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 | 909004 | 909009 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7f283d604180 | 12076086146705435 | 12076086146753232 | 12076086147076749 | 12076086147182061 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 909004 | 909009 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7f283d635100 | 12076086162295699 | 12076086162418931 | 12076086162425171 | 12076086162431722 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7f29491c1900 | 0x7f283d635140 | 12076086162469292 | 12076086162483891 | 12076086162615730 | 12076086162619431 |
| 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 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7f29491c1800 | 0x7f283d635180 | 12076086162654326 | 12076086162668529 | 12076086162915247 | 12076086163017360 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7f29491c1700 | 0x7f283d6351c0 | 12076086163035464 | 12076086163052046 | 12076086163298444 | 12076086163396595 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7f29491c1600 | 0x7f283d635200 | 12076086163412394 | 12076086163435402 | 12076086163561481 | 12076086163565148 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7f29491c1500 | 0x7f283d635240 | 12076086163590335 | 12076086163604841 | 12076086163729800 | 12076086163733271 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7f29491c1400 | 0x7f283d635280 | 12076086163779256 | 12076086163793639 | 12076086163917798 | 12076086163921110 |
| 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 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7f29491c1300 | 0x7f283d6352c0 | 12076086163942139 | 12076086163955558 | 12076086164201475 | 12076086164301527 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7f29491c1a00 | 0x7f283d635300 | 12076086164311806 | 12076086164336354 | 12076086164579552 | 12076086164676233 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7f29491c1900 | 0x7f283d635340 | 12076086164692023 | 12076086164711391 | 12076086164836670 | 12076086164840218 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7f29491c1800 | 0x7f283d635380 | 12076086164858792 | 12076086164871709 | 12076086164996668 | 12076086165000115 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7f29491c1700 | 0x7f283d6353c0 | 12076086165033657 | 12076086165051068 | 12076086165175547 | 12076086165178807 |
| 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 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7f29491c1600 | 0x7f283d635400 | 12076086165197843 | 12076086165213786 | 12076086165467064 | 12076086165538275 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7f29491c1500 | 0x7f283d635440 | 12076086165551931 | 12076086165576983 | 12076086165821781 | 12076086165888717 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7f29491c1400 | 0x7f283d635480 | 12076086165908804 | 12076086165921620 | 12076086166045939 | 12076086166049596 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7f29491c1300 | 0x7f283d6354c0 | 12076086166068320 | 12076086166081779 | 12076086166206738 | 12076086166210244 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7f29491c1a00 | 0x7f283d635500 | 12076086166241933 | 12076086166255377 | 12076086166380656 | 12076086166383747 |
| 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 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7f29491c1900 | 0x7f283d635540 | 12076086166403333 | 12076086166417456 | 12076086166669453 | 12076086166710925 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7f29491c1800 | 0x7f283d635580 | 12076086166724710 | 12076086166739213 | 12076086166986251 | 12076086167055004 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7f29491c1700 | 0x7f283d6355c0 | 12076086167071535 | 12076086167086570 | 12076086167211689 | 12076086167214711 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7f29491c1600 | 0x7f283d635600 | 12076086167234858 | 12076086167248648 | 12076086167374087 | 12076086167377153 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7f29491c1500 | 0x7f283d635640 | 12076086167409473 | 12076086167423047 | 12076086167547046 | 12076086167550044 |
| 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 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7f29491c1400 | 0x7f283d635680 | 12076086167569190 | 12076086167582565 | 12076086167828003 | 12076086167899514 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7f29491c1300 | 0x7f283d6356c0 | 12076086167915203 | 12076086167934082 | 12076086168181920 | 12076086168278818 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7f29491c1a00 | 0x7f283d635700 | 12076086168292213 | 12076086168317759 | 12076086168442238 | 12076086168445829 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7f29491c1900 | 0x7f283d635740 | 12076086168466227 | 12076086168478877 | 12076086168603676 | 12076086168606898 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7f29491c1800 | 0x7f283d635780 | 12076086168638166 | 12076086168652316 | 12076086168776795 | 12076086168779870 |
