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 | 875394 | 875399 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7f9114204180 | 4194304 | 3178902 | 406901080 | 12075443676964683 | 12075443921800580 | 12075443922128098 | 12075443922232171 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 875394 | 875399 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7f9114235100 | 512 | 22856 | 2927128 | 12075443936949303 | 12075443937266695 | 12075443937273575 | 12075443937283263 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7f921ff0c900 | 0x7f9114235140 | 65536 | 176256 | 22446856 | 12075443937346050 | 12075443937557573 | 12075443937689093 | 12075443937693215 |
| 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 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7f921ff0c800 | 0x7f9114235180 | 65536 | 160938 | 20524784 | 12075443937772482 | 12075443937946691 | 12075443938197090 | 12075443938251302 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7f921ff0c700 | 0x7f91142351c0 | 65536 | 174736 | 22409352 | 12075443938285566 | 12075443938476928 | 12075443938725567 | 12075443938772130 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7f921ff0c600 | 0x7f9114235200 | 65536 | 179566 | 22962832 | 12075443938797107 | 12075443938983646 | 12075443939122685 | 12075443939126679 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7f921ff0c500 | 0x7f9114235240 | 65536 | 176732 | 22518544 | 12075443939185378 | 12075443939354524 | 12075443939486203 | 12075443939489924 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7f921ff0c400 | 0x7f9114235280 | 131072 | 243478 | 31106144 | 12075443939576766 | 12075443939743802 | 12075443939877241 | 12075443939880510 |
| 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 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7f921ff0c300 | 0x7f91142352c0 | 131072 | 206672 | 26585200 | 12075443939939289 | 12075443940108600 | 12075443940357718 | 12075443940378355 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7f921ff0ca00 | 0x7f9114235300 | 65536 | 176386 | 22712224 | 12075443940429120 | 12075443940593877 | 12075443940843956 | 12075443940889846 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7f921ff0c900 | 0x7f9114235340 | 131072 | 265694 | 33729488 | 12075443940911977 | 12075443941112274 | 12075443941242513 | 12075443941246429 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7f921ff0c800 | 0x7f9114235380 | 131072 | 262702 | 33638944 | 12075443941303495 | 12075443941475312 | 12075443941609711 | 12075443941613581 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7f921ff0c700 | 0x7f91142353c0 | 131072 | 252098 | 31995920 | 12075443941682389 | 12075443941846510 | 12075443941976269 | 12075443941979972 |
| 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 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7f921ff0c600 | 0x7f9114235400 | 131072 | 206376 | 26454400 | 12075443942042809 | 12075443942206668 | 12075443942458027 | 12075443942505308 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7f921ff0c500 | 0x7f9114235440 | 65536 | 175466 | 22451568 | 12075443942532849 | 12075443942710185 | 12075443942966024 | 12075443943019303 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7f921ff0c400 | 0x7f9114235480 | 131072 | 248976 | 31763776 | 12075443943047365 | 12075443943229703 | 12075443943359782 | 12075443943363463 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7f921ff0c300 | 0x7f91142354c0 | 131072 | 272994 | 34866624 | 12075443943420429 | 12075443943585861 | 12075443943719940 | 12075443943723572 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7f921ff0ca00 | 0x7f9114235500 | 131072 | 243180 | 31007224 | 12075443943791549 | 12075443943956419 | 12075443944088098 | 12075443944092308 |
| 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 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7f921ff0c900 | 0x7f9114235540 | 131072 | 207818 | 26691120 | 12075443944149654 | 12075443944316577 | 12075443944572895 | 12075443944618826 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7f921ff0c800 | 0x7f9114235580 | 65536 | 178210 | 22801072 | 12075443944643301 | 12075443944829374 | 12075443945084733 | 12075443945131970 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7f921ff0c700 | 0x7f91142355c0 | 131072 | 267008 | 34025040 | 12075443945159371 | 12075443945338651 | 12075443945469370 | 12075443945472883 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7f921ff0c600 | 0x7f9114235600 | 131072 | 259572 | 33189520 | 12075443945532644 | 12075443945693049 | 12075443945828089 | 12075443945831991 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7f921ff0c500 | 0x7f9114235640 | 131072 | 260274 | 33313672 | 12075443945900628 | 12075443946062967 | 12075443946194167 | 12075443946198111 |
