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 | 883441 | 883446 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7ff824e04180 | 12075586759212326 | 12075586759255753 | 12075586759580870 | 12075586759688601 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 883441 | 883446 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7ff824e35100 | 12075586774242810 | 12075586774350126 | 12075586774357486 | 12075586774362522 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7ff930a16900 | 0x7ff824e35140 | 12075586774402597 | 12075586774416205 | 12075586774548844 | 12075586774551744 |
| 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 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7ff930a16800 | 0x7ff824e35180 | 12075586774591848 | 12075586774603244 | 12075586774849001 | 12075586774947830 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7ff930a16700 | 0x7ff824e351c0 | 12075586774972847 | 12075586774984840 | 12075586775229158 | 12075586775332735 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7ff930a16600 | 0x7ff824e35200 | 12075586775361308 | 12075586775373796 | 12075586775500675 | 12075586775503162 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7ff930a16500 | 0x7ff824e35240 | 12075586775529661 | 12075586775541155 | 12075586775666593 | 12075586775669261 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7ff930a16400 | 0x7ff824e35280 | 12075586775717420 | 12075586775728993 | 12075586775852992 | 12075586775855457 |
| 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 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7ff930a16300 | 0x7ff824e352c0 | 12075586775880864 | 12075586775894911 | 12075586776147549 | 12075586776248698 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7ff930a16a00 | 0x7ff824e35300 | 12075586776269617 | 12075586776284667 | 12075586776529145 | 12075586776628984 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7ff930a16900 | 0x7ff824e35340 | 12075586776650074 | 12075586776661624 | 12075586776786423 | 12075586776788902 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7ff930a16800 | 0x7ff824e35380 | 12075586776813988 | 12075586776825302 | 12075586776950741 | 12075586776953447 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7ff930a16700 | 0x7ff824e353c0 | 12075586776988993 | 12075586777000501 | 12075586777125459 | 12075586777128142 |
| 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 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7ff930a16600 | 0x7ff824e35400 | 12075586777154010 | 12075586777165619 | 12075586777414897 | 12075586777514109 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7ff930a16500 | 0x7ff824e35440 | 12075586777539797 | 12075586777550895 | 12075586777798253 | 12075586777866855 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7ff930a16400 | 0x7ff824e35480 | 12075586777892162 | 12075586777903852 | 12075586778028651 | 12075586778031230 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7ff930a16300 | 0x7ff824e354c0 | 12075586778059012 | 12075586778070250 | 12075586778195849 | 12075586778198391 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7ff930a16a00 | 0x7ff824e35500 | 12075586778233206 | 12075586778244489 | 12075586778369287 | 12075586778371743 |
| 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 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7ff930a16900 | 0x7ff824e35540 | 12075586778396489 | 12075586778408007 | 12075586778653285 | 12075586778697128 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7ff930a16800 | 0x7ff824e35580 | 12075586778717546 | 12075586778728804 | 12075586778972802 | 12075586779040536 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7ff930a16700 | 0x7ff824e355c0 | 12075586779060624 | 12075586779073921 | 12075586779198879 | 12075586779201105 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7ff930a16600 | 0x7ff824e35600 | 12075586779226301 | 12075586779238719 | 12075586779364158 | 12075586779366652 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7ff930a16500 | 0x7ff824e35640 | 12075586779400425 | 12075586779412477 | 12075586779536636 | 12075586779539063 |
| 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 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7ff930a16400 | 0x7ff824e35680 | 12075586779564560 | 12075586779575996 | 12075586779828793 | 12075586779871390 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7ff930a16300 | 0x7ff824e356c0 | 12075586779890947 | 12075586779903833 | 12075586780149590 | 12075586780250665 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7ff930a16a00 | 0x7ff824e35700 | 12075586780270873 | 12075586780282709 | 12075586780406708 | 12075586780409430 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7ff930a16900 | 0x7ff824e35740 | 12075586780433755 | 12075586780444467 | 12075586780570226 | 12075586780572914 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7ff930a16800 | 0x7ff824e35780 | 12075586780608089 | 12075586780623026 | 12075586780747664 | 12075586780750244 |
