37 KiB
37 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_fillBufferAligned.kd | 0 | 0 | 0 | 62337 | 62337 | 33554432 | 256 | 0 | 0 | 4 | 32 | 4160 | 0x0 | 0x7f3277004280 | 14711872586034 | 14711872611205 | 14711872849605 | 14711872938945 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 62337 | 62337 | 32768 | 256 | 0 | 0 | 12 | 24 | 13888 | 0x0 | 0x7f3277023f80 | 14711877626503 | 14711877642252 | 14711877655692 | 14711877675622 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 5 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 14336 | 0x7f3279f96380 | 0x7f3277023fc0 | 14711877678932 | 14711877726572 | 14711877819372 | 14711877821588 |
| 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 | 8 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15040 | 0x7f3279f96200 | 0x7f3277024000 | 14711877844557 | 14711877854092 | 14711878033452 | 14711878035592 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 11 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15488 | 0x7f3279f96080 | 0x7f3277024040 | 14711878051642 | 14711878059692 | 14711878239053 | 14711878241197 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 14 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 15936 | 0x7f32777fdf00 | 0x7f3277024080 | 14711878256737 | 14711878264973 | 14711878358093 | 14711878360254 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 17 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 16384 | 0x7f32777fdd80 | 0x7f32770240c0 | 14711878376474 | 14711878384333 | 14711878476653 | 14711878478631 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 20 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 17088 | 0x7f32777fdc00 | 0x7f3277024100 | 14711878506410 | 14711878516813 | 14711878609453 | 14711878611357 |
| 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 | 23 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 16 | 24 | 17792 | 0x7f32777fda80 | 0x7f3277024140 | 14711878631087 | 14711878641453 | 14711878821933 | 14711878823932 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 26 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 16 | 24 | 18496 | 0x7f32777fd900 | 0x7f3277024180 | 14711878844231 | 14711878854734 | 14711879035854 | 14711879038016 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 29 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19200 | 0x7f32777fd780 | 0x7f32770241c0 | 14711879055676 | 14711879075854 | 14711879169774 | 14711879172023 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 32 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19904 | 0x7f32777fd600 | 0x7f3277024200 | 14711879190132 | 14711879198734 | 14711879292014 | 14711879294140 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 35 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 20608 | 0x7f3279f96480 | 0x7f3277024240 | 14711879314439 | 14711879324334 | 14711879418094 | 14711879420176 |
| 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 | 38 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 16 | 24 | 21312 | 0x7f3279f96300 | 0x7f3277024280 | 14711879437956 | 14711879446094 | 14711879625455 | 14711879627421 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 41 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22016 | 0x7f3279f96180 | 0x7f32770242c0 | 14711879650820 | 14711879661295 | 14711879840975 | 14711879842965 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 44 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22720 | 0x7f3279f96000 | 0x7f3277024300 | 14711879860665 | 14711879870575 | 14711879964015 | 14711879966012 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 47 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 23424 | 0x7f32777fde80 | 0x7f3277024340 | 14711879984572 | 14711879994415 | 14711880088335 | 14711880090339 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 50 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 24128 | 0x7f32777fdd00 | 0x7f3277024380 | 14711880112298 | 14711880122255 | 14711880215536 | 14711880217626 |
| 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 | 53 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 16 | 24 | 24832 | 0x7f32777fdb80 | 0x7f32770243c0 | 14711880236535 | 14711880247376 | 14711880427376 | 14711880429490 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 56 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 16 | 24 | 25536 | 0x7f32777fda00 | 0x7f3277024400 | 14711880449300 | 14711880459536 | 14711880640496 | 14711880642565 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 59 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26240 | 0x7f32777fd880 | 0x7f3277024440 | 14711880659864 | 14711880668656 | 14711880762256 | 14711880764311 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 62 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26944 | 0x7f32777fd700 | 0x7f3277024480 | 14711880784551 | 14711880792976 | 14711880887217 | 14711880889168 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 65 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 27648 | 0x7f3279f96580 | 0x7f32770244c0 | 14711880911078 | 14711880921297 | 14711881013937 | 14711881015925 |
