989e29cf81
Signed-off-by: Jose Santos <josantos@login1.hpcfund>
46 KiB
46 KiB
| 1 | Dispatch_ID | Kernel_Name | GPU_ID | queue-id | queue-index | pid | tid | grd | Workgroup_Size | LDS_Per_Workgroup | scr | vgpr | SGPR | fbar | sig | obj | GRBM_COUNT | GRBM_GUI_ACTIVE | SQ_WAVES | SQ_IFETCH | SQ_IFETCH_LEVEL | SQ_ACCUM_PREV_HIRES | DispatchNs | Start_Timestamp | End_Timestamp | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBuffer.kd | 0 | 0 | 0 | 894519 | 894524 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7fbd92804180 | 500721 | 500721 | 524288 | 6291456 | 791858 | 101408836 | 12075821832194819 | 12075822077796279 | 12075822078117717 | 12075822078232389 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 894519 | 894524 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7fbd92835100 | 27875 | 27875 | 512 | 8192 | 8931 | 1153012 | 12075822092747455 | 12075822093085159 | 12075822093091559 | 12075822093100361 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7fbe9e487900 | 0x7fbd92835140 | 217572 | 217572 | 65536 | 917504 | 146298 | 18793520 | 12075822093156745 | 12075822093388837 | 12075822093521476 | 12075822093524258 |
| 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 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7fbe9e487800 | 0x7fbd92835180 | 388233 | 388233 | 65536 | 1245184 | 181290 | 23213684 | 12075822093593607 | 12075822093772995 | 12075822094020834 | 12075822094118062 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7fbe9e487700 | 0x7fbd928351c0 | 390235 | 390235 | 65536 | 983040 | 146283 | 18592192 | 12075822094142728 | 12075822094397472 | 12075822094644991 | 12075822094715492 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7fbe9e487600 | 0x7fbd92835200 | 216057 | 216057 | 65536 | 1048576 | 157920 | 20202960 | 12075822094741020 | 12075822094939069 | 12075822095071868 | 12075822095074840 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7fbe9e487500 | 0x7fbd92835240 | 218652 | 218652 | 65536 | 983040 | 148864 | 19019232 | 12075822095117900 | 12075822095316987 | 12075822095450587 | 12075822095453183 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7fbe9e487400 | 0x7fbd92835280 | 216673 | 216673 | 65536 | 1048576 | 148636 | 19063604 | 12075822095528964 | 12075822095703225 | 12075822095836505 | 12075822095839191 |
| 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 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7fbe9e487300 | 0x7fbd928352c0 | 393388 | 393388 | 65536 | 1572864 | 229729 | 29430020 | 12075822095890496 | 12075822096077623 | 12075822096328182 | 12075822096398540 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7fbe9e487a00 | 0x7fbd92835300 | 397897 | 397897 | 65536 | 1179648 | 158094 | 20256140 | 12075822096417545 | 12075822096623060 | 12075822096877299 | 12075822096921472 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7fbe9e487900 | 0x7fbd92835340 | 208547 | 208547 | 65536 | 1114112 | 156698 | 20130672 | 12075822096949153 | 12075822097144818 | 12075822097271857 | 12075822097274678 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7fbe9e487800 | 0x7fbd92835380 | 220649 | 220649 | 65536 | 1114112 | 156939 | 20088692 | 12075822097319782 | 12075822097509456 | 12075822097645615 | 12075822097647962 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7fbe9e487700 | 0x7fbd928353c0 | 219155 | 219155 | 65536 | 1179648 | 171411 | 21971496 | 12075822097715628 | 12075822097890414 | 12075822098022573 | 12075822098025444 |
| 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 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7fbe9e487600 | 0x7fbd92835400 | 405017 | 405017 | 65536 | 1835008 | 256074 | 32803420 | 12075822098078452 | 12075822098268492 | 12075822098527051 | 12075822098595764 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7fbe9e487500 | 0x7fbd92835440 | 402459 | 402459 | 65536 | 1310720 | 177202 | 22726616 | 12075822098624707 | 12075822098814089 | 12075822099068328 | 12075822099138833 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7fbe9e487400 | 0x7fbd92835480 | 211385 | 211385 | 65536 | 1245184 | 173333 | 22237848 | 12075822099167596 | 12075822099364646 | 12075822099494246 | 12075822099496918 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7fbe9e487300 | 0x7fbd928354c0 | 208916 | 208916 | 65536 | 1310720 | 184995 | 23663428 | 12075822099548444 | 12075822099730084 | 12075822099857444 | 12075822099860073 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7fbe9e487a00 | 0x7fbd92835500 | 214201 | 214201 | 65536 | 1310720 | 181370 | 23199868 | 12075822099924152 | 12075822100100642 | 12075822100232322 | 12075822100235311 |
