StartDate: 2023-02-16 11:05:57+00:00 CpuId: 32x AMD EPYC (3rd Gen) (Milan) [Zen 3], 7nm (SMT disabled) CommitSHA: 64b48f68786da735e4ff87e2b764c1eaa5e5eb12 CommitTime: 2023-02-16 10:54:27 +0100 CommitAuthor: Ole Schütt CommitSubject: Conventions: Assign more specific c-numbers Populating docker build cache... done. #################### Building Image cp2k-perf-openmp #################### Dockerfile: /tools/docker/Dockerfile.test_performance Build-Path: / Build-Args: GIT_COMMIT_SHA=64b48f68786da735e4ff87e2b764c1eaa5e5eb12 Sending build context to Docker daemon 367.2MB Step 1/42 : FROM ubuntu:22.04 22.04: Pulling from library/ubuntu 677076032cca: Pulling fs layer 677076032cca: Verifying Checksum 677076032cca: Download complete 677076032cca: Pull complete Digest: sha256:9a0bdde4188b896a372804be2384015e90e3f84906b750c1a53539b585fbbe7f Status: Downloaded newer image for ubuntu:22.04 ---> 58db3edaf2be Step 2/42 : WORKDIR /opt/cp2k-toolchain ---> Using cache ---> edd1e7417230 Step 3/42 : COPY ./tools/toolchain/install_requirements*.sh ./ ---> Using cache ---> e333f6f6eb13 Step 4/42 : RUN ./install_requirements.sh ubuntu:22.04 ---> Using cache ---> 0dc3a5e6039e Step 5/42 : RUN mkdir scripts ---> Using cache ---> fcdc33ff0215 Step 6/42 : 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 ---> ac3f34dc87e0 Step 7/42 : COPY ./tools/toolchain/install_cp2k_toolchain.sh . ---> Using cache ---> 204996a81221 Step 8/42 : RUN ./install_cp2k_toolchain.sh --install-all --with-gcc=system --dry-run ---> Using cache ---> d7c2a3fffd92 Step 9/42 : COPY ./tools/toolchain/scripts/stage0/ ./scripts/stage0/ ---> Using cache ---> 1a5a1c3b23ac Step 10/42 : RUN ./scripts/stage0/install_stage0.sh && rm -rf ./build ---> Using cache ---> bc03c3af2a3a Step 11/42 : COPY ./tools/toolchain/scripts/stage1/ ./scripts/stage1/ ---> Using cache ---> dde44b019e59 Step 12/42 : RUN ./scripts/stage1/install_stage1.sh && rm -rf ./build ---> Using cache ---> 764d28356a4a Step 13/42 : COPY ./tools/toolchain/scripts/stage2/ ./scripts/stage2/ ---> Using cache ---> ca51e9f6f59f Step 14/42 : RUN ./scripts/stage2/install_stage2.sh && rm -rf ./build ---> Using cache ---> e8d56e65cb06 Step 15/42 : COPY ./tools/toolchain/scripts/stage3/ ./scripts/stage3/ ---> Using cache ---> a70f414de598 Step 16/42 : RUN ./scripts/stage3/install_stage3.sh && rm -rf ./build ---> Using cache ---> a7f7217d5823 Step 17/42 : COPY ./tools/toolchain/scripts/stage4/ ./scripts/stage4/ ---> Using cache ---> 56fc65f62d41 Step 18/42 : RUN ./scripts/stage4/install_stage4.sh && rm -rf ./build ---> Using cache ---> 6651e0bb2b9c Step 19/42 : COPY ./tools/toolchain/scripts/stage5/ ./scripts/stage5/ ---> Using cache ---> 23c5669f1bcc Step 20/42 : RUN ./scripts/stage5/install_stage5.sh && rm -rf ./build ---> Using cache ---> 030d3c0b6987 Step 21/42 : COPY ./tools/toolchain/scripts/stage6/ ./scripts/stage6/ ---> Using cache ---> 07c71248410e Step 22/42 : RUN ./scripts/stage6/install_stage6.sh && rm -rf ./build ---> Using cache ---> c7dafdd15c4d Step 23/42 : COPY ./tools/toolchain/scripts/stage7/ ./scripts/stage7/ ---> Using cache ---> d00e2bd2f815 Step 24/42 : RUN ./scripts/stage7/install_stage7.sh && rm -rf ./build ---> Using cache ---> dfc253b29b2f Step 25/42 : COPY ./tools/toolchain/scripts/stage8/ ./scripts/stage8/ ---> Using cache ---> a54e1f32ffeb Step 26/42 : RUN ./scripts/stage8/install_stage8.sh && rm -rf ./build ---> Using cache ---> 58de3dd6b470 Step 27/42 : COPY ./tools/toolchain/scripts/arch_base.tmpl ./tools/toolchain/scripts/generate_arch_files.sh ./scripts/ ---> Using cache ---> 62910f2df29e Step 28/42 : RUN ./scripts/generate_arch_files.sh && rm -rf ./build ---> Using cache ---> 90fb2fec2b2e Step 29/42 : WORKDIR /opt/cp2k ---> Using cache ---> c7247b5bc7d6 Step 30/42 : COPY ./Makefile . ---> Using cache ---> ff757054de8b Step 31/42 : COPY ./src ./src ---> Using cache ---> 83f4ad5998bc Step 32/42 : COPY ./exts ./exts ---> Using cache ---> e3b92ba05aa8 Step 33/42 : COPY ./tools/build_utils ./tools/build_utils ---> Using cache ---> 707e9c3b94ed Step 34/42 : RUN /bin/bash -c " mkdir -p arch && ln -vs /opt/cp2k-toolchain/install/arch/local.psmp ./arch/ && echo 'Compiling cp2k...' && source /opt/cp2k-toolchain/install/setup && ( make -j ARCH=local VERSION=psmp &> /dev/null || true ) && ( [ ! -f ./exe/local/cp2k.psmp ] || ldd ./exe/local/cp2k.psmp | grep -q libmpi )" ---> Running in f650a1c9ba25 './arch/local.psmp' -> '/opt/cp2k-toolchain/install/arch/local.psmp' Compiling cp2k... Removing intermediate container f650a1c9ba25 ---> 92d35179c6b4 Step 35/42 : COPY ./data ./data ---> d1af0abd46b5 Step 36/42 : COPY ./tests ./tests ---> 28e2ed0c9b9f Step 37/42 : COPY ./tools/regtesting ./tools/regtesting ---> 932b4fcfe427 Step 38/42 : COPY ./benchmarks ./benchmarks ---> d9730a248eac Step 39/42 : COPY ./tools/docker/scripts/test_performance.sh ./tools/docker/scripts/plot_performance.py ./ ---> 7c72f940c323 Step 40/42 : RUN ./test_performance.sh "local" 2>&1 | tee report.log ---> Running in 4482b60ac219 ========== Compiling CP2K ========== Compiling cp2k... done. Checking benchmark inputs... Found 69 input files and 0 errors. ========== 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 0.027 0.027 86.334 86.334 qs_mol_dyn_low 1 2.0 0.003 0.003 85.710 85.710 qs_forces 11 3.9 0.001 0.001 85.670 85.670 qs_energies 11 4.9 0.001 0.001 79.766 79.766 scf_env_do_scf 11 5.9 0.001 0.001 69.200 69.200 velocity_verlet 10 3.0 0.002 0.002 55.807 55.807 scf_env_do_scf_inner_loop 108 6.5 0.011 0.011 52.827 52.827 rebuild_ks_matrix 119 8.3 0.001 0.001 20.076 20.076 qs_ks_build_kohn_sham_matrix 119 9.3 0.012 0.012 20.076 20.076 dbcsr_multiply_generic 2286 12.5 0.169 0.169 19.356 19.356 qs_scf_new_mos 108 7.5 0.001 0.001 19.308 19.308 qs_scf_loop_do_ot 108 8.5 0.001 0.001 19.308 19.308 qs_rho_update_rho_low 119 7.7 0.001 0.001 18.700 18.700 calculate_rho_elec 119 8.7 0.942 0.942 18.700 18.700 qs_ks_update_qs_env 119 7.6 0.001 0.001 18.500 18.500 ot_scf_mini 108 9.5 0.002 0.002 18.003 18.003 init_scf_loop 11 6.9 0.000 0.000 16.238 16.238 grid_collocate_task_list 119 9.7 14.460 14.460 14.460 14.460 prepare_preconditioner 11 7.9 0.000 0.000 13.786 13.786 make_preconditioner 11 8.9 0.000 0.000 13.786 13.786 sum_up_and_integrate 119 10.3 0.771 0.771 13.065 13.065 make_full_inverse_cholesky 11 9.9 0.000 0.000 12.661 12.661 integrate_v_rspace 119 11.3 0.086 0.086 12.294 12.294 ot_mini 108 10.5 0.001 0.001 11.772 11.772 make_m2s 4572 13.5 0.045 0.045 10.723 10.723 grid_integrate_task_list 119 12.3 10.369 10.369 10.369 10.369 qs_ot_get_derivative 108 11.5 0.001 0.001 6.269 6.269 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 6.162 6.162 dbcsr_make_dense_low 5837 15.5 0.074 0.074 5.974 5.974 pw_transfer 1439 11.6 0.062 0.062 5.918 5.918 make_dense_data 5837 16.5 5.246 5.246 5.887 5.887 fft_wrap_pw1pw2 1201 12.6 0.006 0.006 5.709 5.709 ot_diis_step 108 11.5 0.004 0.004 5.501 5.501 make_images 4572 14.5 2.129 2.129 5.247 5.247 dbcsr_make_images_dense 3978 14.8 0.017 0.017 5.175 5.175 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 5.009 5.009 apply_single 119 13.6 0.000 0.000 5.009 5.009 fft_wrap_pw1pw2_140 487 13.2 0.419 0.419 4.925 4.925 multiply_cannon 2286 13.5 0.175 0.175 4.679 4.679 cp_fm_cholesky_decompose 22 10.9 4.558 4.558 4.558 4.558 multiply_cannon_loop 2286 14.5 0.039 0.039 4.225 4.225 multiply_cannon_multrec 2286 15.5 4.129 4.129 4.185 4.185 cp_fm_cholesky_invert 11 10.9 4.035 4.035 4.035 4.035 init_scf_run 11 5.9 0.002 0.002 3.741 3.741 scf_env_initial_rho_setup 11 6.9 0.001 0.001 3.739 3.739 dbcsr_complete_redistribute 329 12.2 1.911 1.911 3.624 3.624 dbcsr_copy 2102 12.0 0.240 