cp2k/benchmarks/QS_reference/w64SCAN.ref

164 lines
13 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] -0.110101136939E+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
-------------------------------------------------------------------------------