StartDate: 2024-02-28 08:04:49+00:00 CpuId: 32x AMD EPYC (3rd Gen) (Milan) [Zen 3], 7nm (SMT disabled) CommitSHA: 904d571b43f5f0873637c980131f2c93e7676bc7 CommitTime: 2024-02-27 11:37:46 +0100 CommitAuthor: Juerg Hutter CommitSubject: Primitives for MinBas expansion can be set in input (#3288) #################### Building Image cp2k-perf-openmp #################### Dockerfile: /tools/docker/Dockerfile.test_performance Build-Path: / Build-Args: GIT_COMMIT_SHA=904d571b43f5f0873637c980131f2c93e7676bc7 Build-Cache: Yes Populating docker build cache... done. DEPRECATED: The legacy builder is deprecated and will be removed in a future release. BuildKit is currently disabled; enable it by removing the DOCKER_BUILDKIT=0 environment-variable. Sending build context to Docker daemon 393.7MB Step 1/42 : FROM ubuntu:22.04 22.04: Pulling from library/ubuntu 01007420e9b0: Pulling fs layer 01007420e9b0: Verifying Checksum 01007420e9b0: Download complete 01007420e9b0: Pull complete Digest: sha256:f9d633ff6640178c2d0525017174a688e2c1aef28f0a0130b26bd5554491f0da Status: Downloaded newer image for ubuntu:22.04 ---> 3db8720ecbf5 Step 2/42 : WORKDIR /opt/cp2k-toolchain ---> Using cache ---> c91877cf7c4f Step 3/42 : COPY ./tools/toolchain/install_requirements*.sh ./ ---> Using cache ---> 40cd32e951b0 Step 4/42 : RUN ./install_requirements.sh ubuntu:22.04 ---> Using cache ---> 0e0c260a973e Step 5/42 : RUN mkdir scripts ---> Using cache ---> c18ee2447245 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 ---> 50a53065b028 Step 7/42 : COPY ./tools/toolchain/install_cp2k_toolchain.sh . ---> Using cache ---> 410cc668ef16 Step 8/42 : RUN ./install_cp2k_toolchain.sh --install-all --with-gcc=system --dry-run ---> Using cache ---> ef458af826b9 Step 9/42 : COPY ./tools/toolchain/scripts/stage0/ ./scripts/stage0/ ---> Using cache ---> 5b5e2bc49cd5 Step 10/42 : RUN ./scripts/stage0/install_stage0.sh && rm -rf ./build ---> Using cache ---> b6701df80a4f Step 11/42 : COPY ./tools/toolchain/scripts/stage1/ ./scripts/stage1/ ---> Using cache ---> 65bb47d5e0be Step 12/42 : RUN ./scripts/stage1/install_stage1.sh && rm -rf ./build ---> Using cache ---> 3235032c243b Step 13/42 : COPY ./tools/toolchain/scripts/stage2/ ./scripts/stage2/ ---> Using cache ---> 9fdaac814822 Step 14/42 : RUN ./scripts/stage2/install_stage2.sh && rm -rf ./build ---> Using cache ---> 89a5d839f744 Step 15/42 : COPY ./tools/toolchain/scripts/stage3/ ./scripts/stage3/ ---> Using cache ---> d4181b8c9115 Step 16/42 : RUN ./scripts/stage3/install_stage3.sh && rm -rf ./build ---> Using cache ---> a200824ab62c Step 17/42 : COPY ./tools/toolchain/scripts/stage4/ ./scripts/stage4/ ---> Using cache ---> cf4e3530cfac Step 18/42 : RUN ./scripts/stage4/install_stage4.sh && rm -rf ./build ---> Using cache ---> b7543240dd55 Step 19/42 : COPY ./tools/toolchain/scripts/stage5/ ./scripts/stage5/ ---> Using cache ---> 7661f7b25b97 Step 20/42 : RUN ./scripts/stage5/install_stage5.sh && rm -rf ./build ---> Using cache ---> 2b02d0f56252 Step 21/42 : COPY ./tools/toolchain/scripts/stage6/ ./scripts/stage6/ ---> Using cache ---> c6fa05294c14 Step 22/42 : RUN ./scripts/stage6/install_stage6.sh && rm -rf ./build ---> Using cache ---> 57c0d372fca0 Step 23/42 : COPY ./tools/toolchain/scripts/stage7/ ./scripts/stage7/ ---> Using cache ---> c6bed1fbbe7e Step 24/42 : RUN ./scripts/stage7/install_stage7.sh && rm -rf ./build ---> Using cache ---> 3c67707a23a0 Step 25/42 : COPY ./tools/toolchain/scripts/stage8/ ./scripts/stage8/ ---> Using cache ---> b8ef848c5e78 Step 26/42 : RUN ./scripts/stage8/install_stage8.sh && rm -rf ./build ---> Using cache ---> 61b028d7894a Step 27/42 : COPY ./tools/toolchain/scripts/arch_base.tmpl ./tools/toolchain/scripts/generate_arch_files.sh ./scripts/ ---> Using cache ---> 7eda2a584141 Step 28/42 : RUN ./scripts/generate_arch_files.sh && rm -rf ./build ---> Using cache ---> 7ac6d70c4f6f Step 29/42 : WORKDIR /opt/cp2k ---> Using cache ---> 1c08b4b239c6 Step 30/42 : COPY ./Makefile . ---> Using cache ---> f0c5e49b29f4 Step 31/42 : COPY ./src ./src ---> Using cache ---> 20f6ab5945bc Step 32/42 : COPY ./exts ./exts ---> Using cache ---> b6fb8553e726 Step 33/42 : COPY ./tools/build_utils ./tools/build_utils ---> Using cache ---> 264dd36a6fce Step 34/42 : RUN /bin/bash -c " mkdir -p arch && ln -vs /opt/cp2k-toolchain/install/arch/local.psmp ./arch/" ---> Running in d510a621d1cd './arch/local.psmp' -> '/opt/cp2k-toolchain/install/arch/local.psmp' Removing intermediate container d510a621d1cd ---> 7e01bb8f7895 Step 35/42 : COPY ./data ./data ---> c6fe5517abef Step 36/42 : COPY ./tests ./tests ---> 2fe022d72d02 Step 37/42 : COPY ./tools/regtesting ./tools/regtesting ---> 911211ecb0e6 Step 38/42 : COPY ./benchmarks ./benchmarks ---> 1c6da61df1de Step 39/42 : COPY ./tools/docker/scripts/test_performance.sh ./tools/docker/scripts/plot_performance.py ./ ---> 24b60a1a8957 Step 40/42 : RUN ./test_performance.sh "local" 2>&1 | tee report.log ---> Running in 18f315fe96a9 ========== Compiling CP2K ========== Compiling cp2k... done. Checking benchmark inputs... Found 75 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 0.035 0.035 87.080 87.080 qs_mol_dyn_low 1 2.0 0.003 0.003 86.512 86.512 qs_forces 11 3.9 0.001 0.001 86.469 86.469 qs_energies 11 4.9 0.001 0.001 80.368 80.368 scf_env_do_scf 11 5.9 0.002 0.002 69.231 69.231 velocity_verlet 10 3.0 0.002 0.002 55.805 55.805 scf_env_do_scf_inner_loop 108 6.5 0.013 0.013 55.580 55.580 qs_scf_new_mos 108 7.5 0.001 0.001 20.881 20.881 qs_scf_loop_do_ot 108 8.5 0.001 0.001 20.880 20.880 dbcsr_multiply_generic 2286 12.5 0.170 0.170 20.857 20.857 rebuild_ks_matrix 119 8.3 0.001 0.001 20.547 20.547 qs_ks_build_kohn_sham_matrix 119 9.3 0.013 0.013 20.546 20.546 qs_rho_update_rho_low 119 7.7 0.001 0.001 19.699 19.699 calculate_rho_elec 119 8.7 0.955 0.955 19.698 19.698 ot_scf_mini 108 9.5 0.002 0.002 19.532 19.532 qs_ks_update_qs_env 119 7.6 0.001 0.001 18.838 18.838 grid_collocate_task_list 119 9.7 15.021 15.021 15.021 15.021 init_scf_loop 11 6.9 0.000 0.000 13.429 13.429 sum_up_and_integrate 119 10.3 0.001 0.001 12.899 12.899 integrate_v_rspace 119 11.3 0.108 0.108 12.835 12.835 ot_mini 108 10.5 0.001 0.001 12.531 12.531 make_m2s 4572 13.5 0.046 0.046 10.946 10.946 prepare_preconditioner 11 7.9 0.000 0.000 10.800 10.800 make_preconditioner 11 8.9 0.000 0.000 10.800 10.800 grid_integrate_task_list 119 12.3 10.531 10.531 10.531 10.531 make_full_inverse_cholesky 11 9.9 0.026 0.026 9.689 9.689 qs_ot_get_derivative 108 11.5 0.001 0.001 6.885 6.885 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 6.646 6.646 fft_wrap_pw1pw2 1201 11.6 0.009 0.009 6.583 6.583 multiply_cannon 2286 13.5 0.181 0.181 5.816 5.816 dbcsr_make_dense_low 5837 15.5 0.069 0.069 5.760 5.760 make_images 4572 14.5 2.374 2.374 5.689 5.689 make_dense_data 5837 16.5 5.151 5.151 5.677 5.677 ot_diis_step 108 11.5 0.003 0.003 5.644 5.644 fft_wrap_pw1pw2_140 487 12.2 0.906 0.906 5.624 5.624 multiply_cannon_loop 2286 14.5 0.059 0.059 5.344 5.344 multiply_cannon_multrec 2286 15.5 5.236 5.236 5.283 5.283 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 5.177 5.177 apply_single 119 13.6 0.000 0.000 5.176 5.176 dbcsr_make_images_dense 3978 14.8 0.017 0.017 4.972 4.972 init_scf_run 11 5.9 0.003 0.003 3.873 3.873 scf_env_initial_rho_setup 11 6.9 0.002 0.002 3.870 3.870 density_rs2pw 119 9.7 0.004 0.004 3.722 3.722 qs_env_update_s_mstruct 11 6.9 0.000 0.000 3.699 3.699 dbcsr_copy 2102 12.0 0.236 0.236 3.576 3.576 