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 | 893996 | 894001 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7f407f004180 | 12075800624243814 | 12075800624292466 | 12075800624617742 | 12075800624722904 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 893996 | 894001 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7f407f035100 | 12075800639093611 | 12075800639194481 | 12075800639201361 | 12075800639206802 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7f41af0ba900 | 0x7f407f035140 | 12075800639248890 | 12075800639261520 | 12075800639392399 | 12075800639395683 |
| 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 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7f41af0ba800 | 0x7f407f035180 | 12075800639438733 | 12075800639452878 | 12075800639696716 | 12075800639792871 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7f41af0ba700 | 0x7f407f0351c0 | 12075800639818719 | 12075800639830154 | 12075800640075112 | 12075800640174560 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7f41af0ba600 | 0x7f407f035200 | 12075800640197824 | 12075800640209671 | 12075800640335270 | 12075800640338605 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7f41af0ba500 | 0x7f407f035240 | 12075800640364724 | 12075800640375909 | 12075800640501028 | 12075800640503832 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7f41af0ba400 | 0x7f407f035280 | 12075800640560437 | 12075800640572227 | 12075800640696066 | 12075800640698795 |
| 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 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7f41af0ba300 | 0x7f407f0352c0 | 12075800640725083 | 12075800640736866 | 12075800640984543 | 12075800641081556 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7f41af0baa00 | 0x7f407f035300 | 12075800641103637 | 12075800641116062 | 12075800641359260 | 12075800641456272 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7f41af0ba900 | 0x7f407f035340 | 12075800641477201 | 12075800641489658 | 12075800641614297 | 12075800641617462 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7f41af0ba800 | 0x7f407f035380 | 12075800641643971 | 12075800641655897 | 12075800641780856 | 12075800641783881 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7f41af0ba700 | 0x7f407f0353c0 | 12075800641819918 | 12075800641832215 | 12075800641957014 | 12075800641959928 |
| 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 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7f41af0ba600 | 0x7f407f035400 | 12075800641985656 | 12075800641997334 | 12075800642246771 | 12075800642320248 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7f41af0ba500 | 0x7f407f035440 | 12075800642342028 | 12075800642353650 | 12075800642600368 | 12075800642667323 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7f41af0ba400 | 0x7f407f035480 | 12075800642686298 | 12075800642698287 | 12075800642823086 | 12075800642826008 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7f41af0ba300 | 0x7f407f0354c0 | 12075800642850914 | 12075800642862285 | 12075800642987404 | 12075800642990424 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7f41af0baa00 | 0x7f407f035500 | 12075800643033043 | 12075800643044683 | 12075800643169002 | 12075800643172101 |
| 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 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7f41af0ba900 | 0x7f407f035540 | 12075800643197538 | 12075800643208682 | 12075800643454599 | 12075800643520178 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7f41af0ba800 | 0x7f407f035580 | 12075800643540486 | 12075800643553959 | 12075800643798596 | 12075800643863576 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7f41af0ba700 | 0x7f407f0355c0 | 12075800643883503 | 12075800643897155 | 12075800644021154 | 12075800644024125 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7f41af0ba600 | 0x7f407f035600 | 12075800644051455 | 12075800644063074 | 12075800644188352 | 12075800644191145 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7f41af0ba500 | 0x7f407f035640 | 12075800644227002 | 12075800644238592 | 12075800644362911 | 12075800644366070 |
| 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 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7f41af0ba400 | 0x7f407f035680 | 12075800644391748 | 12075800644403710 | 12075800644650428 | 12075800644715710 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7f41af0ba300 | 0x7f407f0356c0 | 12075800644736669 | 12075800644750107 | 12075800644996185 | 12075800645092961 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7f41af0baa00 | 0x7f407f035700 | 12075800645114010 | 12075800645128183 | 12075800645252022 | 12075800645255162 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7f41af0ba900 | 0x7f407f035740 | 12075800645282203 | 12075800645294262 | 12075800645419220 | 12075800645422303 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7f41af0ba800 | 0x7f407f035780 | 12075800645458039 | 12075800645470420 | 12075800645595219 | 12075800645598050 |