0.240 3.605 3.605 build_core_hamiltonian_matrix_ 11 4.9 0.001 0.001 3.385 3.385 dbcsr_copy_into_existing 22 7.9 3.335 3.335 3.336 3.336 density_rs2pw 119 9.7 0.004 0.004 3.298 3.298 wfi_extrapolate 11 7.9 0.001 0.001 3.279 3.279 qs_env_update_s_mstruct 11 6.9 0.000 0.000 3.251 3.251 copy_dbcsr_to_fm 153 11.3 0.002 0.002 2.937 2.937 fft3d_s 1202 14.6 2.895 2.895 2.899 2.899 qs_create_task_list 11 7.9 0.000 0.000 2.886 2.886 generate_qs_task_list 11 8.9 1.969 1.969 2.886 2.886 qs_ot_get_p 119 10.4 0.001 0.001 2.854 2.854 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 2.517 2.517 build_core_hamiltonian_matrix 11 6.9 0.001 0.001 2.508 2.508 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.300 2.300 pw_poisson_solve 119 10.3 0.332 0.332 1.984 1.984 dbcsr_data_release 279534 16.0 1.978 1.978 1.978 1.978 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 1.972 1.972 qs_ot_get_derivative_taylor 59 13.0 0.001 0.001 1.912 1.912 potential_pw2rs 119 12.3 0.046 0.046 1.839 1.839 copy_fm_to_dbcsr 176 11.2 0.001 0.001 1.833 1.833 ------------------------------------------------------------------------------- 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 0.008 0.023 43.600 43.610 qs_mol_dyn_low 1 2.0 0.003 0.004 43.469 43.473 qs_forces 11 3.9 0.001 0.001 43.429 43.429 qs_energies 11 4.9 0.001 0.001 40.568 40.570 scf_env_do_scf 11 5.9 0.000 0.002 37.177 37.178 scf_env_do_scf_inner_loop 108 6.5 0.003 0.022 34.309 34.310 velocity_verlet 10 3.0 0.002 0.003 25.895 25.896 rebuild_ks_matrix 119 8.3 0.000 0.001 15.838 15.929 qs_ks_build_kohn_sham_matrix 119 9.3 0.014 0.016 15.837 15.929 qs_ks_update_qs_env 119 7.6 0.001 0.001 14.085 14.166 qs_rho_update_rho_low 119 7.7 0.001 0.001 13.159 13.171 calculate_rho_elec 119 8.7 0.030 0.031 13.159 13.170 dbcsr_multiply_generic 2286 12.5 0.069 0.073 12.303 12.507 sum_up_and_integrate 119 10.3 0.031 0.035 11.786 11.810 integrate_v_rspace 119 11.3 0.004 0.005 11.755 11.781 qs_scf_new_mos 108 7.5 0.001 0.001 9.721 9.968 qs_scf_loop_do_ot 108 8.5 0.001 0.001 9.721 9.967 multiply_cannon 2286 13.5 0.141 0.158 9.062 9.535 ot_scf_mini 108 9.5 0.002 0.002 9.122 9.350 grid_collocate_task_list 119 9.7 8.868 9.207 8.868 9.207 multiply_cannon_loop 2286 14.5 0.085 0.100 8.545 9.014 grid_integrate_task_list 119 12.3 7.972 8.145 7.972 8.145 mp_waitall_1 158411 16.6 7.002 7.778 7.002 7.778 multiply_cannon_metrocomm3 18288 15.5 0.035 0.040 4.844 5.853 ot_mini 108 10.5 0.001 0.001 5.314 5.569 rs_pw_transfer 974 11.9 0.010 0.013 4.026 4.468 density_rs2pw 119 9.7 0.005 0.006 3.710 4.124 pw_transfer 1439 11.6 0.098 0.114 3.991 4.066 fft_wrap_pw1pw2 1201 12.6 0.009 0.010 3.827 3.893 fft_wrap_pw1pw2_140 487 13.2 0.244 0.300 3.297 3.453 potential_pw2rs 119 12.3 0.006 0.007 3.253 3.282 multiply_cannon_multrec 18288 15.5 2.880 3.197 2.890 3.207 fft3d_ps 1201 14.6 1.191 1.370 2.974 3.055 qs_ot_get_derivative 108 11.5 0.001 0.001 2.759 2.988 init_scf_loop 11 6.9 0.000 0.000 2.855 2.856 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 2.455 2.559 apply_single 119 13.6 0.000 0.000 2.454 2.559 ot_diis_step 108 11.5 0.003 0.003 2.533 2.533 init_scf_run 11 5.9 0.000 0.004 2.400 2.400 scf_env_initial_rho_setup 11 6.9 0.000 0.004 2.399 2.400 make_m2s 4572 13.5 0.044 0.048 2.152 2.244 wfi_extrapolate 11 7.9 0.001 0.001 2.165 2.165 multiply_cannon_metrocomm1 18288 15.5 0.017 0.020 0.546 2.084 make_images 4572 14.5 0.113 0.118 1.841 1.939 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 1.890 1.901 mp_waitany 9880 13.7 1.256 1.790 1.256 1.790 qs_ot_get_p 119 10.4 0.001 0.001 1.181 1.474 mp_sum_l 11218 13.2 0.671 1.433 0.671 1.433 mp_alltoall_z22v 1201 16.6 1.063 1.386 1.063 1.386 rs_pw_transfer_RS2PW_140 130 11.5 0.166 0.190 0.914 1.353 make_images_data 4572 15.5 0.033 0.040 1.040 1.202 rs_pw_transfer_PW2RS_140 130 13.9 0.321 0.401 1.126 1.196 prepare_preconditioner 11 7.9 0.000 0.000 1.121 1.155 make_preconditioner 11 8.9 0.000 0.000 1.121 1.155 make_full_inverse_cholesky 11 9.9 0.000 0.000 1.016 1.043 hybrid_alltoall_any 4725 16.4 0.053 0.138 0.898 1.023 mp_alltoall_d11v 2130 13.8 0.713 1.013 0.713 1.013 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 0.901 1.009 mp_sum_d 4127 12.0 0.589 0.997 0.589 0.997 rs_pw_transfer_PW2RS_50 119 14.3 0.261 0.344 0.815 0.994 qs_ot_get_derivative_taylor 59 13.0 0.001 0.001 0.866 0.986 yz_to_x 487 15.3 0.297 0.392 0.865 0.978 x_to_yz 476 15.9 0.388 0.470 0.878 0.955 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 0.861 0.946 cp_dbcsr_sm_fm_multiply 37 9.5 0.001 0.001 0.883 0.884 ------------------------------------------------------------------------------- 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=47.572, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=14.46, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=10.369, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="make_dense_data", label="make_dense_data", y=5.246, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=4.558, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=4.129, 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=15.622000000000003, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=8.868, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=7.972, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="make_dense_data", label="make_dense_data", 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=2.88, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=7.002, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitany", label="mp_waitany", y=1.256, 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 0.027 0.027 111.082 111.082 qs_mol_dyn_low 1 2.0 0.003 0.003 110.408 110.408 qs_forces 11 3.9 0.001 0.001 110.369 110.369 qs_energies 11 4.9 0.001 0.001 102.528 102.528 scf_env_do_scf 11 5.9 0.001 0.001 90.057 90.057 velocity_verlet 10 3.0 0.002 0.002 71.896 71.896 scf_env_do_scf_inner_loop 96 6.5 0.010 0.010 71.722 71.722 rebuild_ks_matrix 107 8.3 0.001 0.001 33.390 33.390 qs_ks_build_kohn_sham_matrix 107 9.3 0.011 0.011 33.390 33.390 qs_rho_update_rho_low 107 7.7 0.001 0.001 31.123 31.123 calculate_rho_elec 107 8.7 0.849 0.849 31.123 31.123 qs_ks_update_qs_env 107 7.6 0.001 0.001 29.903 29.903 grid_collocate_task_list 107 9.7 26.969 26.969 26.969 26.969 sum_up_and_integrate 107 10.3 0.705 0.705 26.846 26.846 integrate_v_rspace 107 11.3 0.080 0.080 26.140 26.140 grid_integrate_task_list 107 12.3 24.371 24.371 24.371 24.371 init_scf_loop 11 6.9 0.000 0.000 18.194 18.194 dbcsr_multiply_generic 1966 12.4 0.149 0.149 18.003 18.003 qs_scf_new_mos 96 7.5 0.001 0.001 17.421 17.421 qs_scf_loop_do_ot 96 8.5 0.001 0.001 17.420 17.420 ot_scf_mini 96 9.5 0.002 0.002 16.227 16.227 prepare_preconditioner 11 7.9 0.000 0.000 14.111 14.111 make_preconditioner 11 8.9 0.000 0.000 14.111 14.111 make_full_inverse_cholesky 11 9.9 0.000 0.000 12.946 12.946 ot_mini 96 10.5 0.001 0.001 10.731 10.731 make_m2s 3932 13.4 0.039 0.039 10.091 10.091 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 6.567 6.567 pw_transfer 1295 11.6 0.056 0.056 5.706 5.706 qs_ot_get_derivative 96 11.5 0.001 0.001 5.684 5.684 fft_wrap_pw1pw2 1081 12.6 0.005 0.005 5.524 5.524 dbcsr_make_dense_low 4961 15.5 0.082 0.082 5.409 5.409 make_dense_data 4961 16.5 4.770 4.770 5.316 5.316 init_scf_run 11 5.9 0.002 0.002 5.273 5.273 scf_env_initial_rho_setup 11 6.9 0.000 0.000 5.271 5.271 make_images 3932 14.4 2.027 2.027 5.123 5.123 ot_diis_step 96 11.5 0.003 0.003 5.044 5.044 fft_wrap_pw1pw2_140 439 13.2 0.552 0.552 4.808 4.808 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 4.725 4.725 apply_single 107 13.6 0.000 0.000 4.724 4.724 dbcsr_make_images_dense 3386 14.7 0.015 0.015 