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_SMEM | SQ_INST_LEVEL_SMEM | SQ_ACCUM_PREV_HIRES | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBuffer.kd | 0 | 0 | 0 | 764935 | 764940 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7f8a19404180 | 4194304 | 3088996 | 395039432 | 12073466213072332 | 12073466456014836 | 12073466456339634 | 12073466456458346 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 764935 | 764940 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7f8a19435100 | 512 | 22210 | 2831400 | 12073466471032120 | 12073466471333596 | 12073466471340476 | 12073466471353988 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7f8b25119900 | 0x7f8a19435140 | 65536 | 171692 | 21946688 | 12073466471404091 | 12073466471620475 | 12073466471755514 | 12073466471759442 |
| 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 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7f8b25119800 | 0x7f8a19435180 | 65536 | 158326 | 20144712 | 12073466471830714 | 12073466471997273 | 12073466472242552 | 12073466472313722 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7f8b25119700 | 0x7f8a194351c0 | 65536 | 171130 | 21909440 | 12073466472348316 | 12073466472533910 | 12073466472790389 | 12073466472857202 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7f8b25119600 | 0x7f8a19435200 | 65536 | 201280 | 25803216 | 12073466472881026 | 12073466473080307 | 12073466473218867 | 12073466473222881 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7f8b25119500 | 0x7f8a19435240 | 65536 | 172394 | 22054096 | 12073466473275208 | 12073466473443826 | 12073466473575185 | 12073466473578993 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7f8b25119400 | 0x7f8a19435280 | 131072 | 244430 | 31330520 | 12073466473660154 | 12073466473823024 | 12073466473951823 | 12073466473955563 |
| 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 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7f8b25119300 | 0x7f8a194352c0 | 131072 | 209626 | 26906032 | 12073466474008501 | 12073466474190222 | 12073466474443501 | 12073466474485037 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7f8b25119a00 | 0x7f8a19435300 | 65536 | 175300 | 22392208 | 12073466474511145 | 12073466474691659 | 12073466474945258 | 12073466474985637 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7f8b25119900 | 0x7f8a19435340 | 131072 | 241000 | 30935816 | 12073466475015683 | 12073466475204297 | 12073466475339496 | 12073466475343232 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7f8b25119800 | 0x7f8a19435380 | 131072 | 249348 | 32140288 | 12073466475391712 | 12073466475562375 | 12073466475692774 | 12073466475696378 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7f8b25119700 | 0x7f8a194353c0 | 131072 | 246536 | 31632104 | 12073466475758363 | 12073466475923173 | 12073466476057412 | 12073466476061316 |
| 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 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7f8b25119600 | 0x7f8a19435400 | 131072 | 206192 | 26403232 | 12073466476109115 | 12073466476281731 | 12073466476530370 | 12073466476597893 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7f8b25119500 | 0x7f8a19435440 | 65536 | 172048 | 21987256 | 12073466476621016 | 12073466476799168 | 12073466477048287 | 12073466477094175 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7f8b25119400 | 0x7f8a19435480 | 131072 | 241262 | 30889016 | 12073466477117789 | 12073466477300606 | 12073466477428125 | 12073466477432113 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7f8b25119300 | 0x7f8a194354c0 | 131072 | 253544 | 32479744 | 12073466477471246 | 12073466477651644 | 12073466477786843 | 12073466477790750 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7f8b25119a00 | 0x7f8a19435500 | 131072 | 262174 | 33632880 | 12073466477851393 | 12073466478022842 | 12073466478151002 | 12073466478154887 |
