StartDate: 2022-01-29 11:02:53+00:00 CpuId: 64x Intel Xeon W 2000 / D-2100 (Skylake / Cascade Lake) {Skylake}, 14nm CommitSHA: 21c490e547270aa3f6e2322f7e6d04b537173553 CommitTime: 2022-01-28 23:48:28 +0100 CommitAuthor: Dr. Mathieu Taillefumier CommitSubject: Fix for fft performance regression Trying to pull image cp2k-toolchain-mpich... success :-) Trying to pull image cp2k-perf-openmp... success :-) #################### Running Image cp2k-perf-openmp #################### ========== Fetching Git Commit ========== CommitSHA: 21c490e547270aa3f6e2322f7e6d04b537173553 CommitTime: 2022-01-28 23:48:28 +0100 CommitAuthor: Dr. Mathieu Taillefumier CommitSubject: Fix for fft performance regression ========== Running Test ========== ========== Compiling CP2K ========== Compiling cp2k... done. ========== Running Performance Test ========== Running H2O-64.inp with 1 threads and 32 ranks... done. Running H2O-64.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/H2O-64_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.030 0.030 153.405 153.405 qs_mol_dyn_low 1 2.0 0.004 0.004 152.618 152.618 qs_forces 11 3.9 0.001 0.001 152.561 152.561 qs_energies 11 4.9 0.001 0.001 142.598 142.598 scf_env_do_scf 11 5.9 0.001 0.001 115.531 115.531 velocity_verlet 10 3.0 0.002 0.002 105.852 105.852 scf_env_do_scf_inner_loop 108 6.5 0.010 0.010 77.979 77.979 init_scf_loop 11 6.9 0.000 0.000 37.370 37.370 prepare_preconditioner 11 7.9 0.000 0.000 33.559 33.559 make_preconditioner 11 8.9 0.000 0.000 33.559 33.559 make_full_inverse_cholesky 11 9.9 0.000 0.000 31.579 31.579 rebuild_ks_matrix 119 8.3 0.001 0.001 31.335 31.335 qs_ks_build_kohn_sham_matrix 119 9.3 0.018 0.018 31.335 31.335 qs_ks_update_qs_env 119 7.6 0.001 0.001 29.263 29.263 qs_rho_update_rho 119 7.7 0.001 0.001 27.406 27.406 calculate_rho_elec 119 8.7 1.545 1.545 27.405 27.405 qs_scf_new_mos 108 7.5 0.001 0.001 27.100 27.100 qs_scf_loop_do_ot 108 8.5 0.001 0.001 27.099 27.099 ot_scf_mini 108 9.5 0.003 0.003 25.326 25.326 dbcsr_multiply_generic 2286 12.5 0.188 0.188 22.669 22.669 grid_collocate_task_list 119 9.7 21.612 21.612 21.612 21.612 sum_up_and_integrate 119 10.3 0.375 0.375 19.860 19.860 integrate_v_rspace 119 11.3 0.470 0.470 19.485 19.485 cp_fm_cholesky_invert 11 10.9 19.275 19.275 19.275 19.275 grid_integrate_task_list 119 12.3 16.684 16.684 16.684 16.684 ot_mini 108 10.5 0.001 0.001 15.101 15.101 init_scf_run 11 5.9 0.001 0.001 13.067 13.067 scf_env_initial_rho_setup 11 6.9 0.001 0.001 13.066 13.066 make_m2s 4572 13.5 0.065 0.065 12.664 12.664 wfi_extrapolate 11 7.9 0.001 0.001 12.267 12.267 cp_gemm 81 9.0 0.000 0.000 10.709 10.709 cp_gemm_cosma 81 10.0 10.709 10.709 10.709 10.709 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 10.302 10.302 qs_ot_get_derivative 108 11.5 0.001 0.001 7.958 7.958 pw_transfer 1439 11.6 0.090 0.090 7.215 7.215 ot_diis_step 108 11.5 0.005 0.005 7.140 7.140 fft_wrap_pw1pw2 1201 12.6 0.010 0.010 6.938 6.938 make_images 4572 14.5 2.523 2.523 6.752 6.752 qs_ot_get_p 119 10.4 0.001 0.001 6.384 6.384 cp_fm_cholesky_decompose 22 10.9 6.302 6.302 6.302 6.302 dbcsr_complete_redistribute 329 12.2 2.957 2.957 6.157 6.157 build_core_hamiltonian_matrix_ 11 4.9 0.001 0.001 6.139 6.139 dbcsr_make_dense_low 5837 15.5 0.100 0.100 6.049 6.049 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 5.986 5.986 apply_single 119 13.6 0.000 0.000 5.986 5.986 make_dense_data 5837 16.5 5.270 5.270 5.926 5.926 fft_wrap_pw1pw2_140 487 13.2 0.549 0.549 5.845 5.845 qs_env_update_s_mstruct 11 6.9 0.000 0.000 5.744 5.744 multiply_cannon 2286 13.5 0.871 0.871 5.598 5.598 dbcsr_make_images_dense 3978 14.8 0.026 0.026 5.449 5.449 dbcsr_copy 2102 12.0 0.269 0.269 5.291 5.291 qs_create_task_list 11 7.9 0.000 0.000 5.232 5.232 generate_qs_task_list 11 8.9 3.624 3.624 5.232 5.232 copy_dbcsr_to_fm 153 11.3 0.003 0.003 4.982 4.982 dbcsr_copy_into_existing 22 7.9 4.974 4.974 4.974 4.974 qs_ot_p2m_diag 50 11.0 0.216 0.216 4.810 4.810 pw_poisson_solve 119 10.3 1.786 1.786 4.382 4.382 cp_dbcsr_syevd 50 12.0 0.004 0.004 4.264 4.264 density_rs2pw 119 9.7 0.006 0.006 4.248 4.248 multiply_cannon_loop 2286 14.5 0.054 0.054 4.191 4.191 multiply_cannon_multrec 2286 15.5 4.071 4.071 4.136 4.136 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 4.131 4.131 cp_fm_diag_elpa 50 13.0 0.000 0.000 4.109 4.109 cp_fm_diag_elpa_base 50 14.0 4.053 4.053 4.108 4.108 build_core_hamiltonian_matrix 11 6.9 0.001 0.001 3.994 3.994 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 3.822 3.822 qs_energies_compute_matrix_w 11 5.9 0.000 0.000 3.537 3.537 calculate_w_matrix_ot 11 6.9 0.008 0.008 3.537 3.537 copy_fm_to_dbcsr 176 11.2 0.002 0.002 3.319 3.319 fft3d_s 1202 14.6 3.192 3.192 3.198 3.198 ------------------------------------------------------------------------------- From /workspace/artifacts/H2O-64_32mpi.out: ------------------------------------------------------------------------------- - - - 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 70.297 70.298 qs_mol_dyn_low 1 2.0 0.006 0.007 70.156 70.164 qs_forces 11 3.9 0.002 0.002 70.100 70.100 qs_energies 11 4.9 0.001 0.001 65.215 65.218 scf_env_do_scf 11 5.9 0.001 0.001 59.117 59.118 scf_env_do_scf_inner_loop 108 6.5 0.003 0.011 54.859 54.859 velocity_verlet 10 3.0 0.002 0.002 41.863 41.865 rebuild_ks_matrix 119 8.3 0.001 0.001 27.247 27.297 qs_ks_build_kohn_sham_matrix 119 9.3 0.021 0.021 27.247 27.297 qs_ks_update_qs_env 119 7.6 0.001 0.001 24.138 24.183 qs_rho_update_rho 119 7.7 0.001 0.001 21.906 21.923 calculate_rho_elec 119 8.7 0.048 0.049 21.905 21.922 sum_up_and_integrate 119 10.3 0.043 0.045 21.563 21.584 integrate_v_rspace 119 11.3 0.004 0.005 21.520 21.543 grid_collocate_task_list 119 9.7 15.808 16.632 15.808 16.632 dbcsr_multiply_generic 2286 12.5 0.131 0.134 16.034 16.110 grid_integrate_task_list 119 12.3 15.655 15.960 15.655 15.960 qs_scf_new_mos 108 7.5 0.001 0.001 13.269 13.307 qs_scf_loop_do_ot 108 8.5 0.001 0.001 13.268 13.306 ot_scf_mini 108 9.5 0.003 0.003 12.428 12.465 multiply_cannon 2286 13.5 0.220 0.224 10.588 10.881 multiply_cannon_loop 2286 14.5 0.217 0.229 9.536 9.845 mp_waitall_1 169478 16.3 7.851 8.233 7.851 8.233 ot_mini 108 10.5 0.001 0.001 7.328 7.371 rs_pw_transfer 974 11.9 0.015 0.017 6.450 6.981 density_rs2pw 119 9.7 0.008 0.009 5.545 6.081 multiply_cannon_metrocomm3 18288 15.5 0.081 0.084 5.042 5.484 pw_transfer 1439 11.6 0.138 0.148 5.412 5.468 fft_wrap_pw1pw2 1201 12.6 0.013 0.015 5.134 5.196 potential_pw2rs 119 12.3 0.010 0.010 4.801 4.809 fft_wrap_pw1pw2_140 487 13.2 0.511 0.533 4.436 4.575 init_scf_loop 11 6.9 0.000 0.000 4.242 4.243 init_scf_run 11 5.9 0.000 0.002 4.175 4.176 scf_env_initial_rho_setup 11 6.9 0.000 0.001 4.175 4.175 fft3d_ps 1201 14.6 2.092 2.223 3.822 3.888 wfi_extrapolate 11 7.9 0.001 0.001 3.806 3.806 qs_ot_get_derivative 108 11.5 0.001 0.001 3.765 3.801 make_m2s 4572 13.5 0.075 0.077 3.659 3.715 ot_diis_step 108 11.5 0.005 0.005 3.526 3.527 multiply_cannon_multrec 18288 15.5 3.360 3.504 3.377 3.521 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 3.434 3.470 apply_single 119 13.6 0.001 0.001 3.434 3.470 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 3.310 3.316 make_images 4572 14.5 0.188 0.194 