4.687 4.687 wfi_extrapolate 11 7.9 0.001 0.001 4.663 4.663 cp_fm_cholesky_decompose 22 10.9 4.496 4.496 4.496 4.496 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 4.349 4.349 multiply_cannon 1966 13.4 0.151 0.151 4.321 4.321 cp_fm_cholesky_invert 11 10.9 4.165 4.165 4.165 4.165 multiply_cannon_loop 1966 14.4 0.034 0.034 3.925 3.925 multiply_cannon_multrec 1966 15.4 3.850 3.850 3.890 3.890 dbcsr_complete_redistribute 317 12.2 1.893 1.893 3.812 3.812 qs_env_update_s_mstruct 11 6.9 0.000 0.000 3.691 3.691 dbcsr_copy 1855 11.9 0.200 0.200 3.542 3.542 build_core_hamiltonian_matrix_ 11 4.9 0.001 0.001 3.491 3.491 qs_create_task_list 11 7.9 0.000 0.000 3.324 3.324 generate_qs_task_list 11 8.9 2.402 2.402 3.324 3.324 dbcsr_copy_into_existing 22 7.9 3.312 3.312 3.312 3.312 density_rs2pw 107 9.7 0.004 0.004 3.305 3.305 copy_dbcsr_to_fm 147 11.2 0.002 0.002 3.090 3.090 fft3d_s 1082 14.6 2.681 2.681 2.685 2.685 build_core_hamiltonian_matrix 11 6.9 0.001 0.001 2.464 2.464 qs_ot_get_p 107 10.4 0.001 0.001 2.416 2.416 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.387 2.387 ------------------------------------------------------------------------------- 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 0.008 0.024 70.349 70.359 qs_mol_dyn_low 1 2.0 0.003 0.003 70.223 70.228 qs_forces 11 3.9 0.001 0.001 70.183 70.184 qs_energies 11 4.9 0.001 0.001 65.469 65.470 scf_env_do_scf 11 5.9 0.000 0.002 60.640 60.641 scf_env_do_scf_inner_loop 96 6.5 0.002 0.017 56.064 56.064 velocity_verlet 10 3.0 0.002 0.003 42.036 42.037 rebuild_ks_matrix 107 8.3 0.000 0.000 30.744 30.844 qs_ks_build_kohn_sham_matrix 107 9.3 0.013 0.014 30.743 30.844 qs_ks_update_qs_env 107 7.6 0.001 0.001 27.101 27.196 sum_up_and_integrate 107 10.3 0.032 0.042 26.966 26.996 integrate_v_rspace 107 11.3 0.004 0.005 26.934 26.968 qs_rho_update_rho_low 107 7.7 0.000 0.001 25.768 25.780 calculate_rho_elec 107 8.7 0.027 0.028 25.768 25.780 grid_integrate_task_list 107 12.3 22.657 23.371 22.657 23.371 grid_collocate_task_list 107 9.7 21.679 22.100 21.679 22.100 dbcsr_multiply_generic 1966 12.4 0.062 0.065 11.529 11.708 qs_scf_new_mos 96 7.5 0.000 0.001 8.950 9.092 qs_scf_loop_do_ot 96 8.5 0.001 0.001 8.949 9.091 multiply_cannon 1966 13.4 0.126 0.140 8.573 9.047 multiply_cannon_loop 1966 14.4 0.081 0.091 8.102 8.576 ot_scf_mini 96 9.5 0.002 0.002 8.391 8.529 mp_waitall_1 136719 16.5 6.702 7.355 6.702 7.355 multiply_cannon_metrocomm3 15728 15.4 0.032 0.036 4.728 5.568 ot_mini 96 10.5 0.001 0.001 4.887 5.050 rs_pw_transfer 878 11.9 0.009 0.011 4.019 4.745 init_scf_loop 11 6.9 0.000 0.000 4.564 4.564 density_rs2pw 107 9.7 0.004 0.005 3.587 4.301 init_scf_run 11 5.9 0.000 0.004 3.809 3.809 scf_env_initial_rho_setup 11 6.9 0.000 0.003 3.809 3.809 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 3.757 3.766 pw_transfer 1295 11.6 0.089 0.108 3.602 3.675 fft_wrap_pw1pw2 1081 12.6 0.008 0.009 3.456 3.521 wfi_extrapolate 11 7.9 0.001 0.001 3.463 3.464 fft_wrap_pw1pw2_140 439 13.2 0.217 0.257 2.982 3.133 potential_pw2rs 107 12.3 0.006 0.006 3.039 3.062 multiply_cannon_multrec 15728 15.4 2.641 2.852 2.649 2.862 fft3d_ps 1081 14.6 1.075 1.226 2.677 2.735 qs_ot_get_derivative 96 11.5 0.001 0.001 2.517 2.660 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 2.321 2.431 apply_single 107 13.6 0.000 0.000 2.321 2.431 ot_diis_step 96 11.5 0.003 0.003 2.349 2.349 mp_waitany 8968 13.7 1.450 2.300 1.450 2.300 mp_alltoall_d11v 1998 13.7 1.410 2.215 1.410 2.215 make_m2s 3932 13.4 0.039 0.042 1.962 2.038 rs_gather_matrices 107 12.3 0.080 0.089 1.184 1.963 rs_pw_transfer_RS2PW_140 118 11.5 0.150 0.182 1.093 1.821 make_images 3932 14.4 0.101 0.103 1.685 1.764 ------------------------------------------------------------------------------- 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=42.461, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=26.969, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=24.371, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="make_dense_data", label="make_dense_data", y=4.77, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=4.496, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=4.165, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=3.85, 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="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=15.220000000000006, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=21.679, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=22.657, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="make_dense_data", label="make_dense_data", 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="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=2.641, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=6.702, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitany", label="mp_waitany", y=1.45, 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 0.187 0.187 104.499 104.499 qs_energies 1 2.0 0.000 0.000 103.653 103.653 scf_env_do_scf 1 3.0 0.000 0.000 102.480 102.480 qs_ks_update_qs_env 8 5.0 0.000 0.000 97.371 97.371 rebuild_ks_matrix 7 6.0 0.000 0.000 97.315 97.315 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.001 97.315 97.315 hfx_ks_matrix 7 8.0 0.000 0.000 88.127 88.127 integrate_four_center 7 9.0 1.532 1.532 88.098 88.098 integrate_four_center_main 7 10.0 0.545 0.545 80.550 80.550 integrate_four_center_bin 446 11.0 80.005 80.005 80.005 80.005 scf_env_do_scf_inner_loop 7 4.0 0.001 0.001 56.451 56.451 init_scf_loop 1 4.0 0.000 0.000 46.014 46.014 integrate_four_center_load 7 10.0 0.000 0.000 5.762 5.762 hfx_load_balance 1 11.0 0.001 0.001 5.761 5.761 qs_vxc_create 14 8.0 0.000 0.000 3.118 3.118 xc_vxc_pw_create 14 9.0 0.123 0.123 3.118 3.118 hfx_load_balance_bin 1 12.0 2.883 2.883 2.883 2.883 hfx_load_balance_count 1 12.0 2.862 2.862 2.862 2.862 calculate_rho_elec 15 7.4 0.120 0.120 2.441 2.441 admm_mo_calc_rho_aux 7 8.0 0.000 0.000 2.438 2.438 prepare_preconditioner 1 5.0 0.000 0.000 2.404 2.404 make_preconditioner 1 6.0 0.000 0.000 2.404 2.404 xc_rho_set_and_dset_create 14 10.0 0.092 0.092 2.394 2.394 ------------------------------------------------------------------------------- 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 0.220 0.248 94.972 94.982 qs_energies 1 2.0 0.000 0.000 94.560 94.567 scf_env_do_scf 1 3.0 0.000 0.000 94.224 94.225 qs_ks_update_qs_env 8 5.0 0.000 0.000 92.287 92.288 rebuild_ks_matrix 7 6.0 0.000 0.000 92.280 92.280 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.001 92.280 92.280 hfx_ks_matrix 7 8.0 0.000 0.000 86.940 86.941 integrate_four_center 7 9.0 0.052 0.327 86.932 86.933 integrate_four_center_main 7 10.0 0.003 0.003 78.424 80.048 integrate_four_center_bin 448 11.0 78.422 80.045 78.422 80.045 scf_env_do_scf_inner_loop 7 4.0 0.000 0.001 52.760 52.760 init_scf_loop 1 4.0 0.000 0.000 41.464 41.464 integrate_four_center_load 7 10.0 0.000 0.000 5.839 5.839 hfx_load_balance 1 11.0 0.001 0.001 5.839 5.839 hfx_load_balance_bin 1 12.0 2.771 2.919 2.771 2.919 hfx_load_balance_count 1 12.0 2.771 2.916 2.771 2.916 mp_sync 70 11.3 1.998 2.891 1.998 2.891 qs_vxc_create 14 8.0 0.000 0.000 2.446 2.446 xc_vxc_pw_create 14 9.0 0.006 0.007 2.446 2.446 xc_rho_set_and_dset_create 14 10.0 0.009 0.011 1.947 2.059 ------------------------------------------------------------------------------- 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=16.485000000000014, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_bin", label="integrate_four_center_bin", y=80.005, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=2.883, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_count", label="hfx_load_balance_count", y=2.862, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center", label="integrate_four_center", y=1.532, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_main", label="integrate_four_center_main", y=0.545, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="CP2K", label="CP2K", y=0.187, 