| 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 | 68 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 16 | 24 | 28608 | 0x7f3279f96400 | 0x7f3277024500 | 14711881034274 | 14711881042897 | 14711881223217 | 14711881225369 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 71 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 16 | 24 | 29312 | 0x7f3279f96280 | 0x7f3277024540 | 14711881239199 | 14711881253297 | 14711881435057 | 14711881437084 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 74 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 30016 | 0x7f3279f96100 | 0x7f3277024580 | 14711881456313 | 14711881467857 | 14711881560018 | 14711881562021 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 77 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 8 | 24 | 30976 | 0x7f32777fdf80 | 0x7f32770245c0 | 14711881578390 | 14711881606418 | 14711881698578 | 14711881700737 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 80 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 31680 | 0x7f32777fde00 | 0x7f3277024600 | 14711881723706 | 14711881733938 | 14711881825938 | 14711881827984 |
| 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 | 83 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 16 | 24 | 32640 | 0x7f32777fdc80 | 0x7f3277024640 | 14711881848413 | 14711881863698 | 14711882043698 | 14711882045858 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 86 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 33600 | 0x7f32777fdb00 | 0x7f3277024680 | 14711882063428 | 14711882072178 | 14711882253619 | 14711882255883 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 89 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 34560 | 0x7f32777fd980 | 0x7f32770246c0 | 14711882269922 | 14711882279859 | 14711882373779 | 14711882375869 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 92 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 8 | 24 | 35520 | 0x7f32777fd800 | 0x7f3277024700 | 14711882392729 | 14711882403059 | 14711882496979 | 14711882498906 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 95 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 36224 | 0x7f32777fd680 | 0x7f3277024740 | 14711882521506 | 14711882531059 | 14711882624979 | 14711882626593 |
| 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 | 98 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 37184 | 0x7f3279f96500 | 0x7f3277024780 | 14711882641763 | 14711882649779 | 14711882830420 | 14711882832028 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 101 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 38144 | 0x7f3279f96380 | 0x7f32770247c0 | 14711882846697 | 14711882855220 | 14711883036340 | 14711883037672 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 104 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 39104 | 0x7f3279f96200 | 0x7f3277024800 | 14711883051802 | 14711883060020 | 14711883153300 | 14711883154909 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 107 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 8 | 24 | 40320 | 0x7f3279f96080 | 0x7f3277024840 | 14711883170079 | 14711883178100 | 14711883271860 | 14711883273356 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 110 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 41280 | 0x7f32777fdf00 | 0x7f3277024880 | 14711883294296 | 14711883305140 | 14711883398900 | 14711883400463 |
| 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 | 113 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 42240 | 0x7f32777fdd80 | 0x7f32770248c0 | 14711883415412 | 14711883423700 | 14711883603061 | 14711883604608 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 116 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 43200 | 0x7f32777fdc00 | 0x7f3277024900 | 14711883619397 | 14711883627541 | 14711883808341 | 14711883809872 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 119 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 8 | 24 | 44160 | 0x7f32777fda80 | 0x7f3277024940 | 14711883825832 | 14711883835381 | 14711883929621 | 14711883931059 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 122 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 45376 | 0x7f32777fd900 | 0x7f3277024980 | 14711883946839 | 14711883954581 | 14711884049781 | 14711884051306 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 125 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 46336 | 0x7f32777fd780 | 0x7f32770249c0 | 14711884071375 | 14711884081781 | 14711884175062 | 14711884176593 |
| 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 | 128 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 47552 | 0x7f32777fd600 | 0x7f3277024a00 | 14711884192052 | 14711884200182 | 14711884379222 | 14711884380707 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 131 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 48512 | 0x7f3279f96480 | 0x7f3277024a40 | 14711884396417 | 14711884411542 | 14711884590582 | 14711884592232 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 134 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 8 | 24 | 49472 | 0x7f3279f96300 | 0x7f3277024a80 | 14711884605991 | 14711884614262 | 14711884707062 | 14711884708519 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 137 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 50688 | 0x7f3279f96180 | 0x7f3277024ac0 | 14711884723228 | 14711884732342 | 14711884826103 | 14711884827956 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 140 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 51648 | 0x7f3279f96000 | 0x7f3277024b00 | 14711884849865 | 14711884860663 | 14711884952663 | 14711884954152 |
