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 | 885650 | 885655 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7f3db2804180 | 4194304 | 3150786 | 403220608 | 12075643646573035 | 12075643891053217 | 12075643891374335 | 12075643891492447 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 885650 | 885655 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7f3db2835100 | 512 | 21880 | 2779208 | 12075643906340522 | 12075643906646578 | 12075643906653138 | 12075643906665255 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7f3ebe4d9900 | 0x7f3db2835140 | 65536 | 196232 | 25070520 | 12075643906724375 | 12075643906937777 | 12075643907077616 | 12075643907082491 |
| 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 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7f3ebe4d9800 | 0x7f3db2835180 | 65536 | 151298 | 19387376 | 12075643907149044 | 12075643907320975 | 12075643907577293 | 12075643907646779 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7f3ebe4d9700 | 0x7f3db28351c0 | 65536 | 195854 | 25112400 | 12075643907680732 | 12075643907870092 | 12075643908127371 | 12075643908197372 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7f3ebe4d9600 | 0x7f3db2835200 | 65536 | 172596 | 22044576 | 12075643908217700 | 12075643908406569 | 12075643908540489 | 12075643908544267 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7f3ebe4d9500 | 0x7f3db2835240 | 65536 | 175438 | 22345048 | 12075643908593859 | 12075643908764008 | 12075643908897927 | 12075643908901922 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7f3ebe4d9400 | 0x7f3db2835280 | 131072 | 243992 | 31243232 | 12075643908981981 | 12075643909151046 | 12075643909279045 | 12075643909282569 |
| 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 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7f3ebe4d9300 | 0x7f3db28352c0 | 131072 | 216866 | 27802432 | 12075643909332733 | 12075643909505124 | 12075643909757923 | 12075643909799430 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7f3ebe4d9a00 | 0x7f3db2835300 | 65536 | 171770 | 21950240 | 12075643909826751 | 12075643910001921 | 12075643910255840 | 12075643910297105 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7f3ebe4d9900 | 0x7f3db2835340 | 131072 | 243914 | 31207328 | 12075643910321811 | 12075643910521759 | 12075643910654718 | 12075643910658246 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7f3ebe4d9800 | 0x7f3db2835380 | 131072 | 242996 | 31042640 | 12075643910708139 | 12075643910877917 | 12075643911016796 | 12075643911021361 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7f3ebe4d9700 | 0x7f3db28353c0 | 131072 | 247128 | 31574488 | 12075643911089217 | 12075643911256475 | 12075643911387515 | 12075643911391709 |
| 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 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7f3ebe4d9600 | 0x7f3db2835400 | 131072 | 201206 | 25676432 | 12075643911442183 | 12075643911603513 | 12075643911865752 | 12075643911932785 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7f3ebe4d9500 | 0x7f3db2835440 | 65536 | 177162 | 22531584 | 12075643911966157 | 12075643912149751 | 12075643912409589 | 12075643912476826 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7f3ebe4d9400 | 0x7f3db2835480 | 131072 | 237312 | 30461288 | 12075643912502984 | 12075643912688948 | 12075643912819987 | 12075643912824141 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7f3ebe4d9300 | 0x7f3db28354c0 | 131072 | 252736 | 32598696 | 12075643912872611 | 12075643913046866 | 12075643913182706 | 12075643913186525 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7f3ebe4d9a00 | 0x7f3db2835500 | 131072 | 240228 | 30856232 | 12075643913249902 | 12075643913417264 | 12075643913546864 | 12075643913550872 |
| 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 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7f3ebe4d9900 | 0x7f3db2835540 | 131072 | 220462 | 28224664 | 12075643913599462 | 12075643913769103 | 12075643914026541 | 12075643914093270 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7f3ebe4d9800 | 0x7f3db2835580 | 65536 | 171500 | 21947736 | 12075643914122234 | 12075643914311820 | 12075643914567019 | 12075643914634145 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7f3ebe4d9700 | 0x7f3db28355c0 | 131072 | 269324 | 34367376 | 12075643914661947 | 12075643914846057 | 12075643915022376 | 12075643915027135 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7f3ebe4d9600 | 0x7f3db2835600 | 131072 | 265770 | 34063800 | 12075643915085784 | 12075643915251175 | 12075643915382215 | 12075643915386082 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7f3ebe4d9500 | 0x7f3db2835640 | 131072 | 244584 | 31329448 | 12075643915448438 | 12075643915613573 | 12075643915747813 | 12075643915751782 |