| 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 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7ff930a16700 | 0x7ff824e357c0 | 12075586780773968 | 12075586780785744 | 12075586781041262 | 12075586781121263 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7ff930a16600 | 0x7ff824e35800 | 12075586781141571 | 12075586781153421 | 12075586781398058 | 12075586781478006 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7ff930a16500 | 0x7ff824e35840 | 12075586781497653 | 12075586781508617 | 12075586781633416 | 12075586781636060 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7ff930a16400 | 0x7ff824e35880 | 12075586781660355 | 12075586781672296 | 12075586781798534 | 12075586781801317 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7ff930a16300 | 0x7ff824e358c0 | 12075586781834479 | 12075586781845734 | 12075586781970533 | 12075586781972746 |
| 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 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7ff930a16a00 | 0x7ff824e35900 | 12075586781997131 | 12075586782013252 | 12075586782258850 | 12075586782319971 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7ff930a16900 | 0x7ff824e35940 | 12075586782339888 | 12075586782360449 | 12075586782607487 | 12075586782633934 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7ff930a16800 | 0x7ff824e35980 | 12075586782655895 | 12075586782668126 | 12075586782793405 | 12075586782796016 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7ff930a16700 | 0x7ff824e359c0 | 12075586782821353 | 12075586782833244 | 12075586782959163 | 12075586782961553 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7ff930a16600 | 0x7ff824e35a00 | 12075586782995787 | 12075586783007323 | 12075586783132281 | 12075586783135016 |
| 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 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7ff930a16500 | 0x7ff824e35a40 | 12075586783161124 | 12075586783175641 | 12075586783422519 | 12075586783452135 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7ff930a16400 | 0x7ff824e35a80 | 12075586783472793 | 12075586783485558 | 12075586783731156 | 12075586783759015 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7ff930a16300 | 0x7ff824e35ac0 | 12075586783779513 | 12075586783793075 | 12075586783917394 | 12075586783919774 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7ff930a16a00 | 0x7ff824e35b00 | 12075586783945231 | 12075586783956273 | 12075586784082192 | 12075586784084500 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7ff930a16900 | 0x7ff824e35b40 | 12075586784121679 | 12075586784133232 | 12075586784257871 | 12075586784260547 |
| 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 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7ff930a16800 | 0x7ff824e35b80 | 12075586784284983 | 12075586784296750 | 12075586784555628 | 12075586784579700 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7ff930a16700 | 0x7ff824e35bc0 | 12075586784601210 | 12075586784612427 | 12075586784855945 | 12075586784879788 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7ff930a16600 | 0x7ff824e35c00 | 12075586784898813 | 12075586784910984 | 12075586785035943 | 12075586785038734 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7ff930a16500 | 0x7ff824e35c40 | 12075586785065103 | 12075586785078983 | 12075586785206501 | 12075586785208950 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7ff930a16400 | 0x7ff824e35c80 | 12075586785243454 | 12075586785256421 | 12075586785381380 | 12075586785383985 |
| 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 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7ff930a16300 | 0x7ff824e35cc0 | 12075586785408801 | 12075586785421379 | 12075586785684897 | 12075586785708598 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7ff930a16a00 | 0x7ff824e35d00 | 12075586785730649 | 12075586785742016 | 12075586785989374 | 12075586786017392 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7ff930a16900 | 0x7ff824e35d40 | 12075586786040495 | 12075586786053373 | 12075586786178652 | 12075586786181307 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7ff930a16800 | 0x7ff824e35d80 | 12075586786206323 | 12075586786217372 | 12075586786345530 | 12075586786348037 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7ff930a16700 | 0x7ff824e35dc0 | 12075586786382751 | 12075586786395290 | 12075586786520409 | 12075586786523042 |
| 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 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7ff930a16600 | 0x7ff824e35e00 | 12075586786548079 | 12075586786559608 | 12075586786814806 | 12075586786843838 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7ff930a16500 | 0x7ff824e35e40 | 12075586786864877 | 12075586786877845 | 12075586787122323 | 12075586787152812 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7ff930a16400 | 0x7ff824e35e80 | 12075586787173010 | 12075586787185842 | 12075586787310801 | 12075586787313150 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7ff930a16300 | 0x7ff824e35ec0 | 12075586787339630 | 12075586787350961 | 12075586787480400 | 12075586787482806 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7ff930a16a00 | 0x7ff824e35f00 | 12075586787518833 | 12075586787531439 | 12075586787657038 | 12075586787659534 |