| 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 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7fbe9e487900 | 0x7fbd92835540 | 397388 | 397388 | 65536 | 2097152 | 299487 | 38299288 | 12075822100289692 | 12075822100465441 | 12075822100718559 | 12075822100788278 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7fbe9e487800 | 0x7fbd92835580 | 390585 | 390585 | 65536 | 1441792 | 197221 | 25199740 | 12075822100814787 | 12075822101004958 | 12075822101254397 | 12075822101324916 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7fbe9e487700 | 0x7fbd928355c0 | 214836 | 214836 | 65536 | 1376256 | 187291 | 23999996 | 12075822101353749 | 12075822101547675 | 12075822101678714 | 12075822101681218 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7fbe9e487600 | 0x7fbd92835600 | 212401 | 212401 | 65536 | 1507328 | 217945 | 27870204 | 12075822101731952 | 12075822101911353 | 12075822102042072 | 12075822102045014 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7fbe9e487500 | 0x7fbd92835640 | 209131 | 209131 | 65536 | 1441792 | 200570 | 25632148 | 12075822102110105 | 12075822102284951 | 12075822102412471 | 12075822102415132 |
| 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 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7fbe9e487400 | 0x7fbd92835680 | 401241 | 401241 | 65536 | 2359296 | 327821 | 41968500 | 12075822102463331 | 12075822102649589 | 12075822102906708 | 12075822102976024 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7fbe9e487300 | 0x7fbd928356c0 | 392499 | 392499 | 65536 | 1572864 | 210674 | 27034872 | 12075822103010729 | 12075822103203506 | 12075822103453105 | 12075822103524624 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7fbe9e487a00 | 0x7fbd92835700 | 208289 | 208289 | 65536 | 1507328 | 210341 | 26910112 | 12075822103550001 | 12075822103746384 | 12075822103874383 | 12075822103877109 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7fbe9e487900 | 0x7fbd92835740 | 217396 | 217396 | 65536 | 1703936 | 240233 | 30760988 | 12075822103926961 | 12075822104115022 | 12075822104248301 | 12075822104251074 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7fbe9e487800 | 0x7fbd92835780 | 213217 | 213217 | 65536 | 1572864 | 211670 | 27101220 | 12075822104314472 | 12075822104485100 | 12075822104616459 | 12075822104619188 |
| 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 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7fbe9e487700 | 0x7fbd928357c0 | 390972 | 390972 | 65536 | 2621440 | 355411 | 45588192 | 12075822104664853 | 12075822104850378 | 12075822105100297 | 12075822105173207 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7fbe9e487600 | 0x7fbd92835800 | 394425 | 394425 | 65536 | 1703936 | 230936 | 29574992 | 12075822105193756 | 12075822105390375 | 12075822105642694 | 12075822105712159 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7fbe9e487500 | 0x7fbd92835840 | 214931 | 214931 | 65536 | 1638400 | 229891 | 29472504 | 12075822105739851 | 12075822105926532 | 12075822106057732 | 12075822106060877 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7fbe9e487400 | 0x7fbd92835880 | 208713 | 208713 | 65536 | 1900544 | 272653 | 34940372 | 12075822106105360 | 12075822106298530 | 12075822106427170 | 12075822106429983 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7fbe9e487300 | 0x7fbd928358c0 | 212228 | 212228 | 65536 | 1703936 | 232246 | 29691084 | 12075822106492149 | 12075822106662689 | 12075822106792288 | 12075822106795021 |
| 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 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7fbe9e487a00 | 0x7fbd92835900 | 398241 | 398241 | 65536 | 2883584 | 397456 | 50969716 | 12075822106837771 | 12075822107035007 | 12075822107290685 | 12075822107363458 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7fbe9e487900 | 0x7fbd92835940 | 397427 | 397427 | 65536 | 1835008 | 247624 | 31720792 | 12075822107389196 | 12075822107581244 | 12075822107834523 | 12075822107904323 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7fbe9e487800 | 0x7fbd92835980 | 212529 | 212529 | 65536 | 1769472 | 270047 | 34636148 | 12075822107930021 | 12075822108119801 | 12075822108250840 | 12075822108253813 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7fbe9e487700 | 0x7fbd928359c0 | 221899 | 221899 | 65536 | 2097152 | 301535 | 38596532 | 12075822108296963 | 12075822108489239 | 12075822108625558 | 12075822108628549 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7fbe9e487600 | 0x7fbd92835a00 | 220105 | 220105 | 65536 | 1835008 | 252909 | 32418732 | 12075822108692378 | 12075822108863157 | 12075822108998997 | 12075822109007613 |
| 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 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7fbe9e487500 | 0x7fbd92835a40 | 406579 | 406579 | 65536 | 3145728 | 416444 | 53420440 | 12075822109048279 | 12075822109237395 | 12075822109497554 | 12075822109568055 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7fbe9e487400 | 0x7fbd92835a80 | 384977 | 384977 | 65536 | 1966080 | 261674 | 33422292 | 12075822109588313 | 12075822109780432 | 12075822110027631 | 12075822110078153 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7fbe9e487300 | 0x7fbd92835ac0 | 217740 | 217740 | 65536 | 1900544 | 273739 | 35049532 | 12075822110102288 | 12075822110299470 | 12075822110432749 | 12075822110435387 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7fbe9e487a00 | 0x7fbd92835b00 | 217465 | 217465 | 65536 | 2293760 | 321013 | 41060132 | 12075822110486061 | 12075822110666828 | 12075822110801707 | 12075822110804373 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7fbe9e487900 | 0x7fbd92835b40 | 208451 | 208451 | 65536 | 1966080 | 270864 | 34703028 | 12075822110869143 | 12075822111048906 | 12075822111176425 | 12075822111179440 |
