46 KiB
46 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | GRBM_COUNT | GRBM_GUI_ACTIVE | SQ_WAVES | SQ_IFETCH | SQ_IFETCH_LEVEL | SQ_ACCUM_PREV_HIRES | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBuffer.kd | 0 | 0 | 0 | 763517 | 763522 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7f1e10e04180 | 505857 | 505857 | 524288 | 6291456 | 792695 | 101403392 | 12073442306812763 | 12073442552623215 | 12073442552948813 | 12073442553060085 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 763517 | 763522 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7f1e10e35100 | 28539 | 28539 | 512 | 8192 | 9217 | 1173568 | 12073442567379506 | 12073442567681010 | 12073442567687570 | 12073442567692658 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7f1f1ca96900 | 0x7f1e10e35140 | 214259 | 214259 | 65536 | 917504 | 142240 | 18192764 | 12073442567759682 | 12073442567986768 | 12073442568117488 | 12073442568121335 |
| 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 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7f1f1ca96800 | 0x7f1e10e35180 | 393065 | 393065 | 65536 | 1245184 | 186478 | 24045128 | 12073442568191485 | 12073442568370446 | 12073442568621965 | 12073442568692055 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7f1f1ca96700 | 0x7f1e10e351c0 | 401499 | 401499 | 65536 | 983040 | 136900 | 17499500 | 12073442568722141 | 12073442568916523 | 12073442569172522 | 12073442569242528 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7f1f1ca96600 | 0x7f1e10e35200 | 213081 | 213081 | 65536 | 1048576 | 160724 | 20564616 | 12073442569267755 | 12073442569460360 | 12073442569591079 | 12073442569594713 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7f1f1ca96500 | 0x7f1e10e35240 | 227035 | 227035 | 65536 | 983040 | 148738 | 19037424 | 12073442569641490 | 12073442569825158 | 12073442569964197 | 12073442569967836 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7f1f1ca96400 | 0x7f1e10e35280 | 222873 | 222873 | 65536 | 1048576 | 146512 | 18741904 | 12073442570053776 | 12073442570236036 | 12073442570373795 | 12073442570377387 |
| 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 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7f1f1ca96300 | 0x7f1e10e352c0 | 401427 | 401427 | 65536 | 1572864 | 230484 | 29428540 | 12073442570422100 | 12073442570609954 | 12073442570864352 | 12073442570907833 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7f1f1ca96a00 | 0x7f1e10e35300 | 400665 | 400665 | 65536 | 1179648 | 158696 | 20293616 | 12073442570932338 | 12073442571137151 | 12073442571394109 | 12073442571435854 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7f1f1ca96900 | 0x7f1e10e35340 | 209635 | 209635 | 65536 | 1114112 | 157401 | 20120112 | 12073442571473424 | 12073442571646588 | 12073442571774587 | 12073442571778290 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7f1f1ca96800 | 0x7f1e10e35380 | 218289 | 218289 | 65536 | 1114112 | 158885 | 20326760 | 12073442571830367 | 12073442572007066 | 12073442572139865 | 12073442572143519 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7f1f1ca96700 | 0x7f1e10e353c0 | 211643 | 211643 | 65536 | 1179648 | 163612 | 20977828 | 12073442572211586 | 12073442572383544 | 12073442572513143 | 12073442572516633 |
| 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 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7f1f1ca96600 | 0x7f1e10e35400 | 391025 | 391025 | 65536 | 1835008 | 259721 | 33301056 | 12073442572568198 | 12073442572748182 | 12073442572999220 | 12073442573049282 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7f1f1ca96500 | 0x7f1e10e35440 | 397499 | 397499 | 65536 | 1310720 | 176643 | 22690832 | 12073442573075060 | 12073442573269459 | 12073442573523217 | 12073442573569629 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7f1f1ca96400 | 0x7f1e10e35480 | 212137 | 212137 | 65536 | 1245184 | 177253 | 22659800 | 12073442573594476 | 12073442573783056 | 12073442573913455 | 12073442573917075 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7f1f1ca96300 | 0x7f1e10e354c0 | 225907 | 225907 | 65536 | 1310720 | 199209 | 25442024 | 12073442573963602 | 12073442574152494 | 12073442574290893 | 12073442574294577 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7f1f1ca96a00 | 0x7f1e10e35500 | 207801 | 207801 | 65536 | 1310720 | 181602 | 23188560 | 12073442574359828 | 12073442574528972 | 12073442574656811 | 12073442574660477 |
