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 | 815652 | 815657 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7fe94c604180 | 12074243664847671 | 12074243664893082 | 12074243665216759 | 12074243665326411 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 815652 | 815657 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7fe94c635100 | 12074243680217791 | 12074243680327024 | 12074243680333584 | 12074243680339377 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7fea58305900 | 0x7fe94c635140 | 12074243680385021 | 12074243680398223 | 12074243680529902 | 12074243680533557 |
| 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 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7fea58305800 | 0x7fe94c635180 | 12074243680577078 | 12074243680589742 | 12074243680832459 | 12074243680929673 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7fea58305700 | 0x7fe94c6351c0 | 12074243680956463 | 12074243680968778 | 12074243681214856 | 12074243681316342 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7fea58305600 | 0x7fe94c635200 | 12074243681342380 | 12074243681354215 | 12074243681479814 | 12074243681483533 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7fea58305500 | 0x7fe94c635240 | 12074243681511575 | 12074243681522693 | 12074243681647492 | 12074243681650843 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7fea58305400 | 0x7fe94c635280 | 12074243681703201 | 12074243681717092 | 12074243681840930 | 12074243681844193 |
| 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 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7fea58305300 | 0x7fe94c6352c0 | 12074243681870151 | 12074243681882050 | 12074243682127648 | 12074243682227335 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7fea58305a00 | 0x7fe94c635300 | 12074243682248233 | 12074243682262847 | 12074243682507325 | 12074243682604976 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7fea58305900 | 0x7fe94c635340 | 12074243682626927 | 12074243682639163 | 12074243682763962 | 12074243682767358 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7fea58305800 | 0x7fe94c635380 | 12074243682793687 | 12074243682805402 | 12074243682930521 | 12074243682933817 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7fea58305700 | 0x7fe94c6353c0 | 12074243682970766 | 12074243682984920 | 12074243683109559 | 12074243683112970 |
| 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 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7fea58305600 | 0x7fe94c635400 | 12074243683140361 | 12074243683151959 | 12074243683406037 | 12074243683479181 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7fea58305500 | 0x7fe94c635440 | 12074243683500941 | 12074243683512116 | 12074243683758033 | 12074243683826726 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7fea58305400 | 0x7fe94c635480 | 12074243683847375 | 12074243683859793 | 12074243683984911 | 12074243683987996 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7fea58305300 | 0x7fe94c6354c0 | 12074243684022821 | 12074243684034351 | 12074243684159470 | 12074243684162641 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7fea58305a00 | 0x7fe94c635500 | 12074243684199459 | 12074243684211789 | 12074243684336268 | 12074243684339489 |
| 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 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7fea58305900 | 0x7fe94c635540 | 12074243684366640 | 12074243684378668 | 12074243684623946 | 12074243684667008 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7fea58305800 | 0x7fe94c635580 | 12074243684688347 | 12074243684700265 | 12074243684943943 | 12074243685018260 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7fea58305700 | 0x7fe94c6355c0 | 12074243685039309 | 12074243685052422 | 12074243685177381 | 12074243685180332 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7fea58305600 | 0x7fe94c635600 | 12074243685206811 | 12074243685218020 | 12074243685343299 | 12074243685346600 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7fea58305500 | 0x7fe94c635640 | 12074243685385242 | 12074243685397219 | 12074243685521378 | 12074243685524561 |
| 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 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7fea58305400 | 0x7fe94c635680 | 12074243685551521 | 12074243685564257 | 12074243685814655 | 12074243685887415 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7fea58305300 | 0x7fe94c6356c0 | 12074243685907873 | 12074243685918814 | 12074243686165212 | 12074243686266279 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7fea58305a00 | 0x7fe94c635700 | 12074243686286898 | 12074243686297691 | 12074243686422170 | 12074243686425696 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7fea58305900 | 0x7fe94c635740 | 12074243686450862 | 12074243686462329 | 12074243686587608 | 12074243686591063 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7fea58305800 | 0x7fe94c635780 | 12074243686627741 | 12074243686639288 | 12074243686763607 | 12074243686766829 |