| 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 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7f921ff0c400 | 0x7f9114235680 | 131072 | 216698 | 27809224 | 12075443946255227 | 12075443946415605 | 12075443946670324 | 12075443946715953 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7f921ff0c300 | 0x7f91142356c0 | 65536 | 175054 | 22497048 | 12075443946742212 | 12075443946918483 | 12075443947168721 | 12075443947214911 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7f921ff0ca00 | 0x7f9114235700 | 131072 | 242096 | 31119888 | 12075443947241670 | 12075443947423440 | 12075443947553199 | 12075443947556936 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7f921ff0c900 | 0x7f9114235740 | 131072 | 246282 | 31573880 | 12075443947616086 | 12075443947777678 | 12075443947953997 | 12075443947957631 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7f921ff0c800 | 0x7f9114235780 | 131072 | 254598 | 32555664 | 12075443948033181 | 12075443948201996 | 12075443948334795 | 12075443948339050 |
| 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 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7f921ff0c700 | 0x7f91142357c0 | 131072 | 208250 | 26750672 | 12075443948395535 | 12075443948557514 | 12075443948815112 | 12075443948861280 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7f921ff0c600 | 0x7f9114235800 | 65536 | 176924 | 22621888 | 12075443948887770 | 12075443949072231 | 12075443949326950 | 12075443949375416 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7f921ff0c500 | 0x7f9114235840 | 131072 | 249048 | 31797936 | 12075443949399781 | 12075443949585348 | 12075443949717507 | 12075443949721068 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7f921ff0c400 | 0x7f9114235880 | 131072 | 240158 | 30836632 | 12075443949778094 | 12075443949941826 | 12075443950074466 | 12075443950078653 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7f921ff0c300 | 0x7f91142358c0 | 131072 | 249072 | 31960592 | 12075443950146178 | 12075443950314624 | 12075443950445503 | 12075443950449262 |
| 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 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7f921ff0ca00 | 0x7f9114235900 | 131072 | 205292 | 26265632 | 12075443950506508 | 12075443950669022 | 12075443950919741 | 12075443950965782 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7f921ff0c900 | 0x7f9114235940 | 65536 | 173388 | 22196336 | 12075443950989766 | 12075443951177500 | 12075443951432538 | 12075443951478815 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7f921ff0c800 | 0x7f9114235980 | 131072 | 245386 | 31401872 | 12075443951505304 | 12075443951684537 | 12075443951813176 | 12075443951816903 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7f921ff0c700 | 0x7f91142359c0 | 131072 | 244704 | 31280944 | 12075443951875813 | 12075443952039575 | 12075443952171574 | 12075443952175440 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7f921ff0c600 | 0x7f9114235a00 | 131072 | 230270 | 29560216 | 12075443952243316 | 12075443952405653 | 12075443952535732 | 12075443952539436 |
| 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 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7f921ff0c500 | 0x7f9114235a40 | 131072 | 213050 | 27272104 | 12075443952596101 | 12075443952756851 | 12075443953004050 | 12075443953051458 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7f921ff0c400 | 0x7f9114235a80 | 65536 | 176548 | 22627512 | 12075443953075623 | 12075443953258128 | 12075443953511727 | 12075443953558029 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7f921ff0c300 | 0x7f9114235ac0 | 131072 | 253226 | 32444520 | 12075443953585190 | 12075443953761326 | 12075443953892845 | 12075443953896538 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7f921ff0ca00 | 0x7f9114235b00 | 131072 | 250244 | 32125736 | 12075443953953173 | 12075443954120044 | 12075443954257963 | 12075443954262118 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7f921ff0c900 | 0x7f9114235b40 | 131072 | 246322 | 31591152 | 12075443954332909 | 12075443954494122 | 12075443954624841 | 12075443954628358 |
