StartDate: 2022-04-06 19:11:10+00:00 CpuId: 64x AMD (unknown model) [Zen 3], 7nm CommitSHA: 1cf8ef67de9c39cfc2d982a83bd7f3c2fc3c9fca CommitTime: 2022-04-06 13:59:52 +0200 CommitAuthor: Hans Pabst CommitSubject: toolchain: support Intel MPI with GNU Compiler Collection (#2055) Populating docker build cache... done. #################### Building Image cp2k-perf-openmp #################### Dockerfile: /tools/docker/Dockerfile.test_performance Build-Path: / Build-Args: GIT_COMMIT_SHA=1cf8ef67de9c39cfc2d982a83bd7f3c2fc3c9fca Sending build context to Docker daemon 362.7MB Step 1/41 : FROM ubuntu:20.04 20.04: Pulling from library/ubuntu e0b25ef51634: Already exists Digest: sha256:9101220a875cee98b016668342c489ff0674f247f6ca20dfc91b91c0f28581ae Status: Downloaded newer image for ubuntu:20.04 ---> 825d55fb6340 Step 2/41 : WORKDIR /opt/cp2k-toolchain ---> Using cache ---> 841cb194a0cf Step 3/41 : COPY ./tools/toolchain/install_requirements*.sh ./ ---> Using cache ---> 5df7ca39fa7a Step 4/41 : RUN ./install_requirements.sh ubuntu:20.04 ---> Using cache ---> 0366c3f03bee Step 5/41 : RUN mkdir scripts ---> Using cache ---> e5dca24c5811 Step 6/41 : 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 ---> 2f976ef702d2 Step 7/41 : COPY ./tools/toolchain/install_cp2k_toolchain.sh . ---> Using cache ---> 70693b4da5d3 Step 8/41 : RUN ./install_cp2k_toolchain.sh --install-all --mpi-mode=mpich --dry-run ---> Using cache ---> 417174236f96 Step 9/41 : COPY ./tools/toolchain/scripts/stage0/ ./scripts/stage0/ ---> Using cache ---> c142e73ac6f9 Step 10/41 : RUN ./scripts/stage0/install_stage0.sh && rm -rf ./build ---> Using cache ---> 3744aa52ba6c Step 11/41 : COPY ./tools/toolchain/scripts/stage1/ ./scripts/stage1/ ---> Using cache ---> 66293bae5149 Step 12/41 : RUN ./scripts/stage1/install_stage1.sh && rm -rf ./build ---> Using cache ---> ef6faeee6591 Step 13/41 : COPY ./tools/toolchain/scripts/stage2/ ./scripts/stage2/ ---> Using cache ---> 234703ee18e2 Step 14/41 : RUN ./scripts/stage2/install_stage2.sh && rm -rf ./build ---> Using cache ---> 5fb752c942cb Step 15/41 : COPY ./tools/toolchain/scripts/stage3/ ./scripts/stage3/ ---> Using cache ---> 003a4a2609f6 Step 16/41 : RUN ./scripts/stage3/install_stage3.sh && rm -rf ./build ---> Using cache ---> d10229657c43 Step 17/41 : COPY ./tools/toolchain/scripts/stage4/ ./scripts/stage4/ ---> Using cache ---> 24e654e68278 Step 18/41 : RUN ./scripts/stage4/install_stage4.sh && rm -rf ./build ---> Using cache ---> 39501a1ed873 Step 19/41 : COPY ./tools/toolchain/scripts/stage5/ ./scripts/stage5/ ---> Using cache ---> 03da04a45542 Step 20/41 : RUN ./scripts/stage5/install_stage5.sh && rm -rf ./build ---> Using cache ---> 1c10a430f39f Step 21/41 : COPY ./tools/toolchain/scripts/stage6/ ./scripts/stage6/ ---> Using cache ---> 530881d2040c Step 22/41 : RUN ./scripts/stage6/install_stage6.sh && rm -rf ./build ---> Using cache ---> db0dcfd7679e Step 23/41 : COPY ./tools/toolchain/scripts/stage7/ ./scripts/stage7/ ---> Using cache ---> 32ad5cc20a7f Step 24/41 : RUN ./scripts/stage7/install_stage7.sh && rm -rf ./build ---> Using cache ---> 4ce3fdb53f2b Step 25/41 : COPY ./tools/toolchain/scripts/stage8/ ./scripts/stage8/ ---> Using cache ---> 25c1ad0d5c3d Step 26/41 : RUN ./scripts/stage8/install_stage8.sh && rm -rf ./build ---> Using cache ---> 95e2ff3f0aaf Step 27/41 : COPY ./tools/toolchain/scripts/arch_base.tmpl ./tools/toolchain/scripts/generate_arch_files.sh ./scripts/ ---> Using cache ---> 6f1221f1c2c4 Step 28/41 : RUN ./scripts/generate_arch_files.sh && rm -rf ./build ---> Using cache ---> b47e67dede47 Step 29/41 : WORKDIR /opt/cp2k ---> Using cache ---> 8bdb45f35659 Step 30/41 : COPY ./Makefile . ---> Using cache ---> 9f7848fdd1a1 Step 31/41 : COPY ./src ./src ---> Using cache ---> 55d1358282a3 Step 32/41 : COPY ./exts ./exts ---> Using cache ---> 42d94bf68ecf Step 33/41 : COPY ./tools/build_utils ./tools/build_utils ---> Using cache ---> 103a67a09483 Step 34/41 : 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 )" ---> Running in 8679d53f86b5 './arch/local.psmp' -> '/opt/cp2k-toolchain/install/arch/local.psmp' Compiling cp2k... Removing intermediate container 8679d53f86b5 ---> 6aefa9c96504 Step 35/41 : COPY ./data ./data ---> ee97f8185681 Step 36/41 : COPY ./tests ./tests ---> b4991bc2b25c Step 37/41 : COPY ./tools/regtesting ./tools/regtesting ---> caa241ba4e38 Step 38/41 : COPY ./benchmarks ./benchmarks ---> 33e758089c32 Step 39/41 : COPY ./tools/docker/scripts/test_performance.sh ./tools/docker/scripts/plot_performance.py ./ ---> b2cfec1c352f Step 40/41 : RUN ./test_performance.sh "local" 2>&1 | tee report.log ---> Running in f8fd4b02bf25 ========== Compiling CP2K ========== Compiling cp2k... done. Checking benchmark inputs... Found 60 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 0.034 0.034 202.756 202.756 qs_mol_dyn_low 1 2.0 0.003 0.003 202.139 202.139 qs_forces 11 3.9 0.001 0.001 202.085 202.085 qs_energies 11 4.9 0.001 0.001 194.954 194.954 scf_env_do_scf 11 5.9 0.002 0.002 181.374 181.374 velocity_verlet 10 3.0 0.002 0.002 139.577 139.577 init_scf_loop 11 6.9 0.000 0.000 93.649 93.649 prepare_preconditioner 11 7.9 0.000 0.000 90.641 90.641 make_preconditioner 11 8.9 0.000 0.000 90.641 90.641 make_full_inverse_cholesky 11 9.9 0.000 0.000 89.386 89.386 scf_env_do_scf_inner_loop 108 6.5 0.014 0.014 87.594 87.594 cp_fm_cholesky_invert 11 10.9 61.929 61.929 61.929 61.929 qs_scf_new_mos 108 7.5 0.001 0.001 43.569 43.569 qs_scf_loop_do_ot 108 8.5 0.001 0.001 43.568 43.568 ot_scf_mini 108 9.5 0.003 0.003 41.507 41.507 qs_rho_update_rho 119 7.7 0.001 0.001 26.310 26.310 calculate_rho_elec 119 8.7 0.989 0.989 26.309 26.309 rebuild_ks_matrix 119 8.3 0.001 0.001 24.740 24.740 qs_ks_build_kohn_sham_matrix 119 9.3 0.017 0.017 24.739 24.739 dbcsr_multiply_generic 2286 12.5 0.177 0.177 23.946 23.946 cp_fm_cholesky_decompose 22 10.9 23.093 23.093 23.093 23.093 qs_ks_update_qs_env 119 7.6 0.001 0.001 22.674 22.674 qs_ot_get_p 119 10.4 0.001 0.001 21.663 21.663 grid_collocate_task_list 119 9.7 21.631 21.631 21.631 21.631 qs_ot_p2m_diag 50 11.0 0.180 0.180 20.288 20.288 cp_dbcsr_syevd 50 12.0 0.003 0.003 19.836 19.836 cp_fm_diag_elpa 50 13.0 0.000 0.000 18.544 18.544 cp_fm_diag_elpa_base 50 14.0 18.488 18.488 18.543 18.543 sum_up_and_integrate 119 10.3 0.200 0.200 15.993 15.993 integrate_v_rspace 119 11.3 0.365 0.365 15.793 15.793 ot_mini 108 10.5 0.001 0.001 15.522 15.522 grid_integrate_task_list 119 12.3 13.388 13.388 13.388 13.388 make_m2s 4572 13.5 0.059 0.059 12.004 12.004 qs_ot_get_derivative 108 11.5 0.001 0.001 9.546 9.546 multiply_cannon 2286 13.5 0.683 0.683 7.644 7.644 make_images 4572 14.5 2.219 2.219 6.535 6.535 multiply_cannon_loop 2286 14.5 0.024 0.024 6.510 6.510 multiply_cannon_multrec 2286 15.5 6.413 6.413 6.486 6.486 pw_transfer 1439 11.6 0.075 0.075 6.479 6.479 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 6.322 6.322 fft_wrap_pw1pw2 1201 12.6 0.008 0.008 6.210 6.210 init_scf_run 11 5.9 0.002 0.002 6.080 6.080 scf_env_initial_rho_setup 11 6.9 0.001 0.001 6.078 6.078 ot_diis_step 108 11.5 0.005 0.005 5.972 5.972 dbcsr_make_dense_low 5837 15.5 0.073 0.073 5.855 5.855 make_dense_data 5837 16.5 5.431 5.431 5.765 5.765 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 5.591 5.591 apply_single 119 13.6 0.001 0.001 5.591 5.591 wfi_extrapolate 11 7.9 0.001 0.001 5.457 5.457 fft_wrap_pw1pw2_140 487 13.2 0.525 0.525 5.366 5.366 dbcsr_make_images_dense 3978 14.8 0.022 0.022 5.104 5.104 build_core_hamiltonian_matrix_ 11 4.9 0.001 0.001 4.101 4.101 ------------------------------------------------------------------------------- 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 0.006 0.008 49.280 49.281 qs_mol_dyn_low 1 2.0 0.004 0.005 