diff --git a/benchmarks/QS_reference/README.txt b/benchmarks/QS_reference/README.txt new file mode 100644 index 0000000000..bedd97c4d0 --- /dev/null +++ b/benchmarks/QS_reference/README.txt @@ -0,0 +1,17 @@ +This is a set of small/medium sized inputs with realistic parameter settings +to perform MD simulations on 64 water molecules using different functionals. +The jobs start from an atomic guess but converge without problems and the +inputs are set to cover 10 MD steps. + +Reference results for a dual socket AMD EPYC 7401 24-Core machine using +48 MPI threads are given. + +Functional Combined Memory[GB] Wall Time[s] +======================================================== +PBE 11.0 119 +PBE/GAPW/AE 30.2 845 +SCAN 14.2 249 +PBE0/ADMM 16.8 1306 +DC-SCAN 20.2 3525 + + diff --git a/benchmarks/QS_reference/geom.xyz b/benchmarks/QS_reference/geom.xyz new file mode 100644 index 0000000000..9034472bcb --- /dev/null +++ b/benchmarks/QS_reference/geom.xyz @@ -0,0 +1,194 @@ + 192 + + O 12.2653784723 1.3579911114 10.8740408138 + O 6.4509184999 3.7068983139 8.6469007489 + O 0.0764687486 2.1676564936 8.2601487412 + O 12.0889014586 2.6364415193 2.1694325453 + O 12.2901845594 4.1725704303 12.0994369500 + O 7.2017860631 0.9427415232 4.7579350578 + O 8.3341412151 7.2071769548 4.6840399886 + O 12.3301285103 11.5198785457 8.0834933594 + O 3.2748050482 4.4593783159 9.1772633437 + O 2.8583347687 3.7889558961 6.5425615043 + O 1.3824714483 6.3935488029 0.5664274563 + O 1.8726738116 8.6871135963 2.0920293595 + O 3.7730767723 12.1058907360 8.6218752975 + O 6.4233128509 3.6640445878 2.7879942430 + O 1.9970733782 1.8516895642 4.8696731655 + O 8.2898896064 2.4206851632 6.9415908011 + O 5.7532970460 3.3335652191 12.4848259568 + O 11.3130798154 5.6564604705 2.2456065915 + O 4.2890207438 2.1128976248 10.5860195355 + O 5.3974786525 3.3596140282 5.4863631661 + O 6.5073921079 11.8694355022 0.7151133831 + O 3.2518787563 2.3399893121 2.4131601817 + O 8.0091259020 6.3550342320 7.4980859963 + O 5.9289268966 6.5064055837 12.1948889583 + O 10.6093962096 11.8622464767 12.2009547871 + O 9.3399300668 3.6879585799 3.5249275673 + O 1.1104118860 5.7900496143 6.6459278382 + O 8.0223626218 3.3261643987 10.8671600363 + O 12.3760247422 9.6748048075 11.7729447725 + O 4.2085952808 7.0917842864 8.1402782548 + O 3.7849842851 8.2247869704 11.5862609157 + O 11.0753084381 4.5441006254 7.8302989376 + O 10.4339404936 8.4226381283 1.0326606489 + O 1.9801939437 6.4006260573 10.3532960004 + O 4.7025541028 0.5645080436 5.6121216045 + O 8.7200355703 12.2406139583 8.0990354746 + O 2.6314728696 10.5195509666 0.0812367575 + O 7.2372170981 10.5128872249 4.2407693494 + O 2.2785106988 0.2735158759 10.8093081745 + O 8.8603338997 0.9475062310 1.3383490537 + O 1.9428454388 8.0933013675 7.5349610168 + O 9.6586885990 8.0354674891 9.8561801095 + O 10.9027016087 8.3314031190 6.4766468047 + O 3.5126605794 4.8681604571 1.5447193099 + O 7.9752195662 8.6025995319 12.0531935982 + O 8.3666863349 10.0168595418 6.6846564422 + O 5.6515454504 6.0831806402 5.5282838146 + O 11.7419281413 1.6243137536 5.0852528911 + O 9.7577982015 9.8129976466 3.5379380130 + O 3.9623475617 10.5501046888 4.6883966734 + O 0.9008735880 6.3698300196 4.0579309357 + O 6.8850257432 6.4069669347 2.5052035668 + O 3.8151074058 6.6390328148 3.7776794426 + O 6.5623475561 8.3060555774 8.8128281758 + O 9.7770427586 0.1367986200 3.8513708395 + O 4.1048067647 11.6455572918 2.2181305762 + O 5.3226714278 8.7360297304 2.7509914647 + O 10.0100106914 5.3721423736 5.3751121410 + O 12.2578402812 8.6481327937 3.9720814240 + O 2.3413100238 10.7498563115 6.8131612211 + O 7.0035770383 0.6611797552 10.5330160453 + O 5.1727234009 10.2177394652 10.3577222886 + O 11.1837022597 5.8856780735 10.2974137221 + O 12.2749231672 8.9553185979 9.0729730984 + H 12.3544834143 2.3096435033 11.1760351932 + H 11.9458162515 1.5267805409 9.9105980569 + H 5.6069287135 3.4535986547 9.0331480668 + H 6.8774231490 3.0384173458 8.0060675603 + H -0.1386649787 1.5226970061 7.5393390838 + H -0.3702603007 3.0262114100 7.9345037980 + H 12.1747920844 2.9655957291 1.2118760798 + H 12.9768489794 2.9103236365 2.5090267835 + H 11.5319515417 4.3120224477 11.4517865821 + H 12.7665929142 5.0396556318 12.0360849841 + H 6.9714703453 1.7193305687 4.1963585079 + H 6.2667561829 0.6941830852 5.1416273286 + H 7.7449837821 7.2224617803 5.4662739285 + H 9.1484133461 6.6491878868 4.9372349121 + H 12.8376123914 11.7750817392 8.8852295478 + H 11.9852135152 10.5846629304 8.3100981908 + H 3.5143596472 3.8628171269 9.9355194733 + H 2.4494103558 4.9111603105 9.5101739635 + H 2.1892552625 4.5354456757 6.3032448130 + H 2.8532686709 3.8531426515 7.5505489382 + H 1.1402127988 7.1741190997 1.1430939749 + H 2.2191319051 6.0211680210 0.9920923462 + H 2.7938846740 8.9689579393 2.2950559276 + H 1.3468500915 8.9922583807 2.8800584927 + H 4.4398996680 11.5606974094 9.1473742418 + H 3.0727708172 12.4629214645 9.2612912943 + H 5.8721989974 3.4620820089 3.6327423704 + H 5.8474722691 3.4047312757 2.0064470858 + H 0.9913740856 1.6508298057 4.8396639823 + H 2.2171490853 2.4587328102 5.6667858050 + H 8.4371749508 1.6297986972 7.5311537710 + H 8.0763892388 2.0257612585 6.0577956420 + H 5.2360689869 2.9118408682 11.7015197527 + H 6.6507647678 3.4144886539 11.9958822329 + H 10.7991616974 6.4945630803 2.1017392943 + H 11.6659569672 5.3697633164 1.3641965242 + H 3.4646958309 1.5650342123 10.8909380591 + H 4.8211643124 1.4442389627 10.1024917650 + H 4.4142205177 3.3626638640 5.6802896922 + H 5.6789899492 4.3365508109 5.5474292206 + H 6.3035844692 11.8276154858 1.6998950294 + H 5.6421462736 12.1134957913 0.3411215368 + H 3.5375980001 1.4132612995 2.1891354801 + H 2.6241365275 2.2060053732 3.2132924632 + H 7.1449622250 5.8844493586 7.5264739540 + H 8.6381073530 5.7440713919 7.0467993697 + H 6.0029216529 5.6717561197 11.6829661809 + H 6.2514339130 6.3286286837 13.1351851126 + H 11.0955155646 12.6202273865 11.7060713336 + H 10.2786488857 12.2835261105 13.0272009156 + H 9.8860073755 4.0432657500 2.7481490229 + H 8.5550022710 3.4682783676 2.9531230583 + H 1.4445811101 6.6399150071 7.0953464745 + H 1.0057925377 6.1660105424 5.6899871206 + H 7.9936086928 3.6884682654 9.9542120576 + H 8.0796959995 2.3423291051 10.7525016228 + H 11.7628533121 10.4326231217 12.0927105067 + H 12.1557236265 8.9513178168 12.3956482037 + H 3.3657871424 7.5983731085 7.8597709277 + H 3.8526478049 6.2612428223 8.6016406276 + H 3.1366425544 7.6391042055 11.0868788984 + H 4.4505713377 7.6487660835 12.0638382646 + H 11.5794883190 4.9706862515 7.0748708106 + H 10.3165955549 4.1409872174 7.3321494877 + H 10.0724726904 8.9326803696 1.8456469066 + H 9.5979227205 8.2640467756 0.5151528347 + H 1.3331063206 6.6845822590 9.6675449967 + H 1.4163583831 6.4504370217 11.1969811689 + H 4.1410778925 1.3126371573 5.2748625309 + H 4.6865451449 0.6452838272 6.5948881938 + H 9.4591316801 12.3320616069 8.7311992641 + H 8.8525427313 11.3793105094 7.5605567418 + H 1.7600563766 10.0360314577 0.1437672100 + H 3.3207872566 9.8673245642 -0.2242585423 + H 7.0502734804 11.4792998544 4.1234469567 + H 6.4914894880 9.9515150702 3.8026481305 + H 1.3582957395 0.5711270847 11.1288260978 + H 2.5160042652 -0.5187336552 11.4415291455 + H 8.7720961492 1.8569506515 0.9950434098 + H 8.1145400226 0.3577848233 0.9962810952 + H 1.1493030773 8.3601784117 8.1546861959 + H 2.0825088058 8.9651042157 7.0244540835 + H 8.9258176857 7.7999755185 9.2341145657 + H 9.0828941143 8.4400830099 10.5902972469 + H 10.1419661022 7.7110672445 6.4564628507 + H 10.5115519465 9.1830585779 6.1628560182 + H 3.4989777389 3.9839242517 2.0998598496 + H 4.0431355735 4.5925639574 0.7589237278 + H 7.3650794684 9.3754576635 12.0348940422 + H 7.3552684240 7.7980327455 12.0535077076 + H 7.8371817880 10.1564746893 5.8086472191 + H 7.7288915542 9.5229176856 7.2678642936 + H 5.2999002697 6.4825089374 6.3699322788 + H 4.8915129145 6.3092372043 4.8574585929 + H 11.5248865409 2.1803260224 4.2654701493 + H 11.2438102029 0.8027415240 4.7969758662 + H 8.8354611627 9.6771107172 3.9591064050 + H 9.9327357845 10.7802148407 3.7773375883 + H 3.1267442003 10.5435669475 5.2645069929 + H 4.3028218657 11.4277579725 5.0513935282 + H 0.4381602471 7.2678778127 3.8071037512 + H 0.3209110206 5.7854293901 3.4754834445 + H 7.5662525916 6.5596481246 3.2618595873 + H 6.6845113337 5.4142224113 2.5181264343 + H 3.8515968138 6.3203858474 2.8396990290 + H 2.8268385827 6.5488857341 3.9504375221 + H 5.5853374932 8.0246674305 8.6631279279 + H 6.9871691024 7.4946819346 8.4220888751 + H 9.5663080484 0.7209123672 3.0488880464 + H 8.9504270082 0.1320145383 4.3959839446 + H 3.8612664418 11.1887914406 1.3659290086 + H 3.9627362788 10.9834596106 2.9773368596 + H 5.9279307139 7.9206694462 2.8017862627 + H 4.7808210604 8.7246351474 3.5707426303 + H 10.8866988962 5.5256567387 4.9391579674 + H 9.5176535166 4.6990230516 4.7435070953 + H 11.5189056932 8.9934862938 3.4129537396 + H 11.9710864312 8.7894412015 4.9177789094 + H 2.9178674161 11.3160300298 7.4625492958 + H 1.4241973905 11.1115039657 6.7997037322 + H 7.2108590883 0.1374157907 9.7241397114 + H 7.1653760614 0.1174442105 11.3449376078 + H 4.8273104326 9.3480748209 10.8250953606 + H 6.0635272223 9.8243983732 10.1952812829 + H 10.5838329307 6.7052354376 10.3178927461 + H 11.2376964555 5.6040605672 9.3357903104 + H 12.1892115946 8.9902053958 10.1002136816 + H 11.4366040185 8.6438361286 8.6499776246 diff --git a/benchmarks/QS_reference/w64DCSCAN.inp b/benchmarks/QS_reference/w64DCSCAN.inp new file mode 100644 index 0000000000..590d033241 --- /dev/null +++ b/benchmarks/QS_reference/w64DCSCAN.inp @@ -0,0 +1,114 @@ +&FORCE_EVAL + METHOD QS + &DFT + BASIS_SET_FILE_NAME BASIS_ADMM_UZH + BASIS_SET_FILE_NAME BASIS_MOLOPT_UZH + POTENTIAL_FILE_NAME POTENTIAL_UZH + &AUXILIARY_DENSITY_MATRIX_METHOD + ADMM_PURIFICATION_METHOD NONE + METHOD BASIS_PROJECTION + EXCH_SCALING_MODEL NONE + EXCH_CORRECTION_FUNC NONE + &END + &ENERGY_CORRECTION + ENERGY_FUNCTIONAL DCDFT + &RESPONSE_SOLVER + METHOD MO_SOLVER + PRECONDITIONER FULL_SINGLE_INVERSE + MAX_ITER 50 + EPS 1.E-9 + &END + &XC + &XC_FUNCTIONAL + &MGGA_X_R2SCAN + &END + &MGGA_C_R2SCAN + &END + &END XC_FUNCTIONAL + &END XC + &END ENERGY_CORRECTION + &MGRID + CUTOFF 600 + REL_CUTOFF 60 + &END MGRID + &QS + METHOD GPW + EPS_DEFAULT 1.0E-12 + MIN_PAIR_LIST_RADIUS -1 + &END QS + &SCF + SCF_GUESS ATOMIC + EPS_SCF 1.E-7 + MAX_SCF 10 + &OUTER_SCF + EPS_SCF 1.E-7 + MAX_SCF 10 + &END + &OT ON + MINIMIZER DIIS + PRECONDITIONER FULL_ALL + &END OT + &PRINT + &RESTART OFF + &END + &END + &END SCF + &XC + &XC_FUNCTIONAL NONE + &END XC_FUNCTIONAL + &HF + &HF_INFO ON + &END + &SCREENING + EPS_SCHWARZ 1.0E-08 + SCREEN_ON_INITIAL_P .TRUE. + &END + &MEMORY + MAX_MEMORY 500 + EPS_STORAGE_SCALING 0.01 + &END + &INTERACTION_POTENTIAL + POTENTIAL_TYPE TRUNCATED + CUTOFF_RADIUS 4.0 + T_C_G_DATA t_c_g.dat + &END + FRACTION 1.00 + &END + &END XC + &END DFT + &SUBSYS + &CELL + ABC 12.4138 12.4138 12.4138 + &END CELL + &TOPOLOGY + COORD_FILE_NAME geom.xyz + COORD_FILE_FORMAT xyz + &END TOPOLOGY + &KIND H + BASIS_SET ORB TZVP-MOLOPT-MGGA-GTH-q1 + BASIS_SET AUX_FIT admm-dz-q1 + POTENTIAL GTH-MGGA-q1 + &END KIND + &KIND O + BASIS_SET ORB TZVP-MOLOPT-MGGA-GTH-q6 + BASIS_SET AUX_FIT admm-dz-q6 + POTENTIAL GTH-MGGA-q6 + &END KIND + &END SUBSYS +&END FORCE_EVAL +&GLOBAL + PROJECT H2O-64 + RUN_TYPE MD + PRINT_LEVEL LOW + &TIMINGS + THRESHOLD 0.001 + &END +&END GLOBAL +&MOTION + &MD + ENSEMBLE NVE + STEPS 10 + TIMESTEP 0.5 + TEMPERATURE 300.0 + &END MD +&END MOTION diff --git a/benchmarks/QS_reference/w64DCSCAN.ref b/benchmarks/QS_reference/w64DCSCAN.ref new file mode 100644 index 0000000000..a15b354a30 --- /dev/null +++ b/benchmarks/QS_reference/w64DCSCAN.ref @@ -0,0 +1,219 @@ + CP2K| version string: CP2K version 2023.2 (Development Version) + CP2K| source code revision number: git:15ad1db + CP2K| cp2kflags: omp libint fftw3 libxc elpa parallel mpi_f08 scalapack cosma x + CP2K| smm spglib sirius libvori libbqb libvdwxc + GLOBAL| Total number of message passing processes 48 + GLOBAL| Number of threads for this process 1 + GLOBAL| CPU model name AMD EPYC 7401 24-Core Processor + + HFX_MEM_INFO| Est. max. program size before HFX [MiB]: 420 + HFX_MEM_INFO| Number of cart. primitive ERI's calculated: 2676340060 + HFX_MEM_INFO| Number of sph. ERI's calculated: 1254621964 + HFX_MEM_INFO| Number of sph. ERI's stored in-core: 1229080496 + HFX_MEM_INFO| Number of sph. ERI's stored on disk: 0 + HFX_MEM_INFO| Number of sph. ERI's calculated on the fly: 0 + HFX_MEM_INFO| Total memory consumption ERI's RAM [MiB]: 2039 + HFX_MEM_INFO| Whereof max-vals [MiB]: 182 + HFX_MEM_INFO| Total compression factor ERI's RAM: 4.60 + HFX_MEM_INFO| Total memory consumption ERI's disk [MiB]: 0 + HFX_MEM_INFO| Total compression factor ERI's disk: 0.00 + HFX_MEM_INFO| Size of density/Fock matrix [MiB]: 4 + HFX_MEM_INFO| Size of buffers [MiB]: 3 + HFX_MEM_INFO| Number of periodic image cells considered: 27 + HFX_MEM_INFO| Est. max. program size after HFX [MiB]: 420 + + HFX_MEM_INFO| Number of cart. primitive DERIV's calculated: 1911834576 + HFX_MEM_INFO| Number of sph. DERIV's calculated: 806040600 + HFX_MEM_INFO| Number of sph. DERIV's stored in-core: 0 + HFX_MEM_INFO| Number of sph. DERIV's calculated on the fly: 806040600 + HFX_MEM_INFO| Total memory consumption DERIV's RAM [MiB]: 0 + HFX_MEM_INFO| Whereof max-vals [MiB]: 1 + HFX_MEM_INFO| Total compression factor DERIV's RAM: 0.00 + + MD| *************************************************************************** + MD| Step number 10 + MD| Time [fs] 5.000000 + MD| Conserved quantity [hartree] -0.109840290012E+04 + MD| --------------------------------------------------------------------------- + MD| Instantaneous Averages + MD| CPU time per MD step [s] 384.387586 351.997366 + MD| Energy drift per atom [K] -0.107012779194E+01 -0.229751555682E+00 + MD| Potential energy [hartree] -0.109867181233E+04 -0.109864823761E+04 + MD| Kinetic energy [hartree] 0.268912205167E+00 0.245843289099E+00 + MD| Temperature [K] 296.389727 270.963623 + MD| *************************************************************************** + MD| Estimated peak process memory after this step [MiB] 421 + + ------------------------------------------------------------------------------- + - - + - T I M I N G - + - - + ------------------------------------------------------------------------------- + SUBROUTINE CALLS ASD SELF TIME TOTAL TIME + MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM + CP2K 1 1.0 0.396 0.437 3524.749 3524.783 + qs_mol_dyn_low 1 2.0 0.006 0.022 3519.971 3520.003 + qs_forces 11 3.9 0.002 0.003 3519.295 3519.373 + velocity_verlet 10 3.0 0.002 0.002 3010.487 3010.525 + integrate_four_center 214 11.2 0.350 1.035 2664.588 2664.658 + integrate_four_center_main 214 12.2 0.136 0.151 1897.231 2577.328 + integrate_four_center_bin 13732 13.2 1897.095 2577.197 1897.095 2577.197 + energy_correction 22 5.4 0.001 0.002 1991.096 1991.155 + qs_energies 11 4.9 0.001 0.001 1536.975 1537.004 + scf_env_do_scf 11 5.9 0.001 0.002 1484.616 1484.637 + qs_ks_update_qs_env 105 7.8 0.001 0.002 1412.793 1412.828 + rebuild_ks_matrix 93 8.8 0.000 0.000 1412.432 1412.471 + qs_ks_build_kohn_sham_matrix 93 9.8 0.020 0.023 1412.431 1412.470 + response_calculation 11 5.9 0.001 0.002 1399.965 1400.014 + hfx_ks_matrix 93 10.8 0.003 0.016 1315.095 1315.127 + response_equation_new 11 6.9 0.001 0.001 1276.501 1276.548 + linres_solver 11 7.9 0.003 0.011 1264.279 1264.324 + apply_op 99 8.9 0.006 0.007 1242.977 1243.124 + apply_hfx 88 9.9 0.003 0.003 978.176 978.237 + hfx_matrix 88 10.9 0.001 0.001 978.158 978.219 + scf_env_do_scf_inner_loop 82 6.8 0.002 0.007 938.993 939.003 + mp_sync 1250 12.8 728.534 797.069 728.534 797.069 + init_scf_loop 12 6.8 0.000 0.001 545.604 545.629 + response_force 11 5.9 0.003 0.004 429.693 429.772 + calculate_rho_elec 642 10.7 0.433 0.463 259.715 259.875 + qs_rho_update_rho_low 269 9.5 0.003 0.004 235.655 235.781 + ec_dc_build_ks_matrix_force 11 5.9 0.002 0.002 146.767 146.915 + grid_collocate_task_list 642 11.7 133.781 142.331 133.781 142.331 + density_rs2pw 642 11.7 0.040 0.055 121.450 129.182 + derivatives_four_center 