2.986 3.050 mp_waitany 9880 13.7 2.307 2.806 2.307 2.806 rs_pw_transfer_RS2PW_140 130 11.5 0.474 0.497 2.076 2.616 rs_pw_transfer_PW2RS_140 130 13.9 1.122 1.186 2.372 2.410 qs_ot_get_p 119 10.4 0.001 0.001 1.807 1.853 mp_alltoall_d11v 2130 13.8 1.316 1.736 1.316 1.736 build_core_hamiltonian_matrix_ 11 4.9 0.001 0.001 1.439 1.541 prepare_preconditioner 11 7.9 0.000 0.000 1.452 1.468 make_preconditioner 11 8.9 0.000 0.000 1.452 1.468 make_images_data 4572 15.5 0.061 0.067 1.339 1.451 qs_energies_init_hamiltonians 11 5.9 0.001 0.001 1.423 1.424 ------------------------------------------------------------------------------- Plot: name="H2O-64_timings_32omp", title="Timings of H2O-64 with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="H2O-64_timings_32omp", name="rest", label="rest", y=74.75200000000001, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=21.612, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=19.275, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=16.684, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_gemm_cosma", label="cp_gemm_cosma", y=10.709, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=6.302, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=4.071, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="mp_waitany", label="mp_waitany", y=0.0, yerr=0.0 Plot: name="H2O-64_timings_32mpi", title="Timings of H2O-64 with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="H2O-64_timings_32mpi", name="rest", label="rest", y=25.315999999999995, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=15.808, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=15.655, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="cp_gemm_cosma", label="cp_gemm_cosma", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=3.36, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=7.851, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitany", label="mp_waitany", y=2.307, yerr=0.0 Running H2O-64_nonortho.inp with 1 threads and 32 ranks... done. Running H2O-64_nonortho.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/H2O-64_nonortho_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.037 0.037 206.363 206.363 qs_mol_dyn_low 1 2.0 0.004 0.004 205.595 205.595 qs_forces 11 3.9 0.002 0.002 205.536 205.536 qs_energies 11 4.9 0.001 0.001 192.032 192.032 scf_env_do_scf 11 5.9 0.001 0.001 160.779 160.779 velocity_verlet 10 3.0 0.002 0.002 137.440 137.440 scf_env_do_scf_inner_loop 96 6.5 0.008 0.008 119.925 119.925 rebuild_ks_matrix 107 8.3 0.001 0.001 61.089 61.089 qs_ks_build_kohn_sham_matrix 107 9.3 0.016 0.016 61.088 61.088 qs_ks_update_qs_env 107 7.6 0.001 0.001 55.038 55.038 qs_rho_update_rho 107 7.7 0.001 0.001 53.595 53.595 calculate_rho_elec 107 8.7 1.379 1.379 53.595 53.595 sum_up_and_integrate 107 10.3 0.332 0.332 50.822 50.822 integrate_v_rspace 107 11.3 0.564 0.564 50.490 50.490 grid_collocate_task_list 107 9.7 48.440 48.440 48.440 48.440 grid_integrate_task_list 107 12.3 47.846 47.846 47.846 47.846 init_scf_loop 11 6.9 0.000 0.000 40.654 40.654 prepare_preconditioner 11 7.9 0.000 0.000 33.487 33.487 make_preconditioner 11 8.9 0.000 0.000 33.487 33.487 make_full_inverse_cholesky 11 9.9 0.000 0.000 31.551 31.551 qs_scf_new_mos 96 7.5 0.001 0.001 23.440 23.440 qs_scf_loop_do_ot 96 8.5 0.001 0.001 23.439 23.439 ot_scf_mini 96 9.5 0.003 0.003 21.729 21.729 dbcsr_multiply_generic 1966 12.4 0.163 0.163 19.887 19.887 cp_fm_cholesky_invert 11 10.9 19.094 19.094 19.094 19.094 init_scf_run 11 5.9 0.001 0.001 16.074 16.074 scf_env_initial_rho_setup 11 6.9 0.001 0.001 16.073 16.073 wfi_extrapolate 11 7.9 0.001 0.001 15.035 15.035 ot_mini 96 10.5 0.001 0.001 12.746 12.746 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 11.449 11.449 make_m2s 3932 13.4 0.055 0.055 10.818 10.818 cp_gemm 81 9.0 0.000 0.000 10.591 10.591 cp_gemm_cosma 81 10.0 10.591 10.591 10.591 10.591 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 7.628 7.628 qs_ot_get_derivative 96 11.5 0.001 0.001 6.883 6.883 qs_env_update_s_mstruct 11 6.9 0.000 0.000 6.880 6.880 pw_transfer 1295 11.6 0.078 0.078 6.427 6.427 qs_create_task_list 11 7.9 0.000 0.000 6.355 6.355 generate_qs_task_list 11 8.9 4.760 4.760 6.355 6.355 cp_fm_cholesky_decompose 22 10.9 6.304 6.304 6.304 6.304 dbcsr_complete_redistribute 317 12.2 2.947 2.947 6.218 6.218 fft_wrap_pw1pw2 1081 12.6 0.009 0.009 6.185 6.185 make_images 3932 14.4 2.204 2.204 5.877 5.877 build_core_hamiltonian_matrix_ 11 4.9 0.001 0.001 5.873 5.873 ot_diis_step 96 11.5 0.005 0.005 5.859 5.859 qs_ot_get_p 107 10.4 0.001 0.001 5.623 5.623 multiply_cannon 1966 13.4 0.918 0.918 5.220 5.220 fft_wrap_pw1pw2_140 439 13.2 0.477 0.477 5.214 5.214 copy_dbcsr_to_fm 147 11.2 0.003 0.003 5.145 5.145 dbcsr_make_dense_low 4961 15.5 0.082 0.082 5.077 5.077 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 5.031 5.031 apply_single 107 13.6 0.000 0.000 5.031 5.031 make_dense_data 4961 16.5 4.429 4.429 4.975 4.975 dbcsr_copy 1855 11.9 0.237 0.237 4.871 4.871 dbcsr_copy_into_existing 22 7.9 4.593 4.593 4.594 4.594 dbcsr_make_images_dense 3386 14.7 0.023 0.023 4.546 4.546 qs_ot_p2m_diag 44 11.0 0.193 0.193 4.322 4.322 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 4.286 4.286 ------------------------------------------------------------------------------- From /workspace/artifacts/H2O-64_nonortho_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.007 0.011 123.214 123.215 qs_mol_dyn_low 1 2.0 0.005 0.005 123.096 123.102 qs_forces 11 3.9 0.002 0.002 123.041 123.042 qs_energies 11 4.9 0.001 0.002 114.521 114.522 scf_env_do_scf 11 5.9 0.001 0.001 105.760 105.761 scf_env_do_scf_inner_loop 96 6.5 0.003 0.010 98.361 98.361 velocity_verlet 10 3.0 0.002 0.002 73.208 73.209 rebuild_ks_matrix 107 8.3 0.001 0.001 56.912 56.953 qs_ks_build_kohn_sham_matrix 107 9.3 0.018 0.019 56.912 56.953 sum_up_and_integrate 107 10.3 0.036 0.038 52.071 52.113 integrate_v_rspace 107 11.3 0.004 0.004 52.035 52.078 qs_ks_update_qs_env 107 7.6 0.001 0.001 50.139 50.175 qs_rho_update_rho 107 7.7 0.001 0.001 47.902 47.912 calculate_rho_elec 107 8.7 0.042 0.044 47.901 47.911 grid_integrate_task_list 107 12.3 45.989 46.856 45.989 46.856 grid_collocate_task_list 107 9.7 42.037 42.887 42.037 42.887 dbcsr_multiply_generic 1966 12.4 0.112 0.114 13.313 13.467 qs_scf_new_mos 96 7.5 0.001 0.001 10.872 10.918 qs_scf_loop_do_ot 96 8.5 0.001 0.001 10.872 10.917 ot_scf_mini 96 9.5 0.003 0.003 10.170 10.208 multiply_cannon 1966 13.4 0.191 0.195 8.786 9.057 multiply_cannon_loop 1966 14.4 0.182 0.190 7.925 8.151 rs_pw_transfer 878 11.9 0.013 0.014 6.309 7.760 init_scf_loop 11 6.9 0.000 0.000 7.383 7.384 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 6.950 6.957 init_scf_run 11 5.9 0.001 0.002 6.875 6.875 scf_env_initial_rho_setup 11 6.9 0.000 0.001 6.875 6.875 density_rs2pw 107 9.7 0.007 0.008 5.409 6.872 mp_waitall_1 146670 16.2 6.427 6.812 6.427 6.812 wfi_extrapolate 11 7.9 0.001 0.001 6.292 6.292 ot_mini 96 10.5 0.001 0.001 5.975 6.019 pw_transfer 1295 11.6 0.118 0.125 4.547 4.591 multiply_cannon_metrocomm3 15728 15.4 0.067 0.070 4.082 4.513 fft_wrap_pw1pw2 1081 12.6 0.011 0.012 4.313 4.361 mp_waitany 8968 13.7 2.743 4.245 2.743 4.245 potential_pw2rs 107 12.3 