| 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 | 143 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 52864 | 0x7f32777fde80 | 0x7f3277024b40 | 14711884972512 | 14711884980183 | 14711885160183 | 14711885161747 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 146 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 54080 | 0x7f32777fdd00 | 0x7f3277024b80 | 14711885178397 | 14711885186743 | 14711885366903 | 14711885368492 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 149 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 8 | 24 | 55296 | 0x7f32777fdb80 | 0x7f3277024bc0 | 14711885385221 | 14711885392823 | 14711885486264 | 14711885487749 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 152 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 56768 | 0x7f32777fda00 | 0x7f3277024c00 | 14711885503098 | 14711885511704 | 14711885606744 | 14711885608325 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 155 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 57728 | 0x7f32777fd880 | 0x7f3277024c40 | 14711885628525 | 14711885639384 | 14711885732024 | 14711885733552 |
| 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 | 158 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 58944 | 0x7f32777fd700 | 0x7f3277024c80 | 14711885749352 | 14711885757304 | 14711885937464 | 14711885939097 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 161 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 60160 | 0x7f3279f96580 | 0x7f3277024cc0 | 14711885954506 | 14711885962424 | 14711886144665 | 14711886146221 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 164 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 8 | 24 | 61376 | 0x7f3279f96400 | 0x7f3277024d00 | 14711886161161 | 14711886169145 | 14711886263545 | 14711886265138 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 167 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 62848 | 0x7f3279f96280 | 0x7f3277024d40 | 14711886280268 | 14711886288025 | 14711886387705 | 14711886389445 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 170 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 63808 | 0x7f3279f96100 | 0x7f3277024d80 | 14711886409585 | 14711886420185 | 14711886514585 | 14711886516082 |
| 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 | 173 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 65024 | 0x7f32777fdf80 | 0x7f3277024dc0 | 14711886535511 | 14711886546585 | 14711886725945 | 14711886727396 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 176 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 66240 | 0x7f32777fde00 | 0x7f3277024e00 | 14711886742136 | 14711886750266 | 14711886931226 | 14711886932681 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 179 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 8 | 24 | 67456 | 0x7f32777fdc80 | 0x7f3277024e40 | 14711886947081 | 14711886955386 | 14711887050106 | 14711887051598 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 182 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 68928 | 0x7f32777fdb00 | 0x7f3277024e80 | 14711887065757 | 14711887076026 | 14711887179066 | 14711887180565 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 185 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 70144 | 0x7f32777fd980 | 0x7f3277024ec0 | 14711887200964 | 14711887211546 | 14711887304506 | 14711887305961 |
| 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 | 188 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 71616 | 0x7f32777fd800 | 0x7f3277024f00 | 14711887319971 | 14711887328026 | 14711887508027 | 14711887509466 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 191 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 72832 | 0x7f32777fd680 | 0x7f3277024f40 | 14711887526326 | 14711887534587 | 14711887714747 | 14711887716291 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 194 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 8 | 24 | 74048 | 0x7f3279f96500 | 0x7f3277024f80 | 14711887730930 | 14711887739387 | 14711887832987 | 14711887834487 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 197 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 75776 | 0x7f3279f96380 | 0x7f3277024fc0 | 14711887848367 | 14711887856827 | 14711887964347 | 14711887965794 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 200 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 76992 | 0x7f3279f96200 | 0x7f3277025000 | 14711887984904 | 14711887996347 | 14711888090908 | 14711888092451 |
| 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 | 203 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 78464 | 0x7f3279f96080 | 0x7f3277025040 | 14711888107650 | 14711888115548 | 14711888295228 | 14711888296845 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 206 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 79936 | 0x7f32777fdf00 | 0x7f3277025080 | 14711888313465 | 14711888321148 | 14711888500508 | 14711888502130 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 209 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 8 | 24 | 81408 | 0x7f32777fdd80 | 0x7f32770250c0 | 14711888518280 | 14711888527068 | 14711888622428 | 14711888624127 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 212 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 83136 | 0x7f32777fdc00 | 0x7f3277025100 | 14711888638497 | 14711888646748 | 14711888762909 | 14711888764523 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 215 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 84352 | 0x7f32777fda80 | 0x7f3277025140 | 14711888799262 | 14711888808829 | 14711888902429 | 14711888903810 |
