 12073467735264753 | 12073467735268194 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7f20972e5800 | 0x7f1f67235380 | 524288 | 12393409 | 1586189152 | 12073467735328306 | 12073467735491792 | 12073467735625071 | 12073467735628354 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7f20972e5700 | 0x7f1f672353c0 | 524288 | 12595801 | 1612221756 | 12073467735697402 | 12073467735858670 | 12073467735988909 | 12073467735992150 |
| 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 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7f20972e5600 | 0x7f1f67235400 | 524288 | 13722627 | 1756453672 | 12073467736052141 | 12073467736214028 | 12073467736470027 | 12073467736512487 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7f20972e5500 | 0x7f1f67235440 | 524288 | 13140875 | 1682007424 | 12073467736539797 | 12073467736715306 | 12073467736970825 | 12073467737018116 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7f20972e5400 | 0x7f1f67235480 | 524288 | 12819847 | 1640939380 | 12073467737042031 | 12073467737227304 | 12073467737355463 | 12073467737358849 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7f20972e5300 | 0x7f1f672354c0 | 524288 | 12002575 | 1536271232 | 12073467737416647 | 12073467737577542 | 12073467737710822 | 12073467737714130 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7f20972e5a00 | 0x7f1f67235500 | 524288 | 12934253 | 1655634392 | 12073467737784360 | 12073467737943940 | 12073467738072260 | 12073467738075672 |
| 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 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7f20972e5900 | 0x7f1f67235540 | 524288 | 14273962 | 1827008660 | 12073467738134281 | 12073467738297699 | 12073467738549538 | 12073467738591130 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7f20972e5800 | 0x7f1f67235580 | 524288 | 14260194 | 1825268628 | 12073467738613631 | 12073467738797697 | 12073467739049056 | 12073467739091239 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7f20972e5700 | 0x7f1f672355c0 | 524288 | 12590690 | 1611563376 | 12073467739112659 | 12073467739301374 | 12073467739431774 | 12073467739435028 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7f20972e5600 | 0x7f1f67235600 | 524288 | 11256730 | 1440851624 | 12073467739495671 | 12073467739656573 | 12073467739791932 | 12073467739795187 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7f20972e5500 | 0x7f1f67235640 | 524288 | 12478517 | 1597226992 | 12073467739863815 | 12073467740029851 | 12073467740160090 | 12073467740163682 |
| 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 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7f20972e5400 | 0x7f1f67235680 | 524288 | 12727518 | 1629193324 | 12073467740220197 | 12073467740382169 | 12073467740639288 | 12073467740680522 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7f20972e5300 | 0x7f1f672356c0 | 524288 | 13020527 | 1666546816 | 12073467740705188 | 12073467740884087 | 12073467741140086 | 12073467741182946 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7f20972e5a00 | 0x7f1f67235700 | 524288 | 13164330 | 1684975944 | 12073467741209325 | 12073467741386325 | 12073467741514644 | 12073467741517808 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7f20972e5900 | 0x7f1f67235740 | 524288 | 12800208 | 1638333520 | 12073467741576528 | 12073467741739923 | 12073467741870003 | 12073467741873329 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7f20972e5800 | 0x7f1f67235780 | 524288 | 12793405 | 1637451032 | 12073467741943970 | 12073467742108562 | 12073467742238321 | 12073467742241684 |
| 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 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7f20972e5700 | 0x7f1f672357c0 | 524288 | 11618586 | 1487224464 | 12073467742299271 | 12073467742458960 | 12073467742715279 | 12073467742755569 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7f20972e5600 | 0x7f1f67235800 | 524288 | 13380870 | 1712752668 | 12073467742779022 | 12073467742959438 | 12073467743215597 | 12073467743260818 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7f20972e5500 | 0x7f1f67235840 | 524288 | 12631798 | 1616832696 | 12073467743283570 | 12073467743470316 | 12073467743600235 | 12073467743603464 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7f20972e5400 | 0x7f1f67235880 | 524288 | 11939594 | 1528229124 | 12073467743661001 | 12073467743820874 | 12073467743997033 | 12073467744005782 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7f20972e5300 | 0x7f1f672358c0 | 524288 | 12225704 | 1564951948 | 12073467744071664 | 12073467744234632 | 12073467744366152 | 12073467744369568 |