dbcsr_complete_redistribute 329 12.2 1.749 1.749 3.514 3.514 qs_ot_get_p 119 10.4 0.001 0.001 3.443 3.443 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 3.418 3.418 wfi_extrapolate 11 7.9 0.001 0.001 3.383 3.383 dbcsr_copy_into_existing 22 7.9 3.280 3.280 3.280 3.280 qs_create_task_list 11 7.9 0.000 0.000 3.214 3.214 generate_qs_task_list 11 8.9 1.953 1.953 3.214 3.214 copy_dbcsr_to_fm 153 11.3 0.002 0.002 2.945 2.945 fft3d_s 1202 13.6 2.814 2.814 2.819 2.819 cp_fm_cholesky_invert 11 10.9 2.794 2.794 2.794 2.794 cp_fm_cholesky_decompose 22 10.9 2.779 2.779 2.779 2.779 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 2.681 2.681 build_core_hamiltonian_matrix 11 6.9 0.001 0.001 2.513 2.513 pw_poisson_solve 119 10.3 0.002 0.002 2.351 2.351 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.261 2.261 potential_pw2rs 119 12.3 0.047 0.047 2.196 2.196 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 2.144 2.144 qs_ot_get_derivative_taylor 59 13.0 0.001 0.001 2.076 2.076 qs_ot_p2m_diag 50 11.0 0.154 0.154 2.061 2.061 dbcsr_data_release 279532 16.0 1.959 1.959 1.959 1.959 copy_fm_to_dbcsr 176 11.2 0.001 0.001 1.870 1.870 dbcsr_finalize 5186 13.8 0.137 0.137 1.779 1.779 cp_fm_upper_to_full 72 14.2 1.756 1.756 1.756 1.756 ------------------------------------------------------------------------------- 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 0.010 0.035 48.053 48.070 qs_mol_dyn_low 1 2.0 0.004 0.005 47.918 47.923 qs_forces 11 3.9 0.001 0.002 47.824 47.825 qs_energies 11 4.9 0.001 0.001 44.819 44.823 scf_env_do_scf 11 5.9 0.000 0.003 40.892 40.892 scf_env_do_scf_inner_loop 108 6.5 0.003 0.024 37.713 37.713 velocity_verlet 10 3.0 0.001 0.003 28.381 28.383 rebuild_ks_matrix 119 8.3 0.000 0.001 16.949 17.020 qs_ks_build_kohn_sham_matrix 119 9.3 0.016 0.020 16.948 17.019 dbcsr_multiply_generic 2286 12.5 0.072 0.075 15.260 15.396 qs_ks_update_qs_env 119 7.6 0.001 0.005 15.074 15.144 qs_rho_update_rho_low 119 7.7 0.001 0.001 13.095 13.107 calculate_rho_elec 119 8.7 0.030 0.031 13.094 13.107 qs_scf_new_mos 108 7.5 0.001 0.001 12.273 12.342 qs_scf_loop_do_ot 108 8.5 0.001 0.001 12.273 12.342 sum_up_and_integrate 119 10.3 0.002 0.002 12.083 12.100 integrate_v_rspace 119 11.3 0.004 0.004 12.060 12.076 multiply_cannon 2286 13.5 0.137 0.153 11.470 11.867 ot_scf_mini 108 9.5 0.002 0.002 11.573 11.644 multiply_cannon_loop 2286 14.5 0.113 0.123 10.859 11.198 grid_collocate_task_list 119 9.7 8.873 9.181 8.873 9.181 mp_waitall_1 158411 16.6 8.685 9.163 8.685 9.163 grid_integrate_task_list 119 12.3 8.001 8.151 8.001 8.151 multiply_cannon_metrocomm3 18288 15.5 0.056 0.067 6.807 7.201 ot_mini 108 10.5 0.001 0.002 6.763 6.841 density_rs2pw 119 9.7 0.005 0.006 3.810 4.215 multiply_cannon_multrec 18288 15.5 3.620 3.751 3.631 3.762 fft_wrap_pw1pw2 1201 11.6 0.016 0.018 3.560 3.597 qs_ot_get_derivative 108 11.5 0.001 0.001 3.415 3.490 potential_pw2rs 119 12.3 0.006 0.007 3.475 3.483 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 3.352 3.443 apply_single 119 13.6 0.000 0.000 3.352 3.443 ot_diis_step 108 11.5 0.003 0.003 3.310 3.310 init_scf_loop 11 6.9 0.000 0.000 3.161 3.161 fft_wrap_pw1pw2_140 487 12.2 0.142 0.151 3.019 3.074 fft3d_ps 1201 13.6 1.255 1.311 2.647 2.705 make_m2s 4572 13.5 0.047 0.058 2.627 2.684 init_scf_run 11 5.9 0.000 0.006 2.576 2.576 scf_env_initial_rho_setup 11 6.9 0.000 0.005 2.576 2.576 transfer_pw2rs 487 13.2 0.006 0.007 2.527 2.532 transfer_rs2pw 487 10.6 0.006 0.008 2.109 2.486 wfi_extrapolate 11 7.9 0.001 0.001 2.338 2.339 make_images 4572 14.5 0.117 0.124 2.276 2.337 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 2.015 2.023 mp_waitany 9880 13.7 1.554 1.971 1.554 1.971 qs_ot_get_p 119 10.4 0.001 0.001 1.575 1.696 transfer_rs2pw_140 130 11.5 0.198 0.235 1.141 1.519 make_images_data 4572 15.5 0.040 0.046 1.292 1.415 prepare_preconditioner 11 7.9 0.000 0.000 1.307 1.329 make_preconditioner 11 8.9 0.000 0.000 1.307 1.329 transfer_pw2rs_140 130 13.9 0.420 0.451 1.290 1.312 hybrid_alltoall_any 4725 16.4 0.073 0.202 1.143 1.260 make_full_inverse_cholesky 11 9.9 0.000 0.000 1.191 1.214 mp_alltoall_z22v 1201 15.6 1.126 1.212 1.126 1.212 mp_alltoall_d11v 2130 13.8 0.891 1.156 0.891 1.156 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 1.147 1.148 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 1.062 1.109 qs_ot_get_derivative_taylor 59 13.0 0.001 0.001 1.033 1.069 cp_dbcsr_sm_fm_multiply 37 9.5 0.001 0.001 1.017 1.018 mp_sum_l 11298 13.2 0.717 0.995 0.717 0.995 transfer_pw2rs_50 119 14.3 0.375 0.398 0.962 0.994 ------------------------------------------------------------------------------- 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=47.861, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=15.021, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=10.531, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=5.236, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="make_dense_data", label="make_dense_data", y=5.151, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="dbcsr_copy_into_existing", label="dbcsr_copy_into_existing", y=3.28, 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=17.32, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=8.873, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=8.001, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=3.62, 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="dbcsr_copy_into_existing", label="dbcsr_copy_into_existing", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitany", label="mp_waitany", y=1.554, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=8.685, yerr=0.0 Running H2O-64_nonortho.inp with 1 threads and 32 ranks... done. Running H2O-64_nonortho.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/H2O-64_nonortho_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.037 0.037 114.281 114.281 qs_mol_dyn_low 1 2.0 0.003 0.003 113.608 113.608 qs_forces 11 3.9 0.001 0.001 113.565 113.565 qs_energies 11 4.9 0.001 0.001 105.475 105.475 scf_env_do_scf 11 5.9 0.002 0.002 92.287 92.287 scf_env_do_scf_inner_loop 96 6.5 0.011 0.011 76.726 76.726 velocity_verlet 10 3.0 0.002 0.002 72.261 72.261 rebuild_ks_matrix 107 8.3 0.001 0.001 34.481 34.481 qs_ks_build_kohn_sham_matrix 107 9.3 0.012 0.012 34.480 34.480 qs_rho_update_rho_low 107 7.7 0.000 0.000 33.173 33.173 calculate_rho_elec 107 8.7 0.872 0.872 33.172 33.172 qs_ks_update_qs_env 107 7.6 0.001 0.001 30.897 30.897 grid_collocate_task_list 107 9.7 28.645 28.645 28.645 28.645 sum_up_and_integrate 107 10.3 0.001 0.001 27.319 27.319 integrate_v_rspace 107 11.3 0.106 0.106 27.222 27.222 grid_integrate_task_list 107 12.3 24.639 24.639 24.639 24.639 dbcsr_multiply_generic 1966 12.4 0.136 0.136 19.725 19.725 qs_scf_new_mos 96 7.5 0.001 0.001 19.691 19.691 qs_scf_loop_do_ot 96 8.5 0.001 0.001 19.691 19.691 ot_scf_mini 96 9.5 0.002 0.002 18.455 18.455 init_scf_loop 11 6.9 0.000 0.000 15.353 15.353 ot_mini 96 10.5 0.001 0.001 11.509 11.509 prepare_preconditioner 11 7.9 0.000 0.000 11.185 11.185 make_preconditioner 11 8.9 0.000 0.000 11.185 11.185 make_m2s 3932 13.4 0.040 0.040 10.213 10.213 make_full_inverse_cholesky 11 9.9 0.025 0.025 9.972 9.972 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 7.040 7.040 fft_wrap_pw1pw2 1081 11.6 0.009 0.009 6.644 6.644 qs_ot_get_derivative 96 11.5 0.001 0.001 6.104 6.104 multiply_cannon 1966 13.4 0.156 0.156 5.920 5.920 fft_wrap_pw1pw2_140 439 12.2 0.913 0.913 5.512 5.512 init_scf_run 11 5.9 0.003 0.003 5.506 5.506 scf_env_initial_rho_setup 