| 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 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7ff930a16900 | 0x7ff824e35f40 | 12075586787685202 | 12075586787697357 | 12075586787958155 | 12075586787981873 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7ff930a16800 | 0x7ff824e35f80 | 12075586788006419 | 12075586788017834 | 12075586788270632 | 12075586788302399 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7ff930a16700 | 0x7ff824e35fc0 | 12075586788322907 | 12075586788335591 | 12075586788461030 | 12075586788463378 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7ff930a16600 | 0x7ff824e36000 | 12075586788487313 | 12075586788499270 | 12075586788636388 | 12075586788638864 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7ff930a16500 | 0x7ff824e36040 | 12075586788673579 | 12075586788685188 | 12075586788809987 | 12075586788812387 |
| 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 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7ff930a16400 | 0x7ff824e36080 | 12075586788836922 | 12075586788848226 | 12075586789106624 | 12075586789131680 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7ff930a16300 | 0x7ff824e360c0 | 12075586789152679 | 12075586789165823 | 12075586789412381 | 12075586789435214 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7ff930a16a00 | 0x7ff824e36100 | 12075586789457335 | 12075586789470300 | 12075586789594939 | 12075586789597396 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7ff930a16900 | 0x7ff824e36140 | 12075586789622592 | 12075586789634939 | 12075586789777337 | 12075586789779795 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7ff930a16800 | 0x7ff824e36180 | 12075586789814449 | 12075586789825977 | 12075586789951576 | 12075586789954089 |
| 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 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7ff930a16700 | 0x7ff824e361c0 | 12075586789978243 | 12075586789989655 | 12075586790247253 | 12075586790272751 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7ff930a16600 | 0x7ff824e36200 | 12075586790293780 | 12075586790307252 | 12075586790556050 | 12075586790579040 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7ff930a16500 | 0x7ff824e36240 | 12075586790598596 | 12075586790611409 | 12075586790736848 | 12075586790739288 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7ff930a16400 | 0x7ff824e36280 | 12075586790764775 | 12075586790776048 | 12075586790925806 | 12075586790928209 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7ff930a16300 | 0x7ff824e362c0 | 12075586790982389 | 12075586790994926 | 12075586791120364 | 12075586791123432 |
| 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 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7ff930a16a00 | 0x7ff824e36300 | 12075586791148749 | 12075586791163404 | 12075586791426601 | 12075586791450009 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7ff930a16900 | 0x7ff824e36340 | 12075586791471659 | 12075586791484681 | 12075586791732199 | 12075586791755106 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7ff930a16800 | 0x7ff824e36380 | 12075586791775744 | 12075586791788038 | 12075586791913957 | 12075586791916315 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7ff930a16700 | 0x7ff824e363c0 | 12075586791940650 | 12075586791953956 | 12075586792111395 | 12075586792114213 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7ff930a16600 | 0x7ff824e36400 | 12075586792149438 | 12075586792162594 | 12075586792287553 | 12075586792290340 |
| 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 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7ff930a16500 | 0x7ff824e36440 | 12075586792314906 | 12075586792326753 | 12075586792580990 | 12075586792605346 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7ff930a16400 | 0x7ff824e36480 | 12075586792625393 | 12075586792636830 | 12075586792886907 | 12075586792914550 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7ff930a16300 | 0x7ff824e364c0 | 12075586792938174 | 12075586792949307 | 12075586793076186 | 12075586793079086 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7ff930a16a00 | 0x7ff824e36500 | 12075586793103111 | 12075586793114105 | 12075586793280024 | 12075586793282845 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7ff930a16900 | 0x7ff824e36540 | 12075586793317710 | 12075586793330103 | 12075586793455862 | 12075586793458501 |