49.181 49.185 qs_forces 11 3.9 0.001 0.001 49.148 49.150 qs_energies 11 4.9 0.001 0.001 46.062 46.064 scf_env_do_scf 11 5.9 0.000 0.001 42.316 42.317 scf_env_do_scf_inner_loop 108 6.5 0.002 0.008 39.286 39.286 velocity_verlet 10 3.0 0.001 0.002 28.565 28.566 rebuild_ks_matrix 119 8.3 0.000 0.001 18.438 18.517 qs_ks_build_kohn_sham_matrix 119 9.3 0.015 0.017 18.437 18.517 qs_ks_update_qs_env 119 7.6 0.001 0.001 16.494 16.572 dbcsr_multiply_generic 2286 12.5 0.069 0.074 15.154 15.302 qs_rho_update_rho 119 7.7 0.001 0.001 14.073 14.079 calculate_rho_elec 119 8.7 0.030 0.031 14.073 14.078 sum_up_and_integrate 119 10.3 0.019 0.022 13.595 13.605 integrate_v_rspace 119 11.3 0.004 0.005 13.576 13.586 multiply_cannon 2286 13.5 0.131 0.137 11.721 12.020 qs_scf_new_mos 108 7.5 0.001 0.001 11.658 11.688 qs_scf_loop_do_ot 108 8.5 0.001 0.001 11.657 11.687 multiply_cannon_loop 2286 14.5 0.094 0.104 11.230 11.579 ot_scf_mini 108 9.5 0.002 0.002 11.002 11.031 mp_waitall_1 169478 16.3 10.287 10.747 10.287 10.747 grid_collocate_task_list 119 9.7 9.439 10.218 9.439 10.218 grid_integrate_task_list 119 12.3 8.367 9.325 8.367 9.325 multiply_cannon_metrocomm3 18288 15.5 0.040 0.044 7.008 7.514 ot_mini 108 10.5 0.001 0.001 6.349 6.378 rs_pw_transfer 974 11.9 0.013 0.014 5.713 6.133 density_rs2pw 119 9.7 0.006 0.006 4.248 4.675 potential_pw2rs 119 12.3 0.007 0.008 3.989 4.001 pw_transfer 1439 11.6 0.088 0.097 3.489 3.540 multiply_cannon_multrec 18288 15.5 3.308 3.447 3.317 3.457 fft_wrap_pw1pw2 1201 12.6 0.010 0.011 3.327 3.377 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 3.204 3.312 apply_single 119 13.6 0.000 0.000 3.204 3.312 ot_diis_step 108 11.5 0.004 0.004 3.224 3.224 qs_ot_get_derivative 108 11.5 0.001 0.001 3.104 3.132 init_scf_loop 11 6.9 0.000 0.000 3.017 3.017 fft_wrap_pw1pw2_140 487 13.2 0.301 0.324 2.865 2.943 init_scf_run 11 5.9 0.000 0.001 2.691 2.691 scf_env_initial_rho_setup 11 6.9 0.000 0.001 2.691 2.691 make_m2s 4572 13.5 0.044 0.050 2.423 2.469 fft3d_ps 1201 14.6 1.294 1.389 2.385 2.448 wfi_extrapolate 11 7.9 0.001 0.001 2.388 2.388 mp_waitany 9880 13.7 1.800 2.247 1.800 2.247 make_images 4572 14.5 0.116 0.126 2.103 2.155 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 2.088 2.092 rs_pw_transfer_RS2PW_140 130 11.5 0.308 0.360 1.488 1.912 mp_alltoall_d11v 2130 13.8 1.470 1.761 1.470 1.761 rs_pw_transfer_PW2RS_140 130 13.9 0.666 0.718 1.648 1.698 rs_gather_matrices 119 12.3 0.070 0.078 1.177 1.471 qs_ot_get_p 119 10.4 0.001 0.001 1.286 1.338 make_images_data 4572 15.5 0.035 0.040 1.182 1.266 rs_pw_transfer_PW2RS_50 119 14.3 0.375 0.394 1.120 1.155 hybrid_alltoall_any 4725 16.4 0.065 0.191 1.063 1.148 cp_dbcsr_sm_fm_multiply 37 9.5 0.001 0.001 1.084 1.085 prepare_preconditioner 11 7.9 0.000 0.000 1.026 1.035 make_preconditioner 11 8.9 0.000 0.000 1.026 1.035 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 0.991 1.010 cp_dbcsr_sm_fm_multiply_core 37 10.5 0.000 0.000 0.967 0.998 ------------------------------------------------------------------------------- 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=57.81399999999999, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=61.929, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=23.093, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=21.631, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=18.488, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.388, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=6.413, 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=16.079, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=9.439, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=8.367, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=3.308, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=10.287, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitany", label="mp_waitany", y=1.8, yerr=0.0 Running H2O-64_nonortho.inp with 1 threads and 32 ranks... done. Running H2O-64_nonortho.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/H2O-64_nonortho_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.032 0.032 233.148 233.148 qs_mol_dyn_low 1 2.0 0.003 0.003 232.490 232.490 qs_forces 11 3.9 0.001 0.001 232.435 232.435 qs_energies 11 4.9 0.001 0.001 223.208 223.208 scf_env_do_scf 11 5.9 0.002 0.002 206.667 206.667 velocity_verlet 10 3.0 0.002 0.002 160.454 160.454 scf_env_do_scf_inner_loop 96 6.5 0.013 0.013 109.445 109.445 init_scf_loop 11 6.9 0.000 0.000 97.103 97.103 prepare_preconditioner 11 7.9 0.000 0.000 92.298 92.298 make_preconditioner 11 8.9 0.000 0.000 92.298 92.298 make_full_inverse_cholesky 11 9.9 0.000 0.000 91.075 91.075 cp_fm_cholesky_invert 11 10.9 63.219 63.219 63.219 63.219 rebuild_ks_matrix 107 8.3 0.001 0.001 41.492 41.492 qs_ks_build_kohn_sham_matrix 107 9.3 0.015 0.015 41.491 41.491 qs_rho_update_rho 107 7.7 0.001 0.001 40.778 40.778 calculate_rho_elec 107 8.7 0.888 0.888 40.777 40.777 qs_scf_new_mos 96 7.5 0.001 0.001 39.972 39.972 qs_scf_loop_do_ot 96 8.5 0.001 0.001 39.972 39.972 ot_scf_mini 96 9.5 0.003 0.003 38.114 38.114 qs_ks_update_qs_env 107 7.6 0.001 0.001 37.188 37.188 grid_collocate_task_list 107 9.7 36.491 36.491 36.491 36.491 sum_up_and_integrate 107 10.3 0.178 0.178 33.622 33.622 integrate_v_rspace 107 11.3 0.332 0.332 33.443 33.443 grid_integrate_task_list 107 12.3 31.258 31.258 31.258 31.258 cp_fm_cholesky_decompose 22 10.9 23.856 23.856 23.856 23.856 dbcsr_multiply_generic 1966 12.4 0.156 0.156 21.692 21.692 qs_ot_get_p 107 10.4 0.001 0.001 19.773 19.773 qs_ot_p2m_diag 44 11.0 0.158 0.158 18.568 18.568 cp_dbcsr_syevd 44 12.0 0.003 0.003 18.167 18.167 cp_fm_diag_elpa 44 13.0 0.000 0.000 16.901 16.901 cp_fm_diag_elpa_base 44 14.0 16.851 16.851 16.900 16.900 ot_mini 96 10.5 0.001 0.001 14.417 14.417 make_m2s 3932 13.4 0.050 0.050 10.709 10.709 qs_ot_get_derivative 96 11.5 0.001 0.001 8.934 8.934 init_scf_run 11 5.9 0.002 0.002 7.768 7.768 scf_env_initial_rho_setup 11 6.9 0.001 0.001 7.766 7.766 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 7.678 7.678 multiply_cannon 1966 13.4 0.624 0.624 7.138 7.138 wfi_extrapolate 11 7.9 0.001 0.001 6.919 6.919 multiply_cannon_loop 1966 14.4 0.021 0.021 6.109 6.109 multiply_cannon_multrec 1966 15.4 6.023 6.023 6.087 6.087 pw_transfer 1295 11.6 0.068 0.068 5.949 5.949 make_images 3932 14.4 1.983 1.983 5.834 5.834 fft_wrap_pw1pw2 1081 12.6 0.007 0.007 5.708 5.708 ot_diis_step 96 11.5 0.004 0.004 5.479 5.479 dbcsr_make_dense_low 4961 15.5 0.062 0.062 5.207 5.207 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 5.193 5.193 apply_single 107 13.6 0.000 0.000 5.193 5.193 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 5.190 5.190 make_dense_data 4961 16.5 4.846 4.846 5.130 5.130 fft_wrap_pw1pw2_140 439 13.2 0.486 0.486 4.951 4.951 ------------------------------------------------------------------------------- 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 0.006 0.008 87.215 87.216 qs_mol_dyn_low 1 2.0 0.004 0.005 87.121 87.125 qs_forces 11 3.9 0.001 0.001 87.089 87.090 qs_energies 11 4.9 0.001 0.001 81.287 81.288 scf_env_do_scf 11 5.9 0.000 0.001 75.369 75.370 scf_env_do_scf_inner_loop 96 6.5 0.002 0.007 70.074 70.074 velocity_verlet 10 3.0 0.001 0.002 51.272 51.273 rebuild_ks_matrix 107 8.3 0.000 0.000 38.562 38.608 qs_ks_build_kohn_sham_matrix 107 9.3 0.014 0.020 38.562 38.607 sum_up_and_integrate 107 10.3 0.018 0.021 33.747 34.177 integrate_v_rspace 107 11.3 0.004 0.005 33.728 34.159 qs_ks_update_qs_env 107 7.6 0.001 0.001 34.100 34.140 qs_rho_update_rho 107 7.7 0.001 0.001 32.559 32.568 calculate_rho_elec 107 8.7 0.027 0.028 32.559 32.567 grid_integrate_task_list 107 12.3 23.383 30.382 23.383 30.382 grid_collocate_task_list 107 9.7 22.853 29.333 22.853 29.333 dbcsr_multiply_generic 1966 12.4 0.064 