| 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 | 218 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 85824 | 0x7f32777fd900 | 0x7f3277025180 | 14711888918809 | 14711888926909 | 14711889107229 | 14711889108824 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 221 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 87296 | 0x7f32777fd780 | 0x7f32770251c0 | 14711889122284 | 14711889130269 | 14711889309629 | 14711889311259 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 224 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 88768 | 0x7f32777fd600 | 0x7f3277025200 | 14711889327999 | 14711889337309 | 14711889432670 | 14711889434236 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 227 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 90752 | 0x7f3279f96480 | 0x7f3277025240 | 14711889449015 | 14711889457790 | 14711889578430 | 14711889580042 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 230 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 91968 | 0x7f3279f96300 | 0x7f3277025280 | 14711889601802 | 14711889612190 | 14711889706910 | 14711889708549 |
| 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 | 233 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 93440 | 0x7f3279f96180 | 0x7f32770252c0 | 14711889723498 | 14711889732510 | 14711889912350 | 14711889913893 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 236 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 94912 | 0x7f3279f96000 | 0x7f3277025300 | 14711889928563 | 14711889936670 | 14711890115391 | 14711890116958 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 239 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 96384 | 0x7f32777fde80 | 0x7f3277025340 | 14711890132978 | 14711890141311 | 14711890236671 | 14711890238125 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 242 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 98368 | 0x7f32777fdd00 | 0x7f3277025380 | 14711890253515 | 14711890261631 | 14711890387551 | 14711890389021 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 245 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 99584 | 0x7f32777fdb80 | 0x7f32770253c0 | 14711890409251 | 14711890419711 | 14711890514591 | 14711890516218 |
| 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 | 248 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 101312 | 0x7f32777fda00 | 0x7f3277025400 | 14711890533227 | 14711890541471 | 14711890721632 | 14711890723232 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 251 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 102784 | 0x7f32777fd880 | 0x7f3277025440 | 14711890738182 | 14711890746752 | 14711890927392 | 14711890928997 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 254 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 104256 | 0x7f32777fd700 | 0x7f3277025480 | 14711890942777 | 14711890950752 | 14711891044672 | 14711891046134 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 257 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 106240 | 0x7f3279f96580 | 0x7f32770254c0 | 14711891060854 | 14711891069152 | 14711891199552 | 14711891201280 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 260 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 107712 | 0x7f3279f96400 | 0x7f3277025500 | 14711891222639 | 14711891232992 | 14711891326113 | 14711891327717 |
| 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 | 263 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 16 | 24 | 109440 | 0x7f3279f96280 | 0x7f3277025540 | 14711891343486 | 14711891352673 | 14711891531873 | 14711891533401 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 266 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 16 | 24 | 111168 | 0x7f3279f96100 | 0x7f3277025580 | 14711891548251 | 14711891556513 | 14711891735233 | 14711891736786 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 269 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 8 | 24 | 112896 | 0x7f32777fdf80 | 0x7f32770255c0 | 14711891753316 | 14711891760833 | 14711891856993 | 14711891858493 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 272 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 115136 | 0x7f32777fde00 | 0x7f3277025600 | 14711891875062 | 14711891882913 | 14711892021474 | 14711892022949 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 275 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 116608 | 0x7f32777fdc80 | 0x7f3277025640 | 14711892044998 | 14711892055554 | 14711892150114 | 14711892151625 |
| 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 | 278 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 16 | 24 | 118336 | 0x7f32777fdb00 | 0x7f3277025680 | 14711892169055 | 14711892176994 | 14711892357314 | 14711892358890 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 281 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 16 | 24 | 120064 | 0x7f32777fd980 | 0x7f32770256c0 | 14711892373139 | 14711892381954 | 14711892563714 | 14711892565244 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 284 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 121792 | 0x7f32777fd800 | 0x7f3277025700 | 14711892579974 | 14711892587714 | 14711892685155 | 14711892686731 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 287 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 124032 | 0x7f32777fd680 | 0x7f3277025740 | 14711892702741 | 14711892710595 | 14711892855555 | 14711892857127 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 290 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 125504 | 0x7f3279f96500 | 0x7f3277025780 | 14711892877586 | 14711892888035 | 14711892983555 | 14711892985054 |
