46 KiB
46 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | GRBM_COUNT | GRBM_GUI_ACTIVE | SQ_WAVES | SQ_IFETCH | SQ_IFETCH_LEVEL | SQ_ACCUM_PREV_HIRES | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBuffer.kd | 0 | 0 | 0 | 746327 | 746332 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7f3319204180 | 500953 | 500953 | 524288 | 6291456 | 792994 | 101695980 | 12073172382107123 | 12073172629300944 | 12073172629623022 | 12073172629738095 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 746327 | 746332 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7f3319235100 | 27081 | 27081 | 512 | 8192 | 9933 | 1272264 | 12073172644318466 | 12073172644642895 | 12073172644648815 | 12073172644657947 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7f3424d9e900 | 0x7f3319235140 | 215542 | 215542 | 65536 | 917504 | 141630 | 18080276 | 12073172644714753 | 12073172644951053 | 12073172645082253 | 12073172645086052 |
| 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 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7f3424d9e800 | 0x7f3319235180 | 390302 | 390302 | 65536 | 1245184 | 181281 | 23162200 | 12073172645155652 | 12073172645348651 | 12073172645597290 | 12073172645670969 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7f3424d9e700 | 0x7f33192351c0 | 389990 | 389990 | 65536 | 983040 | 136016 | 17443688 | 12073172645708780 | 12073172645897768 | 12073172646146086 | 12073172646220611 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7f3424d9e600 | 0x7f3319235200 | 214678 | 214678 | 65536 | 1048576 | 160891 | 20591816 | 12073172646253842 | 12073172646445925 | 12073172646577764 | 12073172646580890 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7f3424d9e500 | 0x7f3319235240 | 220806 | 220806 | 65536 | 983040 | 149191 | 19138968 | 12073172646627236 | 12073172646816643 | 12073172646951522 | 12073172646954945 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7f3424d9e400 | 0x7f3319235280 | 206830 | 206830 | 65536 | 1048576 | 146333 | 18771048 | 12073172647037388 | 12073172647215360 | 12073172647342080 | 12073172647345050 |
| 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 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7f3424d9e300 | 0x7f33192352c0 | 392142 | 392142 | 65536 | 1572864 | 229067 | 29328684 | 12073172647397658 | 12073172647582878 | 12073172647832637 | 12073172647878591 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7f3424d9ea00 | 0x7f3319235300 | 397254 | 397254 | 65536 | 1179648 | 157835 | 20269052 | 12073172647903387 | 12073172648124315 | 12073172648378074 | 12073172648422372 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7f3424d9e900 | 0x7f3319235340 | 214790 | 214790 | 65536 | 1114112 | 159359 | 20444908 | 12073172648457527 | 12073172648638232 | 12073172648769271 | 12073172648772442 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7f3424d9e800 | 0x7f3319235380 | 212774 | 212774 | 65536 | 1114112 | 156361 | 20022216 | 12073172648824339 | 12073172649008950 | 12073172649138069 | 12073172649141528 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7f3424d9e700 | 0x7f33192353c0 | 209086 | 209086 | 65536 | 1179648 | 166393 | 21333648 | 12073172649213542 | 12073172649389108 | 12073172649516787 | 12073172649519881 |
| 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 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7f3424d9e600 | 0x7f3319235400 | 399198 | 399198 | 65536 | 1835008 | 256039 | 32797620 | 12073172649576927 | 12073172649749906 | 12073172650004944 | 12073172650077136 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7f3424d9e500 | 0x7f3319235440 | 391470 | 391470 | 65536 | 1310720 | 179171 | 22862844 | 12073172650106801 | 12073172650306543 | 12073172650555981 | 12073172650626627 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7f3424d9e400 | 0x7f3319235480 | 210318 | 210318 | 65536 | 1245184 | 177391 | 22728612 | 12073172650659138 | 12073172650843020 | 12073172650971979 | 12073172650975015 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7f3424d9e300 | 0x7f33192354c0 | 219766 | 219766 | 65536 | 1310720 | 183632 | 23458652 | 12073172651033724 | 12073172651219817 | 12073172651354697 | 12073172651357706 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7f3424d9ea00 | 0x7f3319235500 | 212910 | 212910 | 65536 | 1310720 | 182901 | 23347736 | 12073172651422887 | 12073172651596295 | 12073172651726695 | 12073172651730058 |