| 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 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7f3ebe4d9400 | 0x7f3db2835680 | 131072 | 210026 | 26832424 | 12075643915799350 | 12075643915969732 | 12075643916229410 | 12075643916296855 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7f3ebe4d9300 | 0x7f3db28356c0 | 65536 | 167390 | 21416176 | 12075643916323374 | 12075643916504129 | 12075643916759488 | 12075643916826439 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7f3ebe4d9a00 | 0x7f3db2835700 | 131072 | 272056 | 34648680 | 12075643916851456 | 12075643917039966 | 12075643917173566 | 12075643917177552 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7f3ebe4d9900 | 0x7f3db2835740 | 131072 | 249226 | 31842376 | 12075643917227775 | 12075643917395005 | 12075643917531964 | 12075643917535727 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7f3ebe4d9800 | 0x7f3db2835780 | 131072 | 248186 | 31803872 | 12075643917596891 | 12075643917760123 | 12075643917895962 | 12075643917899884 |
| 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 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7f3ebe4d9700 | 0x7f3db28357c0 | 131072 | 200170 | 25634432 | 12075643917947683 | 12075643918127801 | 12075643918386200 | 12075643918428256 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7f3ebe4d9600 | 0x7f3db2835800 | 65536 | 172588 | 22048320 | 12075643918456699 | 12075643918632118 | 12075643918889237 | 12075643918956498 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7f3ebe4d9500 | 0x7f3db2835840 | 131072 | 241310 | 30731584 | 12075643918985772 | 12075643919165076 | 12075643919294995 | 12075643919299415 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7f3ebe4d9400 | 0x7f3db2835880 | 131072 | 251282 | 32163192 | 12075643919352023 | 12075643919513714 | 12075643919654033 | 12075643919658052 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7f3ebe4d9300 | 0x7f3db28358c0 | 131072 | 238908 | 30686736 | 12075643919719536 | 12075643919887632 | 12075643920018512 | 12075643920022329 |
| 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 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7f3ebe4d9a00 | 0x7f3db2835900 | 131072 | 204718 | 26237936 | 12075643920071430 | 12075643920244590 | 12075643920502189 | 12075643920569065 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7f3ebe4d9900 | 0x7f3db2835940 | 65536 | 175866 | 22532816 | 12075643920592057 | 12075643920772908 | 12075643921026667 | 12075643921094541 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7f3ebe4d9800 | 0x7f3db2835980 | 131072 | 250646 | 32069208 | 12075643921119137 | 12075643921309545 | 12075643921439785 | 12075643921443901 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7f3ebe4d9700 | 0x7f3db28359c0 | 131072 | 241330 | 30794048 | 12075643921491920 | 12075643921661063 | 12075643921796583 | 12075643921800543 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7f3ebe4d9600 | 0x7f3db2835a00 | 131072 | 256302 | 32769528 | 12075643921862609 | 12075643922032742 | 12075643922166341 | 12075643922170451 |
| 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 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7f3ebe4d9500 | 0x7f3db2835a40 | 131072 | 200300 | 25513288 | 12075643922218610 | 12075643922393540 | 12075643922649218 | 12075643922715394 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7f3ebe4d9400 | 0x7f3db2835a80 | 65536 | 186888 | 23940336 | 12075643922739258 | 12075643922922337 | 12075643923177856 | 12075643923247502 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7f3ebe4d9300 | 0x7f3db2835ac0 | 131072 | 240220 | 30779072 | 12075643923273431 | 12075643923463134 | 12075643923593534 | 12075643923597303 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7f3ebe4d9a00 | 0x7f3db2835b00 | 131072 | 264812 | 33989864 | 12075643923644821 | 12075643923814653 | 12075643923951292 | 12075643923954907 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7f3ebe4d9900 | 0x7f3db2835b40 | 131072 | 240546 | 30896040 | 12075643924020239 | 12075643924184251 | 12075643924318170 | 12075643924322110 |