| 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 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7f1f1ca96900 | 0x7f1e10e35540 | 393595 | 393595 | 65536 | 2097152 | 293196 | 37577396 | 12073442574705751 | 12073442574890410 | 12073442575141928 | 12073442575184310 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7f1f1ca96800 | 0x7f1e10e35580 | 391921 | 391921 | 65536 | 1441792 | 196009 | 25073804 | 12073442575218724 | 12073442575398887 | 12073442575649926 | 12073442575691673 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7f1f1ca96700 | 0x7f1e10e355c0 | 215067 | 215067 | 65536 | 1376256 | 187092 | 23944812 | 12073442575723623 | 12073442575901284 | 12073442576032963 | 12073442576036684 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7f1f1ca96600 | 0x7f1e10e35600 | 215097 | 215097 | 65536 | 1507328 | 211274 | 27029248 | 12073442576090454 | 12073442576269602 | 12073442576402241 | 12073442576406031 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7f1f1ca96500 | 0x7f1e10e35640 | 221331 | 221331 | 65536 | 1441792 | 203730 | 26016836 | 12073442576470440 | 12073442576642240 | 12073442576777759 | 12073442576781539 |
| 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 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7f1f1ca96400 | 0x7f1e10e35680 | 400689 | 400689 | 65536 | 2359296 | 322581 | 41426080 | 12073442576827153 | 12073442577006558 | 12073442577263357 | 12073442577333975 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7f1f1ca96300 | 0x7f1e10e356c0 | 397699 | 397699 | 65536 | 1572864 | 210836 | 26967904 | 12073442577359623 | 12073442577548635 | 12073442577802554 | 12073442577870763 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7f1f1ca96a00 | 0x7f1e10e35700 | 210769 | 210769 | 65536 | 1507328 | 212415 | 27184588 | 12073442577899957 | 12073442578098072 | 12073442578227831 | 12073442578231774 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7f1f1ca96900 | 0x7f1e10e35740 | 208835 | 208835 | 65536 | 1703936 | 233960 | 29945436 | 12073442578284111 | 12073442578462870 | 12073442578590709 | 12073442578594418 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7f1f1ca96800 | 0x7f1e10e35780 | 220609 | 220609 | 65536 | 1572864 | 215161 | 27548040 | 12073442578658086 | 12073442578821588 | 12073442578957907 | 12073442578961710 |
| 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 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7f1f1ca96700 | 0x7f1e10e357c0 | 398907 | 398907 | 65536 | 2621440 | 359664 | 46029156 | 12073442579020008 | 12073442579203346 | 12073442579458864 | 12073442579480344 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7f1f1ca96600 | 0x7f1e10e35800 | 397993 | 397993 | 65536 | 1703936 | 227991 | 29164236 | 12073442579534515 | 12073442579703183 | 12073442579958062 | 12073442580013865 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7f1f1ca96500 | 0x7f1e10e35840 | 221179 | 221179 | 65536 | 1638400 | 230483 | 29472216 | 12073442580038691 | 12073442580228300 | 12073442580364139 | 12073442580367933 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7f1f1ca96400 | 0x7f1e10e35880 | 213433 | 213433 | 65536 | 1900544 | 291679 | 37284400 | 12073442580420681 | 12073442580594058 | 12073442580726057 | 12073442580729666 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7f1f1ca96300 | 0x7f1e10e358c0 | 209395 | 209395 | 65536 | 1703936 | 236591 | 30233080 | 12073442580794817 | 12073442580960616 | 12073442581088615 | 12073442581092630 |
| 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 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7f1f1ca96a00 | 0x7f1e10e35900 | 467529 | 467529 | 65536 | 2883584 | 393079 | 50321740 | 12073442581143655 | 12073442581326854 | 12073442581629252 | 12073442581676665 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7f1f1ca96900 | 0x7f1e10e35940 | 400083 | 400083 | 65536 | 1835008 | 243204 | 31316336 | 12073442581699808 | 12073442581889091 | 12073442582144449 | 12073442582191592 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7f1f1ca96800 | 0x7f1e10e35980 | 216321 | 216321 | 65536 | 1769472 | 251354 | 32255872 | 12073442582217440 | 12073442582405248 | 12073442582538687 | 12073442582542495 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7f1f1ca96700 | 0x7f1e10e359c0 | 217259 | 217259 | 65536 | 2097152 | 297237 | 38154228 | 12073442582594601 | 12073442582773246 | 12073442582906525 | 12073442582910358 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7f1f1ca96600 | 0x7f1e10e35a00 | 209569 | 209569 | 65536 | 1835008 | 249844 | 31898912 | 12073442582972995 | 12073442583146044 | 12073442583275323 | 12073442583279274 |
| 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 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7f1f1ca96500 | 0x7f1e10e35a40 | 408987 | 408987 | 65536 | 3145728 | 433871 | 55425672 | 12073442583331321 | 12073442583506682 | 12073442583768920 | 12073442583836770 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7f1f1ca96400 | 0x7f1e10e35a80 | 386481 | 386481 | 65536 | 1966080 | 264139 | 33689908 | 12073442583863399 | 12073442584052119 | 12073442584300597 | 12073442584370472 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7f1f1ca96300 | 0x7f1e10e35ac0 | 214859 | 214859 | 65536 | 1900544 | 299881 | 38375928 | 12073442584394516 | 12073442584589236 | 12073442584721235 | 12073442584724910 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7f1f1ca96a00 | 0x7f1e10e35b00 | 217057 | 217057 | 65536 | 2293760 | 306196 | 39360280 | 12073442584778189 | 12073442584951314 | 12073442585086033 | 12073442585090019 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7f1f1ca96900 | 0x7f1e10e35b40 | 212467 | 212467 | 65536 | 1966080 | 271943 | 34729740 | 12073442585156302 | 12073442585326032 | 12073442585456271 | 12073442585459986 |
