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 | 747744 | 747749 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7f064ba04180 | 4194304 | 3076172 | 393679528 | 12073196115389249 | 12073196360017531 | 12073196360339289 | 12073196360448031 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 747744 | 747749 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7f064ba35100 | 512 | 22348 | 2859312 | 12073196375206414 | 12073196375506653 | 12073196375512733 | 12073196375518183 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7f077bc5d900 | 0x7f064ba35140 | 65536 | 165008 | 21035712 | 12073196375582593 | 12073196375793532 | 12073196375922491 | 12073196375926542 |
| 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 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7f077bc5d800 | 0x7f064ba35180 | 65536 | 175142 | 22613256 | 12073196375998105 | 12073196376177210 | 12073196376428088 | 12073196376497393 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7f077bc5d700 | 0x7f064ba351c0 | 65536 | 191534 | 24562928 | 12073196376531356 | 12073196376719767 | 12073196376973846 | 12073196377042325 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7f077bc5d600 | 0x7f064ba35200 | 65536 | 180122 | 23067952 | 12073196377072241 | 12073196377257844 | 12073196377385844 | 12073196377389400 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7f077bc5d500 | 0x7f064ba35240 | 65536 | 193772 | 24699496 | 12073196377433833 | 12073196377611443 | 12073196377743122 | 12073196377746774 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7f077bc5d400 | 0x7f064ba35280 | 131072 | 248598 | 31943480 | 12073196377828336 | 12073196377992561 | 12073196378123760 | 12073196378127451 |
| 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 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7f077bc5d300 | 0x7f064ba352c0 | 131072 | 230300 | 29483152 | 12073196378178837 | 12073196378356399 | 12073196378613678 | 12073196378657116 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7f077bc5da00 | 0x7f064ba35300 | 65536 | 178674 | 22864408 | 12073196378686160 | 12073196378860236 | 12073196379113195 | 12073196379155101 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7f077bc5d900 | 0x7f064ba35340 | 131072 | 241260 | 30809088 | 12073196379180278 | 12073196379374474 | 12073196379505193 | 12073196379508988 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7f077bc5d800 | 0x7f064ba35380 | 131072 | 255956 | 32698000 | 12073196379561015 | 12073196379726152 | 12073196379864231 | 12073196379867685 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7f077bc5d700 | 0x7f064ba353c0 | 131072 | 243962 | 31189488 | 12073196379931073 | 12073196380101670 | 12073196380227430 | 12073196380231381 |
| 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 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7f077bc5d600 | 0x7f064ba35400 | 131072 | 215864 | 27565448 | 12073196380281504 | 12073196380445509 | 12073196380707747 | 12073196380774340 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7f077bc5d500 | 0x7f064ba35440 | 65536 | 174424 | 22249744 | 12073196380802843 | 12073196380976546 | 12073196381230145 | 12073196381297542 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7f077bc5d400 | 0x7f064ba35480 | 131072 | 247648 | 31832696 | 12073196381327267 | 12073196381504063 | 12073196381633183 | 12073196381636882 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7f077bc5d300 | 0x7f064ba354c0 | 131072 | 250708 | 32266520 | 12073196381686334 | 12073196381850462 | 12073196381982141 | 12073196381985821 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7f077bc5da00 | 0x7f064ba35500 | 131072 | 246994 | 31550816 | 12073196382050872 | 12073196382215260 | 12073196382348699 | 12073196382352512 |
| 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 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7f077bc5d900 | 0x7f064ba35540 | 131072 | 213000 | 27304736 | 12073196382405240 | 12073196382566618 | 12073196382827897 | 12073196382895120 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7f077bc5d800 | 0x7f064ba35580 | 65536 | 190290 | 24316600 | 12073196382920528 | 12073196383112215 | 12073196383366454 | 12073196383434362 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7f077bc5d700 | 0x7f064ba355c0 | 131072 | 235684 | 30582288 | 12073196383459639 | 12073196383640053 | 12073196383774292 | 12073196383778051 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7f077bc5d600 | 0x7f064ba35600 | 131072 | 249520 | 31779008 | 12073196383830759 | 12073196383989651 | 12073196384124530 | 12073196384128422 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7f077bc5d500 | 0x7f064ba35640 | 131072 | 239770 | 30551032 | 12073196384190417 | 12073196384353649 | 12073196384484689 | 12073196384488601 |