0.076 14.344 20.586 rs_pw_transfer 878 11.9 0.011 0.013 10.803 11.603 multiply_cannon 1966 13.4 0.121 0.129 10.843 11.006 qs_scf_new_mos 96 7.5 0.001 0.001 10.581 10.610 qs_scf_loop_do_ot 96 8.5 0.001 0.001 10.580 10.610 multiply_cannon_loop 1966 14.4 0.091 0.109 10.379 10.531 density_rs2pw 107 9.7 0.005 0.006 9.358 10.167 ot_scf_mini 96 9.5 0.002 0.002 9.986 10.015 mp_waitall_1 146670 16.2 9.386 9.628 9.386 9.628 mp_alltoall_d11v 1998 13.7 6.949 8.254 6.949 8.254 mp_waitany 8968 13.7 7.301 8.121 7.301 8.121 rs_gather_matrices 107 12.3 0.063 0.071 6.680 7.950 rs_pw_transfer_RS2PW_140 118 11.5 0.240 0.269 6.963 7.758 mp_sum_l 9666 13.1 0.880 7.104 0.880 7.104 multiply_cannon_metrocomm3 15728 15.4 0.038 0.046 6.471 6.746 ot_mini 96 10.5 0.001 0.001 5.846 5.875 init_scf_loop 11 6.9 0.000 0.000 5.282 5.283 init_scf_run 11 5.9 0.000 0.001 4.678 4.679 scf_env_initial_rho_setup 11 6.9 0.000 0.001 4.678 4.679 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 4.590 4.595 wfi_extrapolate 11 7.9 0.001 0.001 4.232 4.232 potential_pw2rs 107 12.3 0.007 0.008 3.624 3.633 multiply_cannon_multrec 15728 15.4 3.080 3.304 3.090 3.314 pw_transfer 1295 11.6 0.083 0.093 3.197 3.244 fft_wrap_pw1pw2 1081 12.6 0.009 0.011 3.048 3.100 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 2.994 3.032 apply_single 107 13.6 0.000 0.000 2.994 3.032 ot_diis_step 96 11.5 0.003 0.004 2.943 2.943 qs_ot_get_derivative 96 11.5 0.001 0.001 2.882 2.909 fft_wrap_pw1pw2_140 439 13.2 0.268 0.284 2.639 2.710 make_m2s 3932 13.4 0.040 0.049 2.223 2.260 fft3d_ps 1081 14.6 1.177 1.239 2.186 2.221 make_images 3932 14.4 0.105 0.126 1.923 1.963 ------------------------------------------------------------------------------- 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=61.472999999999985, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=63.219, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=36.491, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=31.258, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=23.856, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=16.851, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="mp_waitany", label="mp_waitany", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="mp_alltoall_d11v", label="mp_alltoall_d11v", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 Plot: name="H2O-64_nonortho_timings_32mpi", title="Timings of H2O-64_nonortho with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="rest", label="rest", y=17.343000000000004, 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="grid_collocate_task_list", label="grid_collocate_task_list", y=22.853, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=23.383, 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_diag_elpa_base", label="cp_fm_diag_elpa_base", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitany", label="mp_waitany", y=7.301, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_alltoall_d11v", label="mp_alltoall_d11v", y=6.949, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=9.386, 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 0.259 0.259 203.040 203.040 qs_energies 1 2.0 0.000 0.000 202.132 202.132 scf_env_do_scf 1 3.0 0.000 0.000 200.564 200.564 qs_ks_update_qs_env 8 5.0 0.000 0.000 162.595 162.595 rebuild_ks_matrix 7 6.0 0.000 0.000 162.536 162.536 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.001 162.536 162.536 hfx_ks_matrix 7 8.0 0.000 0.000 142.980 142.980 integrate_four_center 7 9.0 1.466 1.466 142.952 142.952 integrate_four_center_main 7 10.0 0.751 0.751 128.620 128.620 integrate_four_center_bin 452 11.0 127.868 127.868 127.868 127.868 init_scf_loop 1 4.0 0.000 0.000 110.641 110.641 scf_env_do_scf_inner_loop 7 4.0 0.001 0.001 89.913 89.913 prepare_preconditioner 1 5.0 0.000 0.000 31.854 31.854 make_preconditioner 1 6.0 0.000 0.000 31.854 31.854 arnoldi_normal_ev 11 9.3 0.002 0.002 18.959 18.959 estimate_cond_num 1 7.0 0.000 0.000 18.917 18.917 build_subspace 28 9.5 0.010 0.010 18.702 18.702 integrate_four_center_load 7 10.0 0.000 0.000 12.535 12.535 hfx_load_balance 1 11.0 0.001 0.001 12.535 12.535 admm_mo_calc_rho_aux 7 8.0 0.000 0.000 10.949 10.949 admm_fit_mo_coeffs 7 9.0 0.000 0.000 9.466 9.466 DGKS_ortho_d 673 10.6 8.694 8.694 8.696 8.696 cp_fm_cholesky_invert 2 9.5 8.136 8.136 8.136 8.136 make_full_inverse_cholesky 1 7.0 0.000 0.000 7.996 7.996 Gram_Schmidt_ortho_d 673 10.6 7.964 7.964 7.965 7.965 dbcsr_sym_m_v_mult 562 10.0 0.017 0.017 6.561 6.561 hfx_load_balance_count 1 12.0 6.261 6.261 6.261 6.261 hfx_load_balance_bin 1 12.0 6.253 6.253 6.253 6.253 purify_mo_diag 7 10.0 0.000 0.000 5.394 5.394 cp_fm_syevd 7 11.0 0.000 0.000 4.776 4.776 cp_fm_syevd_base 7 12.0 4.776 4.776 4.776 4.776 make_full_single_inverse 1 7.0 0.000 0.000 4.754 4.754 arnoldi_generalized_ev 1 8.0 0.000 0.000 4.647 4.647 qs_scf_new_mos 7 5.0 0.000 0.000 4.495 4.495 qs_scf_loop_do_ot 7 6.0 0.000 0.000 4.495 4.495 gev_build_subspace 4 9.0 0.005 0.005 4.486 4.486 ot_scf_mini 7 7.0 0.000 0.000 4.363 4.363 qs_vxc_create 14 8.0 0.000 0.000 4.339 4.339 xc_vxc_pw_create 14 9.0 0.121 0.121 4.339 4.339 fit_mo_coeffs 7 10.0 0.000 0.000 4.072 4.072 ------------------------------------------------------------------------------- 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 0.102 0.108 97.905 97.905 qs_energies 1 2.0 0.000 0.000 97.706 97.706 scf_env_do_scf 1 3.0 0.000 0.000 97.225 97.225 qs_ks_update_qs_env 8 5.0 0.000 0.000 95.146 95.146 rebuild_ks_matrix 7 6.0 0.000 0.000 95.137 95.137 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.002 95.137 95.137 hfx_ks_matrix 7 8.0 0.000 0.000 89.643 89.644 integrate_four_center 7 9.0 0.053 0.326 89.634 89.635 integrate_four_center_main 7 10.0 0.003 0.003 81.221 82.351 integrate_four_center_bin 448 11.0 81.219 82.349 81.219 82.349 scf_env_do_scf_inner_loop 7 4.0 0.000 0.001 54.167 54.167 init_scf_loop 1 4.0 0.000 0.000 43.057 43.057 integrate_four_center_load 7 10.0 0.000 0.000 5.777 5.781 hfx_load_balance 1 11.0 0.001 0.001 5.777 5.781 mp_sync 70 11.3 1.934 3.223 1.934 3.223 hfx_load_balance_bin 1 12.0 2.844 2.902 2.844 2.902 hfx_load_balance_count 1 12.0 2.817 2.869 2.817 2.869 qs_vxc_create 14 8.0 0.001 0.001 2.417 2.417 xc_vxc_pw_create 14 9.0 0.008 0.008 2.417 2.417 xc_rho_set_and_dset_create 14 10.0 0.011 0.013 1.929 2.045 ------------------------------------------------------------------------------- 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=37.60500000000002, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_bin", label="integrate_four_center_bin", y=127.868, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="DGKS_ortho_d", label="DGKS_ortho_d", y=8.694, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=8.136, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="Gram_Schmidt_ortho_d", label="Gram_Schmidt_ortho_d", y=7.964, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_count", label="hfx_load_balance_count", y=6.261, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=6.253, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="CP2K", label="CP2K", y=0.259, 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=8.989000000000004, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center_bin", label="integrate_four_center_bin", y=81.219, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="DGKS_ortho_d", label="DGKS_ortho_d", y=0.0, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=0.0, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="Gram_Schmidt_ortho_d", label="Gram_Schmidt_ortho_d", y=0.0, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_count", label="hfx_load_balance_count", y=2.817, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=2.844, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="CP2K", label="CP2K", y=0.102, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="mp_sync", label="mp_sync", y=1.934, 