| 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 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7f29491c1700 | 0x7f283d6357c0 | 12076086168800919 | 12076086168815034 | 12076086169059992 | 12076086169139668 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7f29491c1600 | 0x7f283d635800 | 12076086169153324 | 12076086169174871 | 12076086169418229 | 12076086169496161 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7f29491c1500 | 0x7f283d635840 | 12076086169509235 | 12076086169534388 | 12076086169659187 | 12076086169662861 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7f29491c1400 | 0x7f283d635880 | 12076086169681485 | 12076086169693746 | 12076086169819185 | 12076086169822798 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7f29491c1300 | 0x7f283d6358c0 | 12076086169854126 | 12076086169868145 | 12076086169992944 | 12076086169996431 |
| 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 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7f29491c1a00 | 0x7f283d635900 | 12076086170018732 | 12076086170032463 | 12076086170278221 | 12076086170325021 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7f29491c1900 | 0x7f283d635940 | 12076086170339328 | 12076086170352941 | 12076086170597258 | 12076086170643583 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7f29491c1800 | 0x7f283d635980 | 12076086170658050 | 12076086170671498 | 12076086170796777 | 12076086170800244 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7f29491c1700 | 0x7f283d6359c0 | 12076086170819110 | 12076086170832296 | 12076086170957415 | 12076086170960673 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7f29491c1600 | 0x7f283d635a00 | 12076086170991159 | 12076086171004775 | 12076086171129094 | 12076086171132562 |
| 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 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7f29491c1500 | 0x7f283d635a40 | 12076086171152128 | 12076086171165573 | 12076086171417411 | 12076086171469478 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7f29491c1400 | 0x7f283d635a80 | 12076086171479447 | 12076086171504770 | 12076086171754208 | 12076086171831110 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7f29491c1300 | 0x7f283d635ac0 | 12076086171840648 | 12076086171867487 | 12076086171992766 | 12076086171996347 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7f29491c1a00 | 0x7f283d635b00 | 12076086172022145 | 12076086172035325 | 12076086172161884 | 12076086172165772 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7f29491c1900 | 0x7f283d635b40 | 12076086172201308 | 12076086172215964 | 12076086172340923 | 12076086172344324 |
| 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 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7f29491c1800 | 0x7f283d635b80 | 12076086172362748 | 12076086172375802 | 12076086172665240 | 12076086172690397 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7f29491c1700 | 0x7f283d635bc0 | 12076086172703612 | 12076086172718199 | 12076086172962357 | 12076086172990345 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7f29491c1600 | 0x7f283d635c00 | 12076086173008148 | 12076086173022997 | 12076086173147156 | 12076086173150352 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7f29491c1500 | 0x7f283d635c40 | 12076086173169928 | 12076086173183955 | 12076086173310354 | 12076086173313796 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7f29491c1400 | 0x7f283d635c80 | 12076086173345084 | 12076086173359954 | 12076086173484753 | 12076086173488140 |
| 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 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7f29491c1300 | 0x7f283d635cc0 | 12076086173506444 | 12076086173519792 | 12076086173776750 | 12076086173799428 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7f29491c1a00 | 0x7f283d635d00 | 12076086173812993 | 12076086173826350 | 12076086174069707 | 12076086174093755 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7f29491c1900 | 0x7f283d635d40 | 12076086174107110 | 12076086174120747 | 12076086174246026 | 12076086174249324 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7f29491c1800 | 0x7f283d635d80 | 12076086174269682 | 12076086174282825 | 12076086174410664 | 12076086174413950 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7f29491c1700 | 0x7f283d635dc0 | 12076086174444487 | 12076086174457864 | 12076086174582823 | 12076086174586180 |
| 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 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7f29491c1600 | 0x7f283d635e00 | 12076086174604665 | 12076086174617862 | 12076086174875940 | 12076086174902619 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7f29491c1500 | 0x7f283d635e40 | 12076086174915783 | 12076086174929220 | 12076086175175137 | 12076086175201985 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7f29491c1400 | 0x7f283d635e80 | 12076086175215019 | 12076086175228737 | 12076086175353536 | 12076086175357133 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7f29491c1300 | 0x7f283d635ec0 | 12076086175375457 | 12076086175388736 | 12076086175518014 | 12076086175521298 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7f29491c1a00 | 0x7f283d635f00 | 12076086175552526 | 12076086175566014 | 12076086175691133 | 12076086175694420 |
