StartDate: 2021-12-17 11:18:30+00:00 CpuId: 64x Intel Xeon W 2000 / D-2100 (Skylake / Cascade Lake) {Skylake}, 14nm CommitSHA: e26e4f068159c22d4100340963196ff3891bb2f7 CommitTime: 2021-12-17 12:00:10 +0100 CommitAuthor: Alfio Lazzaro CommitSubject: Avoid ELPA for small GPU runs in the benchmarks test (MP2/RPA) (#1818) 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: e26e4f068159c22d4100340963196ff3891bb2f7 CommitTime: 2021-12-17 12:00:10 +0100 CommitAuthor: Alfio Lazzaro CommitSubject: Avoid ELPA for small GPU runs in the benchmarks test (MP2/RPA) (#1818) ========== 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 0.032 0.032 161.247 161.247 qs_mol_dyn_low 1 2.0 0.004 0.004 160.433 160.433 qs_forces 11 3.9 0.001 0.001 160.376 160.376 qs_energies 11 4.9 0.001 0.001 149.663 149.663 scf_env_do_scf 11 5.9 0.001 0.001 122.269 122.269 velocity_verlet 10 3.0 0.002 0.002 110.715 110.715 scf_env_do_scf_inner_loop 108 6.5 0.010 0.010 83.350 83.350 init_scf_loop 11 6.9 0.000 0.000 38.738 38.738 prepare_preconditioner 11 7.9 0.000 0.000 34.696 34.696 make_preconditioner 11 8.9 0.000 0.000 34.696 34.696 rebuild_ks_matrix 119 8.3 0.001 0.001 33.765 33.765 qs_ks_build_kohn_sham_matrix 119 9.3 0.019 0.019 33.764 33.764 make_full_inverse_cholesky 11 9.9 0.000 0.000 32.684 32.684 qs_ks_update_qs_env 119 7.6 0.001 0.001 31.513 31.513 qs_rho_update_rho 119 7.7 0.001 0.001 29.288 29.288 calculate_rho_elec 119 8.7 1.560 1.560 29.287 29.287 qs_scf_new_mos 108 7.5 0.001 0.001 28.766 28.766 qs_scf_loop_do_ot 108 8.5 0.001 0.001 28.765 28.765 ot_scf_mini 108 9.5 0.003 0.003 26.709 26.709 dbcsr_multiply_generic 2286 12.5 0.179 0.179 24.702 24.702 grid_collocate_task_list 119 9.7 22.909 22.909 22.909 22.909 sum_up_and_integrate 119 10.3 0.383 0.383 21.428 21.428 integrate_v_rspace 119 11.3 0.691 0.691 21.045 21.045 cp_fm_cholesky_invert 11 10.9 19.566 19.566 19.566 19.566 grid_integrate_task_list 119 12.3 17.806 17.806 17.806 17.806 ot_mini 108 10.5 0.001 0.001 15.836 15.836 make_m2s 4572 13.5 0.067 0.067 13.665 13.665 init_scf_run 11 5.9 0.001 0.001 13.119 13.119 scf_env_initial_rho_setup 11 6.9 0.001 0.001 13.118 13.118 wfi_extrapolate 11 7.9 0.001 0.001 12.355 12.355 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 10.606 10.606 cp_gemm 81 9.0 0.000 0.000 10.355 10.355 cp_gemm_cosma 81 10.0 10.354 10.354 10.354 10.354 qs_ot_get_derivative 108 11.5 0.002 0.002 8.157 8.157 pw_transfer 1439 11.6 0.096 0.096 8.121 8.121 fft_wrap_pw1pw2 1201 12.6 0.011 0.011 7.804 7.804 ot_diis_step 108 11.5 0.006 0.006 7.675 7.675 make_images 4572 14.5 2.680 2.680 7.268 7.268 cp_fm_cholesky_decompose 22 10.9 6.927 6.927 6.927 6.927 build_core_hamiltonian_matrix_ 11 4.9 0.001 0.001 6.671 6.671 qs_ot_get_p 119 10.4 0.001 0.001 6.661 6.661 fft_wrap_pw1pw2_140 487 13.2 0.816 0.816 6.648 6.648 dbcsr_make_dense_low 5837 15.5 0.100 0.100 6.551 6.551 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 6.461 6.461 apply_single 119 13.6 0.001 0.001 6.461 6.461 make_dense_data 5837 16.5 5.718 5.718 6.428 6.428 dbcsr_complete_redistribute 329 12.2 2.970 2.970 6.219 6.219 multiply_cannon 2286 13.5 1.168 1.168 6.160 6.160 qs_env_update_s_mstruct 11 6.9 0.000 0.000 6.033 6.033 dbcsr_make_images_dense 3978 14.8 0.027 0.027 5.903 5.903 qs_create_task_list 11 7.9 0.000 0.000 5.500 5.500 generate_qs_task_list 11 8.9 3.763 3.763 5.500 5.500 copy_dbcsr_to_fm 153 11.3 0.004 0.004 5.090 5.090 qs_ot_p2m_diag 50 11.0 0.229 0.229 5.034 5.034 dbcsr_copy 2102 12.0 0.290 0.290 5.021 5.021 density_rs2pw 119 9.7 0.006 0.006 4.818 4.818 pw_poisson_solve 119 10.3 2.093 2.093 4.760 4.760 dbcsr_copy_into_existing 22 7.9 4.682 4.682 4.682 4.682 cp_dbcsr_syevd 50 12.0 0.004 0.004 4.437 4.437 multiply_cannon_loop 2286 14.5 0.059 0.059 4.383 4.383 multiply_cannon_multrec 2286 15.5 4.251 4.251 4.322 4.322 cp_fm_diag_elpa 50 13.0 0.000 0.000 4.266 4.266 cp_fm_diag_elpa_base 50 14.0 4.209 4.209 4.265 4.265 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 4.239 4.239 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 4.040 4.040 build_core_hamiltonian_matrix 11 6.9 0.001 0.001 3.993 3.993 qs_energies_compute_matrix_w 11 5.9 0.000 0.000 3.504 3.504 calculate_w_matrix_ot 11 6.9 0.008 0.008 3.504 3.504 fft3d_s 1202 14.6 3.431 3.431 3.437 3.437 copy_fm_to_dbcsr 176 11.2 0.002 0.002 3.258 3.258 ------------------------------------------------------------------------------- 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 0.014 0.017 73.782 73.783 qs_mol_dyn_low 1 2.0 0.005 0.007 73.647 73.654 qs_forces 11 3.9 0.002 0.002 73.592 73.592 qs_energies 11 4.9 0.001 0.002 68.600 68.602 scf_env_do_scf 11 5.9 0.001 0.001 62.427 62.429 scf_env_do_scf_inner_loop 108 6.5 0.003 0.011 57.885 57.885 velocity_verlet 10 3.0 0.002 0.003 43.865 43.867 rebuild_ks_matrix 119 8.3 0.001 0.001 28.634 28.689 qs_ks_build_kohn_sham_matrix 119 9.3 0.022 0.024 28.633 28.688 qs_ks_update_qs_env 119 7.6 0.001 0.001 25.456 25.508 qs_rho_update_rho 119 7.7 0.001 0.001 22.555 22.574 calculate_rho_elec 119 8.7 0.048 0.050 22.554 22.574 sum_up_and_integrate 119 10.3 0.050 0.054 22.381 22.410 integrate_v_rspace 119 11.3 0.005 0.005 22.331 22.357 dbcsr_multiply_generic 2286 12.5 0.134 0.138 17.674 17.781 grid_collocate_task_list 119 9.7 15.943 16.524 15.943 16.524 grid_integrate_task_list 119 12.3 15.817 16.186 15.817 16.186 qs_scf_new_mos 108 7.5 0.001 0.001 14.505 14.575 qs_scf_loop_do_ot 108 8.5 0.001 0.001 14.504 14.574 ot_scf_mini 108 9.5 0.003 0.004 13.602 13.664 multiply_cannon 2286 13.5 0.231 0.238 11.776 12.129 multiply_cannon_loop 2286 14.5 0.227 0.244 10.621 10.880 mp_waitall_1 169478 16.3 8.898 9.161 8.898 9.161 ot_mini 108 10.5 0.001 0.001 8.042 8.108 rs_pw_transfer 974 11.9 0.017 0.018 6.966 7.803 density_rs2pw 119 9.7 0.009 0.009 6.002 6.838 multiply_cannon_metrocomm3 18288 15.5 0.083 0.091 5.780 6.099 pw_transfer 1439 11.6 0.155 0.167 5.988 6.052 fft_wrap_pw1pw2 1201 12.6 0.014 0.016 5.669 5.745 potential_pw2rs 119 12.3 0.010 0.011 5.285 5.293 fft_wrap_pw1pw2_140 487 13.2 0.566 0.599 4.891 5.082 init_scf_loop 11 6.9 0.000 0.001 4.525 4.526 fft3d_ps 1201 14.6 2.314 2.461 4.220 4.298 init_scf_run 11 5.9 0.000 0.002 4.240 4.241 scf_env_initial_rho_setup 11 6.9 0.001 0.001 4.240 4.240 qs_ot_get_derivative 108 11.5 0.001 0.002 3.990 4.050 make_m2s 4572 13.5 0.077 0.079 3.967 4.024 ot_diis_step 108 11.5 0.005 0.005 4.014 4.015 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 3.937 3.991 apply_single 119 13.6 0.001 0.001 3.936 3.990 wfi_extrapolate 11 7.9 0.001 0.001 3.852 3.852 multiply_cannon_multrec 18288 15.5 3.609 3.748 3.627 3.767 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 3.397 3.404 make_images 4572 14.5 0.188 0.194 3.260 3.319 mp_waitany 9880 13.7 2.439 3.261 