Reference benchmark (#5063)

This commit is contained in:
Juerg Hutter 2026-04-14 13:09:36 +02:00 committed by GitHub
parent 30cea4fbde
commit af0c710417
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 265 additions and 0 deletions

View file

@ -13,5 +13,6 @@ PBE/GAPW/AE 30.2 845
SCAN 14.2 249
PBE0/ADMM 16.8 1306
DC-SCAN 20.2 3525
ccGRB-Q/SCAN 33.2 479

View file

@ -0,0 +1,75 @@
&GLOBAL
PRINT_LEVEL LOW
PROJECT H2O-64
RUN_TYPE MD
&TIMINGS
THRESHOLD 0.001
&END TIMINGS
&END GLOBAL
&MOTION
&MD
ENSEMBLE NVE
STEPS 10
TEMPERATURE 300.0
TIMESTEP 0.5
&END MD
&END MOTION
&FORCE_EVAL
METHOD QS
&DFT
BASIS_SET_FILE_NAME BASIS_ccGRB_UZH
POTENTIAL_FILE_NAME POTENTIAL_UZH
&MGRID
CUTOFF 800
REL_CUTOFF 60
&END MGRID
&QS
EPS_DEFAULT 1.0E-12
METHOD GPW
&END QS
&SCF
EPS_SCF 1.E-7
MAX_SCF 10
SCF_GUESS ATOMIC
&OT ON
MINIMIZER DIIS
PRECONDITIONER FULL_SINGLE_INVERSE
&END OT
&OUTER_SCF
EPS_SCF 1.E-7
MAX_SCF 10
&END OUTER_SCF
&PRINT
&RESTART OFF
&END RESTART
&END PRINT
&END SCF
&XC
&XC_FUNCTIONAL
&MGGA_C_R2SCAN
&END MGGA_C_R2SCAN
&MGGA_X_R2SCAN
&END MGGA_X_R2SCAN
&END XC_FUNCTIONAL
&END XC
&END DFT
&SUBSYS
&CELL
ABC 12.4138 12.4138 12.4138
&END CELL
&KIND H
BASIS_SET ORB ccGRB-Q-q1
POTENTIAL GTH-MGGA-q1
&END KIND
&KIND O
BASIS_SET ORB ccGRB-Q-q6
POTENTIAL GTH-MGGA-q6
&END KIND
&TOPOLOGY
COORD_FILE_FORMAT xyz
COORD_FILE_NAME geom.xyz
&END TOPOLOGY
&END SUBSYS
&END FORCE_EVAL