| 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 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7f1f1ca96800 | 0x7f1e10e35b80 | 404441 | 404441 | 65536 | 3407872 | 457462 | 58465704 | 12073442585510751 | 12073442585685230 | 12073442585946028 | 12073442586024636 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7f1f1ca96700 | 0x7f1e10e35bc0 | 463259 | 463259 | 65536 | 2097152 | 277035 | 35336816 | 12073442586049873 | 12073442586236427 | 12073442586534345 | 12073442586602510 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7f1f1ca96600 | 0x7f1e10e35c00 | 209873 | 209873 | 65536 | 2031616 | 275313 | 35241344 | 12073442586626735 | 12073442586809703 | 12073442586938023 | 12073442586941810 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7f1f1ca96500 | 0x7f1e10e35c40 | 223387 | 223387 | 65536 | 2490368 | 347507 | 44738152 | 12073442586993446 | 12073442587175141 | 12073442587313861 | 12073442587317969 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7f1f1ca96400 | 0x7f1e10e35c80 | 213105 | 213105 | 65536 | 2097152 | 298675 | 38320440 | 12073442587381818 | 12073442587545059 | 12073442587675939 | 12073442587679872 |
| 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 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7f1f1ca96300 | 0x7f1e10e35cc0 | 400931 | 400931 | 65536 | 3670016 | 498096 | 63565992 | 12073442587731588 | 12073442587907777 | 12073442588166496 | 12073442588214996 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7f1f1ca96a00 | 0x7f1e10e35d00 | 397057 | 397057 | 65536 | 2228224 | 297527 | 38063000 | 12073442588239512 | 12073442588427134 | 12073442588682333 | 12073442588728741 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7f1f1ca96900 | 0x7f1e10e35d40 | 218387 | 218387 | 65536 | 2162688 | 343442 | 44023484 | 12073442588755711 | 12073442588934492 | 12073442589069371 | 12073442589073452 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7f1f1ca96800 | 0x7f1e10e35d80 | 227785 | 227785 | 65536 | 2686976 | 411894 | 52827384 | 12073442589125679 | 12073442589309369 | 12073442589450969 | 12073442589454770 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7f1f1ca96700 | 0x7f1e10e35dc0 | 214883 | 214883 | 65536 | 2228224 | 339702 | 43427736 | 12073442589517577 | 12073442589683607 | 12073442589814167 | 12073442589818406 |
| 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 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7f1f1ca96600 | 0x7f1e10e35e00 | 411881 | 411881 | 65536 | 3932160 | 526145 | 67191120 | 12073442589872116 | 12073442590053525 | 12073442590319124 | 12073442590366034 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7f1f1ca96500 | 0x7f1e10e35e40 | 389043 | 389043 | 65536 | 2359296 | 311032 | 39816072 | 12073442590390820 | 12073442590574802 | 12073442590825361 | 12073442590871543 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7f1f1ca96400 | 0x7f1e10e35e80 | 220625 | 220625 | 65536 | 2293760 | 332872 | 42534424 | 12073442590894446 | 12073442591086960 | 12073442591220879 | 12073442591224890 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7f1f1ca96300 | 0x7f1e10e35ec0 | 226355 | 226355 | 65536 | 2883584 | 385551 | 49343860 | 12073442591276636 | 12073442591460237 | 12073442591601517 | 12073442591605357 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7f1f1ca96a00 | 0x7f1e10e35f00 | 208465 | 208465 | 65536 | 2359296 | 324810 | 41567772 | 12073442591670718 | 12073442591833195 | 12073442591961675 | 12073442591965356 |
| 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 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7f1f1ca96900 | 0x7f1e10e35f40 | 412379 | 412379 | 65536 | 4194304 | 552439 | 70512872 | 12073442592013786 | 12073442592198793 | 12073442592465192 | 12073442592514587 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7f1f1ca96800 | 0x7f1e10e35f80 | 395281 | 395281 | 65536 | 2490368 | 336091 | 42975544 | 12073442592538110 | 12073442592722310 | 12073442592976549 | 12073442593024404 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7f1f1ca96700 | 0x7f1e10e35fc0 | 282939 | 282939 | 65536 | 2424832 | 364732 | 46738432 | 12073442593047928 | 12073442593235268 | 12073442593413187 | 12073442593417024 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7f1f1ca96600 | 0x7f1e10e36000 | 229849 | 229849 | 65536 | 3080192 | 486313 | 62282884 | 12073442593468279 | 12073442593645025 | 12073442593786944 | 12073442593790908 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7f1f1ca96500 | 0x7f1e10e36040 | 216219 | 216219 | 65536 | 2490368 | 340514 | 43604024 | 12073442593854447 | 12073442594023583 | 12073442594157022 | 12073442594161076 |