| 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 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7fbe9e487800 | 0x7fbd92835b80 | 402185 | 402185 | 65536 | 3407872 | 458781 | 58792868 | 12075822111226327 | 12075822111412424 | 12075822111671303 | 12075822111741184 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7fbe9e487700 | 0x7fbd92835bc0 | 385747 | 385747 | 65536 | 2097152 | 277792 | 35579964 | 12075822111768104 | 12075822111953861 | 12075822112200900 | 12075822112270497 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7fbe9e487600 | 0x7fbd92835c00 | 209793 | 209793 | 65536 | 2031616 | 297049 | 38019012 | 12075822112300724 | 12075822112487618 | 12075822112617218 | 12075822112619807 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7fbe9e487500 | 0x7fbd92835c40 | 218483 | 218483 | 65536 | 2490368 | 344741 | 44077924 | 12075822112672144 | 12075822112846337 | 12075822112980896 | 12075822112983533 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7fbe9e487400 | 0x7fbd92835c80 | 217545 | 217545 | 65536 | 2097152 | 302054 | 38741136 | 12075822113047371 | 12075822113220255 | 12075822113354014 | 12075822113356756 |
| 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 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7fbe9e487300 | 0x7fbd92835cc0 | 414739 | 414739 | 65536 | 3670016 | 491691 | 62895576 | 12075822113409354 | 12075822113592253 | 12075822113858491 | 12075822113903963 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7fbe9e487a00 | 0x7fbd92835d00 | 402505 | 402505 | 65536 | 2228224 | 298116 | 38120852 | 12075822113931354 | 12075822114133530 | 12075822114392089 | 12075822114462601 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7fbe9e487900 | 0x7fbd92835d40 | 212340 | 212340 | 65536 | 2162688 | 322823 | 41354932 | 12075822114483330 | 12075822114678007 | 12075822114808406 | 12075822114811069 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7fbe9e487800 | 0x7fbd92835d80 | 224193 | 224193 | 65536 | 2686976 | 399701 | 51304472 | 12075822114863066 | 12075822115042645 | 12075822115182485 | 12075822115185525 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7fbe9e487700 | 0x7fbd92835dc0 | 220083 | 220083 | 65536 | 2228224 | 350363 | 44866324 | 12075822115250626 | 12075822115422963 | 12075822115558163 | 12075822115561063 |
| 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 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7fbe9e487600 | 0x7fbd92835e00 | 404561 | 404561 | 65536 | 3932160 | 536083 | 68664516 | 12075822115605826 | 12075822115786961 | 12075822116047760 | 12075822116118769 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7fbe9e487500 | 0x7fbd92835e40 | 384852 | 384852 | 65536 | 2359296 | 321450 | 40958096 | 12075822116145098 | 12075822116334479 | 12075822116580877 | 12075822116650908 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7fbe9e487400 | 0x7fbd92835e80 | 214081 | 214081 | 65536 | 2293760 | 321454 | 41125392 | 12075822116676456 | 12075822116866316 | 12075822116998635 | 12075822117004545 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7fbe9e487300 | 0x7fbd92835ec0 | 228580 | 228580 | 65536 | 2883584 | 400445 | 51442368 | 12075822117054939 | 12075822117243274 | 12075822117385193 | 12075822117387858 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7fbe9e487a00 | 0x7fbd92835f00 | 211457 | 211457 | 65536 | 2359296 | 328891 | 42056924 | 12075822117451035 | 12075822117620872 | 12075822117751591 | 12075822117754349 |
| 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 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7fbe9e487900 | 0x7fbd92835f40 | 412340 | 412340 | 65536 | 4194304 | 576028 | 73708732 | 12075822117800585 | 12075822117981830 | 12075822118247589 | 12075822118319579 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7fbe9e487800 | 0x7fbd92835f80 | 398961 | 398961 | 65536 | 2490368 | 333036 | 42614540 | 12075822118340057 | 12075822118532707 | 12075822118789666 | 12075822118859894 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7fbe9e487700 | 0x7fbd92835fc0 | 214228 | 214228 | 65536 | 2424832 | 332232 | 42620728 | 12075822118887284 | 12075822119077344 | 12075822119208704 | 12075822119211928 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7fbe9e487600 | 0x7fbd92836000 | 225897 | 225897 | 65536 | 3080192 | 508355 | 65195272 | 12075822119259516 | 12075822119443423 | 12075822119582782 | 12075822119585482 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7fbe9e487500 | 0x7fbd92836040 | 217899 | 217899 | 65536 | 2490368 | 343225 | 44013468 | 12075822119651334 | 12075822119821341 | 12075822119955100 | 12075822119958094 |