11 6.9 0.002 0.002 5.503 5.503 multiply_cannon_loop 1966 14.4 0.051 0.051 5.502 5.502 multiply_cannon_multrec 1966 15.4 5.404 5.404 5.450 5.450 ot_diis_step 96 11.5 0.003 0.003 5.402 5.402 make_images 3932 14.4 2.092 2.092 5.361 5.361 dbcsr_make_dense_low 4961 15.5 0.060 0.060 5.209 5.209 make_dense_data 4961 16.5 4.705 4.705 5.137 5.137 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 5.130 5.130 apply_single 107 13.6 0.000 0.000 5.130 5.130 wfi_extrapolate 11 7.9 0.001 0.001 4.847 4.847 dbcsr_make_images_dense 3386 14.7 0.015 0.015 4.571 4.571 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 4.472 4.472 qs_env_update_s_mstruct 11 6.9 0.000 0.000 4.081 4.081 dbcsr_complete_redistribute 317 12.2 1.805 1.805 3.671 3.671 qs_create_task_list 11 7.9 0.000 0.000 3.660 3.660 generate_qs_task_list 11 8.9 2.387 2.387 3.660 3.660 density_rs2pw 107 9.7 0.003 0.003 3.655 3.655 dbcsr_copy 1855 11.9 0.232 0.232 3.631 3.631 build_core_hamiltonian_matrix_ 11 4.9 0.001 0.001 3.616 3.616 qs_ot_get_p 107 10.4 0.001 0.001 3.518 3.518 dbcsr_copy_into_existing 22 7.9 3.341 3.341 3.342 3.342 copy_dbcsr_to_fm 147 11.2 0.002 0.002 3.130 3.130 cp_fm_cholesky_decompose 22 10.9 2.923 2.923 2.923 2.923 cp_fm_cholesky_invert 11 10.9 2.893 2.893 2.893 2.893 fft3d_s 1082 13.6 2.864 2.864 2.869 2.869 build_core_hamiltonian_matrix 11 6.9 0.000 0.000 2.514 2.514 potential_pw2rs 107 12.3 0.044 0.044 2.478 2.478 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.397 2.397 ------------------------------------------------------------------------------- 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 0.028 75.244 75.257 qs_mol_dyn_low 1 2.0 0.003 0.005 75.100 75.105 qs_forces 11 3.9 0.002 0.002 75.057 75.058 qs_energies 11 4.9 0.001 0.001 70.134 70.136 scf_env_do_scf 11 5.9 0.000 0.002 64.906 64.907 scf_env_do_scf_inner_loop 96 6.5 0.003 0.020 59.954 59.955 velocity_verlet 10 3.0 0.001 0.003 44.866 44.867 rebuild_ks_matrix 107 8.3 0.000 0.001 31.582 31.644 qs_ks_build_kohn_sham_matrix 107 9.3 0.015 0.017 31.582 31.643 qs_ks_update_qs_env 107 7.6 0.001 0.001 27.818 27.878 sum_up_and_integrate 107 10.3 0.002 0.002 27.038 27.061 integrate_v_rspace 107 11.3 0.004 0.005 27.013 27.038 qs_rho_update_rho_low 107 7.7 0.001 0.001 26.363 26.371 calculate_rho_elec 107 8.7 0.028 0.029 26.362 26.371 grid_integrate_task_list 107 12.3 22.723 23.135 22.723 23.135 grid_collocate_task_list 107 9.7 21.907 22.269 21.907 22.269 dbcsr_multiply_generic 1966 12.4 0.066 0.072 14.623 14.776 qs_scf_new_mos 96 7.5 0.001 0.001 11.665 11.724 qs_scf_loop_do_ot 96 8.5 0.001 0.001 11.665 11.723 multiply_cannon 1966 13.4 0.129 0.148 10.916 11.333 ot_scf_mini 96 9.5 0.002 0.002 11.017 11.080 multiply_cannon_loop 1966 14.4 0.107 0.122 10.347 10.639 mp_waitall_1 136719 16.5 8.144 8.625 8.144 8.625 multiply_cannon_metrocomm3 15728 15.4 0.051 0.054 6.396 6.770 ot_mini 96 10.5 0.001 0.001 6.454 6.526 init_scf_loop 11 6.9 0.000 0.001 4.934 4.934 density_rs2pw 107 9.7 0.005 0.005 4.067 4.772 init_scf_run 11 5.9 0.000 0.006 4.106 4.107 scf_env_initial_rho_setup 11 6.9 0.000 0.004 4.106 4.107 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 3.895 3.904 multiply_cannon_multrec 15728 15.4 3.561 3.782 3.571 3.795 wfi_extrapolate 11 7.9 0.001 0.001 3.726 3.726 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 3.353 3.470 apply_single 107 13.6 0.000 0.000 3.353 3.470 potential_pw2rs 107 12.3 0.006 0.007 3.369 3.377 fft_wrap_pw1pw2 1081 11.6 0.016 0.018 3.312 3.364 ot_diis_step 96 11.5 0.003 0.003 3.261 3.262 qs_ot_get_derivative 96 11.5 0.001 0.001 3.170 3.232 transfer_rs2pw 439 10.6 0.006 0.006 2.461 3.150 fft_wrap_pw1pw2_140 439 12.2 0.139 0.142 2.838 2.913 mp_waitany 8968 13.7 1.939 2.668 1.939 2.668 make_m2s 3932 13.4 0.043 0.054 2.484 2.534 fft3d_ps 1081 13.6 1.199 1.250 2.435 2.501 transfer_pw2rs 439 13.2 0.006 0.007 2.495 2.498 make_images 3932 14.4 0.107 0.112 2.165 2.222 transfer_rs2pw_140 118 11.5 0.176 0.196 1.507 2.203 mp_alltoall_d11v 1998 13.7 1.218 1.836 1.218 1.836 qs_ot_get_p 107 10.4 0.001 0.001 1.580 1.669 ------------------------------------------------------------------------------- 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=47.54700000000001, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=28.645, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=24.639, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=5.404, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="make_dense_data", label="make_dense_data", y=4.705, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="dbcsr_copy_into_existing", label="dbcsr_copy_into_existing", y=3.341, 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=16.970000000000006, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=21.907, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=22.723, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=3.561, 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="dbcsr_copy_into_existing", label="dbcsr_copy_into_existing", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=8.144, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitany", label="mp_waitany", y=1.939, 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 0.225 0.225 138.204 138.204 qs_energies 1 2.0 0.000 0.000 137.348 137.348 scf_env_do_scf 1 3.0 0.000 0.000 136.110 136.110 qs_ks_update_qs_env 8 5.0 0.000 0.000 130.446 130.446 rebuild_ks_matrix 7 6.0 0.000 0.000 130.389 130.389 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.001 130.389 130.389 hfx_ks_matrix 7 8.0 0.000 0.000 121.625 121.625 integrate_four_center 7 9.0 1.631 1.631 121.549 121.549 integrate_four_center_main 7 10.0 0.665 0.665 107.134 107.134 integrate_four_center_bin 465 11.0 106.469 106.469 106.469 106.469 scf_env_do_scf_inner_loop 7 4.0 0.001 0.001 77.022 77.022 init_scf_loop 1 4.0 0.000 0.000 59.080 59.080 integrate_four_center_load 7 10.0 0.000 0.000 12.494 12.494 hfx_load_balance 1 11.0 0.007 0.007 12.494 12.494 hfx_load_balance_count 1 12.0 6.251 6.251 6.251 6.251 hfx_load_balance_bin 1 12.0 6.212 6.212 6.212 6.212 qs_vxc_create 14 8.0 0.000 0.000 3.330 3.330 xc_vxc_pw_create 14 9.0 0.122 0.122 3.330 3.330 calculate_rho_elec 15 7.4 0.119 0.119 2.934 2.934 ------------------------------------------------------------------------------- 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 0.206 0.236 135.073 135.086 qs_energies 1 2.0 0.000 0.000 134.647 134.657 scf_env_do_scf 1 3.0 0.000 0.000 134.263 134.264 qs_ks_update_qs_env 8 5.0 0.000 0.000 131.815 131.816 rebuild_ks_matrix 7 6.0 0.000 0.000 131.793 131.794 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.002 131.793 131.794 hfx_ks_matrix 7 8.0 0.000 0.000 125.654 125.657 integrate_four_center 7 9.0 0.060 0.348 125.644 125.646 integrate_four_center_main 7 10.0 0.003 0.003 105.602 112.322 integrate_four_center_bin 448 11.0 105.599 112.319 105.599 112.319 scf_env_do_scf_inner_loop 7 4.0 0.000 0.002 79.116 79.116 init_scf_loop 1 4.0 0.000 0.000 55.145 55.146 mp_sync 56 11.2 7.077 13.237 7.077 13.237 integrate_four_center_load 7 10.0 0.000 0.000 12.268 12.271 hfx_load_balance 1 11.0 0.001 0.001 12.268 12.271 hfx_load_balance_bin 1 12.0 6.071 6.143 6.071 6.143 hfx_load_balance_count 1 12.0 6.058 6.142 6.058 6.142 ------------------------------------------------------------------------------- 