StartDate: 2022-02-03 12:53:54+00:00 CpuId: 64x Intel Xeon W 2000 / D-2100 (Skylake / Cascade Lake) {Skylake}, 14nm CommitSHA: 85e7b7d615593baa5aa20072a9b472cc16e28bed CommitTime: 2022-02-03 11:35:01 +0100 CommitAuthor: Eisuke Kawashima CommitSubject: Python: PEP8 fixes (#1926) Trying to pull image cp2k-perf-openmp... image not found. #################### Building Image cp2k-perf-openmp #################### Dockerfile: /tools/docker/Dockerfile.test_performance Build-Path: / Build-Args: Sending build context to Docker daemon 362.2MB Step 1/35 : FROM ubuntu:20.04 20.04: Pulling from library/ubuntu 08c01a0ec47e: Already exists Digest: sha256:669e010b58baf5beb2836b253c1fd5768333f0d1dbcb834f7c07a4dc93f474be Status: Downloaded newer image for ubuntu:20.04 ---> 54c9d81cbb44 Step 2/35 : WORKDIR /opt/cp2k-toolchain ---> Using cache ---> 3a843b424587 Step 3/35 : COPY ./tools/toolchain/install_requirements*.sh ./ ---> Using cache ---> 9621b4b5709d Step 4/35 : RUN ./install_requirements.sh ubuntu:20.04 ---> Using cache ---> c1cdc0430e60 Step 5/35 : RUN mkdir scripts ---> Using cache ---> 3877592c52c6 Step 6/35 : COPY ./tools/toolchain/scripts/VERSION ./tools/toolchain/scripts/parse_if.py ./tools/toolchain/scripts/tool_kit.sh ./tools/toolchain/scripts/common_vars.sh ./tools/toolchain/scripts/signal_trap.sh ./tools/toolchain/scripts/get_openblas_arch.sh ./scripts/ ---> Using cache ---> 924d174bd2f7 Step 7/35 : COPY ./tools/toolchain/install_cp2k_toolchain.sh . ---> Using cache ---> bed5482f3bdc Step 8/35 : RUN ./install_cp2k_toolchain.sh --install-all --mpi-mode=mpich --dry-run ---> Using cache ---> 4545b3f8e688 Step 9/35 : COPY ./tools/toolchain/scripts/stage0/ ./scripts/stage0/ ---> Using cache ---> e003f334855c Step 10/35 : RUN ./scripts/stage0/install_stage0.sh && rm -rf ./build ---> Using cache ---> 18720d1f74c1 Step 11/35 : COPY ./tools/toolchain/scripts/stage1/ ./scripts/stage1/ ---> Using cache ---> 81c18310a38f Step 12/35 : RUN ./scripts/stage1/install_stage1.sh && rm -rf ./build ---> Using cache ---> 9daca1454dbe Step 13/35 : COPY ./tools/toolchain/scripts/stage2/ ./scripts/stage2/ ---> Using cache ---> 715983fc286f Step 14/35 : RUN ./scripts/stage2/install_stage2.sh && rm -rf ./build ---> Using cache ---> 10af9b1b86fe Step 15/35 : COPY ./tools/toolchain/scripts/stage3/ ./scripts/stage3/ ---> Using cache ---> 9b855f1d4974 Step 16/35 : RUN ./scripts/stage3/install_stage3.sh && rm -rf ./build ---> Using cache ---> 319da87e9099 Step 17/35 : COPY ./tools/toolchain/scripts/stage4/ ./scripts/stage4/ ---> Using cache ---> e0ebc9146770 Step 18/35 : RUN ./scripts/stage4/install_stage4.sh && rm -rf ./build ---> Using cache ---> 2424739ad03f Step 19/35 : COPY ./tools/toolchain/scripts/stage5/ ./scripts/stage5/ ---> Using cache ---> 43860c06a134 Step 20/35 : RUN ./scripts/stage5/install_stage5.sh && rm -rf ./build ---> Using cache ---> 773b4c804b1e Step 21/35 : COPY ./tools/toolchain/scripts/stage6/ ./scripts/stage6/ ---> Using cache ---> e5e6eaf26fff Step 22/35 : RUN ./scripts/stage6/install_stage6.sh && rm -rf ./build ---> Using cache ---> fda949cbc0fa Step 23/35 : COPY ./tools/toolchain/scripts/stage7/ ./scripts/stage7/ ---> Using cache ---> 9f983162361a Step 24/35 : RUN ./scripts/stage7/install_stage7.sh && rm -rf ./build ---> Using cache ---> 97030262a893 Step 25/35 : COPY ./tools/toolchain/scripts/stage8/ ./scripts/stage8/ ---> Using cache ---> 5db62a9d77f1 Step 26/35 : RUN ./scripts/stage8/install_stage8.sh && rm -rf ./build ---> Using cache ---> 75c7d5787f22 Step 27/35 : COPY ./tools/toolchain/scripts/arch_base.tmpl ./tools/toolchain/scripts/generate_arch_files.sh ./scripts/ ---> Using cache ---> 8896f476778a Step 28/35 : RUN ./scripts/generate_arch_files.sh && rm -rf ./build ---> Using cache ---> ce06f90bef22 Step 29/35 : WORKDIR /workspace ---> Using cache ---> 81ead46b42fe Step 30/35 : COPY ./tools/docker/scripts/install_basics.sh . ---> Using cache ---> 62638e82774b Step 31/35 : RUN ./install_basics.sh ---> Using cache ---> 2e3cb8f87b91 Step 32/35 : COPY ./tools/docker/scripts/install_performance.sh . ---> 8d7dde662d7f Step 33/35 : RUN ./install_performance.sh "local" ---> Running in 567218d1db4f './local.pdbg' -> '/opt/cp2k-toolchain/install/arch/local.pdbg' './local.psmp' -> '/opt/cp2k-toolchain/install/arch/local.psmp' './local.sdbg' -> '/opt/cp2k-toolchain/install/arch/local.sdbg' './local.ssmp' -> '/opt/cp2k-toolchain/install/arch/local.ssmp' './local_coverage.pdbg' -> '/opt/cp2k-toolchain/install/arch/local_coverage.pdbg' './local_static.psmp' -> '/opt/cp2k-toolchain/install/arch/local_static.psmp' './local_static.ssmp' -> '/opt/cp2k-toolchain/install/arch/local_static.ssmp' './local_warn.psmp' -> '/opt/cp2k-toolchain/install/arch/local_warn.psmp' Warming cache by trying to compile cp2k... done. Removing intermediate container 567218d1db4f ---> f7ff987171db Step 34/35 : COPY ./tools/docker/scripts/ci_entrypoint.sh ./tools/docker/scripts/test_performance.sh ./tools/docker/scripts/plot_performance.py ./ ---> 8e298b053167 Step 35/35 : CMD ["./ci_entrypoint.sh", "./test_performance.sh", "local"] ---> Running in 0db146f68691 Removing intermediate container 0db146f68691 ---> 7c422541707c Successfully built 7c422541707c Successfully tagged gcr.io/cp2k-org-project/img_cp2k-perf-openmp-arch-b51:gittree-85e7b7d-buildargs-68b329d Pushing image cp2k-perf-openmp... done. #################### Running Image cp2k-perf-openmp #################### ========== Fetching Git Commit ========== CommitSHA: 85e7b7d615593baa5aa20072a9b472cc16e28bed CommitTime: 2022-02-03 11:35:01 +0100 CommitAuthor: Eisuke Kawashima CommitSubject: Python: PEP8 fixes (#1926) ========== Cleaning Build Cache ========== Discovering programs ... rm -rf /workspace/cp2k/obj/precommit rm -rf /workspace/cp2k/obj/prettified rm -rf /workspace/cp2k/obj/doxified rm -rf /workspace/cp2k/regtesting/local/ssmp/TEST-* rm -rf /workspace/cp2k/regtesting/local/ssmp/LAST-* rm -rf /workspace/cp2k/exe /workspace/cp2k/obj /workspace/cp2k/lib /workspace/cp2k/regtesting ========== 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 0.031 0.031 152.304 152.304 qs_mol_dyn_low 1 2.0 0.004 0.004 151.546 151.546 qs_forces 11 3.9 0.002 0.002 151.490 151.490 qs_energies 11 4.9 0.001 0.001 141.696 141.696 scf_env_do_scf 11 5.9 0.001 0.001 115.086 115.086 velocity_verlet 10 3.0 0.002 0.002 105.194 105.194 scf_env_do_scf_inner_loop 108 6.5 0.009 0.009 78.235 78.235 init_scf_loop 11 6.9 0.000 0.000 36.679 36.679 prepare_preconditioner 11 7.9 0.000 0.000 32.844 32.844 make_preconditioner 11 8.9 0.000 0.000 32.844 32.844 rebuild_ks_matrix 119 8.3 0.001 0.001 31.803 31.803 qs_ks_build_kohn_sham_matrix 119 9.3 0.017 0.017 31.802 31.802 make_full_inverse_cholesky 11 9.9 0.000 0.000 30.817 30.817 qs_ks_update_qs_env 119 7.6 0.001 0.001 29.671 29.671 qs_rho_update_rho 119 7.7 0.001 0.001 27.468 27.468 calculate_rho_elec 119 8.7 1.541 1.541 27.468 27.468 qs_scf_new_mos 108 7.5 0.001 0.001 27.062 27.062 qs_scf_loop_do_ot 108 8.5 0.001 0.001 27.061 27.061 ot_scf_mini 108 9.5 0.003 0.003 25.234 25.234 dbcsr_multiply_generic 2286 12.5 0.182 0.182 22.822 22.822 grid_collocate_task_list 119 9.7 21.475 21.475 21.475 21.475 sum_up_and_integrate 