11 6.9 0.009 0.382 127.137 127.190 + p_env_psi0_changed 11 6.9 0.001 0.001 123.235 123.237 + add_exx_to_rhs 11 6.9 0.001 0.001 117.454 117.456 + tddft_hfx_matrix 22 7.9 0.000 0.001 116.642 116.643 + derivatives_four_center_main 11 7.9 0.018 0.020 107.943 107.977 + derivatives_four_center_bin 725 8.9 80.480 104.428 80.480 104.428 + integrate_v_rspace 269 10.0 0.011 0.012 102.791 102.968 + p_env_update_rho 88 9.9 0.002 0.002 94.336 94.401 + prepare_preconditioner 12 7.8 0.000 0.000 93.882 93.914 + transfer_rs2pw 2579 12.6 0.060 0.087 81.793 89.884 + make_preconditioner 23 8.9 0.000 0.000 86.967 87.021 + parallel_gemm_fm 1637 10.8 0.005 0.016 80.781 81.243 + parallel_gemm_fm_cosma 1637 11.8 80.776 81.239 80.776 81.239 + dbcsr_complete_redistribute 2868 12.2 0.925 1.094 78.929 79.302 + make_full_all 12 9.8 0.003 0.003 74.209 74.250 + dbcsr_multiply_generic 2640 12.4 0.140 0.152 70.920 72.336 + copy_dbcsr_to_fm 1124 11.2 0.022 0.027 69.420 70.680 + cp_dbcsr_sm_fm_multiply 530 10.1 0.016 0.034 67.267 67.439 + mp_waitany 40810 14.4 54.811 63.257 54.811 63.257 + pw_transfer 5170 12.2 0.503 0.600 59.270 59.981 + grid_integrate_task_list 269 11.0 55.408 59.533 55.408 59.533 + fft_wrap_pw1pw2 4676 13.3 0.062 0.070 58.230 59.011 + transfer_rs2pw_300 653 13.6 3.709 4.134 50.116 58.084 + fft_wrap_pw1pw2_300 1943 14.2 6.445 6.739 47.256 48.289 + fft3d_ps 4676 15.3 20.703 23.277 44.180 46.112 + mp_waitall_1 267124 15.9 40.991 44.502 40.991 44.502 + admm_mo_calc_rho_aux 93 10.8 0.001 0.001 44.307 44.361 + hfx_load_balance 2 10.5 0.003 0.004 43.800 43.832 + mp_alltoall_d11v 13324 13.5 39.514 43.650 39.514 43.650 + mp_sum_l 12074 13.1 31.860 35.154 31.860 35.154 + cp_fm_cholesky_reduce 12 10.8 34.893 34.923 34.893 34.923 + init_scf_run 11 5.9 0.001 0.016 33.712 33.741 + scf_env_initial_rho_setup 11 6.9 0.000 0.001 33.711 33.740 + mp_cart_sub 2251 13.2 32.672 32.910 32.672 32.910 + apply_op_2_dft 88 9.9 0.047 0.062 32.700 32.740 + mp_sum_lv 65 5.4 27.624 32.545 27.624 32.545 + multiply_cannon 2640 13.4 0.251 0.331 29.977 31.802 + qs_scf_new_mos 82 7.8 0.001 0.001 30.551 30.630 + qs_scf_loop_do_ot 82 8.8 0.001 0.001 30.551 30.630 + potential_pw2rs 269 11.0 0.027 0.030 29.057 29.257 + ot_scf_mini 82 9.8 0.002 0.002 29.017 29.054 + sum_up_and_integrate 93 10.8 0.002 0.002 29.007 29.041 + integrate_four_center_load 214 12.2 0.001 0.001 28.465 28.537 + wfi_extrapolate 11 7.9 0.001 0.001 26.285 26.312 + cp_fm_diag_elpa 46 11.6 0.000 0.000 25.926 26.017 + multiply_cannon_loop 2640 14.4 0.176 0.205 23.357 25.662 + mp_sendrecv_dv 60348 14.7 23.492 23.954 23.492 23.954 + cp_dbcsr_sm_fm_multiply_core 530 11.1 0.002 0.002 22.704 23.515 + copy_fm_to_dbcsr 1744 11.3 0.008 0.009 22.277 22.680 + hfx_load_balance_count 2 11.5 14.714 22.610 14.714 22.610 + apply_op_1 99 9.9 0.001 0.002 22.473 22.533 + rs_gather_matrices 269 11.0 0.100 0.116 18.083 21.737 + hfx_load_balance_bin 2 11.5 14.289 20.953 14.289 20.953 + ot_mini 82 10.8 0.001 0.001 20.857 20.886 + make_m2s 5280 13.4 0.083 0.087 19.231 20.260 + transfer_pw2rs 1098 11.9 0.025 0.030 19.840 20.007 + admm_projection_derivative 22 6.9 0.001 0.001 19.866 19.909 + make_images 5280 14.4 0.208 0.225 18.705 19.638 + p_env_finish_kpp1 88 9.9 0.002 0.002 19.149 19.191 + multiply_cannon_metrocomm3 31680 15.4 0.080 0.091 14.914 19.070 + cp_dbcsr_plus_fm_fm_t_native 247 10.7 0.005 0.005 18.502 18.791 + mp_alltoall_z22v 4676 17.3 17.420 18.666 17.420 18.666 + subspace_eigenvalues_ks_dbcsr 24 9.3 0.001 0.001 18.197 18.251 + cp_fm_diag_elpa_base 46 12.4 16.188 17.595 16.372 17.928 + derivatives_four_center_load 11 7.9 0.000 0.000 17.242 17.276 + hfx_load_balance_dist 2 11.5 0.000 0.000 14.600 16.941 + admm_fit_mo_coeffs 93 11.8 0.000 0.000 16.395 16.533 + admm_aux_response_density 88 10.9 0.001 0.002 16.426 16.505 + qs_ot_get_derivative 82 11.8 0.001 0.001 15.332 15.374 + mp_alltoall_i11v 10121 13.3 14.780 15.131 14.780 15.131 + make_images_sizes 5280 15.4 0.006 0.006 12.580 14.620 + mp_alltoall_i44 5280 16.4 12.574 14.614 12.574 14.614 + mp_alltoall_i22 4123 13.3 12.498 14.283 12.498 14.283 + transfer_rs2pw_40 642 13.7 0.631 0.690 13.605 13.947 + dbcsr_desymmetrize_deep 1124 12.2 0.149 0.188 12.396 13.708 + fit_mo_coeffs 93 12.8 0.000 0.000 13.659 13.692 + cp_dbcsr_syevd 34 10.8 0.003 0.003 13.528 13.640 + yz_to_x 2272 16.5 1.985 2.114 12.767 13.631 + ec_build_ks_matrix 11 6.9 0.001 0.001 12.581 12.594 + mp_cart_create 1129 13.2 11.412 12.007 11.412 12.007 + admm_mo_merge_ks_matrix 93 10.8 0.000 0.000 11.487 11.527 + merge_ks_matrix_none 93 11.8 0.003 0.004 11.487 11.527 + transfer_rs2pw_20 642 13.7 0.186 0.199 10.705 11.198 + hybrid_alltoall_any 6404 15.8 0.071 0.148 8.628 10.046 + postortho 187 8.9 0.005 0.006 9.593 9.805 + qs_vxc_create 230 10.2 0.003 0.003 8.074 8.094 + xc_vxc_pw_create 22 8.4 0.038 0.045 8.071 8.092 + mp_allgather_i34 2640 14.4 6.000 7.987 6.000 7.987 + multiply_cannon_multrec 31680 15.4 5.196 7.640 5.214 7.656 + x_to_yz 1493 16.0 1.500 1.542 7.176 7.564 + cp_fm_cholesky_decompose 46 11.5 7.421 7.534 7.421 7.534 + transfer_rs2pw_100 642 13.7 2.197 2.301 7.307 7.444 + transfer_pw2rs_300 291 12.7 2.906 3.033 7.154 7.388 + mp_sum_d 5540 11.7 6.438 7.079 6.438 7.079 + make_images_data 5280 15.4 0.063 0.086 5.203 7.027 + cp_fm_redistribute_end 46 12.6 4.832 6.470 4.954 6.573 + integrate_four_center_dist_KS 214 12.2 0.106 0.123 6.375 6.464 + qs_ot_get_derivative_taylor 73 12.9 0.002 0.002 6.363 6.417 + generate_qs_task_list 33 9.9 0.151 0.199 6.166 6.234 + apply_preconditioner_fm 99 8.9 0.000 0.000 6.096 6.190 + apply_full_single 99 9.9 0.000 0.000 6.095 6.189 + integrate_four_center_getP 214 12.2 0.178 0.197 6.070 6.150 + apply_preconditioner_dbcsr 94 12.8 0.000 0.000 5.912 6.079 + apply_all 94 13.8 0.003 0.005 5.911 6.079 + distribute_tasks 33 10.9 0.033 0.036 5.988 6.071 + make_basis_sm 12 9.6 0.001 0.016 5.838 5.992 + cp_fm_cholesky_restore 24 10.8 5.526 5.616 5.526 5.616 + calculate_wz_matrix 11 7.9 0.000 0.000 5.554 5.604 + fft_wrap_pw1pw2_100 911 14.5 0.319 0.408 5.081 5.527 + ot_diis_step 82 11.8 0.004 0.004 5.377 5.417 + xc_rho_set_and_dset_create 121 11.9 0.047 0.054 5.079 5.414 + transfer_pw2rs_40 269 13.0 0.414 0.440 5.046 5.352 + calculate_dm_mo_no_diag 93 11.8 0.002 0.002 4.938 5.105 + qs_energies_init_hamiltonians 11 5.9 0.001 0.016 4.988 5.030 + get_current_loads 396 12.9 0.006 0.007 4.516 4.899 + mp_sum_dm 504 6.0 4.800 4.871 4.800 4.871 + calculate_whz_matrix 11 6.9 0.000 0.000 4.810 4.843 + pw_gather_p 2914 15.6 4.453 4.811 4.453 4.811 + cp_fm_redistribute_start 46 12.6 4.009 4.133 4.600 4.795 + calculate_first_density_matrix 1 7.0 0.000 0.007 4.358 4.397 + mp_sum_b 3720 13.7 4.213 4.389 4.213 4.389 + xc_pw_derive 132 10.4 0.002 0.002 4.097 4.289 + qs_env_update_s_mstruct 11 6.9 0.000 0.000 4.033 4.153 + reorthogonalize_vectors 10 9.0 0.000 0.000 3.996 4.124 + transfer_pw2rs_20 269 13.0 0.061 0.065 3.834 3.997 + qs_ot_get_p 94 10.5 0.001 0.001 3.753 3.977 + transfer_pw2rs_100 269 13.0 1.106 1.173 3.781 3.930 + mp_sum_iv 963 10.2 3.526 3.768 3.526 3.768 + cp_fm_cholesky_invert 22 12.4 3.601 3.681 3.601 3.681 + mp_irecv_dv 95390 15.8 1.484 3.679 1.484 3.679 + multiply_cannon_metrocomm4 29040 15.4 0.081 0.088 1.405 3.634 + hfx_admm_init 93 10.8 0.003 0.003 3.592 3.624 + fft_wrap_pw1pw2_20 911 14.5 0.015 0.016 3.432 3.581 + xc_functional_eval 44 10.4 0.001 0.001 3.220 3.565 + libxc_lda_eval 44 11.4 3.218 3.563 3.219 3.565 + ------------------------------------------------------------------------------- + diff --git a/benchmarks/QS_reference/w64GAPW.inp b/benchmarks/QS_reference/w64GAPW.inp new file mode 100644 index 0000000000..3ca76ad504 --- /dev/null +++ b/benchmarks/QS_reference/w64GAPW.inp @@ -0,0 +1,69 @@ +&FORCE_EVAL + METHOD QS + &DFT + BASIS_SET_FILE_NAME BASIS_MOLOPT_UZH + POTENTIAL_FILE_NAME POTENTIAL_UZH + &MGRID + CUTOFF 280 + REL_CUTOFF 60 + &END MGRID + &QS + METHOD GAPW + EPS_DEFAULT 1.0E-12 + &END QS + &SCF + SCF_GUESS ATOMIC + EPS_SCF 1.E-7 + MAX_SCF 10 + &OUTER_SCF + EPS_SCF 1.E-7 + MAX_SCF 10 + &END + &OT ON + MINIMIZER DIIS + PRECONDITIONER FULL_ALL + &END OT + &PRINT + &RESTART OFF + &END + &END + &END SCF + &XC + &XC_FUNCTIONAL PBE + &END XC_FUNCTIONAL + &END XC + &END DFT + &SUBSYS + &CELL + ABC 12.4138 12.4138 12.4138 + &END CELL + &TOPOLOGY + COORD_FILE_NAME geom.xyz + COORD_FILE_FORMAT xyz + &END TOPOLOGY + &KIND H + BASIS_SET ORB TZVPP-MOLOPT-GGA-ae + POTENTIAL ALL + &END KIND + &KIND O + BASIS_SET ORB TZVPP-MOLOPT-GGA-ae + POTENTIAL ALL + &END KIND + &END SUBSYS +&END FORCE_EVAL +&GLOBAL + PROJECT H2O-64 + RUN_TYPE MD + PRINT_LEVEL LOW + &TIMINGS + THRESHOLD 0.001 + &END +&END GLOBAL +&MOTION + &MD + ENSEMBLE NVE + STEPS 10 + TIMESTEP 0.5 + TEMPERATURE 300.0 + &END MD +&END MOTION diff --git a/benchmarks/QS_reference/w64GAPW.ref b/benchmarks/QS_reference/w64GAPW.ref new file mode 100644 index 0000000000..f340bb781b --- /dev/null +++ b/benchmarks/QS_reference/w64GAPW.ref @@ -0,0 +1,157 @@ + CP2K| version string: CP2K version 2023.2 (Development Version) + CP2K| source code revision number: git:15ad1db + CP2K| cp2kflags: omp libint fftw3 libxc elpa parallel mpi_f08 scalapack cosma x + CP2K| smm spglib sirius libvori libbqb libvdwxc + GLOBAL| Total number of message passing processes 48 + GLOBAL| Number of threads for this process 1 + GLOBAL| CPU model name AMD EPYC 7401 24-Core Processor + + MD| *************************************************************************** + MD| Step number 10 + MD| Time [fs] 5.000000 + MD| Conserved quantity [hartree] -0.488796321361E+04 + MD| --------------------------------------------------------------------------- + MD| Instantaneous Averages + MD| CPU time per MD step [s] 65.484219 84.432567 + MD| Energy drift per atom [K] -0.104690735602E+01 0.235911979593E+00 + MD| Potential energy [hartree] -0.488822834948E+04 -0.488819537025E+04 + MD| Kinetic energy [hartree] 0.265135866567E+00 0.232934310730E+00 + MD| Temperature [K] 292.227522 256.735602 + MD| *************************************************************************** + MD| Estimated peak process memory after this step [MiB] 630 + + ------------------------------------------------------------------------------- + - - + - T I M I N G - + - - + ------------------------------------------------------------------------------- + SUBROUTINE CALLS ASD SELF TIME TOTAL TIME + MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM + CP2K 1 1.0 0.022 0.054 844.629 844.661 + qs_mol_dyn_low 1 2.0 0.004 0.005 844.339 844.371 + qs_forces 11 3.9 0.002 0.002 844.281 844.313 + velocity_verlet 10 3.0 0.002 0.002 665.475 665.501 + qs_energies 11 4.9 0.001 0.001 557.462 557.485 + scf_env_do_scf 11 5.9 0.001 0.002 501.987 502.007 + scf_env_do_scf_inner_loop 88 6.7 0.003 0.008 435.615 435.631 + rebuild_ks_matrix 99 8.4 0.001 0.001 379.936 380.304 + qs_ks_build_kohn_sham_matrix 99 9.4 0.022 0.025 379.936 380.304 + update_ks_atom 99 10.4 229.483 266.030 234.222 270.742 + qs_rho_update_rho_low 99 7.8 0.002 0.003 254.226 254.309 + qs_ks_update_qs_env 101 7.7 0.001 0.002 217.547 217.882 + calculate_rho_atom_coeff 99 8.8 163.135 183.833 193.476 193.486 + qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 162.545 162.579 + build_core_hamiltonian_matrix_ 11 4.9 0.034 0.048 114.666 124.210 + dbcsr_multiply_generic 1885 12.5 0.103 0.113 69.521 100.240 + build_oce_matrices_forces 11 5.9 62.213 68.690 62.213 68.690 + sum_up_and_integrate 99 10.4 0.028 0.034 67.572 67.626 + integrate_v_rspace 99 11.4 0.003 0.004 67.543 67.601 + mp_sum_l 9247 13.1 38.486 67.024 38.486 67.024 + init_scf_loop 13 6.8 0.000 0.001 66.347 66.350 + grid_integrate_task_list 99 12.4 62.714 63.920 62.714 63.920 + calculate_rho_elec 99 8.8 0.020 0.023 60.747 60.831 + mp_sum_dm 57462 10.3 38.337 59.197 38.337 59.197 + grid_collocate_task_list 99 9.8 56.227 57.626 56.227 57.626 + build_core_ae_forces 11 5.9 46.112 51.778 46.112 51.778 + prepare_preconditioner 13 7.8 0.000 0.000 33.362 33.421 + make_preconditioner 13 8.8 0.000 0.000 32.136 32.144 + init_scf_run 11 5.9 0.000 0.002 31.306 31.307 + scf_env_initial_rho_setup 11 6.9 0.000 0.001 31.305 31.307 + make_full_all 13 9.8 0.004 0.005 30.920 30.929 + wfi_extrapolate 11 7.9 0.001 0.001 28.417 28.419 + multiply_cannon 1885 13.5 0.190 0.279 25.963 28.171 + mp_sum_d 3114 11.1 12.236 27.922 12.236 27.922 + multiply_cannon_loop 1885 14.5 0.176 0.200 24.433 26.908 + calculate_ecore_overlap 22 5.9 0.000 0.001 9.557 24.820 + qs_scf_new_mos 88 7.7 0.001 0.001 24.183 24.519 + qs_scf_loop_do_ot 88 8.7 0.001 0.001 24.182 24.518 + qs_energies_init_hamiltonians 11 5.9 0.000 0.001 23.787 23.788 + build_core_hamiltonian_matrix 11 6.9 0.088 0.187 21.496 23.456 + ot_scf_mini 88 9.7 0.002 0.003 22.968 23.277 + mp_waitall_1 166739 16.5 14.631 22.509 14.631 22.509 + multiply_cannon_metrocomm3 22620 15.5 0.067 0.075 12.225 20.143 + build_oce_matrices 11 7.9 15.168 16.792 15.168 16.792 + ot_mini 88 10.7 0.001 0.001 16.049 16.387 + cp_fm_diag_elpa 59 11.7 0.000 0.000 15.851 15.854 + cp_fm_diag_elpa_base 59 12.6 15.156 15.630 15.349 15.759 + integrate_vhg0_rspace 99 10.4 2.350 3.035 11.645 11.702 + multiply_cannon_multrec 22620 15.5 9.221 11.560 9.234 11.573 + apply_preconditioner_dbcsr 101 12.7 0.000 0.000 10.659 11.016 + apply_all 101 13.7 0.006 0.007 10.659 11.016 + prepare_gapw_den 99 10.4 0.003 0.004 10.834 10.852 + ot_diis_step 88 11.7 0.004 0.005 9.826 9.826 + cp_fm_cholesky_reduce 13 10.8 8.578 8.585 8.578 8.585 + multiply_cannon_metrocomm4 20735 15.5 0.068 0.074 2.578 8.441 + mp_irecv_dv 65157 15.8 2.537 8.314 2.537 8.314 + calculate_vxc_atom 99 10.4 0.711 0.792 7.624 7.624 + qs_ot_get_derivative 88 11.7 0.001 0.001 6.172 6.481 + pw_transfer 2079 12.6 0.190 0.229 6.101 6.371 + calculate_rho_atom 198 11.4 4.601 6.214 4.601 6.214 + fft_wrap_pw1pw2 1782 13.8 0.022 0.025 5.867 6.134 + gaVxcgb_GC 396 11.4 4.559 6.028 4.559 6.028 + fft_wrap_pw1pw2_140 1188 15.1 0.679 0.809 5.470 5.738 + density_rs2pw 99 9.8 0.005 0.005 4.020 5.648 + qs_env_update_s_mstruct 11 6.9 0.000 0.000 2.174 5.611 + qs_create_task_list 11 7.9 0.000 0.000 2.166 5.605 + generate_qs_task_list 11 8.9 0.122 0.143 2.166 5.604 + qs_vxc_create 99 10.4 0.002 0.002 5.552 5.553 + xc_vxc_pw_create 99 11.4 0.041 0.048 5.550 5.551 + transfer_rs2pw 495 11.1 0.009 0.013 3.889 5.482 + distribute_tasks 11 9.9 0.016 0.018 2.031 5.479 + load_balance_distributed 11 10.9 0.000 0.000 1.993 5.441 + compute_load_list 22 11.9 0.008 0.009 1.990 5.438 + get_current_loads 110 11.7 0.002 0.003 1.988 5.438 + mp_alltoall_l 121 12.6 1.984 5.435 1.984 5.435 + mp_bcast_dm 38118 11.4 4.746 4.894 4.746 4.894 + fft3d_ps 1782 15.8 2.160 2.533 4.455 4.797 + make_m2s 3770 13.5 0.062 0.072 4.471 4.751 + build_core_ae 11 7.9 4.161 4.696 4.161 4.696 + mp_waitany 22176 14.0 3.076 4.690 3.076 4.690 + transfer_rs2pw_140 198 12.6 0.650 0.691 2.946 4.540 + build_kinetic_matrix_low 22 6.9 4.181 4.420 4.190 4.428 + build_overlap_matrix_low 22 6.9 4.166 4.407 4.177 4.418 + make_images 3770 14.5 0.132 0.145 3.711 4.022 + cp_dbcsr_sm_fm_multiply 71 9.9 0.002 0.003 3.749 3.756 + xc_pw_derive 594 13.4 0.004 0.005 3.257 3.663 + transfer_pw2rs 495 13.0 0.010 0.012 3.527 3.613 + xc_rho_set_and_dset_create 99 12.4 0.051 0.057 3.233 3.550 + mp_alltoall_d11v 2549 13.5 2.305 3.472 2.305 3.472 + cp_dbcsr_sm_fm_multiply_core 71 10.9 0.000 0.000 3.230 3.460 + calculate_rho0_atom 198 11.4 2.719 3.147 2.719 3.147 + potential_pw2rs 99 12.4 0.005 0.006 2.983 2.993 + rs_gather_matrices 99 12.4 0.141 0.173 1.794 2.981 + mp_alltoall_z22v 1782 17.8 1.914 2.742 1.914 2.742 + mp_sum_dv 2908 15.0 1.717 2.620 1.717 2.620 + xc_pw_divergence 99 12.4 0.002 0.003 2.181 2.562 + xc_functional_eval 891 12.5 0.003 0.003 2.261 2.525 + pbe_lda_eval 891 13.5 2.258 2.523 2.258 2.523 + transfer_pw2rs_140 198 13.4 0.947 1.018 2.369 2.509 + qs_ot_get_derivative_taylor 70 12.9 0.002 0.003 2.278 2.506 + cp_fm_cholesky_restore 26 10.8 2.384 2.397 2.384 2.397 + subspace_eigenvalues_ks_dbcsr 26 9.3 0.001 0.001 2.240 2.295 + qs_ot_get_p 101 10.5 0.001 0.001 1.803 2.292 + parallel_gemm_fm 160 9.7 0.000 0.001 2.118 2.196 + parallel_gemm_fm_cosma 160 10.7 2.118 2.195 2.118 2.195 + make_images_data 3770 15.5 0.048 