StartDate: 2024-02-14 08:04:52+00:00 CpuId: 32x AMD EPYC (3rd Gen) (Milan) [Zen 3], 7nm (SMT disabled) CommitSHA: 7eeddba65004ce63710e802b2136684b4a3d7a4d CommitTime: 2024-02-13 15:06:01 +0100 CommitAuthor: Frederick Stein CommitSubject: Fix branches to calculate dot products of grids #################### Building Image cp2k-perf-openmp #################### Dockerfile: /tools/docker/Dockerfile.test_performance Build-Path: / Build-Args: GIT_COMMIT_SHA=7eeddba65004ce63710e802b2136684b4a3d7a4d 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 393.6MB Step 1/42 : FROM ubuntu:22.04 22.04: Pulling from library/ubuntu 57c139bbda7e: Pulling fs layer 57c139bbda7e: Download complete 57c139bbda7e: Pull complete Digest: sha256:e9569c25505f33ff72e88b2990887c9dcf230f23259da296eb814fc2b41af999 Status: Downloaded newer image for ubuntu:22.04 ---> fd1d8f58e8ae Step 2/42 : WORKDIR /opt/cp2k-toolchain ---> Using cache ---> 2ca4dd565bb6 Step 3/42 : COPY ./tools/toolchain/install_requirements*.sh ./ ---> Using cache ---> 78840181f2fc Step 4/42 : RUN ./install_requirements.sh ubuntu:22.04 ---> Using cache ---> 4405fd4fd88a Step 5/42 : RUN mkdir scripts ---> Using cache ---> 84eb17de1839 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 ---> 4c00242fd761 Step 7/42 : COPY ./tools/toolchain/install_cp2k_toolchain.sh . ---> Using cache ---> f452716d8b52 Step 8/42 : RUN ./install_cp2k_toolchain.sh --install-all --with-gcc=system --dry-run ---> Using cache ---> 1f3099229067 Step 9/42 : COPY ./tools/toolchain/scripts/stage0/ ./scripts/stage0/ ---> Using cache ---> 1c5bc6fd8849 Step 10/42 : RUN ./scripts/stage0/install_stage0.sh && rm -rf ./build ---> Using cache ---> 58d7352320cf Step 11/42 : COPY ./tools/toolchain/scripts/stage1/ ./scripts/stage1/ ---> Using cache ---> 4b99a3051d37 Step 12/42 : RUN ./scripts/stage1/install_stage1.sh && rm -rf ./build ---> Using cache ---> f39100e41012 Step 13/42 : COPY ./tools/toolchain/scripts/stage2/ ./scripts/stage2/ ---> Using cache ---> b16ace3ade6c Step 14/42 : RUN ./scripts/stage2/install_stage2.sh && rm -rf ./build ---> Using cache ---> 63241ee271b3 Step 15/42 : COPY ./tools/toolchain/scripts/stage3/ ./scripts/stage3/ ---> Using cache ---> daffb7eaf645 Step 16/42 : RUN ./scripts/stage3/install_stage3.sh && rm -rf ./build ---> Using cache ---> e34aecdf98dd Step 17/42 : COPY ./tools/toolchain/scripts/stage4/ ./scripts/stage4/ ---> Using cache ---> 84bd59c71ca4 Step 18/42 : RUN ./scripts/stage4/install_stage4.sh && rm -rf ./build ---> Using cache ---> c0b2798304dd Step 19/42 : COPY ./tools/toolchain/scripts/stage5/ ./scripts/stage5/ ---> Using cache ---> cd1be9963d0a Step 20/42 : RUN ./scripts/stage5/install_stage5.sh && rm -rf ./build ---> Using cache ---> 8512dc6791ab Step 21/42 : COPY ./tools/toolchain/scripts/stage6/ ./scripts/stage6/ ---> Using cache ---> 993eb40cf086 Step 22/42 : RUN ./scripts/stage6/install_stage6.sh && rm -rf ./build ---> Using cache ---> 2548bbd11dc8 Step 23/42 : COPY ./tools/toolchain/scripts/stage7/ ./scripts/stage7/ ---> Using cache ---> 32ed5197df0c Step 24/42 : RUN ./scripts/stage7/install_stage7.sh && rm -rf ./build ---> Using cache ---> 86321fcdf3ea Step 25/42 : COPY ./tools/toolchain/scripts/stage8/ ./scripts/stage8/ ---> Using cache ---> 64ebb08e7776 Step 26/42 : RUN ./scripts/stage8/install_stage8.sh && rm -rf ./build ---> Using cache ---> bfd32597144b Step 27/42 : COPY ./tools/toolchain/scripts/arch_base.tmpl ./tools/toolchain/scripts/generate_arch_files.sh ./scripts/ ---> Using cache ---> b4e916f73410 Step 28/42 : RUN ./scripts/generate_arch_files.sh && rm -rf ./build ---> Using cache ---> c509af6864d5 Step 29/42 : WORKDIR /opt/cp2k ---> Using cache ---> 1423553c5074 Step 30/42 : COPY ./Makefile . ---> Using cache ---> 76f30729ae95 Step 31/42 : COPY ./src ./src ---> Using cache ---> 254a0b2dc457 Step 32/42 : COPY ./exts ./exts ---> Using cache ---> 51c1deeb7501 Step 33/42 : COPY ./tools/build_utils ./tools/build_utils ---> Using cache ---> 2085e389472d Step 34/42 : RUN /bin/bash -c " mkdir -p arch && ln -vs /opt/cp2k-toolchain/install/arch/local.psmp ./arch/" ---> Running in a01f059c50e2 './arch/local.psmp' -> '/opt/cp2k-toolchain/install/arch/local.psmp' Removing intermediate container a01f059c50e2 ---> 81119a8363ab Step 35/42 : COPY ./data ./data ---> 2f8e0c87a893 Step 36/42 : COPY ./tests ./tests ---> 0452fd783108 Step 