View file

@ -0,0 +1,189 @@
CP2K| version string: CP2K version 2026.1 (Development Version)
CP2K| source code revision number: 39a6033793
CP2K| cp2kflags: omp libint fftw3 libxc elpa parallel scalapack mpi_f08 cosma a
CP2K| ce deepmd xsmm plumed2 spglib libdftd4 mctc-lib tblite sirius
CP2K| libvori libbqb libtorch mimic libvdwxc hdf5 trexio libsmeagol
CP2K| l greenx
GLOBAL| Total number of message passing processes 48
GLOBAL| Number of threads for this process 2
GLOBAL| CPU model name AMD EPYC 7401 24-Core Processor
MD| ***************************************************************************
MD| Step number 10
MD| Time [fs] 5.000000
MD| Conserved quantity [hartree] -0.110131201702E+04
MD| ---------------------------------------------------------------------------
MD| Instantaneous Averages
MD| CPU time per MD step [s] 35.218158 47.869443
MD| Energy drift per atom [K] -0.131390165988E+01 -0.698963310316E+00
MD| Potential energy [hartree] -0.110158135777E+04 -0.110156769201E+04
MD| Kinetic energy [hartree] 0.269340752994E+00 0.256042491407E+00
MD| Temperature [K] 296.862064 282.204983
MD| ***************************************************************************
MD| Estimated peak process memory after this step [MiB] 692
-------------------------------------------------------------------------------
- -
- T I M I N G -
- -
-------------------------------------------------------------------------------
SUBROUTINE CALLS ASD SELF TIME TOTAL TIME
MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM
CP2K 1 1.0 0.019 0.023 479.099 479.111
qs_mol_dyn_low 1 2.0 0.020 0.020 478.890 478.902
qs_forces 11 3.9 0.002 0.002 478.816 478.828
qs_energies 11 4.9 0.002 0.003 442.333 442.396
scf_env_do_scf 11 5.9 0.001 0.002 413.851 413.872
velocity_verlet 10 3.0 0.002 0.002 372.446 372.457
scf_env_do_scf_inner_loop 99 6.8 0.005 0.014 359.191 359.203
rebuild_ks_matrix 110 8.5 0.001 0.001 227.840 228.878
qs_ks_build_kohn_sham_matrix 110 9.5 0.030 0.039 227.839 228.877
qs_ks_update_qs_env 112 7.8 0.002 0.002 197.044 197.946
sum_up_and_integrate 110 10.5 0.008 0.011 169.438 169.692
integrate_v_rspace 220 11.5 0.015 0.018 169.282 169.526
qs_rho_update_rho_low 110 7.9 0.002 0.002 156.297 156.689
calculate_rho_elec 220 8.9 0.210 0.232 156.295 156.687
grid_integrate_task_list 220 12.5 140.219 147.201 140.219 147.201
grid_collocate_task_list 220 9.9 123.134 131.477 123.134 131.477
dbcsr_multiply_generic 1975 12.5 0.135 0.160 71.642 73.450
multiply_cannon 1975 13.5 0.258 0.349 55.160 58.975
multiply_cannon_loop 1975 14.5 0.279 0.348 52.039 57.039
init_scf_loop 13 6.8 0.001 0.001 54.630 54.638
multiply_cannon_multrec 23700 15.5 30.767 51.243 30.787 51.262
mp_waitall_1 182288 16.5 20.746 51.062 20.746 51.062
qs_scf_new_mos 99 7.8 0.001 0.003 47.097 48.519
qs_scf_loop_do_ot 99 8.8 0.001 0.002 47.096 48.517
multiply_cannon_metrocomm3 23700 15.5 0.074 0.081 15.797 46.330
ot_scf_mini 99 9.8 0.003 0.003 42.776 44.032
fft_wrap_pw1pw2 2871 12.6 0.122 0.152 41.986 43.782
fft_wrap_pw1pw2_400 1551 13.9 1.712 1.887 36.891 38.622
qs_vxc_create 110 10.5 0.004 0.005 37.743 37.950
xc_vxc_pw_create 110 11.5 0.199 0.252 37.740 37.947
density_rs2pw 220 9.9 0.017 0.019 28.646 35.958
fft3d_ps 2871 14.6 14.807 15.986 31.881 33.324
qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 31.335 31.467
ot_mini 99 10.8 0.001 0.001 25.690 27.038
prepare_preconditioner 13 7.8 0.000 0.000 26.319 26.529
make_preconditioner 13 8.8 0.000 0.001 26.319 26.529
xc_rho_set_and_dset_create 110 12.5 0.263 0.323 24.080 25.772
init_scf_run 11 5.9 0.000 0.000 23.815 23.825
scf_env_initial_rho_setup 11 6.9 0.000 0.001 23.815 23.824
transfer_rs2pw 891 10.8 0.024 0.033 16.101 23.518
mp_waitany 19844 14.1 15.159 23.172 15.159 23.172
wfi_extrapolate 11 7.9 0.002 0.002 21.786 21.787
xc_pw_derive 660 13.5 0.018 0.021 19.453 21.364
potential_pw2rs 220 12.5 0.028 0.031 19.402 19.753
transfer_rs2pw_400 231 11.8 1.350 1.798 11.391 18.677
make_full_inverse_cholesky 13 9.8 0.000 0.001 17.807 17.993
mp_alltoall_d11v 2283 13.5 11.289 16.957 11.289 16.957
apply_preconditioner_dbcsr 112 12.8 0.000 0.000 15.272 16.451
apply_single 112 13.8 0.001 0.001 15.272 16.451
xc_functional_eval 220 13.5 0.004 0.005 14.164 15.815
libxc_lda_eval 220 14.5 14.148 15.801 14.160 15.812
ot_diis_step 99 11.8 0.005 0.006 15.161 15.161
rs_gather_matrices 220 12.5 1.066 1.291 9.280 15.066
mp_alltoall_z22v 2871 16.6 12.407 14.961 12.407 14.961
xc_pw_divergence 110 12.5 0.009 0.011 13.089 14.726
multiply_cannon_metrocomm4 21725 15.5 0.092 0.117 4.602 12.389
mp_irecv_dv 62105 16.0 4.643 12.385 4.643 12.385
transfer_pw2rs 891 13.4 0.028 0.038 11.855 11.896
qs_ot_get_derivative 99 11.8 0.001 0.002 10.443 11.717
cp_fm_cholesky_invert 13 10.8 11.168 11.211 11.168 11.211
yz_to_x 1221 15.3 1.975 2.374 8.688 10.837
make_m2s 3950 13.5 0.072 0.081 9.953 10.273
mp_sum_l 9279 13.6 5.067 9.274 5.067 9.274
make_images 3950 14.5 0.734 1.143 8.571 8.930
make_full_single_inverse 13 9.8 0.002 0.003 7.885 8.086
x_to_yz 1210 16.0 1.789 2.030 7.361 7.672
transfer_pw2rs_400 231 14.3 3.143 3.414 6.507 6.754
cp_dbcsr_sm_fm_multiply 45 9.4 0.002 0.002 6.539 6.554
qs_ot_get_derivative_taylor 81 12.9 0.003 0.004 5.114 6.150
cp_dbcsr_sm_fm_multiply_core 45 10.4 0.000 0.000 5.638 6.015
mp_sum_d 3837 11.5 3.298 5.774 3.298 5.774
qs_ot_get_p 112 10.5 0.001 0.002 3.745 5.453
cp_fm_cholesky_decompose 26 10.6 5.275 5.362 5.275 5.362
calculate_dm_sparse 110 9.7 0.001 0.002 4.805 5.290
build_core_hamiltonian_matrix_ 11 4.9 0.001 0.002 4.564 4.829
rs_scatter_matrices 242 9.9 1.481 1.780 4.123 4.647
dbcsr_dot 1040 12.2 0.447 0.495 2.215 4.289
make_images_data 3950 15.5 0.057 0.070 3.529 4.119
pw_gather_p 1441 14.1 3.490 3.731 3.490 3.731
hybrid_alltoall_any 4089 16.4 0.289 1.555 3.073 3.593
transfer_pw2rs_140 220 14.5 1.238 1.324 3.288 3.395
pw_scatter_p 1430 15.1 2.982 3.382 2.982 3.382
qs_energies_init_hamiltonians 11 5.9 0.000 0.001 3.361 3.361
transfer_rs2pw_140 220 11.9 1.136 1.370 3.147 3.298
make_images_sizes 3950 15.5 0.005 0.006 2.536 3.183
mp_alltoall_i44 3950 16.5 2.531 3.179 2.531 3.179
pw_derive 990 13.8 2.904 3.176 2.904 3.176
arnoldi_generalized_ev 13 10.8 0.001 0.001 3.044 3.087
mp_alltoall_i22 607 13.6 1.709 2.928 1.709 2.928
dbcsr_sym_matrix_vector_mult 1266 12.5 0.029 0.041 2.855 2.888
fft_wrap_pw1pw2_140 440 13.2 0.084 0.111 2.543 2.785
build_core_ppl_forces 11 5.9 2.474 2.781 2.474 2.781
pw_poisson_solve 110 10.5 0.005 0.008 2.707 2.765
gev_build_subspace 23 11.4 0.012 0.026 2.613 2.623
copy_dbcsr_to_fm 139 10.8 0.004 0.005 1.657 2.436