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=16.751000000000005, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_bin", label="integrate_four_center_bin", y=106.469, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_count", label="hfx_load_balance_count", y=6.251, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=6.212, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center", label="integrate_four_center", y=1.631, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_main", label="integrate_four_center_main", y=0.665, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="CP2K", label="CP2K", y=0.225, 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=9.998999999999995, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center_bin", label="integrate_four_center_bin", y=105.599, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_count", label="hfx_load_balance_count", y=6.058, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=6.071, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center", label="integrate_four_center", y=0.06, 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=0.206, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="mp_sync", label="mp_sync", y=7.077, 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 0.028 0.028 88.395 88.395 qs_energies 1 2.0 0.000 0.000 88.001 88.001 mp2_main 1 3.0 0.000 0.000 84.975 84.975 mp2_gpw_main 1 4.0 0.000 0.000 84.872 84.872 rpa_ri_compute_en 1 5.0 0.000 0.000 81.208 81.208 rpa_num_int 1 6.0 0.002 0.002 81.202 81.202 compute_mat_P_omega 1 7.0 0.004 0.004 71.916 71.916 compute_mat_P_omega_contract 10 8.0 9.005 9.005 71.714 71.714 dbt_total 2336 9.6 0.015 0.015 57.855 57.855 dbt_contract 787 11.0 0.042 0.042 50.363 50.363 dbt_tas_total 1149 12.2 0.257 0.257 48.901 48.901 dbt_tas_multiply 807 12.1 0.002 0.002 47.502 47.502 dbt_tas_dbm 807 14.1 0.003 0.003 40.815 40.815 dbm_multiply 807 16.1 40.807 40.807 40.807 40.807 dbt_tas_mm_1N 524 15.1 0.002 0.002 33.126 33.126 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 31.239 31.239 compute_mat_P_omega_calc_M_occ 250 9.0 8.993 8.993 18.274 18.274 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 7.138 7.138 dbt_tas_mm_2 251 15.0 0.001 0.001 6.188 6.188 dbt_copy 1103 10.7 0.119 0.119 6.073 6.073 compute_QP_energies 1 7.0 0.000 0.000 5.331 5.331 compute_self_energy_cubic_gw 1 8.0 0.053 0.053 5.329 5.329 contract_cubic_gw 21 9.0 0.000 0.000 4.163 4.163 dbt_tas_reserve_blocks_index 3261 14.3 0.492 0.492 4.132 4.132 dbm_reserve_blocks 3628 15.3 3.704 3.704 3.704 3.704 mp2_ri_gpw_compute_in 1 5.0 0.001 0.001 3.657 3.657 dbt_reserve_blocks_index 2280 13.1 0.066 0.066 3.140 3.140 dbt_reserve_blocks_index_array 2222 12.2 0.009 0.009 3.076 3.076 scf_env_do_scf 1 3.0 0.000 0.000 2.910 2.910 scf_env_do_scf_inner_loop 17 4.0 0.002 0.002 2.910 2.910 dbt_crop 1042 12.0 1.590 1.590 2.743 2.743 dbt_tas_copy 574 11.4 1.363 1.363 2.427 2.427 convert_to_new_pgrid 2421 14.1 0.105 0.105 2.206 2.206 dbt_tas_reshape 367 15.0 0.018 0.018 2.174 2.174 dbm_copy 1614 15.1 2.101 2.101 2.101 2.101 dbt_reshape 278 11.9 1.090 1.090 2.000 2.000 ------------------------------------------------------------------------------- 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 0.031 38.326 38.338 qs_energies 1 2.0 0.000 0.000 38.168 38.169 mp2_main 1 3.0 0.000 0.000 37.021 37.022 mp2_gpw_main 1 4.0 0.000 0.000 36.911 36.913 rpa_ri_compute_en 1 5.0 0.000 0.000 35.572 35.573 rpa_num_int 1 6.0 0.000 0.002 35.571 35.573 dbt_total 2336 9.6 0.016 0.017 31.216 31.309 compute_mat_P_omega 1 7.0 0.001 0.006 29.468 29.528 compute_mat_P_omega_contract 10 8.0 0.459 0.472 29.313 29.316 dbt_contract 787 11.0 0.041 0.042 22.469 22.481 dbt_tas_total 1149 12.2 0.086 0.094 19.861 19.899 dbt_tas_multiply 807 12.1 0.002 0.002 19.642 19.654 dbt_tas_dbm 807 14.1 0.003 0.004 14.244 14.264 dbm_multiply 807 16.1 11.441 12.221 11.441 12.221 compute_mat_P_omega_calc_M_occ 250 9.0 0.436 0.447 8.691 8.704 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 8.627 8.628 dbt_copy 1149 10.8 0.014 0.015 7.487 7.711 dbt_reshape 1136 11.8 2.856 3.032 6.729 6.988 dbt_tas_mm_2 251 15.0 0.001 0.002 6.798 6.811 mp_sync 8688 11.6 5.310 6.116 5.310 6.116 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 5.905 5.905 dbt_tas_mm_1N 524 15.1 0.001 0.002 5.158 5.523 compute_QP_energies 1 7.0 0.000 0.000 4.272 4.273 compute_self_energy_cubic_gw 1 8.0 0.003 0.003 4.271 4.272 mp_waitall_2 3812 15.3 2.748 2.953 2.748 2.953 dbt_communicate_buffer 1136 12.8 0.052 0.057 2.730 2.892 contract_cubic_gw 21 9.0 0.000 0.000 2.413 2.413 dbt_reserve_blocks_index 2887 13.1 0.077 0.084 2.048 2.229 dbt_reserve_blocks_index_array 2829 12.2 0.009 0.010 2.039 2.221 dbt_tas_reserve_blocks_index 3347 14.5 0.435 0.468 2.026 2.203 dbm_reserve_blocks 3752 15.4 1.693 1.847 1.693 1.847 dbt_crop 1042 12.0 1.001 1.103 1.644 1.798 mp2_ri_gpw_compute_in 1 5.0 0.003 0.004 1.337 1.338 dbt_tas_replicate 405 14.1 0.558 0.734 1.174 1.231 parallel_gemm_fm 105 8.4 0.000 0.000 1.187 1.209 parallel_gemm_fm_cosma 105 9.4 1.186 1.209 1.186 1.209 compute_mat_P_omega_copy_M_vir 250 9.0 0.001 0.001 1.178 1.186 compute_mat_P_omega_copy_M_occ 250 9.0 0.001 0.001 1.147 1.158 scf_env_do_scf 1 3.0 0.000 0.000 1.094 1.094 scf_env_do_scf_inner_loop 17 4.0 0.000 0.003 1.094 1.094 convert_to_new_pgrid 2421 14.1 0.028 0.033 0.946 1.005 mp_max_i 2009 9.8 0.810 0.995 0.810 0.995 dbm_copy 1608 15.1 0.912 0.973 0.912 0.973 compute_W_cubic_GW 10 7.0 0.001 0.001 0.823 0.832 mp_sum_l 6165 12.9 0.738 0.785 0.738 0.785 ------------------------------------------------------------------------------- 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=22.69499999999998, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=40.807, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=9.005, 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=8.993, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=3.704, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_copy", label="dbm_copy", y=2.101, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=1.09, 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=12.471, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=11.441, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=0.459, 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=0.436, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=1.693, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_copy", label="dbm_copy", y=0.912, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=2.856, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.748, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_sync", label="mp_sync", y=5.31, 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 0.024 0.024 255.936 255.936 qs_forces 1 2.0 0.000 0.000 255.397 255.397 rebuild_ks_matrix 7 6.6 0.000 0.000 253.849 253.849 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.001 253.849 253.849 hfx_ks_matrix 7 8.6 0.000 0.000 251.765 251.765 hfx_ri_update_ks 7 9.6 0.000 0.000 211.159 211.159 hfx_ri_update_ks_Pmat 7 10.6 32.190 32.190 211.156 211.156 dbt_total 849 11.0 0.006 0.006 196.650 196.650 qs_energies 1 3.0 0.000 0.000 187.765 187.765 scf_env_do_scf 1 4.0 0.001 0.001 187.439 187.439 qs_ks_update_qs_env 8 6.0 0.000 0.000 186.270 186.270 dbt_contract 207 12.4 0.069 0.069 176.551 176.551 dbt_tas_total 369 13.4 1.538 1.538 175.375 175.375 dbt_tas_multiply 216 13.5 0.001 0.001 171.241 171.241 dbt_tas_dbm 216 15.5 0.001 0.001 160.217 160.217 dbm_multiply 216 17.5 160.214 160.214 160.214 160.214 hfx_ri_update_ks_Pmat_KS 63 11.6 0.001 0.001 154.399 154.399 dbt_tas_mm_2 91 16.5 0.001 0.001 146.161 146.161 scf_env_do_scf_inner_loop 6 