| 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 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7f921ff0c800 | 0x7f9114235b80 | 131072 | 207174 | 26611992 | 12075443954685875 | 12075443954846760 | 12075443955109478 | 12075443955156289 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7f921ff0c700 | 0x7f9114235bc0 | 65536 | 199814 | 25631008 | 12075443955183730 | 12075443955360677 | 12075443955617795 | 12075443955664133 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7f921ff0c600 | 0x7f9114235c00 | 131072 | 242300 | 31067336 | 12075443955687637 | 12075443955867074 | 12075443955995553 | 12075443955999366 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7f921ff0c500 | 0x7f9114235c40 | 131072 | 248392 | 31757824 | 12075443956056192 | 12075443956217472 | 12075443956350591 | 12075443956354095 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7f921ff0c400 | 0x7f9114235c80 | 131072 | 271254 | 34937152 | 12075443956422733 | 12075443956584030 | 12075443956713470 | 12075443956717200 |
| 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 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7f921ff0c300 | 0x7f9114235cc0 | 131072 | 211108 | 27142936 | 12075443956775248 | 12075443956936668 | 12075443957193467 | 12075443957239982 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7f921ff0ca00 | 0x7f9114235d00 | 65536 | 190364 | 24404048 | 12075443957266742 | 12075443957445466 | 12075443957702104 | 12075443957748136 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7f921ff0c900 | 0x7f9114235d40 | 131072 | 243952 | 31163720 | 12075443957770898 | 12075443957951383 | 12075443958082422 | 12075443958086565 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7f921ff0c800 | 0x7f9114235d80 | 131072 | 273172 | 34935840 | 12075443958144493 | 12075443958311541 | 12075443958452500 | 12075443958456122 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7f921ff0c700 | 0x7f9114235dc0 | 131072 | 245852 | 31625752 | 12075443958525070 | 12075443958686899 | 12075443958815858 | 12075443958819998 |
| 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 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7f921ff0c600 | 0x7f9114235e00 | 131072 | 251352 | 32213752 | 12075443958876994 | 12075443959042897 | 12075443959306095 | 12075443959352187 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7f921ff0c500 | 0x7f9114235e40 | 65536 | 198048 | 25375304 | 12075443959376422 | 12075443959557934 | 12075443959813453 | 12075443959833933 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7f921ff0c400 | 0x7f9114235e80 | 131072 | 256026 | 32722304 | 12075443959884837 | 12075443960053611 | 12075443960183691 | 12075443960187540 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7f921ff0c300 | 0x7f9114235ec0 | 131072 | 264488 | 33814704 | 12075443960243764 | 12075443960401930 | 12075443960547369 | 12075443960551166 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7f921ff0ca00 | 0x7f9114235f00 | 131072 | 248388 | 31763632 | 12075443960621857 | 12075443960781927 | 12075443960913927 | 12075443960917737 |
| 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 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7f921ff0c900 | 0x7f9114235f40 | 131072 | 247570 | 31755800 | 12075443960974011 | 12075443961142565 | 12075443961406884 | 12075443961453482 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7f921ff0c800 | 0x7f9114235f80 | 65536 | 172218 | 22018672 | 12075443961478038 | 12075443961657923 | 12075443961911681 | 12075443961931691 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7f921ff0c700 | 0x7f9114235fc0 | 131072 | 248132 | 31772408 | 12075443961982075 | 12075443962150880 | 12075443962284799 | 12075443962288635 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7f921ff0c600 | 0x7f9114236000 | 131072 | 245500 | 31323944 | 12075443962347063 | 12075443962511838 | 12075443962650077 | 12075443962653954 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7f921ff0c500 | 0x7f9114236040 | 131072 | 267116 | 34113400 | 12075443962722942 | 12075443962882876 | 12075443963016635 | 12075443963020935 |