| 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 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7fea58305700 | 0x7fe94c6357c0 | 12074243686792577 | 12074243686804566 | 12074243687054004 | 12074243687136777 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7fea58305600 | 0x7fe94c635800 | 12074243687158888 | 12074243687170003 | 12074243687416561 | 12074243687494481 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7fea58305500 | 0x7fe94c635840 | 12074243687515120 | 12074243687526160 | 12074243687650639 | 12074243687654118 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7fea58305400 | 0x7fe94c635880 | 12074243687680587 | 12074243687691918 | 12074243687817197 | 12074243687820527 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7fea58305300 | 0x7fe94c6358c0 | 12074243687856644 | 12074243687869997 | 12074243687994956 | 12074243687997957 |
| 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 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7fea58305a00 | 0x7fe94c635900 | 12074243688026480 | 12074243688038635 | 12074243688287273 | 12074243688365680 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7fea58305900 | 0x7fe94c635940 | 12074243688386950 | 12074243688404392 | 12074243688649350 | 12074243688726671 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7fea58305800 | 0x7fe94c635980 | 12074243688746939 | 12074243688758949 | 12074243688883748 | 12074243688887179 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7fea58305700 | 0x7fe94c6359c0 | 12074243688915281 | 12074243688926627 | 12074243689052546 | 12074243689056113 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7fea58305600 | 0x7fe94c635a00 | 12074243689092010 | 12074243689103586 | 12074243689228385 | 12074243689231479 |
| 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 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7fea58305500 | 0x7fe94c635a40 | 12074243689257247 | 12074243689269024 | 12074243689522142 | 12074243689547186 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7fea58305400 | 0x7fe94c635a80 | 12074243689567183 | 12074243689579902 | 12074243689825019 | 12074243689871799 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7fea58305300 | 0x7fe94c635ac0 | 12074243689894271 | 12074243689908379 | 12074243690033338 | 12074243690036625 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7fea58305a00 | 0x7fe94c635b00 | 12074243690062042 | 12074243690073337 | 12074243690199896 | 12074243690202864 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7fea58305900 | 0x7fe94c635b40 | 12074243690238310 | 12074243690251576 | 12074243690375895 | 12074243690378971 |
| 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 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7fea58305800 | 0x7fe94c635b80 | 12074243690404639 | 12074243690417974 | 12074243690677972 | 12074243690698745 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7fea58305700 | 0x7fe94c635bc0 | 12074243690721728 | 12074243690734771 | 12074243690985969 | 12074243691012468 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7fea58305600 | 0x7fe94c635c00 | 12074243691033547 | 12074243691046449 | 12074243691171247 | 12074243691174409 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7fea58305500 | 0x7fe94c635c40 | 12074243691200818 | 12074243691213327 | 12074243691340366 | 12074243691343583 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7fea58305400 | 0x7fe94c635c80 | 12074243691379079 | 12074243691393165 | 12074243691518444 | 12074243691521594 |
| 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 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7fea58305300 | 0x7fe94c635cc0 | 12074243691548244 | 12074243691561964 | 12074243691825802 | 12074243691846207 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7fea58305a00 | 0x7fe94c635d00 | 12074243691868138 | 12074243691881001 | 12074243692125799 | 12074243692150743 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7fea58305900 | 0x7fe94c635d40 | 12074243692171642 | 12074243692182918 | 12074243692307557 | 12074243692310821 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7fea58305800 | 0x7fe94c635d80 | 12074243692337911 | 12074243692349477 | 12074243692477156 | 12074243692480165 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7fea58305700 | 0x7fe94c635dc0 | 12074243692516303 | 12074243692530115 | 12074243692655234 | 12074243692658256 |
| 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 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7fea58305600 | 0x7fe94c635e00 | 12074243692684205 | 12074243692697314 | 12074243692949472 | 12074243692973492 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7fea58305500 | 0x7fe94c635e40 | 12074243692994601 | 12074243693010271 | 12074243693255069 | 12074243693280352 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7fea58305400 | 0x7fe94c635e80 | 12074243693300229 | 12074243693311228 | 12074243693435867 | 12074243693438877 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7fea58305300 | 0x7fe94c635ec0 | 12074243693464324 | 12074243693476347 | 12074243693604346 | 12074243693607500 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7fea58305a00 | 0x7fe94c635f00 | 12074243693643387 | 12074243693656825 | 12074243693781784 | 12074243693785010 |