5.0 0.001 0.001 116.186 116.186 init_scf_loop 2 5.0 0.000 0.000 71.250 71.250 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 67.582 67.582 hfx_ri_update_forces 1 7.0 1.564 1.564 40.603 40.603 hfx_ri_forces_Pmat_3c 1 8.0 4.651 4.651 23.262 23.262 dbt_copy 423 11.8 0.071 0.071 15.956 15.956 precalc_derivatives 1 8.0 2.236 2.236 13.590 13.590 dbt_reshape 132 13.2 6.683 6.683 10.856 10.856 dbt_tas_mm_3T 77 17.1 0.000 0.000 9.748 9.748 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 9.243 9.243 dbt_tas_reserve_blocks_index 1323 15.4 1.075 1.075 8.102 8.102 build_3c_derivatives 3 9.0 3.239 3.239 7.603 7.603 dbm_reserve_blocks 1491 16.2 7.256 7.256 7.256 7.256 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 7.088 7.088 dbt_reserve_blocks_index 846 14.4 0.098 0.098 6.254 6.254 dbt_reserve_blocks_index_array 816 13.5 0.007 0.007 6.133 6.133 ------------------------------------------------------------------------------- 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 0.008 0.037 50.643 50.654 qs_forces 1 2.0 0.000 0.000 50.441 50.441 rebuild_ks_matrix 7 6.6 0.000 0.000 49.632 49.633 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.002 49.632 49.633 hfx_ks_matrix 7 8.6 0.000 0.000 48.583 48.590 dbt_total 849 11.0 0.006 0.006 43.352 43.362 dbt_contract 207 12.4 0.026 0.026 33.454 33.462 dbt_tas_total 369 13.4 0.064 0.159 29.810 29.821 dbt_tas_multiply 216 13.5 0.001 0.001 29.312 29.313 hfx_ri_update_ks 7 9.6 0.000 0.000 28.908 28.909 hfx_ri_update_ks_Pmat 7 10.6 1.305 1.371 28.904 28.905 qs_energies 1 3.0 0.000 0.000 27.067 27.068 scf_env_do_scf 1 4.0 0.000 0.001 26.906 26.906 qs_ks_update_qs_env 8 6.0 0.000 0.000 26.270 26.271 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 23.364 23.364 dbt_tas_dbm 216 15.5 0.001 0.001 22.439 22.453 dbm_multiply 216 17.5 20.170 20.663 20.170 20.663 hfx_ri_update_forces 1 7.0 0.060 0.064 19.673 19.680 scf_env_do_scf_inner_loop 6 5.0 0.000 0.001 14.926 14.926 hfx_ri_forces_Pmat_3c 1 8.0 0.161 0.171 14.669 14.678 hfx_ri_update_ks_Pmat_KS 63 11.6 0.000 0.001 13.174 13.175 init_scf_loop 2 5.0 0.000 0.000 11.979 11.979 dbt_tas_mm_2 91 16.5 0.001 0.001 10.206 10.208 dbt_copy 539 12.5 0.012 0.014 8.927 9.105 dbt_reshape 393 13.9 3.604 3.683 6.857 7.021 dbt_tas_mm_3T 77 17.1 0.000 0.000 6.119 6.506 mp_sync 2901 12.8 4.731 5.501 4.731 5.501 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 5.241 5.241 dbt_tas_mm_3N 37 15.4 0.000 0.000 4.477 4.657 precalc_derivatives 1 8.0 0.088 0.094 3.740 3.740 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 3.689 3.695 dbt_tas_reserve_blocks_index 1471 15.8 0.889 0.915 3.310 3.528 mp_waitall_2 1318 16.2 3.027 3.104 3.027 3.104 dbt_reserve_blocks_index 1107 14.8 0.114 0.126 2.737 2.937 dbt_reserve_blocks_index_array 1077 13.9 0.005 0.006 2.708 2.908 dbm_reserve_blocks 1641 16.6 2.634 2.887 2.634 2.887 dbt_crop 372 13.7 1.777 1.813 2.595 2.674 dbt_communicate_buffer 393 14.9 0.013 0.013 2.093 2.188 build_3c_derivatives 3 9.0 0.223 0.254 2.084 2.090 hfx_ri_pre_scf_Pmat_RIx3C 9 13.0 0.000 0.000 1.941 1.944 dbt_tas_replicate 170 15.1 0.671 0.697 1.722 1.761 hfx_ri_update_ks_Pmat_copy_2 63 11.6 0.000 0.002 1.727 1.733 convert_to_new_pgrid 648 15.5 0.039 0.070 1.423 1.660 dbm_copy 452 16.3 1.236 1.468 1.236 1.468 dbt_tas_copy 146 12.6 0.703 0.729 1.333 1.429 dbt_tas_communicate_buffer 370 16.3 0.012 0.013 1.063 1.114 mp_sum_l 6385 13.7 0.964 1.072 0.964 1.072 ------------------------------------------------------------------------------- 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=44.94200000000001, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=160.214, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=32.19, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=7.256, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=6.683, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_forces_Pmat_3c", label="hfx_ri_forces_Pmat_3c", y=4.651, 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=15.010999999999996, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=20.17, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=1.305, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=2.634, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=3.604, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_forces_Pmat_3c", label="hfx_ri_forces_Pmat_3c", y=0.161, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_sync", label="mp_sync", y=4.731, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=3.027, 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 0.016 0.016 188.614 188.614 qs_energies 1 2.0 0.000 0.000 188.431 188.431 mp2_main 1 3.0 0.000 0.000 183.878 183.878 mp2_gpw_main 1 4.0 0.001 0.001 183.485 183.485 mp2_ri_gpw_compute_in 1 5.0 0.391 0.391 138.331 138.331 mp2_ri_gpw_compute_in_loop 1 6.0 0.009 0.009 129.093 129.093 mp2_eri_3c_integrate_gpw 2656 7.0 0.013 0.013 101.669 101.669 integrate_v_rspace 2666 8.0 0.630 0.630 88.034 88.034 grid_integrate_task_list 2666 9.0 85.190 85.190 85.190 85.190 mp2_ri_gpw_compute_en 1 5.0 0.086 0.086 45.133 45.133 mp2_ri_gpw_compute_en_RI_loop 1 6.0 9.861 9.861 43.253 43.253 mp2_ri_gpw_compute_en_expansio 2080 7.0 2.024 2.024 26.487 26.487 local_gemm 2080 8.0 24.463 24.463 24.463 24.463 dbcsr_multiply_generic 5322 8.0 0.162 0.162 21.171 21.171 ao_to_mo_and_store_B_mult_1 2656 7.0 0.009 0.009 21.149 21.149 fft_wrap_pw1pw2 53228 10.4 0.108 0.108 12.718 12.718 calculate_wavefunction 2656 8.0 7.892 7.892 12.204 12.204 multiply_cannon 5322 9.0 0.440 0.440 10.772 10.772 multiply_cannon_loop 5322 10.0 0.195 0.195 9.436 9.436 fft_wrap_pw1pw2_20 21271 11.4 1.035 1.035 9.191 9.191 get_2c_integrals 1 6.0 0.000 0.000 8.846 8.846 compute_2c_integrals 1 7.0 0.005 0.005 8.290 8.290 compute_2c_integrals_loop_lm 1 8.0 0.009 0.009 8.279 8.279 mp2_eri_2c_integrate_gpw 1 9.0 0.864 0.864 8.269 8.269 make_m2s 10644 9.0 0.061 0.061 8.198 8.198 make_images 10644 10.0 3.086 3.086 7.873 7.873 multiply_cannon_multrec 5322 11.0 7.806 7.806 7.845 7.845 fft3d_s 53229 12.4 7.065 7.065 7.101 7.101 ao_to_mo_and_store_B_E_Ex_1 2656 7.0 2.252 2.252 6.159 6.159 mp2_ri_gpw_compute_en_ener 2080 7.0 5.123 5.123 5.123 5.123 potential_pw2rs 5322 10.0 0.145 0.145 4.375 4.375 copy_dbcsr_to_fm 2679 8.0 0.026 0.026 4.363 4.363 scf_env_do_scf 1 3.0 0.000 0.000 4.155 4.155 scf_env_do_scf_inner_loop 10 4.0 0.001 0.001 4.155 4.155 ------------------------------------------------------------------------------- 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 0.043 36.132 36.150 qs_energies 1 2.0 0.000 0.000 35.977 35.978 mp2_main 1 3.0 0.000 0.001 33.935 33.935 mp2_gpw_main 1 4.0 0.001 0.002 33.831 33.831 mp2_ri_gpw_compute_in 1 5.0 0.044 0.045 17.192 17.633 mp2_ri_gpw_compute_en 1 5.0 0.297 0.305 16.573 16.850 mp2_ri_gpw_compute_in_loop 1 6.0 0.001 0.001 15.927 16.363 mp2_ri_gpw_compute_en_RI_loop 1 6.0 2.164 2.522 15.240 15.250 mp2_eri_3c_integrate_gpw 83 7.0 0.001 0.001 13.776 14.248 integrate_v_rspace 93 8.1 0.102 0.110 13.631 14.098 grid_integrate_task_list 93 9.1 13.333 13.805 13.333 13.805 mp2_ri_gpw_compute_en_expansio 65 7.0 0.091 0.108 10.386 10.604 local_gemm 65 8.0 10.295 10.497 10.295 10.497 mp2_ri_gpw_compute_en_comm 17 7.0 0.078 0.121 2.390 3.016 mp_sendrecv_dm3 1054 8.0 1.900 2.699 1.900 2.699 dbcsr_multiply_generic 176 8.0 0.008 0.008 1.838 2.067 ao_to_mo_and_store_B_mult_1 83 7.0 0.001 0.001 1.821 2.044 scf_env_do_scf 1 3.0 0.000 0.001 1.899 1.900 scf_env_do_scf_inner_loop 10 4.0 0.000 0.002 1.899 1.899 get_2c_integrals 1 