| 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 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7fbe9e487400 | 0x7fbd92836080 | 403017 | 403017 | 65536 | 4456448 | 585855 | 75107276 | 12075822120011093 | 12075822120201659 | 12075822120460857 | 12075822120530388 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7fbe9e487300 | 0x7fbd928360c0 | 394203 | 394203 | 65536 | 2621440 | 345598 | 44048692 | 12075822120555104 | 12075822120748056 | 12075822121001174 | 12075822121071694 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7fbe9e487a00 | 0x7fbd92836100 | 220137 | 220137 | 65536 | 2555904 | 384532 | 49163740 | 12075822121097512 | 12075822121294453 | 12075822121430932 | 12075822121433707 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7fbe9e487900 | 0x7fbd92836140 | 229419 | 229419 | 65536 | 3276800 | 489314 | 62559476 | 12075822121479241 | 12075822121672691 | 12075822121815410 | 12075822121818382 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7fbe9e487800 | 0x7fbd92836180 | 213697 | 213697 | 65536 | 2621440 | 411821 | 52738288 | 12075822121882020 | 12075822122056049 | 12075822122188528 | 12075822122191876 |
| 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 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7fbe9e487700 | 0x7fbd928361c0 | 410916 | 410916 | 65536 | 4718592 | 657144 | 84113668 | 12075822122243281 | 12075822122424207 | 12075822122689486 | 12075822122760252 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7fbe9e487600 | 0x7fbd92836200 | 387217 | 387217 | 65536 | 2752512 | 362889 | 46480876 | 12075822122786120 | 12075822122973804 | 12075822123223403 | 12075822123295487 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7fbe9e487500 | 0x7fbd92836240 | 219428 | 219428 | 65536 | 2686976 | 461975 | 59245692 | 12075822123321696 | 12075822123508522 | 12075822123643721 | 12075822123646329 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7fbe9e487400 | 0x7fbd92836280 | 239553 | 239553 | 65536 | 3473408 | 510305 | 65217684 | 12075822123696923 | 12075822123875720 | 12075822124026279 | 12075822124029311 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7fbe9e487300 | 0x7fbd928362c0 | 220515 | 220515 | 65536 | 2752512 | 430348 | 55136092 | 12075822124112345 | 12075822124283238 | 12075822124419077 | 12075822124421810 |
| 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 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7fbe9e487a00 | 0x7fbd92836300 | 410857 | 410857 | 65536 | 4980736 | 656585 | 83981548 | 12075822124466884 | 12075822124650596 | 12075822124916994 | 12075822124967224 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7fbe9e487900 | 0x7fbd92836340 | 455012 | 455012 | 65536 | 2883584 | 378732 | 48638572 | 12075822124994274 | 12075822125185313 | 12075822125479231 | 12075822125530651 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7fbe9e487800 | 0x7fbd92836380 | 215441 | 215441 | 65536 | 2818048 | 416921 | 53428952 | 12075822125559715 | 12075822125751230 | 12075822125883549 | 12075822125886262 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7fbe9e487700 | 0x7fbd928363c0 | 252419 | 252419 | 65536 | 3670016 | 555025 | 71174780 | 12075822125937637 | 12075822126135868 | 12075822126293947 | 12075822126296885 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7fbe9e487600 | 0x7fbd92836400 | 224985 | 224985 | 65536 | 2883584 | 407358 | 52003124 | 12075822126361234 | 12075822126530426 | 12075822126669625 | 12075822126672573 |
| 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 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7fbe9e487500 | 0x7fbd92836440 | 401308 | 401308 | 65536 | 5177344 | 691863 | 88529416 | 12075822126718879 | 12075822126901784 | 12075822127161463 | 12075822127215953 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7fbe9e487400 | 0x7fbd92836480 | 388265 | 388265 | 65536 | 3014656 | 398395 | 50885440 | 12075822127244185 | 12075822127432821 | 12075822127683220 | 12075822127734236 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7fbe9e487300 | 0x7fbd928364c0 | 215827 | 215827 | 65536 | 2949120 | 406632 | 52020956 | 12075822127758772 | 12075822127950579 | 12075822128084018 | 12075822128087312 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7fbe9e487a00 | 0x7fbd92836500 | 266625 | 266625 | 65536 | 3866624 | 562373 | 72027648 | 12075822128142866 | 12075822128317777 | 12075822128483856 | 12075822128486644 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7fbe9e487900 | 0x7fbd92836540 | 218972 | 218972 | 65536 | 3014656 | 437106 | 56014972 | 12075822128553308 | 12075822128723215 | 12075822128858734 | 12075822128861571 |