| 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 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7f077bc5d400 | 0x7f064ba35680 | 131072 | 221582 | 28201560 | 12073196384537472 | 12073196384699568 | 12073196384953006 | 12073196385022924 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7f077bc5d300 | 0x7f064ba356c0 | 65536 | 186726 | 24011264 | 12073196385054252 | 12073196385235245 | 12073196385493324 | 12073196385561254 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7f077bc5da00 | 0x7f064ba35700 | 131072 | 245836 | 31457656 | 12073196385589847 | 12073196385768042 | 12073196385900842 | 12073196385904672 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7f077bc5d900 | 0x7f064ba35740 | 131072 | 248930 | 31783120 | 12073196385953593 | 12073196386133640 | 12073196386271560 | 12073196386275411 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7f077bc5d800 | 0x7f064ba35780 | 131072 | 249282 | 31960296 | 12073196386338629 | 12073196386498919 | 12073196386630118 | 12073196386633657 |
| 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 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7f077bc5d700 | 0x7f064ba357c0 | 131072 | 193398 | 24758080 | 12073196386684481 | 12073196386856197 | 12073196387112036 | 12073196387180102 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7f077bc5d600 | 0x7f064ba35800 | 65536 | 177776 | 22748448 | 12073196387207373 | 12073196387384834 | 12073196387643233 | 12073196387709997 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7f077bc5d500 | 0x7f064ba35840 | 131072 | 242598 | 30748056 | 12073196387737408 | 12073196387911232 | 12073196388090911 | 12073196388094842 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7f077bc5d400 | 0x7f064ba35880 | 131072 | 249556 | 32109584 | 12073196388145636 | 12073196388309790 | 12073196388445949 | 12073196388449761 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7f077bc5d300 | 0x7f064ba358c0 | 131072 | 242518 | 30858816 | 12073196388511426 | 12073196388671068 | 12073196388802107 | 12073196388805693 |
| 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 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7f077bc5da00 | 0x7f064ba35900 | 131072 | 204750 | 26149280 | 12073196388855685 | 12073196389023066 | 12073196389285945 | 12073196389353941 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7f077bc5d900 | 0x7f064ba35940 | 65536 | 167086 | 21403592 | 12073196389383085 | 12073196389557944 | 12073196389814582 | 12073196389882013 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7f077bc5d800 | 0x7f064ba35980 | 131072 | 247748 | 31309000 | 12073196389908993 | 12073196390096181 | 12073196390228500 | 12073196390232504 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7f077bc5d700 | 0x7f064ba359c0 | 131072 | 243142 | 31228288 | 12073196390276556 | 12073196390447059 | 12073196390579378 | 12073196390583235 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7f077bc5d600 | 0x7f064ba35a00 | 131072 | 251000 | 32214528 | 12073196390644900 | 12073196390806577 | 12073196390938417 | 12073196390942072 |
| 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 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7f077bc5d500 | 0x7f064ba35a40 | 131072 | 198832 | 25509072 | 12073196390995371 | 12073196391163696 | 12073196391422574 | 12073196391491172 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7f077bc5d400 | 0x7f064ba35a80 | 65536 | 171676 | 21978608 | 12073196391517692 | 12073196391695853 | 12073196391946892 | 12073196391987875 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7f077bc5d300 | 0x7f064ba35ac0 | 131072 | 260670 | 33217232 | 12073196392016989 | 12073196392213450 | 12073196392344010 | 12073196392347894 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7f077bc5da00 | 0x7f064ba35b00 | 131072 | 255642 | 32573760 | 12073196392403197 | 12073196392568169 | 12073196392709288 | 12073196392713063 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7f077bc5d900 | 0x7f064ba35b40 | 131072 | 241666 | 30908968 | 12073196392777903 | 12073196392938087 | 12073196393067526 | 12073196393071639 |