6.0 0.005 0.014 1.207 1.222 multiply_cannon 176 9.0 0.017 0.018 1.146 1.207 multiply_cannon_loop 176 10.0 0.002 0.002 1.089 1.151 multiply_cannon_multrec 246 11.0 0.959 1.005 0.964 1.009 qs_scf_new_mos 10 5.0 0.000 0.000 0.934 0.944 compute_2c_integrals 1 7.0 0.002 0.003 0.878 0.884 eigensolver 11 5.8 0.001 0.001 0.870 0.873 make_m2s 352 9.0 0.003 0.003 0.657 0.822 compute_2c_integrals_loop_lm 1 8.0 0.001 0.002 0.781 0.812 mp2_eri_2c_integrate_gpw 1 9.0 0.199 0.208 0.780 0.812 make_images 352 10.0 0.050 0.052 0.645 0.809 ------------------------------------------------------------------------------- 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=53.402000000000015, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=85.19, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="local_gemm", label="local_gemm", y=24.463, 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=9.861, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="calculate_wavefunction", label="calculate_wavefunction", y=7.892, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=7.806, 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=7.480999999999998, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.333, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="local_gemm", label="local_gemm", y=10.295, 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=2.164, 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=0.959, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="mp_sendrecv_dm3", label="mp_sendrecv_dm3", y=1.9, 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 0.098 0.098 128.495 128.495 qs_energies 1 2.0 0.000 0.000 127.168 127.168 scf_env_do_scf 1 3.0 0.000 0.000 119.860 119.860 scf_env_do_scf_inner_loop 15 4.0 0.002 0.002 119.860 119.860 qs_ks_update_qs_env 15 5.0 0.000 0.000 53.718 53.718 rebuild_ks_matrix 15 6.0 0.000 0.000 53.508 53.508 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.002 53.508 53.508 qs_scf_new_mos 15 5.0 0.000 0.000 42.792 42.792 qs_vxc_create 15 8.0 0.032 0.032 38.207 38.207 eigensolver 15 6.0 0.002 0.002 35.241 35.241 calculate_dispersion_nonloc 15 9.0 6.973 6.973 33.627 33.627 fft_wrap_pw1pw2 1086 10.0 0.015 0.015 27.534 27.534 cp_fm_diag_elpa 15 7.0 0.000 0.000 22.469 22.469 cp_fm_diag_elpa_base 15 8.0 19.967 19.967 22.468 22.468 fft_wrap_pw1pw2_150 765 11.0 6.703 6.703 21.004 21.004 qs_rho_update_rho_low 16 5.0 0.000 0.000 20.037 20.037 calculate_rho_elec 16 6.0 0.240 0.240 20.037 20.037 grid_collocate_task_list 16 7.0 18.565 18.565 18.565 18.565 sum_up_and_integrate 15 8.0 0.000 0.000 14.202 14.202 integrate_v_rspace 15 9.0 0.019 0.019 14.190 14.190 grid_integrate_task_list 15 10.0 13.602 13.602 13.602 13.602 fft3d_s 1087 12.0 11.079 11.079 11.087 11.087 cp_fm_cholesky_restore 45 7.0 10.500 10.500 10.500 10.500 pw_scatter_s 585 12.1 6.759 6.759 6.759 6.759 fft_wrap_pw1pw2_200 197 11.3 1.091 1.091 6.323 6.323 copy_dbcsr_to_fm 16 5.9 0.001 0.001 5.331 5.331 dbcsr_complete_redistribute 46 8.3 1.989 1.989 5.237 5.237 cp_fm_upper_to_full 30 8.0 4.772 4.772 4.772 4.772 xc_vxc_pw_create 15 9.0 0.211 0.211 4.548 4.548 gspace_mixing 14 5.0 0.171 0.171 4.417 4.417 vdW_energy 15 10.0 4.353 4.353 4.353 4.353 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 4.198 4.198 broyden_mixing 14 6.0 3.831 3.831 3.831 3.831 xc_pw_derive 90 11.0 0.001 0.001 3.155 3.155 build_core_hamiltonian_matrix 1 4.0 0.000 0.000 2.979 2.979 init_scf_run 1 3.0 0.000 0.000 2.651 2.651 ------------------------------------------------------------------------------- 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 0.032 61.346 61.359 qs_energies 1 2.0 0.000 0.000 61.023 61.031 scf_env_do_scf 1 3.0 0.000 0.001 56.869 56.869 scf_env_do_scf_inner_loop 15 4.0 0.001 0.003 56.869 56.869 qs_ks_update_qs_env 15 5.0 0.000 0.000 24.294 24.324 rebuild_ks_matrix 15 6.0 0.000 0.000 24.257 24.287 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.003 24.257 24.287 qs_rho_update_rho_low 16 5.0 0.000 0.000 19.545 19.549 calculate_rho_elec 16 6.0 0.007 0.007 19.544 19.549 grid_collocate_task_list 16 7.0 17.444 17.848 17.444 17.848 sum_up_and_integrate 15 8.0 0.000 0.001 14.722 14.788 integrate_v_rspace 15 9.0 0.001 0.001 14.714 14.783 qs_scf_new_mos 15 5.0 0.000 0.000 13.558 13.834 grid_integrate_task_list 15 10.0 13.149 13.444 13.149 13.444 eigensolver 15 6.0 0.001 0.002 12.560 12.597 qs_vxc_create 15 8.0 0.001 0.001 9.155 9.160 cp_fm_diag_elpa 15 7.0 0.000 0.000 8.725 8.731 cp_fm_diag_elpa_base 15 8.0 8.595 8.632 8.721 8.722 calculate_dispersion_nonloc 15 9.0 0.902 0.920 7.331 7.361 fft_wrap_pw1pw2 1086 10.0 0.016 0.021 6.812 6.936 fft3d_ps 1086 12.0 2.410 2.766 5.132 5.474 fft_wrap_pw1pw2_150 765 11.0 0.103 0.136 4.387 4.419 cp_fm_cholesky_restore 45 7.0 3.689 3.769 3.689 3.769 mp_alltoall_z22v 1086 14.0 2.201 3.052 2.201 3.052 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 2.665 2.665 build_core_hamiltonian_matrix 1 4.0 0.000 0.000 2.369 2.570 fft_wrap_pw1pw2_200 197 11.3 0.080 0.100 2.296 2.397 density_rs2pw 16 7.0 0.001 0.001 1.959 2.205 transfer_rs2pw 82 8.0 0.001 0.001 1.725 2.041 mp_waitany 520 11.3 1.563 2.025 1.563 2.025 xc_vxc_pw_create 15 9.0 0.014 0.019 1.822 1.852 x_to_yz 585 13.1 0.301 0.321 1.378 1.750 yz_to_x 501 12.9 0.200 0.258 1.323 1.729 transfer_rs2pw_200 18 8.8 0.026 0.031 1.150 1.622 build_core_ppnl 1 5.0 1.477 1.598 1.477 1.598 mp_alltoall_d11v 217 9.2 1.310 1.509 1.310 1.509 vdW_energy 15 10.0 1.267 1.324 1.267 1.324 xc_pw_derive 90 11.0 0.001 0.002 1.220 1.291 init_scf_run 1 3.0 0.000 0.001 1.261 1.262 rs_gather_matrices 15 10.0 0.019 0.023 1.057 1.240 ------------------------------------------------------------------------------- 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=54.78200000000001, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=19.967, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=18.565, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.602, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="fft3d_s", label="fft3d_s", y=11.079, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=10.5, 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=16.05899999999999, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=8.595, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=17.444, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.149, 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="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=3.689, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=2.41, 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 0.079 0.079 309.319 309.319 qs_energies 1 2.0 0.000 0.000 309.178 309.178 ls_scf 1 3.0 0.000 0.000 307.907 307.907 ls_scf_main 1 4.0 0.002 0.002 298.718 298.718 density_matrix_trs4 11 5.0 0.013 0.013 204.514 204.514 arnoldi_extremal 12 6.1 0.000 0.000 118.659 118.659 arnoldi_normal_ev 12 7.1 0.032 0.032 118.659 118.659 dbcsr_matrix_vector_mult 652 9.0 0.198 0.198 116.797 116.797 build_subspace 23 8.1 0.074 0.074 116.410 116.410 dbcsr_matrix_vector_mult_local 652 10.0 115.183 115.183 115.192 115.192 ls_scf_dm_to_ks 11 5.0 0.000 0.000 88.896 88.896 matrix_ls_to_qs 11 6.0 0.000 0.000 85.605 85.605 dbcsr_multiply_generic 185 6.1 0.869 0.869 74.577 74.577 dbcsr_copy_into_existing 11 7.0 46.620 46.620 46.620 46.620 multiply_cannon 185 7.1 0.379 0.379 45.122 45.122 dbcsr_complete_redistribute 23 7.5 31.308 31.308 42.758 42.758 matrix_decluster 11 7.0 0.000 0.000 38.983 38.983 multiply_cannon_loop 185 8.1 0.245 0.245 32.668 