39 KiB
39 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBuffer.kd | 0 | 0 | 0 | 878445 | 878450 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7f1ad1004180 | 12075493288149052 | 12075493288191172 | 12075493288515649 | 12075493288621740 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 878445 | 878450 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7f1ad1035100 | 12075493302808305 | 12075493302909906 | 12075493302916626 | 12075493302922527 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7f1bdcd26900 | 0x7f1ad1035140 | 12075493302964405 | 12075493302977585 | 12075493303109584 | 12075493303113051 |
| 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 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7f1bdcd26800 | 0x7f1ad1035180 | 12075493303160540 | 12075493303175503 | 12075493303420941 | 12075493303518725 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7f1bdcd26700 | 0x7f1ad10351c0 | 12075493303546968 | 12075493303558539 | 12075493303801897 | 12075493303899022 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7f1bdcd26600 | 0x7f1ad1035200 | 12075493303925031 | 12075493303937096 | 12075493304062214 | 12075493304065983 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7f1bdcd26500 | 0x7f1ad1035240 | 12075493304095598 | 12075493304106854 | 12075493304231493 | 12075493304234796 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7f1bdcd26400 | 0x7f1ad1035280 | 12075493304288266 | 12075493304302852 | 12075493304427331 | 12075493304430530 |
| 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 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7f1bdcd26300 | 0x7f1ad10352c0 | 12075493304458662 | 12075493304470530 | 12075493304721248 | 12075493304818220 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7f1bdcd26a00 | 0x7f1ad1035300 | 12075493304839650 | 12075493304850847 | 12075493305096284 | 12075493305195882 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7f1bdcd26900 | 0x7f1ad1035340 | 12075493305215018 | 12075493305231483 | 12075493305356122 | 12075493305359476 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7f1bdcd26800 | 0x7f1ad1035380 | 12075493305387168 | 12075493305399001 | 12075493305523800 | 12075493305527058 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7f1bdcd26700 | 0x7f1ad10353c0 | 12075493305565149 | 12075493305578839 | 12075493305703638 | 12075493305706842 |
| 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 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7f1bdcd26600 | 0x7f1ad1035400 | 12075493305734513 | 12075493305747318 | 12075493305993555 | 12075493306069837 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7f1bdcd26500 | 0x7f1ad1035440 | 12075493306097147 | 12075493306109074 | 12075493306354352 | 12075493306421961 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7f1bdcd26400 | 0x7f1ad1035480 | 12075493306447859 | 12075493306460111 | 12075493306585070 | 12075493306588320 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7f1bdcd26300 | 0x7f1ad10354c0 | 12075493306614839 | 12075493306626189 | 12075493306750828 | 12075493306754058 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7f1bdcd26a00 | 0x7f1ad1035500 | 12075493306791017 | 12075493306804427 | 12075493306929226 | 12075493306932500 |
| 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 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7f1bdcd26900 | 0x7f1ad1035540 | 12075493306957787 | 12075493306971146 | 12075493307221383 | 12075493307291958 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7f1bdcd26800 | 0x7f1ad1035580 | 12075493307315522 | 12075493307328902 | 12075493307572260 | 12075493307638502 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7f1bdcd26700 | 0x7f1ad10355c0 | 12075493307664450 | 12075493307677539 | 12075493307801858 | 12075493307804951 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7f1bdcd26600 | 0x7f1ad1035600 | 12075493307831571 | 12075493307843297 | 12075493307967936 | 12075493307971210 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7f1bdcd26500 | 0x7f1ad1035640 | 12075493308015312 | 12075493308029375 | 12075493308154014 | 12075493308157056 |
| 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 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7f1bdcd26400 | 0x7f1ad1035680 | 12075493308185989 | 12075493308199454 | 12075493308445051 | 12075493308487169 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7f1bdcd26300 | 0x7f1ad10356c0 | 12075493308510092 | 12075493308523130 | 12075493308769688 | 12075493308835536 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7f1bdcd26a00 | 0x7f1ad1035700 | 12075493308856195 | 12075493308869527 | 12075493308993526 | 12075493308996626 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7f1bdcd26900 | 0x7f1ad1035740 | 12075493309027283 | 12075493309038165 | 12075493309162804 | 12075493309166081 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7f1bdcd26800 | 0x7f1ad1035780 | 12075493309202208 | 12075493309216564 | 12075493309341362 | 12075493309344552 |