0.008 0.009 4.125 4.132 rs_pw_transfer_RS2PW_140 118 11.5 0.382 0.405 2.500 3.946 fft_wrap_pw1pw2_140 439 13.2 0.439 0.458 3.736 3.850 mp_alltoall_d11v 1998 13.7 2.138 3.663 2.138 3.663 rs_gather_matrices 107 12.3 0.109 0.118 1.874 3.371 fft3d_ps 1081 14.6 1.748 1.853 3.179 3.254 qs_ot_get_derivative 96 11.5 0.001 0.001 3.071 3.111 make_m2s 3932 13.4 0.064 0.066 3.057 3.109 multiply_cannon_multrec 15728 15.4 2.898 2.997 2.913 3.013 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 2.841 2.879 apply_single 107 13.6 0.001 0.001 2.841 2.879 ot_diis_step 96 11.5 0.004 0.004 2.876 2.877 make_images 3932 14.4 0.162 0.166 2.487 2.546 ------------------------------------------------------------------------------- Plot: name="H2O-64_nonortho_timings_32omp", title="Timings of H2O-64_nonortho with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="rest", label="rest", y=74.08800000000002, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=48.44, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=47.846, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=19.094, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_gemm_cosma", label="cp_gemm_cosma", y=10.591, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=6.304, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="mp_waitany", label="mp_waitany", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 Plot: name="H2O-64_nonortho_timings_32mpi", title="Timings of H2O-64_nonortho with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="rest", label="rest", y=23.120000000000005, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=42.037, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=45.989, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="cp_gemm_cosma", label="cp_gemm_cosma", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=2.898, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitany", label="mp_waitany", y=2.743, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=6.427, yerr=0.0 Running H2O-hyb.inp with 1 threads and 32 ranks... done. Running H2O-hyb.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/H2O-hyb_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.352 0.352 254.297 254.297 qs_energies 1 2.0 0.000 0.000 253.147 253.147 scf_env_do_scf 1 3.0 0.000 0.000 250.881 250.881 qs_ks_update_qs_env 8 5.0 0.000 0.000 233.994 233.994 rebuild_ks_matrix 7 6.0 0.000 0.000 233.891 233.891 qs_ks_build_kohn_sham_matrix 7 7.0 0.002 0.002 233.891 233.891 hfx_ks_matrix 7 8.0 0.000 0.000 172.345 172.345 integrate_four_center 7 9.0 2.204 2.204 172.317 172.317 integrate_four_center_main 7 10.0 1.085 1.085 159.016 159.016 integrate_four_center_bin 452 11.0 157.930 157.930 157.930 157.930 scf_env_do_scf_inner_loop 7 4.0 0.001 0.001 142.846 142.846 init_scf_loop 1 4.0 0.000 0.000 108.021 108.021 cp_gemm 129 10.3 0.000 0.000 47.415 47.415 cp_gemm_cosma 129 11.3 47.414 47.414 47.414 47.414 admm_mo_calc_rho_aux 7 8.0 0.000 0.000 28.840 28.840 admm_fit_mo_coeffs 7 9.0 0.000 0.000 27.259 27.259 admm_mo_merge_derivs 7 8.0 0.000 0.000 24.251 24.251 merge_mo_derivs_diag 7 9.0 0.021 0.021 24.251 24.251 purify_mo_diag 7 10.0 0.001 0.001 15.732 15.732 prepare_preconditioner 1 5.0 0.000 0.000 13.296 13.296 make_preconditioner 1 6.0 0.000 0.000 13.296 13.296 fit_mo_coeffs 7 10.0 0.000 0.000 11.527 11.527 integrate_four_center_load 7 10.0 0.001 0.001 10.724 10.724 hfx_load_balance 1 11.0 0.002 0.002 10.723 10.723 arnoldi_normal_ev 11 9.3 0.002 0.002 8.147 8.147 estimate_cond_num 1 7.0 0.000 0.000 8.077 8.077 build_subspace 28 9.5 0.014 0.014 7.999 7.999 hfx_load_balance_count 1 12.0 5.352 5.352 5.352 5.352 hfx_load_balance_bin 1 12.0 5.340 5.340 5.340 5.340 ------------------------------------------------------------------------------- From /workspace/artifacts/H2O-hyb_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.193 0.199 191.585 191.586 qs_energies 1 2.0 0.000 0.000 191.255 191.256 scf_env_do_scf 1 3.0 0.000 0.000 190.735 190.735 qs_ks_update_qs_env 8 5.0 0.000 0.000 187.953 187.953 rebuild_ks_matrix 7 6.0 0.000 0.000 187.941 187.941 qs_ks_build_kohn_sham_matrix 7 7.0 0.002 0.002 187.941 187.941 hfx_ks_matrix 7 8.0 0.000 0.000 177.371 177.373 integrate_four_center 7 9.0 0.090 0.378 177.357 177.359 integrate_four_center_main 7 10.0 0.004 0.005 157.341 164.756 integrate_four_center_bin 448 11.0 157.336 164.751 157.336 164.751 scf_env_do_scf_inner_loop 7 4.0 0.000 0.001 112.157 112.157 init_scf_loop 1 4.0 0.000 0.000 78.576 78.577 mp_sync 70 11.3 8.368 12.218 8.368 12.218 integrate_four_center_load 7 10.0 0.000 0.001 10.863 10.867 hfx_load_balance 1 11.0 0.001 0.002 10.863 10.867 hfx_load_balance_count 1 12.0 5.206 5.436 5.206 5.436 hfx_load_balance_bin 1 12.0 5.181 5.419 5.181 5.419 ------------------------------------------------------------------------------- Plot: name="H2O-hyb_timings_32omp", title="Timings of H2O-hyb with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="H2O-hyb_timings_32omp", name="rest", label="rest", y=35.704999999999984, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_bin", label="integrate_four_center_bin", y=157.93, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="cp_gemm_cosma", label="cp_gemm_cosma", y=47.414, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_count", label="hfx_load_balance_count", y=5.352, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=5.34, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center", label="integrate_four_center", y=2.204, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="CP2K", label="CP2K", y=0.352, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="mp_sync", label="mp_sync", y=0.0, yerr=0.0 Plot: name="H2O-hyb_timings_32mpi", title="Timings of H2O-hyb with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="H2O-hyb_timings_32mpi", name="rest", label="rest", y=15.210999999999984, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center_bin", label="integrate_four_center_bin", y=157.336, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="cp_gemm_cosma", label="cp_gemm_cosma", y=0.0, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_count", label="hfx_load_balance_count", y=5.206, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=5.181, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center", label="integrate_four_center", y=0.09, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="CP2K", label="CP2K", y=0.193, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="mp_sync", label="mp_sync", y=8.368, yerr=0.0 Running GW_PBE_4benzene.inp with 1 threads and 32 ranks... done. Running GW_PBE_4benzene.