| 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 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7ff930a16800 | 0x7ff824e36580 | 12075586793483267 | 12075586793496502 | 12075586793755539 | 12075586793779448 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7ff930a16700 | 0x7ff824e365c0 | 12075586793799184 | 12075586793811858 | 12075586794060976 | 12075586794086569 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7ff930a16600 | 0x7ff824e36600 | 12075586794107197 | 12075586794120175 | 12075586794246094 | 12075586794248720 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7ff930a16500 | 0x7ff824e36640 | 12075586794272364 | 12075586794283374 | 12075586794456492 | 12075586794459031 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7ff930a16400 | 0x7ff824e36680 | 12075586794494897 | 12075586794506412 | 12075586794633131 | 12075586794635669 |
| 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 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7ff930a16300 | 0x7ff824e366c0 | 12075586794660846 | 12075586794673930 | 12075586794927368 | 12075586794950484 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7ff930a16a00 | 0x7ff824e36700 | 12075586794969489 | 12075586794980807 | 12075586795226085 | 12075586795250602 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7ff930a16900 | 0x7ff824e36740 | 12075586795272853 | 12075586795284004 | 12075586795409923 | 12075586795412373 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7ff930a16800 | 0x7ff824e36780 | 12075586795436147 | 12075586795447363 | 12075586795630081 | 12075586795632602 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7ff930a16700 | 0x7ff824e367c0 | 12075586795667076 | 12075586795678080 | 12075586795803839 | 12075586795806615 |
| 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 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7ff930a16600 | 0x7ff824e36800 | 12075586795831251 | 12075586795844639 | 12075586796107836 | 12075586796140015 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7ff930a16500 | 0x7ff824e36840 | 12075586796160152 | 12075586796172156 | 12075586796417273 | 12075586796446655 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7ff930a16400 | 0x7ff824e36880 | 12075586796470188 | 12075586796481113 | 12075586796607032 | 12075586796609527 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7ff930a16300 | 0x7ff824e368c0 | 12075586796634193 | 12075586796647031 | 12075586796837909 | 12075586796840326 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7ff930a16a00 | 0x7ff824e36900 | 12075586796875201 | 12075586796886389 | 12075586797013908 | 12075586797017165 |
| 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 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7ff930a16900 | 0x7ff824e36940 | 12075586797041791 | 12075586797053267 | 12075586797335664 | 12075586797359742 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7ff930a16800 | 0x7ff824e36980 | 12075586797379548 | 12075586797392304 | 12075586797640462 | 12075586797663396 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7ff930a16700 | 0x7ff824e369c0 | 12075586797683163 | 12075586797694701 | 12075586797820460 | 12075586797823023 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7ff930a16600 | 0x7ff824e36a00 | 12075586797849221 | 12075586797862219 | 12075586798071497 | 12075586798095870 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7ff930a16500 | 0x7ff824e36a40 | 12075586798127478 | 12075586798140137 | 12075586798267656 | 12075586798270214 |
| 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 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7ff930a16400 | 0x7ff824e36a80 | 12075586798295721 | 12075586798308615 | 12075586798614692 | 12075586798637737 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7ff930a16300 | 0x7ff824e36ac0 | 12075586798659177 | 12075586798671652 | 12075586798920289 | 12075586798943214 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7ff930a16a00 | 0x7ff824e36b00 | 12075586798964474 | 12075586798976129 | 12075586799104447 | 12075586799107470 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7ff930a16900 | 0x7ff824e36b40 | 12075586799134320 | 12075586799148287 | 12075586799375965 | 12075586799398741 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7ff930a16800 | 0x7ff824e36b80 | 12075586799428406 | 12075586799440284 | 12075586799567003 | 12075586799569558 |
| 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 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7ff930a16700 | 0x7ff824e36bc0 | 12075586799593523 | 12075586799605083 | 12075586799963959 | 12075586799986634 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7ff930a16600 | 0x7ff824e36c00 | 12075586800013313 | 12075586800024759 | 12075586800275796 | 12075586800302491 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7ff930a16500 | 0x7ff824e36c40 | 12075586800325083 | 12075586800337236 | 12075586800467474 | 12075586800469982 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7ff930a16400 | 0x7ff824e36c80 | 12075586800493976 | 12075586800505234 | 12075586800749072 | 12075586800772284 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7ff930a16300 | 0x7ff824e36cc0 | 12075586800801498 | 12075586800814031 | 12075586800942030 | 12075586800944884 |