| 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 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7f3424d9e900 | 0x7f3319235540 | 391326 | 391326 | 65536 | 2097152 | 296253 | 37898484 | 12073172651777596 | 12073172651963493 | 12073172652213412 | 12073172652286131 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7f3424d9e800 | 0x7f3319235580 | 392334 | 392334 | 65536 | 1441792 | 198890 | 25458836 | 12073172652312310 | 12073172652504610 | 12073172652755329 | 12073172652825874 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7f3424d9e700 | 0x7f33192355c0 | 215270 | 215270 | 65536 | 1376256 | 190768 | 24361664 | 12073172652844949 | 12073172653046367 | 12073172653177726 | 12073172653181294 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7f3424d9e600 | 0x7f3319235600 | 210622 | 210622 | 65536 | 1507328 | 210870 | 26957900 | 12073172653227330 | 12073172653414365 | 12073172653543644 | 12073172653547134 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7f3424d9e500 | 0x7f3319235640 | 212854 | 212854 | 65536 | 1441792 | 207220 | 26617924 | 12073172653611353 | 12073172653785883 | 12073172653915962 | 12073172653919125 |
| 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 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7f3424d9e400 | 0x7f3319235680 | 401422 | 401422 | 65536 | 2359296 | 321632 | 41197652 | 12073172653962506 | 12073172654159801 | 12073172654417559 | 12073172654491008 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7f3424d9e300 | 0x7f33192356c0 | 399854 | 399854 | 65536 | 1572864 | 211625 | 27001776 | 12073172654515453 | 12073172654709717 | 12073172654965076 | 12073172655038235 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7f3424d9ea00 | 0x7f3319235700 | 213334 | 213334 | 65536 | 1507328 | 209108 | 26684256 | 12073172655062339 | 12073172655260434 | 12073172655391794 | 12073172655394877 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7f3424d9e900 | 0x7f3319235740 | 212054 | 212054 | 65536 | 1703936 | 239148 | 30474748 | 12073172655438348 | 12073172655628752 | 12073172655758671 | 12073172655761769 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7f3424d9e800 | 0x7f3319235780 | 209878 | 209878 | 65536 | 1572864 | 228670 | 29275928 | 12073172655825868 | 12073172655998670 | 12073172656126989 | 12073172656130043 |
| 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 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7f3424d9e700 | 0x7f33192357c0 | 393646 | 393646 | 65536 | 2621440 | 356007 | 45538576 | 12073172656182040 | 12073172656366828 | 12073172656618826 | 12073172656690525 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7f3424d9e600 | 0x7f3319235800 | 391886 | 391886 | 65536 | 1703936 | 231017 | 29575444 | 12073172656714319 | 12073172656906665 | 12073172657157703 | 12073172657231520 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7f3424d9e500 | 0x7f3319235840 | 212910 | 212910 | 65536 | 1638400 | 231667 | 29745200 | 12073172657257939 | 12073172657453702 | 12073172657583621 | 12073172657586800 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7f3424d9e400 | 0x7f3319235880 | 211214 | 211214 | 65536 | 1900544 | 272981 | 34859264 | 12073172657632275 | 12073172657817700 | 12073172657947779 | 12073172657950947 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7f3424d9e300 | 0x7f33192358c0 | 215934 | 215934 | 65536 | 1703936 | 240845 | 30878256 | 12073172658020215 | 12073172658196417 | 12073172658328097 | 12073172658331384 |
| 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 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7f3424d9ea00 | 0x7f3319235900 | 390662 | 390662 | 65536 | 2883584 | 384843 | 49320436 | 12073172658383210 | 12073172658572255 | 12073172658823134 | 12073172658893979 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7f3424d9e900 | 0x7f3319235940 | 392270 | 392270 | 65536 | 1835008 | 249017 | 31774032 | 12073172658917703 | 12073172659115612 | 12073172659366331 | 12073172659437389 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7f3424d9e800 | 0x7f3319235980 | 208278 | 208278 | 65536 | 1769472 | 266968 | 34165916 | 12073172659467014 | 12073172659661209 | 12073172659788728 | 12073172659791827 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7f3424d9e700 | 0x7f33192359c0 | 209454 | 209454 | 65536 | 2097152 | 298753 | 38180872 | 12073172659837853 | 12073172660032407 | 12073172660160886 | 12073172660164460 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7f3424d9e600 | 0x7f3319235a00 | 207398 | 207398 | 65536 | 1835008 | 245600 | 31435424 | 12073172660229490 | 12073172660404245 | 12073172660531604 | 12073172660534918 |
| 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 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7f3424d9e500 | 0x7f3319235a40 | 396150 | 396150 | 65536 | 3145728 | 427977 | 54708052 | 12073172660587466 | 12073172660770483 | 12073172661024721 | 12073172661097674 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7f3424d9e400 | 0x7f3319235a80 | 398590 | 398590 | 65536 | 1966080 | 261559 | 33426856 | 12073172661115988 | 12073172661317040 | 12073172661573038 | 12073172661643408 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7f3424d9e300 | 0x7f3319235ac0 | 216398 | 216398 | 65536 | 1900544 | 262661 | 33531792 | 12073172661664076 | 12073172661871596 | 12073172662002316 | 12073172662005851 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7f3424d9ea00 | 0x7f3319235b00 | 215382 | 215382 | 65536 | 2293760 | 308776 | 39655500 | 12073172662065863 | 12073172662246314 | 12073172662379433 | 12073172662382882 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7f3424d9e900 | 0x7f3319235b40 | 208406 | 208406 | 65536 | 1966080 | 286333 | 36614080 | 12073172662446971 | 12073172662621032 | 12073172662748391 | 12073172662751737 |
