989e29cf81
Signed-off-by: Jose Santos <josantos@login1.hpcfund>
39 KiB
39 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 | DispatchNs | Start_Timestamp | End_Timestamp | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBuffer.kd | 0 | 0 | 0 | 860821 | 860826 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7fc432204180 | 12075093208441641 | 12075093208489155 | 12075093208815232 | 12075093208922645 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 860821 | 860826 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7fc432235100 | 12075093223823516 | 12075093223931152 | 12075093223937872 | 12075093223943489 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7fc53ddef900 | 0x7fc432235140 | 12075093223991688 | 12075093224005071 | 12075093224143150 | 12075093224146646 |
| 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 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7fc53ddef800 | 0x7fc432235180 | 12075093224192211 | 12075093224210190 | 12075093224457388 | 12075093224554875 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7fc53ddef700 | 0x7fc4322351c0 | 12075093224581605 | 12075093224593867 | 12075093224841225 | 12075093224937676 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7fc53ddef600 | 0x7fc432235200 | 12075093224964246 | 12075093224975944 | 12075093225101543 | 12075093225105268 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7fc53ddef500 | 0x7fc432235240 | 12075093225135504 | 12075093225147302 | 12075093225272901 | 12075093225275995 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7fc53ddef400 | 0x7fc432235280 | 12075093225330777 | 12075093225347461 | 12075093225472100 | 12075093225475336 |
| 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 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7fc53ddef300 | 0x7fc4322352c0 | 12075093225502716 | 12075093225516099 | 12075093225764257 | 12075093225860381 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7fc53ddefa00 | 0x7fc432235300 | 12075093225881330 | 12075093225892576 | 12075093226137054 | 12075093226233615 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7fc53ddef900 | 0x7fc432235340 | 12075093226255335 | 12075093226267773 | 12075093226392572 | 12075093226395896 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7fc53ddef800 | 0x7fc432235380 | 12075093226422716 | 12075093226434332 | 12075093226559131 | 12075093226562356 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7fc53ddef700 | 0x7fc4322353c0 | 12075093226600837 | 12075093226615291 | 12075093226740250 | 12075093226743302 |
| 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 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7fc53ddef600 | 0x7fc432235400 | 12075093226770543 | 12075093226783449 | 12075093227027767 | 12075093227124330 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7fc53ddef500 | 0x7fc432235440 | 12075093227146732 | 12075093227158486 | 12075093227402804 | 12075093227470814 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7fc53ddef400 | 0x7fc432235480 | 12075093227493035 | 12075093227506324 | 12075093227631603 | 12075093227634809 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7fc53ddef300 | 0x7fc4322354c0 | 12075093227661208 | 12075093227674162 | 12075093227799121 | 12075093227802250 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7fc53ddefa00 | 0x7fc432235500 | 12075093227839549 | 12075093227852561 | 12075093227976720 | 12075093227979810 |
| 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 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7fc53ddef900 | 0x7fc432235540 | 12075093228009876 | 12075093228022959 | 12075093228267438 | 12075093228336352 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7fc53ddef800 | 0x7fc432235580 | 12075093228359395 | 12075093228372877 | 12075093228618795 | 12075093228684740 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7fc53ddef700 | 0x7fc4322355c0 | 12075093228704226 | 12075093228717034 | 12075093228841833 | 12075093228844777 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7fc53ddef600 | 0x7fc432235600 | 12075093228871246 | 12075093228883913 | 12075093229009672 | 12075093229013210 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7fc53ddef500 | 0x7fc432235640 | 12075093229051662 | 12075093229063271 | 12075093229187110 | 12075093229190299 |
| 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 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7fc53ddef400 | 0x7fc432235680 | 12075093229217400 | 12075093229230470 | 12075093229481828 | 12075093229523639 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7fc53ddef300 | 0x7fc4322356c0 | 12075093229544317 | 12075093229558307 | 12075093229801025 | 12075093229866786 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7fc53ddefa00 | 0x7fc432235700 | 12075093229887345 | 12075093229899745 | 12075093230024064 | 12075093230027124 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7fc53ddef900 | 0x7fc432235740 | 12075093230055557 | 12075093230067103 | 12075093230192062 | 12075093230195157 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7fc53ddef800 | 0x7fc432235780 | 12075093230232075 | 12075093230244862 | 12075093230369661 | 12075093230372737 |