| 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 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7f29491c1900 | 0x7f283d635f40 | 12076086175714417 | 12076086175727453 | 12076086175990810 | 12076086176016028 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7f29491c1800 | 0x7f283d635f80 | 12076086176031657 | 12076086176045370 | 12076086176288728 | 12076086176312328 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7f29491c1700 | 0x7f283d635fc0 | 12076086176326034 | 12076086176339927 | 12076086176465046 | 12076086176468418 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7f29491c1600 | 0x7f283d636000 | 12076086176488666 | 12076086176501686 | 12076086176638164 | 12076086176641530 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7f29491c1500 | 0x7f283d636040 | 12076086176672768 | 12076086176686164 | 12076086176811123 | 12076086176814682 |
| 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 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7f29491c1400 | 0x7f283d636080 | 12076086176832956 | 12076086176846163 | 12076086177099760 | 12076086177132913 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7f29491c1300 | 0x7f283d6360c0 | 12076086177146388 | 12076086177159920 | 12076086177405038 | 12076086177429354 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7f29491c1a00 | 0x7f283d636100 | 12076086177443661 | 12076086177456877 | 12076086177581676 | 12076086177585094 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7f29491c1900 | 0x7f283d636140 | 12076086177603268 | 12076086177616556 | 12076086177758474 | 12076086177762043 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7f29491c1800 | 0x7f283d636180 | 12076086177792429 | 12076086177805674 | 12076086177931273 | 12076086177934854 |
| 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 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7f29491c1700 | 0x7f283d6361c0 | 12076086177952887 | 12076086177965673 | 12076086178218790 | 12076086178241434 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7f29491c1600 | 0x7f283d636200 | 12076086178255129 | 12076086178268710 | 12076086178516868 | 12076086178543204 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7f29491c1500 | 0x7f283d636240 | 12076086178556639 | 12076086178569987 | 12076086178696226 | 12076086178699605 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7f29491c1400 | 0x7f283d636280 | 12076086178718781 | 12076086178731746 | 12076086178880064 | 12076086178883367 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7f29491c1300 | 0x7f283d6362c0 | 12076086178932839 | 12076086178946464 | 12076086179071903 | 12076086179075123 |
| 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 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7f29491c1a00 | 0x7f283d636300 | 12076086179095601 | 12076086179109022 | 12076086179362620 | 12076086179384658 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7f29491c1900 | 0x7f283d636340 | 12076086179400187 | 12076086179413660 | 12076086179659257 | 12076086179685087 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7f29491c1800 | 0x7f283d636380 | 12076086179698502 | 12076086179712057 | 12076086179837976 | 12076086179841437 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7f29491c1700 | 0x7f283d6363c0 | 12076086179859631 | 12076086179872535 | 12076086180030454 | 12076086180033885 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7f29491c1600 | 0x7f283d636400 | 12076086180066375 | 12076086180079894 | 12076086180204693 | 12076086180207868 |
| 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 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7f29491c1500 | 0x7f283d636440 | 12076086180228026 | 12076086180241332 | 12076086180497490 | 12076086180519477 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7f29491c1400 | 0x7f283d636480 | 12076086180533223 | 12076086180546929 | 12076086180793007 | 12076086180819004 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7f29491c1300 | 0x7f283d6364c0 | 12076086180833821 | 12076086180847087 | 12076086180972526 | 12076086180975885 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7f29491c1a00 | 0x7f283d636500 | 12076086180994560 | 12076086181011245 | 12076086181176684 | 12076086181179925 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7f29491c1900 | 0x7f283d636540 | 12076086181211944 | 12076086181225643 | 12076086181351722 | 12076086181355180 |