| 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 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7fea58305900 | 0x7fe94c635f40 | 12074243693811149 | 12074243693823064 | 12074243694079062 | 12074243694107309 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7fea58305800 | 0x7fe94c635f80 | 12074243694129761 | 12074243694142901 | 12074243694387859 | 12074243694413638 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7fea58305700 | 0x7fe94c635fc0 | 12074243694434266 | 12074243694447538 | 12074243694572977 | 12074243694575980 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7fea58305600 | 0x7fe94c636000 | 12074243694602078 | 12074243694615057 | 12074243694753616 | 12074243694757106 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7fea58305500 | 0x7fe94c636040 | 12074243694793313 | 12074243694806895 | 12074243694931534 | 12074243694934335 |
| 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 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7fea58305400 | 0x7fe94c636080 | 12074243694958971 | 12074243694971534 | 12074243695225611 | 12074243695252316 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7fea58305300 | 0x7fe94c6360c0 | 12074243695272834 | 12074243695284651 | 12074243695529289 | 12074243695553396 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7fea58305a00 | 0x7fe94c636100 | 12074243695574405 | 12074243695585608 | 12074243695710247 | 12074243695713423 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7fea58305900 | 0x7fe94c636140 | 12074243695740844 | 12074243695752167 | 12074243695893765 | 12074243695896974 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7fea58305800 | 0x7fe94c636180 | 12074243695932921 | 12074243695944485 | 12074243696069924 | 12074243696073242 |
| 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 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7fea58305700 | 0x7fe94c6361c0 | 12074243696100282 | 12074243696111843 | 12074243696371521 | 12074243696395550 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7fea58305600 | 0x7fe94c636200 | 12074243696415888 | 12074243696427201 | 12074243696710558 | 12074243696734029 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7fea58305500 | 0x7fe94c636240 | 12074243696755179 | 12074243696766558 | 12074243696893117 | 12074243696896451 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7fea58305400 | 0x7fe94c636280 | 12074243696923481 | 12074243696936316 | 12074243697085915 | 12074243697089209 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7fea58305300 | 0x7fe94c6362c0 | 12074243697143440 | 12074243697155994 | 12074243697280633 | 12074243697284202 |
| 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 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7fea58305a00 | 0x7fe94c636300 | 12074243697309970 | 12074243697321913 | 12074243697583030 | 12074243697608254 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7fea58305900 | 0x7fe94c636340 | 12074243697632108 | 12074243697643990 | 12074243697889428 | 12074243697917649 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7fea58305800 | 0x7fe94c636380 | 12074243697938257 | 12074243697949427 | 12074243698075346 | 12074243698078858 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7fea58305700 | 0x7fe94c6363c0 | 12074243698107602 | 12074243698118866 | 12074243698275664 | 12074243698279100 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7fea58305600 | 0x7fe94c636400 | 12074243698315298 | 12074243698328144 | 12074243698453423 | 12074243698456650 |
| 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 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7fea58305500 | 0x7fe94c636440 | 12074243698483450 | 12074243698495822 | 12074243698753900 | 12074243698778779 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7fea58305400 | 0x7fe94c636480 | 12074243698801371 | 12074243698813739 | 12074243699063657 | 12074243699092812 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7fea58305300 | 0x7fe94c6364c0 | 12074243699114272 | 12074243699126537 | 12074243699252296 | 12074243699255585 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7fea58305a00 | 0x7fe94c636500 | 12074243699283887 | 12074243699295175 | 12074243699461734 | 12074243699464934 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7fea58305900 | 0x7fe94c636540 | 12074243699502193 | 12074243699515013 | 12074243699640452 | 12074243699643656 |