37/42 : COPY ./tools/regtesting ./tools/regtesting ---> 19171586a4ac Step 38/42 : COPY ./benchmarks ./benchmarks ---> abcc500d69b6 Step 39/42 : COPY ./tools/docker/scripts/test_performance.sh ./tools/docker/scripts/plot_performance.py ./ ---> 6f0d190ccb34 Step 40/42 : RUN ./test_performance.sh "local" 2>&1 | tee report.log ---> Running in f4761db22d98 ========== 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 0.031 0.031 93.845 93.845 qs_mol_dyn_low 1 2.0 0.003 0.003 93.267 93.267 qs_forces 11 3.9 0.001 0.001 93.225 93.225 qs_energies 11 4.9 0.001 0.001 86.766 86.766 scf_env_do_scf 11 5.9 0.002 0.002 75.291 75.291 velocity_verlet 10 3.0 0.002 0.002 60.293 60.293 scf_env_do_scf_inner_loop 108 6.5 0.013 0.013 58.119 58.119 dbcsr_multiply_generic 2286 12.5 0.164 0.164 21.980 21.980 qs_scf_new_mos 108 7.5 0.001 0.001 21.924 21.924 qs_scf_loop_do_ot 108 8.5 0.001 0.001 21.923 21.923 rebuild_ks_matrix 119 8.3 0.001 0.001 21.151 21.151 qs_ks_build_kohn_sham_matrix 119 9.3 0.014 0.014 21.151 21.151 qs_rho_update_rho_low 119 7.7 0.001 0.001 20.924 20.924 calculate_rho_elec 119 8.7 0.967 0.967 20.923 20.923 ot_scf_mini 108 9.5 0.002 0.002 20.489 20.489 qs_ks_update_qs_env 119 7.6 0.001 0.001 19.352 19.352 init_scf_loop 11 6.9 0.000 0.000 17.046 17.046 grid_collocate_task_list 119 9.7 16.073 16.073 16.073 16.073 prepare_preconditioner 11 7.9 0.000 0.000 14.459 14.459 make_preconditioner 11 8.9 0.000 0.000 14.459 14.459 sum_up_and_integrate 119 10.3 0.001 0.001 13.485 13.485 integrate_v_rspace 119 11.3 0.092 0.092 13.419 13.419 make_full_inverse_cholesky 11 9.9 0.014 0.014 13.129 13.129 ot_mini 108 10.5 0.001 0.001 13.075 13.075 make_m2s 4572 13.5 0.046 0.046 11.309 11.309 grid_integrate_task_list 119 12.3 10.984 10.984 10.984 10.984 qs_ot_get_derivative 108 11.5 0.001 0.001 7.007 7.007 fft_wrap_pw1pw2 1201 11.6 0.010 0.010 6.881 6.881 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 6.632 6.632 multiply_cannon 2286 13.5 0.189 0.189 6.609 6.609 multiply_cannon_loop 2286 14.5 0.046 0.046 6.119 6.119 multiply_cannon_multrec 2286 15.5 6.023 6.023 6.071 6.071 ot_diis_step 108 11.5 0.004 0.004 6.065 6.065 make_images 4572 14.5 2.313 2.313 5.866 5.866 dbcsr_make_dense_low 5837 15.5 0.078 0.078 5.802 5.802 fft_wrap_pw1pw2_140 487 12.2 1.064 1.064 5.796 5.796 make_dense_data 5837 16.5 5.164 5.164 5.710 5.710 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 5.582 5.582 apply_single 119 13.6 0.000 0.000 5.582 5.582 dbcsr_make_images_dense 3978 14.8 0.017 0.017 5.090 5.090 cp_fm_cholesky_decompose 22 10.9 4.551 4.551 4.551 4.551 cp_fm_cholesky_invert 11 10.9 4.423 4.423 4.423 4.423 init_scf_run 11 5.9 0.003 0.003 4.203 4.203 scf_env_initial_rho_setup 11 6.9 0.001 0.001 4.200 4.200 dbcsr_complete_redistribute 329 12.2 1.953 1.953 3.898 3.898 density_rs2pw 119 9.7 0.004 0.004 3.883 3.883 qs_env_update_s_mstruct 11 6.9 0.000 0.000 3.717 3.717 wfi_extrapolate 11 7.9 0.001 0.001 3.701 3.701 build_core_hamiltonian_matrix_ 11 4.9 0.001 0.001 3.688 3.688 qs_ot_get_p 119 10.4 0.001 0.001 3.640 3.640 dbcsr_copy 2102 12.0 0.234 0.234 3.574 3.574 dbcsr_copy_into_existing 22 7.9 3.300 3.300 3.301 3.301 qs_create_task_list 11 7.9 0.000 0.000 3.236 3.236 generate_qs_task_list 11 8.9 1.956 1.956 3.236 3.236 copy_dbcsr_to_fm 153 11.3 0.002 0.002 3.029 3.029 fft3d_s 1202 13.6 2.972 2.972 2.978 2.978 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 2.769 2.769 build_core_hamiltonian_matrix 11 6.9 0.001 0.001 2.505 2.505 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.377 2.377 potential_pw2rs 119 12.3 0.049 0.049 2.343 2.343 dbcsr_data_release 279532 16.0 2.212 2.212 2.212 2.212 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 2.206 2.206 qs_ot_get_derivative_taylor 59 13.0 0.001 0.001 2.176 2.176 pw_poisson_solve 119 10.3 0.002 0.002 2.139 2.139 copy_fm_to_dbcsr 176 11.2 0.001 0.001 2.102 2.102 qs_ot_p2m_diag 50 11.0 0.155 0.155 2.059 2.059 dbcsr_finalize 5186 13.8 0.115 0.115 1.905 1.905 ------------------------------------------------------------------------------- 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 0.037 52.559 52.577 qs_mol_dyn_low 1 2.0 0.004 0.005 52.414 52.419 qs_forces 11 3.9 0.002 0.002 52.367 52.367 qs_energies 11 4.9 0.001 0.001 49.042 49.046 scf_env_do_scf 11 5.9 0.001 0.003 45.011 45.012 scf_env_do_scf_inner_loop 108 6.5 0.003 0.025 41.557 41.557 velocity_verlet 