2.439 3.261 rs_pw_transfer_RS2PW_140 130 11.5 0.515 0.540 2.173 3.025 rs_pw_transfer_PW2RS_140 130 13.9 1.255 1.316 2.623 2.651 mp_alltoall_d11v 2130 13.8 1.522 2.140 1.522 2.140 qs_ot_get_p 119 10.4 0.001 0.001 1.914 2.002 rs_gather_matrices 119 12.3 0.136 0.146 1.176 1.840 make_images_data 4572 15.5 0.063 0.069 1.483 1.588 prepare_preconditioner 11 7.9 0.000 0.000 1.553 1.563 make_preconditioner 11 8.9 0.000 0.000 1.553 1.562 build_core_hamiltonian_matrix_ 11 4.9 0.001 0.001 1.446 1.546 ------------------------------------------------------------------------------- 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=79.43400000000003, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=22.909, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=19.566, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=17.806, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_gemm_cosma", label="cp_gemm_cosma", y=10.354, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=6.927, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=4.251, 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=27.076, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=15.943, 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=15.817, 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=3.609, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=8.898, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitany", label="mp_waitany", y=2.439, 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 0.032 0.032 213.075 213.075 qs_mol_dyn_low 1 2.0 0.004 0.004 212.252 212.252 qs_forces 11 3.9 0.002 0.002 212.196 212.196 qs_energies 11 4.9 0.001 0.001 198.510 198.510 scf_env_do_scf 11 5.9 0.001 0.001 166.765 166.765 velocity_verlet 10 3.0 0.002 0.002 142.392 142.392 scf_env_do_scf_inner_loop 96 6.5 0.009 0.009 123.379 123.379 rebuild_ks_matrix 107 8.3 0.001 0.001 62.053 62.053 qs_ks_build_kohn_sham_matrix 107 9.3 0.017 0.017 62.052 62.052 qs_ks_update_qs_env 107 7.6 0.001 0.001 55.949 55.949 qs_rho_update_rho 107 7.7 0.001 0.001 55.409 55.409 calculate_rho_elec 107 8.7 1.402 1.402 55.408 55.408 sum_up_and_integrate 107 10.3 0.342 0.342 51.235 51.235 integrate_v_rspace 107 11.3 0.419 0.419 50.892 50.892 grid_collocate_task_list 107 9.7 49.857 49.857 49.857 49.857 grid_integrate_task_list 107 12.3 48.195 48.195 48.195 48.195 init_scf_loop 11 6.9 0.000 0.000 43.165 43.165 prepare_preconditioner 11 7.9 0.000 0.000 35.808 35.808 make_preconditioner 11 8.9 0.000 0.000 35.808 35.808 make_full_inverse_cholesky 11 9.9 0.000 0.000 33.764 33.764 qs_scf_new_mos 96 7.5 0.001 0.001 24.507 24.507 qs_scf_loop_do_ot 96 8.5 0.001 0.001 24.506 24.506 ot_scf_mini 96 9.5 0.003 0.003 22.900 22.900 dbcsr_multiply_generic 1966 12.4 0.157 0.157 20.512 20.512 cp_fm_cholesky_invert 11 10.9 20.304 20.304 20.304 20.304 init_scf_run 11 5.9 0.001 0.001 16.176 16.176 scf_env_initial_rho_setup 11 6.9 0.001 0.001 16.175 16.175 wfi_extrapolate 11 7.9 0.001 0.001 15.100 15.100 ot_mini 96 10.5 0.001 0.001 13.501 13.501 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 11.756 11.756 make_m2s 3932 13.4 0.058 0.058 11.464 11.464 cp_gemm 81 9.0 0.000 0.000 10.446 10.446 cp_gemm_cosma 81 10.0 10.446 10.446 10.446 10.446 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 7.733 7.733 qs_ot_get_derivative 96 11.5 0.001 0.001 7.342 7.342 qs_env_update_s_mstruct 11 6.9 0.000 0.000 7.224 7.224 cp_fm_cholesky_decompose 22 10.9 7.108 7.108 7.108 7.108 pw_transfer 1295 11.6 0.086 0.086 7.082 7.082 fft_wrap_pw1pw2 1081 12.6 0.009 0.009 6.802 6.802 qs_create_task_list 11 7.9 0.000 0.000 6.681 6.681 generate_qs_task_list 11 8.9 4.967 4.967 6.681 6.681 dbcsr_complete_redistribute 317 12.2 3.024 3.024 6.475 6.475 make_images 3932 14.4 2.302 2.302 6.224 6.224 ot_diis_step 96 11.5 0.005 0.005 6.155 6.155 build_core_hamiltonian_matrix_ 11 4.9 0.001 0.001 5.950 5.950 qs_ot_get_p 107 10.4 0.001 0.001 5.929 5.929 fft_wrap_pw1pw2_140 439 13.2 0.608 0.608 5.765 5.765 dbcsr_make_dense_low 4961 15.5 0.088 0.088 5.406 5.406 make_dense_data 4961 16.5 4.706 4.706 5.298 5.298 copy_dbcsr_to_fm 147 11.2 0.004 0.004 5.289 5.289 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 5.258 5.258 apply_single 107 13.6 0.000 0.000 5.258 5.258 dbcsr_copy 1855 11.9 0.264 0.264 5.253 5.253 multiply_cannon 1966 13.4 0.749 0.749 5.094 5.094 dbcsr_copy_into_existing 22 7.9 4.944 4.944 4.945 4.945 dbcsr_make_images_dense 3386 14.7 0.023 0.023 4.824 4.824 qs_ot_p2m_diag 44 11.0 0.193 0.193 4.559 4.559 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 4.358 4.358 ------------------------------------------------------------------------------- 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 0.011 128.414 128.415 qs_mol_dyn_low 1 2.0 0.005 0.005 128.294 128.300 qs_forces 11 3.9 0.002 0.002 128.240 128.240 qs_energies 11 4.9 0.001 0.001 119.511 119.513 scf_env_do_scf 11 5.9 0.001 0.001 110.379 110.380 scf_env_do_scf_inner_loop 96 6.5 0.003 0.010 102.570 102.570 velocity_verlet 10 3.0 0.002 0.002 76.396 76.398 rebuild_ks_matrix 107 8.3 0.001 0.001 58.693 58.743 qs_ks_build_kohn_sham_matrix 107 9.3 0.019 0.021 58.692 58.743 sum_up_and_integrate 107 10.3 0.041 0.046 53.198 53.260 integrate_v_rspace 107 11.3 0.004 0.005 53.156 53.221 qs_ks_update_qs_env 107 7.6 0.001 0.001 51.758 51.800 qs_rho_update_rho 107 7.7 0.001 0.001 49.507 49.525 calculate_rho_elec 107 8.7 0.043 0.045 49.506 49.524 grid_integrate_task_list 107 12.3 46.302 47.984 46.302 47.984 grid_collocate_task_list 107 9.7 42.862 44.354 42.862 44.354 dbcsr_multiply_generic 1966 12.4 0.115 0.120 15.189 15.636 qs_scf_new_mos 96 7.5 0.001 0.001 12.315 12.355 qs_scf_loop_do_ot 96 8.5 0.001 0.001 12.314 12.354 ot_scf_mini 96 9.5 0.003 0.003 11.538 11.574 multiply_cannon 1966 13.4 0.201 0.206 10.045 10.232 multiply_cannon_loop 1966 14.4 0.194 0.212 9.062 9.342 rs_pw_transfer 878 11.9 0.015 0.016 7.096 8.164 mp_waitall_1 146670 16.2 7.561 7.891 7.561 7.891 init_scf_loop 11 6.9 0.000 0.001 7.790 7.791 density_rs2pw 107 9.7 0.008 0.008 6.102 7.230 init_scf_run 11 5.9 0.000 0.002 7.171 7.172 scf_env_initial_rho_setup 11 6.9 0.000 0.001 7.171 7.172 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 7.136 7.148 ot_mini 96 10.5 0.001 0.001 6.814 6.853 wfi_extrapolate 11 7.9 0.001 0.001 6.564 6.564 pw_transfer 1295 11.6 0.138 0.146 5.246 5.319 multiply_cannon_metrocomm3 15728 15.4 0.071 0.075 4.846 5.236 fft_wrap_pw1pw2 1081 12.6 0.013 0.014 4.969 5.034 potential_pw2rs 107 12.3 0.009 0.009 4.730 4.737 fft_wrap_pw1pw2_140 439 13.2 0.500 0.514 4.279 4.445 mp_waitany 8968 13.7 3.098 4.229 3.098 4.229 rs_pw_transfer_RS2PW_140 118 11.5 0.405 0.424 2.768 3.835 mp_alltoall_d11v 1998 13.7 2.392 3.775 2.392 3.775 fft3d_ps 1081 14.6 2.011 2.120 3.682 3.753 make_m2s 