| 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 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7fbe9e487800 | 0x7fbd92836580 | 398697 | 398697 | 65536 | 5439488 | 711851 | 91163332 | 12075822128907557 | 12075822129099533 | 12075822129357451 | 12075822129385685 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7fbe9e487700 | 0x7fbd928365c0 | 395068 | 395068 | 65536 | 3145728 | 423464 | 54138684 | 12075822129433564 | 12075822129603050 | 12075822129857769 | 12075822129884592 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7fbe9e487600 | 0x7fbd92836600 | 220137 | 220137 | 65536 | 3080192 | 508986 | 65123116 | 12075822129932802 | 12075822130117927 | 12075822130254087 | 12075822130256924 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7fbe9e487500 | 0x7fbd92836640 | 276156 | 276156 | 65536 | 4063232 | 595340 | 76499592 | 12075822130306477 | 12075822130486085 | 12075822130660485 | 12075822130663480 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7fbe9e487400 | 0x7fbd92836680 | 220233 | 220233 | 65536 | 3145728 | 464929 | 59565464 | 12075822130731677 | 12075822130902883 | 12075822131039043 | 12075822131042214 |
| 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 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7fbe9e487300 | 0x7fbd928366c0 | 398652 | 398652 | 65536 | 5701632 | 752008 | 96333352 | 12075822131086606 | 12075822131281761 | 12075822131540640 | 12075822131569293 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7fbe9e487a00 | 0x7fbd92836700 | 392641 | 392641 | 65536 | 3276800 | 458173 | 58829472 | 12075822131615780 | 12075822131783999 | 12075822132037597 | 12075822132066197 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7fbe9e487900 | 0x7fbd92836740 | 217356 | 217356 | 65536 | 3211264 | 459020 | 58688268 | 12075822132119095 | 12075822132292636 | 12075822132427355 | 12075822132430424 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7fbe9e487800 | 0x7fbd92836780 | 288201 | 288201 | 65536 | 4259840 | 613522 | 78105084 | 12075822132481569 | 12075822132661594 | 12075822132844473 | 12075822132847188 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7fbe9e487700 | 0x7fbd928367c0 | 221763 | 221763 | 65536 | 3276800 | 491746 | 62922300 | 12075822132910185 | 12075822133088152 | 12075822133225431 | 12075822133228507 |
| 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 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7fbe9e487600 | 0x7fbd92836800 | 410169 | 410169 | 65536 | 7733248 | 977628 | 125313328 | 12075822133272248 | 12075822133460310 | 12075822133726549 | 12075822133754054 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7fbe9e487500 | 0x7fbd92836840 | 385692 | 385692 | 65536 | 3407872 | 445093 | 56942240 | 12075822133801652 | 12075822133973107 | 12075822134222546 | 12075822134252770 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7fbe9e487400 | 0x7fbd92836880 | 220985 | 220985 | 65536 | 3342336 | 476684 | 61026060 | 12075822134289429 | 12075822134472465 | 12075822134609264 | 12075822134612269 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7fbe9e487300 | 0x7fbd928368c0 | 302540 | 302540 | 65536 | 4456448 | 636059 | 81664664 | 12075822134663033 | 12075822134842383 | 12075822135035182 | 12075822135062305 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7fbe9e487a00 | 0x7fbd92836900 | 220273 | 220273 | 65536 | 3538944 | 573696 | 73426376 | 12075822135124571 | 12075822135300941 | 12075822135437740 | 12075822135440478 |
| 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 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7fbe9e487900 | 0x7fbd92836940 | 435500 | 435500 | 65536 | 8978432 | 1129910 | 144517116 | 12075822135490972 | 12075822135669579 | 12075822135953897 | 12075822135980562 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7fbe9e487800 | 0x7fbd92836980 | 397201 | 397201 | 65536 | 3670016 | 506615 | 64916360 | 12075822136033810 | 12075822136206376 | 12075822136463335 | 12075822136490640 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7fbe9e487700 | 0x7fbd928369c0 | 226012 | 226012 | 65536 | 3604480 | 539302 | 68952840 | 12075822136533469 | 12075822136702373 | 12075822136842853 | 12075822136845739 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7fbe9e487600 | 0x7fbd92836a00 | 328809 | 328809 | 65536 | 4849664 | 734856 | 93977396 | 12075822136891314 | 12075822137080131 | 12075822137290210 | 12075822137317937 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7fbe9e487500 | 0x7fbd92836a40 | 216060 | 216060 | 65536 | 3801088 | 601519 | 77076060 | 12075822137374773 | 12075822137546209 | 12075822137680448 | 12075822137683206 |