| 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 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7f3ebe4d9800 | 0x7f3db2835b80 | 131072 | 204356 | 26121600 | 12075643924371321 | 12075643924544409 | 12075643924813848 | 12075643924880848 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7f3ebe4d9700 | 0x7f3db2835bc0 | 65536 | 165192 | 21182536 | 12075643924908439 | 12075643925089846 | 12075643925342805 | 12075643925411624 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7f3ebe4d9600 | 0x7f3db2835c00 | 131072 | 251504 | 32155944 | 12075643925440869 | 12075643925616244 | 12075643925745043 | 12075643925749001 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7f3ebe4d9500 | 0x7f3db2835c40 | 131072 | 240894 | 30756856 | 12075643925798814 | 12075643925973522 | 12075643926116881 | 12075643926121323 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7f3ebe4d9400 | 0x7f3db2835c80 | 131072 | 255060 | 32617088 | 12075643926183058 | 12075643926349520 | 12075643926482319 | 12075643926486863 |
| 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 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7f3ebe4d9300 | 0x7f3db2835cc0 | 131072 | 209364 | 26699112 | 12075643926533740 | 12075643926702958 | 12075643926974637 | 12075643927043377 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7f3ebe4d9a00 | 0x7f3db2835d00 | 65536 | 174936 | 22504448 | 12075643927072501 | 12075643927250476 | 12075643927500234 | 12075643927567982 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7f3ebe4d9900 | 0x7f3db2835d40 | 131072 | 243786 | 31178744 | 12075643927591175 | 12075643927769033 | 12075643927897672 | 12075643927901532 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7f3ebe4d9800 | 0x7f3db2835d80 | 131072 | 250462 | 31952640 | 12075643927951194 | 12075643928122471 | 12075643928264871 | 12075643928269225 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7f3ebe4d9700 | 0x7f3db2835dc0 | 131072 | 241430 | 31043576 | 12075643928329858 | 12075643928494469 | 12075643928629349 | 12075643928633242 |
| 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 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7f3ebe4d9600 | 0x7f3db2835e00 | 131072 | 250884 | 32232632 | 12075643928682163 | 12075643928847428 | 12075643929119906 | 12075643929188033 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7f3ebe4d9500 | 0x7f3db2835e40 | 65536 | 159390 | 20438144 | 12075643929212298 | 12075643929393985 | 12075643929648384 | 12075643929714401 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7f3ebe4d9400 | 0x7f3db2835e80 | 131072 | 244196 | 31144960 | 12075643929738866 | 12075643929920382 | 12075643930051262 | 12075643930055575 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7f3ebe4d9300 | 0x7f3db2835ec0 | 131072 | 240172 | 30882760 | 12075643930101611 | 12075643930277021 | 12075643930415580 | 12075643930419682 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7f3ebe4d9a00 | 0x7f3db2835f00 | 131072 | 249898 | 31915816 | 12075643930483270 | 12075643930645979 | 12075643930776378 | 12075643930780552 |
| 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 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7f3ebe4d9900 | 0x7f3db2835f40 | 131072 | 241518 | 30820224 | 12075643930827500 | 12075643930992697 | 12075643931262616 | 12075643931331065 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7f3ebe4d9800 | 0x7f3db2835f80 | 65536 | 175508 | 22504144 | 12075643931355531 | 12075643931533814 | 12075643931793333 | 12075643931860630 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7f3ebe4d9700 | 0x7f3db2835fc0 | 131072 | 257056 | 32879344 | 12075643931888401 | 12075643932065172 | 12075643932197971 | 12075643932201984 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7f3ebe4d9600 | 0x7f3db2836000 | 131072 | 246166 | 31332712 | 12075643932251666 | 12075643932416370 | 12075643932555889 | 12075643932560140 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7f3ebe4d9500 | 0x7f3db2836040 | 131072 | 243736 | 31144480 | 12075643932621093 | 12075643932780368 | 12075643932912527 | 12075643932916692 |