| 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 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7f077bc5d800 | 0x7f064ba35b80 | 131072 | 206340 | 26250752 | 12073196393124397 | 12073196393285925 | 12073196393556004 | 12073196393622753 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7f077bc5d700 | 0x7f064ba35bc0 | 65536 | 168476 | 21557376 | 12073196393649583 | 12073196393831522 | 12073196394087841 | 12073196394157727 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7f077bc5d600 | 0x7f064ba35c00 | 131072 | 249356 | 31866728 | 12073196394186300 | 12073196394360960 | 12073196394493759 | 12073196394497599 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7f077bc5d500 | 0x7f064ba35c40 | 131072 | 244822 | 31422408 | 12073196394548373 | 12073196394716958 | 12073196394855997 | 12073196394859712 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7f077bc5d400 | 0x7f064ba35c80 | 131072 | 252116 | 32426760 | 12073196394921496 | 12073196395085916 | 12073196395221916 | 12073196395225972 |
| 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 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7f077bc5d300 | 0x7f064ba35cc0 | 131072 | 204578 | 26212512 | 12073196395275334 | 12073196395446554 | 12073196395708953 | 12073196395750587 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7f077bc5da00 | 0x7f064ba35d00 | 65536 | 185696 | 23734624 | 12073196395779160 | 12073196395953752 | 12073196396211351 | 12073196396280291 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7f077bc5d900 | 0x7f064ba35d40 | 131072 | 258562 | 33169368 | 12073196396307942 | 12073196396481429 | 12073196396616469 | 12073196396620613 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7f077bc5d800 | 0x7f064ba35d80 | 131072 | 275196 | 35186344 | 12073196396673031 | 12073196396832308 | 12073196396970547 | 12073196396974311 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7f077bc5d700 | 0x7f064ba35dc0 | 131072 | 250142 | 31956136 | 12073196397051254 | 12073196397212306 | 12073196397340785 | 12073196397344749 |
| 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 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7f077bc5d600 | 0x7f064ba35e00 | 131072 | 251522 | 32153864 | 12073196397397507 | 12073196397562704 | 12073196397828943 | 12073196397895743 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7f077bc5d500 | 0x7f064ba35e40 | 65536 | 168838 | 21671320 | 12073196397924005 | 12073196398110541 | 12073196398365100 | 12073196398433432 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7f077bc5d400 | 0x7f064ba35e80 | 131072 | 288950 | 37158712 | 12073196398458649 | 12073196398637739 | 12073196398777418 | 12073196398781338 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7f077bc5d300 | 0x7f064ba35ec0 | 131072 | 241194 | 31106232 | 12073196398834006 | 12073196398992137 | 12073196399131816 | 12073196399135667 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7f077bc5da00 | 0x7f064ba35f00 | 131072 | 244436 | 31290880 | 12073196399199555 | 12073196399360135 | 12073196399491494 | 12073196399495375 |
| 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 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7f077bc5d900 | 0x7f064ba35f40 | 131072 | 244466 | 31188288 | 12073196399543865 | 12073196399704933 | 12073196399976292 | 12073196400043433 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7f077bc5d800 | 0x7f064ba35f80 | 65536 | 166050 | 21329720 | 12073196400068901 | 12073196400247651 | 12073196400507169 | 12073196400574731 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7f077bc5d700 | 0x7f064ba35fc0 | 131072 | 253686 | 32434440 | 12073196400602632 | 12073196400774848 | 12073196400957087 | 12073196400960908 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7f077bc5d600 | 0x7f064ba36000 | 131072 | 242712 | 31277400 | 12073196401015750 | 12073196401179646 | 12073196401318525 | 12073196401322450 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7f077bc5d500 | 0x7f064ba36040 | 131072 | 256210 | 32674760 | 12073196401385707 | 12073196401544444 | 12073196401684284 | 12073196401688220 |