3932 13.4 0.066 0.068 3.499 3.548 rs_gather_matrices 107 12.3 0.121 0.133 2.071 3.451 qs_ot_get_derivative 96 11.5 0.001 0.001 3.413 3.448 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 3.348 3.389 apply_single 107 13.6 0.001 0.001 3.347 3.389 ot_diis_step 96 11.5 0.004 0.005 3.364 3.365 multiply_cannon_multrec 15728 15.4 3.154 3.280 3.169 3.296 make_images 3932 14.4 0.164 0.169 2.893 2.953 ------------------------------------------------------------------------------- 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=77.16499999999999, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=49.857, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=48.195, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=20.304, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_gemm_cosma", label="cp_gemm_cosma", y=10.446, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=7.108, 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 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", 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=25.436999999999983, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=42.862, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=46.302, 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="mp_waitany", label="mp_waitany", y=3.098, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=7.561, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=3.154, 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 0.343 0.343 254.234 254.234 qs_energies 1 2.0 0.000 0.000 252.999 252.999 scf_env_do_scf 1 3.0 0.000 0.000 250.623 250.623 qs_ks_update_qs_env 8 5.0 0.000 0.000 232.937 232.937 rebuild_ks_matrix 7 6.0 0.000 0.000 232.827 232.827 qs_ks_build_kohn_sham_matrix 7 7.0 0.002 0.002 232.827 232.827 hfx_ks_matrix 7 8.0 0.000 0.000 169.076 169.076 integrate_four_center 7 9.0 2.055 2.055 169.045 169.045 integrate_four_center_main 7 10.0 1.312 1.312 157.759 157.759 integrate_four_center_bin 449 11.0 156.447 156.447 156.447 156.447 scf_env_do_scf_inner_loop 7 4.0 0.001 0.001 143.786 143.786 init_scf_loop 1 4.0 0.000 0.000 106.823 106.823 cp_gemm 129 10.3 0.001 0.001 48.332 48.332 cp_gemm_cosma 129 11.3 48.331 48.331 48.331 48.331 admm_mo_calc_rho_aux 7 8.0 0.000 0.000 30.187 30.187 admm_fit_mo_coeffs 7 9.0 0.000 0.000 28.469 28.469 admm_mo_merge_derivs 7 8.0 0.000 0.000 24.427 24.427 merge_mo_derivs_diag 7 9.0 0.025 0.025 24.427 24.427 purify_mo_diag 7 10.0 0.001 0.001 15.814 15.814 prepare_preconditioner 1 5.0 0.000 0.000 13.724 13.724 make_preconditioner 1 6.0 0.000 0.000 13.724 13.724 fit_mo_coeffs 7 10.0 0.000 0.000 12.655 12.655 integrate_four_center_load 7 10.0 0.001 0.001 8.849 8.849 hfx_load_balance 1 11.0 0.002 0.002 8.848 8.848 arnoldi_normal_ev 11 9.3 0.002 0.002 8.322 8.322 estimate_cond_num 1 7.0 0.000 0.000 8.244 8.244 build_subspace 28 9.5 0.014 0.014 8.214 8.214 qs_vxc_create 14 8.0 0.000 0.000 5.383 5.383 xc_vxc_pw_create 14 9.0 0.967 0.967 5.382 5.382 ------------------------------------------------------------------------------- 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 0.200 0.207 183.656 183.657 qs_energies 1 2.0 0.000 0.000 183.317 183.318 scf_env_do_scf 1 3.0 0.000 0.000 182.738 182.738 qs_ks_update_qs_env 8 5.0 0.000 0.000 179.679 179.680 rebuild_ks_matrix 7 6.0 0.000 0.000 179.666 179.666 qs_ks_build_kohn_sham_matrix 7 7.0 0.002 0.002 179.666 179.666 hfx_ks_matrix 7 8.0 0.000 0.001 168.942 168.943 integrate_four_center 7 9.0 0.094 0.405 168.926 168.926 integrate_four_center_main 7 10.0 0.004 0.005 156.015 158.881 integrate_four_center_bin 448 11.0 156.011 158.877 156.011 158.877 scf_env_do_scf_inner_loop 7 4.0 0.000 0.001 106.856 106.857 init_scf_loop 1 4.0 0.000 0.000 75.880 75.880 integrate_four_center_load 7 10.0 0.000 0.001 8.884 8.888 hfx_load_balance 1 11.0 0.001 0.001 8.884 8.888 mp_sync 70 11.3 3.193 5.552 3.193 5.552 hfx_load_balance_count 1 12.0 4.325 4.450 4.325 4.450 hfx_load_balance_bin 1 12.0 4.336 4.426 4.336 4.426 qs_vxc_create 14 8.0 0.001 0.001 3.679 3.679 xc_vxc_pw_create 14 9.0 0.020 0.021 3.679 3.679 ------------------------------------------------------------------------------- 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=44.77899999999997, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_bin", label="integrate_four_center_bin", y=156.447, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="cp_gemm_cosma", label="cp_gemm_cosma", y=48.331, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center", label="integrate_four_center", y=2.055, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_main", label="integrate_four_center_main", y=1.312, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="xc_vxc_pw_create", label="xc_vxc_pw_create", y=0.967, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="CP2K", label="CP2K", y=0.343, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=0.0, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_count", label="hfx_load_balance_count", y=0.0, 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=15.473000000000013, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center_bin", label="integrate_four_center_bin", y=156.011, 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="integrate_four_center", label="integrate_four_center", y=0.094, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center_main", label="integrate_four_center_main", y=0.004, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="xc_vxc_pw_create", label="xc_vxc_pw_create", y=0.02, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="CP2K", label="CP2K", y=0.2, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=4.336, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_count", label="hfx_load_balance_count", y=4.325, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="mp_sync", label="mp_sync", y=3.193, 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 0.015 0.015 373.203 373.203 qs_energies 1 2.0 0.000 0.000 372.652 372.652 mp2_main 1 3.0 0.000 0.000 366.162 366.162 mp2_gpw_main 1 4.0 0.000 0.000 365.675 365.675 rpa_ri_compute_en 1 5.0 0.000 0.000 351.034 351.034 rpa_num_int 1 6.0 0.001 0.001 351.009 351.009 compute_mat_P_omega 1 7.0 0.002 0.002 223.947 223.947 compute_mat_P_omega_contract 10 8.0 13.025 13.025 222.753 222.753 dbcsr_t_total 2336 9.6 0.015 0.015 212.342 212.342 dbcsr_t_contract 787 11.0 47.872 47.872 138.798 138.798 cp_gemm 105 8.4 0.000 0.000 95.536 95.536 cp_gemm_cosma 105 9.4 95.536 95.536 95.536 95.536 compute_mat_P_omega_calc_M_occ 250 9.0 13.096 13.096 87.013 87.013 dbcsr_tas_total 1149 12.2 0.050 0.050 85.053 85.053 dbcsr_tas_multiply 807 12.1 0.003 0.003 83.534 83.534 dbcsr_t_copy 1103 10.7 20.320 20.320 72.002 72.002 GW_matrix_operations 10 