| 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 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7f20972e5a00 | 0x7f1f67235900 | 524288 | 13391489 | 1714133964 | 12073467744428127 | 12073467744587271 | 12073467744848389 | 12073467744889063 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7f20972e5900 | 0x7f1f67235940 | 524288 | 14263111 | 1825681648 | 12073467744915553 | 12073467745097508 | 12073467745350307 | 12073467745392840 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7f20972e5800 | 0x7f1f67235980 | 524288 | 12362779 | 1582550624 | 12073467745417796 | 12073467745595906 | 12073467745728865 | 12073467745732210 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7f20972e5700 | 0x7f1f672359c0 | 524288 | 12077629 | 1545842920 | 12073467745789958 | 12073467745949984 | 12073467746123424 | 12073467746127154 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7f20972e5600 | 0x7f1f67235a00 | 524288 | 11641155 | 1489977712 | 12073467746193668 | 12073467746358623 | 12073467746492062 | 12073467746495639 |
| 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 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7f20972e5500 | 0x7f1f67235a40 | 524288 | 13451688 | 1721749628 | 12073467746553316 | 12073467746711101 | 12073467746965340 | 12073467747013021 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7f20972e5400 | 0x7f1f67235a80 | 524288 | 14203952 | 1818038408 | 12073467747040081 | 12073467747218939 | 12073467747468538 | 12073467747510615 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7f20972e5300 | 0x7f1f67235ac0 | 524288 | 12872195 | 1647710996 | 12073467747532326 | 12073467747710136 | 12073467747839576 | 12073467747843053 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7f20972e5a00 | 0x7f1f67235b00 | 524288 | 12291264 | 1573306556 | 12073467747901101 | 12073467748057815 | 12073467748191574 | 12073467748195037 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7f20972e5900 | 0x7f1f67235b40 | 524288 | 11174749 | 1430389996 | 12073467748267502 | 12073467748427893 | 12073467748562293 | 12073467748565606 |
| 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 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7f20972e5800 | 0x7f1f67235b80 | 524288 | 13921533 | 1781915976 | 12073467748623474 | 12073467748783252 | 12073467749048850 | 12073467749089800 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7f20972e5700 | 0x7f1f67235bc0 | 524288 | 14232490 | 1821785964 | 12073467749115969 | 12073467749293329 | 12073467749580848 | 12073467749622901 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7f20972e5600 | 0x7f1f67235c00 | 524288 | 12276567 | 1571279480 | 12073467749645443 | 12073467749827727 | 12073467749959886 | 12073467749963253 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7f20972e5500 | 0x7f1f67235c40 | 524288 | 11216693 | 1435660440 | 12073467750031079 | 12073467750194125 | 12073467750333165 | 12073467750336617 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7f20972e5400 | 0x7f1f67235c80 | 524288 | 10978312 | 1405285500 | 12073467750405956 | 12073467750567244 | 12073467750702923 | 12073467750706294 |
| 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 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7f20972e5300 | 0x7f1f67235cc0 | 524288 | 13999164 | 1791899548 | 12073467750763711 | 12073467750923082 | 12073467751190761 | 12073467751236189 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7f20972e5a00 | 0x7f1f67235d00 | 524288 | 13004315 | 1664526796 | 12073467751264071 | 12073467751442120 | 12073467751697798 | 12073467751738502 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7f20972e5900 | 0x7f1f67235d40 | 524288 | 12614457 | 1614587496 | 12073467751760223 | 12073467751941637 | 12073467752071877 | 12073467752075549 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7f20972e5800 | 0x7f1f67235d80 | 524288 | 10410984 | 1332545528 | 12073467752135891 | 12073467752297796 | 12073467752438275 | 12073467752441709 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7f20972e5700 | 0x7f1f67235dc0 | 524288 | 11853986 | 1517350104 | 12073467752510587 | 12073467752668674 | 12073467752801313 | 12073467752804714 |