| 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 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7f29491c1800 | 0x7f283d636580 | 12076086181373965 | 12076086181387082 | 12076086181644200 | 12076086181666218 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7f29491c1700 | 0x7f283d6365c0 | 12076086181680084 | 12076086181693799 | 12076086181939557 | 12076086181961547 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7f29491c1600 | 0x7f283d636600 | 12076086181975473 | 12076086181988837 | 12076086182113635 | 12076086182117447 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7f29491c1500 | 0x7f283d636640 | 12076086182135881 | 12076086182148995 | 12076086182321474 | 12076086182325023 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7f29491c1400 | 0x7f283d636680 | 12076086182356221 | 12076086182369633 | 12076086182495392 | 12076086182498876 |
| 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 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7f29491c1300 | 0x7f283d6366c0 | 12076086182517490 | 12076086182530592 | 12076086182782430 | 12076086182805676 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7f29491c1a00 | 0x7f283d636700 | 12076086182822187 | 12076086182835549 | 12076086183080987 | 12076086183107537 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7f29491c1900 | 0x7f283d636740 | 12076086183121082 | 12076086183134906 | 12076086183260505 | 12076086183264058 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7f29491c1800 | 0x7f283d636780 | 12076086183284346 | 12076086183297305 | 12076086183480023 | 12076086183483506 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7f29491c1700 | 0x7f283d6367c0 | 12076086183514063 | 12076086183527223 | 12076086183654582 | 12076086183658040 |
| 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 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7f29491c1600 | 0x7f283d636800 | 12076086183676875 | 12076086183690261 | 12076086183952979 | 12076086183971733 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7f29491c1500 | 0x7f283d636840 | 12076086183990548 | 12076086184003859 | 12076086184289616 | 12076086184313148 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7f29491c1400 | 0x7f283d636880 | 12076086184327114 | 12076086184340336 | 12076086184466734 | 12076086184470189 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7f29491c1300 | 0x7f283d6368c0 | 12076086184488714 | 12076086184502254 | 12076086184693132 | 12076086184697342 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7f29491c1a00 | 0x7f283d636900 | 12076086184727778 | 12076086184741292 | 12076086184868331 | 12076086184871936 |
| 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 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7f29491c1900 | 0x7f283d636940 | 12076086184890871 | 12076086184903851 | 12076086185185608 | 12076086185219322 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7f29491c1800 | 0x7f283d636980 | 12076086185232596 | 12076086185246247 | 12076086185495045 | 12076086185522846 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7f29491c1700 | 0x7f283d6369c0 | 12076086185535770 | 12076086185548965 | 12076086185674564 | 12076086185677904 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7f29491c1600 | 0x7f283d636a00 | 12076086185698041 | 12076086185711363 | 12076086185920641 | 12076086185947475 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7f29491c1500 | 0x7f283d636a40 | 12076086185972481 | 12076086185985921 | 12076086186113600 | 12076086186116960 |
| 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 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7f29491c1400 | 0x7f283d636a80 | 12076086186138450 | 12076086186151519 | 12076086186487676 | 12076086186506263 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7f29491c1300 | 0x7f283d636ac0 | 12076086186524998 | 12076086186538716 | 12076086186788154 | 12076086186810749 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7f29491c1a00 | 0x7f283d636b00 | 12076086186829534 | 12076086186843353 | 12076086186971832 | 12076086186975165 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7f29491c1900 | 0x7f283d636b40 | 12076086186993920 | 12076086187006872 | 12076086187234230 | 12076086187259884 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7f29491c1800 | 0x7f283d636b80 | 12076086187290942 | 12076086187304629 | 12076086187432948 | 12076086187436462 |
| 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 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7f29491c1700 | 0x7f283d636bc0 | 12076086187454916 | 12076086187467988 | 12076086187796145 | 12076086187814775 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7f29491c1600 | 0x7f283d636c00 | 12076086187836055 | 12076086187849424 | 12076086188099342 | 12076086188131754 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7f29491c1500 | 0x7f283d636c40 | 12076086188156731 | 12076086188169101 | 12076086188297100 | 12076086188300528 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7f29491c1400 | 0x7f283d636c80 | 12076086188319453 | 12076086188331020 | 12076086188575018 | 12076086188600946 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7f29491c1300 | 0x7f283d636cc0 | 12076086188629770 | 12076086188642057 | 12076086188770696 | 12076086188774298 |