| 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 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7fbe9e487400 | 0x7fbd92836a80 | 471257 | 471257 | 65536 | 14548992 | 1828440 | 233842540 | 12075822137733850 | 12075822137917087 | 12075822138225405 | 12075822138255059 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7fbe9e487300 | 0x7fbd92836ac0 | 383443 | 383443 | 65536 | 3932160 | 551860 | 70473684 | 12075822138291356 | 12075822138465884 | 12075822138714203 | 12075822138739619 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7fbe9e487a00 | 0x7fbd92836b00 | 217689 | 217689 | 65536 | 3866624 | 575989 | 73883680 | 12075822138788750 | 12075822138960282 | 12075822139095321 | 12075822139098586 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7fbe9e487900 | 0x7fbd92836b40 | 358764 | 358764 | 65536 | 5242880 | 779297 | 99234604 | 12075822139148329 | 12075822139332280 | 12075822139560439 | 12075822139586603 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7fbe9e487800 | 0x7fbd92836b80 | 227761 | 227761 | 65536 | 4063232 | 635652 | 81457508 | 12075822139648328 | 12075822139821237 | 12075822139962997 | 12075822139965678 |
| 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 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7fbe9e487700 | 0x7fbd92836bc0 | 504868 | 504868 | 65536 | 10027008 | 1264044 | 161473328 | 12075822140014017 | 12075822140202675 | 12075822140533714 | 12075822140558840 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7fbe9e487600 | 0x7fbd92836c00 | 396177 | 396177 | 65536 | 4194304 | 582248 | 74486932 | 12075822140603162 | 12075822140771617 | 12075822141028256 | 12075822141057537 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7fbe9e487500 | 0x7fbd92836c40 | 227491 | 227491 | 65536 | 4128768 | 625780 | 80080000 | 12075822141103582 | 12075822141274814 | 12075822141414813 | 12075822141416895 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7fbe9e487400 | 0x7fbd92836c80 | 381657 | 381657 | 65536 | 5636096 | 769845 | 98461652 | 12075822141468811 | 12075822141654332 | 12075822141899451 | 12075822141923005 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7fbe9e487300 | 0x7fbd92836cc0 | 219531 | 219531 | 65536 | 4587520 | 689804 | 88260676 | 12075822141980763 | 12075822142160730 | 12075822142297209 | 12075822142299806 |
| 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 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7fbe9e487a00 | 0x7fbd92836d00 | 577881 | 577881 | 65536 | 11075584 | 1391452 | 178035044 | 12075822142351181 | 12075822142533048 | 12075822142911927 | 12075822142935577 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7fbe9e487900 | 0x7fbd92836d40 | 408427 | 408427 | 65536 | 4718592 | 614273 | 78243160 | 12075822142974169 | 12075822143149526 | 12075822143414485 | 12075822143441658 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7fbe9e487800 | 0x7fbd92836d80 | 225849 | 225849 | 65536 | 4653056 | 694422 | 88983384 | 12075822143485479 | 12075822143653844 | 12075822143794643 | 12075822143796697 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7fbe9e487700 | 0x7fbd92836dc0 | 432492 | 432492 | 65536 | 6422528 | 905097 | 115756888 | 12075822143846340 | 12075822144041842 | 12075822144321041 | 12075822144346650 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7fbe9e487600 | 0x7fbd92836e00 | 220729 | 220729 | 65536 | 5111808 | 764770 | 97992960 | 12075822144405038 | 12075822144579920 | 12075822144717359 | 12075822144719593 |
| 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 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7fbe9e487500 | 0x7fbd92836e40 | 645044 | 645044 | 65536 | 15007744 | 1882714 | 240990280 | 12075822144770718 | 12075822144948558 | 12075822145373836 | 12075822145399196 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7fbe9e487400 | 0x7fbd92836e80 | 399489 | 399489 | 65536 | 5242880 | 718943 | 92502736 | 12075822145447616 | 12075822145620555 | 12075822145879914 | 12075822145903383 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7fbe9e487300 | 0x7fbd92836ec0 | 221164 | 221164 | 65536 | 5177344 | 756547 | 96900476 | 12075822145948496 | 12075822146118153 | 12075822146256233 | 12075822146258703 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7fbe9e487a00 | 0x7fbd92836f00 | 487705 | 487705 | 65536 | 7208960 | 1057685 | 135342424 | 12075822146308856 | 12075822146501512 | 12075822146817510 | 12075822146841526 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7fbe9e487900 | 0x7fbd92836f40 | 241188 | 241188 | 65536 | 6160384 | 877744 | 112342412 | 12075822146898783 | 12075822147076869 | 12075822147228549 | 12075822147231040 |
| 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 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7fbe9e487800 | 0x7fbd92836f80 | 784361 | 784361 | 65536 | 17104896 | 2143929 | 274464596 | 12075822147276474 | 12075822147465668 | 12075822147983105 | 12075822148011701 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7fbe9e487700 | 0x7fbd92836fc0 | 452747 | 452747 | 65536 | 6291456 | 827736 | 105472684 | 12075822148055362 | 12075822148226944 | 12075822148523423 | 12075822148547577 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7fbe9e487600 | 0x7fbd92837000 | 247497 | 247497 | 65536 | 6225920 | 946734 | 121177656 | 12075822148591909 | 12075822148762142 | 12075822148917821 | 12075822148920079 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7fbe9e487500 | 0x7fbd92837040 | 594364 | 594364 | 65536 | 8781824 | 1310842 | 167729944 | 12075822148972286 | 12075822149161020 | 12075822149547739 | 12075822149573063 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7fbe9e487400 | 0x7fbd92837080 | 277817 | 277817 | 65536 | 7208960 | 1065671 | 136445596 | 12075822149632984 | 12075822149804858 | 12075822149981497 | 12075822149983606 |