| 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 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7f3ebe4d9400 | 0x7f3db2836080 | 131072 | 218610 | 27899976 | 12075643932964341 | 12075643933141966 | 12075643933411085 | 12075643933460994 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7f3ebe4d9300 | 0x7f3db28360c0 | 65536 | 165992 | 21274160 | 12075643933483616 | 12075643933667884 | 12075643933926602 | 12075643933948600 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7f3ebe4d9a00 | 0x7f3db2836100 | 131072 | 241568 | 30979864 | 12075643933991400 | 12075643934156681 | 12075643934291561 | 12075643934295785 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7f3ebe4d9900 | 0x7f3db2836140 | 131072 | 202640 | 25801560 | 12075643934343504 | 12075643934513479 | 12075643934661159 | 12075643934665172 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7f3ebe4d9800 | 0x7f3db2836180 | 131072 | 254810 | 32638760 | 12075643934726325 | 12075643934884518 | 12075643935019557 | 12075643935023668 |
| 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 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7f3ebe4d9700 | 0x7f3db28361c0 | 131072 | 201038 | 25676792 | 12075643935072348 | 12075643935242276 | 12075643935511395 | 12075643935559424 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7f3ebe4d9600 | 0x7f3db2836200 | 65536 | 186662 | 23833120 | 12075643935585753 | 12075643935761153 | 12075643936023232 | 12075643936049975 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7f3ebe4d9500 | 0x7f3db2836240 | 131072 | 242352 | 30815456 | 12075643936093416 | 12075643936256031 | 12075643936390910 | 12075643936395007 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7f3ebe4d9400 | 0x7f3db2836280 | 131072 | 203380 | 26273384 | 12075643936442926 | 12075643936610909 | 12075643936763068 | 12075643936767258 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7f3ebe4d9300 | 0x7f3db28362c0 | 131072 | 240904 | 30752280 | 12075643936845704 | 12075643937003867 | 12075643937137466 | 12075643937141724 |
| 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 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7f3ebe4d9a00 | 0x7f3db2836300 | 131072 | 206476 | 26461648 | 12075643937190595 | 12075643937363065 | 12075643937636024 | 12075643937685886 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7f3ebe4d9900 | 0x7f3db2836340 | 65536 | 166432 | 21220736 | 12075643937709189 | 12075643937887703 | 12075643938140661 | 12075643938192307 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7f3ebe4d9800 | 0x7f3db2836380 | 131072 | 246698 | 31581248 | 12075643938219547 | 12075643938397940 | 12075643938534099 | 12075643938538210 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7f3ebe4d9700 | 0x7f3db28363c0 | 131072 | 239876 | 30792440 | 12075643938586069 | 12075643938752658 | 12075643938911858 | 12075643938915651 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7f3ebe4d9600 | 0x7f3db2836400 | 131072 | 271736 | 34640800 | 12075643938977696 | 12075643939142896 | 12075643939280176 | 12075643939284406 |
| 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 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7f3ebe4d9500 | 0x7f3db2836440 | 131072 | 199558 | 25500352 | 12075643939331073 | 12075643939501135 | 12075643939768813 | 12075643939792971 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7f3ebe4d9400 | 0x7f3db2836480 | 65536 | 172130 | 22008720 | 12075643939839328 | 12075643940014892 | 12075643940276011 | 12075643940323968 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7f3ebe4d9300 | 0x7f3db28364c0 | 131072 | 239270 | 30863264 | 12075643940348434 | 12075643940538089 | 12075643940671849 | 12075643940676133 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7f3ebe4d9a00 | 0x7f3db2836500 | 131072 | 238582 | 30594496 | 12075643940724723 | 12075643940904968 | 12075643941109127 | 12075643941158740 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7f3ebe4d9900 | 0x7f3db2836540 | 131072 | 246086 | 31654552 | 12075643941196129 | 12075643941370405 | 12075643941498565 | 12075643941502669 |