| 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 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7f3424d9e800 | 0x7f3319235b80 | 406238 | 406238 | 65536 | 3407872 | 458752 | 58871604 | 12073172662802171 | 12073172662995910 | 12073172663257828 | 12073172663329641 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7f3424d9e700 | 0x7f3319235bc0 | 396382 | 396382 | 65536 | 2097152 | 281174 | 35884548 | 12073172663357823 | 12073172663549507 | 12073172663803425 | 12073172663847102 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7f3424d9e600 | 0x7f3319235c00 | 204038 | 204038 | 65536 | 2031616 | 280506 | 35956720 | 12073172663871317 | 12073172664074624 | 12073172664200223 | 12073172664203755 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7f3424d9e500 | 0x7f3319235c40 | 220054 | 220054 | 65536 | 2490368 | 350446 | 44975664 | 12073172664253567 | 12073172664446462 | 12073172664582301 | 12073172664585344 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7f3424d9e400 | 0x7f3319235c80 | 210606 | 210606 | 65536 | 2097152 | 286543 | 36630384 | 12073172664648181 | 12073172664822779 | 12073172664952539 | 12073172664955772 |
| 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 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7f3424d9e300 | 0x7f3319235cc0 | 407814 | 407814 | 65536 | 3670016 | 485928 | 62219908 | 12073172665013690 | 12073172665202777 | 12073172665465016 | 12073172665537313 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7f3424d9ea00 | 0x7f3319235d00 | 391094 | 391094 | 65536 | 2228224 | 310423 | 39715132 | 12073172665561378 | 12073172665754134 | 12073172666005653 | 12073172666076745 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7f3424d9e900 | 0x7f3319235d40 | 209718 | 209718 | 65536 | 2162688 | 300552 | 38462616 | 12073172666104617 | 12073172666301331 | 12073172666429810 | 12073172666433177 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7f3424d9e800 | 0x7f3319235d80 | 224206 | 224206 | 65536 | 2686976 | 412737 | 53087548 | 12073172666485154 | 12073172666667729 | 12073172666806768 | 12073172666809928 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7f3424d9e700 | 0x7f3319235dc0 | 215598 | 215598 | 65536 | 2228224 | 306005 | 39150428 | 12073172666874558 | 12073172667054767 | 12073172667187246 | 12073172667190655 |
| 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 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7f3424d9e600 | 0x7f3319235e00 | 408422 | 408422 | 65536 | 3932160 | 566646 | 72543060 | 12073172667245908 | 12073172667425645 | 12073172667689163 | 12073172667760774 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7f3424d9e500 | 0x7f3319235e40 | 395750 | 395750 | 65536 | 2359296 | 316462 | 40551900 | 12073172667785450 | 12073172667976361 | 12073172668229800 | 12073172668275310 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7f3424d9e400 | 0x7f3319235e80 | 209966 | 209966 | 65536 | 2293760 | 318575 | 40743500 | 12073172668301659 | 12073172668490278 | 12073172668619238 | 12073172668622666 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7f3424d9e300 | 0x7f3319235ec0 | 227086 | 227086 | 65536 | 2883584 | 448948 | 57477512 | 12073172668674863 | 12073172668858436 | 12073172668999396 | 12073172669005938 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7f3424d9ea00 | 0x7f3319235f00 | 212990 | 212990 | 65536 | 2359296 | 349686 | 44735480 | 12073172669067062 | 12073172669240034 | 12073172669371233 | 12073172669374833 |
| 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 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7f3424d9e900 | 0x7f3319235f40 | 408214 | 408214 | 65536 | 4194304 | 556712 | 71155656 | 12073172669421250 | 12073172669606912 | 12073172669870271 | 12073172669940995 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7f3424d9e800 | 0x7f3319235f80 | 393830 | 393830 | 65536 | 2490368 | 332713 | 42521260 | 12073172669965230 | 12073172670161469 | 12073172670413307 | 12073172670486439 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7f3424d9e700 | 0x7f3319235fc0 | 214774 | 214774 | 65536 | 2424832 | 342778 | 43773200 | 12073172670512117 | 12073172670703066 | 12073172670834745 | 12073172670838162 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7f3424d9e600 | 0x7f3319236000 | 221182 | 221182 | 65536 | 3080192 | 455435 | 58082292 | 12073172670883166 | 12073172671076664 | 12073172671214423 | 12073172671218048 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7f3424d9e500 | 0x7f3319236040 | 215126 | 215126 | 65536 | 2490368 | 381342 | 48877564 | 12073172671284422 | 12073172671457781 | 12073172671589781 | 12073172671593075 |