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=8.734999999999985, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center_bin", label="integrate_four_center_bin", y=78.422, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=2.771, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_count", label="hfx_load_balance_count", y=2.771, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center", label="integrate_four_center", y=0.052, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center_main", label="integrate_four_center_main", y=0.003, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="CP2K", label="CP2K", y=0.22, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="mp_sync", label="mp_sync", y=1.998, 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 79.958 79.958 qs_energies 1 2.0 0.000 0.000 79.553 79.553 mp2_main 1 3.0 0.000 0.000 76.701 76.701 mp2_gpw_main 1 4.0 0.000 0.000 76.583 76.583 rpa_ri_compute_en 1 5.0 0.000 0.000 72.923 72.923 rpa_num_int 1 6.0 0.001 0.001 72.917 72.917 compute_mat_P_omega 1 7.0 0.003 0.003 63.102 63.102 compute_mat_P_omega_contract 10 8.0 8.761 8.761 62.909 62.909 dbt_total 2336 9.6 0.011 0.011 49.392 49.392 dbt_contract 787 11.0 0.035 0.035 42.548 42.548 dbt_tas_total 1149 12.2 0.237 0.237 41.684 41.684 dbt_tas_multiply 807 12.1 0.002 0.002 40.323 40.323 dbt_tas_dbm 807 14.1 0.003 0.003 33.794 33.794 dbm_multiply 807 16.1 33.786 33.786 33.786 33.786 dbt_tas_mm_1N 524 15.1 0.002 0.002 26.552 26.552 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 25.168 25.168 compute_mat_P_omega_calc_M_occ 250 9.0 8.778 8.778 16.664 16.664 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 6.785 6.785 dbt_tas_mm_2 251 15.0 0.001 0.001 5.780 5.780 dbt_copy 1103 10.7 0.100 0.100 5.468 5.468 compute_QP_energies 1 7.0 0.000 0.000 4.959 4.959 compute_self_energy_cubic_gw 1 8.0 0.051 0.051 4.958 4.958 contract_cubic_gw 21 9.0 0.000 0.000 3.983 3.983 mp2_ri_gpw_compute_in 1 5.0 0.001 0.001 3.652 3.652 dbt_tas_reserve_blocks_index 3261 14.3 0.142 0.142 3.315 3.315 dbm_reserve_blocks 3628 15.3 3.234 3.234 3.234 3.234 scf_env_do_scf 1 3.0 0.000 0.000 2.744 2.744 scf_env_do_scf_inner_loop 17 4.0 0.002 0.002 2.743 2.743 dbt_reserve_blocks_index 2280 13.1 0.052 0.052 2.546 2.546 dbt_reserve_blocks_index_array 2222 12.2 0.008 0.008 2.501 2.501 convert_to_new_pgrid 2421 14.1 0.131 0.131 2.363 2.363 dbm_copy 1614 15.1 2.232 2.232 2.232 2.232 dbt_tas_copy 574 11.4 1.286 1.286 2.151 2.151 dbt_crop 1042 12.0 1.356 1.356 2.121 2.121 dbt_tas_reshape 367 15.0 0.006 0.006 2.091 2.091 compute_W_cubic_GW 10 7.0 0.010 0.010 2.068 2.068 rpa_num_int_RPA_matrix_operati 10 7.0 0.000 0.000 1.951 1.951 get_2c_integrals 1 6.0 0.000 0.000 1.770 1.770 dbt_reshape 278 11.9 0.923 0.923 1.761 1.761 ------------------------------------------------------------------------------- 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 0.021 30.254 30.265 qs_energies 1 2.0 0.000 0.000 30.153 30.154 mp2_main 1 3.0 0.000 0.000 29.244 29.246 mp2_gpw_main 1 4.0 0.000 0.000 29.211 29.212 rpa_ri_compute_en 1 5.0 0.000 0.000 27.970 27.972 rpa_num_int 1 6.0 0.000 0.002 27.970 27.971 dbt_total 2336 9.6 0.011 0.012 24.800 24.807 compute_mat_P_omega 1 7.0 0.001 0.005 23.718 23.731 compute_mat_P_omega_contract 10 8.0 0.378 0.402 23.605 23.610 dbt_contract 787 11.0 0.027 0.028 18.804 18.810 dbt_tas_total 1149 12.2 0.047 0.056 16.754 16.755 dbt_tas_multiply 807 12.1 0.002 0.002 16.700 16.702 dbt_tas_dbm 807 14.1 0.003 0.003 12.621 12.635 dbm_multiply 807 16.1 9.890 10.588 9.890 10.588 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 7.057 7.058 compute_mat_P_omega_calc_M_occ 250 9.0 0.369 0.392 6.967 6.967 dbt_tas_mm_2 251 15.0 0.001 0.001 5.888 5.894 mp_sync 8706 11.6 4.443 5.649 4.443 5.649 dbt_copy 1149 10.8 0.011 0.012 5.217 5.496 dbt_reshape 1136 11.8 1.978 2.161 4.968 5.234 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 5.101 5.106 dbt_tas_mm_1N 524 15.1 0.001 0.002 4.446 5.065 compute_QP_energies 1 7.0 0.000 0.000 2.660 2.661 compute_self_energy_cubic_gw 1 8.0 0.002 0.003 2.658 2.659 mp_waitall_2 3812 15.3 2.351 2.558 2.351 2.558 dbt_communicate_buffer 1136 12.8 0.052 0.057 2.389 2.508 contract_cubic_gw 21 9.0 0.000 0.000 2.134 2.134 dbt_reserve_blocks_index 2887 13.1 0.065 0.071 1.436 1.679 dbt_reserve_blocks_index_array 2829 12.2 0.008 0.011 1.427 1.669 dbt_tas_reserve_blocks_index 3347 14.5 0.110 0.126 1.403 1.643 dbm_reserve_blocks 3752 15.4 1.378 1.615 1.378 1.615 dbt_crop 1042 12.0 0.857 0.962 1.312 1.496 mp2_ri_gpw_compute_in 1 5.0 0.000 0.001 1.239 1.240 dbt_tas_replicate 405 14.1 0.521 0.687 1.048 1.117 parallel_gemm_fm 105 8.4 0.000 0.000 0.944 0.951 parallel_gemm_fm_cosma 105 9.4 0.944 0.951 0.944 0.951 compute_mat_P_omega_copy_M_vir 250 9.0 0.001 0.001 0.921 0.923 compute_mat_P_omega_copy_M_occ 250 9.0 0.001 0.001 0.868 0.871 scf_env_do_scf 1 3.0 0.000 0.000 0.869 0.869 scf_env_do_scf_inner_loop 17 4.0 0.000 0.002 0.869 0.869 convert_to_new_pgrid 2421 14.1 0.024 0.028 0.720 0.850 dbm_copy 1608 15.1 0.691 0.818 0.691 0.818 compute_W_cubic_GW 10 7.0 0.001 0.001 0.733 0.739 mp_max_i 1995 9.8 0.528 0.719 0.528 0.719 rpa_num_int_RPA_matrix_operati 10 7.0 0.000 0.000 0.611 0.611 mp_bcast_im 6 9.7 0.585 0.606 0.585 0.606 ------------------------------------------------------------------------------- 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=22.243999999999993, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=33.786, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="compute_mat_P_omega_calc_M_occ", label="compute_mat_P_omega_calc_M_occ", y=8.778, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=8.761, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=3.234, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_copy", label="dbm_copy", y=2.232, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=0.923, 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=8.776, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=9.89, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="compute_mat_P_omega_calc_M_occ", label="compute_mat_P_omega_calc_M_occ", y=0.369, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=0.378, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=1.378, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_copy", label="dbm_copy", y=0.691, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=1.978, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_sync", label="mp_sync", y=4.443, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.351, 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 0.018 0.018 313.084 313.084 qs_forces 1 2.0 0.000 0.000 312.521 312.521 rebuild_ks_matrix 7 6.6 0.000 0.000 311.101 311.101 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.001 311.101 311.101 hfx_ks_matrix 7 8.6 0.000 0.000 309.299 309.299 hfx_ri_update_ks 7 9.6 0.000 0.000 274.381 274.381 hfx_ri_update_ks_Pmat 7 10.6 30.933 30.933 274.366 274.366 dbt_total 783 11.1 0.005 0.005 255.962 255.962 qs_energies 1 3.0 0.000 0.000 242.275 242.275 scf_env_do_scf 1 4.0 0.000 0.000 241.987 241.987 qs_ks_update_qs_env 8 6.0 0.000 0.000 240.903 240.903 dbt_contract 207 12.4 0.030 0.030 238.140 238.140 dbt_tas_total 317 14.0 1.490 1.490 236.724 236.724 dbt_tas_multiply 216 13.5 0.001 0.001 233.301 233.301 dbt_tas_dbm 216 15.5 0.001 0.001 224.926 224.926 