10 3.0 0.001 0.003 31.223 31.224 rebuild_ks_matrix 119 8.3 0.001 0.001 18.904 19.004 qs_ks_build_kohn_sham_matrix 119 9.3 0.018 0.020 18.903 19.003 qs_ks_update_qs_env 119 7.6 0.001 0.001 16.851 16.944 dbcsr_multiply_generic 2286 12.5 0.080 0.084 16.448 16.585 qs_rho_update_rho_low 119 7.7 0.001 0.001 14.529 14.542 calculate_rho_elec 119 8.7 0.031 0.033 14.529 14.541 sum_up_and_integrate 119 10.3 0.002 0.002 13.612 13.626 integrate_v_rspace 119 11.3 0.005 0.006 13.585 13.598 qs_scf_new_mos 108 7.5 0.001 0.001 13.193 13.276 qs_scf_loop_do_ot 108 8.5 0.001 0.001 13.193 13.275 ot_scf_mini 108 9.5 0.002 0.003 12.444 12.536 multiply_cannon 2286 13.5 0.151 0.173 12.123 12.395 multiply_cannon_loop 2286 14.5 0.109 0.119 11.407 11.743 grid_collocate_task_list 119 9.7 9.824 10.235 9.824 10.235 mp_waitall_1 158411 16.6 9.096 9.551 9.096 9.551 grid_integrate_task_list 119 12.3 8.844 9.065 8.844 9.065 ot_mini 108 10.5 0.001 0.001 7.313 7.412 multiply_cannon_metrocomm3 18288 15.5 0.050 0.056 6.971 7.324 density_rs2pw 119 9.7 0.006 0.006 4.220 4.557 multiply_cannon_multrec 18288 15.5 4.001 4.185 4.014 4.198 potential_pw2rs 119 12.3 0.007 0.008 3.964 3.981 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 3.744 3.846 apply_single 119 13.6 0.000 0.001 3.743 3.846 fft_wrap_pw1pw2 1201 11.6 0.019 0.023 3.781 3.835 qs_ot_get_derivative 108 11.5 0.001 0.001 3.600 3.693 ot_diis_step 108 11.5 0.003 0.004 3.686 3.686 init_scf_loop 11 6.9 0.000 0.001 3.434 3.435 fft_wrap_pw1pw2_140 487 12.2 0.178 0.183 3.163 3.215 make_m2s 4572 13.5 0.050 0.061 3.014 3.103 transfer_pw2rs 487 13.2 0.007 0.009 2.902 2.914 init_scf_run 11 5.9 0.000 0.006 2.825 2.829 scf_env_initial_rho_setup 11 6.9 0.000 0.005 2.825 2.828 fft3d_ps 1201 13.6 1.402 1.458 2.725 2.788 transfer_rs2pw 487 10.6 0.008 0.010 2.405 2.740 make_images 4572 14.5 0.125 0.134 2.642 2.729 wfi_extrapolate 11 7.9 0.001 0.001 2.559 2.559 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 2.231 2.244 mp_waitany 9880 13.7 1.835 2.200 1.835 2.200 qs_ot_get_p 119 10.4 0.001 0.001 1.666 1.812 transfer_rs2pw_140 130 11.5 0.236 0.266 1.368 1.703 make_images_data 4572 15.5 0.042 0.049 1.443 1.581 transfer_pw2rs_140 130 13.9 0.509 0.548 1.513 1.539 hybrid_alltoall_any 4725 16.4 0.079 0.255 1.296 1.468 mp_alltoall_d11v 2130 13.8 1.124 1.412 1.124 1.412 prepare_preconditioner 11 7.9 0.000 0.000 1.370 1.391 make_preconditioner 11 8.9 0.000 0.000 1.370 1.391 make_full_inverse_cholesky 11 9.9 0.000 0.000 1.239 1.257 qs_ot_get_derivative_taylor 59 13.0 0.001 0.001 1.126 1.184 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 1.093 1.138 cp_dbcsr_sm_fm_multiply 37 9.5 0.001 0.002 1.102 1.104 transfer_pw2rs_50 119 14.3 0.404 0.442 1.059 1.101 mp_sum_l 11298 13.2 0.796 1.082 0.796 1.082 rs_gather_matrices 119 12.3 0.082 0.094 0.729 1.068 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 0.965 1.068 mp_alltoall_z22v 1201 15.6 0.994 1.059 0.994 1.059 ------------------------------------------------------------------------------- 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=51.05, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=16.073, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=10.984, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=6.023, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="make_dense_data", label="make_dense_data", y=5.164, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=4.551, 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=18.958999999999996, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=9.824, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=8.844, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=4.001, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="make_dense_data", label="make_dense_data", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=9.096, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitany", label="mp_waitany", y=1.835, 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 0.032 116.330 116.330 qs_mol_dyn_low 1 2.0 0.003 0.003 115.679 115.679 qs_forces 11 3.9 0.001 0.001 115.638 115.638 qs_energies 11 4.9 0.001 0.001 107.916 107.916 scf_env_do_scf 11 5.9 0.002 0.002 94.492 94.492 scf_env_do_scf_inner_loop 96 6.5 0.011 0.011 75.839 75.839 velocity_verlet 10 3.0 0.002 0.002 74.520 74.520 rebuild_ks_matrix 107 8.3 0.001 0.001 34.187 34.187 qs_ks_build_kohn_sham_matrix 