| 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 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7f3424d9e400 | 0x7f3319236080 | 406870 | 406870 | 65536 | 4456448 | 597772 | 76573604 | 12073172671636285 | 12073172671825619 | 12073172672088818 | 12073172672160910 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7f3424d9e300 | 0x7f33192360c0 | 394342 | 394342 | 65536 | 2621440 | 345765 | 44261564 | 12073172672187339 | 12073172672382096 | 12073172672635215 | 12073172672680516 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7f3424d9ea00 | 0x7f3319236100 | 212118 | 212118 | 65536 | 2555904 | 386260 | 49472184 | 12073172672704119 | 12073172672894253 | 12073172673025133 | 12073172673029003 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7f3424d9e900 | 0x7f3319236140 | 232294 | 232294 | 65536 | 3276800 | 498962 | 63840284 | 12073172673074898 | 12073172673263051 | 12073172673407210 | 12073172673410402 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7f3424d9e800 | 0x7f3319236180 | 217222 | 217222 | 65536 | 2621440 | 371727 | 47606196 | 12073172673475242 | 12073172673646889 | 12073172673781128 | 12073172673784517 |
| 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 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7f3424d9e700 | 0x7f33192361c0 | 406494 | 406494 | 65536 | 4718592 | 691614 | 88532692 | 12073172673829300 | 12073172674012807 | 12073172674275525 | 12073172674349026 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7f3424d9e600 | 0x7f3319236200 | 388054 | 388054 | 65536 | 2752512 | 364529 | 46742924 | 12073172674374673 | 12073172674566244 | 12073172674816802 | 12073172674887226 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7f3424d9e500 | 0x7f3319236240 | 214934 | 214934 | 65536 | 2686976 | 416318 | 53297068 | 12073172674914056 | 12073172675124960 | 12073172675257120 | 12073172675260780 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7f3424d9e400 | 0x7f3319236280 | 241278 | 241278 | 65536 | 3473408 | 529509 | 68003104 | 12073172675307867 | 12073172675490878 | 12073172675641758 | 12073172675645194 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7f3424d9e300 | 0x7f33192362c0 | 211502 | 211502 | 65536 | 2752512 | 414498 | 53038628 | 12073172675726265 | 12073172675897276 | 12073172676026875 | 12073172676031071 |
| 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 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7f3424d9ea00 | 0x7f3319236300 | 410342 | 410342 | 65536 | 4980736 | 650608 | 83413496 | 12073172676076726 | 12073172676263834 | 12073172676529752 | 12073172676601982 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7f3424d9e900 | 0x7f3319236340 | 385358 | 385358 | 65536 | 2883584 | 388815 | 49699896 | 12073172676625937 | 12073172676815511 | 12073172677063509 | 12073172677109305 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7f3424d9e800 | 0x7f3319236380 | 209926 | 209926 | 65536 | 2818048 | 393142 | 50335180 | 12073172677137006 | 12073172677322548 | 12073172677451987 | 12073172677455428 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7f3424d9e700 | 0x7f33192363c0 | 252550 | 252550 | 65536 | 3670016 | 578527 | 74112956 | 12073172677507595 | 12073172677687346 | 12073172677844945 | 12073172677848268 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7f3424d9e600 | 0x7f3319236400 | 211046 | 211046 | 65536 | 2883584 | 429570 | 54950724 | 12073172677910554 | 12073172678090703 | 12073172678220943 | 12073172678224767 |
| 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 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7f3424d9e500 | 0x7f3319236440 | 403774 | 403774 | 65536 | 5177344 | 696382 | 89089376 | 12073172678267898 | 12073172678459181 | 12073172678720460 | 12073172678771994 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7f3424d9e400 | 0x7f3319236480 | 387774 | 387774 | 65536 | 3014656 | 406211 | 51918072 | 12073172678795568 | 12073172678984138 | 12073172679234857 | 12073172679292501 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7f3424d9e300 | 0x7f33192364c0 | 209814 | 209814 | 65536 | 2949120 | 408120 | 52270684 | 12073172679312569 | 12073172679514375 | 12073172679643015 | 12073172679646429 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7f3424d9ea00 | 0x7f3319236500 | 263566 | 263566 | 65536 | 3866624 | 573413 | 73336208 | 12073172679697774 | 12073172679879653 | 12073172680045732 | 12073172680049568 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7f3424d9e900 | 0x7f3319236540 | 217846 | 217846 | 65536 | 3014656 | 412220 | 52725960 | 12073172680115050 | 12073172680289251 | 12073172680423490 | 12073172680426959 |