dbcsr_complete_redistribute 314 11.8 0.461 0.527 1.884 2.349
pw_copy 2090 13.1 2.122 2.316 2.122 2.316
make_basis_sm 13 9.4 0.001 0.001 2.302 2.310
make_images_pack 3950 15.5 1.533 2.280 1.555 2.299
build_core_hamiltonian_matrix 11 6.9 0.002 0.002 2.091 2.225
ot_scf_init 13 7.8 0.002 0.002 2.116 2.131
buffer_matrices_ensure_size 3950 14.5 1.359 1.995 1.359 1.995
dbcsr_sym_matrix_vector_mult_l 1266 13.5 1.598 1.837 1.605 1.843
reorthogonalize_vectors 10 9.0 0.000 0.000 1.809 1.816
pw_poisson_set 111 11.4 0.009 0.012 1.702 1.760
parallel_gemm_fm_cosma 95 8.9 1.694 1.752 1.694 1.752
transfer_pw2rs_50 220 14.5 0.385 0.442 1.576 1.751
copy_fm_to_dbcsr 175 10.8 0.001 0.002 1.303 1.723
mp_allgather_i34 1975 14.5 1.319 1.670 1.319 1.670
dbcsr_desymmetrize_deep 139 11.8 0.083 0.112 0.881 1.625
fft_wrap_pw1pw2_50 440 13.2 0.016 0.018 1.451 1.553
dbcsr_make_dense_low 8068 15.8 0.045 0.048 1.262 1.524
rs_grid_zero 462 15.2 1.445 1.515 1.445 1.515
qs_ot_get_orbitals 99 10.8 0.001 0.001 1.444 1.500
make_dense_data 8068 16.8 1.139 1.368 1.193 1.453
dbcsr_make_images_dense 3286 14.9 0.037 0.040 1.244 1.449
build_core_ppl 11 7.9 1.313 1.443 1.313 1.443
pw_axpy 1540 11.6 1.365 1.430 1.365 1.430
qs_ot_get_derivative_diag 18 12.0 0.001 0.001 1.091 1.394
mp_sendrecv_dv 20680 12.9 1.209 1.343 1.209 1.343
qs_env_update_s_mstruct 11 6.9 0.000 0.000 1.186 1.319
cp_dbcsr_plus_fm_fm_t 22 8.9 0.001 0.001 1.211 1.306
transfer_rs2pw_50 220 11.9 0.243 0.261 1.170 1.283
compute_matrix_w 11 5.9 0.000 0.000 1.178 1.246
calculate_w_matrix_ot 11 6.9 0.001 0.002 1.178 1.246
build_core_ppnl_forces 11 5.9 1.143 1.240 1.143 1.240
pw_copy_to_array 1441 14.1 1.048 1.231 1.048 1.231
mp_sum_dv 7212 14.3 0.931 1.130 0.931 1.130
fft_wrap_pw1pw2_20 440 13.2 0.005 0.006 0.979 1.049
mp_irecv_dm3 5412 14.1 0.461 0.959 0.461 0.959
transfer_fm_to_dbcsr 13 9.8 0.000 0.000 0.627 0.915
transfer_dbcsr_to_fm 13 10.8 0.001 0.002 0.806 0.868
pw_copy_from_array 1430 15.1 0.647 0.835 0.647 0.835
mp_alltoall_z11v 440 16.2 0.771 0.816 0.771 0.816
calculate_rho_core 11 7.9 0.051 0.058 0.671 0.812
dbcsr_rep_row_to_rep_col_vec 1266 13.5 0.036 0.070 0.635 0.810
cp_fm_uplo_to_full 46 13.0 0.578 0.800 0.578 0.800
multiply_cannon_metrocomm1 23700 15.5 0.037 0.046 0.342 0.750
build_kinetic_matrix_low 22 6.9 0.668 0.711 0.689 0.734
calculate_ecore_overlap 22 5.9 0.000 0.001 0.437 0.728
build_overlap_matrix_low 22 6.9 0.645 0.687 0.675 0.716
external_control 109 7.3 0.001 0.002 0.180 0.702
mp_bcast_b_src 129 8.9 0.179 0.702 0.179 0.702
dbcsr_finalize 4461 13.7 0.031 0.059 0.531 0.685
dbcsr_copy 4672 12.8 0.486 0.546 0.562 0.672
dbcsr_merge_all 3948 15.0 0.077 0.143 0.477 0.618
dbcsr_col_vec_to_rep_row 1800 14.0 0.023 0.032 0.411 0.602
mp_isendrecv_dv 20680 15.5 0.199 0.596 0.199 0.596
calculate_first_density_matrix 1 7.0 0.000 0.000 0.585 0.592
qs_ot_p2m_diag 20 11.0 0.002 0.004 0.550 0.553
evaluate_core_matrix_traces 110 8.5 0.001 0.001 0.537 0.539
calculate_ptrace_kp 220 9.5 0.001 0.001 0.536 0.538
qs_create_task_list 11 7.9 0.000 0.000 0.493 0.517
generate_qs_task_list 11 8.9 0.221 0.255 0.493 0.517
transfer_pw2rs_20 220 14.5 0.083 0.097 0.456 0.510
dbcsr_add_wm_from_matrix 418 13.0 0.036 0.108 0.388 0.485
-------------------------------------------------------------------------------