| 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 | 293 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 127488 | 0x7f3279f96380 | 0x7f32770257c0 | 14711893000813 | 14711893008995 | 14711893190435 | 14711893192008 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 296 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 129216 | 0x7f3279f96200 | 0x7f3277025800 | 14711893207278 | 14711893215875 | 14711893397956 | 14711893399573 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 299 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 130944 | 0x7f3279f96080 | 0x7f3277025840 | 14711893414892 | 14711893424356 | 14711893525156 | 14711893526659 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 302 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 133440 | 0x7f32777fdf00 | 0x7f3277025880 | 14711893541319 | 14711893549476 | 14711893704996 | 14711893706495 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 305 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 134912 | 0x7f32777fdd80 | 0x7f32770258c0 | 14711893726984 | 14711893737636 | 14711893833156 | 14711893834671 |
| 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 | 308 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 136896 | 0x7f32777fdc00 | 0x7f3277025900 | 14711893850371 | 14711893858276 | 14711894037797 | 14711894039316 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 311 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 138880 | 0x7f32777fda80 | 0x7f3277025940 | 14711894054566 | 14711894062437 | 14711894243717 | 14711894245271 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 314 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 140864 | 0x7f32777fd900 | 0x7f3277025980 | 14711894260730 | 14711894268357 | 14711894376517 | 14711894378187 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 317 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 143616 | 0x7f32777fd780 | 0x7f32770259c0 | 14711894391717 | 14711894400357 | 14711894571557 | 14711894573322 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 320 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 145344 | 0x7f32777fd600 | 0x7f3277025a00 | 14711894593232 | 14711894603877 | 14711894699558 | 14711894701189 |
| 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 | 323 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 147584 | 0x7f3279f96480 | 0x7f3277025a40 | 14711894716319 | 14711894724678 | 14711894906118 | 14711894907764 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 326 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 149568 | 0x7f3279f96300 | 0x7f3277025a80 | 14711894922113 | 14711894930278 | 14711895113638 | 14711895115278 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 329 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 151552 | 0x7f3279f96180 | 0x7f3277025ac0 | 14711895128718 | 14711895136678 | 14711895247878 | 14711895249485 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 332 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 154304 | 0x7f3279f96000 | 0x7f3277025b00 | 14711895263634 | 14711895271559 | 14711895452359 | 14711895454060 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 335 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 156288 | 0x7f32777fde80 | 0x7f3277025b40 | 14711895474959 | 14711895484519 | 14711895584839 | 14711895586406 |
| 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 | 338 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 158784 | 0x7f32777fdd00 | 0x7f3277025b80 | 14711895602106 | 14711895610119 | 14711895796679 | 14711895798301 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 341 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 161024 | 0x7f32777fdb80 | 0x7f3277025bc0 | 14711895813590 | 14711895821479 | 14711896007240 | 14711896008885 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 344 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 163264 | 0x7f32777fda00 | 0x7f3277025c00 | 14711896023745 | 14711896031880 | 14711896154600 | 14711896156301 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 347 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 166528 | 0x7f32777fd880 | 0x7f3277025c40 | 14711896171121 | 14711896179080 | 14711896385960 | 14711896430664 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 350 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 168512 | 0x7f32777fd700 | 0x7f3277025c80 | 14711896446574 | 14711896457000 | 14711896567560 | 14711896569171 |