119 10.3 0.387 0.387 20.119 20.119 integrate_v_rspace 119 11.3 0.517 0.517 19.732 19.732 cp_fm_cholesky_invert 11 10.9 18.789 18.789 18.789 18.789 grid_integrate_task_list 119 12.3 16.849 16.849 16.849 16.849 ot_mini 108 10.5 0.001 0.001 14.787 14.787 init_scf_run 11 5.9 0.001 0.001 13.032 13.032 scf_env_initial_rho_setup 11 6.9 0.001 0.001 13.031 13.031 make_m2s 4572 13.5 0.064 0.064 12.782 12.782 wfi_extrapolate 11 7.9 0.001 0.001 12.282 12.282 cp_gemm 81 9.0 0.000 0.000 10.503 10.503 cp_gemm_cosma 81 10.0 10.502 10.502 10.502 10.502 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 9.956 9.956 qs_ot_get_derivative 108 11.5 0.001 0.001 7.594 7.594 pw_transfer 1439 11.6 0.089 0.089 7.456 7.456 ot_diis_step 108 11.5 0.005 0.005 7.188 7.188 fft_wrap_pw1pw2 1201 12.6 0.010 0.010 7.176 7.176 make_images 4572 14.5 2.524 2.524 6.822 6.822 qs_ot_get_p 119 10.4 0.001 0.001 6.533 6.533 dbcsr_make_dense_low 5837 15.5 0.093 0.093 6.122 6.122 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 6.120 6.120 apply_single 119 13.6 0.001 0.001 6.119 6.119 dbcsr_complete_redistribute 329 12.2 2.932 2.932 6.089 6.089 fft_wrap_pw1pw2_140 487 13.2 0.676 0.676 6.080 6.080 cp_fm_cholesky_decompose 22 10.9 6.030 6.030 6.030 6.030 make_dense_data 5837 16.5 5.412 5.412 6.007 6.007 build_core_hamiltonian_matrix_ 11 4.9 0.001 0.001 5.906 5.906 qs_env_update_s_mstruct 11 6.9 0.000 0.000 5.659 5.659 multiply_cannon 2286 13.5 0.923 0.923 5.616 5.616 dbcsr_make_images_dense 3978 14.8 0.026 0.026 5.525 5.525 qs_create_task_list 11 7.9 0.000 0.000 5.147 5.147 generate_qs_task_list 11 8.9 3.551 3.551 5.147 5.147 qs_ot_p2m_diag 50 11.0 0.219 0.219 5.021 5.021 copy_dbcsr_to_fm 153 11.3 0.003 0.003 4.956 4.956 dbcsr_copy 2102 12.0 0.276 0.276 4.750 4.750 cp_dbcsr_syevd 50 12.0 0.004 0.004 4.481 4.481 pw_poisson_solve 119 10.3 1.882 1.882 4.471 4.471 density_rs2pw 119 9.7 0.006 0.006 4.451 4.451 dbcsr_copy_into_existing 22 7.9 4.432 4.432 4.433 4.433 cp_fm_diag_elpa 50 13.0 0.000 0.000 4.329 4.329 cp_fm_diag_elpa_base 50 14.0 4.272 4.272 4.328 4.328 multiply_cannon_loop 2286 14.5 0.044 0.044 4.173 4.173 multiply_cannon_multrec 2286 15.5 4.064 4.064 4.128 4.128 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 4.124 4.124 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 3.885 3.885 build_core_hamiltonian_matrix 11 6.9 0.001 0.001 3.731 3.731 qs_energies_compute_matrix_w 11 5.9 0.000 0.000 3.465 3.465 calculate_w_matrix_ot 11 6.9 0.008 0.008 3.465 3.465 copy_fm_to_dbcsr 176 11.2 0.002 0.002 3.320 3.320 fft3d_s 1202 14.6 3.147 3.147 3.153 3.153 ------------------------------------------------------------------------------- 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 0.022 67.364 67.365 qs_mol_dyn_low 1 2.0 0.007 0.007 67.216 67.223 qs_forces 11 3.9 0.002 0.002 67.161 67.161 qs_energies 11 4.9 0.001 0.001 62.321 62.323 scf_env_do_scf 11 5.9 0.001 0.001 56.452 56.453 scf_env_do_scf_inner_loop 108 6.5 0.003 0.011 52.288 52.288 velocity_verlet 10 3.0 0.002 0.002 40.259 40.260 rebuild_ks_matrix 119 8.3 0.001 0.001 26.623 26.680 qs_ks_build_kohn_sham_matrix 119 9.3 0.021 0.022 26.623 26.679 qs_ks_update_qs_env 119 7.6 0.001 0.001 23.569 23.619 sum_up_and_integrate 119 10.3 0.040 0.042 21.166 21.189 integrate_v_rspace 119 11.3 0.004 0.005 21.126 21.153 qs_rho_update_rho 119 7.7 0.001 0.001 20.793 20.799 calculate_rho_elec 119 8.7 0.048 0.049 20.792 20.798 grid_collocate_task_list 119 9.7 15.093 15.858 15.093 15.858 grid_integrate_task_list 119 12.3 15.346 15.702 15.346 15.702 dbcsr_multiply_generic 2286 12.5 0.128 0.131 14.945 15.100 qs_scf_new_mos 108 7.5 0.001 0.001 12.270 12.324 qs_scf_loop_do_ot 108 8.5 0.001 0.001 12.270 12.323 ot_scf_mini 108 9.5 0.003 0.003 11.500 11.549 multiply_cannon 2286 13.5 0.224 0.230 9.907 10.106 multiply_cannon_loop 2286 14.5 0.205 0.220 9.001 9.235 mp_waitall_1 169478 16.3 7.370 7.904 7.370 7.904 rs_pw_transfer 974 11.9 0.015 0.016 6.143 7.013 ot_mini 108 10.5 0.001 0.001 6.736 6.789 density_rs2pw 119 9.7 0.009 0.009 5.187 6.072 multiply_cannon_metrocomm3 18288 15.5 0.076 0.082 4.705 5.319 pw_transfer 1439 11.6 0.133 0.142 5.118 5.173 fft_wrap_pw1pw2 1201 12.6 0.013 0.014 4.850 4.907 potential_pw2rs 119 12.3 0.010 0.010 4.622 4.631 fft_wrap_pw1pw2_140 487 13.2 0.523 0.547 4.260 4.428 init_scf_loop 11 6.9 0.000 0.000 4.148 4.149 init_scf_run 11 5.9 0.000 0.002 3.983 3.983 scf_env_initial_rho_setup 11 6.9 0.000 0.001 3.982 3.983 wfi_extrapolate 11 7.9 0.001 0.001 3.621 3.621 fft3d_ps 1201 14.6 1.977 2.091 3.537 3.586 make_m2s 4572 13.5 0.074 0.076 3.465 3.515 multiply_cannon_multrec 18288 15.5 3.228 3.429 3.244 3.446 qs_ot_get_derivative 108 11.5 0.001 0.001 3.363 3.411 ot_diis_step 108 11.5 0.005 0.005 3.348 3.348 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 3.265 3.330 apply_single 119 13.6 0.001 0.001 3.264 3.330 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 3.258 3.268 mp_waitany 9880 13.7 2.061 2.941 2.061 2.941 make_images 4572 14.5 0.188 0.194 2.804 2.870 rs_pw_transfer_RS2PW_140 130 11.5 0.519 0.567 1.903 2.785 rs_pw_transfer_PW2RS_140 130 13.9 1.104 1.177 2.325 2.362 mp_alltoall_d11v 2130 13.8 1.418 1.959 1.418 1.959 qs_ot_get_p 119 10.4 0.001 0.001 1.677 1.731 rs_gather_matrices 119 12.3 0.121 0.132 1.109 1.670 build_core_hamiltonian_matrix_ 11 4.9 0.001 0.001 1.429 1.548 make_images_data 4572 15.5 0.061 0.068 1.309 1.424 qs_energies_init_hamiltonians 11 5.9 0.000 0.001 1.418 1.419 prepare_preconditioner 11 7.9 0.000 0.000 1.374 1.384 make_preconditioner 11 8.9 0.000 0.000 1.374 1.384 ------------------------------------------------------------------------------- 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=74.595, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=21.475, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=18.789, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=16.849, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_gemm_cosma", label="cp_gemm_cosma", y=10.502, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=6.03, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=4.064, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="mp_waitany", label="mp_waitany", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", 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=24.266000000000005, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=15.093, 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=15.346, 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=3.228, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitany", label="mp_waitany", y=2.061, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=7.37, 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 0.036 0.036 204.551 204.551 qs_mol_dyn_low 1 2.0 0.004 0.004 203.783 203.783 qs_forces 11 3.9 0.001 0.001 203.725 203.725 qs_energies 11 4.9 0.001 0.001 189.924 189.924 scf_env_do_scf 11 5.9 0.001 0.001 158.866 158.866 velocity_verlet 10 3.0 0.002 0.002 136.839 136.839 scf_env_do_scf_inner_loop 96 6.5 0.008 0.008 118.763 118.763 rebuild_ks_matrix 107 8.3 0.001 0.001 60.600 60.600 qs_ks_build_kohn_sham_matrix 107 9.3 0.016 0.016 60.599 60.599 qs_ks_update_qs_env 107 7.6 0.001 0.001 54.609 54.609 qs_rho_update_rho 107 