| 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 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7f921ff0c400 | 0x7f9114236080 | 131072 | 207488 | 26540744 | 12075443963078953 | 12075443963244154 | 12075443963506553 | 12075443963552744 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7f921ff0c300 | 0x7f91142360c0 | 65536 | 170734 | 21780656 | 12075443963574945 | 12075443963761591 | 12075443964053270 | 12075443964099600 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7f921ff0ca00 | 0x7f9114236100 | 131072 | 229018 | 29084760 | 12075443964125338 | 12075443964307028 | 12075443964439828 | 12075443964443750 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7f921ff0c900 | 0x7f9114236140 | 131072 | 209844 | 26841592 | 12075443964499884 | 12075443964661266 | 12075443964806706 | 12075443964810822 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7f921ff0c800 | 0x7f9114236180 | 131072 | 245982 | 31449280 | 12075443964878828 | 12075443965046064 | 12075443965177264 | 12075443965181361 |
| 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 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7f921ff0c700 | 0x7f91142361c0 | 131072 | 214966 | 27521720 | 12075443965241132 | 12075443965397422 | 12075443965661261 | 12075443965707138 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7f921ff0c600 | 0x7f9114236200 | 65536 | 199180 | 25415056 | 12075443965733677 | 12075443965914220 | 12075443966170858 | 12075443966220352 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7f921ff0c500 | 0x7f9114236240 | 131072 | 248224 | 31661808 | 12075443966248895 | 12075443966425417 | 12075443966553416 | 12075443966557157 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7f921ff0c400 | 0x7f9114236280 | 131072 | 222784 | 28514408 | 12075443966613682 | 12075443966775015 | 12075443966924614 | 12075443966928588 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7f921ff0c300 | 0x7f91142362c0 | 131072 | 246110 | 31584104 | 12075443967020128 | 12075443967183013 | 12075443967317092 | 12075443967320917 |
| 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 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7f921ff0ca00 | 0x7f9114236300 | 131072 | 203866 | 26264584 | 12075443967379355 | 12075443967539331 | 12075443967806369 | 12075443967852966 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7f921ff0c900 | 0x7f9114236340 | 65536 | 182852 | 23369712 | 12075443967875427 | 12075443968076448 | 12075443968333246 | 12075443968379955 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7f921ff0c800 | 0x7f9114236380 | 131072 | 248676 | 31760344 | 12075443968406895 | 12075443968583965 | 12075443968716124 | 12075443968719987 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7f921ff0c700 | 0x7f91142363c0 | 131072 | 247630 | 31669616 | 12075443968776261 | 12075443968934843 | 12075443969092762 | 12075443969096677 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7f921ff0c600 | 0x7f9114236400 | 131072 | 244568 | 31565656 | 12075443969169633 | 12075443969334361 | 12075443969465400 | 12075443969469289 |
| 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 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7f921ff0c500 | 0x7f9114236440 | 131072 | 201126 | 25715064 | 12075443969524913 | 12075443969683799 | 12075443969946678 | 12075443969992322 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7f921ff0c400 | 0x7f9114236480 | 65536 | 170168 | 21722608 | 12075443970016426 | 12075443970202836 | 12075443970458835 | 12075443970506337 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7f921ff0c300 | 0x7f91142364c0 | 131072 | 246470 | 31738312 | 12075443970532626 | 12075443970707314 | 12075443970845873 | 12075443970849545 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7f921ff0ca00 | 0x7f9114236500 | 131072 | 249850 | 31904968 | 12075443970904176 | 12075443971070512 | 12075443971235471 | 12075443971239549 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7f921ff0c900 | 0x7f9114236540 | 131072 | 244804 | 31429912 | 12075443971305282 | 12075443971467150 | 12075443971600109 | 12075443971603836 |