dbm_multiply 216 17.5 224.923 224.923 224.923 224.923 hfx_ri_update_ks_Pmat_KS 63 11.6 0.001 0.001 220.141 220.141 dbt_tas_mm_2 91 16.5 0.001 0.001 211.750 211.750 scf_env_do_scf_inner_loop 6 5.0 0.001 0.001 153.960 153.960 init_scf_loop 2 5.0 0.000 0.000 88.025 88.025 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 70.201 70.201 hfx_ri_update_forces 1 7.0 1.561 1.561 34.915 34.915 hfx_ri_forces_Pmat_3c 1 8.0 4.604 4.604 18.633 18.633 dbt_copy 409 11.7 0.053 0.053 14.393 14.393 precalc_derivatives 1 8.0 2.142 2.142 12.622 12.622 dbt_reshape 132 13.2 6.164 6.164 10.204 10.204 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 9.341 9.341 dbt_tas_mm_3T 77 17.1 0.000 0.000 9.050 9.050 build_3c_derivatives 3 9.0 2.367 2.367 7.117 7.117 dbt_tas_reserve_blocks_index 1229 15.4 0.269 0.269 6.795 6.795 dbm_reserve_blocks 1345 16.4 6.608 6.608 6.608 6.608 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 6.424 6.424 ------------------------------------------------------------------------------- From /workspace/artifacts/RI-HFX_H2O-32_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.007 0.021 42.006 42.015 qs_forces 1 2.0 0.000 0.000 41.872 41.872 rebuild_ks_matrix 7 6.6 0.000 0.000 41.195 41.196 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.002 41.195 41.196 hfx_ks_matrix 7 8.6 0.000 0.000 40.191 40.200 dbt_total 783 11.1 0.004 0.005 35.620 35.622 dbt_contract 207 12.4 0.020 0.023 28.185 28.194 dbt_tas_total 317 14.0 0.031 0.047 24.949 24.950 hfx_ri_update_ks 7 9.6 0.000 0.000 24.909 24.909 hfx_ri_update_ks_Pmat 7 10.6 1.157 1.230 24.908 24.908 dbt_tas_multiply 216 13.5 0.001 0.001 24.859 24.859 qs_energies 1 3.0 0.000 0.000 23.466 23.466 scf_env_do_scf 1 4.0 0.000 0.001 23.327 23.327 qs_ks_update_qs_env 8 6.0 0.000 0.000 22.800 22.801 dbt_tas_dbm 216 15.5 0.001 0.001 20.959 20.960 dbm_multiply 216 17.5 18.877 19.877 18.877 19.877 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 18.396 18.396 hfx_ri_update_forces 1 7.0 0.053 0.061 15.282 15.290 scf_env_do_scf_inner_loop 6 5.0 0.000 0.001 13.311 13.311 hfx_ri_update_ks_Pmat_KS 63 11.6 0.000 0.000 11.951 11.951 hfx_ri_forces_Pmat_3c 1 8.0 0.156 0.170 11.024 11.024 dbt_tas_mm_2 91 16.5 0.001 0.001 10.317 10.319 init_scf_loop 2 5.0 0.000 0.000 10.015 10.015 dbt_copy 497 12.3 0.009 0.010 6.913 7.227 dbt_tas_mm_3T 77 17.1 0.000 0.000 5.226 5.857 mp_sync 2677 13.0 3.955 5.613 3.955 5.613 dbt_reshape 365 13.6 2.637 2.772 5.287 5.533 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 4.631 4.631 dbt_tas_mm_3N 37 15.4 0.000 0.000 3.783 3.927 precalc_derivatives 1 8.0 0.076 0.082 3.267 3.267 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 2.934 2.934 dbt_tas_reserve_blocks_index 1356 15.8 0.221 0.231 2.364 2.664 dbm_reserve_blocks 1481 16.7 2.208 2.501 2.208 2.501 dbt_crop 372 13.7 1.675 1.735 2.257 2.384 dbt_reserve_blocks_index 1051 14.7 0.104 0.111 1.993 2.264 dbt_reserve_blocks_index_array 1028 13.8 0.005 0.006 1.971 2.247 mp_waitall_2 1138 16.4 2.041 2.097 2.041 2.097 dbt_communicate_buffer 365 14.6 0.013 0.014 1.816 1.870 build_3c_derivatives 3 9.0 0.219 0.236 1.821 1.826 hfx_ri_pre_scf_Pmat_RIx3C 9 13.0 0.000 0.000 1.468 1.471 convert_to_new_pgrid 648 15.5 0.035 0.058 1.201 1.350 hfx_ri_update_ks_Pmat_copy_2 63 11.6 0.000 0.000 1.330 1.330 dbm_copy 452 16.3 1.040 1.186 1.040 1.186 dbt_tas_copy 132 12.5 0.555 0.606 1.008 1.153 ------------------------------------------------------------------------------- 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=39.85200000000003, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=224.923, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=30.933, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=6.608, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=6.164, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_forces_Pmat_3c", label="hfx_ri_forces_Pmat_3c", y=4.604, 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=10.975000000000005, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=18.877, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=1.157, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=2.208, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=2.637, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_forces_Pmat_3c", label="hfx_ri_forces_Pmat_3c", y=0.156, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_sync", label="mp_sync", y=3.955, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.041, yerr=0.0 Running RI-MP2_ammonia.inp with 1 threads and 32 ranks... done. Running RI-MP2_ammonia.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/RI-MP2_ammonia_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 0.019 182.208 182.208 qs_energies 1 2.0 0.000 0.000 182.015 182.015 mp2_main 1 3.0 0.000 0.000 177.409 177.409 mp2_gpw_main 1 4.0 0.001 0.001 177.001 177.001 mp2_ri_gpw_compute_in 1 5.0 0.381 0.381 133.994 133.994 mp2_ri_gpw_compute_in_loop 1 6.0 0.010 0.010 122.783 122.783 mp2_eri_3c_integrate_gpw 2656 7.0 0.012 0.012 92.728 92.728 integrate_v_rspace 2666 8.0 0.600 0.600 79.568 79.568 grid_integrate_task_list 2666 9.0 77.018 77.018 77.018 77.018 mp2_ri_gpw_compute_en 1 5.0 0.086 0.086 42.984 42.984 mp2_ri_gpw_compute_en_RI_loop 1 6.0 9.334 9.334 41.166 41.166 mp2_ri_gpw_compute_en_expansio 2080 7.0 2.148 2.148 24.671 24.671 local_gemm 2080 8.0 22.523 22.523 22.523 22.523 dbcsr_multiply_generic 5322 8.0 0.175 0.175 20.913 20.913 ao_to_mo_and_store_B_mult_1 2656 7.0 0.009 0.009 20.892 20.892 pw_transfer 63872 10.6 1.027 1.027 11.869 11.869 calculate_wavefunction 2656 8.0 8.115 8.115 11.786 11.786 get_2c_integrals 1 6.0 0.000 0.000 10.829 10.829 fft_wrap_pw1pw2 53228 11.4 0.107 0.107 10.634 10.634 multiply_cannon 5322 9.0 0.469 0.469 10.493 10.493 compute_2c_integrals 1 7.0 0.005 0.005 10.027 10.027 compute_2c_integrals_loop_lm 1 8.0 0.012 0.012 10.012 10.012 mp2_eri_2c_integrate_gpw 1 9.0 3.174 3.174 10.000 10.000 ao_to_mo_and_store_B_E_Ex_1 2656 7.0 2.306 2.306 9.061 9.061 multiply_cannon_loop 5322 10.0 0.129 0.129 9.055 9.055 make_m2s 10644 9.0 0.061 0.061 8.103 8.103 make_images 10644 10.0 3.152 3.152 7.809 7.809 fft_wrap_pw1pw2_20 21271 12.4 0.498 0.498 7.657 7.657 multiply_cannon_multrec 5322 11.0 7.549 7.549 7.589 7.589 copy_dbcsr_to_fm 2679 8.0 0.027 0.027 7.241 7.241 fft3d_s 53229 13.4 6.504 6.504 6.537 6.537 dbcsr_complete_redistribute 2689 9.0 1.114 1.114 5.489 5.489 mp2_ri_gpw_compute_en_ener 2080 7.0 5.356 5.356 5.356 5.356 dbcsr_finalize 10708 9.5 0.162 0.162 5.046 5.046 dbcsr_merge_all 8011 10.3 3.434 3.434 4.439 4.439 scf_env_do_scf 1 3.0 0.000 0.000 4.208 4.208 scf_env_do_scf_inner_loop 10 4.0 0.001 0.001 4.208 4.208 potential_pw2rs 5322 10.0 0.142 0.142 3.857 3.857 ------------------------------------------------------------------------------- From /workspace/artifacts/RI-MP2_ammonia_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 0.028 34.388 34.399 qs_energies 1 2.0 0.000 0.000 34.280 34.281 mp2_main 1 3.0 0.000 0.000 32.363 32.363 mp2_gpw_main 1 4.0 0.001 0.001 32.260 32.260 mp2_ri_gpw_compute_in 1 5.0 0.052 0.052 16.857 17.084 mp2_ri_gpw_compute_in_loop 1 6.0 0.001 0.001 15.689 15.921 mp2_ri_gpw_compute_en 1 5.0 0.193 0.200 15.314 15.653 mp2_ri_gpw_compute_en_RI_loop 1 6.0 1.324 1.516 14.324 14.330 mp2_eri_3c_integrate_gpw 83 7.0 0.001 0.001 13.762 14.068 integrate_v_rspace 93 8.1 0.095 0.103 13.633 13.944 grid_integrate_task_list 93 9.1 13.350 13.664 13.350 13.664 mp2_ri_gpw_compute_en_expansio 65 7.0 0.097 0.120 10.333 10.509 local_gemm 65 8.0 10.236 10.401 10.236 10.401 mp2_ri_gpw_compute_en_comm 20 7.0 0.072 0.101 2.343 3.003 mp_sendrecv_dm3 1240 8.0 1.836 2.721 1.836 2.721 dbcsr_multiply_generic 