cp2k/benchmarks/QS_reference/w64GAPW.ref

157 lines
12 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] -0.488796321361E+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
-------------------------------------------------------------------------------