| 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 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7f3ebe4d9800 | 0x7f3db2836580 | 131072 | 197124 | 25273904 | 12075643941545889 | 12075643941726884 | 12075643941989282 | 12075643942017816 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7f3ebe4d9700 | 0x7f3db28365c0 | 65536 | 172620 | 22084056 | 12075643942059243 | 12075643942229761 | 12075643942487360 | 12075643942535148 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7f3ebe4d9600 | 0x7f3db2836600 | 131072 | 255636 | 32658176 | 12075643942559733 | 12075643942745439 | 12075643942881598 | 12075643942886200 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7f3ebe4d9500 | 0x7f3db2836640 | 131072 | 267936 | 34218016 | 12075643942935742 | 12075643943117917 | 12075643943292476 | 12075643943296913 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7f3ebe4d9400 | 0x7f3db2836680 | 131072 | 240532 | 30739688 | 12075643943360211 | 12075643943525595 | 12075643943660314 | 12075643943664406 |
| 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 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7f3ebe4d9300 | 0x7f3db28366c0 | 131072 | 210748 | 26851248 | 12075643943712736 | 12075643943889273 | 12075643944152472 | 12075643944200803 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7f3ebe4d9a00 | 0x7f3db2836700 | 65536 | 162830 | 20776136 | 12075643944221171 | 12075643944413110 | 12075643944677269 | 12075643944723785 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7f3ebe4d9900 | 0x7f3db2836740 | 131072 | 242806 | 31031640 | 12075643944749182 | 12075643944939668 | 12075643945078707 | 12075643945083223 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7f3ebe4d9800 | 0x7f3db2836780 | 131072 | 242188 | 30886656 | 12075643945122837 | 12075643945310866 | 12075643945493425 | 12075643945497653 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7f3ebe4d9700 | 0x7f3db28367c0 | 131072 | 242758 | 31196104 | 12075643945558657 | 12075643945723824 | 12075643945867183 | 12075643945871418 |
| 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 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7f3ebe4d9600 | 0x7f3db2836800 | 131072 | 242554 | 31062128 | 12075643945910801 | 12075643946099022 | 12075643946365581 | 12075643946413475 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7f3ebe4d9500 | 0x7f3db2836840 | 65536 | 185230 | 23650512 | 12075643946441097 | 12075643946623819 | 12075643946887498 | 12075643946936217 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7f3ebe4d9400 | 0x7f3db2836880 | 131072 | 239640 | 30830176 | 12075643946959901 | 12075643947152137 | 12075643947291816 | 12075643947296206 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7f3ebe4d9300 | 0x7f3db28368c0 | 131072 | 249578 | 31856880 | 12075643947336010 | 12075643947520295 | 12075643947712454 | 12075643947759587 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7f3ebe4d9a00 | 0x7f3db2836900 | 131072 | 219156 | 27960616 | 12075643947799962 | 12075643947965733 | 12075643948104132 | 12075643948108586 |
| 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 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7f3ebe4d9900 | 0x7f3db2836940 | 131072 | 244436 | 31259712 | 12075643948148229 | 12075643948334211 | 12075643948617569 | 12075643948643640 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7f3ebe4d9800 | 0x7f3db2836980 | 65536 | 167430 | 21471864 | 12075643948682182 | 12075643948860608 | 12075643949120767 | 12075643949148789 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7f3ebe4d9700 | 0x7f3db28369c0 | 131072 | 252798 | 32298584 | 12075643949192891 | 12075643949361566 | 12075643949498685 | 12075643949502646 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7f3ebe4d9600 | 0x7f3db2836a00 | 131072 | 247328 | 31502072 | 12075643949542150 | 12075643949725244 | 12075643949936603 | 12075643949957582 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7f3ebe4d9500 | 0x7f3db2836a40 | 131072 | 266044 | 34071136 | 12075643950023314 | 12075643950191481 | 12075643950330361 | 12075643950334272 |