32.668 make_m2s 370 7.1 0.038 0.038 24.941 24.941 make_images 370 8.1 10.781 10.781 23.300 23.300 multiply_cannon_multrec 185 9.1 23.162 23.162 23.189 23.189 dbcsr_finalize 646 7.5 0.275 0.275 15.163 15.163 dbcsr_merge_all 597 8.5 2.259 2.259 13.969 13.969 setup_rec_index_2d 370 8.1 11.939 11.939 11.939 11.939 tree_to_linear_d 110 9.4 10.429 10.429 10.429 10.429 dbcsr_sort_indices 1103 9.9 10.243 10.243 10.243 10.243 calculate_norms 370 9.1 9.234 9.234 9.234 9.234 quick_finalize 395 10.0 0.356 0.356 8.834 8.834 ls_scf_init_scf 1 4.0 0.000 0.000 8.494 8.494 dbcsr_special_finalize 370 9.1 0.002 0.002 8.162 8.162 ls_scf_init_matrix_S 1 5.0 0.000 0.000 8.159 8.159 matrix_sqrt_Newton_Schulz 1 6.0 0.001 0.001 7.497 7.497 ------------------------------------------------------------------------------- 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 0.016 0.039 68.466 68.484 qs_energies 1 2.0 0.000 0.000 68.340 68.341 ls_scf 1 3.0 0.000 0.000 68.289 68.290 ls_scf_main 1 4.0 0.000 0.007 65.681 65.682 density_matrix_trs4 11 5.0 0.006 0.018 63.146 63.219 dbcsr_multiply_generic 185 6.1 0.058 0.075 59.827 60.076 multiply_cannon 185 7.1 0.033 0.037 49.307 50.088 multiply_cannon_loop 185 8.1 0.106 0.121 46.970 47.815 multiply_cannon_multrec 1480 9.1 28.551 31.346 28.795 31.588 mp_waitall_1 11936 10.3 16.328 19.653 16.328 19.653 multiply_cannon_metrocomm3 1480 9.1 0.013 0.016 12.279 16.142 make_m2s 370 7.1 0.034 0.037 6.880 6.940 make_images 370 8.1 0.626 0.657 6.749 6.808 calculate_norms 2960 9.1 4.586 5.301 4.586 5.301 mp_sum_l 1199 5.3 2.803 3.851 2.803 3.851 make_images_data 370 9.1 0.009 0.014 3.122 3.356 multiply_cannon_metrocomm1 1480 9.1 0.006 0.007 1.171 3.300 hybrid_alltoall_any 393 9.9 0.199 0.964 2.669 3.057 dbcsr_multiply_generic_mpsum_f 137 7.1 0.000 0.000 1.971 2.894 arnoldi_extremal 12 6.1 0.000 0.001 2.589 2.602 arnoldi_normal_ev 12 7.1 0.001 0.007 2.588 2.601 build_subspace 23 8.1 0.018 0.021 2.490 2.492 ls_scf_dm_to_ks 11 5.0 0.000 0.000 2.189 2.283 dbcsr_matrix_vector_mult 652 9.0 0.013 0.047 2.040 2.111 dbcsr_complete_redistribute 23 7.5 1.190 1.241 1.965 2.077 matrix_ls_to_qs 11 6.0 0.000 0.000 1.904 2.022 ls_scf_init_scf 1 4.0 0.000 0.000 1.990 1.991 ls_scf_init_matrix_S 1 5.0 0.000 0.000 1.963 1.970 matrix_decluster 11 7.0 0.000 0.000 1.765 1.880 make_images_pack 370 9.1 1.635 1.858 1.638 1.862 matrix_sqrt_Newton_Schulz 1 6.0 0.000 0.002 1.784 1.786 dbcsr_matrix_vector_mult_local 652 10.0 1.603 1.676 1.605 1.677 buffer_matrices_ensure_size 370 8.1 1.279 1.525 1.279 1.525 ------------------------------------------------------------------------------- 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=71.87300000000002, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=115.183, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_copy_into_existing", label="dbcsr_copy_into_existing", y=46.62, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_complete_redistribute", label="dbcsr_complete_redistribute", y=31.308, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=23.162, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="setup_rec_index_2d", label="setup_rec_index_2d", y=11.939, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="calculate_norms", label="calculate_norms", y=9.234, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="make_images_pack", label="make_images_pack", y=0.0, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="mp_sum_l", label="mp_sum_l", y=0.0, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 Plot: name="bench_dftb_timings_32mpi", title="Timings of bench_dftb with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="bench_dftb_timings_32mpi", name="rest", label="rest", y=11.769999999999996, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=1.603, 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=1.19, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=28.551, 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=4.586, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="make_images_pack", label="make_images_pack", y=1.635, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=2.803, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=16.328, 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 0.016 0.016 75.016 75.016 lib_test 1 2.0 0.000 0.000 74.999 74.999 dbcsr_run_tests 3 3.0 0.002 0.002 74.999 74.999 test_multiplies_multiproc 3 4.0 0.001 0.001 58.439 58.439 dbcsr_redistribute 9 5.0 38.090 38.090 40.027 40.027 dbcsr_multiply_generic 9 5.0 0.001 0.001 17.019 17.019 dbcsr_make_random_matrix 9 4.0 13.242 13.242 16.447 16.447 multiply_cannon 9 6.0 0.002 0.002 11.913 11.913 multiply_cannon_loop 9 7.0 0.045 0.045 11.548 11.548 multiply_cannon_multrec 9 8.0 11.503 11.503 11.503 11.503 dbcsr_finalize 27 5.7 0.042 0.042 5.911 5.911 dbcsr_merge_all 18 6.5 2.140 2.140 5.172 5.172 dbcsr_data_release 975 7.6 2.769 2.769 2.769 2.769 tree_to_linear_d 9 7.0 1.999 1.999 1.999 1.999 make_m2s 18 6.0 0.001 0.001 1.769 1.769 make_images 18 7.0 0.636 0.636 1.719 1.719 mp_alltoall_d11v 27 6.0 1.558 1.558 1.558 1.558 ------------------------------------------------------------------------------- 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 0.005 0.022 20.016 20.023 lib_test 1 2.0 0.000 0.000 19.487 19.504 dbcsr_run_tests 3 3.0 0.000 0.001 19.480 19.498 test_multiplies_multiproc 3 4.0 0.000 0.003 18.638 18.708 dbcsr_multiply_generic 9 5.0 0.001 0.001 17.175 17.266 multiply_cannon 9 6.0 0.002 0.002 15.052 15.578 multiply_cannon_loop 9 7.0 0.002 0.002 14.766 15.214 multiply_cannon_multrec 72 8.0 11.148 11.990 11.149 11.990 mp_waitall_1 576 9.2 3.966 4.906 3.966 4.906 multiply_cannon_metrocomm1 72 8.0 0.001 0.001 3.510 4.507 mp_sum_l 470 2.5 1.125 1.695 1.125 1.695 dbcsr_multiply_generic_mpsum_f 9 6.0 0.000 0.000 0.896 1.453 dbcsr_make_random_matrix 9 4.0 0.669 0.709 0.806 0.852 make_m2s 18 6.0 0.001 0.001 0.727 0.773 make_images 18 7.0 0.021 0.022 0.723 0.770 dbcsr_data_release 444 7.6 0.593 0.689 0.593 0.689 dbcsr_destroy 111 5.9 0.002 0.053 0.532 0.624 dbcsr_redistribute 9 5.0 0.244 0.292 0.564 0.607 dbcsr_finalize 27 5.7 0.000 0.000 0.508 0.603 dbcsr_merge_all 18 6.5 0.079 0.100 0.444 0.526 make_images_data 18 8.0 0.001 0.001 0.392 0.460 ------------------------------------------------------------------------------- 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=7.271999999999991, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_redistribute", label="dbcsr_redistribute", y=38.09, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=13.242, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=11.503, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_data_release", label="dbcsr_data_release", y=2.769, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_merge_all", label="dbcsr_merge_all", y=2.14, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="mp_sum_l", label="mp_sum_l", y=0.0, yerr=0.0 Plot: name="dbcsr_timings_32mpi", title="Timings of dbcsr with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="dbcsr_timings_32mpi", name="rest", label="rest", y=2.1919999999999966, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_redistribute", label="dbcsr_redistribute", y=0.244, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=0.669, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=11.148, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_data_release", label="dbcsr_data_release", y=0.593, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_merge_all", label="dbcsr_merge_all", y=0.079, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=3.966, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=1.125, 