| 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 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7ff930a16a00 | 0x7ff824e36d00 | 12075586800969831 | 12075586800982989 | 12075586801358346 | 12075586801383389 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7ff930a16900 | 0x7ff824e36d40 | 12075586801404529 | 12075586801415465 | 12075586801670503 | 12075586801693015 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7ff930a16800 | 0x7ff824e36d80 | 12075586801714495 | 12075586801725862 | 12075586801855461 | 12075586801857971 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7ff930a16700 | 0x7ff824e36dc0 | 12075586801882727 | 12075586801896261 | 12075586802174178 | 12075586802198855 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7ff930a16600 | 0x7ff824e36e00 | 12075586802231936 | 12075586802244897 | 12075586802379776 | 12075586802382616 |
| 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 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7ff930a16500 | 0x7ff824e36e40 | 12075586802406471 | 12075586802419615 | 12075586802842171 | 12075586802864762 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7ff930a16400 | 0x7ff824e36e80 | 12075586802884950 | 12075586802896091 | 12075586803150648 | 12075586803179998 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7ff930a16300 | 0x7ff824e36ec0 | 12075586803199775 | 12075586803211608 | 12075586803346327 | 12075586803348972 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7ff930a16a00 | 0x7ff824e36f00 | 12075586803372927 | 12075586803384246 | 12075586803698163 | 12075586803725702 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7ff930a16900 | 0x7ff824e36f40 | 12075586803755468 | 12075586803766482 | 12075586803917681 | 12075586803920314 |
| 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 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7ff930a16800 | 0x7ff824e36f80 | 12075586803944880 | 12075586803956721 | 12075586804472716 | 12075586804501334 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7ff930a16700 | 0x7ff824e36fc0 | 12075586804521782 | 12075586804533035 | 12075586804829992 | 12075586804857075 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7ff930a16600 | 0x7ff824e37000 | 12075586804880058 | 12075586804891112 | 12075586805045350 | 12075586805048260 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7ff930a16500 | 0x7ff824e37040 | 12075586805073267 | 12075586805084230 | 12075586805469506 | 12075586805500260 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7ff930a16400 | 0x7ff824e37080 | 12075586805531949 | 12075586805543265 | 12075586805719104 | 12075586805721822 |
| 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 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7ff930a16300 | 0x7ff824e370c0 | 12075586805746478 | 12075586805757983 | 12075586806367577 | 12075586806396616 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7ff930a16a00 | 0x7ff824e37100 | 12075586806418818 | 12075586806429977 | 12075586806757494 | 12075586806785489 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7ff930a16900 | 0x7ff824e37140 | 12075586806805947 | 12075586806817173 | 12075586806994931 | 12075586806997583 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7ff930a16800 | 0x7ff824e37180 | 12075586807024563 | 12075586807036051 | 12075586807492207 | 12075586807520445 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7ff930a16700 | 0x7ff824e371c0 | 12075586807552545 | 12075586807563726 | 12075586807762284 | 12075586807788934 |
| 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 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7ff930a16600 | 0x7ff824e37200 | 12075586807806146 | 12075586807817323 | 12075586808519397 | 12075586808552673 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7ff930a16500 | 0x7ff824e37240 | 12075586808573883 | 12075586808584996 | 12075586808957632 | 12075586808984255 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7ff930a16400 | 0x7ff824e37280 | 12075586809010925 | 12075586809023232 | 12075586809225950 | 12075586809256962 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7ff930a16300 | 0x7ff824e372c0 | 12075586809275577 | 12075586809288029 | 12075586809812824 | 12075586809839595 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7ff930a16a00 | 0x7ff824e37300 | 12075586809871945 | 12075586809883704 | 12075586810108661 | 12075586810137438 |