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/GW_PBE_4benzene_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.013 0.013 316.848 316.848 qs_energies 1 2.0 0.000 0.000 316.269 316.269 mp2_main 1 3.0 0.000 0.000 310.034 310.034 mp2_gpw_main 1 4.0 0.000 0.000 309.596 309.596 rpa_ri_compute_en 1 5.0 0.000 0.000 298.384 298.384 rpa_num_int 1 6.0 0.000 0.000 298.362 298.362 compute_mat_P_omega 1 7.0 0.002 0.002 167.359 167.359 compute_mat_P_omega_contract 10 8.0 11.109 11.109 166.080 166.080 dbt_total 2336 9.6 0.016 0.016 160.416 160.416 cp_gemm 105 8.4 0.000 0.000 101.822 101.822 cp_gemm_cosma 105 9.4 101.822 101.822 101.822 101.822 dbt_contract 787 11.0 46.495 46.495 99.799 99.799 GW_matrix_operations 10 7.0 0.005 0.005 74.579 74.579 compute_mat_P_omega_calc_M_occ 250 9.0 11.142 11.142 59.940 59.940 dbt_copy 1103 10.7 19.937 19.937 59.385 59.385 dbt_tas_total 1149 12.2 0.227 0.227 50.278 50.278 dbt_tas_multiply 807 12.1 0.004 0.004 49.069 49.069 dbt_tas_dbm 807 14.1 0.005 0.005 39.810 39.810 dbm_multiply 807 16.1 39.798 39.798 39.798 39.798 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 37.620 37.620 rpa_num_int_RPA_matrix_operati 10 7.0 0.000 0.000 35.339 35.339 contract_P_omega_with_mat_L 10 8.0 0.000 0.000 33.664 33.664 dbt_tas_mm_1N 524 15.1 0.002 0.002 24.363 24.363 compute_QP_energies 1 7.0 0.000 0.000 19.206 19.206 compute_self_energy_cubic_gw 1 8.0 0.092 0.092 19.206 19.206 dbt_tas_copy 574 11.4 15.379 15.379 18.509 18.509 compute_mat_P_omega_copy_M_occ 250 9.0 0.001 0.001 17.325 17.325 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 14.716 14.716 dbt_tas_mm_2 251 15.0 0.002 0.002 13.714 13.714 compute_mat_P_omega_copy_M_vir 250 9.0 0.001 0.001 12.325 12.325 dbt_copy_nocomm 251 12.0 10.716 10.716 12.271 12.271 dbt_tas_reserve_blocks_index 3261 13.7 7.527 7.527 12.256 12.256 mp2_ri_gpw_compute_in 1 5.0 0.000 0.000 11.198 11.198 dbt_reserve_blocks_index 2280 12.5 1.644 1.644 10.431 10.431 dbt_reserve_blocks_index_array 2222 11.6 0.010 0.010 10.394 10.394 cp_fm_cholesky_invert 10 8.0 8.642 8.642 8.642 8.642 contract_cubic_gw 21 9.0 0.000 0.000 8.452 8.452 ------------------------------------------------------------------------------- From /workspace/artifacts/GW_PBE_4benzene_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.005 0.007 49.991 49.992 qs_energies 1 2.0 0.001 0.001 49.878 49.880 mp2_main 1 3.0 0.000 0.001 48.456 48.457 mp2_gpw_main 1 4.0 0.001 0.001 48.399 48.401 rpa_ri_compute_en 1 5.0 0.000 0.000 46.621 46.622 rpa_num_int 1 6.0 0.001 0.001 46.613 46.614 dbt_total 2336 9.6 0.016 0.017 35.432 35.434 compute_mat_P_omega 1 7.0 0.001 0.002 34.177 34.183 compute_mat_P_omega_contract 10 8.0 0.643 0.673 33.928 33.933 dbt_contract 787 11.0 1.777 1.939 25.933 25.938 dbt_tas_total 1149 12.2 0.070 0.075 22.483 22.483 dbt_tas_multiply 807 12.1 0.003 0.003 22.402 22.404 dbt_tas_dbm 807 14.1 0.005 0.005 15.602 15.602 dbm_multiply 807 16.1 12.295 13.245 12.295 13.245 compute_mat_P_omega_calc_M_occ 250 9.0 0.638 0.661 11.289 11.289 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 8.342 8.342 dbt_copy 1111 10.7 3.622 3.925 7.923 8.289 cp_gemm 105 8.4 0.000 0.000 8.183 8.204 cp_gemm_cosma 105 9.4 8.182 8.203 8.182 8.203 mp_sync 8696 11.6 5.894 7.323 5.894 7.323 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 7.171 7.172 dbt_tas_mm_1N 524 15.1 0.002 0.002 6.162 6.738 dbt_tas_mm_2 251 15.0 0.002 0.002 6.594 6.594 GW_matrix_operations 10 7.0 0.001 0.001 5.360 5.368 compute_QP_energies 1 7.0 0.000 0.000 3.826 3.827 compute_self_energy_cubic_gw 1 8.0 0.004 0.005 3.824 3.826 mp_waitall_2 3776 14.7 2.940 3.176 2.940 3.176 dbt_communicate_buffer 1098 11.7 0.089 0.096 3.069 3.174 contract_cubic_gw 21 9.0 0.000 0.000 2.947 2.947 rpa_num_int_RPA_matrix_operati 10 7.0 0.000 0.000 2.912 2.924 contract_P_omega_with_mat_L 10 8.0 0.000 0.000 2.803 2.816 dbt_reserve_blocks_index_array 2791 11.4 0.010 0.012 2.042 2.284 dbt_reserve_blocks_index 2849 12.4 0.101 0.109 2.044 2.284 dbt_tas_reserve_blocks_index 3300 13.8 0.256 0.273 1.998 2.227 dbt_tas_replicate 396 14.1 1.165 1.392 2.176 2.219 dbm_reserve_blocks 3696 14.8 1.810 2.021 1.810 2.021 mp2_ri_gpw_compute_in 1 5.0 0.001 0.001 1.774 1.776 compute_mat_P_omega_copy_M_vir 250 9.0 0.001 0.002 1.534 1.539 convert_to_new_pgrid 2421 14.1 0.030 0.033 1.387 1.453 dbm_copy 1608 15.1 1.349 1.416 1.349 1.416 compute_mat_P_omega_copy_M_occ 250 9.0 0.001 0.001 1.373 1.377 scf_env_do_scf 1 3.0 0.000 0.000 1.362 1.362 scf_env_do_scf_inner_loop 17 4.0 0.001 0.001 1.362 1.362 mp_max_i 1992 9.8 0.967 1.268 0.967 1.268 ------------------------------------------------------------------------------- Plot: name="GW_PBE_4benzene_timings_32omp", title="Timings of GW_PBE_4benzene with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="rest", label="rest", y=93.417, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="cp_gemm_cosma", label="cp_gemm_cosma", y=101.822, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbt_contract", label="dbt_contract", y=46.495, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=39.798, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbt_copy", label="dbt_copy", y=19.937, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbt_tas_copy", label="dbt_tas_copy", y=15.379, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="mp_sync", label="mp_sync", y=0.0, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="mp_waitall_2", label="mp_waitall_2", y=0.0, yerr=0.0 Plot: name="GW_PBE_4benzene_timings_32mpi", title="Timings of GW_PBE_4benzene with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="rest", label="rest", y=15.281000000000006, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="cp_gemm_cosma", label="cp_gemm_cosma", y=8.182, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbt_contract", label="dbt_contract", y=1.777, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=12.295, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbt_copy", label="dbt_copy", y=3.622, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbt_tas_copy", label="dbt_tas_copy", y=0.0, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_sync", label="mp_sync", y=5.894, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.94, yerr=0.0 Running RI-HFX_H2O-32.inp with 1 threads and 32 ranks... done. Running RI-HFX_H2O-32.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/RI-HFX_H2O-32_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.020 0.020 680.838 680.838 qs_forces 1 2.0 0.000 0.000 680.108 680.108 rebuild_ks_matrix 7 6.6 0.000 0.000 671.134 671.134 qs_ks_build_kohn_sham_matrix 7 7.6 0.002 0.002 671.134 671.134 hfx_ks_matrix 7 8.6 0.000 0.000 668.395 668.395 dbt_total 1051 10.5 0.009 0.009 549.102 549.102 hfx_ri_update_ks 7 9.6 0.000 0.000 367.357 367.357 hfx_ri_update_ks_Pmat 7 10.6 60.346 60.346 367.351 367.351 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 348.521 348.521 dbt_contract 283 11.7 116.926 116.926 345.101 345.101 qs_energies 1 3.0 0.000 0.000 331.520 331.520 scf_env_do_scf 1 4.0 0.000 0.000 331.130 331.130 qs_ks_update_qs_env 8 6.0 0.000 0.000 322.618 322.618 hfx_ri_update_forces 1 7.0 0.026 0.026 301.033 301.033 dbt_tas_total 533 12.7 2.880 2.880 216.873 216.873 dbt_tas_multiply 292 12.8 0.001 0.001 212.313 212.313 dbt_copy 444 11.5 98.806 98.806 199.428 199.428 scf_env_do_scf_inner_loop 6 5.0 0.001 0.001 193.509 193.509 dbt_tas_dbm 292 14.8 0.002 0.002 190.664 190.664 dbm_multiply 292 16.8 190.659 190.659 190.659 190.659 hfx_ri_update_ks_Pmat_KS 63 11.6 0.001 0.001 162.289 162.289 init_scf_loop 2 5.0 0.000 0.000 137.618 137.618 dbt_tas_mm_2 119 16.0 0.001 0.001 109.399 109.399 hfx_ri_forces_Pmat_2c_inv_2 9 8.0 0.000 0.000 54.293 54.293 precalc_derivatives 1 8.0 0.007 0.007 52.928 52.928 hfx_ri_forces_Pmat_metric 9 8.0 0.001 