| 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 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7f20972e5600 | 0x7f1f67235e00 | 524288 | 12448644 | 1593449636 | 12073467752863052 | 12073467753027072 | 12073467753289631 | 12073467753331613 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7f20972e5500 | 0x7f1f67235e40 | 524288 | 13193225 | 1688692688 | 12073467753355147 | 12073467753538430 | 12073467753795229 | 12073467753836391 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7f20972e5400 | 0x7f1f67235e80 | 524288 | 12886389 | 1649380980 | 12073467753858352 | 12073467754041468 | 12073467754169627 | 12073467754173437 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7f20972e5300 | 0x7f1f67235ec0 | 524288 | 9556459 | 1223231480 | 12073467754233780 | 12073467754398266 | 12073467754537626 | 12073467754540970 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7f20972e5a00 | 0x7f1f67235f00 | 524288 | 12716314 | 1627714108 | 12073467754610470 | 12073467754769145 | 12073467754898424 | 12073467754901871 |
| 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 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7f20972e5900 | 0x7f1f67235f40 | 524288 | 13649718 | 1747126196 | 12073467754957555 | 12073467755123543 | 12073467755386102 | 12073467755409685 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7f20972e5800 | 0x7f1f67235f80 | 524288 | 14123489 | 1807768340 | 12073467755451783 | 12073467755608821 | 12073467755855700 | 12073467755877584 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7f20972e5700 | 0x7f1f67235fc0 | 524288 | 12048398 | 1542141120 | 12073467755920604 | 12073467756082579 | 12073467756215058 | 12073467756218518 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7f20972e5600 | 0x7f1f67236000 | 524288 | 7809833 | 999670708 | 12073467756276646 | 12073467756437617 | 12073467756576976 | 12073467756580381 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7f20972e5500 | 0x7f1f67236040 | 524288 | 10436447 | 1335941284 | 12073467756648537 | 12073467756806735 | 12073467756945615 | 12073467756949246 |
| 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 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7f20972e5400 | 0x7f1f67236080 | 524288 | 12324685 | 1577598456 | 12073467757009598 | 12073467757173774 | 12073467757435053 | 12073467757458552 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7f20972e5300 | 0x7f1f672360c0 | 524288 | 12758362 | 1633023620 | 12073467757500831 | 12073467757657132 | 12073467757916970 | 12073467757938524 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7f20972e5a00 | 0x7f1f67236100 | 524288 | 12110279 | 1550002608 | 12073467757983248 | 12073467758146409 | 12073467758278249 | 12073467758281612 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7f20972e5900 | 0x7f1f67236140 | 524288 | 7415433 | 949305008 | 12073467758338418 | 12073467758499048 | 12073467758642567 | 12073467758646180 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7f20972e5800 | 0x7f1f67236180 | 524288 | 12786143 | 1636643000 | 12073467758713996 | 12073467758874726 | 12073467759004645 | 12073467759008312 |
| 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 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7f20972e5700 | 0x7f1f672361c0 | 524288 | 11282040 | 1444040416 | 12073467759065940 | 12073467759225924 | 12073467759488323 | 12073467759511087 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7f20972e5600 | 0x7f1f67236200 | 524288 | 14176218 | 1814555652 | 12073467759553977 | 12073467759712162 | 12073467759970881 | 12073467759993173 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7f20972e5500 | 0x7f1f67236240 | 524288 | 11339231 | 1451321660 | 12073467760039459 | 12073467760196480 | 12073467760331039 | 12073467760334577 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7f20972e5400 | 0x7f1f67236280 | 524288 | 6231314 | 797427636 | 12073467760392164 | 12073467760550078 | 12073467760700958 | 12073467760704565 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7f20972e5300 | 0x7f1f672362c0 | 524288 | 10836144 | 1386997548 | 12073467760790004 | 12073467760949437 | 12073467761085756 | 12073467761089540 |
| 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 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7f20972e5a00 | 0x7f1f67236300 | 524288 | 13189200 | 1688159408 | 12073467761148289 | 12073467761308315 | 12073467761575354 | 12073467761596713 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7f20972e5900 | 0x7f1f67236340 | 524288 | 13663454 | 1748935560 | 12073467761640624 | 12073467761795993 | 12073467762052632 | 12073467762075432 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7f20972e5800 | 0x7f1f67236380 | 524288 | 11790813 | 1509212656 | 12073467762117801 | 12073467762291511 | 12073467762425110 | 12073467762428659 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7f20972e5700 | 0x7f1f672363c0 | 524288 | 4808514 | 615355656 | 12073467762484222 | 12073467762643829 | 12073467762802868 | 12073467762806280 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7f20972e5600 | 0x7f1f67236400 | 524288 | 11238063 | 1438473616 | 12073467762878585 | 12073467763045747 | 12073467763180787 | 12073467763184363 |