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 0.016 0.016 233.241 233.241 qs_energies 1 2.0 0.000 0.000 232.851 232.851 mp2_main 1 3.0 0.000 0.000 207.033 207.033 mp2_gpw_main 1 4.0 0.000 0.000 205.664 205.664 rpa_ri_compute_en 1 5.0 0.000 0.000 195.866 195.866 rpa_num_int 1 6.0 0.001 0.001 195.853 195.853 compute_mat_P_omega 1 7.0 0.003 0.003 135.342 135.342 compute_mat_P_omega_contract 10 8.0 8.668 8.668 134.835 134.835 dbt_total 2336 9.6 0.017 0.017 129.236 129.236 dbt_contract 787 11.0 30.309 30.309 84.718 84.718 dbt_tas_total 1149 12.2 0.244 0.244 51.399 51.399 dbt_tas_multiply 807 12.1 0.003 0.003 50.612 50.612 dbt_copy 1103 10.7 15.987 15.987 43.707 43.707 compute_mat_P_omega_calc_M_occ 250 9.0 8.657 8.657 42.736 42.736 dbt_tas_dbm 807 14.1 0.004 0.004 42.690 42.690 dbm_multiply 807 16.1 42.679 42.679 42.679 42.679 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 40.448 40.448 GW_matrix_operations 10 7.0 0.004 0.004 33.359 33.359 cp_fm_cholesky_invert 10 8.0 32.399 32.399 32.399 32.399 dbt_tas_mm_1N 524 15.1 0.002 0.002 30.421 30.421 scf_env_do_scf 1 3.0 0.000 0.000 25.635 25.635 scf_env_do_scf_inner_loop 17 4.0 0.002 0.002 25.634 25.634 qs_scf_new_mos 17 5.0 0.000 0.000 23.987 23.987 eigensolver 18 5.9 0.001 0.001 22.499 22.499 cp_fm_diag_elpa 18 6.9 0.000 0.000 14.701 14.701 cp_fm_diag_elpa_base 18 7.9 14.646 14.646 14.700 14.700 dbt_tas_copy 574 11.4 11.408 11.408 14.193 14.193 compute_QP_energies 1 7.0 0.000 0.000 13.813 13.813 compute_self_energy_cubic_gw 1 8.0 0.056 0.056 13.812 13.812 compute_mat_P_omega_copy_M_occ 250 9.0 0.001 0.001 13.681 13.681 cp_fm_cholesky_decompose 14 8.1 13.447 13.447 13.447 13.447 rpa_num_int_RPA_matrix_operati 10 7.0 0.000 0.000 12.035 12.035 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 11.242 11.242 RPA_postprocessing_nokp 10 8.0 0.001 0.001 10.936 10.936 dbt_tas_reserve_blocks_index 3261 13.7 5.857 5.857 10.602 10.602 dbt_tas_mm_2 251 15.0 0.002 0.002 10.168 10.168 mp2_ri_gpw_compute_in 1 5.0 0.001 0.001 9.790 9.790 dbt_reserve_blocks_index 2280 12.5 1.585 1.585 9.150 9.150 dbt_reserve_blocks_index_array 2222 11.6 0.008 0.008 9.119 9.119 compute_mat_P_omega_copy_M_vir 250 9.0 0.001 0.001 7.964 7.964 dbt_copy_nocomm 251 12.0 6.536 6.536 7.791 7.791 cp_fm_cholesky_restore 51 7.0 7.719 7.719 7.719 7.719 contract_cubic_gw 21 9.0 0.000 0.000 6.875 6.875 get_2c_integrals 1 6.0 0.000 0.000 5.710 5.710 ------------------------------------------------------------------------------- From /workspace/artifacts/GW_PBE_4benzene_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.005 0.007 34.071 34.072 qs_energies 1 2.0 0.001 0.001 33.980 33.981 mp2_main 1 3.0 0.000 0.000 32.925 32.925 mp2_gpw_main 1 4.0 0.000 0.000 32.890 32.890 rpa_ri_compute_en 1 5.0 0.000 0.000 31.680 31.681 rpa_num_int 1 6.0 0.001 0.001 31.675 31.675 dbt_total 2336 9.6 0.012 0.013 28.248 28.249 compute_mat_P_omega 1 7.0 0.000 0.001 27.118 27.120 compute_mat_P_omega_contract 10 8.0 0.440 0.453 26.998 27.001 dbt_contract 787 11.0 1.005 1.096 20.999 21.012 dbt_tas_total 1149 12.2 0.050 0.058 18.832 18.832 dbt_tas_multiply 807 12.1 0.002 0.002 18.762 18.764 dbt_tas_dbm 807 14.1 0.003 0.003 13.912 13.912 dbm_multiply 807 16.1 10.970 11.856 10.970 11.856 compute_mat_P_omega_calc_M_occ 250 9.0 0.410 0.423 7.991 7.991 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 7.910 7.910 dbt_copy 1111 10.7 2.429 2.589 6.396 6.607 dbt_tas_mm_2 251 15.0 0.001 0.001 6.529 6.529 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 5.701 5.702 dbt_tas_mm_1N 524 15.1 0.001 0.002 5.058 5.511 mp_sync 8706 11.6 4.507 5.508 4.507 5.508 mp_waitall_2 3776 14.7 2.866 3.122 2.866 3.122 dbt_communicate_buffer 1098 11.7 0.055 0.060 2.955 3.074 compute_QP_energies 1 7.0 0.000 0.000 2.897 2.897 compute_self_energy_cubic_gw 1 8.0 0.003 0.003 2.895 2.897 contract_cubic_gw 21 9.0 0.000 0.000 2.290 2.290 dbt_reserve_blocks_index 2849 12.4 0.069 0.073 1.843 2.067 dbt_reserve_blocks_index_array 2791 11.4 0.009 0.010 1.843 2.066 dbt_tas_reserve_blocks_index 3300 13.8 0.176 0.190 1.816 2.033 dbm_reserve_blocks 3696 14.8 1.691 1.901 1.691 1.901 dbt_tas_replicate 396 14.1 0.678 0.836 1.295 1.349 convert_to_new_pgrid 2421 14.1 0.022 0.025 1.145 1.214 mp2_ri_gpw_compute_in 1 5.0 0.000 0.001 1.206 1.208 dbm_copy 1608 15.1 1.116 1.188 1.116 1.188 compute_mat_P_omega_copy_M_vir 250 9.0 0.001 0.001 1.123 1.126 compute_mat_P_omega_copy_M_occ 250 9.0 0.001 0.001 1.079 1.081 scf_env_do_scf 1 3.0 0.000 0.000 1.015 1.015 scf_env_do_scf_inner_loop 17 4.0 0.000 0.001 1.014 1.015 cp_gemm 105 8.4 0.000 0.000 0.983 0.993 cp_gemm_cosma 105 9.4 0.983 0.993 0.983 0.993 GW_matrix_operations 10 7.0 0.001 0.001 0.749 0.754 dbm_add 807 14.1 0.719 0.749 0.719 0.749 mp_max_i 1992 9.8 0.562 0.741 0.562 0.741 ------------------------------------------------------------------------------- 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=97.22100000000003, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=42.679, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=32.399, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbt_contract", label="dbt_contract", y=30.309, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbt_copy", label="dbt_copy", y=15.987, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=14.646, 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="dbm_reserve_blocks", label="dbm_reserve_blocks", 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=10.602999999999994, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=10.97, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=0.0, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbt_contract", label="dbt_contract", y=1.005, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbt_copy", label="dbt_copy", y=2.429, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=0.0, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.866, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=1.691, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_sync", label="mp_sync", y=4.507, yerr=0.0 Running RI-HFX_H2O-32.inp with 1 threads and 32 ranks... done. Running RI-HFX_H2O-32.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/RI-HFX_H2O-32_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.020 0.020 510.021 510.021 qs_forces 1 2.0 0.000 0.000 509.432 509.432 rebuild_ks_matrix 7 6.6 0.000 0.000 482.763 482.763 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.001 482.763 482.763 hfx_ks_matrix 7 8.6 0.000 0.000 480.655 480.655 dbt_total 4939 11.6 0.035 0.035 417.562 417.562 hfx_ri_update_ks 7 9.6 0.000 0.000 361.984 361.984 hfx_ri_update_ks_Pmat 7 10.6 34.884 34.884 361.981 361.981 qs_energies 1 3.0 0.000 0.000 344.707 344.707 scf_env_do_scf 1 4.0 0.000 0.000 344.213 344.213 qs_ks_update_qs_env 8 6.0 0.000 0.000 318.091 318.091 dbt_contract 1473 13.0 111.661 111.661 285.192 285.192 scf_env_do_scf_inner_loop 6 5.0 0.001 0.001 189.237 189.237 dbt_tas_total 2391 14.1 1.070 1.070 182.670 182.670 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 164.676 164.676 dbt_tas_multiply 1482 14.0 0.006 0.006 163.429 163.429 hfx_ri_update_ks_Pmat_KS 567 11.6 0.005 0.005 162.026 162.026 init_scf_loop 2 5.0 0.000 0.000 154.974 154.974 dbt_tas_dbm 1482 16.0 0.007 0.007 141.798 141.798 dbm_multiply 1482 18.0 141.778 141.778 141.778 141.778 hfx_ri_update_forces 1 7.0 0.000 0.000 118.667 118.667 dbt_copy 2411 12.3 61.034 61.034 113.075 113.075 dbt_tas_mm_2 649 17.1 0.005 0.005 108.823 108.823 hfx_ri_update_ks_Pmat_Px3C 567 11.6 0.002 0.002 83.189 83.189 hfx_ri_forces_Pmat_3c 1 8.0 0.003 0.003 62.346 62.346 precalc_derivatives 1 