| 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 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7f1bdcd26700 | 0x7f1ad10357c0 | 12075493309370781 | 12075493309384402 | 12075493309636079 | 12075493309688091 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7f1bdcd26600 | 0x7f1ad1035800 | 12075493309710222 | 12075493309721679 | 12075493309969196 | 12075493310048310 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7f1bdcd26500 | 0x7f1ad1035840 | 12075493310070411 | 12075493310082155 | 12075493310206794 | 12075493310210271 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7f1bdcd26400 | 0x7f1ad1035880 | 12075493310238123 | 12075493310249513 | 12075493310374792 | 12075493310378173 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7f1bdcd26300 | 0x7f1ad10358c0 | 12075493310413729 | 12075493310428392 | 12075493310553030 | 12075493310556415 |
| 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 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7f1bdcd26a00 | 0x7f1ad1035900 | 12075493310583174 | 12075493310594790 | 12075493310845988 | 12075493310898901 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7f1bdcd26900 | 0x7f1ad1035940 | 12075493310921814 | 12075493310934147 | 12075493311182784 | 12075493311263469 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7f1bdcd26800 | 0x7f1ad1035980 | 12075493311285790 | 12075493311297663 | 12075493311422462 | 12075493311425880 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7f1bdcd26700 | 0x7f1ad10359c0 | 12075493311452149 | 12075493311463581 | 12075493311589340 | 12075493311592801 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7f1bdcd26600 | 0x7f1ad1035a00 | 12075493311628848 | 12075493311640380 | 12075493311764858 | 12075493311767846 |
| 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 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7f1bdcd26500 | 0x7f1ad1035a40 | 12075493311795237 | 12075493311809498 | 12075493312092055 | 12075493312148103 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7f1bdcd26400 | 0x7f1ad1035a80 | 12075493312170775 | 12075493312182614 | 12075493312428372 | 12075493312456586 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7f1bdcd26300 | 0x7f1ad1035ac0 | 12075493312479599 | 12075493312492051 | 12075493312617330 | 12075493312620551 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7f1bdcd26a00 | 0x7f1ad1035b00 | 12075493312648262 | 12075493312659570 | 12075493312785968 | 12075493312789014 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7f1bdcd26900 | 0x7f1ad1035b40 | 12075493312826423 | 12075493312840848 | 12075493312965807 | 12075493312968958 |
| 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 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7f1bdcd26800 | 0x7f1ad1035b80 | 12075493312996179 | 12075493313013166 | 12075493313263884 | 12075493313292680 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7f1bdcd26700 | 0x7f1ad1035bc0 | 12075493313315292 | 12075493313326763 | 12075493313572681 | 12075493313596434 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7f1bdcd26600 | 0x7f1ad1035c00 | 12075493313617724 | 12075493313629320 | 12075493313753639 | 12075493313756742 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7f1bdcd26500 | 0x7f1ad1035c40 | 12075493313784263 | 12075493313796198 | 12075493313922117 | 12075493313925155 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7f1bdcd26400 | 0x7f1ad1035c80 | 12075493313961763 | 12075493313975077 | 12075493314100515 | 12075493314103827 |
| 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 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7f1bdcd26300 | 0x7f1ad1035cc0 | 12075493314131799 | 12075493314145795 | 12075493314399553 | 12075493314427950 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7f1bdcd26a00 | 0x7f1ad1035d00 | 12075493314451453 | 12075493314463072 | 12075493314707070 | 12075493314730472 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7f1bdcd26900 | 0x7f1ad1035d40 | 12075493314751912 | 12075493314763389 | 12075493314887708 | 12075493314890830 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7f1bdcd26800 | 0x7f1ad1035d80 | 12075493314917480 | 12075493314931707 | 12075493315059866 | 12075493315063010 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7f1bdcd26700 | 0x7f1ad1035dc0 | 12075493315101922 | 12075493315113306 | 12075493315238424 | 12075493315241722 |