| 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 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7f41af0ba700 | 0x7f407f0357c0 | 12075800645623186 | 12075800645635538 | 12075800645888336 | 12075800645959872 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7f41af0ba600 | 0x7f407f035800 | 12075800645980370 | 12075800645991375 | 12075800646235053 | 12075800646314461 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7f41af0ba500 | 0x7f407f035840 | 12075800646334849 | 12075800646347852 | 12075800646472010 | 12075800646475180 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7f41af0ba400 | 0x7f407f035880 | 12075800646500527 | 12075800646512010 | 12075800646637289 | 12075800646640337 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7f41af0ba300 | 0x7f407f0358c0 | 12075800646675322 | 12075800646690248 | 12075800646814407 | 12075800646817456 |
| 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 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7f41af0baa00 | 0x7f407f035900 | 12075800646842813 | 12075800646855367 | 12075800647103204 | 12075800647183676 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7f41af0ba900 | 0x7f407f035940 | 12075800647209865 | 12075800647221443 | 12075800647465121 | 12075800647542964 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7f41af0ba800 | 0x7f407f035980 | 12075800647566638 | 12075800647578400 | 12075800647703838 | 12075800647707189 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7f41af0ba700 | 0x7f407f0359c0 | 12075800647732126 | 12075800647743198 | 12075800647869437 | 12075800647872436 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7f41af0ba600 | 0x7f407f035a00 | 12075800647907101 | 12075800647919676 | 12075800648044155 | 12075800648047462 |
| 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 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7f41af0ba500 | 0x7f407f035a40 | 12075800648073921 | 12075800648086075 | 12075800648376792 | 12075800648406639 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7f41af0ba400 | 0x7f407f035a80 | 12075800648430524 | 12075800648442871 | 12075800648685909 | 12075800648711386 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7f41af0ba300 | 0x7f407f035ac0 | 12075800648732886 | 12075800648744948 | 12075800648870067 | 12075800648872906 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7f41af0baa00 | 0x7f407f035b00 | 12075800648898804 | 12075800648910067 | 12075800649036306 | 12075800649039315 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7f41af0ba900 | 0x7f407f035b40 | 12075800649075653 | 12075800649086705 | 12075800649211664 | 12075800649214400 |
| 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 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7f41af0ba800 | 0x7f407f035b80 | 12075800649239728 | 12075800649251663 | 12075800649509741 | 12075800649533233 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7f41af0ba700 | 0x7f407f035bc0 | 12075800649552980 | 12075800649565900 | 12075800649809738 | 12075800649833781 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7f41af0ba600 | 0x7f407f035c00 | 12075800649853869 | 12075800649867177 | 12075800649991816 | 12075800649994670 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7f41af0ba500 | 0x7f407f035c40 | 12075800650025137 | 12075800650036136 | 12075800650162695 | 12075800650165588 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7f41af0ba400 | 0x7f407f035c80 | 12075800650201385 | 12075800650213094 | 12075800650337893 | 12075800650340694 |
| 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 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7f41af0ba300 | 0x7f407f035cc0 | 12075800650366071 | 12075800650377573 | 12075800650635010 | 12075800650654797 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7f41af0baa00 | 0x7f407f035d00 | 12075800650677049 | 12075800650689890 | 12075800650933407 | 12075800650956909 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7f41af0ba900 | 0x7f407f035d40 | 12075800650977257 | 12075800650989087 | 12075800651113725 | 12075800651117237 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7f41af0ba800 | 0x7f407f035d80 | 12075800651143275 | 12075800651154685 | 12075800651282364 | 12075800651285149 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7f41af0ba700 | 0x7f407f035dc0 | 12075800651320655 | 12075800651331963 | 12075800651456762 | 12075800651459713 |
| 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 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7f41af0ba600 | 0x7f407f035e00 | 12075800651484850 | 12075800651496442 | 12075800651761399 | 12075800651785298 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7f41af0ba500 | 0x7f407f035e40 | 12075800651805346 | 12075800651816599 | 12075800652060276 | 12075800652088121 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7f41af0ba400 | 0x7f407f035e80 | 12075800652111084 | 12075800652122196 | 12075800652247154 | 12075800652250303 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7f41af0ba300 | 0x7f407f035ec0 | 12075800652277754 | 12075800652288914 | 12075800652417393 | 12075800652420499 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7f41af0baa00 | 0x7f407f035f00 | 12075800652456195 | 12075800652467952 | 12075800652592591 | 12075800652595454 |