| 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 | 353 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 171264 | 0x7f3279f96580 | 0x7f3277025cc0 | 14711896584630 | 14711896593321 | 14711896775401 | 14711896776895 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 356 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 173760 | 0x7f3279f96400 | 0x7f3277025d00 | 14711896790655 | 14711896798761 | 14711896985161 | 14711896986600 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 359 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 176256 | 0x7f3279f96280 | 0x7f3277025d40 | 14711897001390 | 14711897009641 | 14711897144201 | 14711897145696 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 362 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 179776 | 0x7f3279f96100 | 0x7f3277025d80 | 14711897160095 | 14711897168041 | 14711897400362 | 14711897420799 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 365 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 182272 | 0x7f32777fdf80 | 0x7f3277025dc0 | 14711897436418 | 14711897447402 | 14711897574122 | 14711897575635 |
| 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 | 368 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 185536 | 0x7f32777fde00 | 0x7f3277025e00 | 14711897590374 | 14711897598282 | 14711897789322 | 14711897790889 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 371 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 188544 | 0x7f32777fdc80 | 0x7f3277025e40 | 14711897804879 | 14711897813322 | 14711898008523 | 14711898010013 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 374 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 191552 | 0x7f32777fdb00 | 0x7f3277025e80 | 14711898025443 | 14711898033483 | 14711898193963 | 14711898195999 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 377 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 195840 | 0x7f32777fd980 | 0x7f3277025ec0 | 14711898210888 | 14711898219243 | 14711898502763 | 14711898549049 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 380 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 198592 | 0x7f32777fd800 | 0x7f3277025f00 | 14711898565719 | 14711898576364 | 14711898724844 | 14711898726435 |
| 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 | 383 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 202368 | 0x7f32777fd680 | 0x7f3277025f40 | 14711898743144 | 14711898750604 | 14711898959884 | 14711899003288 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 386 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 205888 | 0x7f3279f96500 | 0x7f3277025f80 | 14711899011467 | 14711899021644 | 14711899229805 | 14711899273441 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 389 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 209408 | 0x7f3279f96380 | 0x7f3277025fc0 | 14711899282220 | 14711899292525 | 14711899477965 | 14711899479485 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 392 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 214464 | 0x7f3279f96200 | 0x7f3277026000 | 14711899494065 | 14711899501805 | 14711899836685 | 14711899877165 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 395 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 217728 | 0x7f3279f96080 | 0x7f3277026040 | 14711899892914 | 14711899903406 | 14711900071246 | 14711900072840 |
| 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 | 398 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 222016 | 0x7f32777fdf00 | 0x7f3277026080 | 14711900088029 | 14711900096046 | 14711900324686 | 14711900365192 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 401 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 226048 | 0x7f32777fdd80 | 0x7f32770260c0 | 14711900373352 | 14711900383406 | 14711900611727 | 14711900651875 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 404 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 230080 | 0x7f32777fdc00 | 0x7f3277026100 | 14711900660655 | 14711900670607 | 14711900881807 | 14711900898058 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 407 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 235904 | 0x7f32777fda80 | 0x7f3277026140 | 14711900907658 | 14711900916367 | 14711901302128 | 14711901318467 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 410 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 239424 | 0x7f32777fd900 | 0x7f3277026180 | 14711901336087 | 14711901346608 | 14711901534128 | 14711901535642 |
| 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 | 413 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 244224 | 0x7f32777fd780 | 0x7f32770261c0 | 14711901551511 | 14711901559248 | 14711901809008 | 14711901824424 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 416 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 248768 | 0x7f32777fd600 | 0x7f3277026200 | 14711901832744 | 14711901842929 | 14711902091089 | 14711902117367 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 419 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 253312 | 0x7f3279f96480 | 0x7f3277026240 | 14711902126566 | 14711902136689 | 14711902373969 | 14711902393659 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 422 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 8 | 24 | 255552 | 0x7f3279f96300 | 0x7f3277026280 | 14711902403989 | 14711902413969 | 14711902868370 | 14711902887387 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 425 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 259840 | 0x7f3279f96180 | 0x7f32770262c0 | 14711902905416 | 14711902915730 | 14711903141490 | 14711903184819 |