7.0 0.006 0.006 71.585 71.585 dbcsr_multiply_generic 837 15.8 0.135 0.135 69.812 69.812 dbcsr_tas_dbcsr 807 14.1 0.003 0.003 69.398 69.398 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 58.460 58.460 dbcsr_tas_mm_1N 524 15.1 0.002 0.002 56.756 56.756 multiply_cannon 837 16.8 24.326 24.326 56.019 56.019 rpa_num_int_RPA_matrix_operati 10 7.0 0.000 0.000 33.483 33.483 contract_P_omega_with_mat_L 10 8.0 0.000 0.000 31.629 31.629 multiply_cannon_loop 837 17.8 0.159 0.159 28.941 28.941 multiply_cannon_multrec 837 18.8 27.326 27.326 27.849 27.849 dbcsr_tas_reserve_blocks_index 3261 13.7 7.261 7.261 27.105 27.105 dbcsr_tas_copy 574 11.4 16.920 16.920 24.486 24.486 dbcsr_t_reserve_blocks_index 2280 12.5 1.273 1.273 20.799 20.799 dbcsr_t_reserve_blocks_index_a 2222 11.6 0.011 0.011 20.490 20.490 compute_mat_P_omega_copy_M_occ 250 9.0 0.002 0.002 19.576 19.576 dbcsr_reserve_blocks 3717 14.7 19.152 19.152 19.540 19.540 compute_QP_energies 1 7.0 0.000 0.000 19.230 19.230 compute_self_energy_cubic_gw 1 8.0 0.100 0.100 19.230 19.230 mp2_ri_gpw_compute_in 1 5.0 0.001 0.001 14.625 14.625 compute_mat_P_omega_copy_M_vir 250 9.0 0.002 0.002 14.420 14.420 dbcsr_t_copy_nocomm 251 12.0 11.298 11.298 13.683 13.683 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 12.364 12.364 make_m2s 1674 16.8 0.106 0.106 11.198 11.198 make_images 1674 17.8 5.216 5.216 10.616 10.616 dbcsr_tas_mm_2 251 15.0 0.001 0.001 10.548 10.548 cp_fm_cholesky_invert 10 8.0 9.546 9.546 9.546 9.546 dbcsr_finalize 9888 13.6 1.535 1.535 8.147 8.147 contract_cubic_gw 21 9.0 0.000 0.000 7.924 7.924 mp2_ri_gpw_compute_in_copy_3c 6 6.0 0.687 0.687 7.587 7.587 ------------------------------------------------------------------------------- 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 0.006 0.009 57.798 57.799 qs_energies 1 2.0 0.001 0.001 57.680 57.687 mp2_main 1 3.0 0.001 0.001 56.207 56.214 mp2_gpw_main 1 4.0 0.000 0.001 56.142 56.149 rpa_ri_compute_en 1 5.0 0.000 0.000 54.167 54.174 rpa_num_int 1 6.0 0.000 0.000 54.159 54.166 dbcsr_t_total 2336 9.6 0.016 0.017 43.148 43.149 compute_mat_P_omega 1 7.0 0.001 0.002 42.065 42.076 compute_mat_P_omega_contract 10 8.0 0.790 0.820 41.836 41.841 dbcsr_t_contract 787 11.0 1.918 2.073 31.764 31.768 dbcsr_tas_total 1149 12.2 0.066 0.071 27.930 27.931 dbcsr_tas_multiply 807 12.1 0.003 0.003 27.794 27.796 dbcsr_tas_dbcsr 807 14.1 0.003 0.004 20.208 20.209 dbcsr_multiply_generic 837 15.8 0.072 0.076 16.938 17.919 compute_mat_P_omega_calc_M_occ 250 9.0 0.768 0.794 14.068 14.068 multiply_cannon 837 16.8 0.137 0.153 9.911 10.282 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 10.204 10.204 dbcsr_t_copy 1111 10.7 4.355 4.560 9.734 10.040 dbcsr_tas_mm_1N 524 15.1 0.003 0.003 9.003 9.849 multiply_cannon_loop 837 17.8 0.044 0.048 9.009 9.409 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.002 8.940 8.940 dbcsr_tas_mm_2 251 15.0 0.002 0.002 7.682 7.682 multiply_cannon_multrec 1386 17.8 7.002 7.427 7.259 7.675 mp_sync 8696 11.6 6.531 7.522 6.531 7.522 cp_gemm 105 8.4 0.000 0.000 7.147 7.157 cp_gemm_cosma 105 9.4 7.146 7.157 7.146 7.157 make_m2s 1674 16.8 0.045 0.049 6.045 6.707 make_images 1674 17.8 0.249 0.265 5.960 6.621 GW_matrix_operations 10 7.0 0.001 0.002 4.696 4.705 compute_QP_energies 1 7.0 0.000 0.001 4.323 4.323 compute_self_energy_cubic_gw 1 8.0 0.005 0.006 4.321 4.323 dbcsr_t_communicate_buffer 1098 11.7 0.095 0.101 3.563 3.708 mp_waitall_2 3776 14.7 3.334 3.574 3.334 3.574 make_images_data 1674 18.8 0.038 0.040 3.205 3.339 contract_cubic_gw 21 9.0 0.000 0.000 3.282 3.282 hybrid_alltoall_any 1724 19.5 2.481 2.809 3.080 3.228 dbcsr_t_reserve_blocks_index_a 2791 11.4 0.018 0.019 2.782 3.164 dbcsr_t_reserve_blocks_index 2849 12.4 0.108 0.116 2.777 3.162 dbcsr_tas_reserve_blocks_index 3300 13.8 0.273 0.297 2.729 3.113 make_images_pack 1674 18.8 2.289 2.941 2.304 2.955 dbcsr_reserve_blocks 3785 14.7 2.449 2.815 2.489 2.857 rpa_num_int_RPA_matrix_operati 10 7.0 0.000 0.000 2.686 2.695 contract_P_omega_with_mat_L 10 8.0 0.000 0.000 2.557 2.565 convert_to_new_pgrid 2421 14.1 0.018 0.021 1.923 2.065 dbcsr_copy 3323 15.8 1.855 2.001 1.885 2.032 mp2_ri_gpw_compute_in 1 5.0 0.001 0.001 1.973 1.973 mp_waitall_1 26582 19.0 1.609 1.967 1.609 1.967 compute_mat_P_omega_copy_M_vir 250 9.0 0.002 0.002 1.762 1.768 dbcsr_add_anytype 909 13.7 1.023 1.076 1.606 1.670 compute_mat_P_omega_copy_M_occ 250 9.0 0.001 0.002 1.560 1.563 dbcsr_tas_replicate 396 14.1 0.816 0.889 1.391 1.453 scf_env_do_scf 1 3.0 0.000 0.000 1.420 1.420 scf_env_do_scf_inner_loop 17 4.0 0.001 0.001 1.419 1.420 mp_max_i 2058 9.6 1.010 1.277 1.010 1.277 dbcsr_finalize 10566 13.5 0.046 0.049 1.106 1.157 ------------------------------------------------------------------------------- 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=157.82299999999998, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="cp_gemm_cosma", label="cp_gemm_cosma", y=95.536, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbcsr_t_contract", label="dbcsr_t_contract", y=47.872, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=27.326, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="multiply_cannon", label="multiply_cannon", y=24.326, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbcsr_t_copy", label="dbcsr_t_copy", y=20.32, 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=27.375000000000004, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="cp_gemm_cosma", label="cp_gemm_cosma", y=7.146, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbcsr_t_contract", label="dbcsr_t_contract", y=1.918, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=7.002, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="multiply_cannon", label="multiply_cannon", y=0.137, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbcsr_t_copy", label="dbcsr_t_copy", y=4.355, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_sync", label="mp_sync", y=6.531, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=3.334, 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 0.021 0.021 845.758 845.758 qs_forces 1 2.0 0.000 0.000 844.880 844.880 rebuild_ks_matrix 7 6.6 0.000 0.000 835.378 835.378 qs_ks_build_kohn_sham_matrix 7 7.6 0.002 0.002 835.378 835.378 hfx_ks_matrix 7 8.6 0.000 0.000 832.360 832.360 dbcsr_t_total 1342 10.2 0.010 0.010 709.023 709.023 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 506.591 506.591 hfx_ri_update_forces 1 7.0 0.029 0.029 459.515 459.515 dbcsr_t_contract 445 11.1 173.468 173.468 421.568 421.568 hfx_ri_update_ks 7 9.6 0.000 0.000 372.839 372.839 hfx_ri_update_ks_Pmat 7 10.6 65.330 65.330 372.834 372.834 qs_energies 1 3.0 0.000 0.000 338.211 338.211 scf_env_do_scf 1 4.0 0.000 0.000 337.796 337.796 qs_ks_update_qs_env 8 6.0 0.000 