| 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 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7f41af0ba900 | 0x7f407f035f40 | 12075800652621032 | 12075800652632431 | 12075800652883308 | 12075800652902475 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7f41af0ba800 | 0x7f407f035f80 | 12075800652923173 | 12075800652934668 | 12075800653181705 | 12075800653205508 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7f41af0ba700 | 0x7f407f035fc0 | 12075800653227068 | 12075800653238665 | 12075800653363784 | 12075800653366717 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7f41af0ba600 | 0x7f407f036000 | 12075800653392054 | 12075800653403143 | 12075800653540102 | 12075800653542985 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7f41af0ba500 | 0x7f407f036040 | 12075800653577499 | 12075800653589702 | 12075800653714500 | 12075800653717409 |
| 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 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7f41af0ba400 | 0x7f407f036080 | 12075800653742556 | 12075800653754180 | 12075800654014657 | 12075800654039428 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7f41af0ba300 | 0x7f407f0360c0 | 12075800654062791 | 12075800654076577 | 12075800654320734 | 12075800654348071 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7f41af0baa00 | 0x7f407f036100 | 12075800654368058 | 12075800654379454 | 12075800654503933 | 12075800654506806 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7f41af0ba900 | 0x7f407f036140 | 12075800654532594 | 12075800654543612 | 12075800654685691 | 12075800654688704 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7f41af0ba800 | 0x7f407f036180 | 12075800654723699 | 12075800654734970 | 12075800654859769 | 12075800654862708 |
| 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 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7f41af0ba700 | 0x7f407f0361c0 | 12075800654888185 | 12075800654899609 | 12075800655151126 | 12075800655182812 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7f41af0ba600 | 0x7f407f036200 | 12075800655202439 | 12075800655213686 | 12075800655458483 | 12075800655484623 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7f41af0ba500 | 0x7f407f036240 | 12075800655507566 | 12075800655518963 | 12075800655644082 | 12075800655647005 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7f41af0ba400 | 0x7f407f036280 | 12075800655673825 | 12075800655684881 | 12075800655834000 | 12075800655836998 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7f41af0ba300 | 0x7f407f0362c0 | 12075800655889095 | 12075800655899919 | 12075800656025198 | 12075800656028354 |
| 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 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7f41af0baa00 | 0x7f407f036300 | 12075800656054332 | 12075800656066318 | 12075800656318795 | 12075800656345363 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7f41af0ba900 | 0x7f407f036340 | 12075800656366432 | 12075800656377835 | 12075800656622152 | 12075800656644769 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7f41af0ba800 | 0x7f407f036380 | 12075800656665097 | 12075800656676552 | 12075800656802310 | 12075800656805198 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7f41af0ba700 | 0x7f407f0363c0 | 12075800656831096 | 12075800656842310 | 12075800656998949 | 12075800657005370 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7f41af0ba600 | 0x7f407f036400 | 12075800657038571 | 12075800657049988 | 12075800657175427 | 12075800657178561 |
| 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 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7f41af0ba500 | 0x7f407f036440 | 12075800657204179 | 12075800657215746 | 12075800657478464 | 12075800657501281 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7f41af0ba400 | 0x7f407f036480 | 12075800657523573 | 12075800657534943 | 12075800657779261 | 12075800657801730 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7f41af0ba300 | 0x7f407f0364c0 | 12075800657821316 | 12075800657832701 | 12075800657958459 | 12075800657961386 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7f41af0baa00 | 0x7f407f036500 | 12075800657986263 | 12075800657997499 | 12075800658163257 | 12075800658166628 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7f41af0ba900 | 0x7f407f036540 | 12075800658202605 | 12075800658213657 | 12075800658339256 | 12075800658342314 |