0.001 51.422 51.422 dbt_tas_mm_3N 94 14.7 0.000 0.000 49.938 49.938 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 43.878 43.878 hfx_ri_update_ks_Pmat_copy_2 63 11.6 0.000 0.000 42.460 42.460 dbt_tas_reserve_blocks_index 1569 14.6 16.258 16.258 35.336 35.336 dbt_tas_copy 287 12.3 27.408 27.408 34.414 34.414 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 33.400 33.400 dbt_reserve_blocks_index 1020 13.6 3.586 3.586 31.493 31.493 dbt_reserve_blocks_index_array 999 12.6 0.007 0.007 31.211 31.211 dbt_tas_mm_3T 77 17.1 0.000 0.000 31.152 31.152 hfx_ri_forces_Pmat_PQ_der 9 8.0 1.269 1.269 30.198 30.198 hfx_ri_forces_Pmat_Pmat_2 9 8.0 0.000 0.000 27.653 27.653 hfx_ri_forces_Pmat_2c_inv_1 1 8.0 4.252 4.252 27.276 27.276 build_3c_derivatives 2 9.0 1.191 1.191 26.122 26.122 get_force_from_3c_trace 18 8.0 24.883 24.883 24.883 24.883 dbt_communicate_buffer 157 12.8 20.682 20.682 20.683 20.683 dbt_split_blocks_generic 138 11.7 16.330 16.330 20.012 20.012 dbt_split_copyback 69 11.7 15.749 15.749 17.897 17.897 dbm_reserve_blocks 1813 15.4 15.896 15.896 15.896 15.896 ------------------------------------------------------------------------------- From /workspace/artifacts/RI-HFX_H2O-32_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.007 0.009 97.785 97.786 qs_forces 1 2.0 0.000 0.001 97.623 97.624 rebuild_ks_matrix 7 6.6 0.000 0.000 96.596 96.597 qs_ks_build_kohn_sham_matrix 7 7.6 0.002 0.003 96.596 96.597 hfx_ks_matrix 7 8.6 0.000 0.000 95.105 95.105 dbt_total 1051 10.5 0.009 0.011 87.040 87.040 dbt_contract 283 11.7 4.691 5.057 68.583 68.602 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 64.024 64.024 dbt_tas_total 533 12.7 0.110 0.298 62.967 62.968 dbt_tas_multiply 292 12.8 0.001 0.001 60.063 60.064 hfx_ri_update_forces 1 7.0 0.002 0.003 59.525 59.525 dbt_tas_dbm 292 14.8 0.002 0.003 46.598 46.598 dbm_multiply 292 16.8 41.252 43.561 41.252 43.561 hfx_ri_update_ks 7 9.6 0.000 0.000 35.579 35.579 hfx_ri_update_ks_Pmat 7 10.6 2.401 2.595 35.578 35.578 qs_energies 1 3.0 0.000 0.000 33.583 33.583 scf_env_do_scf 1 4.0 0.000 0.000 33.385 33.385 qs_ks_update_qs_env 8 6.0 0.000 0.000 32.573 32.574 dbt_tas_mm_2 119 16.0 0.001 0.001 20.655 20.655 scf_env_do_scf_inner_loop 6 5.0 0.000 0.001 18.922 18.923 hfx_ri_forces_Pmat_metric 9 8.0 0.001 0.001 17.691 17.691 dbt_copy 464 11.6 5.218 5.465 14.269 14.658 init_scf_loop 2 5.0 0.000 0.000 14.462 14.462 hfx_ri_update_ks_Pmat_KS 63 11.6 0.001 0.001 13.848 13.848 mp_sync 3797 12.3 9.439 12.769 9.439 12.769 dbt_tas_mm_3T 77 17.1 0.000 0.001 11.373 12.269 dbt_tas_mm_3N 94 14.7 0.000 0.001 11.400 12.181 hfx_ri_forces_Pmat_2c_inv_2 9 8.0 0.000 0.000 10.902 10.902 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 9.414 9.415 hfx_ri_forces_Pmat_PQ_der 9 8.0 0.063 0.066 8.774 8.774 hfx_ri_forces_Pmat_Pmat_2 9 8.0 0.000 0.000 7.133 7.149 dbm_reserve_blocks 1848 15.6 5.471 6.326 5.471 6.326 dbt_tas_reserve_blocks_index 1602 14.7 0.560 0.592 5.710 6.133 mp_waitall_2 1484 15.5 5.541 5.991 5.541 5.991 precalc_derivatives 1 8.0 0.002 0.003 5.564 5.564 dbt_reserve_blocks_index 1191 13.5 0.161 0.171 4.912 5.283 dbt_reserve_blocks_index_array 1170 12.5 0.007 0.008 4.876 5.248 dbt_tas_replicate 246 14.5 1.470 2.145 4.831 5.167 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 4.332 4.332 hfx_ri_forces_Pmat_2c_inv_1 1 8.0 0.157 0.167 4.201 4.206 convert_to_new_pgrid 876 14.8 0.028 0.035 3.308 3.936 dbm_copy 578 15.8 3.250 3.879 3.250 3.879 dbt_tas_communicate_buffer 498 15.8 0.020 0.023 3.106 3.495 build_3c_derivatives 2 9.0 0.602 0.651 3.074 3.088 dbt_communicate_buffer 328 12.3 0.021 0.021 2.753 2.881 dbt_tas_replicate_communicate_ 127 15.0 0.003 0.004 2.487 2.866 hfx_ri_forces_Pmat_Pmat_1 3 8.0 0.000 0.000 2.353 2.353 hfx_ri_pre_scf_Pmat_RIx3C 9 13.0 0.000 0.000 2.290 2.300 dbt_tas_copy 141 13.3 1.182 1.275 2.068 2.226 mp_sum_l 8004 13.7 1.519 2.171 1.519 2.171 hfx_ri_update_ks_Pmat_copy_2 63 11.6 0.000 0.000 2.041 2.041 dbt_tas_reshape 252 14.0 0.005 0.005 1.692 2.020 ------------------------------------------------------------------------------- Plot: name="RI-HFX_H2O-32_timings_32omp", title="Timings of RI-HFX_H2O-32 with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="rest", label="rest", y=170.79699999999997, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=190.659, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_contract", label="dbt_contract", y=116.926, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_copy", label="dbt_copy", y=98.806, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=60.346, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_tas_copy", label="dbt_tas_copy", y=27.408, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=15.896, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="mp_waitall_2", label="mp_waitall_2", y=0.0, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="mp_sync", label="mp_sync", y=0.0, yerr=0.0 Plot: name="RI-HFX_H2O-32_timings_32mpi", title="Timings of RI-HFX_H2O-32 with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="rest", label="rest", y=22.590000000000003, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=41.252, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_contract", label="dbt_contract", y=4.691, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_copy", label="dbt_copy", y=5.218, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=2.401, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_tas_copy", label="dbt_tas_copy", y=1.182, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=5.471, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=5.541, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_sync", label="mp_sync", y=9.439, yerr=0.0 Running diag_cu144_broy.inp with 1 threads and 32 ranks... done. Running diag_cu144_broy.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/diag_cu144_broy_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.092 0.092 185.559 185.559 qs_energies 1 2.0 0.000 0.000 183.903 183.903 scf_env_do_scf 1 3.0 0.000 0.000 174.171 174.171 scf_env_do_scf_inner_loop 15 4.0 0.002 0.002 174.171 174.171 qs_scf_new_mos 15 5.0 0.000 0.000 75.901 75.901 qs_ks_update_qs_env 15 5.0 0.000 0.000 67.451 67.451 rebuild_ks_matrix 15 6.0 0.000 0.000 67.093 67.093 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.002 67.093 67.093 eigensolver 15 6.0 0.002 0.002 62.978 62.978 cp_fm_diag_elpa 15 7.0 0.000 0.000 49.981 49.981 cp_fm_diag_elpa_base 15 8.0 45.540 45.540 49.980 49.980 qs_vxc_create 15 8.0 0.044 0.044 43.500 43.500 calculate_dispersion_nonloc 15 9.0 8.924 8.924 37.925 37.925 pw_transfer 1191 9.8 0.089 0.089 25.370 25.370 fft_wrap_pw1pw2 1086 10.9 0.012 0.012 25.094 25.094 qs_rho_update_rho 16 5.0 0.000 0.000 24.846 24.846 calculate_rho_elec 16 6.0 0.338 0.338 24.846 24.846 grid_collocate_task_list 16 7.0 23.349 23.349 23.349 23.349 sum_up_and_integrate 15 8.0 0.073 0.073 22.077 22.077 integrate_v_rspace 15 9.0 0.031 0.031 22.005 22.005 grid_integrate_task_list 15 10.0 21.410 21.410 21.410 21.410 fft_wrap_pw1pw2_150 765 12.0 3.224 3.224 18.986 18.986 fft3d_s 1087 12.8 10.463 10.463 10.474 10.474 copy_dbcsr_to_fm 16 5.9 0.001 0.001 10.330 10.330 pw_scatter_s 585 13.0 9.851 9.851 9.851 9.851 