7.7 0.001 0.001 53.345 53.345 calculate_rho_elec 107 8.7 1.378 1.378 53.344 53.344 sum_up_and_integrate 107 10.3 0.352 0.352 50.161 50.161 integrate_v_rspace 107 11.3 0.526 0.526 49.808 49.808 grid_collocate_task_list 107 9.7 48.035 48.035 48.035 48.035 grid_integrate_task_list 107 12.3 47.141 47.141 47.141 47.141 init_scf_loop 11 6.9 0.000 0.000 39.905 39.905 prepare_preconditioner 11 7.9 0.000 0.000 32.701 32.701 make_preconditioner 11 8.9 0.000 0.000 32.701 32.701 make_full_inverse_cholesky 11 9.9 0.000 0.000 30.731 30.731 qs_scf_new_mos 96 7.5 0.001 0.001 22.927 22.927 qs_scf_loop_do_ot 96 8.5 0.001 0.001 22.926 22.926 ot_scf_mini 96 9.5 0.003 0.003 21.233 21.233 dbcsr_multiply_generic 1966 12.4 0.162 0.162 19.339 19.339 cp_fm_cholesky_invert 11 10.9 18.508 18.508 18.508 18.508 init_scf_run 11 5.9 0.001 0.001 16.020 16.020 scf_env_initial_rho_setup 11 6.9 0.001 0.001 16.020 16.020 wfi_extrapolate 11 7.9 0.001 0.001 15.003 15.003 ot_mini 96 10.5 0.001 0.001 12.401 12.401 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 11.357 11.357 cp_gemm 81 9.0 0.000 0.000 10.442 10.442 cp_gemm_cosma 81 10.0 10.441 10.441 10.441 10.441 make_m2s 3932 13.4 0.055 0.055 10.427 10.427 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 7.594 7.594 qs_env_update_s_mstruct 11 6.9 0.000 0.000 6.805 6.805 qs_ot_get_derivative 96 11.5 0.001 0.001 6.804 6.804 pw_transfer 1295 11.6 0.079 0.079 6.657 6.657 fft_wrap_pw1pw2 1081 12.6 0.009 0.009 6.400 6.400 qs_create_task_list 11 7.9 0.000 0.000 6.278 6.278 generate_qs_task_list 11 8.9 4.689 4.689 6.278 6.278 cp_fm_cholesky_decompose 22 10.9 6.247 6.247 6.247 6.247 build_core_hamiltonian_matrix_ 11 4.9 0.001 0.001 6.204 6.204 dbcsr_complete_redistribute 317 12.2 2.904 2.904 6.183 6.183 make_images 3932 14.4 2.062 2.062 5.679 5.679 ot_diis_step 96 11.5 0.005 0.005 5.593 5.593 qs_ot_get_p 107 10.4 0.001 0.001 5.570 5.570 fft_wrap_pw1pw2_140 439 13.2 0.568 0.568 5.412 5.412 multiply_cannon 1966 13.4 0.879 0.879 5.091 5.091 copy_dbcsr_to_fm 147 11.2 0.003 0.003 4.999 4.999 dbcsr_copy 1855 11.9 0.252 0.252 4.935 4.935 dbcsr_make_dense_low 4961 15.5 0.079 0.079 4.915 4.915 make_dense_data 4961 16.5 4.297 4.297 4.817 4.817 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 4.772 4.772 apply_single 107 13.6 0.000 0.000 4.772 4.772 dbcsr_copy_into_existing 22 7.9 4.643 4.643 4.644 4.644 dbcsr_make_images_dense 3386 14.7 0.022 0.022 4.364 4.364 qs_ot_p2m_diag 44 11.0 0.196 0.196 4.271 4.271 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 4.093 4.093 ------------------------------------------------------------------------------- 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 0.009 0.012 122.489 122.490 qs_mol_dyn_low 1 2.0 0.005 0.007 122.350 122.355 qs_forces 11 3.9 0.002 0.002 122.295 122.295 qs_energies 11 4.9 0.001 0.001 113.817 113.819 scf_env_do_scf 11 5.9 0.001 0.001 105.024 105.025 scf_env_do_scf_inner_loop 96 6.5 0.003 0.009 97.694 97.694 velocity_verlet 10 3.0 0.002 0.002 72.654 72.656 rebuild_ks_matrix 107 8.3 0.001 0.001 56.451 56.482 qs_ks_build_kohn_sham_matrix 107 9.3 0.019 0.021 56.450 56.481 sum_up_and_integrate 107 10.3 0.036 0.039 51.439 51.486 integrate_v_rspace 107 11.3 0.004 0.004 51.402 51.449 qs_ks_update_qs_env 107 7.6 0.001 0.001 49.740 49.768 qs_rho_update_rho 107 7.7 0.001 0.001 47.648 47.654 calculate_rho_elec 107 8.7 0.043 0.045 47.647 47.653 grid_integrate_task_list 107 12.3 45.170 46.493 45.170 46.493 grid_collocate_task_list 107 9.7 41.466 42.990 41.466 42.990 dbcsr_multiply_generic 1966 12.4 0.112 0.116 13.426 13.763 qs_scf_new_mos 96 7.5 0.001 0.001 10.822 10.872 qs_scf_loop_do_ot 96 8.5 0.001 0.001 10.822 10.872 ot_scf_mini 96 9.5 0.003 0.003 10.147 10.187 multiply_cannon 1966 13.4 0.194 0.200 8.919 9.111 multiply_cannon_loop 1966 14.4 0.179 0.193 8.116 8.411 rs_pw_transfer 878 11.9 0.013 0.015 6.721 8.054 init_scf_loop 11 6.9 0.000 0.000 7.315 7.315 density_rs2pw 107 9.7 0.008 0.008 5.721 7.048 mp_waitall_1 146670 16.2 6.658 7.047 6.658 7.047 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 6.900 6.904 init_scf_run 11 5.9 0.001 0.002 6.897 6.897 scf_env_initial_rho_setup 11 6.9 0.000 0.001 6.896 6.897 wfi_extrapolate 11 7.9 0.001 0.001 6.312 6.312 ot_mini 96 10.5 0.001 0.001 5.956 6.002 multiply_cannon_metrocomm3 15728 15.4 0.066 0.070 4.246 4.711 pw_transfer 1295 11.6 0.120 0.131 4.625 4.703 fft_wrap_pw1pw2 1081 12.6 0.012 0.013 4.385 4.456 mp_waitany 8968 13.7 3.055 4.423 3.055 4.423 potential_pw2rs 107 12.3 0.009 0.009 4.256 4.269 rs_pw_transfer_RS2PW_140 118 11.5 0.383 0.406 2.779 4.122 fft_wrap_pw1pw2_140 439 13.2 0.469 0.488 3.849 4.003 mp_alltoall_d11v 1998 13.7 2.211 3.345 2.211 3.345 fft3d_ps 1081 14.6 1.794 1.877 3.194 3.253 make_m2s 3932 13.4 0.064 0.067 3.094 3.132 multiply_cannon_multrec 15728 15.4 2.912 3.061 2.926 3.076 rs_gather_matrices 107 12.3 0.111 0.121 1.926 3.039 qs_ot_get_derivative 96 11.5 0.001 0.001 2.964 3.005 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 2.941 2.976 apply_single 107 13.6 0.001 0.001 2.941 2.976 ot_diis_step 96 11.5 0.005 0.005 2.971 2.971 make_images 3932 14.4 0.165 0.169 2.516 2.559 ------------------------------------------------------------------------------- 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=74.179, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=48.035, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=47.141, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=18.508, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_gemm_cosma", label="cp_gemm_cosma", y=10.441, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=6.247, 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 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="mp_waitany", label="mp_waitany", 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=23.227999999999994, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=41.466, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=45.17, 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_waitall_1", label="mp_waitall_1", y=6.658, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=2.912, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitany", label="mp_waitany", y=3.055, 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 0.375 0.375 254.206 254.206 qs_energies 1 2.0 0.000 0.000 252.916 252.916 scf_env_do_scf 1 3.0 0.000 0.000 250.583 250.583 qs_ks_update_qs_env 8 5.0 0.000 0.000 233.469 233.469 rebuild_ks_matrix 7 6.0 0.000 0.000 233.364 233.364 qs_ks_build_kohn_sham_matrix 7 7.0 0.002 0.002 233.364 233.364 hfx_ks_matrix 7 8.0 0.000 0.000 171.106 171.106 integrate_four_center 7 9.0 2.167 2.167 171.076 171.076 integrate_four_center_main 7 10.0 1.003 1.003 157.758 157.758 integrate_four_center_bin 447 11.0 156.755 156.755 156.755 156.755 scf_env_do_scf_inner_loop 7 4.0 0.001 0.001 142.320 142.320 init_scf_loop 1 4.0 0.000 0.000 108.250 108.250 cp_gemm 129 10.3 0.000 0.000 47.704 47.704 cp_gemm_cosma 129 11.3 47.704 47.704 47.704 47.704 admm_mo_calc_rho_aux 7 8.0 0.000 0.000 29.239 29.239 admm_fit_mo_coeffs 7 9.0 0.000 0.000 27.610 27.610 admm_mo_merge_derivs 7 8.0 0.000 0.000 24.345 24.345 merge_mo_derivs_diag 7 9.0 0.021 0.021 24.345 24.345 purify_mo_diag 7 10.0 