| 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 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7f8b25119900 | 0x7f8a19435540 | 131072 | 230986 | 29484840 | 12073466478203457 | 12073466478377720 | 12073466478638519 | 12073466478680794 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7f8b25119800 | 0x7f8a19435580 | 65536 | 173836 | 22200584 | 12073466478698166 | 12073466478887638 | 12073466479146356 | 12073466479213724 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7f8b25119700 | 0x7f8a194355c0 | 131072 | 268256 | 34333488 | 12073466479242368 | 12073466479418675 | 12073466479550514 | 12073466479554217 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7f8b25119600 | 0x7f8a19435600 | 131072 | 254066 | 32438256 | 12073466479602577 | 12073466479770833 | 12073466479903633 | 12073466479907303 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7f8b25119500 | 0x7f8a19435640 | 131072 | 246366 | 31448528 | 12073466479966153 | 12073466480138991 | 12073466480267631 | 12073466480271781 |
| 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 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7f8b25119400 | 0x7f8a19435680 | 131072 | 209484 | 26887680 | 12073466480310362 | 12073466480490830 | 12073466480753068 | 12073466480819469 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7f8b25119300 | 0x7f8a194356c0 | 65536 | 175000 | 22320096 | 12073466480844665 | 12073466481027467 | 12073466481278826 | 12073466481345646 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7f8b25119a00 | 0x7f8a19435700 | 131072 | 255592 | 32708880 | 12073466481372536 | 12073466481549224 | 12073466481677384 | 12073466481681180 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7f8b25119900 | 0x7f8a19435740 | 131072 | 241444 | 30980536 | 12073466481732866 | 12073466481897222 | 12073466482031302 | 12073466482035559 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7f8b25119800 | 0x7f8a19435780 | 131072 | 246150 | 31516656 | 12073466482097423 | 12073466482263781 | 12073466482392580 | 12073466482396349 |
| 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 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7f8b25119700 | 0x7f8a194357c0 | 131072 | 213256 | 27277704 | 12073466482443767 | 12073466482618339 | 12073466482869697 | 12073466482911957 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7f8b25119600 | 0x7f8a19435800 | 65536 | 174504 | 22275416 | 12073466482937184 | 12073466483126336 | 12073466483376895 | 12073466483443615 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7f8b25119500 | 0x7f8a19435840 | 131072 | 248052 | 31707568 | 12073466483467780 | 12073466483649053 | 12073466483781053 | 12073466483784940 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7f8b25119400 | 0x7f8a19435880 | 131072 | 264422 | 33853128 | 12073466483832298 | 12073466484002812 | 12073466484135931 | 12073466484139929 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7f8b25119300 | 0x7f8a194358c0 | 131072 | 244272 | 31313000 | 12073466484202125 | 12073466484369370 | 12073466484497209 | 12073466484501060 |
| 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 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7f8b25119a00 | 0x7f8a19435900 | 131072 | 214430 | 27291952 | 12073466484543830 | 12073466484716728 | 12073466484975127 | 12073466485042537 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7f8b25119900 | 0x7f8a19435940 | 65536 | 173442 | 22127224 | 12073466485078423 | 12073466485244405 | 12073466485496404 | 12073466485536985 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7f8b25119800 | 0x7f8a19435980 | 131072 | 248270 | 31735896 | 12073466485561160 | 12073466485737523 | 12073466485873202 | 12073466485876947 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7f8b25119700 | 0x7f8a194359c0 | 131072 | 241752 | 31026272 | 12073466485925788 | 12073466486100561 | 12073466486235600 | 12073466486239551 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7f8b25119600 | 0x7f8a19435a00 | 131072 | 260530 | 33424208 | 12073466486301426 | 12073466486464239 | 12073466486593358 | 12073466486597186 |
| 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 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7f8b25119500 | 0x7f8a19435a40 | 131072 | 211802 | 27136752 | 12073466486645986 | 12073466486815437 | 12073466487065356 | 12073466487132000 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7f8b25119400 | 0x7f8a19435a80 | 65536 | 179482 | 22992984 | 12073466487151175 | 12073466487334315 | 12073466487586473 | 12073466487652657 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7f8b25119300 | 0x7f8a19435ac0 | 131072 | 243506 | 31366736 | 12073466487676812 | 12073466487853352 | 12073466487981511 | 12073466487985305 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7f8b25119a00 | 0x7f8a19435b00 | 131072 | 229428 | 29535768 | 12073466488033916 | 12073466488207430 | 12073466488339109 | 12073466488343130 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7f8b25119900 | 0x7f8a19435b40 | 131072 | 251070 | 31975080 | 12073466488402841 | 12073466488568068 | 12073466488701828 | 12073466488705784 |