| 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 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7f20972e5500 | 0x7f1f67236440 | 524288 | 10882773 | 1392896924 | 12073467763240638 | 12073467763400946 | 12073467763660784 | 12073467763682669 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7f20972e5400 | 0x7f1f67236480 | 524288 | 12386923 | 1585454496 | 12073467763725649 | 12073467763882223 | 12073467764141102 | 12073467764164916 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7f20972e5300 | 0x7f1f672364c0 | 524288 | 11321465 | 1449160136 | 12073467764208396 | 12073467764370701 | 12073467764506541 | 12073467764510087 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7f20972e5a00 | 0x7f1f67236500 | 524288 | 4282738 | 548235416 | 12073467764563015 | 12073467764733100 | 12073467764899499 | 12073467764903117 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7f20972e5900 | 0x7f1f67236540 | 524288 | 11799773 | 1510343776 | 12073467764971755 | 12073467765135018 | 12073467765269417 | 12073467765273285 |
| 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 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7f20972e5800 | 0x7f1f67236580 | 524288 | 9883222 | 1264924608 | 12073467765328538 | 12073467765488616 | 12073467765749735 | 12073467765770770 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7f20972e5700 | 0x7f1f672365c0 | 524288 | 12746033 | 1631463956 | 12073467765813770 | 12073467765969734 | 12073467766227493 | 12073467766249219 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7f20972e5600 | 0x7f1f67236600 | 524288 | 11463111 | 1467315020 | 12073467766292229 | 12073467766451972 | 12073467766585091 | 12073467766588580 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7f20972e5500 | 0x7f1f67236640 | 524288 | 3703340 | 473893204 | 12073467766644914 | 12073467766801410 | 12073467766975970 | 12073467766979486 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7f20972e5400 | 0x7f1f67236680 | 524288 | 12476371 | 1596881940 | 12073467767052131 | 12073467767217408 | 12073467767348608 | 12073467767352349 |
| 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 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7f20972e5300 | 0x7f1f672366c0 | 524288 | 8648918 | 1107142632 | 12073467767409746 | 12073467767570687 | 12073467767827166 | 12073467767848601 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7f20972e5a00 | 0x7f1f67236700 | 524288 | 12775435 | 1635229524 | 12073467767897592 | 12073467768074685 | 12073467768334203 | 12073467768356325 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7f20972e5900 | 0x7f1f67236740 | 524288 | 10821550 | 1385171992 | 12073467768398162 | 12073467768555322 | 12073467768693882 | 12073467768697489 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7f20972e5800 | 0x7f1f67236780 | 524288 | 3728171 | 477113592 | 12073467768755517 | 12073467768914841 | 12073467769098040 | 12073467769101550 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7f20972e5700 | 0x7f1f672367c0 | 524288 | 11752794 | 1504369720 | 12073467769174736 | 12073467769337879 | 12073467769470998 | 12073467769474513 |
| 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 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7f20972e5600 | 0x7f1f67236800 | 524288 | 4256803 | 544710860 | 12073467769530517 | 12073467769690197 | 12073467769990836 | 12073467770015618 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7f20972e5500 | 0x7f1f67236840 | 524288 | 12656051 | 1619936896 | 12073467770068076 | 12073467770230195 | 12073467770492754 | 12073467770514205 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7f20972e5400 | 0x7f1f67236880 | 524288 | 12835249 | 1642983620 | 12073467770562404 | 12073467770724273 | 12073467770854512 | 12073467770858134 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7f20972e5300 | 0x7f1f672368c0 | 524288 | 3495695 | 447478504 | 12073467770913988 | 12073467771082351 | 12073467771273550 | 12073467771295827 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7f20972e5a00 | 0x7f1f67236900 | 524288 | 11494105 | 1471210696 | 12073467771351330 | 12073467771510029 | 12073467771645068 | 12073467771648603 |