| 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 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7f3424d9e800 | 0x7f3319236580 | 402454 | 402454 | 65536 | 5439488 | 731445 | 93318640 | 12073172680476912 | 12073172680658049 | 12073172680919007 | 12073172680944761 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7f3424d9e700 | 0x7f33192365c0 | 394246 | 394246 | 65536 | 3145728 | 426557 | 54531112 | 12073172680984124 | 12073172681161726 | 12073172681415964 | 12073172681468635 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7f3424d9e600 | 0x7f3319236600 | 215174 | 215174 | 65536 | 3080192 | 429495 | 55039492 | 12073172681493411 | 12073172681682043 | 12073172681814522 | 12073172681818024 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7f3424d9e500 | 0x7f3319236640 | 276254 | 276254 | 65536 | 4063232 | 574373 | 73822604 | 12073172681861555 | 12073172682054521 | 12073172682228280 | 12073172682232183 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7f3424d9e400 | 0x7f3319236680 | 212014 | 212014 | 65536 | 3145728 | 440229 | 56425032 | 12073172682296433 | 12073172682467638 | 12073172682598998 | 12073172682602331 |
| 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 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7f3424d9e300 | 0x7f33192366c0 | 403110 | 403110 | 65536 | 5701632 | 750186 | 95794276 | 12073172682649349 | 12073172682833076 | 12073172683093715 | 12073172683147344 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7f3424d9ea00 | 0x7f3319236700 | 395350 | 395350 | 65536 | 3276800 | 427325 | 54652220 | 12073172683173312 | 12073172683365713 | 12073172683621712 | 12073172683674283 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7f3424d9e900 | 0x7f3319236740 | 214238 | 214238 | 65536 | 3211264 | 466195 | 59685400 | 12073172683700902 | 12073172683887790 | 12073172684020110 | 12073172684023812 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7f3424d9e800 | 0x7f3319236780 | 288422 | 288422 | 65536 | 4259840 | 602440 | 77346056 | 12073172684073314 | 12073172684254028 | 12073172684436907 | 12073172684440587 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7f3424d9e700 | 0x7f33192367c0 | 216582 | 216582 | 65536 | 3276800 | 477399 | 61149096 | 12073172684503885 | 12073172684675626 | 12073172684808905 | 12073172684812187 |
| 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 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7f3424d9e600 | 0x7f3319236800 | 409558 | 409558 | 65536 | 7733248 | 981903 | 125480404 | 12073172684863172 | 12073172685048904 | 12073172685314342 | 12073172685366938 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7f3424d9e500 | 0x7f3319236840 | 446982 | 446982 | 65536 | 3407872 | 450752 | 57759948 | 12073172685394850 | 12073172685581381 | 12073172685870979 | 12073172685922320 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7f3424d9e400 | 0x7f3319236880 | 220014 | 220014 | 65536 | 3342336 | 490303 | 62780508 | 12073172685948679 | 12073172686151937 | 12073172686287297 | 12073172686290644 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7f3424d9e300 | 0x7f33192368c0 | 304846 | 304846 | 65536 | 4456448 | 641338 | 82202900 | 12073172686333895 | 12073172686529215 | 12073172686721054 | 12073172686772981 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7f3424d9ea00 | 0x7f3319236900 | 223350 | 223350 | 65536 | 3538944 | 575922 | 73676932 | 12073172686812224 | 12073172686985853 | 12073172687124092 | 12073172687127840 |
| 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 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7f3424d9e900 | 0x7f3319236940 | 434542 | 434542 | 65536 | 8978432 | 1129684 | 144622268 | 12073172687174467 | 12073172687361050 | 12073172687644089 | 12073172687696036 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7f3424d9e800 | 0x7f3319236980 | 390990 | 390990 | 65536 | 3670016 | 482585 | 61590680 | 12073172687720551 | 12073172687908727 | 12073172688160886 | 12073172688214399 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7f3424d9e700 | 0x7f33192369c0 | 217150 | 217150 | 65536 | 3604480 | 489614 | 62655836 | 12073172688239075 | 12073172688428084 | 12073172688562643 | 12073172688566032 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7f3424d9e600 | 0x7f3319236a00 | 383230 | 383230 | 65536 | 4849664 | 710245 | 90613032 | 12073172688617658 | 12073172688800722 | 12073172689046161 | 12073172689072032 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7f3424d9e500 | 0x7f3319236a40 | 223422 | 223422 | 65536 | 3801088 | 577709 | 73905428 | 12073172689134829 | 12073172689309999 | 12073172689447918 | 12073172689451347 |