8.0 0.006 0.006 44.532 44.532 hfx_ri_pre_scf_Pmat 1 12.0 0.001 0.001 37.286 37.286 dbt_tas_mm_3T 659 17.1 0.002 0.002 25.358 25.358 hfx_ri_update_ks_Pmat_copy_2 567 11.6 0.002 0.002 24.760 24.760 dbt_tas_reserve_blocks_index 7477 15.3 13.957 13.957 24.256 24.256 prepare_preconditioner 2 6.0 0.000 0.000 23.321 23.321 make_preconditioner 2 7.0 0.000 0.000 22.872 22.872 make_full_all 2 8.0 0.000 0.000 22.390 22.390 dbt_tas_copy 1555 13.0 17.052 17.052 22.219 22.219 cp_fm_syevd 12 10.7 0.000 0.000 22.187 22.187 cp_fm_syevd_base 12 11.7 22.187 22.187 22.187 22.187 dbt_reserve_blocks_index 4998 14.5 3.129 3.129 20.984 20.984 dbt_reserve_blocks_index_array 4963 13.5 0.017 0.017 20.809 20.809 build_3c_derivatives 9 9.0 2.499 2.499 18.461 18.461 dbt_tas_reshape 906 14.4 0.013 0.013 18.045 18.045 hfx_ri_pre_scf_Pmat_RIx3C 81 13.0 0.000 0.000 13.383 13.383 dbt_tas_reshape_buffer_obtain 906 15.4 8.298 8.298 12.076 12.076 ------------------------------------------------------------------------------- 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 0.005 0.008 59.362 59.363 qs_forces 1 2.0 0.000 0.000 59.185 59.185 rebuild_ks_matrix 7 6.6 0.000 0.000 58.486 58.487 qs_ks_build_kohn_sham_matrix 7 7.6 0.002 0.003 58.486 58.487 hfx_ks_matrix 7 8.6 0.001 0.001 57.354 57.360 dbt_total 4939 11.6 0.027 0.030 51.700 51.702 dbt_contract 1473 13.0 3.535 4.537 39.035 39.047 hfx_ri_update_ks 7 9.6 0.000 0.000 38.488 38.488 hfx_ri_update_ks_Pmat 7 10.6 1.512 1.997 38.487 38.487 dbt_tas_total 2391 14.1 0.111 0.138 36.346 36.346 qs_energies 1 3.0 0.000 0.000 35.528 35.528 scf_env_do_scf 1 4.0 0.000 0.000 35.376 35.376 qs_ks_update_qs_env 8 6.0 0.000 0.000 34.843 34.844 dbt_tas_multiply 1482 14.0 0.005 0.005 32.054 32.056 dbt_tas_dbm 1482 16.0 0.005 0.006 24.036 24.037 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 23.644 23.644 dbm_multiply 1482 18.0 17.267 20.945 17.267 20.945 scf_env_do_scf_inner_loop 6 5.0 0.000 0.000 20.198 20.198 hfx_ri_update_ks_Pmat_KS 567 11.6 0.004 0.004 19.926 19.926 hfx_ri_update_forces 1 7.0 0.000 0.000 18.865 18.871 init_scf_loop 2 5.0 0.000 0.000 15.177 15.177 hfx_ri_forces_Pmat_3c 1 8.0 0.002 0.002 13.299 13.314 dbt_tas_mm_2 649 17.1 0.003 0.004 13.182 13.183 mp_sync 17669 13.5 10.546 12.909 10.546 12.909 hfx_ri_update_ks_Pmat_Px3C 567 11.6 0.002 0.002 8.346 8.347 dbt_copy 2429 12.3 2.516 3.071 7.266 7.695 dbt_tas_mm_3T 659 17.1 0.002 0.002 4.715 5.123 dbt_tas_mm_3N 163 16.5 0.000 0.001 4.350 4.403 precalc_derivatives 1 8.0 0.001 0.002 4.342 4.342 hfx_ri_pre_scf_Pmat 1 12.0 0.001 0.001 4.257 4.258 dbt_tas_merge 649 14.1 1.692 2.112 2.813 3.359 mp_waitall_2 5988 16.1 3.040 3.300 3.040 3.300 dbt_tas_reserve_blocks_index 7508 15.4 0.436 0.565 2.552 3.006 dbm_reserve_blocks 8417 16.2 2.266 2.635 2.266 2.635 dbt_tas_replicate 909 15.6 0.726 0.919 2.402 2.529 dbt_reserve_blocks_index 5399 14.4 0.126 0.148 2.158 2.529 dbt_reserve_blocks_index_array 5364 13.5 0.013 0.015 2.153 2.523 hfx_ri_pre_scf_Pmat_RIx3C 81 13.0 0.000 0.000 2.444 2.450 mp_max_i 3372 12.5 1.848 2.349 1.848 2.349 dbt_tas_communicate_buffer 1825 16.3 0.061 0.080 2.065 2.239 build_3c_derivatives 9 9.0 0.239 0.384 2.045 2.047 convert_to_new_pgrid 4446 16.0 0.036 0.046 1.823 2.024 dbm_copy 3043 16.9 1.786 1.991 1.786 1.991 dbt_tas_reshape 916 14.4 0.009 0.011 1.821 1.973 dbt_communicate_buffer 1257 13.5 0.045 0.058 1.791 1.912 mp_alltoall_i 3084 15.2 1.491 1.698 1.491 1.698 hfx_ri_update_ks_Pmat_copy_2 567 11.6 0.002 0.002 1.654 1.655 ------------------------------------------------------------------------------- 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=138.47699999999998, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=141.778, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_contract", label="dbt_contract", y=111.661, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_copy", label="dbt_copy", y=61.034, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=34.884, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="cp_fm_syevd_base", label="cp_fm_syevd_base", y=22.187, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="mp_waitall_2", label="mp_waitall_2", y=0.0, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="mp_sync", label="mp_sync", y=0.0, yerr=0.0 Plot: name="RI-HFX_H2O-32_timings_32mpi", title="Timings of RI-HFX_H2O-32 with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="rest", label="rest", y=20.946000000000005, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=17.267, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_contract", label="dbt_contract", y=3.535, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_copy", label="dbt_copy", y=2.516, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=1.512, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="cp_fm_syevd_base", label="cp_fm_syevd_base", y=0.0, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=3.04, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_sync", label="mp_sync", y=10.546, 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 0.017 0.017 236.610 236.610 qs_energies 1 2.0 0.000 0.000 236.421 236.421 mp2_main 1 3.0 0.000 0.000 197.925 197.925 mp2_gpw_main 1 4.0 0.001 0.001 193.814 193.814 mp2_ri_gpw_compute_in 1 5.0 0.376 0.376 135.624 135.624 mp2_ri_gpw_compute_in_loop 1 6.0 0.015 0.015 110.009 110.009 mp2_eri_3c_integrate_gpw 2656 7.0 0.017 0.017 75.744 75.744 integrate_v_rspace 2666 8.0 3.061 3.061 61.163 61.163 mp2_ri_gpw_compute_en 1 5.0 0.061 0.061 58.166 58.166 mp2_ri_gpw_compute_en_RI_loop 1 6.0 19.418 19.418 56.478 56.478 grid_integrate_task_list 2666 9.0 56.194 56.194 56.194 56.194 scf_env_do_scf 1 3.0 0.000 0.000 37.295 37.295 scf_env_do_scf_inner_loop 10 4.0 0.001 0.001 37.295 37.295 qs_scf_new_mos 10 5.0 0.000 0.000 35.700 35.700 mp2_ri_gpw_compute_en_expansio 2080 7.0 3.303 3.303 31.557 31.557 offload_gemm 2080 8.0 28.254 28.254 28.254 28.254 dbcsr_multiply_generic 5322 8.0 0.213 0.213 26.583 26.583 calculate_wavefunction 5312 9.0 20.497 20.497 26.565 26.565 ao_to_mo_and_store_B_mult_1 2656 7.0 0.016 0.016 26.556 26.556 eigensolver 11 5.8 0.001 0.001 26.051 26.051 get_2c_integrals 1 6.0 0.000 0.000 25.090 25.090 cp_fm_diag_elpa 11 6.8 0.000 0.000 23.230 23.230 cp_fm_diag_elpa_base 11 7.8 23.067 23.067 23.230 23.230 compute_2c_integrals 1 7.0 0.006 0.006 18.872 18.872 compute_2c_integrals_loop_lm 1 8.0 0.012 0.012 18.854 18.854 mp2_eri_2c_integrate_gpw 1 9.0 2.631 2.631 18.843 18.843 multiply_cannon 5322 9.0 3.091 3.091 14.772 14.772 qs_diis_b_step 9 6.0 0.000 0.000 11.462 11.462 multiply_cannon_loop 5322 10.0 0.092 0.092 10.669 10.669 pw_transfer 63872 10.6 1.222 1.222 10.428 10.428 cp_fm_symm 18 7.0 10.360 10.360 10.360 10.360 make_m2s 10644 9.0 0.078 0.078 9.786 9.786 multiply_cannon_multrec 5322 11.0 9.397 9.397 9.448 9.448 make_images 10644 10.0 3.314 3.314 9.296 9.296 fft_wrap_pw1pw2 53228 11.4 0.155 0.155 9.028 9.028 ao_to_mo_and_store_B_E_Ex_1 2656 7.0 3.866 3.866 7.600 7.600 fft_wrap_pw1pw2_20 21271 12.4 0.473 0.473 6.367 6.367 fft3d_s 53229 13.4 5.610 5.610 5.650 5.650 mp2_ri_gpw_compute_en_ener 2080 7.0 5.499 5.499 5.499 5.499 cp_fm_triangular_invert 2 6.0 5.174 5.174 5.174 5.174 ------------------------------------------------------------------------------- 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 0.005 0.007 41.100 41.101 qs_energies 1 2.0 0.000 0.001 41.012 41.012 mp2_main 1 3.0 0.000 0.000 38.775 38.775 mp2_gpw_main 1 4.0 0.001 0.002 38.658 38.659 mp2_ri_gpw_compute_en 1 5.0 0.138 0.146 20.889 21.210 mp2_ri_gpw_compute_en_RI_loop 1 6.0 1.313 1.556 18.514 18.934 mp2_ri_gpw_compute_in 1 5.0 0.026 0.027 17.704 18.063 mp2_ri_gpw_compute_in_loop 1 6.0 0.001 0.001 16.242 16.605 mp2_eri_3c_integrate_gpw 83 7.0 0.001 0.001 14.157 14.577 integrate_v_rspace 