| 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 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7f20972e5900 | 0x7f1f67236940 | 524288 | 2882151 | 368855200 | 12073467771702854 | 12073467771862507 | 12073467772144906 | 12073467772167307 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7f20972e5800 | 0x7f1f67236980 | 524288 | 13266149 | 1698015848 | 12073467772210367 | 12073467772370185 | 12073467772630184 | 12073467772651146 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7f20972e5700 | 0x7f1f672369c0 | 524288 | 11446539 | 1465203996 | 12073467772693866 | 12073467772851623 | 12073467772986662 | 12073467772990196 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7f20972e5600 | 0x7f1f67236a00 | 524288 | 3450907 | 441905468 | 12073467773049837 | 12073467773209701 | 12073467773419460 | 12073467773441856 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7f20972e5500 | 0x7f1f67236a40 | 524288 | 11195501 | 1432990292 | 12073467773496778 | 12073467773657379 | 12073467773793859 | 12073467773797436 |
| 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 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7f20972e5400 | 0x7f1f67236a80 | 524288 | 2578930 | 330126692 | 12073467773853450 | 12073467774013698 | 12073467774323456 | 12073467774344944 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7f20972e5300 | 0x7f1f67236ac0 | 524288 | 13898958 | 1779043092 | 12073467774388234 | 12073467774548095 | 12073467774801854 | 12073467774823303 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7f20972e5a00 | 0x7f1f67236b00 | 524288 | 11796659 | 1509909048 | 12073467774865802 | 12073467775030173 | 12073467775164733 | 12073467775168454 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7f20972e5900 | 0x7f1f67236b40 | 524288 | 3410996 | 436544376 | 12073467775227213 | 12073467775389692 | 12073467775617211 | 12073467775638929 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7f20972e5800 | 0x7f1f67236b80 | 524288 | 11163625 | 1428925968 | 12073467775697918 | 12073467775858329 | 12073467775995929 | 12073467775999699 |
| 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 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7f20972e5700 | 0x7f1f67236bc0 | 524288 | 2460624 | 315002312 | 12073467776056134 | 12073467776215768 | 12073467776544726 | 12073467776566492 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7f20972e5600 | 0x7f1f67236c00 | 524288 | 14182092 | 1815288020 | 12073467776610805 | 12073467776771765 | 12073467777026964 | 12073467777048278 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7f20972e5500 | 0x7f1f67236c40 | 524288 | 10746725 | 1375533556 | 12073467777091698 | 12073467777251443 | 12073467777390643 | 12073467777394241 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7f20972e5400 | 0x7f1f67236c80 | 524288 | 3449262 | 441627204 | 12073467777450695 | 12073467777608882 | 12073467777854960 | 12073467777876096 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7f20972e5300 | 0x7f1f67236cc0 | 524288 | 9936453 | 1271890536 | 12073467777934354 | 12073467778099919 | 12073467778240239 | 12073467778243869 |
| 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 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7f20972e5a00 | 0x7f1f67236d00 | 524288 | 2390119 | 305787448 | 12073467778299964 | 12073467778460370 | 12073467778837809 | 12073467778862760 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7f20972e5900 | 0x7f1f67236d40 | 524288 | 13295392 | 1701821752 | 12073467778901291 | 12073467779072687 | 12073467779338606 | 12073467779360134 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7f20972e5800 | 0x7f1f67236d80 | 524288 | 10300058 | 1318375424 | 12073467779400509 | 12073467779558925 | 12073467779695885 | 12073467779698322 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7f20972e5700 | 0x7f1f67236dc0 | 524288 | 3355659 | 429587388 | 12073467779756020 | 12073467779914924 | 12073467780224843 | 12073467780249447 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7f20972e5600 | 0x7f1f67236e00 | 524288 | 8385515 | 1073268932 | 12073467780304559 | 12073467780466602 | 12073467780605642 | 12073467780608153 |
| 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 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7f20972e5500 | 0x7f1f67236e40 | 524288 | 2338901 | 299253540 | 12073467780665650 | 12073467780823721 | 12073467781271240 | 12073467781294449 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7f20972e5400 | 0x7f1f67236e80 | 524288 | 9451627 | 1209800572 | 12073467781336908 | 12073467781495719 | 12073467781755558 | 12073467781775843 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7f20972e5300 | 0x7f1f67236ec0 | 524288 | 7856352 | 1005586060 | 12073467781817110 | 12073467781973478 | 12073467782112997 | 12073467782115975 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7f20972e5a00 | 0x7f1f67236f00 | 524288 | 3442656 | 440740732 | 12073467782174324 | 12073467782335237 | 12073467782650916 | 12073467782670827 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7f20972e5900 | 0x7f1f67236f40 | 524288 | 3697637 | 473346884 | 12073467782727121 | 12073467782885955 | 12073467783039874 | 12073467783042678 |