0.001 0.001 15.845 15.845 prepare_preconditioner 1 5.0 0.000 0.000 13.343 13.343 make_preconditioner 1 6.0 0.000 0.000 13.343 13.343 fit_mo_coeffs 7 10.0 0.000 0.000 11.766 11.766 integrate_four_center_load 7 10.0 0.001 0.001 10.775 10.775 hfx_load_balance 1 11.0 0.002 0.002 10.774 10.774 arnoldi_normal_ev 11 9.3 0.002 0.002 8.201 8.201 estimate_cond_num 1 7.0 0.000 0.000 8.128 8.128 build_subspace 28 9.5 0.014 0.014 8.102 8.102 hfx_load_balance_count 1 12.0 5.374 5.374 5.374 5.374 hfx_load_balance_bin 1 12.0 5.369 5.369 5.369 5.369 qs_vxc_create 14 8.0 0.000 0.000 5.152 5.152 xc_vxc_pw_create 14 9.0 0.936 0.936 5.152 5.152 ------------------------------------------------------------------------------- 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 0.208 0.214 185.253 185.254 qs_energies 1 2.0 0.000 0.000 184.908 184.909 scf_env_do_scf 1 3.0 0.000 0.000 184.381 184.381 qs_ks_update_qs_env 8 5.0 0.000 0.000 181.625 181.625 rebuild_ks_matrix 7 6.0 0.000 0.000 181.613 181.613 qs_ks_build_kohn_sham_matrix 7 7.0 0.002 0.003 181.613 181.613 hfx_ks_matrix 7 8.0 0.000 0.001 171.059 171.060 integrate_four_center 7 9.0 0.095 0.416 171.044 171.044 integrate_four_center_main 7 10.0 0.005 0.005 154.750 158.955 integrate_four_center_bin 448 11.0 154.746 158.951 154.746 158.951 scf_env_do_scf_inner_loop 7 4.0 0.000 0.001 106.309 106.309 init_scf_loop 1 4.0 0.000 0.000 78.071 78.071 integrate_four_center_load 7 10.0 0.000 0.000 11.246 11.263 hfx_load_balance 1 11.0 0.001 0.002 11.246 11.263 mp_sync 70 11.3 4.219 8.409 4.219 8.409 hfx_load_balance_bin 1 12.0 5.285 5.621 5.285 5.621 hfx_load_balance_count 1 12.0 5.258 5.607 5.258 5.607 cp_gemm 129 10.3 0.000 0.000 3.701 3.706 cp_gemm_cosma 129 11.3 3.701 3.706 3.701 3.706 ------------------------------------------------------------------------------- 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=36.83699999999999, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_bin", label="integrate_four_center_bin", y=156.755, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="cp_gemm_cosma", label="cp_gemm_cosma", y=47.704, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_count", label="hfx_load_balance_count", y=5.374, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=5.369, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center", label="integrate_four_center", y=2.167, 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=11.948999999999984, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center_bin", label="integrate_four_center_bin", y=154.746, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="cp_gemm_cosma", label="cp_gemm_cosma", y=3.701, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_count", label="hfx_load_balance_count", y=5.258, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=5.285, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center", label="integrate_four_center", y=0.095, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="mp_sync", label="mp_sync", y=4.219, 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 0.013 319.623 319.623 qs_energies 1 2.0 0.000 0.000 319.133 319.133 mp2_main 1 3.0 0.000 0.000 312.976 312.976 mp2_gpw_main 1 4.0 0.000 0.000 312.515 312.515 rpa_ri_compute_en 1 5.0 0.000 0.000 301.165 301.165 rpa_num_int 1 6.0 0.000 0.000 301.143 301.143 compute_mat_P_omega 1 7.0 0.002 0.002 170.624 170.624 compute_mat_P_omega_contract 10 8.0 11.586 11.586 169.345 169.345 dbt_total 2336 9.6 0.016 0.016 163.026 163.026 cp_gemm 105 8.4 0.000 0.000 101.009 101.009 cp_gemm_cosma 105 9.4 101.009 101.009 101.009 101.009 dbt_contract 787 11.0 47.275 47.275 100.158 100.158 GW_matrix_operations 10 7.0 0.005 0.005 74.237 74.237 dbt_copy 1103 10.7 20.496 20.496 61.616 61.616 compute_mat_P_omega_calc_M_occ 250 9.0 11.552 11.552 61.250 61.250 dbt_tas_total 1149 12.2 0.225 0.225 49.871 49.871 dbt_tas_multiply 807 12.1 0.003 0.003 48.644 48.644 dbt_tas_dbm 807 14.1 0.005 0.005 39.301 39.301 dbm_multiply 807 16.1 39.288 39.288 39.288 39.288 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 37.838 37.838 rpa_num_int_RPA_matrix_operati 10 7.0 0.000 0.000 35.095 35.095 contract_P_omega_with_mat_L 10 8.0 0.000 0.000 33.366 33.366 dbt_tas_mm_1N 524 15.1 0.002 0.002 24.037 24.037 dbt_tas_copy 574 11.4 16.549 16.549 19.762 19.762 compute_QP_energies 1 7.0 0.000 0.000 19.284 19.284 compute_self_energy_cubic_gw 1 8.0 0.090 0.090 19.283 19.283 compute_mat_P_omega_copy_M_occ 250 9.0 0.001 0.001 17.920 17.920 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 14.514 14.514 dbt_tas_mm_2 251 15.0 0.002 0.002 13.527 13.527 compute_mat_P_omega_copy_M_vir 250 9.0 0.001 0.001 12.554 12.554 dbt_copy_nocomm 251 12.0 10.928 10.928 12.486 12.486 dbt_tas_reserve_blocks_index 3261 13.7 7.488 7.488 12.304 12.304 mp2_ri_gpw_compute_in 1 5.0 0.000 0.000 11.335 11.335 dbt_reserve_blocks_index 2280 12.5 1.577 1.577 10.338 10.338 dbt_reserve_blocks_index_array 2222 11.6 0.010 0.010 10.299 10.299 cp_fm_cholesky_invert 10 8.0 8.863 8.863 8.863 8.863 contract_cubic_gw 21 9.0 0.000 0.000 8.468 8.468 ------------------------------------------------------------------------------- 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 0.008 50.250 50.251 qs_energies 1 2.0 0.001 0.001 50.143 50.144 mp2_main 1 3.0 0.000 0.001 48.593 48.594 mp2_gpw_main 1 4.0 0.000 0.001 48.540 48.540 rpa_ri_compute_en 1 5.0 0.000 0.000 46.770 46.771 rpa_num_int 1 6.0 0.001 0.001 46.763 46.764 dbt_total 2336 9.6 0.017 0.017 35.687 35.688 compute_mat_P_omega 1 7.0 0.001 0.002 34.466 34.476 compute_mat_P_omega_contract 10 8.0 0.642 0.655 34.203 34.207 dbt_contract 787 11.0 1.753 1.911 26.056 26.061 dbt_tas_total 1149 12.2 0.071 0.076 22.646 22.647 dbt_tas_multiply 807 12.1 0.003 0.003 22.561 22.563 dbt_tas_dbm 807 14.1 0.005 0.005 15.547 15.548 dbm_multiply 807 16.1 12.504 13.204 12.504 13.204 compute_mat_P_omega_calc_M_occ 250 9.0 0.634 0.649 11.467 11.468 dbt_copy 1111 10.7 3.705 3.914 8.287 8.647 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 8.365 8.365 cp_gemm 105 8.4 0.000 0.000 8.016 8.030 cp_gemm_cosma 105 9.4 8.015 8.030 8.015 8.030 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 7.142 7.143 dbt_tas_mm_1N 524 15.1 0.002 0.003 6.309 6.874 dbt_tas_mm_2 251 15.0 0.002 0.002 6.536 6.536 mp_sync 8696 11.6 5.344 6.290 5.344 6.290 GW_matrix_operations 10 7.0 0.001 0.001 5.231 5.240 compute_QP_energies 1 7.0 0.000 0.000 3.839 3.839 compute_self_energy_cubic_gw 1 8.0 0.004 0.005 3.836 3.839 dbt_communicate_buffer 1098 11.7 0.091 0.098 3.255 3.436 mp_waitall_2 3776 14.7 3.106 3.367 3.106 3.367 contract_cubic_gw 21 9.0 0.000 0.000 2.944 2.944 rpa_num_int_RPA_matrix_operati 10 7.0 0.000 0.000 2.875 2.886 contract_P_omega_with_mat_L 10 8.0 0.000 0.000 2.768 2.777 dbt_reserve_blocks_index 2849 12.4 0.100 0.107 2.281 2.596 dbt_reserve_blocks_index_array 2791 11.4 0.011 0.012 2.278 2.593 dbt_tas_reserve_blocks_index 3300 13.8 0.260 0.277 2.238 2.553 dbm_reserve_blocks 3696 14.8 2.053 2.354 2.053 2.354 dbt_tas_replicate 396 14.1 1.174 1.401 2.210 2.253 mp2_ri_gpw_compute_in 1 5.0 0.001 0.001 1.765 1.767 convert_to_new_pgrid 2421 14.1 0.031 0.034 1.513 1.579 compute_mat_P_omega_copy_M_vir 250 9.0 0.001 0.002 1.553 