| 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 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7f3ebe4d9400 | 0x7f3db2836a80 | 131072 | 237832 | 30528640 | 12075643950382261 | 12075643950559480 | 12075643950868598 | 12075643950893632 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7f3ebe4d9300 | 0x7f3db2836ac0 | 65536 | 175242 | 22547200 | 12075643950932444 | 12075643951100117 | 12075643951359316 | 12075643951387529 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7f3ebe4d9a00 | 0x7f3db2836b00 | 131072 | 238054 | 30637256 | 12075643951435038 | 12075643951599794 | 12075643951740914 | 12075643951745485 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7f3ebe4d9900 | 0x7f3db2836b40 | 131072 | 241178 | 31354880 | 12075643951786250 | 12075643951971953 | 12075643952200111 | 12075643952227571 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7f3ebe4d9800 | 0x7f3db2836b80 | 131072 | 240632 | 30857600 | 12075643952285769 | 12075643952457390 | 12075643952592910 | 12075643952597378 |
| 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 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7f3ebe4d9700 | 0x7f3db2836bc0 | 131072 | 255848 | 32482344 | 12075643952646169 | 12075643952830828 | 12075643953160427 | 12075643953188987 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7f3ebe4d9600 | 0x7f3db2836c00 | 65536 | 162166 | 20678856 | 12075643953223091 | 12075643953407305 | 12075643953669064 | 12075643953694868 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7f3ebe4d9500 | 0x7f3db2836c40 | 131072 | 239706 | 30758864 | 12075643953740222 | 12075643953907250 | 12075643954049650 | 12075643954056880 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7f3ebe4d9400 | 0x7f3db2836c80 | 131072 | 239530 | 30684768 | 12075643954092747 | 12075643954281328 | 12075643954526767 | 12075643954550738 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7f3ebe4d9300 | 0x7f3db2836cc0 | 131072 | 262118 | 33544784 | 12075643954608906 | 12075643954778126 | 12075643954919245 | 12075643954922720 |
| 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 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7f3ebe4d9a00 | 0x7f3db2836d00 | 131072 | 242374 | 30947456 | 12075643954970308 | 12075643955153644 | 12075643955531403 | 12075643955558411 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7f3ebe4d9900 | 0x7f3db2836d40 | 65536 | 185820 | 23806520 | 12075643955599157 | 12075643955764202 | 12075643956033321 | 12075643956058370 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7f3ebe4d9800 | 0x7f3db2836d80 | 131072 | 242394 | 30872304 | 12075643956101059 | 12075643956268840 | 12075643956410439 | 12075643956414111 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7f3ebe4d9700 | 0x7f3db2836dc0 | 131072 | 277376 | 35483944 | 12075643956462381 | 12075643956650598 | 12075643956929957 | 12075643956953995 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7f3ebe4d9600 | 0x7f3db2836e00 | 131072 | 242900 | 30874976 | 12075643957013425 | 12075643957181636 | 12075643957324675 | 12075643957328390 |
| 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 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7f3ebe4d9500 | 0x7f3db2836e40 | 131072 | 257600 | 33031632 | 12075643957368405 | 12075643957561474 | 12075643957988033 | 12075643958012902 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7f3ebe4d9400 | 0x7f3db2836e80 | 65536 | 172724 | 22101184 | 12075643958049290 | 12075643958220992 | 12075643958489631 | 12075643958509555 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7f3ebe4d9300 | 0x7f3db2836ec0 | 131072 | 260790 | 33485528 | 12075643958555331 | 12075643958721950 | 12075643958862589 | 12075643958866369 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7f3ebe4d9a00 | 0x7f3db2836f00 | 131072 | 240562 | 30838136 | 12075643958907505 | 12075643959096988 | 12075643959413307 | 12075643959440285 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7f3ebe4d9900 | 0x7f3db2836f40 | 131072 | 252470 | 32247480 | 12075643959492673 | 12075643959663386 | 12075643959855225 | 12075643959878219 |