176 8.0 0.007 0.008 1.652 1.888 ao_to_mo_and_store_B_mult_1 83 7.0 0.001 0.001 1.637 1.875 scf_env_do_scf 1 3.0 0.000 0.000 1.800 1.801 scf_env_do_scf_inner_loop 10 4.0 0.000 0.002 1.800 1.801 get_2c_integrals 1 6.0 0.000 0.000 1.100 1.125 multiply_cannon 176 9.0 0.015 0.016 0.992 1.070 multiply_cannon_loop 176 10.0 0.002 0.002 0.937 1.015 qs_scf_new_mos 10 5.0 0.000 0.000 0.872 0.883 multiply_cannon_multrec 246 11.0 0.816 0.858 0.821 0.863 eigensolver 11 5.8 0.001 0.001 0.849 0.850 compute_2c_integrals 1 7.0 0.002 0.003 0.812 0.830 make_m2s 352 9.0 0.003 0.003 0.626 0.804 make_images 352 10.0 0.050 0.051 0.615 0.792 pw_transfer 2120 10.5 0.044 0.046 0.739 0.755 compute_2c_integrals_loop_lm 1 8.0 0.002 0.004 0.718 0.752 mp2_eri_2c_integrate_gpw 1 9.0 0.196 0.207 0.716 0.751 cp_fm_diag_elpa 11 6.8 0.000 0.000 0.697 0.698 fft_wrap_pw1pw2 1768 11.4 0.004 0.004 0.684 0.697 cp_fm_redistribute_end 11 7.8 0.259 0.687 0.272 0.691 ------------------------------------------------------------------------------- Plot: name="RI-MP2_ammonia_timings_32omp", title="Timings of RI-MP2_ammonia with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="rest", label="rest", y=57.669, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=77.018, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="local_gemm", label="local_gemm", y=22.523, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="mp2_ri_gpw_compute_en_RI_loop", label="mp2_ri_gpw_compute_en_RI_loop", y=9.334, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="calculate_wavefunction", label="calculate_wavefunction", y=8.115, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=7.549, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="mp_sendrecv_dm3", label="mp_sendrecv_dm3", y=0.0, yerr=0.0 Plot: name="RI-MP2_ammonia_timings_32mpi", title="Timings of RI-MP2_ammonia with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="rest", label="rest", y=6.8260000000000005, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.35, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="local_gemm", label="local_gemm", y=10.236, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="mp2_ri_gpw_compute_en_RI_loop", label="mp2_ri_gpw_compute_en_RI_loop", y=1.324, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="calculate_wavefunction", label="calculate_wavefunction", y=0.0, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=0.816, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="mp_sendrecv_dm3", label="mp_sendrecv_dm3", y=1.836, 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 0.079 0.079 122.190 122.190 qs_energies 1 2.0 0.000 0.000 120.773 120.773 scf_env_do_scf 1 3.0 0.000 0.000 114.171 114.171 scf_env_do_scf_inner_loop 15 4.0 0.002 0.002 114.170 114.170 qs_ks_update_qs_env 15 5.0 0.000 0.000 48.169 48.169 rebuild_ks_matrix 15 6.0 0.000 0.000 47.961 47.961 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.002 47.961 47.961 qs_scf_new_mos 15 5.0 0.000 0.000 41.432 41.432 eigensolver 15 6.0 0.001 0.001 33.841 33.841 qs_vxc_create 15 8.0 0.038 0.038 32.964 32.964 calculate_dispersion_nonloc 15 9.0 6.819 6.819 28.828 28.828 pw_transfer 1191 10.0 0.060 0.060 22.520 22.520 fft_wrap_pw1pw2 1086 11.0 0.008 0.008 22.357 22.357 qs_rho_update_rho_low 16 5.0 0.000 0.000 21.771 21.771 calculate_rho_elec 16 6.0 0.214 0.214 21.771 21.771 cp_fm_diag_elpa 15 7.0 0.000 0.000 21.425 21.425 cp_fm_diag_elpa_base 15 8.0 18.882 18.882 21.425 21.425 grid_collocate_task_list 16 7.0 20.462 20.462 20.462 20.462 fft_wrap_pw1pw2_150 765 12.0 3.525 3.525 16.395 16.395 sum_up_and_integrate 15 8.0 0.145 0.145 13.906 13.906 integrate_v_rspace 15 9.0 0.018 0.018 13.760 13.760 grid_integrate_task_list 15 10.0 13.243 13.243 13.243 13.243 cp_fm_cholesky_restore 45 7.0 10.187 10.187 10.187 10.187 fft3d_s 1087 13.0 9.898 9.898 9.905 9.905 pw_scatter_s 585 13.1 7.133 7.133 7.133 7.133 fft_wrap_pw1pw2_200 197 12.3 0.700 0.700 5.780 5.780 copy_dbcsr_to_fm 16 5.9 0.001 0.001 5.500 5.500 dbcsr_complete_redistribute 46 8.3 2.236 2.236 5.424 5.424 cp_fm_upper_to_full 30 8.0 4.770 4.770 4.770 4.770 vdW_energy 15 10.0 4.243 4.243 4.243 4.243 xc_vxc_pw_create 15 9.0 0.210 0.210 4.098 4.098 gspace_mixing 14 5.0 0.170 0.170 3.992 3.992 broyden_mixing 14 6.0 3.403 3.403 3.403 3.403 init_scf_run 1 3.0 0.000 0.000 3.134 3.134 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 3.007 3.007 xc_pw_derive 90 11.0 0.001 0.001 2.670 2.670 ------------------------------------------------------------------------------- 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 0.027 59.913 59.923 qs_energies 1 2.0 0.000 0.000 59.653 59.658 scf_env_do_scf 1 3.0 0.000 0.001 55.621 55.622 scf_env_do_scf_inner_loop 15 4.0 0.001 0.003 55.621 55.622 qs_ks_update_qs_env 15 5.0 0.000 0.000 23.960 23.970 rebuild_ks_matrix 15 6.0 0.000 0.000 23.908 23.918 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.003 23.908 23.917 qs_rho_update_rho_low 16 5.0 0.000 0.000 20.444 20.455 calculate_rho_elec 16 6.0 0.007 0.007 20.444 20.454 grid_collocate_task_list 16 7.0 19.150 19.286 19.150 19.286 sum_up_and_integrate 15 8.0 0.012 0.018 13.463 13.509 integrate_v_rspace 15 9.0 0.000 0.001 13.451 13.503 grid_integrate_task_list 15 10.0 12.757 12.878 12.757 12.878 qs_scf_new_mos 15 5.0 0.000 0.000 11.807 11.833 eigensolver 15 6.0 0.001 0.002 10.913 10.937 qs_vxc_create 15 8.0 0.001 0.001 10.099 10.110 calculate_dispersion_nonloc 15 9.0 0.893 0.906 8.161 8.181 pw_transfer 1191 10.0 0.091 0.106 8.051 8.119 fft_wrap_pw1pw2 1086 11.0 0.012 0.014 7.878 7.979 cp_fm_diag_elpa 15 7.0 0.000 0.000 7.730 7.735 cp_fm_diag_elpa_base 15 8.0 7.590 7.618 7.727 7.727 fft3d_ps 1086 13.0 2.530 2.897 6.318 6.612 fft_wrap_pw1pw2_150 765 12.0 0.246 0.306 5.122 5.163 mp_alltoall_z22v 1086 15.0 2.312 3.479 2.312 3.479 cp_fm_cholesky_restore 45 7.0 3.041 3.087 3.041 3.087 fft_wrap_pw1pw2_200 197 12.3 0.165 0.204 2.605 2.663 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 2.435 2.435 x_to_yz 585 14.1 0.845 1.019 2.044 2.411 build_core_hamiltonian_matrix 1 4.0 0.000 0.000 2.140 2.336 yz_to_x 501 13.9 0.608 0.866 1.721 2.107 xc_vxc_pw_create 15 9.0 0.015 0.019 1.938 1.966 xc_pw_derive 90 11.0 0.001 0.002 1.322 1.387 init_scf_run 1 3.0 0.000 0.000 1.375 1.376 build_core_ppnl 1 5.0 1.251 1.369 1.251 1.369 vdW_energy 15 10.0 1.239 1.358 1.239 1.358 scf_env_initial_rho_setup 1 4.0 0.000 0.000 1.290 1.290 rs_pw_transfer 158 9.4 0.001 0.002 0.982 1.257 density_rs2pw 16 7.0 0.001 0.001 1.096 1.244 ------------------------------------------------------------------------------- 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=49.518, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=20.462, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=18.882, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.243, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=10.187, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="fft3d_s", label="fft3d_s", y=9.898, 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=14.844999999999999, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=19.15, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=7.59, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=12.757, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=3.041, 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=2.53, 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 0.085 0.085 303.024 303.024 qs_energies 1 2.0 0.000 0.000 302.878 302.878 ls_scf 1 3.0 0.000 0.000 301.617 301.617 ls_scf_main 1 4.0 0.002 0.002 292.706 292.706 density_matrix_trs4 11 5.0 0.012 0.012 201.779 201.779 arnoldi_extremal 12 6.1 0.000 0.000 118.885 118.885 