| 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 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7fbe9e487300 | 0x7fbd928370c0 | 925203 | 925203 | 65536 | 19202048 | 2404025 | 307985412 | 12075822150034009 | 12075822150218136 | 12075822150829653 | 12075822150856618 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7fbe9e487a00 | 0x7fbd92837100 | 500817 | 500817 | 65536 | 7340032 | 1012144 | 129231792 | 12075822150899177 | 12075822151074292 | 12075822151403731 | 12075822151431156 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7fbe9e487900 | 0x7fbd92837140 | 282379 | 282379 | 65536 | 7274496 | 1081196 | 138403880 | 12075822151473575 | 12075822151640370 | 12075822151820529 | 12075822151822623 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7fbe9e487800 | 0x7fbd92837180 | 697353 | 697353 | 65536 | 10354688 | 1488606 | 191609912 | 12075822151872937 | 12075822152058288 | 12075822152513966 | 12075822152540087 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7fbe9e487700 | 0x7fbd928371c0 | 312756 | 312756 | 65536 | 8257536 | 1219963 | 156041680 | 12075822152602473 | 12075822152778125 | 12075822152978284 | 12075822153008858 |
| 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 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7fbe9e487600 | 0x7fbd92837200 | 1065529 | 1065529 | 65536 | 21299200 | 2668972 | 341759132 | 12075822153056246 | 12075822153226603 | 12075822153929480 | 12075822153954265 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7fbe9e487500 | 0x7fbd92837240 | 566844 | 566844 | 65536 | 8388608 | 1237410 | 157562184 | 12075822153998697 | 12075822154176519 | 12075822154549318 | 12075822154577102 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7fbe9e487400 | 0x7fbd92837280 | 318073 | 318073 | 65536 | 8323072 | 1280128 | 163940940 | 12075822154620884 | 12075822154789477 | 12075822154993156 | 12075822155018994 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7fbe9e487300 | 0x7fbd928372c0 | 802380 | 802380 | 65536 | 11927552 | 1679645 | 213861376 | 12075822155065179 | 12075822155233955 | 12075822155760673 | 12075822155788333 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7fbe9e487a00 | 0x7fbd92837300 | 348113 | 348113 | 65536 | 9306112 | 1388980 | 177710104 | 12075822155843967 | 12075822156023552 | 12075822156246911 | 12075822156273255 |
| 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 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7fbe9e487900 | 0x7fbd92837340 | 1207275 | 1207275 | 65536 | 29163520 | 3654574 | 467551100 | 12075822156312227 | 12075822156483070 | 12075822157282426 | 12075822157333415 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7fbe9e487800 | 0x7fbd92837380 | 637441 | 637441 | 65536 | 9437184 | 1268304 | 162136988 | 12075822157358411 | 12075822157558265 | 12075822157979223 | 12075822158029999 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7fbe9e487700 | 0x7fbd928373c0 | 354243 | 354243 | 65536 | 9371648 | 1435713 | 183945064 | 12075822158055146 | 12075822158252182 | 12075822158479701 | 12075822158529458 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7fbe9e487600 | 0x7fbd92837400 | 908513 | 908513 | 65536 | 13500416 | 1914662 | 245649740 | 12075822158555626 | 12075822158741460 | 12075822159337938 | 12075822159407529 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7fbe9e487500 | 0x7fbd92837440 | 417779 | 417779 | 65536 | 11403264 | 1723915 | 220652128 | 12075822159445139 | 12075822159625777 | 12075822159895375 | 12075822159964935 |
| 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 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7fbe9e487400 | 0x7fbd92837480 | 1488545 | 1488545 | 65536 | 33357824 | 4182447 | 535367516 | 12075822159988920 | 12075822160191054 | 12075822161176490 | 12075822161247228 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7fbe9e487300 | 0x7fbd928374c0 | 777891 | 777891 | 65536 | 11534336 | 1569390 | 200940572 | 12075822161271283 | 12075822161467689 | 12075822161982887 | 12075822162052124 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7fbe9e487a00 | 0x7fbd92837500 | 422105 | 422105 | 65536 | 11534336 | 1803286 | 230751708 | 12075822162075428 | 12075822162271525 | 12075822162544004 | 12075822162613377 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7fbe9e487900 | 0x7fbd92837540 | 1125636 | 1125636 | 65536 | 19267584 | 2417996 | 309650472 | 12075822162638424 | 12075822162826563 | 12075822163564480 | 12075822163636118 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7fbe9e487800 | 0x7fbd92837580 | 489881 | 489881 | 65536 | 13500416 | 2130220 | 272859960 | 12075822163672626 | 12075822163849439 | 12075822164166717 | 12075822164236263 |