| 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 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7f41af0ba800 | 0x7f407f036580 | 12075800658366860 | 12075800658378775 | 12075800658632693 | 12075800658659444 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7f41af0ba700 | 0x7f407f0365c0 | 12075800658678910 | 12075800658690132 | 12075800658939090 | 12075800658961465 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7f41af0ba600 | 0x7f407f036600 | 12075800658982554 | 12075800658993809 | 12075800659118928 | 12075800659122194 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7f41af0ba500 | 0x7f407f036640 | 12075800659149675 | 12075800659160688 | 12075800659332366 | 12075800659335420 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7f41af0ba400 | 0x7f407f036680 | 12075800659370836 | 12075800659382286 | 12075800659508044 | 12075800659511066 |
| 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 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7f41af0ba300 | 0x7f407f0366c0 | 12075800659536343 | 12075800659547884 | 12075800659798922 | 12075800659818738 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7f41af0baa00 | 0x7f407f036700 | 12075800659838455 | 12075800659849321 | 12075800660097799 | 12075800660124897 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7f41af0ba900 | 0x7f407f036740 | 12075800660146898 | 12075800660157958 | 12075800660283397 | 12075800660286517 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7f41af0ba800 | 0x7f407f036780 | 12075800660310783 | 12075800660321636 | 12075800660504035 | 12075800660507017 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7f41af0ba700 | 0x7f407f0367c0 | 12075800660541872 | 12075800660552994 | 12075800660679553 | 12075800660682493 |
| 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 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7f41af0ba600 | 0x7f407f036800 | 12075800660708331 | 12075800660719393 | 12075800660982590 | 12075800661006876 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7f41af0ba500 | 0x7f407f036840 | 12075800661029689 | 12075800661041790 | 12075800661288187 | 12075800661311372 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7f41af0ba400 | 0x7f407f036880 | 12075800661330598 | 12075800661343227 | 12075800661469305 | 12075800661472441 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7f41af0ba300 | 0x7f407f0368c0 | 12075800661497939 | 12075800661510265 | 12075800661700183 | 12075800661703240 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7f41af0baa00 | 0x7f407f036900 | 12075800661738606 | 12075800661751543 | 12075800661877621 | 12075800661880640 |
| 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 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7f41af0ba900 | 0x7f407f036940 | 12075800661905576 | 12075800661918581 | 12075800662200498 | 12075800662227976 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7f41af0ba800 | 0x7f407f036980 | 12075800662248063 | 12075800662259858 | 12075800662506415 | 12075800662533223 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7f41af0ba700 | 0x7f407f0369c0 | 12075800662554172 | 12075800662565295 | 12075800662690574 | 12075800662693611 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7f41af0ba600 | 0x7f407f036a00 | 12075800662720822 | 12075800662731853 | 12075800662941291 | 12075800662967470 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7f41af0ba500 | 0x7f407f036a40 | 12075800662997456 | 12075800663013130 | 12075800663140809 | 12075800663144108 |
| 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 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7f41af0ba400 | 0x7f407f036a80 | 12075800663171299 | 12075800663183209 | 12075800663488966 | 12075800663515438 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7f41af0ba300 | 0x7f407f036ac0 | 12075800663534905 | 12075800663546405 | 12075800663800963 | 12075800663827188 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7f41af0baa00 | 0x7f407f036b00 | 12075800663848738 | 12075800663860002 | 12075800663988321 | 12075800663991373 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7f41af0ba900 | 0x7f407f036b40 | 12075800664024795 | 12075800664036001 | 12075800664263998 | 12075800664290238 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7f41af0ba800 | 0x7f407f036b80 | 12075800664321947 | 12075800664334398 | 12075800664459996 | 12075800664463049 |
| 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 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7f41af0ba700 | 0x7f407f036bc0 | 12075800664488487 | 12075800664499996 | 12075800664857113 | 12075800664879463 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7f41af0ba600 | 0x7f407f036c00 | 12075800664901104 | 12075800664913432 | 12075800665163670 | 12075800665187195 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7f41af0ba500 | 0x7f407f036c40 | 12075800665207683 | 12075800665220949 | 12075800665349588 | 12075800665352663 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7f41af0ba400 | 0x7f407f036c80 | 12075800665377188 | 12075800665387988 | 12075800665631185 | 12075800665653943 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7f41af0ba300 | 0x7f407f036cc0 | 12075800665682686 | 12075800665694545 | 12075800665823983 | 12075800665826974 |