| 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 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7f921ff0c800 | 0x7f9114236580 | 131072 | 208990 | 26707688 | 12075443971660281 | 12075443971823148 | 12075443972086186 | 12075443972133631 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7f921ff0c700 | 0x7f91142365c0 | 65536 | 177714 | 22765776 | 12075443972160170 | 12075443972337225 | 12075443972591303 | 12075443972638058 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7f921ff0c600 | 0x7f9114236600 | 131072 | 242826 | 31243960 | 12075443972665499 | 12075443972839942 | 12075443972975141 | 12075443972979092 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7f921ff0c500 | 0x7f9114236640 | 131072 | 248936 | 31858128 | 12075443973044213 | 12075443973202500 | 12075443973376579 | 12075443973380649 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7f921ff0c400 | 0x7f9114236680 | 131072 | 247466 | 31812280 | 12075443973450128 | 12075443973608738 | 12075443973741857 | 12075443973745787 |
| 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 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7f921ff0c300 | 0x7f91142366c0 | 131072 | 209294 | 26763928 | 12075443973804216 | 12075443973960576 | 12075443974220095 | 12075443974248091 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7f921ff0ca00 | 0x7f9114236700 | 65536 | 178186 | 22781360 | 12075443974288285 | 12075443974453373 | 12075443974704092 | 12075443974727442 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7f921ff0c900 | 0x7f9114236740 | 131072 | 228930 | 29435832 | 12075443974771674 | 12075443974932251 | 12075443975064570 | 12075443975068776 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7f921ff0c800 | 0x7f9114236780 | 131072 | 241714 | 31132504 | 12075443975128036 | 12075443975288889 | 12075443975472408 | 12075443975478668 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7f921ff0c700 | 0x7f91142367c0 | 131072 | 247134 | 31794288 | 12075443975549920 | 12075443975709846 | 12075443975850326 | 12075443975854276 |
| 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 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7f921ff0c600 | 0x7f9114236800 | 131072 | 239838 | 30633728 | 12075443975913205 | 12075443976073045 | 12075443976338163 | 12075443976362460 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7f921ff0c500 | 0x7f9114236840 | 65536 | 174788 | 22369432 | 12075443976405210 | 12075443976565042 | 12075443976823280 | 12075443976844526 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7f921ff0c400 | 0x7f9114236880 | 131072 | 245776 | 31547456 | 12075443976897244 | 12075443977060079 | 12075443977194478 | 12075443977198554 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7f921ff0c300 | 0x7f91142368c0 | 131072 | 266384 | 34057136 | 12075443977258235 | 12075443977421357 | 12075443977614636 | 12075443977636849 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7f921ff0ca00 | 0x7f9114236900 | 131072 | 248048 | 31691688 | 12075443977688875 | 12075443977848075 | 12075443977981834 | 12075443977985937 |
| 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 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7f921ff0c900 | 0x7f9114236940 | 131072 | 247612 | 31843272 | 12075443978045909 | 12075443978207913 | 12075443978492391 | 12075443978518948 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7f921ff0c800 | 0x7f9114236980 | 65536 | 190252 | 24375800 | 12075443978562329 | 12075443978723590 | 12075443978975749 | 12075443979000042 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7f921ff0c700 | 0x7f91142369c0 | 131072 | 243454 | 30928328 | 12075443979049494 | 12075443979214787 | 12075443979347107 | 12075443979350994 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7f921ff0c600 | 0x7f9114236a00 | 131072 | 256432 | 32729896 | 12075443979408371 | 12075443979569666 | 12075443979779744 | 12075443979802533 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7f921ff0c500 | 0x7f9114236a40 | 131072 | 244144 | 31165920 | 12075443979860882 | 12075443980029983 | 12075443980170142 | 12075443980174465 |