93 8.1 0.106 0.118 14.056 14.477 grid_integrate_task_list 93 9.1 13.706 14.117 13.706 14.117 mp2_ri_gpw_compute_en_expansio 65 7.0 0.147 0.172 11.831 12.175 offload_gemm 65 8.0 11.684 12.020 11.684 12.020 mp2_ri_gpw_compute_en_comm 65 7.0 1.595 1.968 4.918 5.596 mp_sendrecv_dm3 390 8.0 3.323 4.072 3.323 4.072 scf_env_do_scf 1 3.0 0.000 0.000 2.083 2.083 scf_env_do_scf_inner_loop 10 4.0 0.000 0.001 2.083 2.083 dbcsr_multiply_generic 176 8.0 0.008 0.008 1.790 2.049 ao_to_mo_and_store_B_mult_1 83 7.0 0.001 0.001 1.774 2.035 mp2_ri_create_group 1 6.0 0.000 0.000 1.439 1.454 replicate_iaK_2intgroup 1 7.0 0.904 1.013 1.325 1.454 get_2c_integrals 1 6.0 0.000 0.000 1.330 1.343 multiply_cannon 176 9.0 0.014 0.016 1.049 1.120 compute_2c_integrals 1 7.0 0.004 0.006 1.102 1.114 multiply_cannon_loop 176 10.0 0.002 0.002 0.994 1.065 eigensolver 11 5.8 0.001 0.001 1.038 1.039 qs_scf_new_mos 10 5.0 0.000 0.000 1.033 1.039 compute_2c_integrals_loop_lm 1 8.0 0.001 0.001 1.012 1.038 mp2_eri_2c_integrate_gpw 1 9.0 0.208 0.221 1.011 1.037 multiply_cannon_multrec 246 11.0 0.864 0.910 0.868 0.916 make_m2s 352 9.0 0.003 0.003 0.704 0.903 make_images 352 10.0 0.052 0.053 0.692 0.891 calculate_wavefunction 166 9.0 0.498 0.505 0.869 0.884 cp_fm_diag_elpa 11 6.8 0.000 0.000 0.870 0.871 mp_sum_d 498 2.3 0.445 0.870 0.445 0.870 cp_fm_redistribute_end 11 7.8 0.328 0.861 0.334 0.863 cp_fm_diag_elpa_base 11 7.8 0.514 0.830 0.526 0.844 ------------------------------------------------------------------------------- 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=89.18, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=56.194, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="offload_gemm", label="offload_gemm", y=28.254, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=23.067, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="calculate_wavefunction", label="calculate_wavefunction", y=20.497, 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=19.418, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="mp2_ri_gpw_compute_en_comm", label="mp2_ri_gpw_compute_en_comm", y=0.0, 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=8.467000000000006, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.706, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="offload_gemm", label="offload_gemm", y=11.684, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=0.514, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="calculate_wavefunction", label="calculate_wavefunction", y=0.498, 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=1.313, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="mp2_ri_gpw_compute_en_comm", label="mp2_ri_gpw_compute_en_comm", y=1.595, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="mp_sendrecv_dm3", label="mp_sendrecv_dm3", y=3.323, 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 0.085 0.085 236.853 236.853 qs_energies 1 2.0 0.000 0.000 235.275 235.275 scf_env_do_scf 1 3.0 0.000 0.000 224.837 224.837 scf_env_do_scf_inner_loop 15 4.0 0.002 0.002 224.837 224.837 qs_scf_new_mos 15 5.0 0.000 0.000 134.615 134.615 eigensolver 15 6.0 0.002 0.002 126.451 126.451 cp_fm_diag_elpa 15 7.0 0.000 0.000 114.486 114.486 cp_fm_diag_elpa_base 15 8.0 112.180 112.180 114.486 114.486 qs_ks_update_qs_env 15 5.0 0.000 0.000 58.110 58.110 rebuild_ks_matrix 15 6.0 0.000 0.000 57.901 57.901 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.002 57.901 57.901 qs_vxc_create 15 8.0 0.025 0.025 35.532 35.532 calculate_dispersion_nonloc 15 9.0 6.755 6.755 30.944 30.944 qs_rho_update_rho 16 5.0 0.000 0.000 29.353 29.353 calculate_rho_elec 16 6.0 0.223 0.223 29.353 29.353 grid_collocate_task_list 16 7.0 28.029 28.029 28.029 28.029 pw_transfer 1191 10.0 0.083 0.083 23.407 23.407 fft_wrap_pw1pw2 1086 11.0 0.013 0.013 23.125 23.125 sum_up_and_integrate 15 8.0 0.039 0.039 21.123 21.123 integrate_v_rspace 15 9.0 0.030 0.030 21.084 21.084 grid_integrate_task_list 15 10.0 20.532 20.532 20.532 20.532 fft_wrap_pw1pw2_150 765 12.0 3.599 3.599 16.906 16.906 fft3d_s 1087 13.0 10.138 10.138 10.148 10.148 cp_fm_cholesky_restore 45 7.0 9.808 9.808 9.808 9.808 pw_scatter_s 585 13.1 7.108 7.108 7.108 7.108 init_scf_run 1 3.0 0.000 0.000 6.126 6.126 fft_wrap_pw1pw2_200 197 12.3 0.609 0.609 6.016 6.016 copy_dbcsr_to_fm 16 5.9 0.001 0.001 5.640 5.640 dbcsr_complete_redistribute 46 8.3 2.223 2.223 5.257 5.257 vdW_energy 15 10.0 5.251 5.251 5.251 5.251 ------------------------------------------------------------------------------- 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 0.010 0.013 64.428 64.428 qs_energies 1 2.0 0.000 0.001 63.998 63.999 scf_env_do_scf 1 3.0 0.000 0.000 59.651 59.651 scf_env_do_scf_inner_loop 15 4.0 0.001 0.002 59.651 59.651 qs_ks_update_qs_env 15 5.0 0.000 0.000 25.569 25.594 rebuild_ks_matrix 15 6.0 0.000 0.000 25.533 25.558 qs_ks_build_kohn_sham_matrix 15 7.0 0.003 0.003 25.532 25.558 qs_rho_update_rho 16 5.0 0.000 0.000 21.966 21.969 calculate_rho_elec 16 6.0 0.007 0.007 21.966 21.969 grid_collocate_task_list 16 7.0 20.218 21.262 20.218 21.262 sum_up_and_integrate 15 8.0 0.008 0.011 14.590 14.650 integrate_v_rspace 15 9.0 0.001 0.001 14.582 14.646 grid_integrate_task_list 15 10.0 13.605 13.957 13.605 13.957 qs_scf_new_mos 15 5.0 0.000 0.000 12.896 13.076 eigensolver 15 6.0 0.001 0.002 11.825 11.841 qs_vxc_create 15 8.0 0.001 0.001 10.612 10.626 calculate_dispersion_nonloc 15 9.0 0.960 1.581 8.663 8.682 cp_fm_diag_elpa 15 7.0 0.000 0.000 8.594 8.597 cp_fm_diag_elpa_base 15 8.0 8.434 8.441 8.591 8.593 pw_transfer 1191 10.0 0.086 0.093 8.161 8.238 fft_wrap_pw1pw2 1086 11.0 0.014 0.015 7.968 8.053 fft3d_ps 1086 13.0 2.761 3.081 6.153 6.277 fft_wrap_pw1pw2_150 765 12.0 0.331 0.351 5.399 5.450 mp_alltoall_z22v 1086 15.0 2.728 3.123 2.728 3.123 cp_fm_cholesky_restore 45 7.0 3.068 3.113 3.068 3.113 qs_energies_init_hamiltonians 1 3.0 0.000 0.001 2.595 2.595 fft_wrap_pw1pw2_200 197 12.3 0.218 0.240 2.455 2.515 build_core_hamiltonian_matrix 1 4.0 0.000 0.000 2.279 2.468 yz_to_x 501 13.9 0.279 0.374 2.028 2.246 rs_pw_transfer 158 9.4 0.002 0.002 1.701 2.102 xc_vxc_pw_create 15 9.0 0.016 0.020 1.948 1.974 density_rs2pw 16 7.0 0.001 0.001 1.612 1.849 mp_waitany 520 11.3 1.113 1.740 1.113 1.740 rs_pw_transfer_RS2PW_200 18 8.8 0.041 0.048 0.796 1.622 init_scf_run 1 3.0 0.000 0.000 1.528 1.528 vdW_energy 15 10.0 1.408 1.494 1.408 1.494 x_to_yz 585 14.1 0.359 0.378 1.338 1.468 scf_env_initial_rho_setup 1 4.0 0.000 0.001 1.449 1.449 build_core_ppnl 1 5.0 1.317 1.442 1.317 1.442 xc_pw_derive 90 11.0 0.001 0.002 1.324 1.407 ------------------------------------------------------------------------------- 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=56.166, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=112.18, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=28.029, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=20.532, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="fft3d_s", label="fft3d_s", y=10.138, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=9.808, 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=16.34199999999999, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=8.434, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=20.218, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.605, 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=3.068, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=2.761, 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 0.076 0.076 274.715 274.715 qs_energies 1 2.0 0.000 0.000 274.562 274.562 ls_scf 1 3.0 0.000 0.000 273.205 273.205 ls_scf_main 1 4.0 0.002 0.002 258.001 258.001 density_matrix_trs4 11 5.0 0.016 0.016 171.661 171.661 dbcsr_multiply_generic 185 6.1 0.752 0.752 99.333 99.333 ls_scf_dm_to_ks 