arnoldi_normal_ev 12 7.1 0.031 0.031 118.885 118.885 dbcsr_matrix_vector_mult 652 9.0 0.199 0.199 116.777 116.777 build_subspace 23 8.1 0.077 0.077 116.638 116.638 dbcsr_matrix_vector_mult_local 652 10.0 115.401 115.401 115.411 115.411 ls_scf_dm_to_ks 11 5.0 0.000 0.000 85.749 85.749 matrix_ls_to_qs 11 6.0 0.000 0.000 82.501 82.501 dbcsr_multiply_generic 185 6.1 0.848 0.848 72.048 72.048 dbcsr_copy_into_existing 11 7.0 45.253 45.253 45.254 45.254 multiply_cannon 185 7.1 0.280 0.280 43.685 43.685 dbcsr_complete_redistribute 23 7.5 29.884 29.884 40.867 40.867 matrix_decluster 11 7.0 0.000 0.000 37.247 37.247 multiply_cannon_loop 185 8.1 0.235 0.235 31.341 31.341 make_m2s 370 7.1 0.038 0.038 24.011 24.011 make_images 370 8.1 10.452 10.452 22.519 22.519 multiply_cannon_multrec 185 9.1 21.927 21.927 21.959 21.959 dbcsr_finalize 646 7.5 0.172 0.172 14.418 14.418 dbcsr_merge_all 597 8.5 2.249 2.249 13.381 13.381 setup_rec_index_2d 370 8.1 11.973 11.973 11.973 11.973 dbcsr_sort_indices 1103 9.9 10.058 10.058 10.058 10.058 tree_to_linear_d 110 9.4 9.897 9.897 9.897 9.897 calculate_norms 370 9.1 9.147 9.147 9.147 9.147 quick_finalize 395 10.0 0.349 0.349 8.692 8.692 ls_scf_init_scf 1 4.0 0.000 0.000 8.235 8.235 dbcsr_special_finalize 370 9.1 0.002 0.002 8.046 8.046 ls_scf_init_matrix_S 1 5.0 0.000 0.000 7.900 7.900 matrix_sqrt_Newton_Schulz 1 6.0 0.001 0.001 7.249 7.249 ------------------------------------------------------------------------------- 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 0.007 0.021 62.392 62.403 qs_energies 1 2.0 0.000 0.000 62.282 62.282 ls_scf 1 3.0 0.000 0.000 62.230 62.231 ls_scf_main 1 4.0 0.000 0.007 59.838 59.839 density_matrix_trs4 11 5.0 0.006 0.018 57.468 57.563 dbcsr_multiply_generic 185 6.1 0.056 0.079 54.217 54.452 multiply_cannon 185 7.1 0.032 0.036 45.011 45.514 multiply_cannon_loop 185 8.1 0.107 0.131 42.753 43.177 multiply_cannon_multrec 1480 9.1 26.423 28.695 26.670 28.957 mp_waitall_1 11936 10.3 14.120 16.815 14.120 16.815 multiply_cannon_metrocomm3 1480 9.1 0.012 0.022 8.069 10.973 make_m2s 370 7.1 0.034 0.036 6.327 6.396 make_images 370 8.1 0.619 0.664 6.203 6.270 multiply_cannon_metrocomm1 1480 9.1 0.007 0.010 3.470 6.010 calculate_norms 2960 9.1 4.382 5.482 4.382 5.482 make_images_data 370 9.1 0.008 0.010 2.785 3.019 hybrid_alltoall_any 393 9.9 0.154 0.785 2.412 2.666 mp_sum_l 1119 5.6 1.857 2.445 1.857 2.445 arnoldi_extremal 12 6.1 0.000 0.000 2.410 2.435 arnoldi_normal_ev 12 7.1 0.001 0.007 2.409 2.435 build_subspace 23 8.1 0.018 0.023 2.318 2.320 ls_scf_dm_to_ks 11 5.0 0.000 0.000 2.053 2.185 dbcsr_matrix_vector_mult 652 9.0 0.013 0.047 1.984 2.040 dbcsr_complete_redistribute 23 7.5 1.154 1.206 1.845 1.945 matrix_ls_to_qs 11 6.0 0.000 0.000 1.805 1.907 ls_scf_init_scf 1 4.0 0.000 0.000 1.832 1.832 ls_scf_init_matrix_S 1 5.0 0.000 0.000 1.809 1.814 matrix_decluster 11 7.0 0.000 0.000 1.666 1.768 dbcsr_matrix_vector_mult_local 652 10.0 1.650 1.698 1.652 1.700 make_images_pack 370 9.1 1.553 1.695 1.557 1.699 matrix_sqrt_Newton_Schulz 1 6.0 0.000 0.001 1.652 1.654 dbcsr_multiply_generic_mpsum_f 137 7.1 0.000 0.000 1.013 1.562 dbcsr_finalize 646 7.5 0.007 0.008 1.276 1.452 buffer_matrices_ensure_size 370 8.1 1.208 1.405 1.208 1.405 ------------------------------------------------------------------------------- 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=69.439, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=115.401, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_copy_into_existing", label="dbcsr_copy_into_existing", y=45.253, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_complete_redistribute", label="dbcsr_complete_redistribute", y=29.884, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=21.927, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="setup_rec_index_2d", label="setup_rec_index_2d", y=11.973, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="calculate_norms", label="calculate_norms", y=9.147, 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="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=12.806000000000012, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=1.65, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="dbcsr_copy_into_existing", label="dbcsr_copy_into_existing", y=0.0, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="dbcsr_complete_redistribute", label="dbcsr_complete_redistribute", y=1.154, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=26.423, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="setup_rec_index_2d", label="setup_rec_index_2d", y=0.0, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="calculate_norms", label="calculate_norms", y=4.382, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=14.12, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=1.857, 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 0.007 0.007 70.111 70.111 lib_test 1 2.0 0.000 0.000 70.103 70.103 dbcsr_run_tests 3 3.0 0.002 0.002 70.103 70.103 test_multiplies_multiproc 3 4.0 0.001 0.001 54.617 54.617 dbcsr_redistribute 9 5.0 36.191 36.191 37.736 37.736 dbcsr_multiply_generic 9 5.0 0.001 0.001 15.567 15.567 dbcsr_make_random_matrix 9 4.0 12.489 12.489 15.379 15.379 multiply_cannon 9 6.0 0.001 0.001 10.950 10.950 multiply_cannon_loop 9 7.0 0.010 0.010 10.595 10.595 multiply_cannon_multrec 9 8.0 10.585 10.585 10.585 10.585 dbcsr_finalize 27 5.7 0.009 0.009 5.350 5.350 dbcsr_merge_all 18 6.5 1.920 1.920 4.628 4.628 dbcsr_data_release 975 7.6 2.765 2.765 2.765 2.765 tree_to_linear_d 9 7.0 1.853 1.853 1.853 1.853 make_m2s 18 6.0 0.001 0.001 1.584 1.584 make_images 18 7.0 0.554 0.554 1.536 1.536 ------------------------------------------------------------------------------- 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 0.010 17.169 17.173 lib_test 1 2.0 0.000 0.000 17.141 17.161 dbcsr_run_tests 3 3.0 0.000 0.001 17.141 17.160 test_multiplies_multiproc 3 4.0 0.000 0.002 16.309 16.363 dbcsr_multiply_generic 9 5.0 0.001 0.001 14.989 15.092 multiply_cannon 9 6.0 0.001 0.002 13.277 13.565 multiply_cannon_loop 9 7.0 0.002 0.002 12.991 13.262 multiply_cannon_multrec 72 8.0 10.785 11.335 10.786 11.336 mp_waitall_1 576 9.2 2.503 3.234 2.503 3.234 multiply_cannon_metrocomm1 72 8.0 0.001 0.001 1.944 2.728 multiply_cannon_metrocomm3 72 8.0 0.000 0.000 0.254 0.928 dbcsr_data_release 444 7.6 0.792 0.918 0.792 0.918 dbcsr_make_random_matrix 9 4.0 0.659 0.665 0.801 0.824 dbcsr_finalize 27 5.7 0.000 0.000 0.709 0.803 mp_sum_l 390 2.5 0.387 0.802 0.387 0.802 dbcsr_multiply_generic_mpsum_f 9 6.0 0.000 0.000 0.383 0.798 dbcsr_destroy 111 5.9 0.000 0.000 0.629 0.714 make_m2s 18 6.0 0.001 0.001 0.634 0.676 make_images 18 7.0 0.021 0.021 0.631 0.673 dbcsr_merge_all 18 6.5 0.099 0.123 0.543 0.650 make_images_data 18 8.0 0.000 0.001 0.333 0.423 dbcsr_redistribute 9 5.0 0.229 0.256 0.386 0.417 dbcsr_data_copy_aa2 18 7.5 0.328 0.407 0.328 0.407 hybrid_alltoall_any 18 9.0 0.024 0.115 0.291 0.377 ------------------------------------------------------------------------------- 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=6.160999999999994, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_redistribute", label="dbcsr_redistribute", y=36.191, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=12.489, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=10.585, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_data_release", label="dbcsr_data_release", y=2.765, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_merge_all", label="dbcsr_merge_all", y=1.92, 