| 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 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7f921ff0c400 | 0x7f9114236a80 | 131072 | 249152 | 31775944 | 12075443980235187 | 12075443980396861 | 12075443980705339 | 12075443980728685 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7f921ff0c300 | 0x7f9114236ac0 | 65536 | 169524 | 21644736 | 12075443980771023 | 12075443980930298 | 12075443981185017 | 12075443981210961 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7f921ff0ca00 | 0x7f9114236b00 | 131072 | 245110 | 31345696 | 12075443981258870 | 12075443981430775 | 12075443981566455 | 12075443981570559 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7f921ff0c900 | 0x7f9114236b40 | 131072 | 246594 | 31418856 | 12075443981626934 | 12075443981783254 | 12075443982012532 | 12075443982036225 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7f921ff0c800 | 0x7f9114236b80 | 131072 | 247402 | 31550128 | 12075443982094623 | 12075443982262931 | 12075443982403090 | 12075443982407174 |
| 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 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7f921ff0c700 | 0x7f9114236bc0 | 131072 | 251520 | 32123152 | 12075443982465522 | 12075443982624209 | 12075443982955567 | 12075443982978265 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7f921ff0c600 | 0x7f9114236c00 | 65536 | 171546 | 21835256 | 12075443983027066 | 12075443983187406 | 12075443983435725 | 12075443983461864 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7f921ff0c500 | 0x7f9114236c40 | 131072 | 241832 | 30933408 | 12075443983503742 | 12075443983661963 | 12075443983802123 | 12075443983806314 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7f921ff0c400 | 0x7f9114236c80 | 131072 | 231484 | 29809224 | 12075443983863781 | 12075443984029161 | 12075443984273960 | 12075443984297287 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7f921ff0c300 | 0x7f9114236cc0 | 131072 | 265046 | 33678264 | 12075443984353000 | 12075443984519239 | 12075443984660358 | 12075443984664629 |
| 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 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7f921ff0ca00 | 0x7f9114236d00 | 131072 | 249188 | 31989408 | 12075443984722868 | 12075443984882382 | 12075443985258221 | 12075443985284792 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7f921ff0c900 | 0x7f9114236d40 | 65536 | 175468 | 22388640 | 12075443985325067 | 12075443985490059 | 12075443985746858 | 12075443985767739 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7f921ff0c800 | 0x7f9114236d80 | 131072 | 272680 | 34752168 | 12075443985811801 | 12075443985973737 | 12075443986111497 | 12075443986114414 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7f921ff0c700 | 0x7f9114236dc0 | 131072 | 250344 | 31803728 | 12075443986171951 | 12075443986335976 | 12075443986616135 | 12075443986638438 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7f921ff0c600 | 0x7f9114236e00 | 131072 | 246166 | 31322968 | 12075443986693911 | 12075443986856774 | 12075443986998374 | 12075443987005540 |
| 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 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7f921ff0c500 | 0x7f9114236e40 | 131072 | 248530 | 31797376 | 12075443987060241 | 12075443987222053 | 12075443987647011 | 12075443987669454 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7f921ff0c400 | 0x7f9114236e80 | 65536 | 183370 | 23458128 | 12075443987718164 | 12075443987880610 | 12075443988141410 | 12075443988163632 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7f921ff0c300 | 0x7f9114236ec0 | 131072 | 244314 | 31137936 | 12075443988205530 | 12075443988368289 | 12075443988508928 | 12075443988511539 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7f921ff0ca00 | 0x7f9114236f00 | 131072 | 242416 | 31204080 | 12075443988568414 | 12075443988728928 | 12075443989044606 | 12075443989067021 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7f921ff0c900 | 0x7f9114236f40 | 131072 | 246202 | 31668256 | 12075443989123105 | 12075443989290046 | 12075443989442045 | 12075443989444573 |