| 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 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7f3424d9e400 | 0x7f3319236a80 | 471518 | 471518 | 65536 | 14548992 | 1828753 | 234002740 | 12073172689501731 | 12073172689690317 | 12073172689998795 | 12073172690051482 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7f3424d9e300 | 0x7f3319236ac0 | 393454 | 393454 | 65536 | 3932160 | 548172 | 70323176 | 12073172690080506 | 12073172690269514 | 12073172690523752 | 12073172690574534 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7f3424d9ea00 | 0x7f3319236b00 | 214310 | 214310 | 65536 | 3866624 | 562509 | 71997948 | 12073172690602015 | 12073172690787431 | 12073172690920550 | 12073172690923924 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7f3424d9e900 | 0x7f3319236b40 | 356422 | 356422 | 65536 | 5242880 | 767469 | 98298132 | 12073172690976131 | 12073172691162789 | 12073172691390147 | 12073172691444711 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7f3424d9e800 | 0x7f3319236b80 | 225926 | 225926 | 65536 | 4063232 | 594806 | 76083388 | 12073172691481550 | 12073172691653346 | 12073172691792545 | 12073172691796064 |
| 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 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7f3424d9e700 | 0x7f3319236bc0 | 504422 | 504422 | 65536 | 10027008 | 1263670 | 161552532 | 12073172691850024 | 12073172692039093 | 12073172692368852 | 12073172692424943 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7f3424d9e600 | 0x7f3319236c00 | 386446 | 386446 | 65536 | 4194304 | 615213 | 78792340 | 12073172692447114 | 12073172692641169 | 12073172692891568 | 12073172692941492 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7f3424d9e500 | 0x7f3319236c40 | 225870 | 225870 | 65536 | 4128768 | 617832 | 78999132 | 12073172692965226 | 12073172693162127 | 12073172693302766 | 12073172693306190 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7f3424d9e400 | 0x7f3319236c80 | 382262 | 382262 | 65536 | 5636096 | 794831 | 101595116 | 12073172693355542 | 12073172693540685 | 12073172693786284 | 12073172693834762 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7f3424d9e300 | 0x7f3319236cc0 | 219846 | 219846 | 65536 | 4587520 | 689043 | 88174120 | 12073172693876790 | 12073172694056843 | 12073172694193322 | 12073172694196074 |
| 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 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7f3424d9ea00 | 0x7f3319236d00 | 576246 | 576246 | 65536 | 11075584 | 1392195 | 178287072 | 12073172694239544 | 12073172694431561 | 12073172694810439 | 12073172694860198 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7f3424d9e900 | 0x7f3319236d40 | 405566 | 405566 | 65536 | 4718592 | 669938 | 85610044 | 12073172694884473 | 12073172695076518 | 12073172695339557 | 12073172695392186 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7f3424d9e800 | 0x7f3319236d80 | 225382 | 225382 | 65536 | 4653056 | 693799 | 88774176 | 12073172695418575 | 12073172695608035 | 12073172695748515 | 12073172695751133 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7f3424d9e700 | 0x7f3319236dc0 | 433766 | 433766 | 65536 | 6422528 | 898973 | 115237248 | 12073172695801126 | 12073172695982754 | 12073172696262432 | 12073172696313057 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7f3424d9e600 | 0x7f3319236e00 | 220182 | 220182 | 65536 | 5111808 | 751778 | 96212732 | 12073172696349845 | 12073172696522591 | 12073172696660510 | 12073172696662967 |
| 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 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7f3424d9e500 | 0x7f3319236e40 | 646030 | 646030 | 65536 | 15007744 | 1884909 | 241388788 | 12073172696706338 | 12073172696894909 | 12073172697319547 | 12073172697369029 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7f3424d9e400 | 0x7f3319236e80 | 400758 | 400758 | 65536 | 5242880 | 739300 | 94726284 | 12073172697394667 | 12073172697588986 | 12073172697849625 | 12073172697872184 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7f3424d9e300 | 0x7f3319236ec0 | 225566 | 225566 | 65536 | 5177344 | 780128 | 99800340 | 12073172697923119 | 12073172698103064 | 12073172698243223 | 12073172698246069 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7f3424d9ea00 | 0x7f3319236f00 | 487062 | 487062 | 65536 | 7208960 | 1054366 | 135141700 | 12073172698296943 | 12073172698477622 | 12073172698792980 | 12073172698843479 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7f3424d9e900 | 0x7f3319236f40 | 243526 | 243526 | 65536 | 6160384 | 925387 | 118415896 | 12073172698880187 | 12073172699058259 | 12073172699210258 | 12073172699213236 |
| 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 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7f3424d9e800 | 0x7f3319236f80 | 783214 | 783214 | 65536 | 17104896 | 2146076 | 274684848 | 12073172699256727 | 12073172699447057 | 12073172699963855 | 12073172700019805 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7f3424d9e700 | 0x7f3319236fc0 | 457750 | 457750 | 65536 | 6291456 | 852834 | 109203960 | 12073172700045322 | 12073172700238733 | 12073172700536972 | 12073172700586508 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7f3424d9e600 | 0x7f3319237000 | 245718 | 245718 | 65536 | 6225920 | 923531 | 118163252 | 12073172700612095 | 12073172700802411 | 12073172700956970 | 12073172700959541 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7f3424d9e500 | 0x7f3319237040 | 593334 | 593334 | 65536 | 8781824 | 1259393 | 161533208 | 12073172701017589 | 12073172701204489 | 12073172701589927 | 12073172701640897 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7f3424d9e400 | 0x7f3319237080 | 276758 | 276758 | 65536 | 7208960 | 1049608 | 134275880 | 12073172701682734 | 12073172701857766 | 12073172702033925 | 12073172702036963 |