| 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 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7f41af0baa00 | 0x7f407f036d00 | 12075800665851309 | 12075800665862863 | 12075800666237739 | 12075800666261632 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7f41af0ba900 | 0x7f407f036d40 | 12075800666282150 | 12075800666293739 | 12075800666551496 | 12075800666573993 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7f41af0ba800 | 0x7f407f036d80 | 12075800666594501 | 12075800666607496 | 12075800666737734 | 12075800666740823 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7f41af0ba700 | 0x7f407f036dc0 | 12075800666767432 | 12075800666777894 | 12075800667056931 | 12075800667090312 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7f41af0ba600 | 0x7f407f036e00 | 12075800667120638 | 12075800667132131 | 12075800667267969 | 12075800667271048 |
| 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 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7f41af0ba500 | 0x7f407f036e40 | 12075800667296145 | 12075800667307649 | 12075800667730045 | 12075800667756741 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7f41af0ba400 | 0x7f407f036e80 | 12075800667776177 | 12075800667787324 | 12075800668042842 | 12075800668070353 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7f41af0ba300 | 0x7f407f036ec0 | 12075800668091342 | 12075800668104121 | 12075800668239160 | 12075800668242383 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7f41af0baa00 | 0x7f407f036f00 | 12075800668267319 | 12075800668278520 | 12075800668592437 | 12075800668619845 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7f41af0ba900 | 0x7f407f036f40 | 12075800668650772 | 12075800668662036 | 12075800668813394 | 12075800668816460 |
| 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 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7f41af0ba800 | 0x7f407f036f80 | 12075800668842559 | 12075800668854194 | 12075800669370189 | 12075800669403210 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7f41af0ba700 | 0x7f407f036fc0 | 12075800669426203 | 12075800669438828 | 12075800669735305 | 12075800669757860 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7f41af0ba600 | 0x7f407f037000 | 12075800669777686 | 12075800669790345 | 12075800669943783 | 12075800669946931 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7f41af0ba500 | 0x7f407f037040 | 12075800669973460 | 12075800669984263 | 12075800670369379 | 12075800670396777 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7f41af0ba400 | 0x7f407f037080 | 12075800670428426 | 12075800670440419 | 12075800670616737 | 12075800670619731 |
| 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 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7f41af0ba300 | 0x7f407f0370c0 | 12075800670644457 | 12075800670657217 | 12075800671266011 | 12075800671295617 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7f41af0baa00 | 0x7f407f037100 | 12075800671317638 | 12075800671330330 | 12075800671657207 | 12075800671684089 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7f41af0ba900 | 0x7f407f037140 | 12075800671706100 | 12075800671718646 | 12075800671896405 | 12075800671899590 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7f41af0ba800 | 0x7f407f037180 | 12075800671925468 | 12075800671936724 | 12075800672412240 | 12075800672443130 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7f41af0ba700 | 0x7f407f0371c0 | 12075800672475420 | 12075800672486159 | 12075800672721677 | 12075800672748317 |
| 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 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7f41af0ba600 | 0x7f407f037200 | 12075800672767633 | 12075800672779596 | 12075800673481349 | 12075800673508570 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7f41af0ba500 | 0x7f407f037240 | 12075800673529890 | 12075800673542469 | 12075800673914625 | 12075800673941525 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7f41af0ba400 | 0x7f407f037280 | 12075800673960420 | 12075800673973345 | 12075800674175903 | 12075800674205515 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7f41af0ba300 | 0x7f407f0372c0 | 12075800674225973 | 12075800674238302 | 12075800674763257 | 12075800674791675 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7f41af0baa00 | 0x7f407f037300 | 12075800674821861 | 12075800674832856 | 12075800675056534 | 12075800675084128 |