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 0.056 0.056 135.010 135.010 qs_mol_dyn_low 1 2.0 0.004 0.004 133.506 133.506 velocity_verlet 5 3.0 0.003 0.003 108.817 108.817 qmmm_el_coupling 6 3.8 0.000 0.000 87.900 87.900 qmmm_elec_with_gaussian 6 4.8 0.013 0.013 87.896 87.896 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 87.269 87.269 qmmm_elec_gaussian_low_G 6 6.8 86.363 86.363 86.363 86.363 qs_forces 6 3.8 0.001 0.001 37.102 37.102 qs_energies 6 4.8 0.000 0.000 33.116 33.116 scf_env_do_scf 6 5.8 0.001 0.001 30.632 30.632 scf_env_do_scf_inner_loop 39 6.8 0.004 0.004 26.549 26.549 rebuild_ks_matrix 45 8.4 0.000 0.000 25.139 25.139 qs_ks_build_kohn_sham_matrix 45 9.4 0.005 0.005 25.139 25.139 qs_ks_update_qs_env 45 7.8 0.000 0.000 21.577 21.577 fft_wrap_pw1pw2 801 12.6 0.010 0.010 20.779 20.779 fft_wrap_pw1pw2_150 507 14.2 5.304 5.304 20.265 20.265 qs_vxc_create 45 10.4 0.001 0.001 15.351 15.351 xc_vxc_pw_create 45 11.4 0.638 0.638 15.350 15.350 xc_pw_derive 270 13.4 0.002 0.002 11.422 11.422 fft3d_s 802 14.6 8.187 8.187 8.236 8.236 xc_pw_divergence 45 12.4 0.001 0.001 7.894 7.894 qs_rho_update_rho_low 45 7.9 0.000 0.000 7.809 7.809 calculate_rho_elec 45 8.9 0.563 0.563 7.809 7.809 xc_rho_set_and_dset_create 45 12.4 0.615 0.615 6.756 6.756 pw_scatter_s 429 14.8 5.600 5.600 5.600 5.600 qmmm_forces 6 3.8 0.002 0.002 5.326 5.326 qmmm_forces_with_gaussian 6 4.8 0.018 0.018 5.001 5.001 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 4.270 4.270 init_scf_loop 6 6.8 0.000 0.000 3.990 3.990 sum_up_and_integrate 45 10.4 0.001 0.001 3.978 3.978 density_rs2pw 45 9.9 0.002 0.002 3.914 3.914 integrate_v_rspace 45 11.4 0.017 0.017 3.868 3.868 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 3.570 3.570 qs_ks_ddapc 45 10.4 0.001 0.001 3.547 3.547 qmmm_forces_gaussian_low_G 6 6.8 3.544 3.544 3.544 3.544 grid_collocate_task_list 45 9.9 3.332 3.332 3.332 3.332 pw_integral_ab 2539 7.4 2.839 2.839 2.839 2.839 ------------------------------------------------------------------------------- From /workspace/artifacts/MQAE_single_node_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.035 0.060 57.868 57.886 qs_mol_dyn_low 1 2.0 0.003 0.005 56.749 56.811 qs_forces 6 3.8 0.001 0.001 42.027 42.028 qs_energies 6 4.8 0.000 0.000 40.143 40.143 scf_env_do_scf 6 5.8 0.000 0.001 39.130 39.131 scf_env_do_scf_inner_loop 113 6.2 0.003 0.021 37.084 37.086 rebuild_ks_matrix 119 8.1 0.000 0.000 27.326 27.337 qs_ks_build_kohn_sham_matrix 119 9.1 0.014 0.016 27.325 27.336 qs_ks_update_qs_env 119 7.3 0.001 0.001 25.734 25.742 velocity_verlet 5 3.0 0.002 0.004 23.907 23.910 fft_wrap_pw1pw2 2059 12.4 0.032 0.038 17.239 17.782 fft_wrap_pw1pw2_150 1321 13.9 0.575 0.699 16.478 16.960 fft3d_ps 2059 14.4 6.681 7.877 12.974 14.141 qs_vxc_create 119 10.1 0.002 0.003 13.822 13.831 xc_vxc_pw_create 119 11.1 0.148 0.221 13.820 13.829 xc_pw_derive 714 13.1 0.009 0.012 10.391 10.699 qs_rho_update_rho_low 119 7.3 0.001 0.001 10.640 10.642 calculate_rho_elec 119 8.3 0.049 0.055 10.640 10.641 sum_up_and_integrate 119 10.1 0.002 0.002 9.340 9.399 integrate_v_rspace 119 11.1 0.004 0.004 9.284 9.357 qmmm_forces 6 3.8 0.002 0.003 7.439 7.439 qmmm_forces_with_gaussian 6 4.8 0.006 0.007 6.983 7.272 xc_pw_divergence 119 12.1 0.004 0.005 6.792 7.068 xc_rho_set_and_dset_create 119 12.1 0.359 0.472 6.637 6.857 mp_alltoall_z22v 2059 16.4 4.883 6.747 4.883 6.747 qmmm_el_coupling 6 3.8 0.000 0.000 6.302 6.514 qmmm_elec_with_gaussian 6 4.8 0.003 0.004 6.301 6.512 density_rs2pw 119 9.3 0.005 0.006 6.077 6.382 potential_pw2rs 119 12.1 0.006 0.007 5.570 5.607 grid_collocate_task_list 119 9.3 4.370 4.634 4.370 4.634 yz_to_x 964 15.0 0.612 0.758 2.931 4.086 x_to_yz 1095 15.8 0.754 0.872 3.317 4.060 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 3.834 3.889 transfer_pw2rs 500 12.8 0.005 0.007 3.859 3.876 mp_waitany 4028 12.8 2.866 3.753 2.866 3.753 grid_integrate_task_list 119 12.1 3.393 3.621 3.393 3.621 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 3.379 3.494 transfer_rs2pw 488 10.2 0.007 0.009 2.992 3.337 qmmm_forces_gaussian_low_G 6 6.8 3.152 3.202 3.152 3.202 qmmm_elec_gaussian_low_G 6 6.8 2.786 2.908 2.786 2.908 pw_restrict_s3 18 5.8 1.417 1.514 2.578 2.855 qs_scf_new_mos 113 7.2 0.000 0.001 2.656 2.662 qs_scf_loop_do_ot 113 8.2 0.000 0.001 2.655 2.661 transfer_pw2rs_150 125 13.9 0.747 1.001 2.544 2.646 ot_scf_mini 113 9.2 0.001 0.001 2.571 2.577 transfer_rs2pw_150 125 11.2 0.602 0.838 2.063 2.414 qmmm_elec_with_gaussian:spline 6 5.8 0.000 0.000 2.119 2.330 pw_prolongate_s3 18 6.8 1.185 1.255 2.119 2.330 qs_ks_ddapc 119 10.1 0.002 0.003 2.096 2.269 init_scf_loop 6 6.8 0.000 0.000 2.042 2.042 dbcsr_multiply_generic 2588 12.3 0.058 0.063 1.932 1.972 mp_sum_d 5826 12.2 1.147 1.891 1.147 1.891 pw_scatter_p 1095 14.8 1.674 1.704 1.674 1.704 pw_gather_p 964 14.0 1.309 1.641 1.309 1.641 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 1.605 1.605 pw_integral_ab 2761 7.7 1.066 1.267 1.403 1.521 pw_copy 2027 12.4 1.211 1.492 1.211 1.492 pw_derive 1089 13.4 1.158 1.486 1.158 1.486 pw_poisson_solve 125 9.9 0.003 0.003 1.206 1.400 mp_waitall_1 177795 16.4 1.102 1.349 1.102 1.349 mp_sum_dm3 33 5.7 1.271 1.348 1.271 1.348 transfer_pw2rs_40 119 14.1 0.272 0.343 1.070 1.283 ot_mini 113 10.2 0.001 0.001 1.234 1.240 cp_fm_diag_elpa 104 12.7 0.000 0.000 1.195 1.199 cp_dbcsr_syevd 98 11.8 0.005 0.006 1.180 1.185 ------------------------------------------------------------------------------- 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=22.680000000000007, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=86.363, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_s", label="fft3d_s", y=8.187, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_scatter_s", label="pw_scatter_s", y=5.6, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft_wrap_pw1pw2_150", label="fft_wrap_pw1pw2_150", y=5.304, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.544, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=3.332, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="mp_alltoall_z22v", label="mp_alltoall_z22v", 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="fft3d_ps", label="fft3d_ps", 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=32.028000000000006, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=2.786, 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="fft_wrap_pw1pw2_150", label="fft_wrap_pw1pw2_150", y=0.575, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.152, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=4.37, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=4.883, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=3.393, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=6.681, yerr=0.0 Summary: Performance test took 35 minutes. Status: OK Removing intermediate container 18f315fe96a9 ---> d86d98125dc5 Step 41/42 : CMD cat $(find ./report.log -mmin +10) | sed '/^Summary:/ s/$/ (cached)/' ---> Running in e432addfb14c Removing intermediate container e432addfb14c ---> 3593b1ba92e7 Step 42/42 : ENTRYPOINT [] ---> Running in fda830250c36 Removing intermediate container fda830250c36 ---> 354009ea2f1f [Warning] One or more build-args [GIT_COMMIT_SHA] were not consumed Successfully built 354009ea2f1f 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: 2024-02-28 08:52:44+00:00