| 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 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7f1bdcd26600 | 0x7f1ad1035e00 | 12075493315268652 | 12075493315280664 | 12075493315538261 | 12075493315562608 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7f1bdcd26500 | 0x7f1ad1035e40 | 12075493315583998 | 12075493315595701 | 12075493315839538 | 12075493315863758 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7f1bdcd26400 | 0x7f1ad1035e80 | 12075493315884767 | 12075493315895698 | 12075493316020977 | 12075493316024417 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7f1bdcd26300 | 0x7f1ad1035ec0 | 12075493316054412 | 12075493316067376 | 12075493316196495 | 12075493316199883 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7f1bdcd26a00 | 0x7f1ad1035f00 | 12075493316237002 | 12075493316250894 | 12075493316375853 | 12075493316379226 |
| 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 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7f1bdcd26900 | 0x7f1ad1035f40 | 12075493316405996 | 12075493316417613 | 12075493316671050 | 12075493316694823 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7f1bdcd26800 | 0x7f1ad1035f80 | 12075493316716543 | 12075493316728490 | 12075493316972967 | 12075493316996734 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7f1bdcd26700 | 0x7f1ad1035fc0 | 12075493317025557 | 12075493317036807 | 12075493317162085 | 12075493317165217 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7f1bdcd26600 | 0x7f1ad1036000 | 12075493317191426 | 12075493317202885 | 12075493317341124 | 12075493317344260 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7f1bdcd26500 | 0x7f1ad1036040 | 12075493317381679 | 12075493317393443 | 12075493317518082 | 12075493317521218 |
| 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 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7f1bdcd26400 | 0x7f1ad1036080 | 12075493317547858 | 12075493317560001 | 12075493317813119 | 12075493317837035 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7f1bdcd26300 | 0x7f1ad10360c0 | 12075493317861681 | 12075493317874078 | 12075493318120316 | 12075493318144467 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7f1bdcd26a00 | 0x7f1ad1036100 | 12075493318168231 | 12075493318179835 | 12075493318304954 | 12075493318308051 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7f1bdcd26900 | 0x7f1ad1036140 | 12075493318334891 | 12075493318345914 | 12075493318488312 | 12075493318491291 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7f1bdcd26800 | 0x7f1ad1036180 | 12075493318528110 | 12075493318539672 | 12075493318664471 | 12075493318667569 |
| 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 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7f1bdcd26700 | 0x7f1ad10361c0 | 12075493318694719 | 12075493318706070 | 12075493318962708 | 12075493318984758 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7f1bdcd26600 | 0x7f1ad1036200 | 12075493319012410 | 12075493319024147 | 12075493319268305 | 12075493319293492 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7f1bdcd26500 | 0x7f1ad1036240 | 12075493319316425 | 12075493319327664 | 12075493319452783 | 12075493319455884 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7f1bdcd26400 | 0x7f1ad1036280 | 12075493319484828 | 12075493319495982 | 12075493319644781 | 12075493319647871 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7f1bdcd26300 | 0x7f1ad10362c0 | 12075493319702703 | 12075493319714220 | 12075493319839179 | 12075493319842482 |
| 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 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7f1bdcd26a00 | 0x7f1ad1036300 | 12075493319869973 | 12075493319882059 | 12075493320135016 | 12075493320166404 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7f1bdcd26900 | 0x7f1ad1036340 | 12075493320189447 | 12075493320202535 | 12075493320448133 | 12075493320474657 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7f1bdcd26800 | 0x7f1ad1036380 | 12075493320497269 | 12075493320510692 | 12075493320635971 | 12075493320639003 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7f1bdcd26700 | 0x7f1ad10363c0 | 12075493320667015 | 12075493320678371 | 12075493320835809 | 12075493320838884 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7f1bdcd26600 | 0x7f1ad1036400 | 12075493320875642 | 12075493320887169 | 12075493321011967 | 12075493321015272 |
| 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 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7f1bdcd26500 | 0x7f1ad1036440 | 12075493321043264 | 12075493321055007 | 12075493321320444 | 12075493321347319 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7f1bdcd26400 | 0x7f1ad1036480 | 12075493321373367 | 12075493321385564 | 12075493321629721 | 12075493321652085 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7f1bdcd26300 | 0x7f1ad10364c0 | 12075493321673926 | 12075493321686841 | 12075493321813240 | 12075493321816451 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7f1bdcd26a00 | 0x7f1ad1036500 | 12075493321842820 | 12075493321855319 | 12075493322020597 | 12075493322023997 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7f1bdcd26900 | 0x7f1ad1036540 | 12075493322062668 | 12075493322073557 | 12075493322199156 | 12075493322202258 |