11 5.0 0.000 0.000 80.941 80.941 matrix_ls_to_qs 11 6.0 0.000 0.000 77.652 77.652 arnoldi_extremal 12 6.1 0.000 0.000 67.433 67.433 arnoldi_normal_ev 12 7.1 0.020 0.020 67.432 67.432 build_subspace 23 8.1 0.079 0.079 66.501 66.501 multiply_cannon 185 7.1 2.994 2.994 65.791 65.791 multiply_cannon_loop 185 8.1 0.425 0.425 49.572 49.572 multiply_cannon_multrec 185 9.1 47.456 47.456 47.506 47.506 dbcsr_complete_redistribute 23 7.5 30.532 30.532 41.406 41.406 dbcsr_copy_into_existing 11 7.0 40.031 40.031 40.031 40.031 matrix_decluster 11 7.0 0.000 0.000 37.620 37.620 dbcsr_matrix_vector_mult 652 9.0 0.199 0.199 33.851 33.851 make_m2s 370 7.1 0.041 0.041 27.874 27.874 make_images 370 8.1 11.447 11.447 25.603 25.603 dbcsr_matrix_vector_mult_local 652 10.0 24.205 24.205 24.211 24.211 DGKS_ortho_d 702 9.1 16.561 16.561 16.566 16.566 dbcsr_finalize 646 7.5 0.276 0.276 15.980 15.980 Gram_Schmidt_ortho_d 702 9.1 14.577 14.577 14.580 14.580 ls_scf_init_scf 1 4.0 0.000 0.000 14.335 14.335 dbcsr_merge_all 597 8.5 2.481 2.481 14.039 14.039 ls_scf_init_matrix_S 1 5.0 0.000 0.000 13.998 13.998 matrix_sqrt_Newton_Schulz 1 6.0 0.001 0.001 13.173 13.173 setup_rec_index_2d 370 8.1 13.068 13.068 13.068 13.068 dbcsr_sort_indices 1103 9.9 10.634 10.634 10.634 10.634 tree_to_linear_d 110 9.4 9.949 9.949 9.949 9.949 quick_finalize 395 10.0 0.374 0.374 9.267 9.267 dbcsr_special_finalize 370 9.1 0.002 0.002 8.551 8.551 create_fast_row_vec_access 776 10.2 0.002 0.002 5.758 5.758 create_fast_row_vec_access_d 776 11.2 5.751 5.751 5.756 5.756 matrix_qs_to_ls 12 5.1 0.000 0.000 5.594 5.594 matrix_cluster 12 6.1 0.000 0.000 5.594 5.594 ------------------------------------------------------------------------------- From /workspace/artifacts/bench_dftb_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.008 0.011 70.163 70.164 qs_energies 1 2.0 0.000 0.000 70.083 70.083 ls_scf 1 3.0 0.000 0.000 70.001 70.004 ls_scf_main 1 4.0 0.000 0.002 67.180 67.180 density_matrix_trs4 11 5.0 0.006 0.010 64.494 64.531 dbcsr_multiply_generic 185 6.1 0.060 0.071 61.449 61.591 multiply_cannon 185 7.1 0.034 0.036 52.178 52.887 multiply_cannon_loop 185 8.1 0.138 0.153 49.566 50.669 multiply_cannon_multrec 1480 9.1 29.774 31.897 30.092 32.224 mp_waitall_1 11936 10.3 16.806 18.804 16.806 18.804 multiply_cannon_metrocomm3 1480 9.1 0.017 0.019 10.276 13.579 make_m2s 370 7.1 0.035 0.037 7.021 7.065 make_images 370 8.1 0.647 0.735 6.889 6.934 calculate_norms 2960 9.1 5.247 6.584 5.247 6.584 multiply_cannon_metrocomm1 1480 9.1 0.009 0.013 3.751 4.948 make_images_data 370 9.1 0.010 0.012 3.043 3.256 hybrid_alltoall_any 393 9.9 0.205 1.066 2.692 2.927 arnoldi_extremal 12 6.1 0.000 0.000 2.691 2.709 arnoldi_normal_ev 12 7.1 0.001 0.004 2.691 2.709 build_subspace 23 8.1 0.022 0.028 2.592 2.595 ls_scf_dm_to_ks 11 5.0 0.000 0.000 2.332 2.392 dbcsr_matrix_vector_mult 652 9.0 0.010 0.046 2.051 2.296 ls_scf_init_scf 1 4.0 0.000 0.000 2.155 2.158 dbcsr_complete_redistribute 23 7.5 1.211 1.631 1.948 2.142 ls_scf_init_matrix_S 1 5.0 0.000 0.000 2.128 2.133 matrix_ls_to_qs 11 6.0 0.000 0.000 1.876 2.097 dbcsr_matrix_vector_mult_local 652 10.0 1.684 2.039 1.686 2.042 matrix_sqrt_Newton_Schulz 1 6.0 0.001 0.001 1.936 1.940 matrix_decluster 11 7.0 0.000 0.000 1.743 1.919 make_images_pack 370 9.1 1.736 1.902 1.739 1.905 mp_sum_l 1119 5.6 1.306 1.814 1.306 1.814 buffer_matrices_ensure_size 370 8.1 1.546 1.675 1.546 1.675 dbcsr_finalize 646 7.5 0.008 0.010 1.374 1.544 ------------------------------------------------------------------------------- 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=115.92999999999998, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=47.456, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_copy_into_existing", label="dbcsr_copy_into_existing", y=40.031, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_complete_redistribute", label="dbcsr_complete_redistribute", y=30.532, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=24.205, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="DGKS_ortho_d", label="DGKS_ortho_d", y=16.561, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="calculate_norms", label="calculate_norms", y=0.0, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="make_images_pack", label="make_images_pack", 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=13.704999999999998, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=29.774, 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=1.211, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=1.684, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="DGKS_ortho_d", label="DGKS_ortho_d", y=0.0, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="calculate_norms", label="calculate_norms", y=5.247, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="make_images_pack", label="make_images_pack", y=1.736, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=16.806, 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 0.009 0.009 72.950 72.950 lib_test 1 2.0 0.000 0.000 72.940 72.940 dbcsr_run_tests 3 3.0 0.002 0.002 72.940 72.940 test_multiplies_multiproc 3 4.0 0.002 0.002 57.117 57.117 dbcsr_redistribute 9 5.0 30.644 30.644 32.138 32.138 dbcsr_multiply_generic 9 5.0 0.001 0.001 23.314 23.314 multiply_cannon 9 6.0 0.001 0.001 18.568 18.568 multiply_cannon_loop 9 7.0 0.018 0.018 18.200 18.200 multiply_cannon_multrec 9 8.0 18.181 18.181 18.182 18.182 dbcsr_make_random_matrix 9 4.0 12.827 12.827 15.729 15.729 dbcsr_finalize 27 5.7 0.003 0.003 5.337 5.337 dbcsr_merge_all 18 6.5 1.847 1.847 4.574 4.574 dbcsr_data_release 975 7.6 2.639 2.639 2.639 2.639 tree_to_linear_d 9 7.0 1.899 1.899 1.899 1.899 make_m2s 18 6.0 0.001 0.001 1.752 1.752 make_images 18 7.0 0.599 0.599 1.693 1.693 ------------------------------------------------------------------------------- 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 0.002 0.004 17.659 17.659 lib_test 1 2.0 0.000 0.000 17.641 17.652 dbcsr_run_tests 3 3.0 0.001 0.001 17.639 17.651 test_multiplies_multiproc 3 4.0 0.000 0.001 16.754 16.839 dbcsr_multiply_generic 9 5.0 0.001 0.001 15.635 15.683 multiply_cannon 9 6.0 0.001 0.002 14.079 14.443 multiply_cannon_loop 9 7.0 0.002 0.002 13.790 14.124 multiply_cannon_multrec 72 8.0 11.514 11.918 11.514 11.919 mp_waitall_1 576 9.2 2.611 3.212 2.611 3.212 multiply_cannon_metrocomm1 72 8.0 0.001 0.001 1.960 2.401 dbcsr_make_random_matrix 9 4.0 0.709 0.751 0.864 0.929 mp_sum_l 390 2.5 0.399 0.844 0.399 0.844 dbcsr_multiply_generic_mpsum_f 9 6.0 0.000 0.000 0.395 0.839 make_m2s 18 6.0 0.001 0.001 0.720 0.757 make_images 18 7.0 0.021 0.022 0.716 0.754 multiply_cannon_metrocomm3 72 8.0 0.000 0.000 0.308 0.736 dbcsr_finalize 27 5.7 0.000 0.000 0.520 0.575 dbcsr_redistribute 9 5.0 0.251 0.298 0.479 0.507 dbcsr_merge_all 18 6.5 0.083 0.093 0.456 0.500 make_images_data 18 8.0 0.001 0.001 0.379 0.450 hybrid_alltoall_any 18 9.0 0.032 0.141 0.339 0.395 dbcsr_data_release 444 7.6 0.310 0.369 0.310 0.369 ------------------------------------------------------------------------------- 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=6.760000000000005, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_redistribute", label="dbcsr_redistribute", y=30.644, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=18.181, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=12.827, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_data_release", label="dbcsr_data_release", y=2.639, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="tree_to_linear_d", label="tree_to_linear_d", y=1.899, 