| 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 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7f3ebe4d9800 | 0x7f3db2836f80 | 131072 | 240374 | 30812776 | 12075643959921960 | 12075643960096984 | 12075643960616182 | 12075643960640906 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7f3ebe4d9700 | 0x7f3db2836fc0 | 65536 | 170548 | 21853640 | 12075643960687343 | 12075643960853301 | 12075643961155060 | 12075643961183946 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7f3ebe4d9600 | 0x7f3db2837000 | 131072 | 241806 | 30858384 | 12075643961216546 | 12075643961411379 | 12075643961566258 | 12075643961569803 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7f3ebe4d9500 | 0x7f3db2837040 | 131072 | 238054 | 30588368 | 12075643961618153 | 12075643961814257 | 12075643962201296 | 12075643962248955 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7f3ebe4d9400 | 0x7f3db2837080 | 131072 | 240364 | 30688920 | 12075643962287216 | 12075643962462735 | 12075643962639054 | 12075643962642486 |
| 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 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7f3ebe4d9300 | 0x7f3db28370c0 | 131072 | 239758 | 30415256 | 12075643962682260 | 12075643962867533 | 12075643963480010 | 12075643963529114 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7f3ebe4d9a00 | 0x7f3db2837100 | 65536 | 172080 | 22039864 | 12075643963554952 | 12075643963745129 | 12075643964074248 | 12075643964122096 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7f3ebe4d9900 | 0x7f3db2837140 | 131072 | 222434 | 28312920 | 12075643964149587 | 12075643964342247 | 12075643964522086 | 12075643964525686 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7f3ebe4d9800 | 0x7f3db2837180 | 131072 | 264310 | 34040880 | 12075643964575429 | 12075643964752165 | 12075643965229603 | 12075643965277203 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7f3ebe4d9700 | 0x7f3db28371c0 | 131072 | 249810 | 32052536 | 12075643965321575 | 12075643965493922 | 12075643965693282 | 12075643965740394 |
| 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 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7f3ebe4d9600 | 0x7f3db2837200 | 131072 | 233986 | 30003792 | 12075643965765090 | 12075643965953120 | 12075643966658558 | 12075643966709264 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7f3ebe4d9500 | 0x7f3db2837240 | 65536 | 175408 | 22547928 | 12075643966729071 | 12075643966926717 | 12075643967299675 | 12075643967348723 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7f3ebe4d9400 | 0x7f3db2837280 | 131072 | 241772 | 30996624 | 12075643967378478 | 12075643967562714 | 12075643967766233 | 12075643967813937 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7f3ebe4d9300 | 0x7f3db28372c0 | 131072 | 254294 | 32434568 | 12075643967833634 | 12075643968032152 | 12075643968558390 | 12075643968605909 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7f3ebe4d9a00 | 0x7f3db2837300 | 131072 | 239632 | 30760648 | 12075643968645753 | 12075643968818709 | 12075643969044308 | 12075643969094397 |
| 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 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7f3ebe4d9900 | 0x7f3db2837340 | 131072 | 259214 | 32772240 | 12075643969120706 | 12075643969298227 | 12075643970098704 | 12075643970148636 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7f3ebe4d9800 | 0x7f3db2837380 | 65536 | 166048 | 21385440 | 12075643970172491 | 12075643970352783 | 12075643970773421 | 12075643970823170 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7f3ebe4d9700 | 0x7f3db28373c0 | 131072 | 253474 | 32221216 | 12075643970841514 | 12075643971038060 | 12075643971265419 | 12075643971315815 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7f3ebe4d9600 | 0x7f3db2837400 | 131072 | 240982 | 30730040 | 12075643971338207 | 12075643971524618 | 12075643972122376 | 12075643972189920 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7f3ebe4d9500 | 0x7f3db2837440 | 131072 | 250488 | 31974632 | 12075643972228441 | 12075643972391814 | 12075643972662373 | 12075643972729282 |
| 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 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7f3ebe4d9400 | 0x7f3db2837480 | 131072 | 238834 | 30559592 | 12075643972759488 | 12075643972937412 | 12075643973923648 | 12075643973993402 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7f3ebe4d9300 | 0x7f3db28374c0 | 65536 | 176176 | 22527344 | 12075643974026373 | 12075643974205567 | 12075643974737725 | 12075643974805220 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7f3ebe4d9a00 | 0x7f3db2837500 | 131072 | 243888 | 30966536 | 12075643974828714 | 12075643975008444 | 12075643975281563 | 12075643975350724 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7f3ebe4d9900 | 0x7f3db2837540 | 131072 | 236936 | 30497224 | 12075643975376141 | 12075643975555482 | 12075643976294999 | 12075643976362544 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7f3ebe4d9800 | 0x7f3db2837580 | 131072 | 246004 | 31327408 | 12075643976408159 | 12075643976572278 | 12075643976889396 | 12075643976956458 |