| 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 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7f1bdcd26800 | 0x7f1ad1036580 | 12075493322228957 | 12075493322240595 | 12075493322495953 | 12075493322522954 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7f1bdcd26700 | 0x7f1ad10365c0 | 12075493322545035 | 12075493322556592 | 12075493322802190 | 12075493322829113 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7f1bdcd26600 | 0x7f1ad1036600 | 12075493322850974 | 12075493322864109 | 12075493322989548 | 12075493322992667 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7f1bdcd26500 | 0x7f1ad1036640 | 12075493323025698 | 12075493323037227 | 12075493323209866 | 12075493323213167 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7f1bdcd26400 | 0x7f1ad1036680 | 12075493323250115 | 12075493323261705 | 12075493323387144 | 12075493323390246 |
| 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 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7f1bdcd26300 | 0x7f1ad10366c0 | 12075493323417396 | 12075493323429224 | 12075493323681701 | 12075493323700953 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7f1bdcd26a00 | 0x7f1ad1036700 | 12075493323721251 | 12075493323734821 | 12075493323981698 | 12075493324007954 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7f1bdcd26900 | 0x7f1ad1036740 | 12075493324030556 | 12075493324043138 | 12075493324168736 | 12075493324172039 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7f1bdcd26800 | 0x7f1ad1036780 | 12075493324199530 | 12075493324211296 | 12075493324393054 | 12075493324396135 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7f1bdcd26700 | 0x7f1ad10367c0 | 12075493324434016 | 12075493324445694 | 12075493324573372 | 12075493324576380 |
| 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 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7f1bdcd26600 | 0x7f1ad1036800 | 12075493324602749 | 12075493324613532 | 12075493324876889 | 12075493324900162 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7f1bdcd26500 | 0x7f1ad1036840 | 12075493324922664 | 12075493324934009 | 12075493325179126 | 12075493325205169 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7f1bdcd26400 | 0x7f1ad1036880 | 12075493325225617 | 12075493325236406 | 12075493325362645 | 12075493325365707 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7f1bdcd26300 | 0x7f1ad10368c0 | 12075493325393469 | 12075493325405044 | 12075493325595922 | 12075493325599462 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7f1bdcd26a00 | 0x7f1ad1036900 | 12075493325634607 | 12075493325645682 | 12075493325772881 | 12075493325775980 |
| 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 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7f1bdcd26900 | 0x7f1ad1036940 | 12075493325802759 | 12075493325814960 | 12075493326097197 | 12075493326121161 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7f1bdcd26800 | 0x7f1ad1036980 | 12075493326142972 | 12075493326154637 | 12075493326403434 | 12075493326426489 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7f1bdcd26700 | 0x7f1ad10369c0 | 12075493326446947 | 12075493326459914 | 12075493326585832 | 12075493326589271 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7f1bdcd26600 | 0x7f1ad1036a00 | 12075493326617263 | 12075493326628552 | 12075493326838150 | 12075493326860325 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7f1bdcd26500 | 0x7f1ad1036a40 | 12075493326891423 | 12075493326902309 | 12075493327030148 | 12075493327033537 |
| 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 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7f1bdcd26400 | 0x7f1ad1036a80 | 12075493327060397 | 12075493327072228 | 12075493327378465 | 12075493327401120 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7f1bdcd26300 | 0x7f1ad1036ac0 | 12075493327422159 | 12075493327433184 | 12075493327689182 | 12075493327713861 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7f1bdcd26a00 | 0x7f1ad1036b00 | 12075493327735111 | 12075493327746141 | 12075493327872860 | 12075493327876012 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7f1bdcd26900 | 0x7f1ad1036b40 | 12075493327902231 | 12075493327913659 | 12075493328141017 | 12075493328167895 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7f1bdcd26800 | 0x7f1ad1036b80 | 12075493328199954 | 12075493328215896 | 12075493328344055 | 12075493328347539 |
| 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 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7f1bdcd26700 | 0x7f1ad1036bc0 | 12075493328373407 | 12075493328384855 | 12075493328713332 | 12075493328735620 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7f1bdcd26600 | 0x7f1ad1036c00 | 12075493328758953 | 12075493328770451 | 12075493329017969 | 12075493329041639 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7f1bdcd26500 | 0x7f1ad1036c40 | 12075493329064681 | 12075493329076208 | 12075493329204367 | 12075493329207537 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7f1bdcd26400 | 0x7f1ad1036c80 | 12075493329234727 | 12075493329246286 | 12075493329491084 | 12075493329513606 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7f1bdcd26300 | 0x7f1ad1036cc0 | 12075493329545505 | 12075493329556683 | 12075493329686122 | 12075493329689312 |