| 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 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7f077bc5d400 | 0x7f064ba36080 | 131072 | 235776 | 30141408 | 12073196401738934 | 12073196401903642 | 12073196402172281 | 12073196402224386 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7f077bc5d300 | 0x7f064ba360c0 | 65536 | 191458 | 24470704 | 12073196402251236 | 12073196402434040 | 12073196402689079 | 12073196402738251 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7f077bc5da00 | 0x7f064ba36100 | 131072 | 243008 | 30969456 | 12073196402764730 | 12073196402937717 | 12073196403070037 | 12073196403074085 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7f077bc5d900 | 0x7f064ba36140 | 131072 | 212952 | 27253592 | 12073196403125039 | 12073196403286676 | 12073196403430355 | 12073196403434144 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7f077bc5d800 | 0x7f064ba36180 | 131072 | 248896 | 31898312 | 12073196403496329 | 12073196403655154 | 12073196403788753 | 12073196403792469 |
| 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 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7f077bc5d700 | 0x7f064ba361c0 | 131072 | 215470 | 27528904 | 12073196403841360 | 12073196404009552 | 12073196404280591 | 12073196404329477 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7f077bc5d600 | 0x7f064ba36200 | 65536 | 172154 | 22006976 | 12073196404357650 | 12073196404533709 | 12073196404786508 | 12073196404835327 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7f077bc5d500 | 0x7f064ba36240 | 131072 | 248894 | 31978784 | 12073196404861897 | 12073196405042347 | 12073196405182826 | 12073196405186720 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7f077bc5d400 | 0x7f064ba36280 | 131072 | 222962 | 28398456 | 12073196405241071 | 12073196405398025 | 12073196405547784 | 12073196405551448 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7f077bc5d300 | 0x7f064ba362c0 | 131072 | 255696 | 32883232 | 12073196405632168 | 12073196405789703 | 12073196405919143 | 12073196405922958 |
| 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 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7f077bc5da00 | 0x7f064ba36300 | 131072 | 205754 | 26323088 | 12073196405972981 | 12073196406147622 | 12073196406413060 | 12073196406463963 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7f077bc5d900 | 0x7f064ba36340 | 65536 | 177230 | 22601600 | 12073196406490923 | 12073196406665539 | 12073196406920418 | 12073196406969202 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7f077bc5d800 | 0x7f064ba36380 | 131072 | 246266 | 31575104 | 12073196406995401 | 12073196407175616 | 12073196407314336 | 12073196407318291 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7f077bc5d700 | 0x7f064ba363c0 | 131072 | 256340 | 32865864 | 12073196407366741 | 12073196407534975 | 12073196407691614 | 12073196407695451 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7f077bc5d600 | 0x7f064ba36400 | 131072 | 268268 | 34248616 | 12073196407757276 | 12073196407915933 | 12073196408053052 | 12073196408057124 |
| 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 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7f077bc5d500 | 0x7f064ba36440 | 131072 | 214002 | 27432656 | 12073196408109811 | 12073196408291931 | 12073196408562970 | 12073196408609269 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7f077bc5d400 | 0x7f064ba36480 | 65536 | 184342 | 23605408 | 12073196408636590 | 12073196408807768 | 12073196409065847 | 12073196409115059 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7f077bc5d300 | 0x7f064ba364c0 | 131072 | 269070 | 34549528 | 12073196409139004 | 12073196409321526 | 12073196409456085 | 12073196409459980 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7f077bc5da00 | 0x7f064ba36500 | 131072 | 261106 | 33468968 | 12073196409510414 | 12073196409688404 | 12073196409855763 | 12073196409859693 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7f077bc5d900 | 0x7f064ba36540 | 131072 | 247422 | 31532040 | 12073196409921187 | 12073196410087122 | 12073196410219441 | 12073196410223128 |