1.559 dbm_copy 1608 15.1 1.473 1.539 1.473 1.539 scf_env_do_scf 1 3.0 0.000 0.000 1.497 1.497 scf_env_do_scf_inner_loop 17 4.0 0.001 0.001 1.497 1.497 compute_mat_P_omega_copy_M_occ 250 9.0 0.001 0.001 1.404 1.408 mp_max_i 1992 9.8 0.901 1.158 0.901 1.158 ------------------------------------------------------------------------------- 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=95.00599999999997, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="cp_gemm_cosma", label="cp_gemm_cosma", y=101.009, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbt_contract", label="dbt_contract", y=47.275, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=39.288, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbt_copy", label="dbt_copy", y=20.496, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbt_tas_copy", label="dbt_tas_copy", y=16.549, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="mp_waitall_2", label="mp_waitall_2", y=0.0, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="mp_sync", label="mp_sync", 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=15.823, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="cp_gemm_cosma", label="cp_gemm_cosma", y=8.015, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbt_contract", label="dbt_contract", y=1.753, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=12.504, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbt_copy", label="dbt_copy", y=3.705, 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_waitall_2", label="mp_waitall_2", y=3.106, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_sync", label="mp_sync", y=5.344, 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 0.019 0.019 688.153 688.153 qs_forces 1 2.0 0.000 0.000 687.370 687.370 rebuild_ks_matrix 7 6.6 0.000 0.000 678.231 678.231 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.001 678.231 678.231 hfx_ks_matrix 7 8.6 0.000 0.000 675.380 675.380 dbt_total 1051 10.5 0.009 0.009 556.308 556.308 hfx_ri_update_ks 7 9.6 0.000 0.000 370.600 370.600 hfx_ri_update_ks_Pmat 7 10.6 60.567 60.567 370.593 370.593 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 351.992 351.992 dbt_contract 283 11.7 115.888 115.888 350.738 350.738 qs_energies 1 3.0 0.000 0.000 335.319 335.319 scf_env_do_scf 1 4.0 0.000 0.000 334.892 334.892 qs_ks_update_qs_env 8 6.0 0.000 0.000 326.245 326.245 hfx_ri_update_forces 1 7.0 0.031 0.031 304.775 304.775 dbt_tas_total 533 12.7 3.010 3.010 223.367 223.367 dbt_tas_multiply 292 12.8 0.001 0.001 218.834 218.834 dbt_copy 444 11.5 99.988 99.988 201.025 201.025 dbt_tas_dbm 292 14.8 0.002 0.002 195.772 195.772 dbm_multiply 292 16.8 195.767 195.767 195.767 195.767 scf_env_do_scf_inner_loop 6 5.0 0.001 0.001 195.194 195.194 hfx_ri_update_ks_Pmat_KS 63 11.6 0.001 0.001 164.483 164.483 init_scf_loop 2 5.0 0.000 0.000 139.695 139.695 dbt_tas_mm_2 119 16.0 0.001 0.001 111.147 111.147 hfx_ri_forces_Pmat_2c_inv_2 9 8.0 0.000 0.000 56.353 56.353 dbt_tas_mm_3N 94 14.7 0.000 0.000 53.667 53.667 hfx_ri_forces_Pmat_metric 9 8.0 0.001 0.001 53.504 53.504 precalc_derivatives 1 8.0 0.007 0.007 52.785 52.785 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 43.666 43.666 hfx_ri_update_ks_Pmat_copy_2 63 11.6 0.000 0.000 43.221 43.221 dbt_tas_reserve_blocks_index 1569 14.6 16.052 16.052 35.678 35.678 dbt_tas_copy 287 12.3 28.025 28.025 35.222 35.222 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 33.388 33.388 dbt_reserve_blocks_index 1020 13.6 3.415 3.415 31.481 31.481 dbt_reserve_blocks_index_array 999 12.6 0.007 0.007 31.184 31.184 dbt_tas_mm_3T 77 17.1 0.000 0.000 30.797 30.797 hfx_ri_forces_Pmat_PQ_der 9 8.0 1.275 1.275 30.247 30.247 hfx_ri_forces_Pmat_Pmat_2 9 8.0 0.000 0.000 27.364 27.364 hfx_ri_forces_Pmat_2c_inv_1 1 8.0 4.187 4.187 26.819 26.819 build_3c_derivatives 2 9.0 1.299 1.299 25.997 25.997 get_force_from_3c_trace 18 8.0 24.915 24.915 24.915 24.915 dbt_communicate_buffer 157 12.8 20.275 20.275 20.276 20.276 dbt_split_blocks_generic 138 11.7 16.389 16.389 20.170 20.170 dbt_split_copyback 69 11.7 15.636 15.636 17.785 17.785 dbm_reserve_blocks 1813 15.4 16.446 16.446 16.446 16.446 ------------------------------------------------------------------------------- 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 0.018 0.020 99.675 99.676 qs_forces 1 2.0 0.000 0.001 99.504 99.504 rebuild_ks_matrix 7 6.6 0.000 0.000 98.482 98.483 qs_ks_build_kohn_sham_matrix 7 7.6 0.002 0.003 98.482 98.483 hfx_ks_matrix 7 8.6 0.000 0.001 96.968 96.968 dbt_total 1051 10.5 0.009 0.011 88.798 88.798 dbt_contract 283 11.7 4.807 5.065 69.520 69.534 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 65.820 65.820 dbt_tas_total 533 12.7 0.140 0.375 63.843 63.844 hfx_ri_update_forces 1 7.0 0.002 0.003 61.316 61.316 dbt_tas_multiply 292 12.8 0.001 0.002 60.757 60.757 dbt_tas_dbm 292 14.8 0.002 0.002 46.481 46.482 dbm_multiply 292 16.8 41.415 42.948 41.415 42.948 hfx_ri_update_ks 7 9.6 0.000 0.000 35.651 35.651 hfx_ri_update_ks_Pmat 7 10.6 2.440 2.621 35.649 35.650 qs_energies 1 3.0 0.000 0.000 33.667 33.667 scf_env_do_scf 1 4.0 0.000 0.000 33.468 33.468 qs_ks_update_qs_env 8 6.0 0.000 0.000 32.663 32.664 dbt_tas_mm_2 119 16.0 0.001 0.002 20.139 20.139 scf_env_do_scf_inner_loop 6 5.0 0.000 0.001 18.841 18.841 hfx_ri_forces_Pmat_metric 9 8.0 0.001 0.001 18.149 18.149 dbt_copy 464 11.6 5.513 5.742 15.241 15.622 init_scf_loop 2 5.0 0.000 0.000 14.626 14.626 hfx_ri_update_ks_Pmat_KS 63 11.6 0.001 0.001 13.907 13.907 dbt_tas_mm_3N 94 14.7 0.001 0.001 11.848 12.465 mp_sync 3797 12.3 9.128 12.450 9.128 12.450 dbt_tas_mm_3T 77 17.1 0.000 0.001 11.509 12.284 hfx_ri_forces_Pmat_2c_inv_2 9 8.0 0.000 0.000 11.572 11.572 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 9.136 9.136 hfx_ri_forces_Pmat_PQ_der 9 8.0 0.063 0.066 8.789 8.789 hfx_ri_forces_Pmat_Pmat_2 9 8.0 0.000 0.000 7.469 7.483 dbm_reserve_blocks 1848 15.6 5.988 6.856 5.988 6.856 dbt_tas_reserve_blocks_index 1602 14.7 0.568 0.603 6.187 6.727 mp_waitall_2 1484 15.5 5.862 6.345 5.862 6.345 dbt_reserve_blocks_index 1191 13.5 0.159 0.168 5.297 5.815 dbt_reserve_blocks_index_array 1170 12.5 0.007 0.008 5.260 5.774 precalc_derivatives 1 8.0 0.003 0.003 5.649 5.650 dbt_tas_replicate 246 14.5 1.503 2.086 4.937 5.315 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 4.353 4.353 convert_to_new_pgrid 876 14.8 0.029 0.037 3.582 4.328 hfx_ri_forces_Pmat_2c_inv_1 1 8.0 0.158 0.166 4.274 4.278 dbm_copy 578 15.8 3.524 4.269 3.524 4.269 dbt_tas_communicate_buffer 498 15.8 0.020 0.023 3.183 3.662 dbt_communicate_buffer 328 12.3 0.021 0.022 3.031 3.164 build_3c_derivatives 2 9.0 0.600 0.658 3.134 3.147 dbt_tas_replicate_communicate_ 127 15.0 0.003 0.004 2.517 2.939 hfx_ri_forces_Pmat_Pmat_1 3 8.0 0.000 0.000 2.431 2.431 dbt_tas_copy 141 13.3 1.231 1.299 2.202 2.362 hfx_ri_pre_scf_Pmat_RIx3C 9 13.0 0.000 0.000 2.285 2.296 hfx_ri_update_ks_Pmat_copy_2 63 11.6 0.000 0.000 2.089 2.089 dbt_tas_reshape 252 14.0 0.005 0.005 1.737 2.062 dbt_tas_merge 119 13.0 0.927 1.413 1.473 2.013 ------------------------------------------------------------------------------- 