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=1.8649999999999984, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_redistribute", label="dbcsr_redistribute", y=0.251, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=11.514, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=0.709, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_data_release", label="dbcsr_data_release", y=0.31, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="tree_to_linear_d", label="tree_to_linear_d", y=0.0, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=2.611, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=0.399, 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 0.048 0.048 154.298 154.298 qs_mol_dyn_low 1 2.0 0.005 0.005 152.771 152.771 velocity_verlet 5 3.0 0.004 0.004 125.055 125.055 qmmm_el_coupling 6 3.8 0.000 0.000 88.922 88.922 qmmm_elec_with_gaussian 6 4.8 0.097 0.097 88.918 88.918 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 88.141 88.141 qmmm_elec_gaussian_low_G 6 6.8 86.985 86.985 86.985 86.985 qs_forces 6 3.8 0.001 0.001 49.456 49.456 qs_energies 6 4.8 0.000 0.000 44.783 44.783 scf_env_do_scf 6 5.8 0.001 0.001 40.796 40.796 scf_env_do_scf_inner_loop 39 6.8 0.005 0.005 28.991 28.991 rebuild_ks_matrix 45 8.4 0.000 0.000 26.836 26.836 qs_ks_build_kohn_sham_matrix 45 9.4 0.006 0.006 26.836 26.836 qs_ks_update_qs_env 45 7.8 0.000 0.000 22.737 22.737 pw_transfer 966 12.3 0.058 0.058 17.912 17.912 fft_wrap_pw1pw2 801 13.6 0.007 0.007 17.610 17.610 fft_wrap_pw1pw2_150 507 15.2 2.374 2.374 17.192 17.192 qs_vxc_create 45 10.4 0.001 0.001 14.506 14.506 xc_vxc_pw_create 45 11.4 0.670 0.670 14.505 14.505 init_scf_loop 6 6.8 0.000 0.000 11.800 11.800 xc_pw_derive 270 13.4 0.003 0.003 9.996 9.996 qs_rho_update_rho 45 7.9 0.000 0.000 9.074 9.074 calculate_rho_elec 45 8.9 0.565 0.565 9.074 9.074 qmmm_forces 6 3.8 0.001 0.001 8.662 8.662 qmmm_forces_with_gaussian 6 4.8 0.101 0.101 8.328 8.328 prepare_preconditioner 6 7.8 0.000 0.000 8.167 8.167 make_preconditioner 6 8.8 0.000 0.000 7.832 7.832 fft3d_s 802 15.6 7.794 7.794 7.802 7.802 xc_rho_set_and_dset_create 45 12.4 0.774 0.774 7.561 7.561 make_full_all 6 9.8 0.001 0.001 7.481 7.481 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 7.420 7.420 qmmm_forces_gaussian_low_G 6 6.8 6.241 6.241 6.241 6.241 xc_pw_divergence 45 12.4 0.001 0.001 6.170 6.170 pw_scatter_s 429 15.8 5.724 5.724 5.724 5.724 fist_calc_energy_force 6 3.8 0.001 0.001 5.110 5.110 grid_collocate_task_list 45 9.9 5.067 5.067 5.067 5.067 qs_ks_ddapc 45 10.4 0.001 0.001 4.481 4.481 pw_integral_ab 2539 7.4 4.306 4.306 4.306 4.306 force_nonbond 6 4.8 4.149 4.149 4.149 4.149 cp_fm_diag_elpa 18 11.2 0.000 0.000 4.115 4.115 cp_fm_diag_elpa_base 18 12.2 4.107 4.107 4.115 4.115 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 4.107 4.107 sum_up_and_integrate 45 10.4 0.138 0.138 3.775 3.775 integrate_v_rspace 45 11.4 0.008 0.008 3.637 3.637 density_rs2pw 45 9.9 0.002 0.002 3.442 3.442 ------------------------------------------------------------------------------- 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 0.019 0.021 63.055 63.056 qs_mol_dyn_low 1 2.0 0.003 0.003 61.765 61.827 qs_forces 6 3.8 0.001 0.001 44.272 44.272 qs_energies 6 4.8 0.000 0.001 42.150 42.150 scf_env_do_scf 6 5.8 0.000 0.000 41.063 41.063 scf_env_do_scf_inner_loop 113 6.2 0.002 0.006 39.374 39.375 rebuild_ks_matrix 119 8.1 0.000 0.000 29.514 29.524 qs_ks_build_kohn_sham_matrix 119 9.1 0.016 0.020 29.514 29.523 qs_ks_update_qs_env 119 7.3 0.001 0.001 27.718 27.727 velocity_verlet 5 3.0 0.002 0.002 26.843 26.847 pw_transfer 2446 12.3 0.174 0.188 18.680 18.934 fft_wrap_pw1pw2 2059 13.4 0.023 0.026 18.237 18.476 fft_wrap_pw1pw2_150 1321 14.9 1.559 1.709 17.580 17.781 qs_vxc_create 119 10.1 0.002 0.003 14.844 14.846 xc_vxc_pw_create 119 11.1 0.159 0.200 14.842 14.844 fft3d_ps 2059 15.4 7.539 8.093 13.542 14.063 qs_rho_update_rho 119 7.3 0.001 0.001 11.838 11.839 calculate_rho_elec 119 8.3 0.049 0.055 11.837 11.838 xc_pw_derive 714 13.1 0.009 0.011 11.259 11.544 sum_up_and_integrate 119 10.1 0.063 0.075 10.973 11.044 integrate_v_rspace 119 11.1 0.003 0.005 10.910 10.990 qmmm_forces 6 3.8 0.002 0.002 8.898 8.898 rs_pw_transfer 988 11.5 0.012 0.017 8.560 8.894 qmmm_forces_with_gaussian 6 4.8 0.327 0.354 8.228 8.802 xc_rho_set_and_dset_create 119 12.1 0.370 0.730 7.072 8.123 qmmm_el_coupling 6 3.8 0.000 0.000 7.646 7.760 qmmm_elec_with_gaussian 6 4.8 0.323 0.380 7.645 7.759 xc_pw_divergence 119 12.1 0.005 0.005 7.400 7.606 density_rs2pw 119 9.3 0.006 0.008 6.970 7.305 potential_pw2rs 119 12.1 0.006 0.009 6.650 6.667 grid_collocate_task_list 119 9.3 4.716 5.017 4.716 5.017 mp_alltoall_z22v 2059 17.4 4.426 4.953 4.426 4.953 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 4.216 4.451 grid_integrate_task_list 119 12.1 3.595 4.297 3.595 4.297 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 3.589 3.850 qmmm_forces_gaussian_low_G 6 6.8 3.467 3.708 3.467 3.708 x_to_yz 1095 16.8 0.876 1.090 3.137 3.496 rs_pw_transfer_PW2RS_150 125 13.9 1.529 1.621 3.421 3.457 mp_waitany 4028 12.8 2.850 3.378 2.850 3.378 pw_restrict_s3 18 5.8 1.517 1.805 2.958 3.266 qmmm_elec_gaussian_low_G 6 6.8 2.980 3.235 2.980 3.235 yz_to_x 964 16.0 0.653 0.960 2.817 3.193 rs_pw_transfer_RS2PW_150 125 11.2 1.049 1.204 2.629 2.949 qmmm_elec_with_gaussian:spline 6 5.8 0.000 0.000 2.473 2.620 pw_prolongate_s3 18 6.8 1.277 1.479 2.473 2.620 mp_waitall_1 188862 16.2 2.155 2.291 2.155 2.291 dbcsr_multiply_generic 2588 12.3 0.057 0.070 1.837 2.266 qs_ks_ddapc 119 10.1 0.002 0.002 2.002 2.081 qs_scf_new_mos 113 7.2 0.000 0.000 1.964 1.969 qs_scf_loop_do_ot 113 8.2 0.000 0.000 1.963 1.969 mp_sum_dm3 33 5.7 1.866 1.964 1.866 1.964 ot_scf_mini 113 9.2 0.001 0.001 1.877 1.882 pw_gather_p 964 15.0 1.465 1.808 1.465 1.808 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 1.803 1.804 pw_integral_ab 2761 7.7 1.368 1.423 1.610 1.702 init_scf_loop 6 6.8 0.000 0.000 1.686 1.686 pw_scatter_p 1095 15.8 1.617 1.647 1.617 1.647 xc_functional_eval 238 13.1 0.003 0.004 0.752 1.405 rs_pw_transfer_PW2RS_40 119 14.1 0.284 0.304 1.271 1.331 ------------------------------------------------------------------------------- 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=42.486999999999995, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=86.985, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_s", label="fft3d_s", y=7.794, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=6.241, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_scatter_s", label="pw_scatter_s", y=5.724, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=5.067, 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="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 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=36.332, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=2.98, 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="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.467, 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="grid_collocate_task_list", label="grid_collocate_task_list", y=4.716, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=4.426, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=7.539, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=3.595, yerr=0.0 Summary: Performance test took 49 minutes. Status: OK Removing intermediate container f8fd4b02bf25 ---> 9995c0b2fa57 Step 41/41 : CMD cat $(find ./report.log -mmin +10) | sed '/^Summary:/ s/$/ (cached)/' ---> Running in 2bdaa3a4741f Removing intermediate container 2bdaa3a4741f ---> 726d61abbb28 [Warning] One or more build-args [GIT_COMMIT_SHA] were not consumed Successfully built 726d61abbb28 Successfully tagged gcr.io/cp2k-org-project/img_cp2k-perf-openmp-arch-668:master Pushing new image... done. #################### Running Image cp2k-perf-openmp #################### Uploading artifacts... done EndDate: 2022-04-06 20:14:05+00:00