0.000 328.793 328.793 dbcsr_t_copy 441 11.6 97.523 97.523 276.067 276.067 scf_env_do_scf_inner_loop 6 5.0 0.001 0.001 197.406 197.406 dbcsr_tas_total 805 12.2 0.062 0.062 187.261 187.261 dbcsr_tas_reserve_blocks_index 2010 14.3 18.737 18.737 176.163 176.163 dbcsr_tas_multiply 456 12.2 0.002 0.002 175.888 175.888 dbcsr_reserve_blocks 2452 14.9 155.205 155.205 156.077 156.077 init_scf_loop 2 5.0 0.000 0.000 140.386 140.386 dbcsr_multiply_generic 611 14.8 0.109 0.109 139.395 139.395 dbcsr_t_reserve_blocks_index 1344 13.2 3.311 3.311 138.970 138.970 dbcsr_tas_dbcsr 456 14.2 0.002 0.002 138.595 138.595 dbcsr_t_reserve_blocks_index_a 1323 12.2 0.011 0.011 137.570 137.570 hfx_ri_update_ks_Pmat_KS 63 11.6 0.001 0.001 103.109 103.109 multiply_cannon 611 15.8 6.674 6.674 97.856 97.856 multiply_cannon_loop 611 16.8 0.145 0.145 87.496 87.496 multiply_cannon_multrec 611 17.8 85.461 85.461 85.581 85.581 precalc_derivatives 1 8.0 0.008 0.008 74.246 74.246 hfx_ri_forces_Pmat_2c_inv_2 9 8.0 0.000 0.000 74.162 74.162 hfx_ri_forces_Pmat_metric 9 8.0 0.001 0.001 73.655 73.655 hfx_ri_forces_Pmat_3c_RI 9 8.0 0.001 0.001 70.213 70.213 dbcsr_tas_copy 290 12.3 29.320 29.320 69.623 69.623 dbcsr_tas_mm_3N 94 14.7 0.000 0.000 61.869 61.869 hfx_ri_forces_Pmat_3c_AO 9 8.0 0.000 0.000 59.814 59.814 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 57.126 57.126 dbcsr_tas_mm_2 283 14.9 0.002 0.002 51.555 51.555 hfx_ri_update_ks_Pmat_copy_2 63 11.6 0.000 0.000 48.998 48.998 hfx_ri_forces_Pmat_PQ_der 9 8.0 1.543 1.543 39.773 39.773 build_3c_derivatives 2 9.0 1.744 1.744 38.583 38.583 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 37.606 37.606 dbcsr_data_release 96260 17.1 33.444 33.444 33.444 33.444 hfx_ri_forces_Pmat_2c_inv_1 1 8.0 4.597 4.597 32.709 32.709 make_m2s 1222 15.8 0.117 0.117 31.628 31.628 make_images 1222 16.8 12.066 12.066 30.770 30.770 dbcsr_t_split_blocks_generic 138 11.8 16.434 16.434 28.930 28.930 dbcsr_t_split_copyback 69 11.8 18.556 18.556 27.885 27.885 dbcsr_tas_mm_3T 77 17.1 0.000 0.000 25.019 25.019 dbcsr_destroy 11406 14.4 0.055 0.055 24.603 24.603 hfx_ri_forces_Pmat_Pmat_2 9 8.0 0.000 0.000 23.741 23.741 dbcsr_t_communicate_buffer 151 13.0 21.052 21.052 21.052 21.052 ------------------------------------------------------------------------------- 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 0.011 0.014 124.054 124.055 qs_forces 1 2.0 0.000 0.000 123.882 123.882 rebuild_ks_matrix 7 6.6 0.000 0.000 122.750 122.751 qs_ks_build_kohn_sham_matrix 7 7.6 0.002 0.003 122.750 122.751 hfx_ks_matrix 7 8.6 0.001 0.001 121.076 121.076 dbcsr_t_total 1342 10.2 0.011 0.013 112.906 112.907 dbcsr_t_contract 445 11.1 7.416 7.877 89.050 89.059 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 88.865 88.866 hfx_ri_update_forces 1 7.0 0.003 0.003 84.259 84.259 dbcsr_tas_total 805 12.2 0.065 0.069 81.531 81.531 dbcsr_tas_multiply 456 12.2 0.002 0.002 75.872 75.874 dbcsr_tas_dbcsr 456 14.2 0.002 0.002 56.798 56.799 dbcsr_multiply_generic 611 14.8 0.051 0.056 51.682 53.739 hfx_ri_update_ks 7 9.6 0.000 0.000 36.816 36.816 hfx_ri_update_ks_Pmat 7 10.6 2.616 2.781 36.814 36.814 multiply_cannon 611 15.8 0.097 0.106 32.880 35.295 qs_energies 1 3.0 0.000 0.000 35.000 35.000 scf_env_do_scf 1 4.0 0.000 0.000 34.789 34.789 multiply_cannon_loop 611 16.8 0.051 0.055 31.529 33.920 qs_ks_update_qs_env 8 6.0 0.000 0.000 33.886 33.887 dbcsr_tas_mm_2 283 14.9 0.002 0.003 29.809 29.810 multiply_cannon_multrec 1893 15.6 25.771 28.711 26.122 29.034 hfx_ri_forces_Pmat_metric 9 8.0 0.001 0.001 23.572 23.572 scf_env_do_scf_inner_loop 6 5.0 0.000 0.001 19.509 19.509 dbcsr_t_copy 469 11.6 6.261 6.511 17.696 18.067 dbcsr_tas_mm_3N 94 14.7 0.000 0.001 16.354 17.397 make_m2s 1222 15.8 0.042 0.045 15.359 16.438 make_images 1222 16.8 0.325 0.350 15.260 16.338 hfx_ri_forces_Pmat_2c_inv_2 9 8.0 0.000 0.001 15.364 15.364 init_scf_loop 2 5.0 0.000 0.000 15.279 15.279 hfx_ri_update_ks_Pmat_KS 63 11.6 0.001 0.001 14.380 14.380 mp_sync 5251 12.1 10.400 14.087 10.400 14.087 hfx_ri_forces_Pmat_3c_RI 9 8.0 0.001 0.001 12.369 12.369 hfx_ri_forces_Pmat_PQ_der 9 8.0 0.073 0.078 9.799 9.799 make_images_data 1222 17.8 0.032 0.034 8.388 8.869 hybrid_alltoall_any 1272 18.5 6.785 7.815 8.209 8.658 mp_waitall_2 1948 15.2 7.593 8.510 7.593 8.510 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 8.507 8.507 dbcsr_tas_mm_3T 77 17.1 0.000 0.001 7.557 8.001 dbcsr_tas_reserve_blocks_index 2058 14.4 0.671 0.757 7.175 7.906 dbcsr_reserve_blocks 2505 15.0 7.001 7.683 7.045 7.729 make_images_pack 1222 17.8 6.255 6.834 6.269 6.848 mp_sum_l 13555 13.9 5.145 6.810 5.145 6.810 dbcsr_t_reserve_blocks_index 1523 13.2 0.176 0.191 6.140 6.720 dbcsr_t_reserve_blocks_index_a 1502 12.2 0.015 0.016 6.102 6.679 mp_waitall_1 24260 17.6 5.031 6.644 5.031 6.644 dbcsr_tas_replicate 359 14.0 1.680 3.093 5.855 6.241 precalc_derivatives 1 8.0 0.003 0.003 6.088 6.089 convert_to_new_pgrid 1368 14.2 0.020 0.021 5.058 5.549 dbcsr_copy 1981 15.7 4.965 5.463 4.984 5.481 hfx_ri_forces_Pmat_3c_AO 9 8.0 0.000 0.001 5.296 5.296 dbcsr_tas_communicate_buffer 728 14.9 0.033 0.036 4.552 5.273 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 4.929 4.929 hfx_ri_forces_Pmat_2c_inv_1 1 8.0 0.161 0.170 4.913 4.919 hfx_ri_forces_Pmat_Pmat_2 9 8.0 0.000 0.000 4.614 4.614 dbcsr_tas_replicate_communicat 127 15.0 0.004 0.005 3.305 3.955 dbcsr_multiply_generic_mpsum_f 445 17.1 0.002 0.002 2.267 3.783 dbcsr_t_communicate_buffer 330 12.4 0.023 0.024 3.484 3.665 build_3c_derivatives 2 9.0 0.612 0.658 3.441 3.447 multiply_cannon_metrocomm3 1893 15.6 0.006 0.007 1.961 3.222 dbcsr_tas_merge 232 12.1 1.664 1.788 2.724 2.927 dbcsr_tas_copy 144 13.2 1.372 1.445 2.521 2.680 hfx_ri_pre_scf_Pmat_RIx3C 9 13.0 0.000 0.000 2.597 2.609 ------------------------------------------------------------------------------- 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=268.77099999999996, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbcsr_t_contract", label="dbcsr_t_contract", y=173.468, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbcsr_reserve_blocks", label="dbcsr_reserve_blocks", y=155.205, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbcsr_t_copy", label="dbcsr_t_copy", y=97.523, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=85.461, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=65.33, 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=56.995999999999995, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbcsr_t_contract", label="dbcsr_t_contract", y=7.416, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbcsr_reserve_blocks", label="dbcsr_reserve_blocks", y=7.001, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbcsr_t_copy", label="dbcsr_t_copy", y=6.261, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=25.771, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=2.616, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=7.593, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_sync", label="mp_sync", y=10.4, 