| 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 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7f077bc5d800 | 0x7f064ba36580 | 131072 | 212876 | 27217992 | 12073196410275516 | 12073196410437840 | 12073196410705039 | 12073196410751750 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7f077bc5d700 | 0x7f064ba365c0 | 65536 | 175668 | 22579328 | 12073196410779392 | 12073196410954158 | 12073196411210956 | 12073196411259003 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7f077bc5d600 | 0x7f064ba36600 | 131072 | 249496 | 31740720 | 12073196411283909 | 12073196411466155 | 12073196411599755 | 12073196411603844 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7f077bc5d500 | 0x7f064ba36640 | 131072 | 243756 | 31282216 | 12073196411656862 | 12073196411811913 | 12073196411985673 | 12073196411989490 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7f077bc5d400 | 0x7f064ba36680 | 131072 | 260644 | 33601488 | 12073196412054211 | 12073196412217191 | 12073196412352231 | 12073196412356071 |
| 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 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7f077bc5d300 | 0x7f064ba366c0 | 131072 | 214448 | 27355360 | 12073196412404692 | 12073196412566150 | 12073196412828708 | 12073196412875827 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7f077bc5da00 | 0x7f064ba36700 | 65536 | 171468 | 21855240 | 12073196412899892 | 12073196413086627 | 12073196413337986 | 12073196413388540 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7f077bc5d900 | 0x7f064ba36740 | 131072 | 260366 | 33379320 | 12073196413412494 | 12073196413600705 | 12073196413743104 | 12073196413747086 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7f077bc5d800 | 0x7f064ba36780 | 131072 | 241142 | 30868256 | 12073196413798101 | 12073196413965823 | 12073196414149822 | 12073196414156266 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7f077bc5d700 | 0x7f064ba367c0 | 131072 | 238904 | 30684672 | 12073196414216919 | 12073196414376061 | 12073196414517660 | 12073196414521846 |
| 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 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7f077bc5d600 | 0x7f064ba36800 | 131072 | 239514 | 30772568 | 12073196414571087 | 12073196414736699 | 12073196415001978 | 12073196415051019 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7f077bc5d500 | 0x7f064ba36840 | 65536 | 170932 | 21994032 | 12073196415080864 | 12073196415258616 | 12073196415551895 | 12073196415598907 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7f077bc5d400 | 0x7f064ba36880 | 131072 | 244220 | 31231088 | 12073196415622200 | 12073196415799414 | 12073196415935093 | 12073196415939069 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7f077bc5d300 | 0x7f064ba368c0 | 131072 | 267520 | 34162768 | 12073196415991506 | 12073196416158932 | 12073196416350931 | 12073196416401498 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7f077bc5da00 | 0x7f064ba36900 | 131072 | 241098 | 30943592 | 12073196416441452 | 12073196416601810 | 12073196416743569 | 12073196416747812 |
| 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 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7f077bc5d900 | 0x7f064ba36940 | 131072 | 258068 | 32950808 | 12073196416794458 | 12073196416959568 | 12073196417243887 | 12073196417293486 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7f077bc5d800 | 0x7f064ba36980 | 65536 | 179264 | 22840328 | 12073196417319865 | 12073196417502765 | 12073196417762284 | 12073196417810196 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7f077bc5d700 | 0x7f064ba369c0 | 131072 | 248000 | 31667568 | 12073196417834020 | 12073196418010443 | 12073196418151562 | 12073196418155708 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7f077bc5d600 | 0x7f064ba36a00 | 131072 | 252064 | 32230824 | 12073196418211902 | 12073196418373801 | 12073196418583880 | 12073196418632694 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7f077bc5d500 | 0x7f064ba36a40 | 131072 | 258392 | 33020888 | 12073196418671145 | 12073196418829479 | 12073196418968998 | 12073196418973157 |