dbcsr_complete_redistribute 46 8.3 3.345 3.345 9.230 9.230 cp_fm_upper_to_full 30 8.0 8.754 8.754 8.754 8.754 cp_fm_cholesky_restore 45 7.0 8.682 8.682 8.682 8.682 vdW_energy 15 10.0 7.711 7.711 7.711 7.711 gspace_mixing 14 5.0 0.273 0.273 7.315 7.315 broyden_mixing 14 6.0 6.577 6.577 6.577 6.577 fft_wrap_pw1pw2_200 197 11.5 0.312 0.312 5.863 5.863 xc_vxc_pw_create 15 9.0 1.435 1.435 5.531 5.531 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 4.552 4.552 init_scf_run 1 3.0 0.000 0.000 4.440 4.440 dbcsr_finalize 159 9.9 0.019 0.019 4.030 4.030 dbcsr_merge_all 91 11.1 0.065 0.065 3.879 3.879 ------------------------------------------------------------------------------- From /workspace/artifacts/diag_cu144_broy_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.018 0.021 83.486 83.487 qs_energies 1 2.0 0.000 0.001 83.106 83.107 scf_env_do_scf 1 3.0 0.000 0.000 77.971 77.971 scf_env_do_scf_inner_loop 15 4.0 0.001 0.002 77.971 77.971 qs_ks_update_qs_env 15 5.0 0.000 0.000 38.045 38.059 rebuild_ks_matrix 15 6.0 0.000 0.000 38.004 38.018 qs_ks_build_kohn_sham_matrix 15 7.0 0.003 0.004 38.004 38.018 qs_rho_update_rho 16 5.0 0.000 0.000 23.638 23.640 calculate_rho_elec 16 6.0 0.011 0.012 23.637 23.639 sum_up_and_integrate 15 8.0 0.012 0.013 22.817 22.837 integrate_v_rspace 15 9.0 0.001 0.001 22.804 22.824 grid_collocate_task_list 16 7.0 21.869 22.493 21.869 22.493 grid_integrate_task_list 15 10.0 20.973 21.953 20.973 21.953 qs_scf_new_mos 15 5.0 0.000 0.001 16.866 16.904 eigensolver 15 6.0 0.002 0.002 15.528 15.535 qs_vxc_create 15 8.0 0.001 0.001 14.715 14.726 calculate_dispersion_nonloc 15 9.0 1.354 1.478 12.039 12.053 cp_fm_diag_elpa 15 7.0 0.000 0.000 11.340 11.348 cp_fm_diag_elpa_base 15 8.0 11.108 11.140 11.335 11.337 pw_transfer 1191 9.8 0.119 0.126 11.096 11.207 fft_wrap_pw1pw2 1086 10.9 0.017 0.019 10.833 10.966 fft3d_ps 1086 12.9 4.766 5.098 8.280 8.467 fft_wrap_pw1pw2_150 765 12.0 0.593 0.633 7.333 7.375 cp_fm_cholesky_restore 45 7.0 3.962 4.018 3.962 4.018 fft_wrap_pw1pw2_200 197 11.5 0.316 0.340 3.350 3.492 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 3.190 3.190 build_core_hamiltonian_matrix 1 4.0 0.000 0.000 2.704 3.020 xc_vxc_pw_create 15 9.0 0.049 0.069 2.675 2.692 mp_alltoall_z22v 1086 14.9 2.161 2.604 2.161 2.604 rs_pw_transfer 158 9.4 0.002 0.002 1.699 2.210 vdW_energy 15 10.0 1.964 2.090 1.964 2.090 x_to_yz 585 14.0 0.841 0.876 1.943 2.050 build_core_ppnl 1 5.0 1.808 2.018 1.808 2.018 density_rs2pw 16 7.0 0.002 0.002 1.616 1.961 yz_to_x 501 13.7 0.483 0.608 1.542 1.820 mp_waitany 520 11.3 1.157 1.764 1.157 1.764 ------------------------------------------------------------------------------- Plot: name="diag_cu144_broy_timings_32omp", title="Timings of diag_cu144_broy with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="diag_cu144_broy_timings_32omp", name="rest", label="rest", y=66.26400000000001, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=45.54, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=23.349, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=21.41, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="fft3d_s", label="fft3d_s", y=10.463, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="pw_scatter_s", label="pw_scatter_s", y=9.851, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=8.682, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="fft3d_ps", label="fft3d_ps", y=0.0, yerr=0.0 Plot: name="diag_cu144_broy_timings_32mpi", title="Timings of diag_cu144_broy with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="rest", label="rest", y=20.808, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=11.108, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=21.869, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=20.973, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="fft3d_s", label="fft3d_s", y=0.0, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="pw_scatter_s", label="pw_scatter_s", y=0.0, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=3.962, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=4.766, yerr=0.0 Running bench_dftb.inp with 1 threads and 32 ranks... done. Running bench_dftb.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/bench_dftb_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.080 0.080 308.998 308.998 qs_energies 1 2.0 0.000 0.000 308.849 308.849 ls_scf 1 3.0 0.000 0.000 307.129 307.129 ls_scf_main 1 4.0 0.002 0.002 293.863 293.863 density_matrix_trs4 11 5.0 0.011 0.011 178.318 178.318 dbcsr_multiply_generic 185 6.1 0.617 0.617 112.929 112.929 ls_scf_dm_to_ks 11 5.0 0.000 0.000 108.361 108.361 matrix_ls_to_qs 11 6.0 0.000 0.000 103.801 103.801 multiply_cannon 185 7.1 3.364 3.364 77.627 77.627 dbcsr_complete_redistribute 23 7.5 41.497 41.497 56.772 56.772 multiply_cannon_loop 185 8.1 0.378 0.378 56.147 56.147 multiply_cannon_multrec 185 9.1 54.079 54.079 54.231 54.231 dbcsr_copy_into_existing 11 7.0 52.101 52.101 52.101 52.101 matrix_decluster 11 7.0 0.000 0.000 51.698 51.698 arnoldi_extremal 12 6.1 0.000 0.000 47.284 47.284 arnoldi_normal_ev 12 7.1 0.028 0.028 47.284 47.284 build_subspace 23 8.1 0.135 0.135 46.592 46.592 dbcsr_matrix_vector_mult 652 9.0 0.253 0.253 36.067 36.067 dbcsr_matrix_vector_mult_local 652 10.0 34.588 34.588 34.596 34.596 make_m2s 370 7.1 0.030 0.030 28.934 28.934 make_images 370 8.1 7.186 7.186 26.644 26.644 dbcsr_finalize 646 7.5 0.194 0.194 20.561 20.561 dbcsr_merge_all 597 8.5 3.336 3.336 18.520 18.520 setup_rec_index_2d 370 8.1 17.752 17.752 17.752 17.752 dbcsr_sort_indices 1103 9.9 16.437 16.437 16.437 16.437 quick_finalize 395 10.0 0.461 0.461 13.992 13.992 tree_to_linear_d 110 9.4 13.074 13.074 13.074 13.074 dbcsr_special_finalize 370 9.1 0.003 0.003 12.870 12.870 ls_scf_init_scf 1 4.0 0.000 0.000 12.296 12.296 ls_scf_init_matrix_S 1 5.0 0.000 0.000 11.858 11.858 matrix_sqrt_Newton_Schulz 1 6.0 0.001 0.001 10.993 10.993 dbcsr_dot_sd 144 6.3 8.746 8.746 8.747 8.747 matrix_qs_to_ls 12 5.1 0.000 0.000 7.481 7.481 matrix_cluster 12 6.1 0.000 0.000 7.481 7.481 dbcsr_frobenius_norm 142 6.1 7.406 7.406 7.408 7.408 make_images_data 370 9.1 0.010 0.010 6.380 6.380 ------------------------------------------------------------------------------- From /workspace/artifacts/bench_dftb_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.011 0.015 89.272 89.273 qs_energies 1 2.0 0.000 0.000 89.176 89.176 ls_scf 1 3.0 0.000 0.000 89.098 89.098 ls_scf_main 1 4.0 0.000 0.003 85.583 85.584 density_matrix_trs4 11 5.0 0.008 0.012 81.653 81.766 dbcsr_multiply_generic 185 6.1 0.074 0.089 76.394 76.706 multiply_cannon 185 7.1 0.039 0.043 63.303 65.016 multiply_cannon_loop 185 8.1 0.183 0.200 59.765 62.248 multiply_cannon_multrec 1480 9.1 38.620 41.373 39.055 41.811 mp_waitall_1 11936 10.3 19.052 22.219 19.052 22.219 multiply_cannon_metrocomm3 1480 9.1 0.017 0.020 11.556 15.926 make_m2s 370 7.1 0.032 0.034 8.282 8.381 make_images 370 8.1 0.694 0.716 8.167 8.261 multiply_cannon_metrocomm1 1480 9.1 0.009 0.011 4.603 7.234 mp_sum_l 1039 5.9 3.624 4.967 3.624 4.967 calculate_norms 2960 9.1 4.293 4.666 4.293 4.666 arnoldi_extremal 12 6.1 0.000 0.001 3.955 3.967 arnoldi_normal_ev 12 7.1 0.002 0.008 3.954 3.967 dbcsr_multiply_generic_mpsum_f 