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 0.104 0.104 235.682 235.682 qs_energies 1 2.0 0.000 0.000 233.810 233.810 scf_env_do_scf 1 3.0 0.000 0.000 222.699 222.699 scf_env_do_scf_inner_loop 15 4.0 0.002 0.002 222.699 222.699 qs_scf_new_mos 15 5.0 0.001 0.001 104.904 104.904 eigensolver 15 6.0 0.002 0.002 89.548 89.548 qs_ks_update_qs_env 15 5.0 0.000 0.000 83.644 83.644 rebuild_ks_matrix 15 6.0 0.000 0.000 83.253 83.253 qs_ks_build_kohn_sham_matrix 15 7.0 0.003 0.003 83.253 83.253 cp_fm_diag_elpa 15 7.0 0.000 0.000 67.069 67.069 cp_fm_diag_elpa_base 15 8.0 62.101 62.101 67.069 67.069 qs_vxc_create 15 8.0 0.040 0.040 56.695 56.695 calculate_dispersion_nonloc 15 9.0 10.471 10.471 49.750 49.750 pw_transfer 1191 9.8 0.109 0.109 36.046 36.046 fft_wrap_pw1pw2 1086 10.9 0.014 0.014 35.661 35.661 fft_wrap_pw1pw2_150 765 12.0 4.790 4.790 27.330 27.330 qs_rho_update_rho 16 5.0 0.000 0.000 27.016 27.016 calculate_rho_elec 16 6.0 0.364 0.364 27.015 27.015 grid_collocate_task_list 16 7.0 24.944 24.944 24.944 24.944 sum_up_and_integrate 15 8.0 0.089 0.089 24.753 24.753 integrate_v_rspace 15 9.0 0.040 0.040 24.664 24.664 grid_integrate_task_list 15 10.0 23.678 23.678 23.678 23.678 cp_fm_cholesky_restore 45 7.0 17.697 17.697 17.697 17.697 fft3d_s 1087 12.8 16.230 16.230 16.244 16.244 pw_scatter_s 585 13.0 11.914 11.914 11.914 11.914 copy_dbcsr_to_fm 16 5.9 0.001 0.001 11.634 11.634 dbcsr_complete_redistribute 46 8.3 3.740 3.740 10.398 10.398 cp_fm_upper_to_full 30 8.0 9.748 9.748 9.748 9.748 vdW_energy 15 10.0 8.874 8.874 8.874 8.874 gspace_mixing 14 5.0 0.284 0.284 8.476 8.476 fft_wrap_pw1pw2_200 197 11.5 0.475 0.475 7.819 7.819 broyden_mixing 14 6.0 7.648 7.648 7.649 7.649 xc_vxc_pw_create 15 9.0 1.496 1.496 6.905 6.905 init_scf_run 1 3.0 0.000 0.000 5.038 5.038 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 4.799 4.799 ------------------------------------------------------------------------------- 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 0.014 0.020 90.943 90.944 qs_energies 1 2.0 0.000 0.000 90.544 90.544 scf_env_do_scf 1 3.0 0.000 0.000 85.312 85.312 scf_env_do_scf_inner_loop 15 4.0 0.002 0.003 85.312 85.312 qs_ks_update_qs_env 15 5.0 0.000 0.000 41.800 41.825 rebuild_ks_matrix 15 6.0 0.000 0.000 41.748 41.772 qs_ks_build_kohn_sham_matrix 15 7.0 0.004 0.005 41.748 41.772 sum_up_and_integrate 15 8.0 0.015 0.017 23.993 24.032 integrate_v_rspace 15 9.0 0.001 0.001 23.978 24.017 qs_rho_update_rho 16 5.0 0.000 0.000 23.680 23.682 calculate_rho_elec 16 6.0 0.012 0.013 23.679 23.682 grid_integrate_task_list 15 10.0 22.142 22.659 22.142 22.659 grid_collocate_task_list 16 7.0 21.679 22.302 21.679 22.302 qs_scf_new_mos 15 5.0 0.001 0.001 20.175 20.332 eigensolver 15 6.0 0.002 0.003 18.567 18.579 qs_vxc_create 15 8.0 0.001 0.001 17.170 17.184 calculate_dispersion_nonloc 15 9.0 1.446 1.593 14.028 14.049 pw_transfer 1191 9.8 0.140 0.147 13.421 13.545 cp_fm_diag_elpa 15 7.0 0.000 0.000 13.453 13.461 cp_fm_diag_elpa_base 15 8.0 13.172 13.203 13.447 13.451 fft_wrap_pw1pw2 1086 10.9 0.021 0.025 13.114 13.224 fft3d_ps 1086 12.9 5.663 5.878 10.025 10.266 fft_wrap_pw1pw2_150 765 12.0 0.699 0.747 8.906 8.954 cp_fm_cholesky_restore 45 7.0 4.861 4.920 4.861 4.920 fft_wrap_pw1pw2_200 197 11.5 0.386 0.412 4.034 4.117 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 3.264 3.264 mp_alltoall_z22v 1086 14.9 2.758 3.244 2.758 3.244 xc_vxc_pw_create 15 9.0 0.059 0.079 3.141 3.162 build_core_hamiltonian_matrix 1 4.0 0.000 0.000 2.809 3.090 x_to_yz 585 14.0 1.015 1.050 2.355 2.490 yz_to_x 501 13.7 0.554 0.594 1.972 2.289 vdW_energy 15 10.0 2.165 2.279 2.165 2.279 rs_pw_transfer 158 9.4 0.003 0.003 1.851 2.275 density_rs2pw 16 7.0 0.002 0.002 1.817 2.136 build_core_ppnl 1 5.0 1.871 2.064 1.871 2.064 ------------------------------------------------------------------------------- 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=91.03200000000001, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=62.101, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=24.944, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=23.678, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=17.697, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="fft3d_s", label="fft3d_s", y=16.23, 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=23.426000000000002, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=13.172, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=21.679, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=22.142, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=4.861, 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="fft3d_ps", label="fft3d_ps", y=5.663, 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 0.086 0.086 319.726 319.726 qs_energies 1 2.0 0.000 0.000 319.562 319.562 ls_scf 1 3.0 0.000 0.000 317.697 317.697 ls_scf_main 1 4.0 0.002 0.002 303.192 303.192 density_matrix_trs4 11 5.0 0.011 0.011 178.846 178.846 ls_scf_dm_to_ks 11 5.0 0.000 0.000 117.195 117.195 matrix_ls_to_qs 11 6.0 0.000 0.000 112.659 112.659 dbcsr_multiply_generic 185 6.1 0.477 0.477 111.319 111.319 multiply_cannon 185 7.1 2.891 2.891 75.837 75.837 dbcsr_copy_into_existing 11 7.0 59.804 59.804 59.804 59.804 dbcsr_complete_redistribute 23 7.5 41.945 41.945 57.974 57.974 multiply_cannon_loop 185 8.1 0.387 0.387 54.235 54.235 matrix_decluster 11 7.0 0.000 0.000 52.853 52.853 multiply_cannon_multrec 185 9.1 51.991 51.991 52.043 52.043 arnoldi_extremal 12 6.1 0.000 0.000 48.246 48.246 arnoldi_normal_ev 12 7.1 0.028 0.028 48.246 48.246 build_subspace 23 8.1 0.134 0.134 47.532 47.532 dbcsr_matrix_vector_mult 652 9.0 0.275 0.275 36.902 36.902 dbcsr_matrix_vector_mult_local 652 10.0 35.324 35.324 35.332 35.332 make_m2s 370 7.1 0.031 0.031 29.288 29.288 make_images 370 8.1 7.544 7.544 26.838 26.838 dbcsr_finalize 646 7.5 0.206 0.206 21.398 21.398 dbcsr_merge_all 597 8.5 3.468 3.468 19.483 19.483 setup_rec_index_2d 370 8.1 18.560 18.560 18.560 18.560 dbcsr_sort_indices 1103 9.9 15.087 15.087 15.087 15.087 tree_to_linear_d 110 9.4 13.697 13.697 13.697 13.697 ls_scf_init_scf 1 4.0 0.000 0.000 13.598 13.598 ls_scf_init_matrix_S 1 5.0 0.000 0.000 13.132 13.132 quick_finalize 395 10.0 0.499 0.499 12.873 12.873 matrix_sqrt_Newton_Schulz 1 6.0 0.001 0.001 12.237 12.237 dbcsr_special_finalize 370 9.1 0.003 0.003 11.852 11.852 dbcsr_dot_sd 144 6.3 9.072 9.072 9.073 9.073 dbcsr_frobenius_norm 142 6.1 8.049 8.049 8.051 8.051 matrix_qs_to_ls 12 5.1 0.000 0.000 7.443 7.443 