| 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 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7f077bc5d400 | 0x7f064ba36a80 | 131072 | 269500 | 34544760 | 12073196419031625 | 12073196419195077 | 12073196419532835 | 12073196419581647 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7f077bc5d300 | 0x7f064ba36ac0 | 65536 | 186720 | 23976336 | 12073196419604790 | 12073196419783554 | 12073196420043553 | 12073196420092867 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7f077bc5da00 | 0x7f064ba36b00 | 131072 | 269400 | 34374936 | 12073196420117763 | 12073196420296672 | 12073196420436991 | 12073196420440964 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7f077bc5d900 | 0x7f064ba36b40 | 131072 | 245862 | 31485824 | 12073196420489955 | 12073196420653950 | 12073196420881789 | 12073196420929061 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7f077bc5d800 | 0x7f064ba36b80 | 131072 | 242270 | 31036200 | 12073196420968043 | 12073196421133627 | 12073196421271867 | 12073196421276096 |
| 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 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7f077bc5d700 | 0x7f064ba36bc0 | 131072 | 249500 | 31962384 | 12073196421327541 | 12073196421494586 | 12073196421825784 | 12073196421873055 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7f077bc5d600 | 0x7f064ba36c00 | 65536 | 173506 | 22202456 | 12073196421900586 | 12073196422079063 | 12073196422328341 | 12073196422378724 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7f077bc5d500 | 0x7f064ba36c40 | 131072 | 269328 | 34390536 | 12073196422403601 | 12073196422581620 | 12073196422718100 | 12073196422722102 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7f077bc5d400 | 0x7f064ba36c80 | 131072 | 244602 | 31393720 | 12073196422771534 | 12073196422933207 | 12073196423178486 | 12073196423230046 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7f077bc5d300 | 0x7f064ba36cc0 | 131072 | 274518 | 35145424 | 12073196423267085 | 12073196423429364 | 12073196423570003 | 12073196423573294 |
| 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 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7f077bc5da00 | 0x7f064ba36d00 | 131072 | 264396 | 33711216 | 12073196423622095 | 12073196423786322 | 12073196424163761 | 12073196424213113 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7f077bc5d900 | 0x7f064ba36d40 | 65536 | 187456 | 23939704 | 12073196424237288 | 12073196424419439 | 12073196424688078 | 12073196424736085 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7f077bc5d800 | 0x7f064ba36d80 | 131072 | 244898 | 31294328 | 12073196424759448 | 12073196424937677 | 12073196425081037 | 12073196425084592 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7f077bc5d700 | 0x7f064ba36dc0 | 131072 | 249156 | 31985672 | 12073196425138663 | 12073196425298636 | 12073196425578794 | 12073196425626249 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7f077bc5d600 | 0x7f064ba36e00 | 131072 | 256480 | 32751552 | 12073196425663067 | 12073196425835273 | 12073196425973033 | 12073196425976489 |
| 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 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7f077bc5d500 | 0x7f064ba36e40 | 131072 | 251320 | 32128528 | 12073196426036160 | 12073196426210152 | 12073196426633830 | 12073196426682211 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7f077bc5d400 | 0x7f064ba36e80 | 65536 | 177698 | 22739456 | 12073196426711926 | 12073196426888549 | 12073196427154788 | 12073196427201926 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7f077bc5d300 | 0x7f064ba36ec0 | 131072 | 237586 | 30462568 | 12073196427228967 | 12073196427408067 | 12073196427546946 | 12073196427550374 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7f077bc5da00 | 0x7f064ba36f00 | 131072 | 261674 | 33305656 | 12073196427600778 | 12073196427767905 | 12073196428083904 | 12073196428134149 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7f077bc5d900 | 0x7f064ba36f40 | 131072 | 246076 | 31536760 | 12073196428181226 | 12073196428344703 | 12073196428497182 | 12073196428500690 |