| 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 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7fc53ddef700 | 0x7fc4322357c0 | 12075093230398845 | 12075093230412061 | 12075093230698938 | 12075093230769825 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7fc53ddef600 | 0x7fc432235800 | 12075093230790453 | 12075093230802297 | 12075093231048856 | 12075093231098876 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7fc53ddef500 | 0x7fc432235840 | 12075093231120737 | 12075093231132855 | 12075093231257174 | 12075093231260336 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7fc53ddef400 | 0x7fc432235880 | 12075093231286535 | 12075093231298294 | 12075093231424533 | 12075093231427968 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7fc53ddef300 | 0x7fc4322358c0 | 12075093231464876 | 12075093231477012 | 12075093231601491 | 12075093231604366 |
| 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 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7fc53ddefa00 | 0x7fc432235900 | 12075093231630124 | 12075093231641651 | 12075093231886769 | 12075093231909893 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7fc53ddef900 | 0x7fc432235940 | 12075093231930492 | 12075093231944208 | 12075093232188527 | 12075093232239376 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7fc53ddef800 | 0x7fc432235980 | 12075093232261256 | 12075093232274126 | 12075093232399245 | 12075093232402258 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7fc53ddef700 | 0x7fc4322359c0 | 12075093232428507 | 12075093232441005 | 12075093232566284 | 12075093232569219 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7fc53ddef600 | 0x7fc432235a00 | 12075093232605236 | 12075093232618123 | 12075093232742922 | 12075093232745957 |
| 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 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7fc53ddef500 | 0x7fc432235a40 | 12075093232771635 | 12075093232785802 | 12075093233037960 | 12075093233069338 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7fc53ddef400 | 0x7fc432235a80 | 12075093233090978 | 12075093233104679 | 12075093233350917 | 12075093233378974 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7fc53ddef300 | 0x7fc432235ac0 | 12075093233404200 | 12075093233417317 | 12075093233542276 | 12075093233545443 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7fc53ddefa00 | 0x7fc432235b00 | 12075093233572223 | 12075093233585315 | 12075093233711074 | 12075093233714066 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7fc53ddef900 | 0x7fc432235b40 | 12075093233750043 | 12075093233763714 | 12075093233888833 | 12075093233891847 |
| 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 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7fc53ddef800 | 0x7fc432235b80 | 12075093233918015 | 12075093233930273 | 12075093234184671 | 12075093234213514 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7fc53ddef700 | 0x7fc432235bc0 | 12075093234235145 | 12075093234248190 | 12075093234493788 | 12075093234521256 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7fc53ddef600 | 0x7fc432235c00 | 12075093234541334 | 12075093234554588 | 12075093234678747 | 12075093234681785 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7fc53ddef500 | 0x7fc432235c40 | 12075093234708945 | 12075093234721626 | 12075093234848665 | 12075093234851730 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7fc53ddef400 | 0x7fc432235c80 | 12075093234890002 | 12075093234902905 | 12075093235027864 | 12075093235031124 |
| 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 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7fc53ddef300 | 0x7fc432235cc0 | 12075093235058144 | 12075093235071224 | 12075093235329142 | 12075093235348674 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7fc53ddefa00 | 0x7fc432235d00 | 12075093235371767 | 12075093235385301 | 12075093235633299 | 12075093235655805 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7fc53ddef900 | 0x7fc432235d40 | 12075093235676844 | 12075093235690099 | 12075093235814578 | 12075093235817515 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7fc53ddef800 | 0x7fc432235d80 | 12075093235844335 | 12075093235855698 | 12075093235983856 | 12075093235986790 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7fc53ddef700 | 0x7fc432235dc0 | 12075093236030160 | 12075093236041776 | 12075093236166415 | 12075093236169379 |