| 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 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7f1f1ca96400 | 0x7f1e10e36080 | 411585 | 411585 | 65536 | 4456448 | 593793 | 75844876 | 12073442594212432 | 12073442594391101 | 12073442594656700 | 12073442594703364 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7f1f1ca96300 | 0x7f1e10e360c0 | 401675 | 401675 | 65536 | 2621440 | 343958 | 43827032 | 12073442594728230 | 12073442594920378 | 12073442595179097 | 12073442595202562 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7f1f1ca96a00 | 0x7f1e10e36100 | 219713 | 219713 | 65536 | 2555904 | 414424 | 53028728 | 12073442595250411 | 12073442595417975 | 12073442595553335 | 12073442595557261 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7f1f1ca96900 | 0x7f1e10e36140 | 231835 | 231835 | 65536 | 3276800 | 511947 | 65632740 | 12073442595601042 | 12073442595781493 | 12073442595926453 | 12073442595930124 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7f1f1ca96800 | 0x7f1e10e36180 | 208473 | 208473 | 65536 | 2621440 | 373879 | 47844520 | 12073442595993091 | 12073442596166291 | 12073442596294450 | 12073442596298438 |
| 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 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7f1f1ca96700 | 0x7f1e10e361c0 | 408771 | 408771 | 65536 | 4718592 | 626189 | 80283920 | 12073442596349704 | 12073442596524049 | 12073442596788528 | 12073442596836869 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7f1f1ca96600 | 0x7f1e10e36200 | 386953 | 386953 | 65536 | 2752512 | 391482 | 50163092 | 12073442596861495 | 12073442597051566 | 12073442597300685 | 12073442597351405 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7f1f1ca96500 | 0x7f1e10e36240 | 211147 | 211147 | 65536 | 2686976 | 380330 | 48688196 | 12073442597376321 | 12073442597562603 | 12073442597692843 | 12073442597696847 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7f1f1ca96400 | 0x7f1e10e36280 | 240985 | 240985 | 65536 | 3473408 | 523245 | 67297524 | 12073442597748423 | 12073442597922281 | 12073442598073161 | 12073442598077454 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7f1f1ca96300 | 0x7f1e10e362c0 | 219995 | 219995 | 65536 | 2752512 | 392850 | 50259220 | 12073442598161561 | 12073442598329799 | 12073442598466118 | 12073442598470034 |
| 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 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7f1f1ca96a00 | 0x7f1e10e36300 | 409625 | 409625 | 65536 | 4980736 | 651163 | 83336044 | 12073442598522051 | 12073442598698437 | 12073442598963556 | 12073442598984009 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7f1f1ca96900 | 0x7f1e10e36340 | 393747 | 393747 | 65536 | 2883584 | 381654 | 49013972 | 12073442599042327 | 12073442599207394 | 12073442599461153 | 12073442599506480 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7f1f1ca96800 | 0x7f1e10e36380 | 219753 | 219753 | 65536 | 2818048 | 392401 | 50235788 | 12073442599529954 | 12073442599714591 | 12073442599849791 | 12073442599853485 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7f1f1ca96700 | 0x7f1e10e363c0 | 252275 | 252275 | 65536 | 3670016 | 551838 | 70822956 | 12073442599906924 | 12073442600083069 | 12073442600241628 | 12073442600245614 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7f1f1ca96600 | 0x7f1e10e36400 | 219793 | 219793 | 65536 | 2883584 | 454836 | 58243924 | 12073442600310064 | 12073442600481147 | 12073442600616826 | 12073442600620721 |
| 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 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7f1f1ca96500 | 0x7f1e10e36440 | 397507 | 397507 | 65536 | 5177344 | 683355 | 87566476 | 12073442600671946 | 12073442600847705 | 12073442601105304 | 12073442601154112 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7f1f1ca96400 | 0x7f1e10e36480 | 394817 | 394817 | 65536 | 3014656 | 431916 | 55385880 | 12073442601179139 | 12073442601366742 | 12073442601621461 | 12073442601668688 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7f1f1ca96300 | 0x7f1e10e364c0 | 220883 | 220883 | 65536 | 2949120 | 503110 | 64358272 | 12073442601698684 | 12073442601888659 | 12073442602025779 | 12073442602029900 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7f1f1ca96a00 | 0x7f1e10e36500 | 263657 | 263657 | 65536 | 3866624 | 577610 | 73763388 | 12073442602082517 | 12073442602263057 | 12073442602429136 | 12073442602432758 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7f1f1ca96900 | 0x7f1e10e36540 | 213171 | 213171 | 65536 | 3014656 | 412032 | 52847900 | 12073442602495214 | 12073442602660335 | 12073442602792334 | 12073442602796274 |