| 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 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7f8b25119800 | 0x7f8a19435b80 | 131072 | 215600 | 27540072 | 12073466488746600 | 12073466488922466 | 12073466489181825 | 12073466489252721 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7f8b25119700 | 0x7f8a19435bc0 | 65536 | 175494 | 22456968 | 12073466489270223 | 12073466489457664 | 12073466489707742 | 12073466489748141 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7f8b25119600 | 0x7f8a19435c00 | 131072 | 258292 | 33029688 | 12073466489785761 | 12073466489947741 | 12073466490078621 | 12073466490082423 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7f8b25119500 | 0x7f8a19435c40 | 131072 | 246416 | 31681464 | 12073466490132325 | 12073466490307899 | 12073466490447259 | 12073466490451228 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7f8b25119400 | 0x7f8a19435c80 | 131072 | 250530 | 32035832 | 12073466490512833 | 12073466490671578 | 12073466490802777 | 12073466490806608 |
| 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 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7f8b25119300 | 0x7f8a19435cc0 | 131072 | 204570 | 26284064 | 12073466490854027 | 12073466491029336 | 12073466491295094 | 12073466491361930 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7f8b25119a00 | 0x7f8a19435d00 | 65536 | 179174 | 23067352 | 12073466491385434 | 12073466491565813 | 12073466491814932 | 12073466491881937 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7f8b25119900 | 0x7f8a19435d40 | 131072 | 250726 | 31960440 | 12073466491904198 | 12073466492086610 | 12073466492215570 | 12073466492219564 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7f8b25119800 | 0x7f8a19435d80 | 131072 | 223282 | 28544448 | 12073466492262193 | 12073466492436048 | 12073466492569968 | 12073466492573742 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7f8b25119700 | 0x7f8a19435dc0 | 131072 | 249552 | 31735736 | 12073466492634355 | 12073466492794607 | 12073466492926766 | 12073466492930485 |
| 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 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7f8b25119600 | 0x7f8a19435e00 | 131072 | 250808 | 32123744 | 12073466492981731 | 12073466493148365 | 12073466493416043 | 12073466493463015 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7f8b25119500 | 0x7f8a19435e40 | 65536 | 171892 | 22039544 | 12073466493486990 | 12073466493666122 | 12073466493920201 | 12073466493967342 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7f8b25119400 | 0x7f8a19435e80 | 131072 | 252818 | 32209616 | 12073466493991547 | 12073466494185480 | 12073466494315399 | 12073466494319376 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7f8b25119300 | 0x7f8a19435ec0 | 131072 | 243218 | 30990688 | 12073466494368588 | 12073466494533798 | 12073466494677157 | 12073466494680938 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7f8b25119a00 | 0x7f8a19435f00 | 131072 | 248632 | 31945696 | 12073466494742934 | 12073466494902756 | 12073466495031875 | 12073466495035587 |
| 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 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7f8b25119900 | 0x7f8a19435f40 | 131072 | 250226 | 32170928 | 12073466495084548 | 12073466495255394 | 12073466495514593 | 12073466495561665 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7f8b25119800 | 0x7f8a19435f80 | 65536 | 173510 | 22288616 | 12073466495584357 | 12073466495760511 | 12073466496016670 | 12073466496065682 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7f8b25119700 | 0x7f8a19435fc0 | 131072 | 253844 | 32489280 | 12073466496088544 | 12073466496273469 | 12073466496408348 | 12073466496412055 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7f8b25119600 | 0x7f8a19436000 | 131072 | 243392 | 31143824 | 12073466496462529 | 12073466496621307 | 12073466496762426 | 12073466496766093 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7f8b25119500 | 0x7f8a19436040 | 131072 | 241504 | 31012880 | 12073466496827738 | 12073466496986425 | 12073466497164664 | 12073466497168651 |