| 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 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7f077bc5d800 | 0x7f064ba36f80 | 131072 | 246612 | 31610832 | 12073196428552776 | 12073196428712221 | 12073196429229659 | 12073196429277333 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7f077bc5d700 | 0x7f064ba36fc0 | 65536 | 173794 | 22123088 | 12073196429310705 | 12073196429484858 | 12073196429780057 | 12073196429828086 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7f077bc5d600 | 0x7f064ba37000 | 131072 | 241754 | 31079472 | 12073196429861979 | 12073196430029176 | 12073196430184855 | 12073196430188386 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7f077bc5d500 | 0x7f064ba37040 | 131072 | 242278 | 31079176 | 12073196430240542 | 12073196430420854 | 12073196430806452 | 12073196430828545 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7f077bc5d400 | 0x7f064ba37080 | 131072 | 249846 | 32174352 | 12073196430885050 | 12073196431050771 | 12073196431226930 | 12073196431230181 |
| 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 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7f077bc5d300 | 0x7f064ba370c0 | 131072 | 261676 | 33503480 | 12073196431282759 | 12073196431444850 | 12073196432054927 | 12073196432103424 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7f077bc5da00 | 0x7f064ba37100 | 65536 | 188128 | 24112792 | 12073196432132237 | 12073196432313486 | 12073196432644044 | 12073196432690986 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7f077bc5d900 | 0x7f064ba37140 | 131072 | 264078 | 33642288 | 12073196432718176 | 12073196432895883 | 12073196433075563 | 12073196433079327 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7f077bc5d800 | 0x7f064ba37180 | 131072 | 245938 | 31570800 | 12073196433130652 | 12073196433292682 | 12073196433749160 | 12073196433796209 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7f077bc5d700 | 0x7f064ba371c0 | 131072 | 269152 | 34587648 | 12073196433837526 | 12073196434000199 | 12073196434201158 | 12073196434249962 |
| 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 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7f077bc5d600 | 0x7f064ba37200 | 131072 | 262968 | 33554584 | 12073196434277273 | 12073196434455077 | 12073196435159394 | 12073196435206379 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7f077bc5d500 | 0x7f064ba37240 | 65536 | 181406 | 23205016 | 12073196435231206 | 12073196435424993 | 12073196435823071 | 12073196435869482 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7f077bc5d400 | 0x7f064ba37280 | 131072 | 264946 | 33881056 | 12073196435896712 | 12073196436084990 | 12073196436287709 | 12073196436337161 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7f077bc5d300 | 0x7f064ba372c0 | 131072 | 259974 | 33200280 | 12073196436368980 | 12073196436540188 | 12073196437066906 | 12073196437118582 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7f077bc5da00 | 0x7f064ba37300 | 131072 | 241456 | 30793376 | 12073196437163917 | 12073196437336344 | 12073196437560823 | 12073196437607621 |
| 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 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7f077bc5d900 | 0x7f064ba37340 | 131072 | 255486 | 32796112 | 12073196437633820 | 12073196437806262 | 12073196438605779 | 12073196438658123 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7f077bc5d800 | 0x7f064ba37380 | 65536 | 172656 | 22077600 | 12073196438686456 | 12073196438861618 | 12073196439283056 | 12073196439334710 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7f077bc5d700 | 0x7f064ba373c0 | 131072 | 263224 | 33763496 | 12073196439363133 | 12073196439538735 | 12073196439764814 | 12073196439812037 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7f077bc5d600 | 0x7f064ba37400 | 131072 | 243148 | 31293592 | 12073196439839578 | 12073196440013773 | 12073196440610731 | 12073196440659332 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7f077bc5d500 | 0x7f064ba37440 | 131072 | 239066 | 30750960 | 12073196440698975 | 12073196440859369 | 12073196441128648 | 12073196441179147 |
| 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 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7f077bc5d400 | 0x7f064ba37480 | 131072 | 252790 | 32090920 | 12073196441203643 | 12073196441386887 | 12073196442371843 | 12073196442440311 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7f077bc5d300 | 0x7f064ba374c0 | 65536 | 169784 | 21677448 | 12073196442472000 | 12073196442652002 | 12073196443166080 | 12073196443234106 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7f077bc5da00 | 0x7f064ba37500 | 131072 | 244472 | 31257784 | 12073196443266877 | 12073196443439998 | 12073196443712477 | 12073196443780351 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7f077bc5d900 | 0x7f064ba37540 | 131072 | 245156 | 31201376 | 12073196443811919 | 12073196443978876 | 12073196444717753 | 12073196444787793 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7f077bc5d800 | 0x7f064ba37580 | 131072 | 248900 | 31646824 | 12073196444831434 | 12073196444993432 | 12073196445309431 | 12073196445376316 |