| 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 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7f3424d9e300 | 0x7f33192370c0 | 925566 | 925566 | 65536 | 19202048 | 2396816 | 308166788 | 12073172702080353 | 12073172702272324 | 12073172702882721 | 12073172702906358 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7f3424d9ea00 | 0x7f3319237100 | 497734 | 497734 | 65536 | 7340032 | 1046488 | 133984752 | 12073172702960018 | 12073172703144960 | 12073172703471518 | 12073172703524046 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7f3424d9e900 | 0x7f3319237140 | 283054 | 283054 | 65536 | 7274496 | 1055794 | 135198900 | 12073172703555955 | 12073172703747517 | 12073172703926556 | 12073172703929128 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7f3424d9e800 | 0x7f3319237180 | 698126 | 698126 | 65536 | 10354688 | 1538817 | 197094864 | 12073172703972028 | 12073172704173595 | 12073172704630393 | 12073172704680925 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7f3424d9e700 | 0x7f33192371c0 | 311574 | 311574 | 65536 | 8257536 | 1168636 | 149521252 | 12073172704721891 | 12073172704893751 | 12073172705092150 | 12073172705143375 |
| 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 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7f3424d9e600 | 0x7f3319237200 | 1074222 | 1074222 | 65536 | 21299200 | 2668730 | 341672264 | 12073172705174442 | 12073172705360629 | 12073172706070546 | 12073172706121272 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7f3424d9e500 | 0x7f3319237240 | 566982 | 566982 | 65536 | 8388608 | 1204715 | 154089704 | 12073172706150316 | 12073172706344784 | 12073172706717423 | 12073172706766480 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7f3424d9e400 | 0x7f3319237280 | 317966 | 317966 | 65536 | 8323072 | 1281376 | 164094368 | 12073172706791046 | 12073172706989421 | 12073172707193260 | 12073172707245370 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7f3424d9e300 | 0x7f33192372c0 | 803062 | 803062 | 65536 | 11927552 | 1696803 | 215641192 | 12073172707269866 | 12073172707463979 | 12073172707989897 | 12073172708059353 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7f3424d9ea00 | 0x7f3319237300 | 348358 | 348358 | 65536 | 9306112 | 1389026 | 177704868 | 12073172708097203 | 12073172708270855 | 12073172708494854 | 12073172708562678 |
| 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 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7f3424d9e900 | 0x7f3319237340 | 1205830 | 1205830 | 65536 | 29163520 | 3652968 | 467549120 | 12073172708588546 | 12073172708777093 | 12073172709575329 | 12073172709645420 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7f3424d9e800 | 0x7f3319237380 | 637726 | 637726 | 65536 | 9437184 | 1304386 | 166908288 | 12073172709676918 | 12073172709867968 | 12073172710289406 | 12073172710359857 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7f3424d9e700 | 0x7f33192373c0 | 404622 | 404622 | 65536 | 9371648 | 1408615 | 180301756 | 12073172710384353 | 12073172710584604 | 12073172710845243 | 12073172710914047 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7f3424d9e600 | 0x7f3319237400 | 909966 | 909966 | 65536 | 13500416 | 1929963 | 245148220 | 12073172710940246 | 12073172711136762 | 12073172711733559 | 12073172711804171 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7f3424d9e500 | 0x7f3319237440 | 417926 | 417926 | 65536 | 11403264 | 1795910 | 229950384 | 12073172711842001 | 12073172712029077 | 12073172712299316 | 12073172712368990 |
| 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 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7f3424d9e400 | 0x7f3319237480 | 1486766 | 1486766 | 65536 | 33357824 | 4176506 | 534608232 | 12073172712393997 | 12073172712587315 | 12073172713572270 | 12073172713642427 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7f3424d9e300 | 0x7f33192374c0 | 776062 | 776062 | 65536 | 11534336 | 1594799 | 203341144 | 12073172713675177 | 12073172713867309 | 12073172714381866 | 12073172714453474 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7f3424d9ea00 | 0x7f3319237500 | 422006 | 422006 | 65536 | 11534336 | 1787419 | 228666988 | 12073172714480013 | 12073172714677705 | 12073172714949224 | 12073172715020938 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7f3424d9e900 | 0x7f3319237540 | 1124142 | 1124142 | 65536 | 19267584 | 2423058 | 310314532 | 12073172715044702 | 12073172715235302 | 12073172715973219 | 12073172716042747 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7f3424d9e800 | 0x7f3319237580 | 488238 | 488238 | 65536 | 13500416 | 2049133 | 262214736 | 12073172716079996 | 12073172716253537 | 12073172716569536 | 12073172716638524 |