| 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 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7f20972e5800 | 0x7f1f67236f80 | 524288 | 2324257 | 297422052 | 12073467783100094 | 12073467783266114 | 12073467783784672 | 12073467783805706 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7f20972e5700 | 0x7f1f67236fc0 | 524288 | 7943928 | 1016791732 | 12073467783849056 | 12073467784007391 | 12073467784306430 | 12073467784327906 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7f20972e5600 | 0x7f1f67237000 | 524288 | 3471218 | 444209676 | 12073467784370916 | 12073467784535230 | 12073467784689949 | 12073467784692674 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7f20972e5500 | 0x7f1f67237040 | 524288 | 3532803 | 452166156 | 12073467784748678 | 12073467784907229 | 12073467785292987 | 12073467785316243 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7f20972e5400 | 0x7f1f67237080 | 524288 | 3435636 | 439837172 | 12073467785374902 | 12073467785539067 | 12073467785716666 | 12073467785719181 |
| 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 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7f20972e5300 | 0x7f1f672370c0 | 524288 | 2352723 | 301244504 | 12073467785776728 | 12073467785935545 | 12073467786548183 | 12073467786571255 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7f20972e5a00 | 0x7f1f67237100 | 524288 | 4478321 | 573082948 | 12073467786615237 | 12073467786775863 | 12073467787102902 | 12073467787125685 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7f20972e5900 | 0x7f1f67237140 | 524288 | 3412646 | 436784236 | 12073467787172903 | 12073467787333621 | 12073467787512340 | 12073467787515219 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7f20972e5800 | 0x7f1f67237180 | 524288 | 3324921 | 425740940 | 12073467787572776 | 12073467787735220 | 12073467788190898 | 12073467788213216 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7f20972e5700 | 0x7f1f672371c0 | 524288 | 3237235 | 414319724 | 12073467788274731 | 12073467788436337 | 12073467788636497 | 12073467788658243 |
| 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 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7f20972e5600 | 0x7f1f67237200 | 524288 | 2356530 | 301769200 | 12073467788705561 | 12073467788864976 | 12073467789568174 | 12073467789593181 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7f20972e5500 | 0x7f1f67237240 | 524288 | 3506012 | 448809888 | 12073467789633846 | 12073467789797133 | 12073467790171372 | 12073467790192154 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7f20972e5400 | 0x7f1f67237280 | 524288 | 3289850 | 421172888 | 12073467790242057 | 12073467790407211 | 12073467790611051 | 12073467790630729 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7f20972e5300 | 0x7f1f672372c0 | 524288 | 4364932 | 558713100 | 12073467790674210 | 12073467790832650 | 12073467791359048 | 12073467791380803 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7f20972e5a00 | 0x7f1f67237300 | 524288 | 3150560 | 403242832 | 12073467791438079 | 12073467791600008 | 12073467791823687 | 12073467791843383 |
| 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 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7f20972e5900 | 0x7f1f67237340 | 524288 | 2291074 | 293413844 | 12073467791887725 | 12073467792052486 | 12073467792851684 | 12073467792872415 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7f20972e5800 | 0x7f1f67237380 | 524288 | 3495666 | 447522840 | 12073467792917228 | 12073467793081763 | 12073467793503042 | 12073467793525739 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7f20972e5700 | 0x7f1f672373c0 | 524288 | 3093776 | 395864544 | 12073467793566565 | 12073467793730401 | 12073467793956960 | 12073467793978871 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7f20972e5600 | 0x7f1f67237400 | 524288 | 4680953 | 599176356 | 12073467794027702 | 12073467794190719 | 12073467794787518 | 12073467794810897 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7f20972e5500 | 0x7f1f67237440 | 524288 | 3292054 | 421311888 | 12073467794863034 | 12073467795030237 | 12073467795298876 | 12073467795320104 |