| 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 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7f8b25119400 | 0x7f8a19436080 | 131072 | 208008 | 26639736 | 12073466497219416 | 12073466497383703 | 12073466497647862 | 12073466497697414 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7f8b25119300 | 0x7f8a194360c0 | 65536 | 177316 | 22596672 | 12073466497713715 | 12073466497901301 | 12073466498151059 | 12073466498200419 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7f8b25119a00 | 0x7f8a19436100 | 131072 | 240066 | 30860264 | 12073466498222921 | 12073466498403218 | 12073466498537137 | 12073466498541102 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7f8b25119900 | 0x7f8a19436140 | 131072 | 205648 | 26310688 | 12073466498592508 | 12073466498749136 | 12073466498894415 | 12073466498898096 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7f8b25119800 | 0x7f8a19436180 | 131072 | 245468 | 31514032 | 12073466498958418 | 12073466499126894 | 12073466499258254 | 12073466499262543 |
| 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 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7f8b25119700 | 0x7f8a194361c0 | 131072 | 227206 | 29101968 | 12073466499311464 | 12073466499481292 | 12073466499749611 | 12073466499774194 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7f8b25119600 | 0x7f8a19436200 | 65536 | 173232 | 22146976 | 12073466499816051 | 12073466499984170 | 12073466500237449 | 12073466500287758 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7f8b25119500 | 0x7f8a19436240 | 131072 | 267522 | 34087256 | 12073466500317614 | 12073466500503207 | 12073466500641447 | 12073466500645493 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7f8b25119400 | 0x7f8a19436280 | 131072 | 217462 | 27809224 | 12073466500694664 | 12073466500870565 | 12073466501021765 | 12073466501025820 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7f8b25119300 | 0x7f8a194362c0 | 131072 | 240278 | 30794168 | 12073466501103334 | 12073466501274723 | 12073466501402723 | 12073466501406607 |
| 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 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7f8b25119a00 | 0x7f8a19436300 | 131072 | 205092 | 26182368 | 12073466501448555 | 12073466501632801 | 12073466501897600 | 12073466501943665 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7f8b25119900 | 0x7f8a19436340 | 65536 | 173916 | 22258224 | 12073466501968421 | 12073466502158239 | 12073466502411677 | 12073466502458502 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7f8b25119800 | 0x7f8a19436380 | 131072 | 237308 | 30220488 | 12073466502476556 | 12073466502667836 | 12073466502805115 | 12073466502808913 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7f8b25119700 | 0x7f8a194363c0 | 131072 | 249182 | 31832096 | 12073466502851482 | 12073466503037434 | 12073466503195353 | 12073466503199369 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7f8b25119600 | 0x7f8a19436400 | 131072 | 242532 | 31196248 | 12073466503260793 | 12073466503428312 | 12073466503559352 | 12073466503563245 |
| 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 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7f8b25119500 | 0x7f8a19436440 | 131072 | 205212 | 26339264 | 12073466503613569 | 12073466503787030 | 12073466504049109 | 12073466504097869 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7f8b25119400 | 0x7f8a19436480 | 65536 | 169656 | 21674600 | 12073466504124087 | 12073466504310868 | 12073466504563826 | 12073466504610722 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7f8b25119300 | 0x7f8a194364c0 | 131072 | 242324 | 30929152 | 12073466504628805 | 12073466504820945 | 12073466504954064 | 12073466504958238 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7f8b25119a00 | 0x7f8a19436500 | 131072 | 243640 | 31433032 | 12073466505013560 | 12073466505200463 | 12073466505366542 | 12073466505370784 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7f8b25119900 | 0x7f8a19436540 | 131072 | 246248 | 31601848 | 12073466505431557 | 12073466505600941 | 12073466505735340 | 12073466505739269 |