| 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 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7f1f1ca96800 | 0x7f1e10e36580 | 400953 | 400953 | 65536 | 5439488 | 725196 | 92966364 | 12073442602839895 | 12073442603029613 | 12073442603289291 | 12073442603315629 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7f1f1ca96700 | 0x7f1e10e365c0 | 391747 | 391747 | 65536 | 3145728 | 427845 | 54831804 | 12073442603358829 | 12073442603523530 | 12073442603776969 | 12073442603798617 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7f1f1ca96600 | 0x7f1e10e36600 | 214761 | 214761 | 65536 | 3080192 | 445284 | 57024600 | 12073442603846205 | 12073442604007047 | 12073442604139687 | 12073442604143598 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7f1f1ca96500 | 0x7f1e10e36640 | 275155 | 275155 | 65536 | 4063232 | 578487 | 74009416 | 12073442604186668 | 12073442604370085 | 12073442604544164 | 12073442604548069 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7f1f1ca96400 | 0x7f1e10e36680 | 216225 | 216225 | 65536 | 3145728 | 454668 | 58180328 | 12073442604613741 | 12073442604779043 | 12073442604912642 | 12073442604916574 |
| 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 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7f1f1ca96300 | 0x7f1e10e366c0 | 400059 | 400059 | 65536 | 5701632 | 755494 | 96449376 | 12073442604966888 | 12073442605154241 | 12073442605414080 | 12073442605440618 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7f1f1ca96a00 | 0x7f1e10e36700 | 393593 | 393593 | 65536 | 3276800 | 434381 | 55782472 | 12073442605484449 | 12073442605648638 | 12073442605903037 | 12073442605924838 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7f1f1ca96900 | 0x7f1e10e36740 | 216915 | 216915 | 65536 | 3211264 | 445162 | 56931524 | 12073442605967327 | 12073442606138076 | 12073442606272635 | 12073442606276441 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7f1f1ca96800 | 0x7f1e10e36780 | 288913 | 288913 | 65536 | 4259840 | 574621 | 74006332 | 12073442606326504 | 12073442606502554 | 12073442606685433 | 12073442606689339 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7f1f1ca96700 | 0x7f1e10e367c0 | 224147 | 224147 | 65536 | 3276800 | 505153 | 64605104 | 12073442606753418 | 12073442606919191 | 12073442607056790 | 12073442607060689 |
| 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 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7f1f1ca96600 | 0x7f1e10e36800 | 411393 | 411393 | 65536 | 7733248 | 981784 | 125386296 | 12073442607115100 | 12073442607298069 | 12073442607565748 | 12073442607589321 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7f1f1ca96500 | 0x7f1e10e36840 | 394339 | 394339 | 65536 | 3407872 | 476893 | 60999828 | 12073442607633583 | 12073442607796146 | 12073442608051985 | 12073442608076757 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7f1f1ca96400 | 0x7f1e10e36880 | 223481 | 223481 | 65536 | 3342336 | 470506 | 60225608 | 12073442608124746 | 12073442608292784 | 12073442608429743 | 12073442608433620 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7f1f1ca96300 | 0x7f1e10e368c0 | 301963 | 301963 | 65536 | 4456448 | 622492 | 79874504 | 12073442608486078 | 12073442608659022 | 12073442608851180 | 12073442608873979 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7f1f1ca96a00 | 0x7f1e10e36900 | 223377 | 223377 | 65536 | 3538944 | 580976 | 74389392 | 12073442608932367 | 12073442609110699 | 12073442609249098 | 12073442609252873 |
| 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 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7f1f1ca96900 | 0x7f1e10e36940 | 437779 | 437779 | 65536 | 8978432 | 1129592 | 144359996 | 12073442609303878 | 12073442609478857 | 12073442609764455 | 12073442609789720 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7f1f1ca96800 | 0x7f1e10e36980 | 389473 | 389473 | 65536 | 3670016 | 530567 | 68144140 | 12073442609830676 | 12073442609992454 | 12073442610244293 | 12073442610273249 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7f1f1ca96700 | 0x7f1e10e369c0 | 218891 | 218891 | 65536 | 3604480 | 502835 | 64327684 | 12073442610315698 | 12073442610480771 | 12073442610616291 | 12073442610620444 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7f1f1ca96600 | 0x7f1e10e36a00 | 330369 | 330369 | 65536 | 4849664 | 713834 | 90731076 | 12073442610662973 | 12073442610844609 | 12073442611054688 | 12073442611081220 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7f1f1ca96500 | 0x7f1e10e36a40 | 222691 | 222691 | 65536 | 3801088 | 587862 | 75238504 | 12073442611138948 | 12073442611305727 | 12073442611444286 | 12073442611448323 |