| 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 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7f20972e5400 | 0x7f1f67237480 | 524288 | 2357316 | 301566312 | 12073467795364737 | 12073467795525275 | 12073467796511192 | 12073467796531495 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7f20972e5300 | 0x7f1f672374c0 | 524288 | 3184283 | 407448480 | 12073467796581287 | 12073467796743191 | 12073467797258710 | 12073467797281058 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7f20972e5a00 | 0x7f1f67237500 | 524288 | 3392906 | 434183876 | 12073467797330159 | 12073467797492629 | 12073467797764628 | 12073467797784654 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7f20972e5900 | 0x7f1f67237540 | 524288 | 2189488 | 280201548 | 12073467797834867 | 12073467797997267 | 12073467798740465 | 12073467798763733 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7f20972e5800 | 0x7f1f67237580 | 524288 | 3324167 | 425450728 | 12073467798823565 | 12073467798986384 | 12073467799302703 | 12073467799323804 |
| 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 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7f20972e5700 | 0x7f1f672375c0 | 524288 | 2295036 | 293590408 | 12073467799366864 | 12073467799526383 | 12073467800696779 | 12073467800718316 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7f20972e5600 | 0x7f1f67237600 | 524288 | 3210817 | 410830088 | 12073467800766585 | 12073467800928778 | 12073467801539816 | 12073467801561843 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7f20972e5500 | 0x7f1f67237640 | 524288 | 3326161 | 425602152 | 12073467801607909 | 12073467801770216 | 12073467802089095 | 12073467802110803 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7f20972e5400 | 0x7f1f67237680 | 524288 | 2247886 | 287631076 | 12073467802164523 | 12073467802336774 | 12073467803214851 | 12073467803237447 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7f20972e5300 | 0x7f1f672376c0 | 524288 | 3257878 | 417078568 | 12073467803297789 | 12073467803459330 | 12073467803891009 | 12073467803911540 |
| 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 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7f20972e5a00 | 0x7f1f67237700 | 524288 | 2314594 | 296190408 | 12073467803960952 | 12073467804129088 | 12073467805678523 | 12073467805723126 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7f20972e5900 | 0x7f1f67237740 | 524288 | 2275512 | 291343996 | 12073467805752581 | 12073467805932923 | 12073467806730360 | 12073467806771074 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7f20972e5800 | 0x7f1f67237780 | 524288 | 2167199 | 277474980 | 12073467806794488 | 12073467806974519 | 12073467807389238 | 12073467807431071 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7f20972e5700 | 0x7f1f672377c0 | 524288 | 2321113 | 297250548 | 12073467807460465 | 12073467807641237 | 12073467808801234 | 12073467808842744 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7f20972e5600 | 0x7f1f67237800 | 524288 | 2256774 | 288697904 | 12073467808885383 | 12073467809054033 | 12073467809839950 | 12073467809882226 |
| 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 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7f20972e5500 | 0x7f1f67237840 | 524288 | 2644137 | 338399476 | 12073467809911260 | 12073467810092429 | 12073467813143140 | 12073467813168302 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7f20972e5400 | 0x7f1f67237880 | 524288 | 2318729 | 296965100 | 12073467813271705 | 12073467813435139 | 12073467814979294 | 12073467815021847 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7f20972e5300 | 0x7f1f672378c0 | 524288 | 2191695 | 280551512 | 12073467815099982 | 12073467815266173 | 12073467816056891 | 12073467816099089 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7f20972e5a00 | 0x7f1f67237900 | 524288 | 2528080 | 323490432 | 12073467816129015 | 12073467816309530 | 12073467818591443 | 12073467818633940 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7f20972e5900 | 0x7f1f67237940 | 524288 | 2529694 | 323776836 | 12073467818706244 | 12073467818868562 | 12073467820404077 | 12073467820446548 |
| 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 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7f20972e5800 | 0x7f1f67237980 | 524288 | 2921941 | 374016748 | 12073467820527970 | 12073467820697996 | 12073467826752537 | 12073467826798312 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7f20972e5700 | 0x7f1f672379c0 | 524288 | 3112900 | 398177868 | 12073467826877790 | 12073467827047896 | 12073467830088687 | 12073467830133029 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7f20972e5600 | 0x7f1f67237a00 | 524288 | 2469860 | 316038660 | 12073467830209562 | 12073467830380526 | 12073467831920521 | 12073467831964102 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 765125 | 765130 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7f20972e5500 | 0x7f1f67237a40 | 524288 | 2559018 | 327580704 | 12073467832059049 | 12073467832222760 | 12073467836749466 | 12073467836795300 |