| 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 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7fea58305800 | 0x7fe94c636580 | 12074243699669865 | 12074243699681252 | 12074243699936129 | 12074243699959493 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7fea58305700 | 0x7fe94c6365c0 | 12074243699980562 | 12074243699993249 | 12074243700239007 | 12074243700270861 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7fea58305600 | 0x7fe94c636600 | 12074243700291640 | 12074243700304286 | 12074243700429725 | 12074243700432872 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7fea58305500 | 0x7fe94c636640 | 12074243700458650 | 12074243700471485 | 12074243700643323 | 12074243700646609 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7fea58305400 | 0x7fe94c636680 | 12074243700683137 | 12074243700695323 | 12074243700820922 | 12074243700824189 |
| 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 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7fea58305300 | 0x7fe94c6366c0 | 12074243700850128 | 12074243700861721 | 12074243701114199 | 12074243701141649 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7fea58305a00 | 0x7fe94c636700 | 12074243701163239 | 12074243701175318 | 12074243701421076 | 12074243701444552 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7fea58305900 | 0x7fe94c636740 | 12074243701465581 | 12074243701478036 | 12074243701603155 | 12074243701606483 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7fea58305800 | 0x7fe94c636780 | 12074243701632682 | 12074243701645714 | 12074243701827953 | 12074243701831351 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7fea58305700 | 0x7fe94c6367c0 | 12074243701867668 | 12074243701878832 | 12074243702004431 | 12074243702007708 |
| 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 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7fea58305600 | 0x7fe94c636800 | 12074243702035119 | 12074243702046831 | 12074243702309548 | 12074243702335838 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7fea58305500 | 0x7fe94c636840 | 12074243702356727 | 12074243702368268 | 12074243702613226 | 12074243702636667 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7fea58305400 | 0x7fe94c636880 | 12074243702657326 | 12074243702668745 | 12074243702794664 | 12074243702798037 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7fea58305300 | 0x7fe94c6368c0 | 12074243702826330 | 12074243702837544 | 12074243703028262 | 12074243703032062 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7fea58305a00 | 0x7fe94c636900 | 12074243703069221 | 12074243703081221 | 12074243703206980 | 12074243703210073 |
| 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 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7fea58305900 | 0x7fe94c636940 | 12074243703236311 | 12074243703248900 | 12074243703531457 | 12074243703555124 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7fea58305800 | 0x7fe94c636980 | 12074243703576193 | 12074243703588577 | 12074243703838655 | 12074243703861383 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7fea58305700 | 0x7fe94c6369c0 | 12074243703881230 | 12074243703892254 | 12074243704018493 | 12074243704021681 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7fea58305600 | 0x7fe94c636a00 | 12074243704048881 | 12074243704059933 | 12074243704268091 | 12074243704291823 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7fea58305500 | 0x7fe94c636a40 | 12074243704322289 | 12074243704333370 | 12074243704462009 | 12074243704464844 |
| 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 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7fea58305400 | 0x7fe94c636a80 | 12074243704491163 | 12074243704502329 | 12074243704808726 | 12074243704828139 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7fea58305300 | 0x7fe94c636ac0 | 12074243704852064 | 12074243704863286 | 12074243705112563 | 12074243705140339 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7fea58305a00 | 0x7fe94c636b00 | 12074243705161058 | 12074243705173523 | 12074243705301362 | 12074243705304534 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7fea58305900 | 0x7fe94c636b40 | 12074243705330212 | 12074243705342801 | 12074243705569999 | 12074243705592970 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7fea58305800 | 0x7fe94c636b80 | 12074243705624429 | 12074243705635759 | 12074243705762798 | 12074243705766022 |
| 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 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7fea58305700 | 0x7fe94c636bc0 | 12074243705791539 | 12074243705802797 | 12074243706131114 | 12074243706162609 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7fea58305600 | 0x7fe94c636c00 | 12074243706184129 | 12074243706195434 | 12074243706445671 | 12074243706469689 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7fea58305500 | 0x7fe94c636c40 | 12074243706491139 | 12074243706502151 | 12074243706630150 | 12074243706633313 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7fea58305400 | 0x7fe94c636c80 | 12074243706661335 | 12074243706672709 | 12074243706916867 | 12074243706939482 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7fea58305300 | 0x7fe94c636cc0 | 12074243706971652 | 12074243706984707 | 12074243707113826 | 12074243707117433 |