137 7.1 0.000 0.001 2.702 3.855 build_subspace 23 8.1 0.036 0.051 3.830 3.834 make_images_data 370 9.1 0.011 0.012 3.238 3.531 ls_scf_dm_to_ks 11 5.0 0.000 0.000 3.418 3.512 dbcsr_matrix_vector_mult 652 9.0 0.018 0.078 3.157 3.245 dbcsr_complete_redistribute 23 7.5 1.863 2.030 2.918 2.999 matrix_ls_to_qs 11 6.0 0.000 0.000 2.869 2.956 hybrid_alltoall_any 393 9.9 0.280 1.382 2.590 2.887 ls_scf_init_scf 1 4.0 0.000 0.000 2.697 2.698 matrix_decluster 11 7.0 0.000 0.000 2.615 2.695 ls_scf_init_matrix_S 1 5.0 0.000 0.000 2.657 2.667 dbcsr_matrix_vector_mult_local 652 10.0 2.453 2.649 2.457 2.654 matrix_sqrt_Newton_Schulz 1 6.0 0.001 0.001 2.436 2.438 make_images_pack 370 9.1 2.192 2.427 2.197 2.431 dbcsr_add_d 280 6.0 0.001 0.002 1.934 2.078 dbcsr_add_anytype 280 7.0 1.046 1.163 1.932 2.076 buffer_matrices_ensure_size 370 8.1 1.951 2.065 1.951 2.065 dbcsr_finalize 646 7.5 0.013 0.014 1.774 1.872 ------------------------------------------------------------------------------- Plot: name="bench_dftb_timings_32omp", title="Timings of bench_dftb with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="bench_dftb_timings_32omp", name="rest", label="rest", y=108.98099999999997, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=54.079, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_copy_into_existing", label="dbcsr_copy_into_existing", y=52.101, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_complete_redistribute", label="dbcsr_complete_redistribute", y=41.497, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=34.588, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="setup_rec_index_2d", label="setup_rec_index_2d", y=17.752, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="calculate_norms", label="calculate_norms", y=0.0, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="mp_sum_l", label="mp_sum_l", y=0.0, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 Plot: name="bench_dftb_timings_32mpi", title="Timings of bench_dftb with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="bench_dftb_timings_32mpi", name="rest", label="rest", y=19.367000000000004, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=38.62, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="dbcsr_copy_into_existing", label="dbcsr_copy_into_existing", y=0.0, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="dbcsr_complete_redistribute", label="dbcsr_complete_redistribute", y=1.863, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=2.453, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="setup_rec_index_2d", label="setup_rec_index_2d", y=0.0, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="calculate_norms", label="calculate_norms", y=4.293, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=3.624, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=19.052, yerr=0.0 Running dbcsr.inp with 1 threads and 32 ranks... done. Running dbcsr.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/dbcsr_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.005 0.005 93.051 93.051 lib_test 1 2.0 0.000 0.000 93.045 93.045 dbcsr_run_tests 3 3.0 0.002 0.002 93.045 93.045 test_multiplies_multiproc 3 4.0 0.001 0.001 73.774 73.774 dbcsr_redistribute 9 5.0 46.300 46.300 49.874 49.874 dbcsr_multiply_generic 9 5.0 0.001 0.001 22.185 22.185 dbcsr_make_random_matrix 9 4.0 14.046 14.046 19.192 19.192 multiply_cannon 9 6.0 0.002 0.002 15.665 15.665 multiply_cannon_loop 9 7.0 0.003 0.003 15.167 15.167 multiply_cannon_multrec 9 8.0 15.164 15.164 15.165 15.165 dbcsr_finalize 27 5.7 0.004 0.004 8.973 8.973 dbcsr_merge_all 18 6.5 3.272 3.272 8.262 8.262 mp_alltoall_d11v 27 6.0 3.243 3.243 3.243 3.243 tree_to_linear_d 9 7.0 3.092 3.092 3.092 3.092 dbcsr_data_release 975 7.6 2.340 2.340 2.340 2.340 make_m2s 18 6.0 0.001 0.001 2.114 2.114 make_images 18 7.0 0.682 0.682 2.047 2.047 ------------------------------------------------------------------------------- From /workspace/artifacts/dbcsr_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.003 0.005 24.337 24.338 lib_test 1 2.0 0.000 0.000 24.311 24.329 dbcsr_run_tests 3 3.0 0.000 0.001 24.310 24.327 test_multiplies_multiproc 3 4.0 0.001 0.001 23.193 23.249 dbcsr_multiply_generic 9 5.0 0.001 0.002 21.396 21.485 multiply_cannon 9 6.0 0.002 0.002 19.175 19.564 multiply_cannon_loop 9 7.0 0.003 0.003 18.772 19.218 multiply_cannon_multrec 72 8.0 15.586 16.411 15.587 16.412 mp_waitall_1 576 9.2 3.566 4.284 3.566 4.284 multiply_cannon_metrocomm1 72 8.0 0.001 0.002 2.759 3.469 mp_sum_l 310 2.7 0.627 1.318 0.627 1.318 dbcsr_multiply_generic_mpsum_f 9 6.0 0.000 0.000 0.624 1.314 multiply_cannon_metrocomm3 72 8.0 0.000 0.000 0.416 1.182 dbcsr_make_random_matrix 9 4.0 0.880 0.899 1.076 1.108 make_m2s 18 6.0 0.001 0.001 0.857 0.920 make_images 18 7.0 0.026 0.027 0.854 0.917 dbcsr_finalize 27 5.7 0.000 0.001 0.767 0.886 dbcsr_merge_all 18 6.5 0.124 0.149 0.682 0.790 dbcsr_data_release 444 7.6 0.617 0.710 0.617 0.710 dbcsr_redistribute 9 5.0 0.355 0.406 0.616 0.638 dbcsr_destroy 111 5.9 0.009 0.053 0.542 0.619 make_images_data 18 8.0 0.001 0.001 0.432 0.514 ------------------------------------------------------------------------------- Plot: name="dbcsr_timings_32omp", title="Timings of dbcsr with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="dbcsr_timings_32omp", name="rest", label="rest", y=8.686000000000007, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_redistribute", label="dbcsr_redistribute", y=46.3, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=15.164, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=14.046, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_merge_all", label="dbcsr_merge_all", y=3.272, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="mp_alltoall_d11v", label="mp_alltoall_d11v", y=3.243, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_data_release", label="dbcsr_data_release", y=2.34, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="mp_sum_l", label="mp_sum_l", y=0.0, yerr=0.0 Plot: name="dbcsr_timings_32mpi", title="Timings of dbcsr with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="dbcsr_timings_32mpi", name="rest", label="rest", y=2.5820000000000007, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_redistribute", label="dbcsr_redistribute", y=0.355, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=15.586, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=0.88, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_merge_all", label="dbcsr_merge_all", y=0.124, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_alltoall_d11v", label="mp_alltoall_d11v", y=0.0, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_data_release", label="dbcsr_data_release", y=0.617, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=3.566, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=0.627, yerr=0.0 Running MQAE_single_node.inp with 1 threads and 32 ranks... done. Running MQAE_single_node.