| 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 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7f29491c1a00 | 0x7f283d636d00 | 12076086188788565 | 12076086188801736 | 12076086189176452 | 12076086189203716 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7f29491c1900 | 0x7f283d636d40 | 12076086189215278 | 12076086189230212 | 12076086189482530 | 12076086189509976 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7f29491c1800 | 0x7f283d636d80 | 12076086189518311 | 12076086189530209 | 12076086189659488 | 12076086189663020 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7f29491c1700 | 0x7f283d636dc0 | 12076086189681504 | 12076086189692288 | 12076086189970205 | 12076086189996540 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7f29491c1600 | 0x7f283d636e00 | 12076086190021697 | 12076086190032445 | 12076086190168444 | 12076086190171946 |
| 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 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7f29491c1500 | 0x7f283d636e40 | 12076086190186273 | 12076086190196923 | 12076086190618840 | 12076086190646207 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7f29491c1400 | 0x7f283d636e80 | 12076086190657498 | 12076086190669399 | 12076086190928917 | 12076086190955302 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7f29491c1300 | 0x7f283d636ec0 | 12076086190963998 | 12076086190974836 | 12076086191110835 | 12076086191114438 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7f29491c1a00 | 0x7f283d636f00 | 12076086191128924 | 12076086191139795 | 12076086191454192 | 12076086191480778 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7f29491c1900 | 0x7f283d636f40 | 12076086191503210 | 12076086191513872 | 12076086191665550 | 12076086191669158 |
| 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 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7f29491c1800 | 0x7f283d636f80 | 12076086191683064 | 12076086191693710 | 12076086192208425 | 12076086192236112 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7f29491c1700 | 0x7f283d636fc0 | 12076086192248104 | 12076086192260585 | 12076086192561862 | 12076086192588036 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7f29491c1600 | 0x7f283d637000 | 12076086192596772 | 12076086192607622 | 12076086192761380 | 12076086192764945 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7f29491c1500 | 0x7f283d637040 | 12076086192781576 | 12076086192792100 | 12076086193201376 | 12076086193234838 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7f29491c1400 | 0x7f283d637080 | 12076086193258131 | 12076086193270656 | 12076086193446814 | 12076086193450579 |
| 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 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7f29491c1300 | 0x7f283d6370c0 | 12076086193464685 | 12076086193475614 | 12076086194096728 | 12076086194124021 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7f29491c1a00 | 0x7f283d637100 | 12076086194132647 | 12076086194143448 | 12076086194473205 | 12076086194499228 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7f29491c1900 | 0x7f283d637140 | 12076086194508004 | 12076086194518965 | 12076086194696403 | 12076086194699931 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7f29491c1800 | 0x7f283d637180 | 12076086194713777 | 12076086194725523 | 12076086195180879 | 12076086195207574 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7f29491c1700 | 0x7f283d6371c0 | 12076086195230227 | 12076086195240878 | 12076086195439756 | 12076086195465283 |
| 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 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7f29491c1600 | 0x7f283d637200 | 12076086195473068 | 12076086195482636 | 12076086196184550 | 12076086196211871 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7f29491c1500 | 0x7f283d637240 | 12076086196223733 | 12076086196234789 | 12076086196606626 | 12076086196632473 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7f29491c1400 | 0x7f283d637280 | 12076086196641930 | 12076086196652386 | 12076086196854944 | 12076086196880714 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7f29491c1300 | 0x7f283d6372c0 | 12076086196888568 | 12076086196898943 | 12076086197440539 | 12076086197473926 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7f29491c1a00 | 0x7f283d637300 | 12076086197495967 | 12076086197506618 | 12076086197729656 | 12076086197755459 |