matrix_cluster 12 6.1 0.000 0.000 7.443 7.443 make_images_data 370 9.1 0.010 0.010 7.281 7.281 dbcsr_new_transposed 2 7.0 0.168 0.168 6.563 6.563 ------------------------------------------------------------------------------- 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 0.019 0.022 116.369 116.370 qs_energies 1 2.0 0.000 0.000 116.202 116.202 ls_scf 1 3.0 0.000 0.000 116.087 116.089 ls_scf_main 1 4.0 0.001 0.003 111.666 111.670 density_matrix_trs4 11 5.0 0.010 0.015 106.749 106.822 dbcsr_multiply_generic 185 6.1 0.082 0.104 97.406 97.687 multiply_cannon 185 7.1 0.054 0.068 79.080 80.482 multiply_cannon_loop 185 8.1 0.228 0.247 74.613 76.021 multiply_cannon_multrec 1480 9.1 45.717 48.291 46.239 48.811 mp_waitall_1 11936 10.3 26.734 29.550 26.734 29.550 multiply_cannon_metrocomm3 1480 9.1 0.020 0.024 16.953 21.598 make_m2s 370 7.1 0.036 0.042 10.790 10.950 make_images 370 8.1 0.767 0.837 10.661 10.825 multiply_cannon_metrocomm1 1480 9.1 0.011 0.013 5.775 9.174 mp_sum_l 1039 5.9 6.226 8.046 6.226 8.046 arnoldi_extremal 12 6.1 0.000 0.001 7.281 7.306 arnoldi_normal_ev 12 7.1 0.002 0.008 7.281 7.306 build_subspace 23 8.1 0.044 0.060 7.073 7.082 dbcsr_multiply_generic_mpsum_f 137 7.1 0.001 0.001 4.558 6.161 dbcsr_matrix_vector_mult 652 9.0 0.024 0.098 5.423 5.933 calculate_norms 2960 9.1 5.298 5.604 5.298 5.604 make_images_data 370 9.1 0.014 0.016 4.413 4.927 ls_scf_dm_to_ks 11 5.0 0.000 0.000 4.268 4.359 hybrid_alltoall_any 393 9.9 0.327 1.681 3.486 3.719 dbcsr_complete_redistribute 23 7.5 2.049 2.269 3.420 3.538 matrix_ls_to_qs 11 6.0 0.000 0.000 3.307 3.444 ls_scf_init_scf 1 4.0 0.000 0.000 3.436 3.438 ls_scf_init_matrix_S 1 5.0 0.000 0.000 3.390 3.401 mp_sum_dv 2907 10.4 3.004 3.325 3.004 3.325 dbcsr_matrix_vector_mult_local 652 10.0 2.973 3.286 2.978 3.291 matrix_decluster 11 7.0 0.000 0.000 3.032 3.150 matrix_sqrt_Newton_Schulz 1 6.0 0.001 0.001 3.099 3.101 make_images_pack 370 9.1 2.661 2.982 2.667 2.989 dbcsr_add_d 280 6.0 0.002 0.003 2.350 2.492 dbcsr_add_anytype 280 7.0 1.279 1.349 2.349 2.490 buffer_matrices_ensure_size 370 8.1 2.292 2.438 2.292 2.438 ------------------------------------------------------------------------------- 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=112.10199999999998, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_copy_into_existing", label="dbcsr_copy_into_existing", y=59.804, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=51.991, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_complete_redistribute", label="dbcsr_complete_redistribute", y=41.945, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=35.324, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="setup_rec_index_2d", label="setup_rec_index_2d", y=18.56, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="mp_sum_dv", label="mp_sum_dv", y=0.0, 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=24.367999999999995, 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="multiply_cannon_multrec", label="multiply_cannon_multrec", y=45.717, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="dbcsr_complete_redistribute", label="dbcsr_complete_redistribute", y=2.049, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=2.973, 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="mp_sum_dv", label="mp_sum_dv", y=3.004, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="calculate_norms", label="calculate_norms", y=5.298, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=6.226, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=26.734, 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 0.006 0.006 101.114 101.114 lib_test 1 2.0 0.000 0.000 101.107 101.107 dbcsr_run_tests 3 3.0 0.003 0.003 101.107 101.107 test_multiplies_multiproc 3 4.0 0.001 0.001 81.169 81.169 dbcsr_redistribute 9 5.0 52.704 52.704 56.362 56.362 dbcsr_multiply_generic 9 5.0 0.001 0.001 22.932 22.932 dbcsr_make_random_matrix 9 4.0 14.560 14.560 19.852 19.852 multiply_cannon 9 6.0 0.002 0.002 16.271 16.271 multiply_cannon_loop 9 7.0 0.004 0.004 15.746 15.746 multiply_cannon_multrec 9 8.0 15.742 15.742 15.743 15.743 dbcsr_finalize 27 5.7 0.004 0.004 9.146 9.146 dbcsr_merge_all 18 6.5 3.261 3.261 8.388 8.388 mp_alltoall_d11v 27 6.0 3.332 3.332 3.332 3.332 tree_to_linear_d 9 7.0 3.198 3.198 3.198 3.198 dbcsr_data_release 975 7.6 2.463 2.463 2.463 2.463 make_m2s 18 6.0 0.001 0.001 2.226 2.226 make_images 18 7.0 0.692 0.692 2.148 2.148 ------------------------------------------------------------------------------- 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 26.711 26.712 lib_test 1 2.0 0.000 0.001 26.681 26.702 dbcsr_run_tests 3 3.0 0.001 0.001 26.680 26.700 test_multiplies_multiproc 3 4.0 0.001 0.001 25.533 25.628 dbcsr_multiply_generic 9 5.0 0.002 0.002 23.521 23.628 multiply_cannon 9 6.0 0.002 0.003 21.197 21.628 multiply_cannon_loop 9 7.0 0.004 0.004 20.752 21.153 multiply_cannon_multrec 72 8.0 17.608 18.497 17.609 18.498 mp_waitall_1 576 9.2 3.551 4.197 3.551 4.197 multiply_cannon_metrocomm1 72 8.0 0.002 0.002 2.835 3.644 dbcsr_make_random_matrix 9 4.0 0.883 0.920 1.104 1.135 mp_sum_l 310 2.7 0.493 1.107 0.493 1.107 dbcsr_multiply_generic_mpsum_f 9 6.0 0.000 0.000 0.489 1.104 dbcsr_finalize 27 5.7 0.001 0.001 0.912 1.027 make_m2s 18 6.0 0.001 0.001 0.973 1.027 make_images 18 7.0 0.027 0.029 0.969 1.024 dbcsr_merge_all 18 6.5 0.149 0.174 0.798 0.955 multiply_cannon_metrocomm3 72 8.0 0.000 0.001 0.296 0.840 dbcsr_data_release 444 7.6 0.680 0.791 0.680 0.791 dbcsr_redistribute 9 5.0 0.405 0.461 0.710 0.755 dbcsr_destroy 111 5.9 0.012 0.116 0.580 0.670 dbcsr_data_copy_aa2 18 7.5 0.472 0.579 0.472 0.579 make_images_data 18 8.0 0.001 0.001 0.470 0.548 ------------------------------------------------------------------------------- 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=9.052000000000021, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_redistribute", label="dbcsr_redistribute", y=52.704, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=15.742, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=14.56, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="mp_alltoall_d11v", label="mp_alltoall_d11v", y=3.332, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_merge_all", label="dbcsr_merge_all", y=3.261, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_data_release", label="dbcsr_data_release", y=2.463, 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=2.9419999999999966, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_redistribute", label="dbcsr_redistribute", y=0.405, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=17.608, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=0.883, 