| 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 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7f8b25119800 | 0x7f8a19436580 | 131072 | 206564 | 26377848 | 12073466505788300 | 12073466505963819 | 12073466506225258 | 12073466506272740 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7f8b25119700 | 0x7f8a194365c0 | 65536 | 178016 | 22779504 | 12073466506297396 | 12073466506485577 | 12073466506742855 | 12073466506789631 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7f8b25119600 | 0x7f8a19436600 | 131072 | 247130 | 31639488 | 12073466506816311 | 12073466506997574 | 12073466507131333 | 12073466507135674 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7f8b25119500 | 0x7f8a19436640 | 131072 | 246082 | 31364832 | 12073466507183814 | 12073466507361892 | 12073466507536131 | 12073466507540096 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7f8b25119400 | 0x7f8a19436680 | 131072 | 246538 | 31675672 | 12073466507601670 | 12073466507768450 | 12073466507904929 | 12073466507908941 |
| 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 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7f8b25119300 | 0x7f8a194366c0 | 131072 | 204098 | 26101008 | 12073466507949226 | 12073466508139328 | 12073466508401247 | 12073466508449886 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7f8b25119a00 | 0x7f8a19436700 | 65536 | 172166 | 22034536 | 12073466508469974 | 12073466508660126 | 12073466508915324 | 12073466508961858 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7f8b25119900 | 0x7f8a19436740 | 131072 | 244062 | 31130848 | 12073466508981054 | 12073466509189403 | 12073466509322842 | 12073466509327207 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7f8b25119800 | 0x7f8a19436780 | 131072 | 243604 | 31107560 | 12073466509367151 | 12073466509558681 | 12073466509741880 | 12073466509745905 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7f8b25119700 | 0x7f8a194367c0 | 131072 | 241702 | 30874400 | 12073466509809213 | 12073466509974679 | 12073466510110038 | 12073466510114119 |
| 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 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7f8b25119600 | 0x7f8a19436800 | 131072 | 234992 | 30304344 | 12073466510163110 | 12073466510340597 | 12073466510607636 | 12073466510655235 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7f8b25119500 | 0x7f8a19436840 | 65536 | 170242 | 21746280 | 12073466510673348 | 12073466510861074 | 12073466511116753 | 12073466511138954 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7f8b25119400 | 0x7f8a19436880 | 131072 | 237852 | 30525720 | 12073466511181603 | 12073466511344752 | 12073466511479791 | 12073466511483724 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7f8b25119300 | 0x7f8a194368c0 | 131072 | 266972 | 33930376 | 12073466511523769 | 12073466511706350 | 12073466511898989 | 12073466511945613 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7f8b25119a00 | 0x7f8a19436900 | 131072 | 242858 | 30973040 | 12073466511980187 | 12073466512155468 | 12073466512292587 | 12073466512296825 |
| 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 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7f8b25119900 | 0x7f8a19436940 | 131072 | 240186 | 30871440 | 12073466512346858 | 12073466512520426 | 12073466512803784 | 12073466512850615 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7f8b25119800 | 0x7f8a19436980 | 65536 | 185100 | 23723632 | 12073466512870451 | 12073466513067783 | 12073466513319462 | 12073466513370010 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7f8b25119700 | 0x7f8a194369c0 | 131072 | 251508 | 32036216 | 12073466513395908 | 12073466513581380 | 12073466513722500 | 12073466513726602 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7f8b25119600 | 0x7f8a19436a00 | 131072 | 252766 | 32267008 | 12073466513775012 | 12073466513948738 | 12073466514160417 | 12073466514210291 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7f8b25119500 | 0x7f8a19436a40 | 131072 | 250344 | 32145968 | 12073466514245968 | 12073466514416256 | 12073466514552415 | 12073466514556565 |