| 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 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7f29491c1900 | 0x7f283d637340 | 12076086197763955 | 12076086197774936 | 12076086198571088 | 12076086198597915 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7f29491c1800 | 0x7f283d637380 | 12076086198611721 | 12076086198622288 | 12076086199040844 | 12076086199067899 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7f29491c1700 | 0x7f283d6373c0 | 12076086199075994 | 12076086199086764 | 12076086199310122 | 12076086199335766 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7f29491c1600 | 0x7f283d637400 | 12076086199348460 | 12076086199358921 | 12076086199954436 | 12076086199980144 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7f29491c1500 | 0x7f283d637440 | 12076086200005902 | 12076086200016516 | 12076086200285953 | 12076086200316319 |
| 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 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7f29491c1400 | 0x7f283d637480 | 12076086200325315 | 12076086200335873 | 12076086201318904 | 12076086201346333 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7f29491c1300 | 0x7f283d6374c0 | 12076086201354618 | 12076086201367064 | 12076086201881139 | 12076086201907796 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7f29491c1a00 | 0x7f283d637500 | 12076086201916803 | 12076086201927858 | 12076086202198896 | 12076086202232149 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7f29491c1900 | 0x7f283d637540 | 12076086202241547 | 12076086202252016 | 12076086202988169 | 12076086203016116 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7f29491c1800 | 0x7f283d637580 | 12076086203038899 | 12076086203049608 | 12076086203364806 | 12076086203390492 |
| 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 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7f29491c1700 | 0x7f283d6375c0 | 12076086203399298 | 12076086203409765 | 12076086204578715 | 12076086204606001 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7f29491c1600 | 0x7f283d637600 | 12076086204618234 | 12076086204628634 | 12076086205238069 | 12076086205265627 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7f29491c1500 | 0x7f283d637640 | 12076086205274113 | 12076086205284629 | 12076086205603346 | 12076086205629213 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7f29491c1400 | 0x7f283d637680 | 12076086205643118 | 12076086205653585 | 12076086206530217 | 12076086206557568 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7f29491c1300 | 0x7f283d6376c0 | 12076086206579609 | 12076086206590217 | 12076086206997893 | 12076086207025167 |
| 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 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7f29491c1a00 | 0x7f283d637700 | 12076086207037560 | 12076086207048133 | 12076086208595159 | 12076086208624549 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7f29491c1900 | 0x7f283d637740 | 12076086208633326 | 12076086208644119 | 12076086209435631 | 12076086209483465 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7f29491c1800 | 0x7f283d637780 | 12076086209492092 | 12076086209507175 | 12076086209919972 | 12076086209971402 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7f29491c1700 | 0x7f283d6377c0 | 12076086209979888 | 12076086209991010 | 12076086211148761 | 12076086211221025 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7f29491c1600 | 0x7f283d637800 | 12076086211243266 | 12076086211254521 | 12076086212039155 | 12076086212109436 |
| 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 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7f29491c1500 | 0x7f283d637840 | 12076086212118392 | 12076086212131154 | 12076086215178970 | 12076086215249301 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7f29491c1400 | 0x7f283d637880 | 12076086215258248 | 12076086215269690 | 12076086216808718 | 12076086216879110 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7f29491c1300 | 0x7f283d6378c0 | 12076086216887596 | 12076086216900237 | 12076086217688551 | 12076086217763033 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7f29491c1a00 | 0x7f283d637900 | 12076086217772360 | 12076086217783590 | 12076086220064053 | 12076086220137836 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7f29491c1900 | 0x7f283d637940 | 12076086220162432 | 12076086220173652 | 12076086221707880 | 12076086221778285 |
| 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 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7f29491c1800 | 0x7f283d637980 | 12076086221786961 | 12076086221797959 | 12076086227849272 | 12076086227926060 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7f29491c1700 | 0x7f283d6379c0 | 12076086227939255 | 12076086227951032 | 12076086230990848 | 12076086231065875 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7f29491c1600 | 0x7f283d637a00 | 12076086231079932 | 12076086231091007 | 12076086232629235 | 12076086232699602 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 909004 | 909009 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7f29491c1500 | 0x7f283d637a40 | 12076086232708198 | 12076086232727475 | 12076086237252720 | 12076086237323495 |