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=171.4720000000001, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=195.767, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_contract", label="dbt_contract", y=115.888, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_copy", label="dbt_copy", y=99.988, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=60.567, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_tas_copy", label="dbt_tas_copy", y=28.025, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=16.446, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="mp_sync", label="mp_sync", y=0.0, 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 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=23.29100000000001, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=41.415, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_contract", label="dbt_contract", y=4.807, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_copy", label="dbt_copy", y=5.513, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=2.44, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_tas_copy", label="dbt_tas_copy", y=1.231, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=5.988, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_sync", label="mp_sync", y=9.128, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=5.862, 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 0.102 0.102 187.866 187.866 qs_energies 1 2.0 0.000 0.000 186.179 186.179 scf_env_do_scf 1 3.0 0.000 0.000 176.548 176.548 scf_env_do_scf_inner_loop 15 4.0 0.002 0.002 176.548 176.548 qs_scf_new_mos 15 5.0 0.000 0.000 78.268 78.268 qs_ks_update_qs_env 15 5.0 0.000 0.000 68.248 68.248 rebuild_ks_matrix 15 6.0 0.000 0.000 67.893 67.893 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.002 67.893 67.893 eigensolver 15 6.0 0.002 0.002 64.472 64.472 cp_fm_diag_elpa 15 7.0 0.000 0.000 50.517 50.517 cp_fm_diag_elpa_base 15 8.0 45.962 45.962 50.517 50.517 qs_vxc_create 15 8.0 0.037 0.037 44.036 44.036 calculate_dispersion_nonloc 15 9.0 8.857 8.857 38.242 38.242 pw_transfer 1191 9.8 0.088 0.088 25.896 25.896 fft_wrap_pw1pw2 1086 10.9 0.012 0.012 25.624 25.624 qs_rho_update_rho 16 5.0 0.000 0.000 23.984 23.984 calculate_rho_elec 16 6.0 0.337 0.337 23.984 23.984 grid_collocate_task_list 16 7.0 22.461 22.461 22.461 22.461 sum_up_and_integrate 15 8.0 0.079 0.079 22.316 22.316 integrate_v_rspace 15 9.0 0.035 0.035 22.237 22.237 grid_integrate_task_list 15 10.0 21.625 21.625 21.625 21.625 fft_wrap_pw1pw2_150 765 12.0 3.297 3.297 19.405 19.405 copy_dbcsr_to_fm 16 5.9 0.001 0.001 11.002 11.002 fft3d_s 1087 12.8 10.590 10.590 10.601 10.601 pw_scatter_s 585 13.0 10.156 10.156 10.156 10.156 dbcsr_complete_redistribute 46 8.3 3.582 3.582 9.793 9.793 cp_fm_cholesky_restore 45 7.0 9.456 9.456 9.456 9.456 cp_fm_upper_to_full 30 8.0 9.051 9.051 9.051 9.051 vdW_energy 15 10.0 7.644 7.644 7.644 7.644 gspace_mixing 14 5.0 0.272 0.272 7.311 7.311 broyden_mixing 14 6.0 6.579 6.579 6.580 6.580 fft_wrap_pw1pw2_200 197 11.5 0.333 0.333 5.969 5.969 xc_vxc_pw_create 15 9.0 1.600 1.600 5.757 5.757 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 4.506 4.506 init_scf_run 1 3.0 0.000 0.000 4.363 4.363 dbcsr_finalize 159 9.9 0.019 0.019 4.216 4.216 dbcsr_merge_all 91 11.1 0.072 0.072 4.068 4.068 ------------------------------------------------------------------------------- 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 0.015 0.018 82.680 82.681 qs_energies 1 2.0 0.000 0.001 82.302 82.303 scf_env_do_scf 1 3.0 0.000 0.000 77.255 77.256 scf_env_do_scf_inner_loop 15 4.0 0.001 0.002 77.255 77.256 qs_ks_update_qs_env 15 5.0 0.000 0.000 38.184 38.195 rebuild_ks_matrix 15 6.0 0.000 0.000 38.136 38.148 qs_ks_build_kohn_sham_matrix 15 7.0 0.004 0.004 38.136 38.148 sum_up_and_integrate 15 8.0 0.011 0.014 23.045 23.080 integrate_v_rspace 15 9.0 0.001 0.001 23.033 23.066 qs_rho_update_rho 16 5.0 0.000 0.000 23.011 23.014 calculate_rho_elec 16 6.0 0.011 0.012 23.010 23.014 grid_integrate_task_list 15 10.0 21.240 22.173 21.240 22.173 grid_collocate_task_list 16 7.0 20.920 21.857 20.920 21.857 qs_scf_new_mos 15 5.0 0.001 0.001 16.550 16.575 eigensolver 15 6.0 0.002 0.002 15.190 15.200 qs_vxc_create 15 8.0 0.001 0.001 14.598 14.612 calculate_dispersion_nonloc 15 9.0 1.399 1.483 11.898 11.911 cp_fm_diag_elpa 15 7.0 0.000 0.000 11.106 11.112 cp_fm_diag_elpa_base 15 8.0 10.873 10.908 11.102 11.104 pw_transfer 1191 9.8 0.125 0.159 10.801 10.887 fft_wrap_pw1pw2 1086 10.9 0.019 0.023 10.525 10.615 fft3d_ps 1086 12.9 4.512 4.697 7.934 8.140 fft_wrap_pw1pw2_150 765 12.0 0.609 0.644 7.035 7.111 cp_fm_cholesky_restore 45 7.0 3.860 3.913 3.860 3.913 fft_wrap_pw1pw2_200 197 11.5 0.350 0.375 3.361 3.404 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 3.152 3.152 build_core_hamiltonian_matrix 1 4.0 0.000 0.000 2.702 2.979 xc_vxc_pw_create 15 9.0 0.052 0.068 2.699 2.717 rs_pw_transfer 158 9.4 0.002 0.003 2.012 2.628 mp_alltoall_z22v 1086 14.9 2.143 2.528 2.143 2.528 density_rs2pw 16 7.0 0.002 0.002 1.940 2.343 vdW_energy 15 10.0 2.060 2.180 2.060 2.180 mp_waitany 520 11.3 1.390 2.161 1.390 2.161 build_core_ppnl 1 5.0 1.805 2.008 1.805 2.008 rs_pw_transfer_RS2PW_200 18 8.8 0.068 0.077 1.136 1.946 x_to_yz 585 14.0 0.817 0.854 1.770 1.891 yz_to_x 501 13.7 0.432 0.497 1.622 1.848 ------------------------------------------------------------------------------- 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=67.616, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=45.962, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=22.461, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=21.625, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="fft3d_s", label="fft3d_s", y=10.59, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="pw_scatter_s", label="pw_scatter_s", y=10.156, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=9.456, 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=21.275000000000006, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=10.873, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=20.92, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=21.24, 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=3.86, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=4.512, 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 0.080 304.736 304.736 qs_energies 1 2.0 0.000 0.000 304.578 304.578 ls_scf 1 3.0 0.000 0.000 302.781 302.781 ls_scf_main 1 4.0 0.002 0.002 289.326 289.326 density_matrix_trs4 11 5.0 0.011 0.011 172.933 172.933 ls_scf_dm_to_ks 11 5.0 0.000 0.000 109.273 109.273 dbcsr_multiply_generic 185 6.1 0.619 0.619 108.895 108.895 matrix_ls_to_qs 11 6.0 0.000 0.000 104.930 104.930 multiply_cannon 185 7.1 3.102 3.102 72.890 72.890 dbcsr_complete_redistribute 23 7.5 40.614 40.614 56.063 56.063 dbcsr_copy_into_existing 11 7.0 53.923 53.923 53.923 53.923 multiply_cannon_loop 185 8.1 0.384 0.384 51.951 51.951 matrix_decluster 11 7.0 0.000 0.000 51.006 51.006 multiply_cannon_multrec 185 9.1 49.831 49.831 49.881 49.881 arnoldi_extremal 12 6.1 0.000 0.000 45.554 45.554 arnoldi_normal_ev 12 7.1 0.027 0.027 45.554 45.554 build_subspace 23 8.1 0.131 0.131 44.929 44.929 dbcsr_matrix_vector_mult 652 9.0 0.256 0.256 34.596 34.596 dbcsr_matrix_vector_mult_local 652 10.0 33.016 33.016 33.024 33.024 make_m2s 