| 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 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7f921ff0c800 | 0x7f9114236f80 | 131072 | 260880 | 33395552 | 12075443989501529 | 12075443989659964 | 12075443990177242 | 12075443990199987 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7f921ff0c700 | 0x7f9114236fc0 | 65536 | 175422 | 22489360 | 12075443990249569 | 12075443990415962 | 12075443990715481 | 12075443990736774 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7f921ff0c600 | 0x7f9114237000 | 131072 | 250684 | 31899984 | 12075443990783581 | 12075443990951160 | 12075443991106039 | 12075443991108465 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7f921ff0c500 | 0x7f9114237040 | 131072 | 245156 | 31280440 | 12075443991166944 | 12075443991333398 | 12075443991718677 | 12075443991743766 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7f921ff0c400 | 0x7f9114237080 | 131072 | 249836 | 32237208 | 12075443991799399 | 12075443991965556 | 12075443992141716 | 12075443992144751 |
| 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 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7f921ff0c300 | 0x7f91142370c0 | 131072 | 246000 | 31511568 | 12075443992207447 | 12075443992372755 | 12075443992996273 | 12075443993019156 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7f921ff0ca00 | 0x7f9114237100 | 65536 | 168024 | 21614584 | 12075443993061404 | 12075443993226672 | 12075443993557551 | 12075443993578505 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7f921ff0c900 | 0x7f9114237140 | 131072 | 251632 | 32112368 | 12075443993622688 | 12075443993784270 | 12075443993963789 | 12075443993966216 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7f921ff0c800 | 0x7f9114237180 | 131072 | 252930 | 32199048 | 12075443994028271 | 12075443994189229 | 12075443994646027 | 12075443994670785 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7f921ff0c700 | 0x7f91142371c0 | 131072 | 243898 | 31179496 | 12075443994726028 | 12075443994892106 | 12075443995092105 | 12075443995117025 |
| 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 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7f921ff0c600 | 0x7f9114237200 | 131072 | 244850 | 31233944 | 12075443995160285 | 12075443995325865 | 12075443996030662 | 12075443996053505 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7f921ff0c500 | 0x7f9114237240 | 65536 | 171414 | 21990840 | 12075443996097938 | 12075443996261061 | 12075443996634820 | 12075443996656005 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7f921ff0c400 | 0x7f9114237280 | 131072 | 255346 | 32737768 | 12075443996698814 | 12075443996857539 | 12075443997061219 | 12075443997082337 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7f921ff0c300 | 0x7f91142372c0 | 131072 | 242284 | 30996696 | 12075443997125898 | 12075443997288738 | 12075443997815776 | 12075443997836459 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7f921ff0ca00 | 0x7f9114237300 | 131072 | 243842 | 31140280 | 12075443997893755 | 12075443998074975 | 12075443998299134 | 12075443998324936 |
| 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 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7f921ff0c900 | 0x7f9114237340 | 131072 | 243598 | 31084496 | 12075443998369329 | 12075443998535293 | 12075443999334811 | 12075443999357445 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7f921ff0c800 | 0x7f9114237380 | 65536 | 165866 | 21345240 | 12075443999400095 | 12075443999564090 | 12075443999984088 | 12075444000015037 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7f921ff0c700 | 0x7f91142373c0 | 131072 | 243344 | 31224176 | 12075444000054320 | 12075444000220248 | 12075444000447927 | 12075444000473509 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7f921ff0c600 | 0x7f9114237400 | 131072 | 245884 | 31522760 | 12075444000523032 | 12075444000689846 | 12075444001287284 | 12075444001310856 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7f921ff0c500 | 0x7f9114237440 | 131072 | 244892 | 31207576 | 12075444001364495 | 12075444001531443 | 12075444001800882 | 12075444001822757 |
| 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 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7f921ff0c400 | 0x7f9114237480 | 131072 | 243530 | 31240224 | 12075444001866628 | 12075444002038161 | 12075444003023598 | 12075444003084692 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7f921ff0c300 | 0x7f91142374c0 | 65536 | 168622 | 21718080 | 12075444003156035 | 12075444003619316 | 12075444004149554 | 12075444004199103 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7f921ff0ca00 | 0x7f9114237500 | 131072 | 246090 | 31525472 | 12075444004266258 | 12075444004502673 | 12075444004775472 | 12075444004824736 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7f921ff0c900 | 0x7f9114237540 | 131072 | 259426 | 33406648 | 12075444004888394 | 12075444005141230 | 12075444005880428 | 12075444005929309 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7f921ff0c800 | 0x7f9114237580 | 131072 | 225748 | 28671872 | 12075444006013826 | 12075444006250187 | 12075444006567465 | 12075444006615604 |