| 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 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7f1bdcd26a00 | 0x7f1ad1036d00 | 12075493329716663 | 12075493329727402 | 12075493330102758 | 12075493330130542 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7f1bdcd26900 | 0x7f1ad1036d40 | 12075493330152173 | 12075493330163237 | 12075493330417315 | 12075493330443935 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7f1bdcd26800 | 0x7f1ad1036d80 | 12075493330465505 | 12075493330476674 | 12075493330606273 | 12075493330609412 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7f1bdcd26700 | 0x7f1ad1036dc0 | 12075493330637985 | 12075493330649152 | 12075493330928030 | 12075493330953892 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7f1bdcd26600 | 0x7f1ad1036e00 | 12075493330985802 | 12075493330998909 | 12075493331133628 | 12075493331137073 |
| 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 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7f1bdcd26500 | 0x7f1ad1036e40 | 12075493331163432 | 12075493331174747 | 12075493331597623 | 12075493331619970 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7f1bdcd26400 | 0x7f1ad1036e80 | 12075493331642152 | 12075493331653143 | 12075493331909300 | 12075493331927742 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7f1bdcd26300 | 0x7f1ad1036ec0 | 12075493331950224 | 12075493331961460 | 12075493332097298 | 12075493332100744 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7f1bdcd26a00 | 0x7f1ad1036f00 | 12075493332127614 | 12075493332138738 | 12075493332454095 | 12075493332478115 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7f1bdcd26900 | 0x7f1ad1036f40 | 12075493332508652 | 12075493332520974 | 12075493332671853 | 12075493332675171 |
| 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 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7f1bdcd26800 | 0x7f1ad1036f80 | 12075493332701240 | 12075493332712652 | 12075493333229927 | 12075493333257674 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7f1bdcd26700 | 0x7f1ad1036fc0 | 12075493333282410 | 12075493333293446 | 12075493333591043 | 12075493333616721 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7f1bdcd26600 | 0x7f1ad1037000 | 12075493333639824 | 12075493333650563 | 12075493333805121 | 12075493333808257 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7f1bdcd26500 | 0x7f1ad1037040 | 12075493333834556 | 12075493333846081 | 12075493334231357 | 12075493334261780 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7f1bdcd26400 | 0x7f1ad1037080 | 12075493334293970 | 12075493334306396 | 12075493334481595 | 12075493334484845 |
| 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 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7f1bdcd26300 | 0x7f1ad10370c0 | 12075493334511584 | 12075493334524154 | 12075493335134548 | 12075493335162434 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7f1bdcd26a00 | 0x7f1ad1037100 | 12075493335184455 | 12075493335197428 | 12075493335524464 | 12075493335550786 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7f1bdcd26900 | 0x7f1ad1037140 | 12075493335573047 | 12075493335585104 | 12075493335763502 | 12075493335766947 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7f1bdcd26800 | 0x7f1ad1037180 | 12075493335795340 | 12075493335806382 | 12075493336262697 | 12075493336296672 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7f1bdcd26700 | 0x7f1ad10371c0 | 12075493336328601 | 12075493336339816 | 12075493336538854 | 12075493336565341 |
| 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 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7f1bdcd26600 | 0x7f1ad1037200 | 12075493336586200 | 12075493336597414 | 12075493337301087 | 12075493337329551 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7f1bdcd26500 | 0x7f1ad1037240 | 12075493337351512 | 12075493337363806 | 12075493337736763 | 12075493337762997 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7f1bdcd26400 | 0x7f1ad1037280 | 12075493337784457 | 12075493337795802 | 12075493337998360 | 12075493338025715 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7f1bdcd26300 | 0x7f1ad10372c0 | 12075493338047746 | 12075493338058839 | 12075493338584274 | 12075493338610402 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7f1bdcd26a00 | 0x7f1ad1037300 | 12075493338642251 | 12075493338654034 | 12075493338878031 | 12075493338900521 |