| 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 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7f1f1ca96400 | 0x7f1e10e36a80 | 471569 | 471569 | 65536 | 14548992 | 1827596 | 234053648 | 12073442611500319 | 12073442611677245 | 12073442611985083 | 12073442612014304 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7f1f1ca96300 | 0x7f1e10e36ac0 | 392179 | 392179 | 65536 | 3932160 | 554864 | 71115860 | 12073442612056894 | 12073442612222202 | 12073442612476600 | 12073442612502712 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7f1f1ca96a00 | 0x7f1e10e36b00 | 218593 | 218593 | 65536 | 3866624 | 535839 | 68588396 | 12073442612544229 | 12073442612706359 | 12073442612841878 | 12073442612845800 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7f1f1ca96900 | 0x7f1e10e36b40 | 357043 | 357043 | 65536 | 5242880 | 784556 | 100599908 | 12073442612895392 | 12073442613079637 | 12073442613308276 | 12073442613334788 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7f1f1ca96800 | 0x7f1e10e36b80 | 221657 | 221657 | 65536 | 4063232 | 639262 | 81788196 | 12073442613390592 | 12073442613560594 | 12073442613697873 | 12073442613702071 |
| 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 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7f1f1ca96700 | 0x7f1e10e36bc0 | 509539 | 509539 | 65536 | 10027008 | 1257905 | 161385132 | 12073442613747345 | 12073442613926992 | 12073442614260750 | 12073442614286828 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7f1f1ca96600 | 0x7f1e10e36c00 | 391961 | 391961 | 65536 | 4194304 | 558151 | 71769680 | 12073442614330589 | 12073442614497549 | 12073442614751148 | 12073442614773171 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7f1f1ca96500 | 0x7f1e10e36c40 | 223875 | 223875 | 65536 | 4128768 | 595188 | 76155112 | 12073442614819738 | 12073442614983146 | 12073442615122666 | 12073442615126979 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7f1f1ca96400 | 0x7f1e10e36c80 | 384353 | 384353 | 65536 | 5636096 | 774194 | 98455948 | 12073442615177423 | 12073442615362463 | 12073442615609182 | 12073442615635073 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7f1f1ca96300 | 0x7f1e10e36cc0 | 221307 | 221307 | 65536 | 4587520 | 685643 | 87677620 | 12073442615689214 | 12073442615856059 | 12073442615993339 | 12073442615996735 |
| 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 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7f1f1ca96a00 | 0x7f1e10e36d00 | 575521 | 575521 | 65536 | 11075584 | 1393954 | 178242856 | 12073442616048772 | 12073442616227898 | 12073442616606456 | 12073442616632256 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7f1f1ca96900 | 0x7f1e10e36d40 | 406235 | 406235 | 65536 | 4718592 | 623928 | 79938820 | 12073442616673172 | 12073442616836055 | 12073442617099894 | 12073442617128108 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7f1f1ca96800 | 0x7f1e10e36d80 | 226753 | 226753 | 65536 | 4653056 | 725681 | 92893836 | 12073442617173622 | 12073442617338293 | 12073442617479412 | 12073442617482547 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7f1f1ca96700 | 0x7f1e10e36dc0 | 433651 | 433651 | 65536 | 6422528 | 905612 | 115866660 | 12073442617527600 | 12073442617705811 | 12073442617985970 | 12073442618024093 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7f1f1ca96600 | 0x7f1e10e36e00 | 218569 | 218569 | 65536 | 5111808 | 768215 | 98202884 | 12073442618074467 | 12073442618245168 | 12073442618380688 | 12073442618384212 |
| 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 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7f1f1ca96500 | 0x7f1e10e36e40 | 679211 | 679211 | 65536 | 15007744 | 1880402 | 240810608 | 12073442618434957 | 12073442618610767 | 12073442619059245 | 12073442619084303 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7f1f1ca96400 | 0x7f1e10e36e80 | 398881 | 398881 | 65536 | 5242880 | 704611 | 90052060 | 12073442619131531 | 12073442619301164 | 12073442619559242 | 12073442619582619 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7f1f1ca96300 | 0x7f1e10e36ec0 | 220843 | 220843 | 65536 | 5177344 | 774816 | 99111148 | 12073442619629046 | 12073442619793001 | 12073442619930921 | 12073442619934283 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7f1f1ca96a00 | 0x7f1e10e36f00 | 488281 | 488281 | 65536 | 7208960 | 1047910 | 133763824 | 12073442619977513 | 12073442620169320 | 12073442620485958 | 12073442620510724 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7f1f1ca96900 | 0x7f1e10e36f40 | 243235 | 243235 | 65536 | 6160384 | 909256 | 116338184 | 12073442620570736 | 12073442620738117 | 12073442620891236 | 12073442620894878 |
| 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 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7f1f1ca96800 | 0x7f1e10e36f80 | 787929 | 787929 | 65536 | 17104896 | 2144510 | 274463800 | 12073442620938509 | 12073442621127875 | 12073442621648513 | 12073442621673936 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7f1f1ca96700 | 0x7f1e10e36fc0 | 456947 | 456947 | 65536 | 6291456 | 923958 | 117714476 | 12073442621718078 | 12073442621882592 | 12073442622181150 | 12073442622204592 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7f1f1ca96600 | 0x7f1e10e37000 | 248689 | 248689 | 65536 | 6225920 | 945074 | 120853200 | 12073442622249916 | 12073442622415069 | 12073442622570908 | 12073442622574159 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7f1f1ca96500 | 0x7f1e10e37040 | 594155 | 594155 | 65536 | 8781824 | 1269590 | 162592020 | 12073442622625955 | 12073442622804827 | 12073442623192186 | 12073442623214619 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7f1f1ca96400 | 0x7f1e10e37080 | 280897 | 280897 | 65536 | 7208960 | 1092984 | 139736816 | 12073442623272426 | 12073442623441944 | 12073442623620344 | 12073442623623990 |