| 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 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7f921ff0c700 | 0x7f91142375c0 | 131072 | 256184 | 32906640 | 12075444006669464 | 12075444006906504 | 12075444008078500 | 12075444008126091 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7f921ff0c600 | 0x7f9114237600 | 65536 | 166628 | 21179832 | 12075444008188247 | 12075444008422819 | 12075444009032097 | 12075444009080114 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7f921ff0c500 | 0x7f9114237640 | 131072 | 245120 | 31201616 | 12075444009136760 | 12075444009379296 | 12075444009700415 | 12075444009748977 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7f921ff0c400 | 0x7f9114237680 | 131072 | 262950 | 33714536 | 12075444009802797 | 12075444010047613 | 12075444010926970 | 12075444010975206 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7f921ff0c300 | 0x7f91142376c0 | 131072 | 248488 | 32070992 | 12075444011060976 | 12075444011300569 | 12075444011711128 | 12075444011760185 |
| 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 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7f921ff0ca00 | 0x7f9114237700 | 131072 | 258048 | 32835632 | 12075444011822651 | 12075444012074966 | 12075444013623761 | 12075444013672910 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7f921ff0c900 | 0x7f9114237740 | 65536 | 181640 | 23420976 | 12075444013727161 | 12075444013966800 | 12075444014761997 | 12075444014810224 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7f921ff0c800 | 0x7f9114237780 | 131072 | 243634 | 31102328 | 12075444014872589 | 12075444015129036 | 12075444015543434 | 12075444015591716 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7f921ff0c700 | 0x7f91142377c0 | 131072 | 245996 | 31425200 | 12075444015644704 | 12075444015884073 | 12075444017042629 | 12075444017090722 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7f921ff0c600 | 0x7f9114237800 | 131072 | 260480 | 33442808 | 12075444017166312 | 12075444017406468 | 12075444018192065 | 12075444018241240 |
| 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 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7f921ff0c500 | 0x7f9114237840 | 131072 | 244126 | 31265712 | 12075444018297845 | 12075444018538624 | 12075444021586613 | 12075444021636300 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7f921ff0c400 | 0x7f9114237880 | 65536 | 189448 | 24214864 | 12075444021694057 | 12075444021935412 | 12075444023477167 | 12075444023525400 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7f921ff0c300 | 0x7f91142378c0 | 131072 | 257882 | 32906328 | 12075444023587977 | 12075444023827405 | 12075444024616683 | 12075444024665840 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7f921ff0ca00 | 0x7f9114237900 | 131072 | 242162 | 31047008 | 12075444024719620 | 12075444024968361 | 12075444027250434 | 12075444027300647 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7f921ff0c900 | 0x7f9114237940 | 131072 | 248252 | 31858480 | 12075444027377880 | 12075444027616192 | 12075444029151227 | 12075444029199876 |
| 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 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7f921ff0c800 | 0x7f9114237980 | 131072 | 252054 | 32173280 | 12075444029255940 | 12075444029492826 | 12075444035545765 | 12075444035624747 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7f921ff0c700 | 0x7f91142379c0 | 65536 | 164054 | 20976840 | 12075444035655373 | 12075444035978243 | 12075444039019513 | 12075444039096529 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7f921ff0c600 | 0x7f9114237a00 | 131072 | 255712 | 32753840 | 12075444039127496 | 12075444039445591 | 12075444040985266 | 12075444041034170 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 875394 | 875399 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7f921ff0c500 | 0x7f9114237a40 | 131072 | 260590 | 33457664 | 12075444041094792 | 12075444041329905 | 12075444045858209 | 12075444045907006 |