0.062 1.822 2.074 + yz_to_x 693 16.9 0.101 0.126 1.227 1.890 + put_rho0_on_grid 99 11.4 0.166 0.174 1.840 1.858 + hybrid_alltoall_any 3987 16.3 0.074 0.312 1.610 1.829 + cp_fm_cholesky_decompose 26 10.6 1.461 1.473 1.461 1.473 + calculate_dm_sparse 99 9.6 0.001 0.001 1.377 1.449 + copy_dbcsr_to_fm 217 10.8 0.005 0.006 1.083 1.443 + make_images_pack 3770 15.5 0.874 1.282 0.885 1.292 + dbcsr_dot_sd 894 12.1 0.130 0.146 0.698 1.213 + make_images_sizes 3770 15.5 0.004 0.004 0.684 1.209 + mp_alltoall_i44 3770 16.5 0.680 1.206 0.680 1.206 + qs_ot_get_orbitals 88 10.7 0.000 0.001 1.154 1.183 + cp_dbcsr_syevd 46 11.0 0.004 0.004 1.005 1.029 + x_to_yz 693 17.0 0.129 0.154 0.888 1.018 + mp_alltoall_i22 780 13.4 0.489 0.968 0.489 0.968 + mp_allgather_i34 1885 14.5 0.596 0.960 0.596 0.960 + transfer_pw2rs_50 99 14.4 0.229 0.544 0.801 0.939 + make_basis_sm 13 9.4 0.000 0.001 0.902 0.908 + qs_ot_get_derivative_diag 18 12.0 0.000 0.001 0.812 0.892 + dbcsr_desymmetrize_deep 217 11.8 0.053 0.067 0.503 0.862 + cp_fm_redistribute_end 59 12.7 0.446 0.859 0.452 0.862 + dbcsr_complete_redistribute 431 11.9 0.253 0.277 0.826 0.855 + ------------------------------------------------------------------------------- diff --git a/benchmarks/QS_reference/w64PBE.inp b/benchmarks/QS_reference/w64PBE.inp new file mode 100644 index 0000000000..ef01c8b863 --- /dev/null +++ b/benchmarks/QS_reference/w64PBE.inp @@ -0,0 +1,69 @@ +&FORCE_EVAL + METHOD QS + &DFT + BASIS_SET_FILE_NAME BASIS_MOLOPT_UZH + POTENTIAL_FILE_NAME POTENTIAL_UZH + &MGRID + CUTOFF 400 + REL_CUTOFF 60 + &END MGRID + &QS + METHOD GPW + EPS_DEFAULT 1.0E-12 + &END QS + &SCF + SCF_GUESS ATOMIC + EPS_SCF 1.E-7 + MAX_SCF 10 + &OUTER_SCF + EPS_SCF 1.E-7 + MAX_SCF 10 + &END + &OT ON + MINIMIZER DIIS + PRECONDITIONER FULL_SINGLE_INVERSE + &END OT + &PRINT + &RESTART OFF + &END + &END + &END SCF + &XC + &XC_FUNCTIONAL PBE + &END XC_FUNCTIONAL + &END XC + &END DFT + &SUBSYS + &CELL + ABC 12.4138 12.4138 12.4138 + &END CELL + &TOPOLOGY + COORD_FILE_NAME geom.xyz + COORD_FILE_FORMAT xyz + &END TOPOLOGY + &KIND H + BASIS_SET ORB TZVP-MOLOPT-GGA-GTH-q1 + POTENTIAL GTH-GGA-q1 + &END KIND + &KIND O + BASIS_SET ORB TZVP-MOLOPT-GGA-GTH-q6 + POTENTIAL GTH-GGA-q6 + &END KIND + &END SUBSYS +&END FORCE_EVAL +&GLOBAL + PROJECT H2O-64 + RUN_TYPE MD + PRINT_LEVEL LOW + &TIMINGS + THRESHOLD 0.001 + &END +&END GLOBAL +&MOTION + &MD + ENSEMBLE NVE + STEPS 10 + TIMESTEP 0.5 + TEMPERATURE 300.0 + &END MD +&END MOTION diff --git a/benchmarks/QS_reference/w64PBE.ref b/benchmarks/QS_reference/w64PBE.ref new file mode 100644 index 0000000000..853721d027 --- /dev/null +++ b/benchmarks/QS_reference/w64PBE.ref @@ -0,0 +1,181 @@ + CP2K| version string: CP2K version 2023.2 (Development Version) + CP2K| source code revision number: git:15ad1db + CP2K| cp2kflags: omp libint fftw3 libxc elpa parallel mpi_f08 scalapack cosma x + CP2K| smm spglib sirius libvori libbqb libvdwxc + GLOBAL| Total number of message passing processes 48 + GLOBAL| Number of threads for this process 1 + GLOBAL| CPU model name AMD EPYC 7401 24-Core Processor + + MD| *************************************************************************** + MD| Step number 10 + MD| Time [fs] 5.000000 + MD| Conserved quantity [hartree] -0.110249596807E+04 + MD| --------------------------------------------------------------------------- + MD| Instantaneous Averages + MD| CPU time per MD step [s] 8.273586 11.854998 + MD| Energy drift per atom [K] -0.856603985250E+00 0.594729349263E+00 + MD| Potential energy [hartree] -0.110275514041E+04 -0.110271804018E+04 + MD| Kinetic energy [hartree] 0.259172340513E+00 0.222954073226E+00 + MD| Temperature [K] 285.654641 245.735581 + MD| *************************************************************************** + MD| Estimated peak process memory after this step [MiB] 230 + + ------------------------------------------------------------------------------- + - - + - T I M I N G - + - - + ------------------------------------------------------------------------------- + SUBROUTINE CALLS ASD SELF TIME TOTAL TIME + MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM + CP2K 1 1.0 0.007 0.029 118.684 118.732 + qs_mol_dyn_low 1 2.0 0.004 0.004 118.556 118.604 + qs_forces 11 3.9 0.002 0.002 118.502 118.549 + qs_energies 11 4.9 0.001 0.001 109.558 109.602 + scf_env_do_scf 11 5.9 0.001 0.002 102.877 102.918 + velocity_verlet 10 3.0 0.001 0.002 94.271 94.309 + scf_env_do_scf_inner_loop 106 6.8 0.003 0.009 93.540 93.578 + rebuild_ks_matrix 117 8.5 0.000 0.001 59.127 59.326 + qs_ks_build_kohn_sham_matrix 117 9.5 0.020 0.024 59.127 59.326 + qs_ks_update_qs_env 120 7.8 0.002 0.002 52.023 52.203 + qs_rho_update_rho_low 117 7.9 0.001 0.001 43.928 43.956 + calculate_rho_elec 117 8.9 0.038 0.048 43.928 43.955 + sum_up_and_integrate 117 10.5 0.048 0.070 43.389 43.414 + integrate_v_rspace 117 11.5 0.004 0.004 43.341 43.368 + grid_collocate_task_list 117 9.9 37.600 38.719 37.600 38.719 + grid_integrate_task_list 117 12.5 36.582 37.686 36.582 37.686 + pw_transfer 2234 12.7 0.214 0.247 12.967 13.176 + fft_wrap_pw1pw2 2000 13.9 0.028 0.031 12.684 12.878 + qs_vxc_create 117 10.5 0.004 0.004 12.401 12.466 + xc_vxc_pw_create 117 11.5 0.092 0.123 12.397 12.461 + fft_wrap_pw1pw2_200 1298 15.3 1.771 2.155 11.888 12.103 + dbcsr_multiply_generic 2035 12.5 0.081 0.089 10.914 11.340 + fft3d_ps 2000 15.9 4.147 5.063 9.222 9.659 + init_scf_loop 14 6.8 0.000 0.000 9.318 9.321 + qs_scf_new_mos 106 7.8 0.001 0.001 8.576 8.786 + qs_scf_loop_do_ot 106 8.8 0.001 0.001 8.575 8.785 + multiply_cannon 2035 13.5 0.163 0.206 7.746 8.724 + ot_scf_mini 106 9.8 0.002 0.003 8.023 8.194 + multiply_cannon_loop 2035 14.5 0.117 0.132 7.113 8.088 + xc_pw_derive 702 13.5 0.007 0.008 7.680 7.878 + xc_rho_set_and_dset_create 117 12.5 0.103 0.128 6.794 7.703 + mp_waitall_1 180577 16.5 5.549 7.213 5.549 7.213 + qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 7.150 7.170 + density_rs2pw 117 9.9 0.006 0.007 6.000 7.137 + multiply_cannon_metrocomm3 24420 15.5 0.056 0.061 3.868 5.573 + xc_pw_divergence 117 12.5 0.004 0.004 5.323 5.486 + init_scf_run 11 5.9 0.000 0.001 5.325 5.327 + scf_env_initial_rho_setup 11 6.9 0.000 0.001 5.325 5.327 + potential_pw2rs 117 12.5 0.008 0.008 5.260 5.273 + ot_mini 106 10.8 0.001 0.001 4.876 5.068 + wfi_extrapolate 11 7.9 0.001 0.001 4.910 4.912 + mp_alltoall_z22v 2000 17.9 4.287 4.820 4.287 4.820 + transfer_rs2pw 479 10.8 0.009 0.011 3.735 4.818 + xc_functional_eval 117 13.5 0.002 0.003 3.152 4.032 + pbe_lda_eval 117 14.5 3.150 4.030 3.150 4.030 + transfer_pw2rs 479 13.4 0.007 0.009 3.939 3.946 + mp_waitany 14336 13.9 2.279 3.512 2.279 3.512 + multiply_cannon_multrec 24420 15.5 2.147 3.298 2.156 3.309 + qs_ot_get_derivative 106 11.8 0.001 0.001 3.122 3.291 + yz_to_x 830 16.8 0.302 0.528 2.902 3.207 + transfer_rs2pw_200 128 11.7 0.377 0.487 2.054 3.157 + mp_alltoall_d11v 2144 13.6 1.701 2.983 1.701 2.983 + rs_gather_matrices 117 12.5 0.036 0.041 1.481 2.749 + x_to_yz 936 17.2 0.357 0.565 2.034 2.202 + prepare_preconditioner 14 7.8 0.000 0.000 2.103 2.132 + make_preconditioner 14 8.8 0.000 0.000 2.102 2.132 + multiply_cannon_metrocomm4 22385 15.5 0.054 0.059 0.810 2.119 + make_m2s 4070 13.5 0.053 0.058 1.968 2.083 + mp_irecv_dv 61473 16.0 0.732 2.034 0.732 2.034 + transfer_pw2rs_200 128 14.1 0.835 0.911 1.918 1.971 + apply_preconditioner_dbcsr 120 12.8 0.000 0.000 1.634 1.842 + apply_single 120 13.8 0.000 0.000 1.634 1.842 + make_images 4070 14.5 0.117 0.130 1.593 1.753 + build_core_hamiltonian_matrix_ 11 4.9 0.000 0.001 1.600 1.744 + ot_diis_step 106 11.8 0.005 0.005 1.721 1.721 + qs_ot_get_derivative_taylor 89 12.9 0.002 0.003 1.529 1.676 + mp_sum_l 9940 13.2 0.785 1.453 0.785 1.453 + transfer_pw2rs_70 117 14.5 0.449 0.549 1.377 1.423 + qs_ot_get_p 120 10.5 0.001 0.001 1.106 1.358 + mp_sendrecv_dv 16497 12.9 1.201 1.270 1.201 1.270 + qs_energies_init_hamiltonians 11 5.9 0.000 0.000 1.160 1.161 + mp_sum_d 3825 11.6 0.782 1.152 0.782 1.152 + make_full_single_inverse 14 9.8 0.001 0.001 1.115 1.144 + pw_gather_p 947 15.5 0.935 1.120 0.935 1.120 + transfer_rs2pw_70 117 11.9 0.384 0.446 1.055 1.096 + build_core_ppl_forces 11 5.9 0.859 1.002 0.859 1.002 + make_full_inverse_cholesky 14 9.8 0.000 0.000 0.940 0.952 + cp_dbcsr_sm_fm_multiply 46 9.3 0.001 0.001 0.800 0.803 + make_images_data 4070 15.5 0.040 0.049 0.632 0.742 + build_core_hamiltonian_matrix 11 6.9 0.001 0.001 0.666 0.739 + make_images_sizes 4070 15.5 0.004 0.004 0.471 0.735 + mp_alltoall_i44 4070 16.5 0.468 0.731 0.468 0.731 + pw_scatter_p 1053 16.2 0.672 0.714 0.672 0.714 + qs_ot_get_orbitals 106 10.8 0.000 0.000 0.670 0.692 + cp_dbcsr_sm_fm_multiply_core 46 10.3 0.000 0.000 0.614 0.690 + calculate_dm_sparse 117 9.7 0.000 0.000 0.617 0.665 + hybrid_alltoall_any 4213 16.4 0.042 0.089 0.514 0.631 + mp_isendrecv_dv 16497 15.5 0.309 0.626 0.309 0.626 + dbcsr_dot_sd 1125 12.2 0.040 0.048 0.318 0.587 + fft_wrap_pw1pw2_70 234 14.2 0.045 0.058 0.486 0.568 + transfer_pw2rs_30 117 14.5 0.108 0.116 0.508 0.531 + qs_env_update_s_mstruct 11 6.9 0.000 0.000 0.447 0.497 + transfer_rs2pw_30 117 11.9 0.068 0.071 0.490 0.496 + mp_allgather_i34 2035 14.5 0.273 0.491 0.273 0.491 + dbcsr_sym_m_v_mult 1269 12.5 0.016 0.022 0.455 0.460 + cp_fm_cholesky_invert 14 10.8 0.445 0.451 0.445 0.451 + arnoldi_generalized_ev 14 10.8 0.000 0.000 0.446 0.450 + pw_derive 702 14.5 0.395 0.448 0.395 0.448 + pw_copy 1404 13.3 0.392 0.431 0.392 0.431 + qs_ot_get_derivative_diag 17 12.0 0.000 0.000 0.390 0.421 + build_kinetic_matrix_low 22 6.9 0.387 0.418 0.390 0.421 + build_core_ppl 11 7.9 0.355 0.415 0.355 0.415 + parallel_gemm_fm 96 8.9 0.000 0.000 0.409 0.415 + parallel_gemm_fm_cosma 96 9.9 0.409 0.414 0.409 0.414 + gev_build_subspace 23 11.5 0.003 0.007 0.408 0.408 + build_overlap_matrix_low 22 6.9 0.371 0.403 0.375 0.408 + cp_fm_cholesky_decompose 28 10.5 0.399 0.403 0.399 0.403 + copy_dbcsr_to_fm 143 10.8 0.002 0.003 0.309 0.400 + make_basis_sm 14 9.3 0.000 0.001 0.373 0.376 + dbcsr_make_images_dense 3364 14.9 0.031 0.033 0.276 0.368 + mp_alltoall_i22 633 13.6 0.192 0.366 0.192 0.366 + dbcsr_make_dense_low 8254 15.7 0.036 0.038 0.250 0.361 + dbcsr_complete_redistribute 323 11.8 0.067 0.079 0.324 0.357 + qs_ot_p2m_diag 19 11.0 0.003 0.004 0.342 0.344 + calculate_rho_core 11 7.9 0.020 0.023 0.287 0.336 + make_images_pack 4070 15.5 0.203 0.325 0.212 0.334 + rs_grid_zero 139 14.6 0.301 0.320 0.301 0.320 + make_dense_data 8254 16.7 0.175 0.277 0.197 0.309 + pw_poisson_solve 117 10.5 0.046 0.049 0.294 0.295 + cp_dbcsr_syevd 19 12.0 0.002 0.002 0.283 0.284 + reorthogonalize_vectors 10 9.0 0.000 0.000 0.269 0.271 + calculate_ecore_overlap 22 5.9 0.000 0.000 0.158 0.266 + cp_fm_diag_elpa 19 13.0 0.000 0.000 0.256 0.256 + cp_fm_redistribute_end 19 14.0 0.125 0.241 0.128 0.243 + dbcsr_sym_m_v_mult_local_mm 1269 13.5 0.214 0.240 0.216 0.243 + ot_scf_init 14 7.8 0.001 0.002 0.240 0.241 + dbcsr_desymmetrize_deep 143 11.8 0.009 0.012 0.142 0.239 + fft_wrap_pw1pw2_30 234 14.2 0.009 0.011 0.202 0.233 + cp_fm_diag_elpa_base 19 14.0 0.110 0.222 0.114 0.229 + build_core_ppnl_forces 11 5.9 0.207 0.228 0.207 0.228 + copy_fm_to_dbcsr 180 10.8 0.001 0.001 0.188 0.225 + pw_axpy 1053 12.0 0.191 0.212 0.191 0.212 + dbcsr_create_new 37103 15.1 0.124 0.132 0.190 0.203 + integrate_v_core_rspace 11 7.9 0.018 0.019 0.185 0.191 + qs_energies_compute_matrix_w 11 5.9 0.000 0.000 0.183 0.187 + calculate_w_matrix_ot 11 6.9 0.000 0.001 0.183 0.187 + rs_scatter_matrices 128 9.9 0.042 0.061 0.165 0.183 + arnoldi_normal_ev 134 12.4 0.002 0.003 0.153 0.177 + qs_create_task_list 11 7.9 0.000 0.000 0.156 0.160 + generate_qs_task_list 11 8.9 0.078 0.094 0.156 0.160 + mp_irecv_dm3 2048 13.9 0.072 0.158 0.072 0.158 + pw_integral_ab 117 11.5 0.124 0.129 0.153 0.158 + multiply_cannon_metrocomm2 18315 15.5 0.042 0.046 0.109 0.156 + mp_sum_dv 7068 14.3 0.127 0.155 0.127 0.155 + pw_zero 585 13.0 0.126 0.154 0.126 0.154 + cp_dbcsr_plus_fm_fm_t_native 22 8.9 0.000 0.000 0.138 0.145 + dbcsr_new_transposed 836 13.4 0.007 0.008 0.108 0.137 + transfer_pw2rs_10 117 14.5 0.018 0.019 0.128 0.135 + transfer_rs2pw_10 117 11.9 0.020 0.021 0.128 0.133 + arnoldi_extremal 120 11.5 0.001 0.002 0.100 0.124 + dbcsr_redistribute 167 14.9 0.005 0.007 0.089 0.122 + ------------------------------------------------------------------------------- diff --git a/benchmarks/QS_reference/w64PBE0.inp b/benchmarks/QS_reference/w64PBE0.inp new file mode 100644 index 0000000000..f6ac221e78 --- /dev/null +++ b/benchmarks/QS_reference/w64PBE0.inp @@ -0,0 +1,101 @@ +&FORCE_EVAL + METHOD QS + &DFT + BASIS_SET_FILE_NAME BASIS_ADMM_UZH + BASIS_SET_FILE_NAME BASIS_MOLOPT_UZH + POTENTIAL_FILE_NAME POTENTIAL_UZH + &MGRID + CUTOFF 400 + REL_CUTOFF 60 + &END MGRID + &QS + METHOD GPW + EPS_DEFAULT 1.0E-12 + MIN_PAIR_LIST_RADIUS -1 + &END QS + &AUXILIARY_DENSITY_MATRIX_METHOD + ADMM_PURIFICATION_METHOD NONE + METHOD CHARGE_CONSTRAINED_PROJECTION + EXCH_SCALING_MODEL MERLOT + EXCH_CORRECTION_FUNC OPTX + &END + &SCF + SCF_GUESS ATOMIC + EPS_SCF 1.E-7 + MAX_SCF 10 + &OUTER_SCF + EPS_SCF 1.E-7 + MAX_SCF 10 + &END + &OT ON + MINIMIZER DIIS + PRECONDITIONER FULL_SINGLE_INVERSE + &END OT + &PRINT + &RESTART OFF + &END + &END + &END SCF + &XC + &XC_FUNCTIONAL PBE + &PBE + SCALE_X 0.75 + SCALE_C 1.0 + &END PBE + &END XC_FUNCTIONAL + &HF + &HF_INFO ON + &END + &SCREENING + EPS_SCHWARZ 1.0E-08 + SCREEN_ON_INITIAL_P .TRUE. + &END + &MEMORY + MAX_MEMORY 500 + EPS_STORAGE_SCALING 0.01 + &END + &INTERACTION_POTENTIAL + POTENTIAL_TYPE TRUNCATED + CUTOFF_RADIUS 5.0 + T_C_G_DATA t_c_g.dat + &END + FRACTION 0.25 + &END + &END XC + &END DFT + &SUBSYS + &CELL + ABC 12.4138 12.4138 12.4138 + &END CELL + &TOPOLOGY + COORD_FILE_NAME geom.xyz + COORD_FILE_FORMAT xyz + &END TOPOLOGY + &KIND H + BASIS_SET ORB TZVP-MOLOPT-HYB-GTH-q1 + BASIS_SET AUX_FIT admm-dz-q1 + POTENTIAL GTH-HYB-q1 + &END KIND + &KIND O + BASIS_SET ORB TZVP-MOLOPT-HYB-GTH-q6 + BASIS_SET AUX_FIT admm-dz-q6 + POTENTIAL GTH-HYB-q6 + &END KIND + &END SUBSYS +&END FORCE_EVAL +&GLOBAL + PROJECT H2O-64 + RUN_TYPE MD + PRINT_LEVEL LOW + &TIMINGS + THRESHOLD 0.001 + &END +&END GLOBAL +&MOTION + &MD + ENSEMBLE NVE + STEPS 10 + TIMESTEP 0.5 + TEMPERATURE 300.0 + &END MD +&END MOTION diff --git a/benchmarks/QS_reference/w64PBE0.ref b/benchmarks/QS_reference/w64PBE0.ref new file mode 100644 index 0000000000..d6fca76315 --- /dev/null +++ b/benchmarks/QS_reference/w64PBE0.ref @@ -0,0 +1,141 @@ + CP2K| version string: CP2K version 2023.2 (Development Version) + CP2K| source code revision number: git:15ad1db + CP2K| cp2kflags: omp libint fftw3 libxc elpa parallel mpi_f08 scalapack cosma x + CP2K| smm spglib sirius libvori libbqb libvdwxc + GLOBAL| Total number of message passing processes 48 + GLOBAL| Number of threads for this process 1 + GLOBAL| CPU model name AMD EPYC 7401 24-Core Processor + + HFX_MEM_INFO| Est. max. program size before HFX [MiB]: 349 + HFX_MEM_INFO| Number of cart. primitive ERI's calculated: 3831517656 + HFX_MEM_INFO| Number of sph. ERI's calculated: 1313217004 + HFX_MEM_INFO| Number of sph. ERI's stored in-core: 1298991352 + HFX_MEM_INFO| Number of sph. ERI's stored on disk: 0 + HFX_MEM_INFO| Number of sph. ERI's calculated on the fly: 0 + HFX_MEM_INFO| Total memory consumption ERI's RAM [MiB]: 2217 + HFX_MEM_INFO| Whereof max-vals [MiB]: 194 + HFX_MEM_INFO| Total compression factor ERI's RAM: 4.47 + HFX_MEM_INFO| Total memory consumption ERI's disk [MiB]: 0 + HFX_MEM_INFO| Total compression factor ERI's disk: 0.00 + HFX_MEM_INFO| Size of density/Fock matrix [MiB]: 4 + HFX_MEM_INFO| Size of buffers [MiB]: 3 + HFX_MEM_INFO| Number of periodic image cells considered: 27 + HFX_MEM_INFO| Est. max. program size after HFX [MiB]: 349 + + MD| *************************************************************************** + MD| Step number 10 + MD| Time [fs] 5.000000 + MD| Conserved quantity [hartree] -0.110123863493E+04 + MD| --------------------------------------------------------------------------- + MD| Instantaneous Averages + MD| CPU time per MD step [s] 91.364253 130.573164 + MD| Energy drift per atom [K] -0.138320451453E+01 -0.572168334182E+00 + MD| Potential energy [hartree] -0.110151044271E+04 -0.110148923645E+04 + MD| Kinetic energy [hartree] 0.271807777884E+00 0.251089492272E+00 + MD| Temperature [K] 299.581171 276.745885 + MD| *************************************************************************** + MD| Estimated peak process memory after this step [MiB] 350 + + ------------------------------------------------------------------------------- + - - + - T I M I N G - + - - + ------------------------------------------------------------------------------- + SUBROUTINE CALLS ASD SELF TIME TOTAL TIME + MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM + CP2K 1 1.0 0.011 0.031 1306.096 1306.177 + qs_mol_dyn_low 1 2.0 0.005 0.005 1305.737 1305.818 + qs_forces 11 3.9 0.002 0.002 1305.679 1305.760 + rebuild_ks_matrix 115 8.5 0.000 0.001 1257.918 1257.983 + qs_ks_build_kohn_sham_matrix 115 9.5 0.025 0.029 1257.918 1257.983 + hfx_ks_matrix 115 10.5 0.006 0.006 1164.668 1164.740 + qs_energies 11 4.9 0.001 0.001 1130.980 1131.048 + scf_env_do_scf 11 5.9 0.001 0.002 1125.267 1125.336 + qs_ks_update_qs_env 117 7.8 0.002 0.002 1085.045 1085.113 + integrate_four_center 115 11.5 0.190 0.558 1082.420 1082.487 + integrate_four_center_main 115 12.5 0.072 0.078 1033.483 1053.688 + integrate_four_center_bin 7360 13.5 1033.411 1053.615 1033.411 1053.615 + velocity_verlet 10 3.0 0.002 0.002 1004.733 1004.796 + scf_env_do_scf_inner_loop 104 6.8 0.003 0.008 790.874 790.923 + init_scf_loop 13 6.8 0.000 0.001 334.374 334.395 + qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 172.912 172.927 + derivatives_four_center 11 8.9 0.009 0.390 82.190 82.195 + derivatives_four_center_main 11 9.9 0.015 0.016 72.142 72.147 + derivatives_four_center_bin 727 10.9 70.036 71.221 70.036 71.221 + mp_sync 706 13.3 34.058 53.657 34.058 53.657 + calculate_rho_elec 230 10.2 0.075 0.096 45.346 45.373 + sum_up_and_integrate 115 10.5 0.067 0.087 44.739 44.747 + integrate_v_rspace 230 11.5 0.007 0.008 44.655 44.670 + grid_collocate_task_list 230 11.2 33.703 34.709 33.703 34.709 + grid_integrate_task_list 230 12.5 31.455 33.860 31.455 33.860 + qs_rho_update_rho_low 115 7.9 0.001 0.001 32.317 32.344 + pw_transfer 4036 13.3 0.383 0.452 23.488 23.869 + fft_wrap_pw1pw2 3806 14.4 0.052 0.059 23.037 23.374 + hfx_load_balance 2 11.5 0.003 0.003 22.014 22.016 + fft_wrap_pw1pw2_200 2426 15.7 3.297 4.009 21.633 22.009 + qs_vxc_create 230 10.5 0.006 0.007 21.691 21.693 + xc_vxc_pw_create 230 11.5 0.180 0.242 21.685 21.687 + fft3d_ps 3806 16.4 7.795 9.263 16.540 17.422 + admm_mo_calc_rho_aux 115 10.5 0.002 0.002 15.406 15.475 + xc_pw_derive 1380 13.5 0.014 0.016 14.459 14.722 + xc_rho_set_and_dset_create 230 12.5 0.196 0.253 11.238 12.668 + integrate_four_center_load 115 12.5 0.001 0.001 12.607 12.611 + density_rs2pw 230 11.2 0.013 0.015 11.125 12.010 + dbcsr_multiply_generic 2192 12.6 0.094 0.100 11.016 11.610 + hfx_load_balance_bin 2 12.5 10.656 11.002 10.656 11.002 + hfx_load_balance_count 2 12.5 10.657 10.999 10.657 10.999 + potential_pw2rs 230 12.5 0.015 0.016 10.230 10.256 + xc_pw_divergence 230 12.5 0.007 0.008 9.898 10.133 + mp_waitall_1 223595 16.4 7.746 9.779 7.746 9.779 + derivatives_four_center_load 11 9.9 0.000 0.000 9.451 9.454 + multiply_cannon 2192 13.6 0.183 0.226 7.886 8.864 + qs_scf_new_mos 104 7.8 0.001 0.001 8.616 8.661 + qs_scf_loop_do_ot 104 8.8 0.001 0.001 8.615 8.660 + multiply_cannon_loop 2192 14.6 0.128 0.139 7.218 8.223 + mp_alltoall_z22v 3806 18.4 7.266 8.189 7.266 8.189 + ot_scf_mini 104 9.8 0.002 0.003 8.060 8.082 + parallel_gemm_fm 884 12.0 0.003 0.003 7.712 7.819 + parallel_gemm_fm_cosma 884 13.0 7.710 7.817 7.710 7.817 + transfer_pw2rs 931 13.5 0.013 0.018 7.504 7.508 + transfer_rs2pw 931 12.2 0.018 0.024 6.625 7.470 + admm_mo_merge_ks_matrix 115 10.5 0.001 0.001 6.655 6.660 + merge_ks_matrix_none 115 11.5 0.010 0.011 6.654 6.659 + yz_to_x 1621 17.3 0.602 1.049 5.020 5.540 + multiply_cannon_metrocomm3 26304 15.6 0.059 0.067 3.882 5.530 + xc_functional_eval 345 13.5 1.114 1.436 4.201 5.435 + ot_mini 104 10.8 0.001 0.001 4.820 4.825 + mp_waitany 26992 14.7 3.532 4.622 3.532 4.622 + mp_alltoall_d11v 7109 14.1 3.671 4.600 3.671 4.600 + init_scf_run 11 5.9 0.000 0.001 4.333 4.333 + scf_env_initial_rho_setup 11 6.9 0.000 0.001 4.332 4.333 + transfer_rs2pw_200 241 13.0 0.811 1.040 3.273 4.168 + pbe_lda_eval 115 14.5 3.087 4.005 3.087 4.005 + wfi_extrapolate 11 7.9 0.001 0.001 3.945 3.945 + rs_gather_matrices 230 12.5 0.055 0.062 2.943 3.865 + x_to_yz 1725 17.5 0.648 1.053 3.474 3.739 + transfer_pw2rs_200 241 14.3 1.558 1.656 3.557 3.602 + multiply_cannon_multrec 26304 15.6 2.186 3.339 2.197 3.350 + mp_sum_lv 61 6.0 2.091 3.272 2.091 3.272 + qs_ot_get_derivative 104 11.8 0.001 0.001 3.060 3.082 + transfer_pw2rs_70 230 14.5 0.908 1.045 2.654 2.715 + mp_sendrecv_dv 32430 14.2 2.396 2.572 2.396 2.572 + pw_gather_p 1851 16.2 1.840 2.312 1.840 2.312 + mp_sum_l 10749 13.3 1.334 2.166 1.334 2.166 + transfer_rs2pw_70 230 13.2 0.760 0.872 2.098 2.163 + make_m2s 4384 13.6 0.059 0.062 2.013 2.140 + multiply_cannon_metrocomm4 24112 15.6 0.058 0.063 0.834 2.118 + prepare_preconditioner 13 7.8 0.000 0.000 2.053 2.054 + make_preconditioner 13 8.8 0.000 0.000 2.053 2.054 + mp_irecv_dv 75995 16.0 0.786 2.052 0.786 2.052 + copy_dbcsr_to_fm 631 11.6 0.012 0.016 1.596 1.965 + apply_preconditioner_dbcsr 117 12.8 0.000 0.000 1.628 1.835 + apply_single 117 13.8 0.000 0.000 1.628 1.834 + make_images 4384 14.6 0.125 0.138 1.597 1.765 + ot_diis_step 104 11.8 0.005 0.005 1.727 1.727 + build_core_hamiltonian_matrix_ 11 4.9 0.000 0.001 1.603 1.724 + dbcsr_complete_redistribute 1402 12.8 0.393 0.436 1.578 1.636 + mp_isendrecv_dv 43757 15.0 0.815 1.624 0.815 1.624 + qs_ot_get_derivative_taylor 87 12.9 0.002 0.002 1.482 1.501 + mp_sum_d 4613 11.9 1.022 1.486 1.022 1.486 + qs_ot_get_p 117 10.6 0.001 0.001 1.171 1.426 + ------------------------------------------------------------------------------- diff --git a/benchmarks/QS_reference/w64SCAN.inp b/benchmarks/QS_reference/w64SCAN.inp new file mode 100644 index 0000000000..3292068699 --- /dev/null +++ b/benchmarks/QS_reference/w64SCAN.inp @@ -0,0 +1,73 @@ +&FORCE_EVAL + METHOD QS + &DFT + BASIS_SET_FILE_NAME BASIS_MOLOPT_UZH + POTENTIAL_FILE_NAME POTENTIAL_UZH + &MGRID + CUTOFF 800 + REL_CUTOFF 60 + &END MGRID + &QS + METHOD GPW + EPS_DEFAULT 1.0E-12 + &END QS + &SCF + SCF_GUESS ATOMIC + EPS_SCF 1.E-7 + MAX_SCF 10 + &OUTER_SCF + EPS_SCF 1.E-7 + MAX_SCF 10 + &END + &OT ON + MINIMIZER DIIS + PRECONDITIONER FULL_SINGLE_INVERSE + &END OT + &PRINT + &RESTART OFF + &END + &END + &END SCF + &XC + &XC_FUNCTIONAL + &MGGA_X_R2SCAN + &END + &MGGA_C_R2SCAN + &END + &END XC_FUNCTIONAL + &END XC + &END DFT + &SUBSYS + &CELL + ABC 12.4138 12.4138 12.4138 + &END CELL + &TOPOLOGY + COORD_FILE_NAME geom.xyz + COORD_FILE_FORMAT xyz + &END TOPOLOGY + &KIND H + BASIS_SET ORB TZVP-MOLOPT-MGGA-GTH-q1 + POTENTIAL GTH-MGGA-q1 + &END KIND + &KIND O + BASIS_SET ORB TZVP-MOLOPT-MGGA-GTH-q6 + POTENTIAL GTH-MGGA-q6 + &END KIND + &END SUBSYS +&END FORCE_EVAL +&GLOBAL + PROJECT H2O-64 + RUN_TYPE MD + PRINT_LEVEL LOW + &TIMINGS + THRESHOLD 0.001 + &END +&END GLOBAL +&MOTION + &MD + ENSEMBLE NVE + STEPS 10 + TIMESTEP 0.5 + TEMPERATURE 300.0 + &END MD +&END MOTION diff --git a/benchmarks/QS_reference/w64SCAN.ref b/benchmarks/QS_reference/w64SCAN.ref new file mode 100644 index 0000000000..5aff860330 --- /dev/null +++ b/benchmarks/QS_reference/w64SCAN.ref @@ -0,0 +1,164 @@ + CP2K| version string: CP2K version 2023.2 (Development Version) + CP2K| source code revision number: git:15ad1db + CP2K| cp2kflags: omp libint fftw3 libxc elpa parallel mpi_f08 scalapack cosma x + CP2K| smm spglib sirius libvori libbqb libvdwxc + GLOBAL| Total number of message passing processes 48 + GLOBAL| Number of threads for this process 1 + GLOBAL| CPU model name AMD EPYC 7401 24-Core Processor + + MD| *************************************************************************** + MD| Step number 10 + MD| Time [fs] 5.000000 + MD| Conserved quantity [hartree] -0.110101136939E+04 + MD| --------------------------------------------------------------------------- + MD| Instantaneous