| 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 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7f1f1ca96300 | 0x7f1e10e370c0 | 926707 | 926707 | 65536 | 19202048 | 2407988 | 308013352 | 12073442623672770 | 12073442623848663 | 12073442624461940 | 12073442624488095 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7f1f1ca96a00 | 0x7f1e10e37100 | 498793 | 498793 | 65536 | 7340032 | 979130 | 125678504 | 12073442624521588 | 12073442624699539 | 12073442625026897 | 12073442625048507 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7f1f1ca96900 | 0x7f1e10e37140 | 282491 | 282491 | 65536 | 7274496 | 1061868 | 136040388 | 12073442625093691 | 12073442625259056 | 12073442625438895 | 12073442625442309 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7f1f1ca96800 | 0x7f1e10e37180 | 697625 | 697625 | 65536 | 10354688 | 1476768 | 190440372 | 12073442625493314 | 12073442625675854 | 12073442626132172 | 12073442626156206 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7f1f1ca96700 | 0x7f1e10e371c0 | 313507 | 313507 | 65536 | 8257536 | 1236365 | 158408276 | 12073442626218081 | 12073442626384971 | 12073442626586410 | 12073442626609829 |
| 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 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7f1f1ca96600 | 0x7f1e10e37200 | 1064233 | 1064233 | 65536 | 21299200 | 2669746 | 341697984 | 12073442626661495 | 12073442626828169 | 12073442627533126 | 12073442627562008 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7f1f1ca96500 | 0x7f1e10e37240 | 567347 | 567347 | 65536 | 8388608 | 1128009 | 143915536 | 12073442627601431 | 12073442627778084 | 12073442628152643 | 12073442628177312 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7f1f1ca96400 | 0x7f1e10e37280 | 317273 | 317273 | 65536 | 8323072 | 1251287 | 160169740 | 12073442628224068 | 12073442628389282 | 12073442628592161 | 12073442628616408 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7f1f1ca96300 | 0x7f1e10e372c0 | 804651 | 804651 | 65536 | 11927552 | 1684583 | 215001824 | 12073442628662483 | 12073442628827040 | 12073442629353277 | 12073442629383924 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7f1f1ca96a00 | 0x7f1e10e37300 | 350305 | 350305 | 65536 | 9306112 | 1443573 | 184791460 | 12073442629436842 | 12073442629605756 | 12073442629831355 | 12073442629852835 |
| 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 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7f1f1ca96900 | 0x7f1e10e37340 | 1206883 | 1206883 | 65536 | 29163520 | 3651387 | 467413296 | 12073442629898450 | 12073442630065754 | 12073442630867030 | 12073442630890604 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7f1f1ca96800 | 0x7f1e10e37380 | 639081 | 639081 | 65536 | 9437184 | 1268919 | 163317228 | 12073442630935998 | 12073442631112309 | 12073442631533267 | 12073442631558515 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7f1f1ca96700 | 0x7f1e10e373c0 | 353803 | 353803 | 65536 | 9371648 | 1417658 | 181490992 | 12073442631603919 | 12073442631767346 | 12073442631995185 | 12073442632018500 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7f1f1ca96600 | 0x7f1e10e37400 | 909673 | 909673 | 65536 | 13500416 | 1917098 | 246449432 | 12073442632070116 | 12073442632237744 | 12073442632836781 | 12073442632881514 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7f1f1ca96500 | 0x7f1e10e37440 | 418163 | 418163 | 65536 | 11403264 | 1750889 | 224148336 | 12073442632916459 | 12073442633124780 | 12073442633395818 | 12073442633443548 |
| 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 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7f1f1ca96400 | 0x7f1e10e37480 | 1487201 | 1487201 | 65536 | 33357824 | 4174473 | 534512792 | 12073442633468194 | 12073442633651657 | 12073442634639173 | 12073442634687650 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7f1f1ca96300 | 0x7f1e10e374c0 | 779427 | 779427 | 65536 | 11534336 | 1571634 | 202350808 | 12073442634712036 | 12073442634904451 | 12073442635421569 | 12073442635473180 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7f1f1ca96a00 | 0x7f1e10e37500 | 423713 | 423713 | 65536 | 11534336 | 1750354 | 223987228 | 12073442635495692 | 12073442635686848 | 12073442635961087 | 12073442636016169 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7f1f1ca96900 | 0x7f1e10e37540 | 1125667 | 1125667 | 65536 | 19267584 | 2422070 | 310140532 | 12073442636045944 | 12073442636225085 | 12073442636965082 | 12073442637033219 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7f1f1ca96800 | 0x7f1e10e37580 | 531873 | 531873 | 65536 | 13500416 | 2073641 | 265457452 | 12073442637072111 | 12073442637241561 | 12073442637587479 | 12073442637655145 |