107 9.3 0.012 0.012 34.187 34.187 qs_rho_update_rho_low 107 7.7 0.001 0.001 32.896 32.896 calculate_rho_elec 107 8.7 0.867 0.867 32.896 32.896 qs_ks_update_qs_env 107 7.6 0.001 0.001 30.704 30.704 grid_collocate_task_list 107 9.7 28.685 28.685 28.685 28.685 sum_up_and_integrate 107 10.3 0.001 0.001 27.222 27.222 integrate_v_rspace 107 11.3 0.081 0.081 27.180 27.180 grid_integrate_task_list 107 12.3 25.048 25.048 25.048 25.048 dbcsr_multiply_generic 1966 12.4 0.139 0.139 19.428 19.428 qs_scf_new_mos 96 7.5 0.001 0.001 19.247 19.247 qs_scf_loop_do_ot 96 8.5 0.001 0.001 19.246 19.246 init_scf_loop 11 6.9 0.000 0.000 18.469 18.469 ot_scf_mini 96 9.5 0.002 0.002 18.002 18.002 prepare_preconditioner 11 7.9 0.000 0.000 14.332 14.332 make_preconditioner 11 8.9 0.000 0.000 14.332 14.332 make_full_inverse_cholesky 11 9.9 0.025 0.025 13.150 13.150 ot_mini 96 10.5 0.001 0.001 11.340 11.340 make_m2s 3932 13.4 0.040 0.040 10.179 10.179 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 6.953 6.953 fft_wrap_pw1pw2 1081 11.6 0.009 0.009 6.061 6.061 qs_ot_get_derivative 96 11.5 0.001 0.001 6.049 6.049 multiply_cannon 1966 13.4 0.159 0.159 5.857 5.857 init_scf_run 11 5.9 0.003 0.003 5.624 5.624 scf_env_initial_rho_setup 11 6.9 0.002 0.002 5.621 5.621 multiply_cannon_loop 1966 14.4 0.044 0.044 5.436 5.436 multiply_cannon_multrec 1966 15.4 5.346 5.346 5.391 5.391 ot_diis_step 96 11.5 0.003 0.003 5.287 5.287 dbcsr_make_dense_low 4961 15.5 0.092 0.092 5.273 5.273 make_images 3932 14.4 2.100 2.100 5.268 5.268 fft_wrap_pw1pw2_140 439 12.2 0.920 0.920 5.198 5.198 make_dense_data 4961 16.5 4.653 4.653 5.169 5.169 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 5.005 5.005 apply_single 107 13.6 0.000 0.000 5.005 5.005 wfi_extrapolate 11 7.9 0.001 0.001 4.990 4.990 cp_fm_cholesky_decompose 22 10.9 4.778 4.778 4.778 4.778 dbcsr_make_images_dense 3386 14.7 0.015 0.015 4.631 4.631 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 4.348 4.348 qs_env_update_s_mstruct 11 6.9 0.000 0.000 4.069 4.069 cp_fm_cholesky_invert 11 10.9 4.046 4.046 4.046 4.046 dbcsr_complete_redistribute 317 12.2 1.938 1.938 3.851 3.851 qs_create_task_list 11 7.9 0.000 0.000 3.682 3.682 generate_qs_task_list 11 8.9 2.386 2.386 3.682 3.682 dbcsr_copy 1855 11.9 0.208 0.208 3.411 3.411 qs_ot_get_p 107 10.4 0.001 0.001 3.386 3.386 build_core_hamiltonian_matrix_ 11 4.9 0.001 0.001 3.372 3.372 density_rs2pw 107 9.7 0.003 0.003 3.343 3.343 dbcsr_copy_into_existing 22 7.9 3.164 3.164 3.164 3.164 copy_dbcsr_to_fm 147 11.2 0.002 0.002 3.151 3.151 fft3d_s 1082 13.6 2.651 2.651 2.656 2.656 build_core_hamiltonian_matrix 11 6.9 0.001 0.001 2.468 2.468 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.425 2.425 ------------------------------------------------------------------------------- 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 0.029 76.795 76.807 qs_mol_dyn_low 1 2.0 0.003 0.005 76.662 76.666 qs_forces 11 3.9 0.002 0.002 76.619 76.619 qs_energies 11 4.9 0.001 0.001 71.582 71.584 scf_env_do_scf 11 5.9 0.000 0.002 66.232 66.236 scf_env_do_scf_inner_loop 96 6.5 0.003 0.020 61.228 61.228 velocity_verlet 10 3.0 0.001 0.003 45.479 45.481 rebuild_ks_matrix 107 8.3 0.000 0.001 32.472 32.546 qs_ks_build_kohn_sham_matrix 107 9.3 0.015 0.017 32.471 32.545 qs_ks_update_qs_env 107 7.6 0.001 0.001 28.595 28.662 sum_up_and_integrate 107 10.3 0.002 0.002 27.860 27.881 integrate_v_rspace 107 11.3 0.004 0.005 27.835 27.856 qs_rho_update_rho_low 107 7.7 0.001 0.001 27.185 27.195 calculate_rho_elec 107 8.7 0.028 0.029 27.185 27.195 grid_integrate_task_list 107 12.3 23.450 23.804 23.450 23.804 grid_collocate_task_list 107 9.7 22.960 23.349 22.960 23.349 dbcsr_multiply_generic 1966 12.4 0.068 0.074 14.406 14.555 qs_scf_new_mos 96 7.5 0.001 0.001 11.453 11.523 qs_scf_loop_do_ot 96 8.5 0.001 0.001 11.452 11.523 multiply_cannon 1966 13.4 0.131 0.145 10.762 11.066 ot_scf_mini 96 9.5 0.002 0.003 10.813 10.888 multiply_cannon_loop 1966 14.4 0.099 0.105 10.178 10.487 mp_waitall_1 136719 16.5 7.952 8.394 7.952 8.394 multiply_cannon_metrocomm3 15728 15.4 0.045 0.049 6.194 6.555 ot_mini 96 10.5 0.001 0.001 6.391 6.472 init_scf_loop 11 6.9 0.000 0.000 4.985 4.985 density_rs2pw 107 9.7 0.005 0.006 3.817 4.510 init_scf_run 11 5.9 0.000 0.005 4.206 4.206 scf_env_initial_rho_setup 11 6.9 0.000 0.004 4.205 4.206 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 