| 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 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7f1bdcd26900 | 0x7f1ad1037340 | 12075493338923784 | 12075493338935631 | 12075493339734503 | 12075493339767202 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7f1bdcd26800 | 0x7f1ad1037380 | 12075493339792078 | 12075493339804742 | 12075493340225218 | 12075493340257232 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7f1bdcd26700 | 0x7f1ad10373c0 | 12075493340278271 | 12075493340289377 | 12075493340515935 | 12075493340538315 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7f1bdcd26600 | 0x7f1ad1037400 | 12075493340563131 | 12075493340574495 | 12075493341170809 | 12075493341198512 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7f1bdcd26500 | 0x7f1ad1037440 | 12075493341229740 | 12075493341241048 | 12075493341541365 | 12075493341568399 |
| 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 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7f1bdcd26400 | 0x7f1ad1037480 | 12075493341590490 | 12075493341603285 | 12075493342588395 | 12075493342618571 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7f1bdcd26300 | 0x7f1ad10374c0 | 12075493342639269 | 12075493342650314 | 12075493343165349 | 12075493343194691 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7f1bdcd26a00 | 0x7f1ad1037500 | 12075493343216392 | 12075493343229029 | 12075493343499106 | 12075493343525677 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7f1bdcd26900 | 0x7f1ad1037540 | 12075493343550683 | 12075493343561825 | 12075493344299418 | 12075493344327497 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7f1bdcd26800 | 0x7f1ad1037580 | 12075493344360147 | 12075493344371257 | 12075493344687414 | 12075493344716259 |
| 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 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7f1bdcd26700 | 0x7f1ad10375c0 | 12075493344738791 | 12075493344749654 | 12075493345922122 | 12075493345949802 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7f1bdcd26600 | 0x7f1ad1037600 | 12075493345972123 | 12075493345984201 | 12075493346594275 | 12075493346627641 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7f1bdcd26500 | 0x7f1ad1037640 | 12075493346648580 | 12075493346661635 | 12075493346980992 | 12075493347009381 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7f1bdcd26400 | 0x7f1ad1037680 | 12075493347032804 | 12075493347045471 | 12075493347924022 | 12075493347952824 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7f1bdcd26300 | 0x7f1ad10376c0 | 12075493347985725 | 12075493347996182 | 12075493348405938 | 12075493348438797 |
| 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 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7f1bdcd26a00 | 0x7f1ad1037700 | 12075493348461880 | 12075493348473297 | 12075493350023682 | 12075493350095075 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7f1bdcd26900 | 0x7f1ad1037740 | 12075493350119371 | 12075493350131361 | 12075493350927033 | 12075493350998054 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7f1bdcd26800 | 0x7f1ad1037780 | 12075493351024242 | 12075493351035779 | 12075493351450015 | 12075493351526556 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7f1bdcd26700 | 0x7f1ad10377c0 | 12075493351549559 | 12075493351560733 | 12075493352718963 | 12075493352789753 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7f1bdcd26600 | 0x7f1ad1037800 | 12075493352823216 | 12075493352835122 | 12075493353620076 | 12075493353694234 |
| 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 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7f1bdcd26500 | 0x7f1ad1037840 | 12075493353719602 | 12075493353730795 | 12075493356786609 | 12075493356857854 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7f1bdcd26400 | 0x7f1ad1037880 | 12075493356879584 | 12075493356892528 | 12075493358436035 | 12075493358511888 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7f1bdcd26300 | 0x7f1ad10378c0 | 12075493358533959 | 12075493358547394 | 12075493359336667 | 12075493359407582 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7f1bdcd26a00 | 0x7f1ad1037900 | 12075493359431577 | 12075493359444346 | 12075493361726087 | 12075493361798075 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7f1bdcd26900 | 0x7f1ad1037940 | 12075493361830405 | 12075493361844166 | 12075493363379673 | 12075493363454584 |
| 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 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7f1bdcd26800 | 0x7f1ad1037980 | 12075493363478538 | 12075493363491832 | 12075493369550821 | 12075493369621825 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7f1bdcd26700 | 0x7f1ad10379c0 | 12075493369642724 | 12075493369654340 | 12075493372698634 | 12075493372770116 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7f1bdcd26600 | 0x7f1ad1037a00 | 12075493372791636 | 12075493372803593 | 12075493374342780 | 12075493374414021 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 878445 | 878450 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7f1bdcd26500 | 0x7f1ad1037a40 | 12075493374434619 | 12075493374446299 | 12075493378974101 | 12075493379046040 |