| 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 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7ff930a16900 | 0x7ff824e37340 | 12075586810159529 | 12075586810170581 | 12075586810968973 | 12075586810995693 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7ff930a16800 | 0x7ff824e37380 | 12075586811023255 | 12075586811035532 | 12075586811454088 | 12075586811482588 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7ff930a16700 | 0x7ff824e373c0 | 12075586811506102 | 12075586811517608 | 12075586811742406 | 12075586811769221 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7ff930a16600 | 0x7ff824e37400 | 12075586811792715 | 12075586811804325 | 12075586812413439 | 12075586812441871 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7ff930a16500 | 0x7ff824e37440 | 12075586812472258 | 12075586812485278 | 12075586812753276 | 12075586812780200 |
| 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 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7ff930a16400 | 0x7ff824e37480 | 12075586812800708 | 12075586812812955 | 12075586813797266 | 12075586813825643 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7ff930a16300 | 0x7ff824e374c0 | 12075586813844899 | 12075586813855665 | 12075586814386700 | 12075586814418775 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7ff930a16a00 | 0x7ff824e37500 | 12075586814441838 | 12075586814455019 | 12075586814725577 | 12075586814752475 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7ff930a16900 | 0x7ff824e37540 | 12075586814773604 | 12075586814786376 | 12075586815523649 | 12075586815552312 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7ff930a16800 | 0x7ff824e37580 | 12075586815584151 | 12075586815596768 | 12075586815911485 | 12075586815938419 |
| 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 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7ff930a16700 | 0x7ff824e375c0 | 12075586815959909 | 12075586815972925 | 12075586817144274 | 12075586817173454 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7ff930a16600 | 0x7ff824e37600 | 12075586817194323 | 12075586817205713 | 12075586817814187 | 12075586817840985 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7ff930a16500 | 0x7ff824e37640 | 12075586817864379 | 12075586817875466 | 12075586818194343 | 12075586818229537 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7ff930a16400 | 0x7ff824e37680 | 12075586818251328 | 12075586818263143 | 12075586819140734 | 12075586819171648 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7ff930a16300 | 0x7ff824e376c0 | 12075586819202786 | 12075586819213694 | 12075586819622170 | 12075586819651350 |
| 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 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7ff930a16a00 | 0x7ff824e37700 | 12075586819673120 | 12075586819684569 | 12075586821233514 | 12075586821305794 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7ff930a16900 | 0x7ff824e37740 | 12075586821328356 | 12075586821338793 | 12075586822133025 | 12075586822205486 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7ff930a16800 | 0x7ff824e37780 | 12075586822232366 | 12075586822244232 | 12075586822658148 | 12075586822734169 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7ff930a16700 | 0x7ff824e377c0 | 12075586822754386 | 12075586822765986 | 12075586823924697 | 12075586823996775 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7ff930a16600 | 0x7ff824e37800 | 12075586824036219 | 12075586824047896 | 12075586824833009 | 12075586824907077 |
| 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 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7ff930a16500 | 0x7ff824e37840 | 12075586824927114 | 12075586824938928 | 12075586827993303 | 12075586828065647 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7ff930a16400 | 0x7ff824e37880 | 12075586828088980 | 12075586828102583 | 12075586829646570 | 12075586829718268 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7ff930a16300 | 0x7ff824e378c0 | 12075586829740550 | 12075586829752169 | 12075586830541283 | 12075586830613061 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7ff930a16a00 | 0x7ff824e37900 | 12075586830635583 | 12075586830646882 | 12075586832928463 | 12075586833000027 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7ff930a16900 | 0x7ff824e37940 | 12075586833040242 | 12075586833052302 | 12075586834587650 | 12075586834662166 |
| 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 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7ff930a16800 | 0x7ff824e37980 | 12075586834682444 | 12075586834693889 | 12075586840750159 | 12075586840822084 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7ff930a16700 | 0x7ff824e379c0 | 12075586840844165 | 12075586840855278 | 12075586843898773 | 12075586843972840 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7ff930a16600 | 0x7ff824e37a00 | 12075586843993879 | 12075586844005813 | 12075586845544840 | 12075586845617056 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 883441 | 883446 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7ff930a16500 | 0x7ff824e37a40 | 12075586845636993 | 12075586845648999 | 12075586850175522 | 12075586850247371 |