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/MQAE_single_node_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.042 0.042 138.291 138.291 qs_mol_dyn_low 1 2.0 0.004 0.004 136.440 136.440 velocity_verlet 5 3.0 0.003 0.003 110.543 110.543 qmmm_el_coupling 6 3.8 0.000 0.000 62.044 62.044 qmmm_elec_with_gaussian 6 4.8 0.178 0.178 62.038 62.038 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 61.080 61.080 qmmm_elec_gaussian_low_G 6 6.8 59.436 59.436 59.436 59.436 qs_forces 6 3.8 0.001 0.001 54.730 54.730 qs_energies 6 4.8 0.000 0.000 48.695 48.695 scf_env_do_scf 6 5.8 0.000 0.000 44.957 44.957 scf_env_do_scf_inner_loop 39 6.8 0.003 0.003 37.679 37.679 rebuild_ks_matrix 45 8.4 0.000 0.000 37.511 37.511 qs_ks_build_kohn_sham_matrix 45 9.4 0.007 0.007 37.511 37.511 qs_ks_update_qs_env 45 7.8 0.000 0.000 32.189 32.189 pw_transfer 966 11.9 0.066 0.066 22.833 22.833 fft_wrap_pw1pw2 801 13.0 0.008 0.008 22.526 22.526 fft_wrap_pw1pw2_150 507 14.3 2.317 2.317 22.027 22.027 qs_vxc_create 45 10.4 0.001 0.001 20.237 20.237 xc_vxc_pw_create 45 11.4 3.951 3.951 20.236 20.236 fist_calc_energy_force 6 3.8 0.001 0.001 10.695 10.695 pw_scatter_s 429 15.4 9.991 9.991 9.991 9.991 qs_rho_update_rho 45 7.9 0.000 0.000 9.873 9.873 calculate_rho_elec 45 8.9 0.882 0.882 9.873 9.873 force_nonbond 6 4.8 9.512 9.512 9.512 9.512 xc_rho_set_and_dset_create 45 12.4 0.235 0.235 9.346 9.346 fft3d_s 802 15.0 8.856 8.856 8.865 8.865 qmmm_forces 6 3.8 0.001 0.001 8.190 8.190 qmmm_forces_with_gaussian 6 4.8 0.123 0.123 7.692 7.692 init_scf_loop 6 6.8 0.000 0.000 7.272 7.272 pw_integral_ab 2539 7.4 7.172 7.172 7.172 7.172 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 6.643 6.643 qs_ks_ddapc 45 10.4 0.001 0.001 6.306 6.306 qmmm_forces_gaussian_low_G 6 6.8 5.586 5.586 5.586 5.586 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 5.333 5.333 pw_poisson_solve 51 9.9 2.160 2.160 4.996 4.996 density_rs2pw 45 9.9 0.003 0.003 4.539 4.539 grid_collocate_task_list 45 9.9 4.452 4.452 4.452 4.452 sum_up_and_integrate 45 10.4 0.221 0.221 4.290 4.290 integrate_v_rspace 45 11.4 0.012 0.012 4.069 4.069 cp_ddapc_apply_CD 45 11.4 0.006 0.006 3.900 3.900 ------------------------------------------------------------------------------- From /workspace/artifacts/MQAE_single_node_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.032 0.035 82.389 82.390 qs_mol_dyn_low 1 2.0 0.004 0.005 80.790 80.884 qs_forces 6 3.8 0.001 0.001 59.448 59.448 qs_energies 6 4.8 0.001 0.001 56.654 56.654 scf_env_do_scf 6 5.8 0.000 0.000 55.224 55.224 scf_env_do_scf_inner_loop 113 6.2 0.003 0.009 53.003 53.004 rebuild_ks_matrix 119 8.1 0.000 0.000 39.002 39.018 qs_ks_build_kohn_sham_matrix 119 9.1 0.020 0.022 39.001 39.018 qs_ks_update_qs_env 119 7.3 0.001 0.001 36.659 36.675 velocity_verlet 5 3.0 0.002 0.002 33.786 33.791 pw_transfer 2446 11.8 0.259 0.283 24.793 25.039 fft_wrap_pw1pw2 2059 12.8 0.031 0.034 24.020 24.309 fft_wrap_pw1pw2_150 1321 14.0 2.044 2.170 23.272 23.628 qs_vxc_create 119 10.1 0.003 0.003 19.687 19.692 xc_vxc_pw_create 119 11.1 0.410 0.553 19.685 19.688 fft3d_ps 2059 14.8 10.653 11.763 18.188 18.442 qs_rho_update_rho 119 7.3 0.001 0.001 15.494 15.495 calculate_rho_elec 119 8.3 0.086 0.096 15.493 15.495 sum_up_and_integrate 119 10.1 0.077 0.085 14.079 14.157 integrate_v_rspace 119 11.1 0.004 0.005 14.002 14.087 qmmm_forces 6 3.8 0.002 0.003 11.871 11.872 qmmm_forces_with_gaussian 6 4.8 0.330 0.413 11.351 11.655 rs_pw_transfer 988 11.5 0.014 0.015 10.274 10.655 xc_rho_set_and_dset_create 119 12.1 0.480 0.547 9.280 9.612 density_rs2pw 119 9.3 0.010 0.012 9.164 9.517 qmmm_el_coupling 6 3.8 0.000 0.000 8.274 8.343 qmmm_elec_with_gaussian 6 4.8 0.295 0.411 8.272 8.340 potential_pw2rs 119 12.1 0.010 0.011 7.998 8.012 grid_collocate_task_list 119 9.3 6.000 6.383 6.000 6.383 mp_alltoall_z22v 2059 16.8 4.697 6.364 4.697 6.364 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 5.767 5.987 grid_integrate_task_list 119 12.1 5.586 5.811 5.586 5.811 qmmm_forces_gaussian_low_G 6 6.8 4.727 4.937 4.727 4.937 x_to_yz 1095 16.3 1.680 1.850 4.111 4.450 rs_pw_transfer_PW2RS_150 125 13.9 2.306 2.374 4.399 4.448 yz_to_x 964 15.3 1.113 1.254 3.379 4.399 pw_restrict_s3 18 5.8 2.284 2.340 4.153 4.272 rs_pw_transfer_RS2PW_150 125 11.2 1.811 1.927 3.771 4.106 mp_waitany 4028 12.8 3.239 3.823 3.239 3.823 qs_scf_new_mos 113 7.2 0.001 0.001 3.577 3.586 qs_scf_loop_do_ot 113 8.2 0.001 0.001 3.577 3.585 qmmm_elec_with_gaussian:spline 6 5.8 0.000 0.000 3.376 3.442 pw_prolongate_s3 18 6.8 1.831 1.875 3.376 3.442 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 3.339 3.441 ot_scf_mini 113 9.2 0.002 0.002 3.420 3.428 dbcsr_multiply_generic 2588 12.3 0.097 0.114 3.267 3.380 qs_ks_ddapc 119 10.1 0.002 0.003 2.679 2.825 pw_integral_ab 2761 7.7 2.017 2.077 2.399 2.537 qmmm_elec_gaussian_low_G 6 6.8 2.396 2.486 2.396 2.486 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 2.351 2.352 mp_sum_dm3 33 5.7 2.198 2.325 2.198 2.325 init_scf_loop 6 6.8 0.000 0.001 2.218 2.218 pw_gather_p 964 14.3 1.916 2.200 1.916 2.200 ot_mini 113 10.2 0.001 0.001 2.165 2.177 mp_waitall_1 188862 16.2 1.817 2.006 1.817 2.006 pw_scatter_p 1095 15.3 1.786 1.869 1.786 1.869 qs_ot_get_derivative 113 11.2 0.001 0.001 1.711 1.718 mp_sum_d 5820 12.2 1.239 1.708 1.239 1.708 ------------------------------------------------------------------------------- Plot: name="MQAE_single_node_timings_32omp", title="Timings of MQAE_single_node with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="MQAE_single_node_timings_32omp", name="rest", label="rest", y=33.286000000000016, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=59.436, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_scatter_s", label="pw_scatter_s", y=9.991, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="force_nonbond", label="force_nonbond", y=9.512, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_s", label="fft3d_s", y=8.856, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_integral_ab", label="pw_integral_ab", y=7.172, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=5.586, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=4.452, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_ps", label="fft3d_ps", y=0.0, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=0.0, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=0.0, yerr=0.0 Plot: name="MQAE_single_node_timings_32mpi", title="Timings of MQAE_single_node with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="MQAE_single_node_timings_32mpi", name="rest", label="rest", y=46.312999999999995, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=2.396, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="pw_scatter_s", label="pw_scatter_s", y=0.0, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="force_nonbond", label="force_nonbond", y=0.0, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="fft3d_s", label="fft3d_s", y=0.0, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="pw_integral_ab", label="pw_integral_ab", y=2.017, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=4.727, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=6.0, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=10.653, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=5.586, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=4.697, yerr=0.0 Summary: Performance test took 52 minutes. Status: OK Uploading artifacts... done EndDate: 2022-01-29 12:00:16+00:00