mirror of
https://github.com/cp2k/cp2k.git
synced 2026-07-28 06:05:29 -04:00
181 lines
14 KiB
Text
181 lines
14 KiB
Text
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
|
|
-------------------------------------------------------------------------------
|