| 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 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7f8b25119400 | 0x7f8a19436a80 | 131072 | 243002 | 30888592 | 12073466514605055 | 12073466514778814 | 12073466515087773 | 12073466515111426 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7f8b25119300 | 0x7f8a19436ac0 | 65536 | 173852 | 22193320 | 12073466515150719 | 12073466515315131 | 12073466515571450 | 12073466515618078 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7f8b25119a00 | 0x7f8a19436b00 | 131072 | 267646 | 34260336 | 12073466515641862 | 12073466515825529 | 12073466515964568 | 12073466515968619 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7f8b25119900 | 0x7f8a19436b40 | 131072 | 257318 | 32956416 | 12073466516013983 | 12073466516200247 | 12073466516428886 | 12073466516478386 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7f8b25119800 | 0x7f8a19436b80 | 131072 | 251902 | 32267536 | 12073466516519032 | 12073466516685524 | 12073466516819604 | 12073466516823778 |
| 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 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7f8b25119700 | 0x7f8a19436bc0 | 131072 | 251854 | 32511800 | 12073466516865175 | 12073466517058323 | 12073466517389841 | 12073466517440815 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7f8b25119600 | 0x7f8a19436c00 | 65536 | 173234 | 22050440 | 12073466517460702 | 12073466517657840 | 12073466517914158 | 12073466517961092 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7f8b25119500 | 0x7f8a19436c40 | 131072 | 249254 | 31776448 | 12073466517984856 | 12073466518176877 | 12073466518311916 | 12073466518316102 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7f8b25119400 | 0x7f8a19436c80 | 131072 | 240696 | 30946816 | 12073466518357038 | 12073466518549035 | 12073466518795114 | 12073466518842650 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7f8b25119300 | 0x7f8a19436cc0 | 131072 | 251822 | 32210104 | 12073466518885009 | 12073466519056024 | 12073466519192664 | 12073466519200004 |
| 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 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7f8b25119a00 | 0x7f8a19436d00 | 131072 | 242484 | 31073120 | 12073466519236562 | 12073466519422582 | 12073466519800660 | 12073466519846436 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7f8b25119900 | 0x7f8a19436d40 | 65536 | 198110 | 25363928 | 12073466519869559 | 12073466520078259 | 12073466520343538 | 12073466520393272 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7f8b25119800 | 0x7f8a19436d80 | 131072 | 242472 | 30823584 | 12073466520418879 | 12073466520605617 | 12073466520746096 | 12073466520749313 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7f8b25119700 | 0x7f8a19436dc0 | 131072 | 262378 | 33796840 | 12073466520798455 | 12073466520971695 | 12073466521252814 | 12073466521303954 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7f8b25119600 | 0x7f8a19436e00 | 131072 | 240722 | 30705848 | 12073466521340582 | 12073466521520333 | 12073466521660013 | 12073466521663232 |
| 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 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7f8b25119500 | 0x7f8a19436e40 | 131072 | 242626 | 30868592 | 12073466521712313 | 12073466521889932 | 12073466522315530 | 12073466522362441 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7f8b25119400 | 0x7f8a19436e80 | 65536 | 177850 | 22694456 | 12073466522390774 | 12073466522575529 | 12073466522843048 | 12073466522889230 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7f8b25119300 | 0x7f8a19436ec0 | 131072 | 241370 | 30742128 | 12073466522912503 | 12073466523119687 | 12073466523259526 | 12073466523262865 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7f8b25119a00 | 0x7f8a19436f00 | 131072 | 231180 | 29629712 | 12073466523303440 | 12073466523487365 | 12073466523832004 | 12073466523854214 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7f8b25119900 | 0x7f8a19436f40 | 131072 | 244146 | 31218312 | 12073466523910117 | 12073466524086403 | 12073466524239362 | 12073466524242826 |