| 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 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7fc53ddef600 | 0x7fc432235e00 | 12075093236196369 | 12075093236209295 | 12075093236467213 | 12075093236486759 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7fc53ddef500 | 0x7fc432235e40 | 12075093236507027 | 12075093236520652 | 12075093236767530 | 12075093236790233 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7fc53ddef400 | 0x7fc432235e80 | 12075093236813125 | 12075093236825930 | 12075093236951049 | 12075093236954188 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7fc53ddef300 | 0x7fc432235ec0 | 12075093236980927 | 12075093236993449 | 12075093237122727 | 12075093237126097 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7fc53ddefa00 | 0x7fc432235f00 | 12075093237162655 | 12075093237177607 | 12075093237303206 | 12075093237306332 |
| 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 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7fc53ddef900 | 0x7fc432235f40 | 12075093237332300 | 12075093237344326 | 12075093237600324 | 12075093237623511 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7fc53ddef800 | 0x7fc432235f80 | 12075093237643709 | 12075093237655683 | 12075093237899841 | 12075093237926665 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7fc53ddef700 | 0x7fc432235fc0 | 12075093237947423 | 12075093237960641 | 12075093238085600 | 12075093238089217 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7fc53ddef600 | 0x7fc432236000 | 12075093238115896 | 12075093238128480 | 12075093238267198 | 12075093238270313 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7fc53ddef500 | 0x7fc432236040 | 12075093238308965 | 12075093238322238 | 12075093238446397 | 12075093238449516 |
| 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 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7fc53ddef400 | 0x7fc432236080 | 12075093238475465 | 12075093238487517 | 12075093238749755 | 12075093238769130 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7fc53ddef300 | 0x7fc4322360c0 | 12075093238790049 | 12075093238803034 | 12075093239049432 | 12075093239076762 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7fc53ddefa00 | 0x7fc432236100 | 12075093239097751 | 12075093239110712 | 12075093239235831 | 12075093239238813 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7fc53ddef900 | 0x7fc432236140 | 12075093239265072 | 12075093239277910 | 12075093239419509 | 12075093239422575 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7fc53ddef800 | 0x7fc432236180 | 12075093239459233 | 12075093239472309 | 12075093239597748 | 12075093239600786 |
| 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 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7fc53ddef700 | 0x7fc4322361c0 | 12075093239627205 | 12075093239639988 | 12075093239892466 | 12075093239916453 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7fc53ddef600 | 0x7fc432236200 | 12075093239936941 | 12075093239950385 | 12075093240197583 | 12075093240224485 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7fc53ddef500 | 0x7fc432236240 | 12075093240247598 | 12075093240260463 | 12075093240386222 | 12075093240389391 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7fc53ddef400 | 0x7fc432236280 | 12075093240414869 | 12075093240427821 | 12075093240576940 | 12075093240580036 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7fc53ddef300 | 0x7fc4322362c0 | 12075093240632874 | 12075093240646220 | 12075093240771979 | 12075093240775239 |
| 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 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7fc53ddefa00 | 0x7fc432236300 | 12075093240800986 | 12075093240813898 | 12075093241068456 | 12075093241095624 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7fc53ddef900 | 0x7fc432236340 | 12075093241116753 | 12075093241129736 | 12075093241376294 | 12075093241401132 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7fc53ddef800 | 0x7fc432236380 | 12075093241422792 | 12075093241435493 | 12075093241561252 | 12075093241564495 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7fc53ddef700 | 0x7fc4322363c0 | 12075093241590614 | 12075093241603652 | 12075093241761251 | 12075093241764427 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7fc53ddef600 | 0x7fc432236400 | 12075093241801896 | 12075093241815650 | 12075093241941249 | 12075093241944451 |
| 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 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7fc53ddef500 | 0x7fc432236440 | 12075093241970109 | 12075093241982849 | 12075093242242207 | 12075093242269756 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7fc53ddef400 | 0x7fc432236480 | 12075093242289793 | 12075093242303007 | 12075093242549405 | 12075093242572108 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7fc53ddef300 | 0x7fc4322364c0 | 12075093242595030 | 12075093242607804 | 12075093242734203 | 12075093242737445 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7fc53ddefa00 | 0x7fc432236500 | 12075093242761961 | 12075093242774683 | 12075093242941561 | 12075093242944640 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7fc53ddef900 | 0x7fc432236540 | 12075093242980657 | 12075093242993081 | 12075093243119160 | 12075093243122350 |