| 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 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7f3424d9e700 | 0x7f33192375c0 | 1767174 | 1767174 | 65536 | 37552128 | 4694230 | 601624340 | 12073172716661977 | 12073172716850335 | 12073172718022489 | 12073172718094058 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7f3424d9e600 | 0x7f3319237600 | 914710 | 914710 | 65536 | 13631488 | 1858971 | 236797596 | 12073172718125797 | 12073172718313208 | 12073172718919925 | 12073172718988841 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7f3424d9e500 | 0x7f3319237640 | 491918 | 491918 | 65536 | 13631488 | 2110370 | 270155396 | 12073172719020870 | 12073172719219923 | 12073172719539762 | 12073172719609213 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7f3424d9e400 | 0x7f3319237680 | 1338566 | 1338566 | 65536 | 21692416 | 2741272 | 350654184 | 12073172719636785 | 12073172719826640 | 12073172720704876 | 12073172720775490 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7f3424d9e300 | 0x7f33192376c0 | 629670 | 629670 | 65536 | 17694720 | 2722568 | 348426444 | 12073172720812700 | 12073172720985035 | 12073172721396873 | 12073172721467296 |
| 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 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7f3424d9ea00 | 0x7f3319237700 | 2332542 | 2332542 | 65536 | 57475072 | 7191361 | 920857240 | 12073172721493204 | 12073172721690792 | 12073172723241664 | 12073172723311974 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7f3424d9e900 | 0x7f3319237740 | 1198262 | 1198262 | 65536 | 19660800 | 2475241 | 316551280 | 12073172723344143 | 12073172723537343 | 12073172724333339 | 12073172724403101 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7f3424d9e800 | 0x7f3319237780 | 676286 | 676286 | 65536 | 20381696 | 2569686 | 328674976 | 12073172724436483 | 12073172724622618 | 12073172725060696 | 12073172725130633 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7f3424d9e700 | 0x7f33192377c0 | 1759278 | 1759278 | 65536 | 28704768 | 3618719 | 463391804 | 12073172725162983 | 12073172725354134 | 12073172726514449 | 12073172726584765 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7f3424d9e600 | 0x7f3319237800 | 1197622 | 1197622 | 65536 | 36634624 | 4633441 | 593088396 | 12073172726631181 | 12073172726805807 | 12073172727591884 | 12073172727662116 |
| 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 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7f3424d9e500 | 0x7f3319237840 | 4584822 | 4584822 | 65536 | 105840640 | 13240913 | 1694924396 | 12073172727687323 | 12073172727882442 | 12073172730938268 | 12073172731023352 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7f3424d9e400 | 0x7f3319237880 | 2322526 | 2322526 | 65536 | 38535168 | 4832856 | 618878016 | 12073172731097891 | 12073172731274746 | 12073172732818259 | 12073172732888518 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7f3424d9e300 | 0x7f33192378c0 | 1202286 | 1202286 | 65536 | 39124992 | 4913462 | 628802328 | 12073172732912412 | 12073172733114577 | 12073172733904014 | 12073172733976259 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7f3424d9ea00 | 0x7f3319237900 | 3442422 | 3442422 | 65536 | 55771136 | 6993800 | 895489680 | 12073172734011334 | 12073172734205292 | 12073172736487361 | 12073172736557916 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7f3424d9e900 | 0x7f3319237940 | 2323526 | 2323526 | 65536 | 72548352 | 9115941 | 1166471016 | 12073172736606546 | 12073172736786240 | 12073172738322073 | 12073172738393817 |
| 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 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7f3424d9e800 | 0x7f3319237980 | 9086662 | 9086662 | 65536 | 210698240 | 26347725 | 3372664772 | 12073172738424684 | 12073172738619191 | 12073172744674683 | 12073172744746060 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7f3424d9e700 | 0x7f33192379c0 | 4572798 | 4572798 | 65536 | 76283904 | 9550857 | 1222289128 | 12073172744776547 | 12073172744970041 | 12073172748014987 | 12073172748090504 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7f3424d9e600 | 0x7f3319237a00 | 2327462 | 2327462 | 65536 | 77398016 | 9704699 | 1242583788 | 12073172748120680 | 12073172748319145 | 12073172749858658 | 12073172749929592 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 746327 | 746332 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7f3424d9e500 | 0x7f3319237a40 | 6812214 | 6812214 | 65536 | 110821376 | 13885191 | 1777121260 | 12073172749961501 | 12073172750160577 | 12073172754687915 | 12073172754763263 |