| 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 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7f1f1ca96700 | 0x7f1e10e375c0 | 1769603 | 1769603 | 65536 | 37552128 | 4706256 | 601629020 | 12073442637673068 | 12073442637866998 | 12073442639041232 | 12073442639114186 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7f1f1ca96600 | 0x7f1e10e37600 | 917137 | 917137 | 65536 | 13631488 | 1866721 | 239089076 | 12073442639144022 | 12073442639326991 | 12073442639937868 | 12073442639984093 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7f1f1ca96500 | 0x7f1e10e37640 | 493547 | 493547 | 65536 | 13631488 | 2078891 | 266034532 | 12073442640008058 | 12073442640206827 | 12073442640526986 | 12073442640575632 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7f1f1ca96400 | 0x7f1e10e37680 | 1335529 | 1335529 | 65536 | 21692416 | 2739938 | 350954280 | 12073442640600008 | 12073442640784424 | 12073442641662980 | 12073442641711714 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7f1f1ca96300 | 0x7f1e10e376c0 | 630443 | 630443 | 65536 | 17694720 | 2715899 | 347766668 | 12073442641747310 | 12073442641915779 | 12073442642327457 | 12073442642395264 |
| 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 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7f1f1ca96a00 | 0x7f1e10e37700 | 2331801 | 2331801 | 65536 | 57475072 | 7191477 | 920872432 | 12073442642420330 | 12073442642607616 | 12073442644158649 | 12073442644227729 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7f1f1ca96900 | 0x7f1e10e37740 | 1200603 | 1200603 | 65536 | 19660800 | 2481756 | 317459580 | 12073442644251313 | 12073442644446327 | 12073442645244404 | 12073442645314148 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7f1f1ca96800 | 0x7f1e10e37780 | 639313 | 639313 | 65536 | 20381696 | 2578971 | 330056884 | 12073442645345637 | 12073442645529042 | 12073442645945040 | 12073442645992238 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7f1f1ca96700 | 0x7f1e10e377c0 | 1757595 | 1757595 | 65536 | 28704768 | 3614964 | 462498544 | 12073442646024749 | 12073442646215759 | 12073442647375434 | 12073442647446731 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7f1f1ca96600 | 0x7f1e10e37800 | 1197489 | 1197489 | 65536 | 36634624 | 4646341 | 594862460 | 12073442647490533 | 12073442647659113 | 12073442648445349 | 12073442648515508 |
| 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 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7f1f1ca96500 | 0x7f1e10e37840 | 4585291 | 4585291 | 65536 | 105840640 | 13234943 | 1694739508 | 12073442648543009 | 12073442648735108 | 12073442651787414 | 12073442651857709 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7f1f1ca96400 | 0x7f1e10e37880 | 2325833 | 2325833 | 65536 | 38535168 | 4829407 | 618342656 | 12073442651886492 | 12073442652089492 | 12073442653633645 | 12073442653704821 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7f1f1ca96300 | 0x7f1e10e378c0 | 1202539 | 1202539 | 65536 | 39124992 | 4913654 | 629036332 | 12073442653734216 | 12073442653924044 | 12073442654713160 | 12073442654783646 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7f1f1ca96a00 | 0x7f1e10e37900 | 3443105 | 3443105 | 65536 | 55771136 | 7008597 | 897236852 | 12073442654817750 | 12073442655000199 | 12073442657283388 | 12073442657353011 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7f1f1ca96900 | 0x7f1e10e37940 | 2323339 | 2323339 | 65536 | 72548352 | 9111881 | 1166246124 | 12073442657397834 | 12073442657569467 | 12073442659105300 | 12073442659174316 |
| 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 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7f1f1ca96800 | 0x7f1e10e37980 | 9087865 | 9087865 | 65536 | 210698240 | 26338872 | 3372660336 | 12073442659197419 | 12073442659389138 | 12073442665446550 | 12073442665515139 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7f1f1ca96700 | 0x7f1e10e379c0 | 4573131 | 4573131 | 65536 | 76283904 | 9537857 | 1222046692 | 12073442665545496 | 12073442665730229 | 12073442668775655 | 12073442668845268 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7f1f1ca96600 | 0x7f1e10e37a00 | 2328265 | 2328265 | 65536 | 77398016 | 9705065 | 1242214316 | 12073442668874292 | 12073442669074694 | 12073442670614687 | 12073442670684546 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 763517 | 763522 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7f1f1ca96500 | 0x7f1e10e37a40 | 6813611 | 6813611 | 65536 | 110821376 | 13882173 | 1777294828 | 12073442670714332 | 12073442670903325 | 12073442675431624 | 12073442675501969 |