4.021 4.029 wfi_extrapolate 11 7.9 0.001 0.001 3.827 3.827 multiply_cannon_multrec 15728 15.4 3.603 3.700 3.614 3.712 potential_pw2rs 107 12.3 0.006 0.007 3.411 3.425 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 3.283 3.389 apply_single 107 13.6 0.000 0.000 3.283 3.389 fft_wrap_pw1pw2 1081 11.6 0.016 0.019 3.301 3.345 qs_ot_get_derivative 96 11.5 0.001 0.001 3.154 3.231 ot_diis_step 96 11.5 0.003 0.003 3.220 3.220 transfer_rs2pw 439 10.6 0.006 0.007 2.220 2.920 fft_wrap_pw1pw2_140 439 12.2 0.146 0.153 2.785 2.845 make_m2s 3932 13.4 0.043 0.051 2.522 2.589 mp_waitany 8968 13.7 1.845 2.579 1.845 2.579 transfer_pw2rs 439 13.2 0.006 0.008 2.541 2.545 fft3d_ps 1081 13.6 1.206 1.289 2.397 2.466 make_images 3932 14.4 0.107 0.112 2.200 2.267 transfer_rs2pw_140 118 11.5 0.175 0.188 1.364 2.064 mp_alltoall_d11v 1998 13.7 1.289 2.015 1.289 2.015 rs_gather_matrices 107 12.3 0.068 0.078 0.929 1.636 qs_ot_get_p 107 10.4 0.001 0.001 1.463 1.602 ------------------------------------------------------------------------------- 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=47.82000000000001, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=28.685, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=25.048, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=5.346, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=4.778, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="make_dense_data", label="make_dense_data", y=4.653, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="mp_waitany", label="mp_waitany", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 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=16.985000000000007, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=22.96, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=23.45, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=3.603, 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="make_dense_data", label="make_dense_data", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitany", label="mp_waitany", y=1.845, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=7.952, 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 0.219 0.219 139.279 139.279 qs_energies 1 2.0 0.000 0.000 138.450 138.450 scf_env_do_scf 1 3.0 0.000 0.000 137.201 137.201 qs_ks_update_qs_env 8 5.0 0.000 0.000 132.188 132.188 rebuild_ks_matrix 7 6.0 0.000 0.000 132.131 132.131 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.001 132.131 132.131 hfx_ks_matrix 7 8.0 0.000 0.000 123.314 123.314 integrate_four_center 7 9.0 1.598 1.598 123.194 123.194 integrate_four_center_main 7 10.0 0.515 0.515 108.831 108.831 integrate_four_center_bin 463 11.0 108.316 108.316 108.316 108.316 scf_env_do_scf_inner_loop 7 4.0 0.001 0.001 77.626 77.626 init_scf_loop 1 4.0 0.000 0.000 59.565 59.565 integrate_four_center_load 7 10.0 0.001 0.001 12.465 12.465 hfx_load_balance 1 11.0 0.010 0.010 12.464 12.464 hfx_load_balance_bin 1 12.0 6.227 6.227 6.227 6.227 hfx_load_balance_count 1 12.0 6.210 6.210 6.210 6.210 qs_vxc_create 14 8.0 0.000 0.000 3.239 3.239 xc_vxc_pw_create 14 9.0 0.117 0.117 3.239 3.239 ------------------------------------------------------------------------------- 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 0.207 0.239 134.107 134.122 qs_energies 1 2.0 0.000 0.000 133.697 133.706 scf_env_do_scf 1 3.0 0.000 0.000 133.338 133.339 qs_ks_update_qs_env 8 5.0 0.000 0.000 131.066 131.067 rebuild_ks_matrix 7 6.0 0.000 0.000 131.057 131.058 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.001 131.057 131.058 hfx_ks_matrix 7 8.0 0.000 0.000 125.141 125.143 integrate_four_center 7 9.0 0.057 0.347 125.131 125.133 integrate_four_center_main 7 10.0 0.003 0.004 105.212 111.680 integrate_four_center_bin 448 11.0 105.209 111.677 105.209 111.677 scf_env_do_scf_inner_loop 7 4.0 0.000 0.001 79.607 79.607 init_scf_loop 1 4.0 0.000 0.000 53.729 53.730 mp_sync 56 11.2 6.753 13.306 6.753 13.306 integrate_four_center_load 7 10.0 0.000 0.000 12.476 12.477 hfx_load_balance 1 11.0 0.001 0.001 12.476 12.477 hfx_load_balance_count 1 12.0 6.161 6.279 6.161 6.279 hfx_load_balance_bin 1 12.0 6.163 6.240 6.163 6.240 ------------------------------------------------------------------------------- 