370 7.1 0.030 0.030 29.457 29.457 make_images 370 8.1 7.310 7.310 27.089 27.089 dbcsr_finalize 646 7.5 0.191 0.191 20.956 20.956 dbcsr_merge_all 597 8.5 3.432 3.432 18.842 18.842 setup_rec_index_2d 370 8.1 17.692 17.692 17.692 17.692 dbcsr_sort_indices 1103 9.9 16.402 16.402 16.402 16.402 quick_finalize 395 10.0 0.453 0.453 13.951 13.951 tree_to_linear_d 110 9.4 13.198 13.198 13.198 13.198 dbcsr_special_finalize 370 9.1 0.003 0.003 12.859 12.859 ls_scf_init_scf 1 4.0 0.000 0.000 12.307 12.307 ls_scf_init_matrix_S 1 5.0 0.000 0.000 11.875 11.875 matrix_sqrt_Newton_Schulz 1 6.0 0.001 0.001 10.999 10.999 dbcsr_dot_sd 144 6.3 8.970 8.970 8.971 8.971 dbcsr_frobenius_norm 142 6.1 7.595 7.595 7.597 7.597 matrix_qs_to_ls 12 5.1 0.000 0.000 7.426 7.426 matrix_cluster 12 6.1 0.000 0.000 7.425 7.425 make_images_data 370 9.1 0.009 0.009 6.741 6.741 ------------------------------------------------------------------------------- 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 0.008 0.010 90.209 90.209 qs_energies 1 2.0 0.000 0.000 90.117 90.117 ls_scf 1 3.0 0.000 0.000 90.039 90.040 ls_scf_main 1 4.0 0.000 0.003 86.448 86.448 density_matrix_trs4 11 5.0 0.008 0.012 82.720 82.794 dbcsr_multiply_generic 185 6.1 0.077 0.090 77.825 78.030 multiply_cannon 185 7.1 0.039 0.043 64.886 65.922 multiply_cannon_loop 185 8.1 0.204 0.213 61.215 63.011 multiply_cannon_multrec 1480 9.1 39.982 42.109 40.444 42.582 mp_waitall_1 11936 10.3 18.898 21.057 18.898 21.057 multiply_cannon_metrocomm3 1480 9.1 0.017 0.019 11.106 14.581 make_m2s 370 7.1 0.033 0.036 8.785 8.856 make_images 370 8.1 0.703 0.727 8.667 8.741 multiply_cannon_metrocomm1 1480 9.1 0.010 0.012 4.595 6.442 calculate_norms 2960 9.1 4.795 5.009 4.795 5.009 make_images_data 370 9.1 0.012 0.013 3.563 3.862 mp_sum_l 1039 5.9 2.810 3.690 2.810 3.690 arnoldi_extremal 12 6.1 0.000 0.001 3.589 3.598 arnoldi_normal_ev 12 7.1 0.002 0.008 3.589 3.597 build_subspace 23 8.1 0.035 0.048 3.469 3.472 ls_scf_dm_to_ks 11 5.0 0.000 0.000 3.215 3.289 hybrid_alltoall_any 393 9.9 0.298 1.500 2.881 3.267 dbcsr_matrix_vector_mult 652 9.0 0.018 0.078 2.969 3.035 dbcsr_complete_redistribute 23 7.5 1.846 1.898 2.900 2.979 matrix_ls_to_qs 11 6.0 0.000 0.000 2.873 2.958 ls_scf_init_scf 1 4.0 0.000 0.000 2.761 2.762 ls_scf_init_matrix_S 1 5.0 0.000 0.000 2.726 2.733 matrix_decluster 11 7.0 0.000 0.000 2.608 2.693 dbcsr_multiply_generic_mpsum_f 137 7.1 0.000 0.001 1.898 2.684 dbcsr_matrix_vector_mult_local 652 10.0 2.414 2.556 2.418 2.560 matrix_sqrt_Newton_Schulz 1 6.0 0.001 0.001 2.493 2.495 make_images_pack 370 9.1 2.315 2.490 2.319 2.494 buffer_matrices_ensure_size 370 8.1 2.073 2.202 2.073 2.202 dbcsr_finalize 646 7.5 0.013 0.014 1.909 2.037 dbcsr_add_d 280 6.0 0.001 0.002 1.954 2.034 dbcsr_add_anytype 280 7.0 1.047 1.113 1.952 2.033 ------------------------------------------------------------------------------- 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=109.66, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_copy_into_existing", label="dbcsr_copy_into_existing", y=53.923, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=49.831, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_complete_redistribute", label="dbcsr_complete_redistribute", y=40.614, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=33.016, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="setup_rec_index_2d", label="setup_rec_index_2d", y=17.692, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", 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 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=19.464, 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=39.982, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="dbcsr_complete_redistribute", label="dbcsr_complete_redistribute", y=1.846, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=2.414, 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_waitall_1", label="mp_waitall_1", y=18.898, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="calculate_norms", label="calculate_norms", y=4.795, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=2.81, 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 94.025 94.025 lib_test 1 2.0 0.000 0.000 94.018 94.018 dbcsr_run_tests 3 3.0 0.002 0.002 94.018 94.018 test_multiplies_multiproc 3 4.0 0.001 0.001 74.680 74.680 dbcsr_redistribute 9 5.0 47.399 47.399 50.831 50.831 dbcsr_multiply_generic 9 5.0 0.001 0.001 22.172 22.172 dbcsr_make_random_matrix 9 4.0 14.022 14.022 19.244 19.244 multiply_cannon 9 6.0 0.002 0.002 15.579 15.579 multiply_cannon_loop 9 7.0 0.003 0.003 15.060 15.060 multiply_cannon_multrec 9 8.0 15.056 15.056 15.057 15.057 dbcsr_finalize 27 5.7 0.004 0.004 9.043 9.043 dbcsr_merge_all 18 6.5 3.267 3.267 8.316 8.316 tree_to_linear_d 9 7.0 3.156 3.156 3.156 3.156 mp_alltoall_d11v 27 6.0 3.081 3.081 3.081 3.081 dbcsr_data_release 975 7.6 2.465 2.465 2.465 2.465 make_m2s 18 6.0 0.001 0.001 2.174 2.174 make_images 18 7.0 0.675 0.675 2.099 2.099 ------------------------------------------------------------------------------- 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 0.006 25.118 25.119 lib_test 1 2.0 0.000 0.001 25.088 25.108 dbcsr_run_tests 3 3.0 0.001 0.001 25.086 25.106 test_multiplies_multiproc 3 4.0 0.001 0.002 23.923 24.009 dbcsr_multiply_generic 9 5.0 0.001 0.002 22.037 22.121 multiply_cannon 9 6.0 0.002 0.002 19.819 20.205 multiply_cannon_loop 9 7.0 0.003 0.004 19.405 19.762 multiply_cannon_multrec 72 8.0 16.369 17.229 16.371 17.230 mp_waitall_1 576 9.2 3.451 4.062 3.451 4.062 multiply_cannon_metrocomm1 72 8.0 0.002 0.002 2.667 3.284 dbcsr_make_random_matrix 9 4.0 0.896 0.928 1.119 1.157 mp_sum_l 310 2.7 0.493 1.044 0.493 1.044 dbcsr_multiply_generic_mpsum_f 9 6.0 0.000 0.000 0.489 1.040 make_m2s 18 6.0 0.001 0.001 0.928 0.999 make_images 18 7.0 0.026 0.026 0.925 0.996 dbcsr_finalize 27 5.7 0.000 0.001 0.857 0.963 multiply_cannon_metrocomm3 72 8.0 0.000 0.001 0.356 0.931 dbcsr_merge_all 18 6.5 0.136 0.162 0.753 0.849 dbcsr_data_release 444 7.6 0.659 0.753 0.659 0.753 dbcsr_redistribute 9 5.0 0.383 0.453 0.661 0.706 dbcsr_destroy 111 5.9 0.009 0.056 0.566 0.656 make_images_data 18 8.0 0.001 0.001 0.476 0.568 dbcsr_data_copy_aa2 18 7.5 0.441 0.512 0.441 0.512 hybrid_alltoall_any 18 9.0 0.042 0.181 0.388 0.503 ------------------------------------------------------------------------------- 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=8.659999999999997, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_redistribute", label="dbcsr_redistribute", y=47.399, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=15.056, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=14.022, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_merge_all", label="dbcsr_merge_all", y=3.267, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="tree_to_linear_d", label="tree_to_linear_d", y=3.156, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_data_release", label="dbcsr_data_release", y=2.465, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="mp_sum_l", label="mp_sum_l", y=0.0, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", 