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_merge_all", label="dbcsr_merge_all", y=0.149, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_data_release", label="dbcsr_data_release", y=0.68, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=3.551, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=0.493, 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 0.049 0.049 143.753 143.753 qs_mol_dyn_low 1 2.0 0.004 0.004 141.807 141.807 velocity_verlet 5 3.0 0.004 0.004 114.857 114.857 qmmm_el_coupling 6 3.8 0.000 0.000 70.454 70.454 qmmm_elec_with_gaussian 6 4.8 0.170 0.170 70.448 70.448 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 69.459 69.459 qmmm_elec_gaussian_low_G 6 6.8 68.099 68.099 68.099 68.099 qs_forces 6 3.8 0.001 0.001 57.956 57.956 qs_energies 6 4.8 0.000 0.000 51.585 51.585 scf_env_do_scf 6 5.8 0.000 0.000 47.622 47.622 scf_env_do_scf_inner_loop 39 6.8 0.003 0.003 39.925 39.925 rebuild_ks_matrix 45 8.4 0.000 0.000 39.623 39.623 qs_ks_build_kohn_sham_matrix 45 9.4 0.007 0.007 39.623 39.623 qs_ks_update_qs_env 45 7.8 0.000 0.000 33.988 33.988 pw_transfer 966 11.9 0.070 0.070 23.641 23.641 fft_wrap_pw1pw2 801 13.0 0.009 0.009 23.301 23.301 fft_wrap_pw1pw2_150 507 14.3 2.410 2.410 22.752 22.752 qs_vxc_create 45 10.4 0.001 0.001 21.366 21.366 xc_vxc_pw_create 45 11.4 4.437 4.437 21.365 21.365 qs_rho_update_rho 45 7.9 0.000 0.000 10.520 10.520 calculate_rho_elec 45 8.9 0.899 0.899 10.520 10.520 pw_scatter_s 429 15.4 10.509 10.509 10.509 10.509 xc_rho_set_and_dset_create 45 12.4 0.254 0.254 9.745 9.745 fft3d_s 802 15.0 8.970 8.970 8.980 8.980 qmmm_forces 6 3.8 0.001 0.001 8.194 8.194 init_scf_loop 6 6.8 0.000 0.000 7.690 7.690 qmmm_forces_with_gaussian 6 4.8 0.126 0.126 7.676 7.676 pw_integral_ab 2539 7.4 7.609 7.609 7.609 7.609 qs_ks_ddapc 45 10.4 0.001 0.001 6.706 6.706 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 6.586 6.586 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 5.648 5.648 qmmm_forces_gaussian_low_G 6 6.8 5.506 5.506 5.506 5.506 pw_poisson_solve 51 9.9 2.367 2.367 5.393 5.393 grid_collocate_task_list 45 9.9 4.911 4.911 4.911 4.911 density_rs2pw 45 9.9 0.003 0.003 4.710 4.710 fist_calc_energy_force 6 3.8 0.002 0.002 4.393 4.393 sum_up_and_integrate 45 10.4 0.244 0.244 4.368 4.368 cp_ddapc_apply_CD 45 11.4 0.006 0.006 4.159 4.159 integrate_v_rspace 45 11.4 0.013 0.013 4.124 4.124 force_nonbond 6 4.8 3.156 3.156 3.156 3.156 ------------------------------------------------------------------------------- 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 0.035 0.038 88.953 88.955 qs_mol_dyn_low 1 2.0 0.005 0.005 87.343 87.434 qs_forces 6 3.8 0.001 0.001 64.850 64.850 qs_energies 6 4.8 0.001 0.001 61.850 61.851 scf_env_do_scf 6 5.8 0.000 0.001 60.296 60.296 scf_env_do_scf_inner_loop 113 6.2 0.003 0.009 57.890 57.892 rebuild_ks_matrix 119 8.1 0.000 0.001 42.615 42.632 qs_ks_build_kohn_sham_matrix 119 9.1 0.022 0.023 42.615 42.631 qs_ks_update_qs_env 119 7.3 0.001 0.001 40.075 40.091 velocity_verlet 5 3.0 0.002 0.003 36.126 36.130 pw_transfer 2446 11.8 0.295 0.315 27.329 27.504 fft_wrap_pw1pw2 2059 12.8 0.034 0.036 26.487 26.708 fft_wrap_pw1pw2_150 1321 14.0 2.288 2.496 25.613 25.814 qs_vxc_create 119 10.1 0.004 0.004 21.533 21.538 xc_vxc_pw_create 119 11.1 0.469 0.633 21.530 21.534 fft3d_ps 2059 14.8 11.882 12.991 20.046 20.318 qs_rho_update_rho 119 7.3 0.001 0.001 16.817 16.818 calculate_rho_elec 119 8.3 0.087 0.097 16.816 16.818 sum_up_and_integrate 119 10.1 0.088 0.097 15.369 15.431 integrate_v_rspace 119 11.1 0.004 0.005 15.281 15.337 qmmm_forces 6 3.8 0.003 0.003 12.426 12.427 rs_pw_transfer 988 11.5 0.016 0.018 11.688 12.318 qmmm_forces_with_gaussian 6 4.8 0.417 0.498 12.055 12.276 density_rs2pw 119 9.3 0.010 0.011 10.176 10.715 xc_rho_set_and_dset_create 119 12.1 0.516 0.601 10.057 10.380 potential_pw2rs 119 12.1 0.011 0.011 9.185 9.198 qmmm_el_coupling 6 3.8 0.000 0.000 8.937 8.982 qmmm_elec_with_gaussian 6 4.8 0.365 0.478 8.934 8.979 grid_collocate_task_list 119 9.3 6.333 6.817 6.333 6.817 mp_alltoall_z22v 2059 16.8 5.056 6.571 5.056 6.571 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 5.785 5.949 grid_integrate_task_list 119 12.1 5.652 5.927 5.652 5.927 rs_pw_transfer_PW2RS_150 125 13.9 2.577 2.659 5.100 5.126 qmmm_forces_gaussian_low_G 6 6.8 4.735 4.875 4.735 4.875 rs_pw_transfer_RS2PW_150 125 11.2 2.006 2.182 4.153 4.764 mp_waitany 4028 12.8 3.701 4.718 3.701 4.718 yz_to_x 964 15.3 1.144 1.296 3.700 4.706 x_to_yz 1095 16.3 1.913 2.093 4.413 4.634 pw_restrict_s3 18 5.8 2.408 2.457 4.559 4.611 qs_scf_new_mos 113 7.2 0.001 0.001 3.959 3.969 qs_scf_loop_do_ot 113 8.2 0.001 0.001 3.958 3.968 ot_scf_mini 113 9.2 0.002 0.002 3.786 3.795 qmmm_elec_with_gaussian:spline 6 5.8 0.000 0.000 3.688 3.731 pw_prolongate_s3 18 6.8 1.930 1.975 3.688 3.731 dbcsr_multiply_generic 2588 12.3 0.099 0.113 3.570 3.651 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 3.382 3.520 qs_ks_ddapc 119 10.1 0.003 0.003 2.951 3.089 mp_sum_dm3 33 5.7 2.589 2.860 2.589 2.860 pw_integral_ab 2761 7.7 2.254 2.282 2.644 2.840 qmmm_elec_gaussian_low_G 6 6.8 2.434 2.565 2.434 2.565 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 2.552 2.553 pw_gather_p 964 14.3 2.132 2.414 2.132 2.414 ot_mini 113 10.2 0.001 0.001 2.392 2.403 init_scf_loop 6 6.8 0.000 0.000 2.402 2.402 mp_waitall_1 188862 16.2 2.135 2.309 2.135 2.309 pw_scatter_p 1095 15.3 1.928 2.001 1.928 2.001 pw_derive 732 12.5 1.686 1.907 1.686 1.907 qs_ot_get_derivative 113 11.2 0.001 0.001 1.886 1.894 ------------------------------------------------------------------------------- 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=38.14899999999999, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=68.099, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_scatter_s", label="pw_scatter_s", y=10.509, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_s", label="fft3d_s", y=8.97, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_integral_ab", label="pw_integral_ab", y=7.609, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=5.506, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=4.911, 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=50.607000000000006, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=2.434, 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="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=2.254, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=4.735, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=6.333, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=11.882, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=5.652, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=5.056, yerr=0.0 Summary: Performance test took 59 minutes. Status: OK Uploading artifacts... done EndDate: 2021-12-17 12:20:57+00:00