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=16.194000000000003, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_bin", label="integrate_four_center_bin", y=108.316, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=6.227, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_count", label="hfx_load_balance_count", y=6.21, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center", label="integrate_four_center", y=1.598, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_main", label="integrate_four_center_main", y=0.515, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="CP2K", label="CP2K", y=0.219, 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=9.554000000000002, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center_bin", label="integrate_four_center_bin", y=105.209, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=6.163, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_count", label="hfx_load_balance_count", y=6.161, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center", label="integrate_four_center", y=0.057, 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=0.207, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="mp_sync", label="mp_sync", y=6.753, 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 82.304 82.304 qs_energies 1 2.0 0.000 0.000 81.927 81.927 mp2_main 1 3.0 0.000 0.000 79.030 79.030 mp2_gpw_main 1 4.0 0.000 0.000 78.923 78.923 rpa_ri_compute_en 1 5.0 0.000 0.000 75.225 75.225 rpa_num_int 1 6.0 0.001 0.001 75.219 75.219 compute_mat_P_omega 1 7.0 0.004 0.004 65.389 65.389 compute_mat_P_omega_contract 10 8.0 8.952 8.952 65.177 65.177 dbt_total 2336 9.6 0.015 0.015 51.347 51.347 dbt_contract 787 11.0 0.070 0.070 43.901 43.901 dbt_tas_total 1149 12.2 0.242 0.242 42.442 42.442 dbt_tas_multiply 807 12.1 0.002 0.002 41.110 41.110 dbt_tas_dbm 807 14.1 0.003 0.003 34.258 34.258 dbm_multiply 807 16.1 34.250 34.250 34.250 34.250 dbt_tas_mm_1N 524 15.1 0.001 0.001 26.790 26.790 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 25.280 25.280 compute_mat_P_omega_calc_M_occ 250 9.0 8.908 8.908 17.791 17.791 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 7.139 7.139 dbt_copy 1103 10.7 0.121 0.121 6.095 6.095 dbt_tas_mm_2 251 15.0 0.001 0.001 6.028 6.028 compute_QP_energies 1 7.0 0.000 0.000 5.087 5.087 compute_self_energy_cubic_gw 1 8.0 0.052 0.052 5.086 5.086 contract_cubic_gw 21 9.0 0.000 0.000 4.086 4.086 dbt_tas_reserve_blocks_index 3261 14.3 0.491 0.491 4.019 4.019 mp2_ri_gpw_compute_in 1 5.0 0.001 0.001 3.690 3.690 dbm_reserve_blocks 3628 15.3 3.603 3.603 3.603 3.603 dbt_reserve_blocks_index 2280 13.1 0.062 0.062 3.003 3.003 dbt_reserve_blocks_index_array 2222 12.2 0.009 0.009 2.949 2.949 scf_env_do_scf 1 3.0 0.000 0.000 2.784 2.784 scf_env_do_scf_inner_loop 17 4.0 0.002 0.002 2.784 2.784 dbt_crop 1042 12.0 1.557 1.557 2.656 2.656 dbt_tas_copy 574 11.4 1.364 1.364 2.491 2.491 convert_to_new_pgrid 2421 14.1 0.167 0.167 2.472 2.472 dbm_copy 1614 15.1 2.306 2.306 2.306 2.306 dbt_tas_reshape 367 15.0 0.019 0.019 2.088 2.088 dbt_reshape 278 11.9 1.145 1.145 2.036 2.036 compute_W_cubic_GW 10 7.0 0.003 0.003 1.980 1.980 rpa_num_int_RPA_matrix_operati 10 7.0 0.000 0.000 1.890 1.890 get_2c_integrals 1 6.0 0.000 0.000 1.746 1.746 compute_mat_P_omega_copy_M_occ 250 9.0 0.001 0.001 1.698 1.698 ------------------------------------------------------------------------------- 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 0.007 0.033 36.247 36.260 qs_energies 1 2.0 0.000 0.000 36.096 36.099 mp2_main 1 3.0 0.000 0.001 35.071 35.074 mp2_gpw_main 1 4.0 0.000 0.001 34.981 34.984 rpa_ri_compute_en 1 5.0 0.000 0.000 33.647 33.650 rpa_num_int 1 6.0 0.000 0.002 33.647 33.650 dbt_total 2336 9.6 0.016 0.017 29.621 29.637 compute_mat_P_omega 1 7.0 0.001 0.006 28.690 28.693 compute_mat_P_omega_contract 10 8.0 0.446 0.469 28.528 28.531 dbt_contract 787 11.0 0.041 0.042 21.803 21.810 dbt_tas_total 1149 12.2 0.084 0.091 19.261 19.270 dbt_tas_multiply 807 12.1 0.002 0.002 19.183 19.197 dbt_tas_dbm 807 14.1 0.003 0.003 14.004 14.011 dbm_multiply 807 16.1 11.315 12.205 11.315 12.205 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 8.293 8.294 compute_mat_P_omega_calc_M_occ 250 9.0 0.424 0.443 8.219 8.220 dbt_copy 1149 10.8 0.014 0.015 6.809 6.983 dbt_tas_mm_2 251 15.0 0.001 0.002 6.615 6.627 dbt_reshape 1136 11.8 2.841 3.029 6.444 6.617 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 6.005 6.018 mp_sync 8688 11.6 4.904 5.838 4.904 5.838 dbt_tas_mm_1N 