| 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 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7f8b25119800 | 0x7f8a19436f80 | 131072 | 250594 | 31987680 | 12073466524284223 | 12073466524470882 | 12073466524989920 | 12073466525036681 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7f8b25119700 | 0x7f8a19436fc0 | 65536 | 166150 | 21232720 | 12073466525056338 | 12073466525250558 | 12073466525549437 | 12073466525596010 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7f8b25119600 | 0x7f8a19437000 | 131072 | 244110 | 31113168 | 12073466525618482 | 12073466525805916 | 12073466525963196 | 12073466525966329 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7f8b25119500 | 0x7f8a19437040 | 131072 | 249292 | 31757128 | 12073466526020359 | 12073466526200635 | 12073466526587193 | 12073466526636624 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7f8b25119400 | 0x7f8a19437080 | 131072 | 246834 | 31468472 | 12073466526671830 | 12073466526845272 | 12073466527021911 | 12073466527024986 |
| 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 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7f8b25119300 | 0x7f8a194370c0 | 131072 | 239518 | 30690496 | 12073466527073055 | 12073466527257751 | 12073466527869588 | 12073466527917334 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7f8b25119a00 | 0x7f8a19437100 | 65536 | 167656 | 21468568 | 12073466527936881 | 12073466528133107 | 12073466528462066 | 12073466528510507 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7f8b25119900 | 0x7f8a19437140 | 131072 | 246240 | 31464680 | 12073466528535042 | 12073466528719505 | 12073466528899344 | 12073466528902706 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7f8b25119800 | 0x7f8a19437180 | 131072 | 238450 | 30592448 | 12073466528945605 | 12073466529131983 | 12073466529590221 | 12073466529640637 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7f8b25119700 | 0x7f8a194371c0 | 131072 | 241696 | 31011280 | 12073466529677786 | 12073466529846380 | 12073466530047179 | 12073466530094530 |
| 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 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7f8b25119600 | 0x7f8a19437200 | 131072 | 241548 | 30755952 | 12073466530113716 | 12073466530305738 | 12073466531010216 | 12073466531059233 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7f8b25119500 | 0x7f8a19437240 | 65536 | 181570 | 23131344 | 12073466531078569 | 12073466531277735 | 12073466531651333 | 12073466531699733 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7f8b25119400 | 0x7f8a19437280 | 131072 | 247918 | 31799832 | 12073466531726203 | 12073466531926052 | 12073466532166211 | 12073466532217005 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7f8b25119300 | 0x7f8a194372c0 | 131072 | 247030 | 31582800 | 12073466532240408 | 12073466532419330 | 12073466532946528 | 12073466532993328 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7f8b25119a00 | 0x7f8a19437300 | 131072 | 262860 | 33730448 | 12073466533037890 | 12073466533200767 | 12073466533425566 | 12073466533472077 |
| 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 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7f8b25119900 | 0x7f8a19437340 | 131072 | 243248 | 31239504 | 12073466533495391 | 12073466533671485 | 12073466534471482 | 12073466534519594 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7f8b25119800 | 0x7f8a19437380 | 65536 | 176764 | 22565304 | 12073466534542837 | 12073466534722521 | 12073466535143959 | 12073466535192955 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7f8b25119700 | 0x7f8a194373c0 | 131072 | 245734 | 31402152 | 12073466535223692 | 12073466535404118 | 12073466535630357 | 12073466535677626 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7f8b25119600 | 0x7f8a19437400 | 131072 | 243518 | 31192064 | 12073466535699907 | 12073466535877236 | 12073466536475634 | 12073466536544757 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7f8b25119500 | 0x7f8a19437440 | 131072 | 239584 | 30959816 | 12073466536583189 | 12073466536749713 | 12073466537019152 | 12073466537085703 |
| 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 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7f8b25119400 | 0x7f8a19437480 | 131072 | 226452 | 28928528 | 12073466537109497 | 12073466537304271 | 12073466538289707 | 12073466538357105 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7f8b25119300 | 0x7f8a194374c0 | 65536 | 174744 | 22261056 | 12073466538388864 | 12073466538569386 | 12073466539083304 | 12073466539150089 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7f8b25119a00 | 0x7f8a19437500 | 131072 | 245946 | 31445840 | 12073466539177710 | 12073466539360262 | 12073466539633221 | 12073466539698939 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7f8b25119900 | 0x7f8a19437540 | 131072 | 264412 | 34068000 | 12073466539722994 | 12073466539906820 | 12073466540646017 | 12073466540715268 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7f8b25119800 | 0x7f8a19437580 | 131072 | 240378 | 30831624 | 12073466540759430 | 12073466540922816 | 12073466541239615 | 12073466541307549 |