Averages + MD| CPU time per MD step [s] 19.175876 24.825771 + MD| Energy drift per atom [K] -0.129279868774E+01 -0.441960124962E+00 + MD| Potential energy [hartree] -0.110128217795E+04 -0.110126151501E+04 + MD| Kinetic energy [hartree] 0.270808556930E+00 0.250657908968E+00 + MD| Temperature [K] 298.479849 276.270202 + MD| *************************************************************************** + MD| Estimated peak process memory after this step [MiB] 295 + + ------------------------------------------------------------------------------- + - - + - T I M I N G - + - - + ------------------------------------------------------------------------------- + SUBROUTINE CALLS ASD SELF TIME TOTAL TIME + MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM + CP2K 1 1.0 0.009 0.035 248.509 248.533 + qs_mol_dyn_low 1 2.0 0.004 0.006 248.264 248.288 + qs_forces 11 3.9 0.002 0.002 248.208 248.232 + qs_energies 11 4.9 0.001 0.001 226.614 226.635 + scf_env_do_scf 11 5.9 0.000 0.002 216.095 216.116 + scf_env_do_scf_inner_loop 106 6.8 0.003 0.008 197.841 197.861 + velocity_verlet 10 3.0 0.001 0.002 197.710 197.730 + rebuild_ks_matrix 117 8.5 0.000 0.001 149.937 150.138 + qs_ks_build_kohn_sham_matrix 117 9.5 0.022 0.026 149.937 150.138 + qs_ks_update_qs_env 119 7.8 0.001 0.002 129.715 129.897 + sum_up_and_integrate 117 10.5 0.246 0.300 88.342 88.373 + integrate_v_rspace 234 11.5 0.009 0.011 88.096 88.161 + qs_rho_update_rho_low 117 7.9 0.001 0.002 82.960 82.991 + calculate_rho_elec 234 8.9 0.219 0.245 82.959 82.989 + grid_integrate_task_list 234 12.5 64.781 67.099 64.781 67.099 + grid_collocate_task_list 234 9.9 57.123 58.477 57.123 58.477 + pw_transfer 3287 12.5 0.389 0.462 54.419 57.003 + fft_wrap_pw1pw2 3053 13.6 0.052 0.057 53.609 56.225 + qs_vxc_create 117 10.5 0.003 0.004 54.738 54.939 + xc_vxc_pw_create 117 11.5 0.339 0.440 54.735 54.936 + fft_wrap_pw1pw2_400 1649 14.9 9.733 10.332 50.474 53.044 + fft3d_ps 3053 15.6 18.660 20.539 35.075 38.116 + xc_rho_set_and_dset_create 117 12.5 0.362 0.465 35.210 38.051 + xc_pw_derive 702 13.5 0.013 0.014 26.314 29.454 + density_rs2pw 234 9.9 0.016 0.018 24.802 26.421 + xc_functional_eval 234 13.5 0.003 0.004 22.784 25.560 + libxc_lda_eval 234 14.5 22.775 25.551 22.781 25.557 + xc_pw_divergence 117 12.5 0.008 0.010 18.617 21.497 + potential_pw2rs 234 12.5 0.026 0.028 20.300 20.367 + qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 20.266 20.284 + init_scf_loop 13 6.8 0.000 0.000 18.236 18.238 + mp_alltoall_z22v 3053 17.6 11.155 16.315 11.155 16.315 + yz_to_x 1298 16.3 2.809 3.372 10.005 13.881 + dbcsr_multiply_generic 2100 12.6 0.084 0.091 11.081 11.452 + transfer_pw2rs 947 13.5 0.022 0.029 11.393 11.422 + transfer_rs2pw 947 10.9 0.024 0.032 9.410 10.712 + qs_scf_new_mos 106 7.8 0.001 0.001 8.850 9.058 + qs_scf_loop_do_ot 106 8.8 0.001 0.001 8.850 9.057 + init_scf_run 11 5.9 0.000 0.001 8.990 8.990 + scf_env_initial_rho_setup 11 6.9 0.000 0.001 8.989 8.990 + multiply_cannon 2100 13.6 0.168 0.205 7.847 8.792 + mp_waitany 21076 14.1 6.976 8.702 6.976 8.702 + ot_scf_mini 106 9.8 0.002 0.003 8.287 8.457 + wfi_extrapolate 11 7.9 0.001 0.001 8.176 8.177 + multiply_cannon_loop 2100 14.6 0.121 0.136 7.193 8.151 + mp_waitall_1 193828 16.5 6.071 7.865 6.071 7.865 + x_to_yz 1287 17.0 2.172 2.591 6.081 6.714 + transfer_rs2pw_400 245 11.8 2.018 2.410 5.240 6.640 + transfer_pw2rs_400 245 14.3 3.113 3.223 6.056 6.232 + mp_alltoall_d11v 2347 13.5 3.255 6.047 3.255 6.047 + rs_gather_matrices 234 12.5 0.077 0.086 2.976 5.759 + multiply_cannon_metrocomm3 25200 15.6 0.058 0.065 3.915 5.550 + ot_mini 106 10.8 0.001 0.001 5.040 5.230 + pw_gather_p 1532 15.1 4.683 4.962 4.683 4.962 + pw_scatter_p 1521 16.1 3.732 3.975 3.732 3.975 + qs_ot_get_derivative 106 11.8 0.001 0.001 3.259 3.426 + multiply_cannon_multrec 25200 15.6 2.161 3.301 2.171 3.311 + transfer_pw2rs_140 234 14.5 1.279 1.371 3.086 3.229 + fft_wrap_pw1pw2_140 468 14.2 0.277 0.323 2.239 2.576 + mp_sum_d 3889 11.5 1.392 2.304 1.392 2.304 + transfer_rs2pw_140 234 11.9 1.035 1.116 2.178 2.274 + pw_derive 702 14.5 2.133 2.199 2.133 2.199 + multiply_cannon_metrocomm4 23100 15.6 0.057 0.061 0.817 2.183 + mp_irecv_dv 65990 16.0 0.777 2.131 0.777 2.131 + make_m2s 4200 13.6 0.056 0.059 1.991 2.091 + prepare_preconditioner 13 7.8 0.000 0.000 2.021 2.047 + make_preconditioner 13 8.8 0.000 0.000 2.021 2.047 + transfer_pw2rs_50 234 14.5 0.411 0.472 1.728 1.881 + apply_preconditioner_dbcsr 119 12.8 0.000 0.000 1.633 1.840 + apply_single 119 13.8 0.000 0.000 1.633 1.840 + pw_copy 1872 13.4 1.735 1.837 1.735 1.837 + qs_ot_get_derivative_taylor 89 12.9 0.002 0.002 1.634 1.775 + make_images 4200 14.6 0.120 0.134 1.599 1.755 + ot_diis_step 106 11.8 0.005 0.005 1.745 1.745 + mp_sendrecv_dv 21996 12.9 1.599 1.655 1.599 1.655 + mp_sum_l 10276 13.2 0.815 1.497 0.815 1.497 + transfer_rs2pw_50 234 11.9 0.275 0.321 1.446 1.474 + pw_axpy 1521 11.7 1.400 1.461 1.400 1.461 + rs_grid_zero 490 15.3 1.388 1.420 1.388 1.420 + qs_ot_get_p 119 10.6 0.001 0.001 1.161 1.412 + qs_energies_init_hamiltonians 11 5.9 0.000 0.000 1.330 1.330 + build_core_hamiltonian_matrix_ 11 4.9 0.001 0.001 1.185 1.285 + pw_poisson_solve 117 10.5 0.230 0.251 1.164 1.165 + make_full_single_inverse 13 9.8 0.001 0.001 1.084 1.110 + make_full_inverse_cholesky 13 9.8 0.000 0.000 0.893 0.904 + qs_env_update_s_mstruct 11 6.9 0.000 0.000 0.776 0.812 + cp_dbcsr_sm_fm_multiply 45 9.4 0.001 0.001 0.788 0.792 + fft_wrap_pw1pw2_50 468 14.2 0.045 0.055 0.588 0.763 + make_images_sizes 4200 15.6 0.004 0.004 0.473 0.743 + make_images_data 4200 15.6 0.041 0.050 0.630 0.741 + mp_alltoall_i44 4200 16.6 0.469 0.739 0.469 0.739 + qs_ot_get_orbitals 106 10.8 0.000 0.000 0.685 0.708 + mp_irecv_dm3 5748 14.1 0.336 0.688 0.336 0.688 + calculate_rho_core 11 7.9 0.051 0.058 0.647 0.681 + cp_dbcsr_sm_fm_multiply_core 45 10.4 0.000 0.000 0.603 0.680 + calculate_dm_sparse 117 9.7 0.000 0.001 0.627 0.673 + build_core_ppl_forces 11 5.9 0.547 0.631 0.547 0.631 + hybrid_alltoall_any 4338 16.5 0.043 0.088 0.513 0.618 + dbcsr_dot_sd 1134 12.2 0.036 0.044 0.330 0.598 + build_core_hamiltonian_matrix 11 6.9 0.001 0.001 0.512 0.573 + pw_zero 702 12.6 0.517 0.564 0.517 0.564 + transfer_rs2pw_20 234 11.9 0.093 0.100 0.522 0.541 + mp_isendrecv_dv 21996 15.5 0.318 0.523 0.318 0.523 + transfer_pw2rs_20 234 14.5 0.090 0.108 0.501 0.515 + pw_integral_ab 117 11.5 0.395 0.415 0.474 0.508 + mp_allgather_i34 2100 14.6 0.282 0.501 0.282 0.501 + dbcsr_sym_m_v_mult 1206 12.5 0.016 0.021 0.458 0.463 + arnoldi_generalized_ev 13 10.8 0.000 0.000 0.452 0.456 + qs_ot_get_derivative_diag 17 12.0 0.000 0.000 0.424 0.454 + cp_fm_cholesky_invert 13 10.8 0.422 0.427 0.422 0.427 + parallel_gemm_fm 95 8.9 0.000 0.000 0.411 0.417 + parallel_gemm_fm_cosma 95 9.9 0.411 0.417 0.411 0.417 + gev_build_subspace 22 11.5 0.003 0.008 0.413 0.414 + copy_dbcsr_to_fm 138 10.8 0.002 0.003 0.303 0.393 + dbcsr_make_images_dense 3508 14.9 0.033 0.034 0.288 0.388 + cp_fm_cholesky_decompose 26 10.6 0.379 0.382 0.379 0.382 + dbcsr_make_dense_low 8616 15.8 0.037 0.040 0.259 0.377 + qs_ot_p2m_diag 19 11.0 0.003 0.004 0.367 0.370 + build_kinetic_matrix_low 22 6.9 0.329 0.363 0.332 0.366 + mp_alltoall_i22 619 13.6 0.195 0.363 0.195 0.363 + build_overlap_matrix_low 22 6.9 0.317 0.352 0.320 0.356 + make_basis_sm 13 9.4 0.000 0.001 0.352 0.355 + dbcsr_complete_redistribute 312 11.8 0.064 0.076 0.315 0.344 + rs_scatter_matrices 256 9.9 0.084 0.113 0.309 0.334 + make_dense_data 8616 16.8 0.180 0.287 0.204 0.321 + make_images_pack 4200 15.6 0.201 0.310 0.210 0.320 + integrate_v_core_rspace 11 7.9 0.040 0.047 0.306 0.318 + cp_dbcsr_syevd 19 12.0 0.002 0.002 0.304 0.304 + pw_scale 468 12.0 0.244 0.297 0.244 0.297 + fft_wrap_pw1pw2_20 468 14.2 0.012 0.014 0.256 0.285 + build_core_ppl 11 7.9 0.244 0.280 0.244 0.280 + cp_fm_diag_elpa 19 13.0 0.000 0.000 0.276 0.277 + reorthogonalize_vectors 10 9.0 0.000 0.000 0.269 0.272 + cp_fm_redistribute_end 19 14.0 0.135 0.261 0.137 0.263 + -------------------------------------------------------------------------------