| 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 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7fc53ddef800 | 0x7fc432236580 | 12075093243149491 | 12075093243161080 | 12075093243418998 | 12075093243445651 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7fc53ddef700 | 0x7fc4322365c0 | 12075093243466289 | 12075093243477877 | 12075093243727635 | 12075093243754255 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7fc53ddef600 | 0x7fc432236600 | 12075093243778059 | 12075093243791155 | 12075093243915954 | 12075093243919221 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7fc53ddef500 | 0x7fc432236640 | 12075093243944849 | 12075093243957873 | 12075093244130352 | 12075093244133750 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7fc53ddef400 | 0x7fc432236680 | 12075093244171901 | 12075093244183952 | 12075093244309711 | 12075093244312903 |
| 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 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7fc53ddef300 | 0x7fc4322366c0 | 12075093244339472 | 12075093244353070 | 12075093244604428 | 12075093244627648 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7fc53ddefa00 | 0x7fc432236700 | 12075093244647575 | 12075093244659948 | 12075093244911146 | 12075093244934177 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7fc53ddef900 | 0x7fc432236740 | 12075093244956639 | 12075093244969865 | 12075093245094984 | 12075093245098533 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7fc53ddef800 | 0x7fc432236780 | 12075093245125543 | 12075093245137224 | 12075093245319783 | 12075093245323210 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7fc53ddef700 | 0x7fc4322367c0 | 12075093245361251 | 12075093245374662 | 12075093245500421 | 12075093245503596 |
| 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 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7fc53ddef600 | 0x7fc432236800 | 12075093245529985 | 12075093245542181 | 12075093245806659 | 12075093245830162 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7fc53ddef500 | 0x7fc432236840 | 12075093245850210 | 12075093245862978 | 12075093246108096 | 12075093246132574 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7fc53ddef400 | 0x7fc432236880 | 12075093246154295 | 12075093246167136 | 12075093246293215 | 12075093246296389 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7fc53ddef300 | 0x7fc4322368c0 | 12075093246322708 | 12075093246334975 | 12075093246525533 | 12075093246530444 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7fc53ddefa00 | 0x7fc432236900 | 12075093246564437 | 12075093246577693 | 12075093246704412 | 12075093246707423 |
| 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 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7fc53ddef900 | 0x7fc432236940 | 12075093246733441 | 12075093246746011 | 12075093247027769 | 12075093247054147 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7fc53ddef800 | 0x7fc432236980 | 12075093247075296 | 12075093247087929 | 12075093247334167 | 12075093247359985 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7fc53ddef700 | 0x7fc4322369c0 | 12075093247382798 | 12075093247395446 | 12075093247521685 | 12075093247524882 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7fc53ddef600 | 0x7fc432236a00 | 12075093247551050 | 12075093247562965 | 12075093247771923 | 12075093247798019 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7fc53ddef500 | 0x7fc432236a40 | 12075093247828406 | 12075093247840563 | 12075093247968562 | 12075093247971632 |
| 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 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7fc53ddef400 | 0x7fc432236a80 | 12075093247997700 | 12075093248015281 | 12075093248321519 | 12075093248347931 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7fc53ddef300 | 0x7fc432236ac0 | 12075093248370413 | 12075093248383278 | 12075093248630316 | 12075093248653619 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7fc53ddefa00 | 0x7fc432236b00 | 12075093248674308 | 12075093248687116 | 12075093248814635 | 12075093248817805 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7fc53ddef900 | 0x7fc432236b40 | 12075093248843041 | 12075093248856235 | 12075093249084233 | 12075093249115317 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7fc53ddef800 | 0x7fc432236b80 | 12075093249147137 | 12075093249160552 | 12075093249287591 | 12075093249290884 |
| 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 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7fc53ddef700 | 0x7fc432236bc0 | 12075093249316702 | 12075093249328231 | 12075093249656868 | 12075093249675749 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7fc53ddef600 | 0x7fc432236c00 | 12075093249698682 | 12075093249710308 | 12075093249957026 | 12075093249983701 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7fc53ddef500 | 0x7fc432236c40 | 12075093250006974 | 12075093250018466 | 12075093250148384 | 12075093250151453 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7fc53ddef400 | 0x7fc432236c80 | 12075093250177902 | 12075093250189184 | 12075093250432862 | 12075093250459786 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7fc53ddef300 | 0x7fc432236cc0 | 12075093250489762 | 12075093250504222 | 12075093250633341 | 12075093250636444 |