| 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 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7fbe9e487700 | 0x7fbd928375c0 | 1767524 | 1767524 | 65536 | 37552128 | 4694858 | 601630088 | 12075822164263805 | 12075822164457276 | 12075822165628151 | 12075822165698311 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7fbe9e487600 | 0x7fbd92837600 | 918609 | 918609 | 65536 | 13631488 | 1862621 | 240031340 | 12075822165722496 | 12075822165919990 | 12075822166530388 | 12075822166602351 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7fbe9e487500 | 0x7fbd92837640 | 534060 | 534060 | 65536 | 13631488 | 2076236 | 265716788 | 12075822166634971 | 12075822166827666 | 12075822167174865 | 12075822167246618 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7fbe9e487400 | 0x7fbd92837680 | 1336009 | 1336009 | 65536 | 21692416 | 2751026 | 352373496 | 12075822167272636 | 12075822167468464 | 12075822168346380 | 12075822168416232 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7fbe9e487300 | 0x7fbd928376c0 | 669548 | 669548 | 65536 | 17694720 | 2847300 | 364389768 | 12075822168461526 | 12075822168638059 | 12075822169073257 | 12075822169142792 |
| 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 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7fbe9e487a00 | 0x7fbd92837700 | 2332593 | 2332593 | 65536 | 57475072 | 7195178 | 920891056 | 12075822169175313 | 12075822169366376 | 12075822170913569 | 12075822170982711 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7fbe9e487900 | 0x7fbd92837740 | 1199403 | 1199403 | 65536 | 19660800 | 2470857 | 316767596 | 12075822171013659 | 12075822171215168 | 12075822172009725 | 12075822172081373 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7fbe9e487800 | 0x7fbd92837780 | 641825 | 641825 | 65536 | 20381696 | 2577483 | 329839216 | 12075822172112782 | 12075822172299483 | 12075822172713562 | 12075822172782176 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7fbe9e487700 | 0x7fbd928377c0 | 1757331 | 1757331 | 65536 | 28704768 | 3615974 | 462508524 | 12075822172809146 | 12075822172995320 | 12075822174154036 | 12075822174224566 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7fbe9e487600 | 0x7fbd92837800 | 1197241 | 1197241 | 65536 | 36634624 | 4648879 | 595004780 | 12075822174264430 | 12075822174437874 | 12075822175223631 | 12075822175293272 |
| 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 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7fbe9e487500 | 0x7fbd92837840 | 4585244 | 4585244 | 65536 | 105840640 | 13248411 | 1694765932 | 12075822175326374 | 12075822175517870 | 12075822178568097 | 12075822178638039 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7fbe9e487400 | 0x7fbd92837880 | 2324601 | 2324601 | 65536 | 38535168 | 4835630 | 618347296 | 12075822178663496 | 12075822178859776 | 12075822180400729 | 12075822180471977 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7fbe9e487300 | 0x7fbd928378c0 | 1202587 | 1202587 | 65536 | 39124992 | 4916643 | 629358772 | 12075822180501492 | 12075822180696888 | 12075822181486165 | 12075822181556042 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7fbe9e487a00 | 0x7fbd92837900 | 3442185 | 3442185 | 65536 | 55771136 | 7009920 | 897269256 | 12075822181587660 | 12075822181778484 | 12075822184060074 | 12075822184130165 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7fbe9e487900 | 0x7fbd92837940 | 2322715 | 2322715 | 65536 | 72548352 | 9117097 | 1167026876 | 12075822184175129 | 12075822184348713 | 12075822185884066 | 12075822185953033 |
| 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 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7fbe9e487800 | 0x7fbd92837980 | 9086361 | 9086361 | 65536 | 210698240 | 26344242 | 3372632460 | 12075822185980194 | 12075822186179585 | 12075822192232360 | 12075822192301862 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7fbe9e487700 | 0x7fbd928379c0 | 4572331 | 4572331 | 65536 | 76283904 | 9558727 | 1223371188 | 12075822192327520 | 12075822192524678 | 12075822195565466 | 12075822195636970 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7fbe9e487600 | 0x7fbd92837a00 | 2328153 | 2328153 | 65536 | 77398016 | 9703622 | 1242288460 | 12075822195665964 | 12075822195858424 | 12075822197397938 | 12075822197469406 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 894519 | 894524 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7fbe9e487500 | 0x7fbd92837a40 | 6813139 | 6813139 | 65536 | 110821376 | 13888222 | 1776882460 | 12075822197493481 | 12075822197693137 | 12075822202219998 | 12075822202292289 |