524 15.1 0.001 0.002 5.132 5.539 compute_QP_energies 1 7.0 0.000 0.000 3.079 3.080 compute_self_energy_cubic_gw 1 8.0 0.003 0.004 3.077 3.078 mp_waitall_2 3812 15.3 2.658 2.880 2.658 2.880 dbt_communicate_buffer 1136 12.8 0.053 0.065 2.638 2.780 contract_cubic_gw 21 9.0 0.000 0.000 2.396 2.396 dbt_reserve_blocks_index 2887 13.1 0.080 0.086 1.963 2.123 dbt_reserve_blocks_index_array 2829 12.2 0.009 0.011 1.953 2.113 dbt_tas_reserve_blocks_index 3347 14.5 0.440 0.474 1.936 2.089 dbt_crop 1042 12.0 0.986 1.090 1.602 1.765 dbm_reserve_blocks 3752 15.4 1.598 1.731 1.598 1.731 mp2_ri_gpw_compute_in 1 5.0 0.003 0.004 1.321 1.321 compute_mat_P_omega_copy_M_vir 250 9.0 0.001 0.001 1.229 1.239 dbt_tas_replicate 405 14.1 0.558 0.726 1.176 1.234 parallel_gemm_fm 105 8.4 0.000 0.000 1.149 1.159 parallel_gemm_fm_cosma 105 9.4 1.148 1.159 1.148 1.159 compute_mat_P_omega_copy_M_occ 250 9.0 0.001 0.001 1.100 1.102 scf_env_do_scf 1 3.0 0.000 0.000 0.971 0.971 scf_env_do_scf_inner_loop 17 4.0 0.000 0.003 0.971 0.971 convert_to_new_pgrid 2421 14.1 0.028 0.034 0.900 0.969 dbm_copy 1608 15.1 0.866 0.937 0.866 0.937 mp_max_i 2009 9.8 0.652 0.876 0.652 0.876 compute_W_cubic_GW 10 7.0 0.001 0.001 0.861 0.870 ------------------------------------------------------------------------------- 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=23.14, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=34.25, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=8.952, 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=8.908, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=3.603, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_copy", label="dbm_copy", y=2.306, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=1.145, 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=11.195, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=11.315, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=0.446, 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=0.424, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=1.598, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_copy", label="dbm_copy", y=0.866, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=2.841, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.658, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_sync", label="mp_sync", y=4.904, 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 0.024 271.470 271.470 qs_forces 1 2.0 0.000 0.000 270.912 270.912 rebuild_ks_matrix 7 6.6 0.000 0.000 269.472 269.472 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.001 269.472 269.472 hfx_ks_matrix 7 8.6 0.000 0.000 267.349 267.349 hfx_ri_update_ks 7 9.6 0.000 0.000 226.139 226.139 hfx_ri_update_ks_Pmat 7 10.6 31.541 31.541 226.113 226.113 dbt_total 849 11.0 0.006 0.006 212.418 212.418 qs_energies 1 3.0 0.000 0.000 199.243 199.243 scf_env_do_scf 1 4.0 0.001 0.001 198.933 198.933 qs_ks_update_qs_env 8 6.0 0.000 0.000 197.852 197.852 dbt_contract 207 12.4 0.073 0.073 192.741 192.741 dbt_tas_total 369 13.4 1.467 1.467 191.781 191.781 dbt_tas_multiply 216 13.5 0.001 0.001 187.483 187.483 dbt_tas_dbm 216 15.5 0.001 0.001 176.053 176.053 dbm_multiply 216 17.5 176.050 176.050 176.050 176.050 hfx_ri_update_ks_Pmat_KS 63 11.6 0.001 0.001 170.584 170.584 dbt_tas_mm_2 91 16.5 0.001 0.001 162.003 162.003 scf_env_do_scf_inner_loop 6 5.0 0.001 0.001 126.877 126.877 init_scf_loop 2 5.0 0.000 0.000 72.054 72.054 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 71.624 71.624 hfx_ri_update_forces 1 7.0 1.618 1.618 41.036 41.036 hfx_ri_forces_Pmat_3c 1 8.0 4.698 4.698 23.752 23.752 dbt_copy 423 11.8 0.064 0.064 15.371 15.371 precalc_derivatives 1 8.0 2.209 2.209 13.327 13.327 dbt_reshape 132 13.2 6.552 6.552 10.617 10.617 dbt_tas_mm_3T 77 17.1 0.000 0.000 9.732 9.732 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 9.601 9.601 dbt_tas_reserve_blocks_index 1323 15.4 1.047 1.047 7.823 7.823 build_3c_derivatives 3 9.0 2.353 2.353 7.433 7.433 dbm_reserve_blocks 1491 16.2 7.038 7.038 7.038 7.038 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 6.611 6.611 dbt_reserve_blocks_index 846 14.4 0.101 0.101 6.088 6.088 dbt_reserve_blocks_index_array 816 13.5 0.007 0.007 5.983 5.983 ------------------------------------------------------------------------------- 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 50.311 50.323 qs_forces 1 2.0 0.000 