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=2.7310000000000016, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_redistribute", label="dbcsr_redistribute", y=0.383, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=16.369, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=0.896, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_merge_all", label="dbcsr_merge_all", y=0.136, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="tree_to_linear_d", label="tree_to_linear_d", y=0.0, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_data_release", label="dbcsr_data_release", y=0.659, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=0.493, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=3.451, 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 0.043 0.043 138.692 138.692 qs_mol_dyn_low 1 2.0 0.004 0.004 136.729 136.729 velocity_verlet 5 3.0 0.004 0.004 110.233 110.233 qmmm_el_coupling 6 3.8 0.000 0.000 64.080 64.080 qmmm_elec_with_gaussian 6 4.8 0.172 0.172 64.074 64.074 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 63.096 63.096 qmmm_elec_gaussian_low_G 6 6.8 61.690 61.690 61.690 61.690 qs_forces 6 3.8 0.001 0.001 56.015 56.015 qs_energies 6 4.8 0.000 0.000 49.762 49.762 scf_env_do_scf 6 5.8 0.000 0.000 45.879 45.879 scf_env_do_scf_inner_loop 39 6.8 0.003 0.003 38.452 38.452 rebuild_ks_matrix 45 8.4 0.000 0.000 38.108 38.108 qs_ks_build_kohn_sham_matrix 45 9.4 0.007 0.007 38.108 38.108 qs_ks_update_qs_env 45 7.8 0.000 0.000 32.619 32.619 pw_transfer 966 11.9 0.067 0.067 22.895 22.895 fft_wrap_pw1pw2 801 13.0 0.008 0.008 22.572 22.572 fft_wrap_pw1pw2_150 507 14.3 2.371 2.371 22.053 22.053 qs_vxc_create 45 10.4 0.001 0.001 20.500 20.500 xc_vxc_pw_create 45 11.4 4.138 4.138 20.499 20.499 qs_rho_update_rho 45 7.9 0.000 0.000 10.152 10.152 calculate_rho_elec 45 8.9 0.884 0.884 10.152 10.152 pw_scatter_s 429 15.4 10.114 10.114 10.114 10.114 xc_rho_set_and_dset_create 45 12.4 0.240 0.240 9.415 9.415 fft3d_s 802 15.0 8.753 8.753 8.763 8.763 qmmm_forces 6 3.8 0.001 0.001 8.108 8.108 fist_calc_energy_force 6 3.8 0.002 0.002 7.742 7.742 qmmm_forces_with_gaussian 6 4.8 0.131 0.131 7.602 7.602 init_scf_loop 6 6.8 0.000 0.000 7.421 7.421 pw_integral_ab 2539 7.4 7.306 7.306 7.306 7.306 force_nonbond 6 4.8 6.543 6.543 6.543 6.543 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 6.481 6.481 qs_ks_ddapc 45 10.4 0.001 0.001 6.438 6.438 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 5.501 5.501 qmmm_forces_gaussian_low_G 6 6.8 5.391 5.391 5.391 5.391 pw_poisson_solve 51 9.9 2.229 2.229 5.129 5.129 grid_collocate_task_list 45 9.9 4.687 4.687 4.687 4.687 density_rs2pw 45 9.9 0.003 0.003 4.581 4.581 sum_up_and_integrate 45 10.4 0.233 0.233 4.315 4.315 integrate_v_rspace 45 11.4 0.013 0.013 4.082 4.082 cp_ddapc_apply_CD 45 11.4 0.006 0.006 4.011 4.011 ------------------------------------------------------------------------------- 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 0.034 0.036 83.803 83.804 qs_mol_dyn_low 1 2.0 0.004 0.005 82.213 82.311 qs_forces 6 3.8 0.001 0.001 60.486 60.486 qs_energies 6 4.8 0.001 0.001 57.665 57.665 scf_env_do_scf 6 5.8 0.000 0.001 56.193 56.193 scf_env_do_scf_inner_loop 113 6.2 0.003 0.009 53.951 53.953 rebuild_ks_matrix 119 8.1 0.000 0.000 39.670 39.689 qs_ks_build_kohn_sham_matrix 119 9.1 0.020 0.022 39.669 39.689 qs_ks_update_qs_env 119 7.3 0.001 0.001 37.307 37.326 velocity_verlet 5 3.0 0.002 0.002 34.497 34.501 pw_transfer 2446 11.8 0.267 0.298 24.888 25.189 fft_wrap_pw1pw2 2059 12.8 0.033 0.036 24.120 24.480 fft_wrap_pw1pw2_150 1321 14.0 2.130 2.316 23.472 23.760 qs_vxc_create 119 10.1 0.003 0.004 19.924 19.927 xc_vxc_pw_create 119 11.1 0.437 0.586 19.921 19.924 fft3d_ps 2059 14.8 10.868 11.911 18.249 18.642 qs_rho_update_rho 119 7.3 0.001 0.001 15.844 15.844 calculate_rho_elec 119 8.3 0.086 0.095 15.843 15.844 sum_up_and_integrate 119 10.1 0.084 0.090 14.423 14.503 integrate_v_rspace 119 11.1 0.004 0.005 14.339 14.423 qmmm_forces 6 3.8 0.003 0.003 12.029 12.030 qmmm_forces_with_gaussian 6 4.8 0.365 0.452 11.738 11.834 rs_pw_transfer 988 11.5 0.015 0.018 10.811 11.422 xc_rho_set_and_dset_create 119 12.1 0.498 0.580 9.524 9.986 density_rs2pw 119 9.3 0.011 0.012 9.414 9.929 qmmm_el_coupling 6 3.8 0.000 0.000 8.546 8.640 qmmm_elec_with_gaussian 6 4.8 0.320 0.421 8.543 8.637 potential_pw2rs 119 12.1 0.011 0.012 8.355 8.367 grid_collocate_task_list 119 9.3 6.157 6.623 6.157 6.623 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 5.764 5.855 grid_integrate_task_list 119 12.1 5.582 5.847 5.582 5.847 mp_alltoall_z22v 2059 16.8 4.492 5.814 4.492 5.814 qmmm_forces_gaussian_low_G 6 6.8 4.698 4.768 4.698 4.768 rs_pw_transfer_PW2RS_150 125 13.9 2.370 2.441 4.646 4.677 rs_pw_transfer_RS2PW_150 125 11.2 1.891 2.026 3.882 4.479 pw_restrict_s3 18 5.8 2.387 2.421 4.393 4.465 mp_waitany 4028 12.8 3.388 4.375 3.388 4.375 x_to_yz 1095 16.3 1.769 1.937 4.086 4.253 yz_to_x 964 15.3 1.073 1.236 3.248 4.155 qmmm_elec_with_gaussian:spline 6 5.8 0.000 0.000 3.528 3.625 pw_prolongate_s3 18 6.8 1.901 2.076 3.528 3.625 qs_scf_new_mos 113 7.2 0.001 0.001 3.569 3.578 qs_scf_loop_do_ot 113 8.2 0.001 0.001 3.568 3.577 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 3.387 3.459 ot_scf_mini 113 9.2 0.002 0.002 3.413 3.423 dbcsr_multiply_generic 2588 12.3 0.096 0.112 3.264 3.350 qs_ks_ddapc 119 10.1 0.003 0.003 2.745 2.890 mp_sum_dm3 33 5.7 2.343 2.684 2.343 2.684 pw_integral_ab 2761 7.7 2.077 2.116 2.428 2.613 qmmm_elec_gaussian_low_G 6 6.8 2.443 2.511 2.443 2.511 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 2.373 2.374 pw_gather_p 964 14.3 1.883 2.283 1.883 2.283 init_scf_loop 6 6.8 0.000 0.000 2.238 2.238 ot_mini 113 10.2 0.001 0.001 2.169 2.183 mp_waitall_1 188862 16.2 1.947 2.176 1.947 2.176 pw_scatter_p 1095 15.3 1.761 1.842 1.761 1.842 pw_derive 732 12.5 1.642 1.829 1.642 1.829 qs_ot_get_derivative 113 11.2 0.001 0.001 1.715 1.724 ------------------------------------------------------------------------------- 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=34.208, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=61.69, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_scatter_s", label="pw_scatter_s", y=10.114, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_s", label="fft3d_s", y=8.753, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_integral_ab", label="pw_integral_ab", y=7.306, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="force_nonbond", label="force_nonbond", y=6.543, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=5.391, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=4.687, 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=47.486, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=2.443, 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=2.077, 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="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=4.698, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=6.157, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=10.868, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=5.582, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=4.492, yerr=0.0 Summary: Performance test took 52 minutes. Status: OK Uploading artifacts... done EndDate: 2022-02-03 14:09:09+00:00