| 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 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7f077bc5d700 | 0x7f064ba375c0 | 131072 | 268010 | 33952480 | 12073196445403897 | 12073196445583349 | 12073196446755184 | 12073196446824036 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7f077bc5d600 | 0x7f064ba37600 | 65536 | 189374 | 24191224 | 12073196446855625 | 12073196447040303 | 12073196447650381 | 12073196447719610 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7f077bc5d500 | 0x7f064ba37640 | 131072 | 241754 | 31123496 | 12073196447744126 | 12073196447928459 | 12073196448247338 | 12073196448317431 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7f077bc5d400 | 0x7f064ba37680 | 131072 | 244782 | 31327784 | 12073196448342708 | 12073196448522697 | 12073196449400773 | 12073196449468229 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7f077bc5d300 | 0x7f064ba376c0 | 131072 | 245232 | 31275400 | 12073196449505559 | 12073196449673732 | 12073196450083650 | 12073196450152651 |
| 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 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7f077bc5da00 | 0x7f064ba37700 | 131072 | 269176 | 34582192 | 12073196450183158 | 12073196450359809 | 12073196451908922 | 12073196451977341 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7f077bc5d900 | 0x7f064ba37740 | 65536 | 162572 | 20805656 | 12073196452016384 | 12073196452188761 | 12073196452983798 | 12073196453054433 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7f077bc5d800 | 0x7f064ba37780 | 131072 | 252188 | 32176952 | 12073196453085350 | 12073196453257077 | 12073196453671635 | 12073196453738664 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7f077bc5d700 | 0x7f064ba377c0 | 131072 | 246014 | 31166968 | 12073196453765514 | 12073196453936754 | 12073196455096109 | 12073196455165275 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7f077bc5d600 | 0x7f064ba37800 | 131072 | 251024 | 32048120 | 12073196455210910 | 12073196455375468 | 12073196456162504 | 12073196456230194 |
| 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 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7f077bc5d500 | 0x7f064ba37840 | 131072 | 246998 | 31789112 | 12073196456262454 | 12073196456438823 | 12073196459489850 | 12073196459558388 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7f077bc5d400 | 0x7f064ba37880 | 65536 | 162156 | 20835104 | 12073196459592030 | 12073196459762649 | 12073196461305522 | 12073196461374112 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7f077bc5d300 | 0x7f064ba378c0 | 131072 | 264716 | 33409400 | 12073196461407263 | 12073196461581361 | 12073196462371758 | 12073196462439351 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7f077bc5da00 | 0x7f064ba37900 | 131072 | 234644 | 29749928 | 12073196462473083 | 12073196462650957 | 12073196464932707 | 12073196465004327 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7f077bc5d900 | 0x7f064ba37940 | 131072 | 231100 | 29618920 | 12073196465046956 | 12073196465206306 | 12073196466740859 | 12073196466808850 |
| 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 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7f077bc5d800 | 0x7f064ba37980 | 131072 | 243182 | 30996056 | 12073196466840789 | 12073196467024698 | 12073196473082112 | 12073196473151896 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7f077bc5d700 | 0x7f064ba379c0 | 65536 | 170332 | 21845920 | 12073196473184456 | 12073196473362591 | 12073196476405298 | 12073196476476884 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7f077bc5d600 | 0x7f064ba37a00 | 131072 | 253358 | 32551224 | 12073196476505227 | 12073196476686897 | 12073196478226410 | 12073196478294341 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 747744 | 747749 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7f077bc5d500 | 0x7f064ba37a40 | 131072 | 228898 | 29539256 | 12073196478327022 | 12073196478498729 | 12073196483026870 | 12073196483098017 |