| 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 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7fc53ddefa00 | 0x7fc432236d00 | 12075093250661641 | 12075093250673180 | 12075093251048057 | 12075093251076051 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7fc53ddef900 | 0x7fc432236d40 | 12075093251097531 | 12075093251109977 | 12075093251363575 | 12075093251390275 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7fc53ddef800 | 0x7fc432236d80 | 12075093251412226 | 12075093251425334 | 12075093251555093 | 12075093251558247 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7fc53ddef700 | 0x7fc432236dc0 | 12075093251583805 | 12075093251596373 | 12075093251874611 | 12075093251897097 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7fc53ddef600 | 0x7fc432236e00 | 12075093251928565 | 12075093251941490 | 12075093252076689 | 12075093252080187 |
| 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 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7fc53ddef500 | 0x7fc432236e40 | 12075093252105665 | 12075093252117809 | 12075093252539886 | 12075093252566691 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7fc53ddef400 | 0x7fc432236e80 | 12075093252587500 | 12075093252600045 | 12075093252855083 | 12075093252881546 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7fc53ddef300 | 0x7fc432236ec0 | 12075093252902606 | 12075093252915403 | 12075093253050122 | 12075093253053536 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7fc53ddefa00 | 0x7fc432236f00 | 12075093253080256 | 12075093253092681 | 12075093253406919 | 12075093253434213 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7fc53ddef900 | 0x7fc432236f40 | 12075093253466734 | 12075093253479558 | 12075093253631397 | 12075093253634506 |
| 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 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7fc53ddef800 | 0x7fc432236f80 | 12075093253659743 | 12075093253672997 | 12075093254187713 | 12075093254215175 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7fc53ddef700 | 0x7fc432236fc0 | 12075093254236044 | 12075093254248832 | 12075093254545150 | 12075093254571417 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7fc53ddef600 | 0x7fc432237000 | 12075093254593718 | 12075093254605309 | 12075093254759868 | 12075093254763083 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7fc53ddef500 | 0x7fc432237040 | 12075093254788049 | 12075093254800828 | 12075093255184505 | 12075093255212097 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7fc53ddef400 | 0x7fc432237080 | 12075093255243035 | 12075093255256184 | 12075093255468822 | 12075093255495234 |
| 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 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7fc53ddef300 | 0x7fc4322370c0 | 12075093255515912 | 12075093255529782 | 12075093256139537 | 12075093256166992 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7fc53ddefa00 | 0x7fc432237100 | 12075093256187500 | 12075093256200177 | 12075093256525614 | 12075093256553190 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7fc53ddef900 | 0x7fc432237140 | 12075093256575181 | 12075093256588174 | 12075093256766252 | 12075093256769442 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7fc53ddef800 | 0x7fc432237180 | 12075093256796041 | 12075093256807052 | 12075093257261448 | 12075093257296010 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7fc53ddef700 | 0x7fc4322371c0 | 12075093257328260 | 12075093257341288 | 12075093257540966 | 12075093257567825 |
| 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 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7fc53ddef600 | 0x7fc432237200 | 12075093257587502 | 12075093257600326 | 12075093258303200 | 12075093258331915 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7fc53ddef500 | 0x7fc432237240 | 12075093258354948 | 12075093258367519 | 12075093258739837 | 12075093258766853 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7fc53ddef400 | 0x7fc432237280 | 12075093258789435 | 12075093258801276 | 12075093259003514 | 12075093259031375 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7fc53ddef300 | 0x7fc4322372c0 | 12075093259052484 | 12075093259063994 | 12075093259588470 | 12075093259615390 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7fc53ddefa00 | 0x7fc432237300 | 12075093259649223 | 12075093259661589 | 12075093259885427 | 12075093259912172 |