| 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 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7f41af0ba900 | 0x7f407f037340 | 12075800675106189 | 12075800675118293 | 12075800675916846 | 12075800675943886 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7f41af0ba800 | 0x7f407f037380 | 12075800675965727 | 12075800675976685 | 12075800676396041 | 12075800676427515 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7f41af0ba700 | 0x7f407f0373c0 | 12075800676447141 | 12075800676458921 | 12075800676682918 | 12075800676709228 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7f41af0ba600 | 0x7f407f037400 | 12075800676729576 | 12075800676740518 | 12075800677349472 | 12075800677377691 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7f41af0ba500 | 0x7f407f037440 | 12075800677408027 | 12075800677420671 | 12075800677688989 | 12075800677715779 |
| 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 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7f41af0ba400 | 0x7f407f037480 | 12075800677737439 | 12075800677748988 | 12075800678732499 | 12075800678760280 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7f41af0ba300 | 0x7f407f0374c0 | 12075800678780187 | 12075800678791538 | 12075800679306573 | 12075800679334157 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7f41af0baa00 | 0x7f407f037500 | 12075800679357029 | 12075800679367852 | 12075800679638410 | 12075800679665072 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7f41af0ba900 | 0x7f407f037540 | 12075800679686812 | 12075800679697769 | 12075800680435042 | 12075800680463065 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7f41af0ba800 | 0x7f407f037580 | 12075800680493331 | 12075800680506401 | 12075800680820638 | 12075800680847088 |
| 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 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7f41af0ba700 | 0x7f407f0375c0 | 12075800680867256 | 12075800680879038 | 12075800682049586 | 12075800682082755 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7f41af0ba600 | 0x7f407f037600 | 12075800682102722 | 12075800682113906 | 12075800682723820 | 12075800682750275 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7f41af0ba500 | 0x7f407f037640 | 12075800682772386 | 12075800682783499 | 12075800683130536 | 12075800683157502 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7f41af0ba400 | 0x7f407f037680 | 12075800683178451 | 12075800683191335 | 12075800684067807 | 12075800684096377 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7f41af0ba300 | 0x7f407f0376c0 | 12075800684126683 | 12075800684139646 | 12075800684548442 | 12075800684575417 |
| 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 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7f41af0baa00 | 0x7f407f037700 | 12075800684595976 | 12075800684607322 | 12075800686156267 | 12075800686205387 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7f41af0ba900 | 0x7f407f037740 | 12075800686228039 | 12075800686240266 | 12075800687034338 | 12075800687106511 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7f41af0ba800 | 0x7f407f037780 | 12075800687125306 | 12075800687138882 | 12075800687552318 | 12075800687626758 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7f41af0ba700 | 0x7f407f0377c0 | 12075800687647276 | 12075800687659836 | 12075800688818227 | 12075800688889295 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7f41af0ba600 | 0x7f407f037800 | 12075800688920442 | 12075800688933906 | 12075800689719019 | 12075800689793144 |
| 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 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7f41af0ba500 | 0x7f407f037840 | 12075800689815376 | 12075800689828938 | 12075800692880433 | 12075800692954770 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7f41af0ba400 | 0x7f407f037880 | 12075800692974988 | 12075800692987952 | 12075800694529219 | 12075800694600699 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7f41af0ba300 | 0x7f407f0378c0 | 12075800694622499 | 12075800694634658 | 12075800695423451 | 12075800695493358 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7f41af0baa00 | 0x7f407f037900 | 12075800695516811 | 12075800695528570 | 12075800697809991 | 12075800697880244 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7f41af0ba900 | 0x7f407f037940 | 12075800697912764 | 12075800697924070 | 12075800699458937 | 12075800699532424 |
| 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 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7f41af0ba800 | 0x7f407f037980 | 12075800699553794 | 12075800699566297 | 12075800705618726 | 12075800705689988 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7f41af0ba700 | 0x7f407f0379c0 | 12075800705709905 | 12075800705721285 | 12075800708762380 | 12075800708832698 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7f41af0ba600 | 0x7f407f037a00 | 12075800708855040 | 12075800708866219 | 12075800710405246 | 12075800710480711 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 893996 | 894001 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7f41af0ba500 | 0x7f407f037a40 | 12075800710500538 | 12075800710511805 | 12075800715038007 | 12075800715108732 |