| 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 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7fea58305a00 | 0x7fe94c636d00 | 12074243707144804 | 12074243707155425 | 12074243707531102 | 12074243707554846 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7fea58305900 | 0x7fe94c636d40 | 12074243707575354 | 12074243707586621 | 12074243707847739 | 12074243707870592 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7fea58305800 | 0x7fe94c636d80 | 12074243707890820 | 12074243707901979 | 12074243708031257 | 12074243708034497 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7fea58305700 | 0x7fe94c636dc0 | 12074243708062389 | 12074243708073657 | 12074243708351735 | 12074243708375881 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7fea58305600 | 0x7fe94c636e00 | 12074243708405777 | 12074243708418294 | 12074243708553973 | 12074243708556938 |
| 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 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7fea58305500 | 0x7fe94c636e40 | 12074243708583657 | 12074243708595892 | 12074243709019409 | 12074243709048942 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7fea58305400 | 0x7fe94c636e80 | 12074243709072816 | 12074243709085488 | 12074243709339246 | 12074243709365841 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7fea58305300 | 0x7fe94c636ec0 | 12074243709385988 | 12074243709398605 | 12074243709534444 | 12074243709537620 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7fea58305a00 | 0x7fe94c636f00 | 12074243709563338 | 12074243709574604 | 12074243709918281 | 12074243709941851 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7fea58305900 | 0x7fe94c636f40 | 12074243709973239 | 12074243709985640 | 12074243710136999 | 12074243710140921 |
| 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 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7fea58305800 | 0x7fe94c636f80 | 12074243710167610 | 12074243710179398 | 12074243710695554 | 12074243710724575 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7fea58305700 | 0x7fe94c636fc0 | 12074243710746967 | 12074243710757953 | 12074243711059870 | 12074243711087369 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7fea58305600 | 0x7fe94c637000 | 12074243711108899 | 12074243711120030 | 12074243711273629 | 12074243711276801 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7fea58305500 | 0x7fe94c637040 | 12074243711304122 | 12074243711314908 | 12074243711700665 | 12074243711727739 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7fea58305400 | 0x7fe94c637080 | 12074243711758937 | 12074243711772504 | 12074243711948183 | 12074243711951445 |
| 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 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7fea58305300 | 0x7fe94c6370c0 | 12074243711978205 | 12074243711990582 | 12074243712601297 | 12074243712632921 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7fea58305a00 | 0x7fe94c637100 | 12074243712653349 | 12074243712664336 | 12074243712990253 | 12074243713019049 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7fea58305900 | 0x7fe94c637140 | 12074243713041440 | 12074243713053773 | 12074243713231851 | 12074243713235160 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7fea58305800 | 0x7fe94c637180 | 12074243713261639 | 12074243713274251 | 12074243713729287 | 12074243713757972 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7fea58305700 | 0x7fe94c6371c0 | 12074243713789881 | 12074243713802886 | 12074243714001604 | 12074243714030207 |
| 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 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7fea58305600 | 0x7fe94c637200 | 12074243714050666 | 12074243714062084 | 12074243714765437 | 12074243714792795 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7fea58305500 | 0x7fe94c637240 | 12074243714816579 | 12074243714827997 | 12074243715227353 | 12074243715261315 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7fea58305400 | 0x7fe94c637280 | 12074243715282404 | 12074243715293753 | 12074243715496311 | 12074243715523763 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7fea58305300 | 0x7fe94c6372c0 | 12074243715545824 | 12074243715557430 | 12074243716082546 | 12074243716111585 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7fea58305a00 | 0x7fe94c637300 | 12074243716143454 | 12074243716155345 | 12074243716379343 | 12074243716406012 |