| 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 | 428 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 265664 | 0x7f3279f96000 | 0x7f3277026300 | 14711903193279 | 14711903203411 | 14711903501971 | 14711903545929 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 431 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 271232 | 0x7f32777fde80 | 0x7f3277026340 | 14711903556639 | 14711903565811 | 14711903863892 | 14711903907430 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 434 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 8 | 24 | 273216 | 0x7f32777fdd00 | 0x7f3277026380 | 14711903921540 | 14711903932052 | 14711904228372 | 14711904271791 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 437 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 8 | 24 | 275712 | 0x7f32777fdb80 | 0x7f32770263c0 | 14711904282730 | 14711904293012 | 14711904851093 | 14711904894534 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 440 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 280768 | 0x7f32777fda00 | 0x7f3277026400 | 14711904910884 | 14711904921813 | 14711905185334 | 14711905205756 |
| 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 | 443 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 287616 | 0x7f32777fd880 | 0x7f3277026440 | 14711905216136 | 14711905226134 | 14711905576854 | 14711905593166 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 446 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 294208 | 0x7f32777fd700 | 0x7f3277026480 | 14711905602006 | 14711905612534 | 14711905963095 | 14711905979086 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 449 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 8 | 24 | 296960 | 0x7f3279f96580 | 0x7f32770264c0 | 14711905988966 | 14711905999415 | 14711906346775 | 14711906363516 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 452 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 8 | 24 | 299968 | 0x7f3279f96400 | 0x7f3277026500 | 14711906373126 | 14711906383255 | 14711907045176 | 14711907090647 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 455 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 8 | 24 | 302720 | 0x7f3279f96280 | 0x7f3277026540 | 14711907108157 | 14711907117657 | 14711907565497 | 14711907610224 |
| 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 | 458 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 305472 | 0x7f3279f96100 | 0x7f3277026580 | 14711907619234 | 14711907629017 | 14711908092698 | 14711908136210 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 461 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 308224 | 0x7f32777fdf80 | 0x7f32770265c0 | 14711908145130 | 14711908154938 | 14711908617659 | 14711908661626 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 464 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 8 | 24 | 310976 | 0x7f32777fde00 | 0x7f3277026600 | 14711908669606 | 14711908680219 | 14711909133340 | 14711909176923 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 467 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 8 | 24 | 313216 | 0x7f32777fdc80 | 0x7f3277026640 | 14711909185313 | 14711909195580 | 14711910065341 | 14711910111049 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 470 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 8 | 24 | 315968 | 0x7f32777fdb00 | 0x7f3277026680 | 14711910129958 | 14711910140221 | 14711910993982 | 14711911040255 |
| 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 | 473 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 318720 | 0x7f32777fd980 | 0x7f32770266c0 | 14711911051874 | 14711911062143 | 14711911948064 | 14711911993560 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 476 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 321472 | 0x7f32777fd800 | 0x7f3277026700 | 14711912003419 | 14711912013504 | 14711912892705 | 14711912936805 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 479 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 8 | 24 | 324224 | 0x7f32777fd680 | 0x7f3277026740 | 14711912946615 | 14711912956545 | 14711913817027 | 14711913861461 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 482 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 8 | 24 | 326464 | 0x7f3279f96500 | 0x7f3277026780 | 14711913869751 | 14711913879907 | 14711915579109 | 14711915657064 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 485 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 8 | 24 | 329216 | 0x7f3279f96380 | 0x7f32770267c0 | 14711915678394 | 14711915714790 | 14711917379912 | 14711917449038 |
| 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 | 488 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 331968 | 0x7f3279f96200 | 0x7f3277026800 | 14711917458578 | 14711917468712 | 14711919194635 | 14711919264341 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 491 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 12 | 24 | 334720 | 0x7f3279f96080 | 0x7f3277026840 | 14711919275660 | 14711919285675 | 14711921002318 | 14711921070514 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 494 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 8 | 24 | 337472 | 0x7f32777fdf00 | 0x7f3277026880 | 14711921080533 | 14711921090638 | 14711922764880 | 14711922834008 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 497 | 62337 | 62337 | 4194304 | 256 | 0 | 0 | 8 | 24 | 0 | 0x7f32777fdd80 | 0x7f32770268c0 | 14711922843238 | 14711922853681 | 14711926213206 | 14711926284258 |