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=1.7149999999999999, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_redistribute", label="dbcsr_redistribute", y=0.229, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=0.659, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=10.785, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_data_release", label="dbcsr_data_release", y=0.792, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_merge_all", label="dbcsr_merge_all", y=0.099, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=0.387, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=2.503, 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 0.053 0.053 131.342 131.342 qs_mol_dyn_low 1 2.0 0.003 0.003 129.794 129.794 velocity_verlet 5 3.0 0.003 0.003 106.041 106.041 qmmm_el_coupling 6 3.8 0.000 0.000 87.273 87.273 qmmm_elec_with_gaussian 6 4.8 0.011 0.011 87.270 87.270 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 86.650 86.650 qmmm_elec_gaussian_low_G 6 6.8 85.744 85.744 85.744 85.744 qs_forces 6 3.8 0.000 0.000 34.069 34.069 qs_energies 6 4.8 0.000 0.000 30.277 30.277 scf_env_do_scf 6 5.8 0.001 0.001 28.001 28.001 scf_env_do_scf_inner_loop 39 6.8 0.004 0.004 24.380 24.380 rebuild_ks_matrix 45 8.4 0.000 0.000 23.497 23.497 qs_ks_build_kohn_sham_matrix 45 9.4 0.005 0.005 23.497 23.497 qs_ks_update_qs_env 45 7.8 0.000 0.000 20.126 20.126 pw_transfer 966 12.3 0.051 0.051 16.722 16.722 fft_wrap_pw1pw2 801 13.6 0.006 0.006 16.536 16.536 fft_wrap_pw1pw2_150 507 15.2 2.226 2.226 16.115 16.115 qs_vxc_create 45 10.4 0.001 0.001 12.854 12.854 xc_vxc_pw_create 45 11.4 0.641 0.641 12.853 12.853 xc_pw_derive 270 13.4 0.002 0.002 9.119 9.119 fft3d_s 802 15.6 7.545 7.545 7.599 7.599 qs_rho_update_rho_low 45 7.9 0.000 0.000 6.898 6.898 calculate_rho_elec 45 8.9 0.563 0.563 6.898 6.898 xc_rho_set_and_dset_create 45 12.4 0.588 0.588 6.674 6.674 pw_scatter_s 429 15.8 5.541 5.541 5.541 5.541 xc_pw_divergence 45 12.4 0.001 0.001 5.494 5.494 qmmm_forces 6 3.8 0.001 0.001 5.242 5.242 qmmm_forces_with_gaussian 6 4.8 0.017 0.017 4.912 4.912 pw_integral_ab 2539 7.4 4.458 4.458 4.458 4.458 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 4.185 4.185 qs_ks_ddapc 45 10.4 0.001 0.001 4.100 4.100 init_scf_loop 6 6.8 0.000 0.000 3.588 3.588 qmmm_forces_gaussian_low_G 6 6.8 3.491 3.491 3.491 3.491 sum_up_and_integrate 45 10.4 0.490 0.490 3.475 3.475 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 3.378 3.378 density_rs2pw 45 9.9 0.002 0.002 3.186 3.186 grid_collocate_task_list 45 9.9 3.150 3.150 3.150 3.150 integrate_v_rspace 45 11.4 0.006 0.006 2.985 2.985 ------------------------------------------------------------------------------- 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 0.039 0.055 54.639 54.650 qs_mol_dyn_low 1 2.0 0.003 0.004 53.526 53.582 qs_forces 6 3.8 0.000 0.001 39.483 39.483 qs_energies 6 4.8 0.000 0.000 37.682 37.682 scf_env_do_scf 6 5.8 0.000 0.001 36.769 36.769 scf_env_do_scf_inner_loop 113 6.2 0.002 0.017 35.276 35.276 rebuild_ks_matrix 119 8.1 0.000 0.000 26.216 26.226 qs_ks_build_kohn_sham_matrix 119 9.1 0.013 0.015 26.216 26.226 qs_ks_update_qs_env 119 7.3 0.001 0.001 24.700 24.709 velocity_verlet 5 3.0 0.002 0.003 22.303 22.306 pw_transfer 2446 12.3 0.191 0.222 18.926 19.420 fft_wrap_pw1pw2 2059 13.4 0.021 0.024 18.531 19.074 fft_wrap_pw1pw2_150 1321 14.9 1.133 1.360 17.911 18.325 fft3d_ps 2059 15.4 6.540 7.556 14.723 15.603 qs_vxc_create 119 10.1 0.002 0.003 14.229 14.233 xc_vxc_pw_create 119 11.1 0.136 0.209 14.227 14.231 xc_pw_derive 714 13.1 0.009 0.012 10.896 11.151 qs_rho_update_rho_low 119 7.3 0.000 0.001 10.498 10.500 calculate_rho_elec 119 8.3 0.048 0.054 10.497 10.499 sum_up_and_integrate 119 10.1 0.072 0.085 8.717 8.735 integrate_v_rspace 119 11.1 0.003 0.003 8.645 8.668 xc_pw_divergence 119 12.1 0.004 0.005 7.127 7.368 qmmm_forces 6 3.8 0.002 0.002 7.144 7.145 xc_rho_set_and_dset_create 119 12.1 0.336 0.432 6.777 6.968 qmmm_forces_with_gaussian 6 4.8 0.007 0.010 6.688 6.885 mp_alltoall_z22v 2059 17.4 4.496 6.352 4.496 6.352 density_rs2pw 119 9.3 0.005 0.006 6.087 6.323 qmmm_el_coupling 6 3.8 0.000 0.000 6.000 6.156 qmmm_elec_with_gaussian 6 4.8 0.003 0.003 5.999 6.154 rs_pw_transfer 988 11.5 0.010 0.012 5.761 6.088 potential_pw2rs 119 12.1 0.006 0.006 5.045 5.064 x_to_yz 1095 16.8 2.097 2.545 4.335 4.986 grid_collocate_task_list 119 9.3 4.240 4.495 4.240 4.495 yz_to_x 964 16.0 1.541 1.999 3.800 4.463 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 3.822 3.918 grid_integrate_task_list 119 12.1 3.342 3.534 3.342 3.534 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 3.400 3.432 qmmm_forces_gaussian_low_G 6 6.8 3.141 3.236 3.141 3.236 qmmm_elec_gaussian_low_G 6 6.8 2.814 2.845 2.814 2.845 mp_waitany 4028 12.8 2.120 2.785 2.120 2.785 pw_restrict_s3 18 5.8 1.294 1.343 2.298 2.454 rs_pw_transfer_PW2RS_150 125 13.9 0.640 0.769 2.119 2.171 qs_ks_ddapc 119 10.1 0.002 0.002 2.042 2.124 qmmm_elec_with_gaussian:spline 6 5.8 0.000 0.000 1.971 2.123 pw_prolongate_s3 18 6.8 1.097 1.142 1.971 2.123 rs_pw_transfer_RS2PW_150 125 11.2 0.501 0.601 1.624 1.956 qs_scf_new_mos 113 7.2 0.000 0.000 1.912 1.917 qs_scf_loop_do_ot 113 8.2 0.000 0.000 1.912 1.916 ot_scf_mini 113 9.2 0.001 0.001 1.832 1.836 dbcsr_multiply_generic 2588 12.3 0.055 0.056 1.731 1.768 pw_gather_p 964 15.0 1.126 1.641 1.126 1.641 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 1.528 1.529 pw_scatter_p 1095 15.8 1.501 1.524 1.501 1.524 init_scf_loop 6 6.8 0.000 0.000 1.491 1.491 pw_integral_ab 2761 7.7 1.049 1.188 1.317 1.431 mp_sum_d 5814 12.2 0.745 1.305 0.745 1.305 mp_waitall_1 177795 16.4 1.075 1.261 1.075 1.261 mp_sum_dm3 33 5.7 1.105 1.180 1.105 1.180 ot_mini 113 10.2 0.000 0.001 1.126 1.131 ------------------------------------------------------------------------------- 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=21.41300000000001, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=85.744, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_s", label="fft3d_s", y=7.545, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_scatter_s", label="pw_scatter_s", y=5.541, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_integral_ab", label="pw_integral_ab", y=4.458, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.491, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=3.15, 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=29.017000000000003, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=2.814, 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_scatter_s", label="pw_scatter_s", y=0.0, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="pw_integral_ab", label="pw_integral_ab", y=1.049, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.141, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=4.24, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=6.54, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=3.342, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=4.496, yerr=0.0 Summary: Performance test took 33 minutes. Status: OK Removing intermediate container 4482b60ac219 ---> 0b9f8d4a2a32 Step 41/42 : CMD cat $(find ./report.log -mmin +10) | sed '/^Summary:/ s/$/ (cached)/' ---> Running in 085b26085df4 Removing intermediate container 085b26085df4 ---> 5379e6c6a0a9 Step 42/42 : ENTRYPOINT [] ---> Running in 4c51c3d71966 Removing intermediate container 4c51c3d71966 ---> 004f33514b48 [Warning] One or more build-args [GIT_COMMIT_SHA] were not consumed Successfully built 004f33514b48 Successfully tagged us-central1-docker.pkg.dev/cp2k-org-project/cp2kci/img_cp2k-perf-openmp:master Pushing new image... done. #################### Running Image cp2k-perf-openmp #################### Uploading artifacts... done EndDate: 2023-02-16 11:51:24+00:00