| 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 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7fea58305900 | 0x7fe94c637340 | 12074243716428784 | 12074243716439983 | 12074243717240775 | 12074243717269547 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7fea58305800 | 0x7fe94c637380 | 12074243717291968 | 12074243717303495 | 12074243717723491 | 12074243717750901 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7fea58305700 | 0x7fe94c6373c0 | 12074243717773002 | 12074243717784611 | 12074243718008929 | 12074243718037483 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7fea58305600 | 0x7fe94c637400 | 12074243718061258 | 12074243718072448 | 12074243718668763 | 12074243718695576 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7fea58305500 | 0x7fe94c637440 | 12074243718728187 | 12074243718739642 | 12074243719008440 | 12074243719038824 |
| 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 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7fea58305400 | 0x7fe94c637480 | 12074243719059513 | 12074243719070519 | 12074243720055630 | 12074243720085128 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7fea58305300 | 0x7fe94c6374c0 | 12074243720105827 | 12074243720116590 | 12074243720631945 | 12074243720658985 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7fea58305a00 | 0x7fe94c637500 | 12074243720679923 | 12074243720691305 | 12074243720963622 | 12074243720990931 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7fea58305900 | 0x7fe94c637540 | 12074243721018513 | 12074243721030182 | 12074243721767775 | 12074243721796508 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7fea58305800 | 0x7fe94c637580 | 12074243721832495 | 12074243721843294 | 12074243722158172 | 12074243722190039 |
| 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 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7fea58305700 | 0x7fe94c6375c0 | 12074243722212842 | 12074243722224251 | 12074243723395601 | 12074243723426106 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7fea58305600 | 0x7fe94c637600 | 12074243723453818 | 12074243723464720 | 12074243724072235 | 12074243724101361 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7fea58305500 | 0x7fe94c637640 | 12074243724126588 | 12074243724137674 | 12074243724456551 | 12074243724484533 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7fea58305400 | 0x7fe94c637680 | 12074243724506774 | 12074243724517991 | 12074243725395103 | 12074243725424359 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7fea58305300 | 0x7fe94c6376c0 | 12074243725456238 | 12074243725468862 | 12074243725876699 | 12074243725907156 |
| 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 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7fea58305a00 | 0x7fe94c637700 | 12074243725930079 | 12074243725941018 | 12074243727490924 | 12074243727565958 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7fea58305900 | 0x7fe94c637740 | 12074243727588751 | 12074243727601021 | 12074243728396695 | 12074243728474006 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7fea58305800 | 0x7fe94c637780 | 12074243728493311 | 12074243728505173 | 12074243728919090 | 12074243728990405 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7fea58305700 | 0x7fe94c6377c0 | 12074243729022435 | 12074243729034129 | 12074243730192520 | 12074243730266055 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7fea58305600 | 0x7fe94c637800 | 12074243730301341 | 12074243730312839 | 12074243731098433 | 12074243731171788 |
| 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 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7fea58305500 | 0x7fe94c637840 | 12074243731199860 | 12074243731211232 | 12074243734264489 | 12074243734335377 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7fea58305400 | 0x7fe94c637880 | 12074243734361926 | 12074243734373288 | 12074243735915196 | 12074243735986314 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7fea58305300 | 0x7fe94c6378c0 | 12074243736014136 | 12074243736025755 | 12074243736815669 | 12074243736886367 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7fea58305a00 | 0x7fe94c637900 | 12074243736909329 | 12074243736920788 | 12074243739203171 | 12074243739278622 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7fea58305900 | 0x7fe94c637940 | 12074243739313567 | 12074243739325410 | 12074243740860438 | 12074243740931593 |
| 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 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7fea58305800 | 0x7fe94c637980 | 12074243740954826 | 12074243740966197 | 12074243747022311 | 12074243747096799 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7fea58305700 | 0x7fe94c6379c0 | 12074243747121134 | 12074243747132710 | 12074243750176046 | 12074243750252092 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7fea58305600 | 0x7fe94c637a00 | 12074243750277970 | 12074243750289645 | 12074243751829154 | 12074243751900034 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 815652 | 815657 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7fea58305500 | 0x7fe94c637a40 | 12074243751923748 | 12074243751934753 | 12074243756462398 | 12074243756537731 |