| 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 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7fc53ddef900 | 0x7fc432237340 | 12075093259933712 | 12075093259945267 | 12075093260742701 | 12075093260774544 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7fc53ddef800 | 0x7fc432237380 | 12075093260793500 | 12075093260804460 | 12075093261223337 | 12075093261251140 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7fc53ddef700 | 0x7fc4322373c0 | 12075093261274203 | 12075093261286536 | 12075093261511655 | 12075093261539246 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7fc53ddef600 | 0x7fc432237400 | 12075093261561607 | 12075093261574694 | 12075093262171009 | 12075093262198721 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7fc53ddef500 | 0x7fc432237440 | 12075093262230701 | 12075093262243969 | 12075093262514367 | 12075093262540957 |
| 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 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7fc53ddef400 | 0x7fc432237480 | 12075093262562587 | 12075093262575166 | 12075093263559638 | 12075093263587652 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7fc53ddef300 | 0x7fc4322374c0 | 12075093263607870 | 12075093263620438 | 12075093264133714 | 12075093264162410 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7fc53ddefa00 | 0x7fc432237500 | 12075093264186946 | 12075093264199953 | 12075093264502991 | 12075093264529192 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7fc53ddef900 | 0x7fc432237540 | 12075093264550792 | 12075093264562030 | 12075093265299305 | 12075093265327355 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7fc53ddef800 | 0x7fc432237580 | 12075093265357611 | 12075093265369384 | 12075093265685222 | 12075093265711880 |
| 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 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7fc53ddef700 | 0x7fc4322375c0 | 12075093265734241 | 12075093265745861 | 12075093266916892 | 12075093266945122 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7fc53ddef600 | 0x7fc432237600 | 12075093266966842 | 12075093266978171 | 12075093267590007 | 12075093267625887 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7fc53ddef500 | 0x7fc432237640 | 12075093267648028 | 12075093267661366 | 12075093267978483 | 12075093268009009 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7fc53ddef400 | 0x7fc432237680 | 12075093268030589 | 12075093268042163 | 12075093268919116 | 12075093268948805 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7fc53ddef300 | 0x7fc4322376c0 | 12075093268982538 | 12075093268994475 | 12075093269404072 | 12075093269433907 |
| 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 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7fc53ddefa00 | 0x7fc432237700 | 12075093269457901 | 12075093269471112 | 12075093271019419 | 12075093271091076 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7fc53ddef900 | 0x7fc432237740 | 12075093271113228 | 12075093271127240 | 12075093271919555 | 12075093271994445 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7fc53ddef800 | 0x7fc432237780 | 12075093272022207 | 12075093272033953 | 12075093272447710 | 12075093272520383 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7fc53ddef700 | 0x7fc4322377c0 | 12075093272543936 | 12075093272556670 | 12075093273714422 | 12075093273786075 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7fc53ddef600 | 0x7fc432237800 | 12075093273818635 | 12075093273831541 | 12075093274616816 | 12075093274691297 |
| 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 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7fc53ddef500 | 0x7fc432237840 | 12075093274714290 | 12075093274726415 | 12075093277777754 | 12075093277848945 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7fc53ddef400 | 0x7fc432237880 | 12075093277870555 | 12075093277882074 | 12075093279422383 | 12075093279498360 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7fc53ddef300 | 0x7fc4322378c0 | 12075093279522164 | 12075093279534062 | 12075093280324137 | 12075093280396259 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7fc53ddefa00 | 0x7fc432237900 | 12075093280416837 | 12075093280428776 | 12075093282709241 | 12075093282780259 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7fc53ddef900 | 0x7fc432237940 | 12075093282812860 | 12075093282824760 | 12075093284359950 | 12075093284435605 |
| 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 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7fc53ddef800 | 0x7fc432237980 | 12075093284459209 | 12075093284470989 | 12075093290525028 | 12075093290596505 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7fc53ddef700 | 0x7fc4322379c0 | 12075093290617764 | 12075093290629027 | 12075093293669646 | 12075093293741409 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7fc53ddef600 | 0x7fc432237a00 | 12075093293763580 | 12075093293775406 | 12075093295313315 | 12075093295384733 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 860821 | 860826 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7fc53ddef500 | 0x7fc432237a40 | 12075093295405792 | 12075093295417315 | 12075093299942884 | 12075093300021981 |