| 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 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7f8b25119700 | 0x7f8a194375c0 | 131072 | 249554 | 31711416 | 12073466541325261 | 12073466541518814 | 12073466542688889 | 12073466542756211 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7f8b25119600 | 0x7f8a19437600 | 65536 | 169736 | 21709656 | 12073466542787088 | 12073466542965208 | 12073466543577526 | 12073466543644762 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7f8b25119500 | 0x7f8a19437640 | 131072 | 247448 | 31415632 | 12073466543675810 | 12073466543855445 | 12073466544204403 | 12073466544273861 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7f8b25119400 | 0x7f8a19437680 | 131072 | 245752 | 31400280 | 12073466544300741 | 12073466544481042 | 12073466545360079 | 12073466545426603 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7f8b25119300 | 0x7f8a194376c0 | 131072 | 245200 | 31618624 | 12073466545463472 | 12073466545639278 | 12073466546049196 | 12073466546116475 |
| 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 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7f8b25119a00 | 0x7f8a19437700 | 131072 | 256660 | 33027736 | 12073466546148625 | 12073466546327115 | 12073466547876229 | 12073466547943561 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7f8b25119900 | 0x7f8a19437740 | 65536 | 175386 | 22592168 | 12073466547973316 | 12073466548158628 | 12073466548953504 | 12073466549022235 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7f8b25119800 | 0x7f8a19437780 | 131072 | 252800 | 32303448 | 12073466549047292 | 12073466549227903 | 12073466549642462 | 12073466549707970 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7f8b25119700 | 0x7f8a194377c0 | 131072 | 261724 | 33506808 | 12073466549726154 | 12073466549907901 | 12073466551067096 | 12073466551133529 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7f8b25119600 | 0x7f8a19437800 | 131072 | 252300 | 32221368 | 12073466551174165 | 12073466551336855 | 12073466552122932 | 12073466552189952 |
| 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 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7f8b25119500 | 0x7f8a19437840 | 131072 | 241512 | 30888496 | 12073466552220349 | 12073466552399411 | 12073466555451719 | 12073466555519600 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7f8b25119400 | 0x7f8a19437880 | 65536 | 172356 | 21958224 | 12073466555551299 | 12073466555729158 | 12073466557271391 | 12073466557339702 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7f8b25119300 | 0x7f8a194378c0 | 131072 | 238778 | 30820760 | 12073466557372323 | 12073466557552670 | 12073466558342107 | 12073466558409661 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7f8b25119a00 | 0x7f8a19437900 | 131072 | 249228 | 31508032 | 12073466558439156 | 12073466558623226 | 12073466560904977 | 12073466560972193 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7f8b25119900 | 0x7f8a19437940 | 131072 | 243078 | 31387280 | 12073466561021334 | 12073466561188496 | 12073466562724650 | 12073466562791744 |
| 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 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7f8b25119800 | 0x7f8a19437980 | 131072 | 248262 | 31780192 | 12073466562825948 | 12073466563000969 | 12073466569057265 | 12073466569130124 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7f8b25119700 | 0x7f8a194379c0 | 65536 | 172094 | 22033704 | 12073466569157715 | 12073466569341263 | 12073466572385731 | 12073466572452949 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7f8b25119600 | 0x7f8a19437a00 | 131072 | 253688 | 32375976 | 12073466572483626 | 12073466572663650 | 12073466574203644 | 12073466574271067 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 764935 | 764940 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7f8b25119500 | 0x7f8a19437a40 | 131072 | 251920 | 32278144 | 12073466574302085 | 12073466574484763 | 12073466579012105 | 12073466579083220 |