| 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 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7f3ebe4d9700 | 0x7f3db28375c0 | 131072 | 237858 | 30549912 | 12075643976986153 | 12075643977166195 | 12075643978338990 | 12075643978406573 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7f3ebe4d9600 | 0x7f3db2837600 | 65536 | 177318 | 22709336 | 12075643978439945 | 12075643978610669 | 12075643979219947 | 12075643979288653 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7f3ebe4d9500 | 0x7f3db2837640 | 131072 | 259654 | 33026584 | 12075643979322566 | 12075643979495946 | 12075643979816104 | 12075643979882596 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7f3ebe4d9400 | 0x7f3db2837680 | 131072 | 251124 | 31904720 | 12075643979913975 | 12075643980100423 | 12075643980979140 | 12075643981049375 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7f3ebe4d9300 | 0x7f3db28376c0 | 131072 | 242708 | 30890176 | 12075643981093567 | 12075643981257699 | 12075643981668577 | 12075643981735299 |
| 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 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7f3ebe4d9a00 | 0x7f3db2837700 | 131072 | 257036 | 33128952 | 12075643981758833 | 12075643981945216 | 12075643983493210 | 12075643983561774 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7f3ebe4d9900 | 0x7f3db2837740 | 65536 | 176552 | 22556248 | 12075643983593302 | 12075643983774648 | 12075643984570325 | 12075643984637683 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7f3ebe4d9800 | 0x7f3db2837780 | 131072 | 244530 | 31596656 | 12075643984669272 | 12075643984848564 | 12075643985264082 | 12075643985333927 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7f3ebe4d9700 | 0x7f3db28377c0 | 131072 | 241310 | 30918240 | 12075643985363202 | 12075643985546001 | 12075643986705677 | 12075643986773072 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7f3ebe4d9600 | 0x7f3db2837800 | 131072 | 243686 | 31102880 | 12075643986816823 | 12075643986979116 | 12075643987765832 | 12075643987836468 |
| 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 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7f3ebe4d9500 | 0x7f3db2837840 | 131072 | 243234 | 31010032 | 12075643987866684 | 12075643988055591 | 12075643991107579 | 12075643991177257 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7f3ebe4d9400 | 0x7f3db2837880 | 65536 | 169608 | 21733136 | 12075643991209377 | 12075643991389338 | 12075643992932692 | 12075643993004703 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7f3ebe4d9300 | 0x7f3db28378c0 | 131072 | 243036 | 31246040 | 12075643993048034 | 12075643993212850 | 12075643994001647 | 12075643994070564 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7f3ebe4d9a00 | 0x7f3db2837900 | 131072 | 243352 | 31090512 | 12075643994100991 | 12075643994288046 | 12075643996570597 | 12075643996639188 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7f3ebe4d9900 | 0x7f3db2837940 | 131072 | 265260 | 34001888 | 12075643996684993 | 12075643996847396 | 12075643998382750 | 12075643998452147 |
| 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 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7f3ebe4d9800 | 0x7f3db2837980 | 131072 | 240440 | 30818288 | 12075643998483816 | 12075643998664988 | 12075644004719204 | 12075644004787231 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7f3ebe4d9700 | 0x7f3db28379c0 | 65536 | 181206 | 23219552 | 12075644004817437 | 12075644005000003 | 12075644008041111 | 12075644008112771 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7f3ebe4d9600 | 0x7f3db2837a00 | 131072 | 242562 | 30895528 | 12075644008142576 | 12075644008324949 | 12075644009865263 | 12075644009933394 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 885650 | 885655 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7f3ebe4d9500 | 0x7f3db2837a40 | 131072 | 253610 | 32463312 | 12075644009964402 | 12075644010152142 | 12075644014679164 | 12075644014751849 |