0.000 50.098 50.098 rebuild_ks_matrix 7 6.6 0.000 0.000 49.286 49.287 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.002 49.286 49.287 hfx_ks_matrix 7 8.6 0.000 0.000 48.246 48.251 dbt_total 849 11.0 0.006 0.006 43.135 43.147 dbt_contract 207 12.4 0.026 0.026 33.330 33.342 dbt_tas_total 369 13.4 0.057 0.138 29.805 29.805 dbt_tas_multiply 216 13.5 0.001 0.001 29.342 29.343 hfx_ri_update_ks 7 9.6 0.000 0.000 27.966 27.966 hfx_ri_update_ks_Pmat 7 10.6 1.281 1.336 27.963 27.964 qs_energies 1 3.0 0.000 0.000 25.750 25.750 scf_env_do_scf 1 4.0 0.000 0.001 25.593 25.593 qs_ks_update_qs_env 8 6.0 0.000 0.000 24.950 24.951 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 24.338 24.338 dbt_tas_dbm 216 15.5 0.001 0.001 21.996 22.005 dbm_multiply 216 17.5 20.126 20.779 20.126 20.779 hfx_ri_update_forces 1 7.0 0.061 0.063 20.279 20.284 hfx_ri_forces_Pmat_3c 1 8.0 0.169 0.179 15.106 15.115 scf_env_do_scf_inner_loop 6 5.0 0.000 0.001 14.374 14.375 hfx_ri_update_ks_Pmat_KS 63 11.6 0.000 0.001 12.753 12.753 init_scf_loop 2 5.0 0.000 0.000 11.218 11.218 dbt_tas_mm_2 91 16.5 0.001 0.001 9.753 9.762 dbt_copy 539 12.5 0.012 0.014 8.896 9.107 dbt_reshape 393 13.9 3.573 3.664 6.717 6.874 dbt_tas_mm_3T 77 17.1 0.000 0.000 6.110 6.553 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 5.095 5.095 mp_sync 2901 12.8 4.228 5.043 4.228 5.043 dbt_tas_mm_3N 37 15.4 0.000 0.000 4.581 4.715 precalc_derivatives 1 8.0 0.089 0.100 3.924 3.924 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 3.514 3.514 dbt_tas_reserve_blocks_index 1471 15.8 0.894 0.923 3.214 3.430 mp_waitall_2 1318 16.2 2.916 3.052 2.916 3.052 dbt_reserve_blocks_index 1107 14.8 0.117 0.127 2.662 2.819 dbt_reserve_blocks_index_array 1077 13.9 0.006 0.006 2.634 2.796 dbm_reserve_blocks 1641 16.6 2.546 2.756 2.546 2.756 dbt_crop 372 13.7 1.753 1.798 2.544 2.644 build_3c_derivatives 3 9.0 0.225 0.243 2.110 2.114 dbt_communicate_buffer 393 14.9 0.013 0.014 2.016 2.112 hfx_ri_pre_scf_Pmat_RIx3C 9 13.0 0.000 0.000 1.857 1.861 dbt_tas_replicate 170 15.1 0.701 0.737 1.758 1.797 hfx_ri_update_ks_Pmat_copy_2 63 11.6 0.000 0.000 1.667 1.667 convert_to_new_pgrid 648 15.5 0.038 0.076 1.395 1.607 mp_sum_l 6385 13.7 1.339 1.451 1.339 1.451 dbm_copy 452 16.3 1.215 1.431 1.215 1.431 dbt_tas_copy 146 12.6 0.699 0.723 1.312 1.391 dbt_tas_communicate_buffer 370 16.3 0.012 0.013 1.029 1.077 ------------------------------------------------------------------------------- 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=45.59100000000001, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=176.05, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=31.541, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=7.038, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=6.552, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_forces_Pmat_3c", label="hfx_ri_forces_Pmat_3c", y=4.698, 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=15.472000000000001, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=20.126, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=1.281, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=2.546, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=3.573, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_forces_Pmat_3c", label="hfx_ri_forces_Pmat_3c", y=0.169, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.916, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_sync", label="mp_sync", y=4.228, 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 0.024 0.024 188.857 188.857 qs_energies 1 2.0 0.000 0.000 188.666 188.666 mp2_main 1 3.0 0.000 0.000 183.768 183.768 mp2_gpw_main 1 4.0 0.001 0.001 183.355 183.355 mp2_ri_gpw_compute_in 1 5.0 0.410 0.410 139.892 139.892 mp2_ri_gpw_compute_in_loop 1 6.0 0.010 0.010 130.001 130.001 mp2_eri_3c_integrate_gpw 2656 7.0 0.014 0.014 101.791 101.791 integrate_v_rspace 2666 8.0 0.622 0.622 89.010 89.010 grid_integrate_task_list 2666 9.0 86.170 86.170 86.170 86.170 mp2_ri_gpw_compute_en 1 5.0 0.087 0.087 43.443 43.443 mp2_ri_gpw_compute_en_RI_loop 1 6.0 9.646 9.646 41.532 41.532 mp2_ri_gpw_compute_en_expansio 2080 7.0 2.145 2.145 24.448 24.448 local_gemm 2080 8.0 22.303 22.303 22.303 22.303 dbcsr_multiply_generic 5322 8.0 0.187 0.187 21.770 21.770 ao_to_mo_and_store_B_mult_1 2656 7.0 0.009 0.009 21.746 21.746 fft_wrap_pw1pw2 53228 10.4 0.118 0.118 12.215 12.215 calculate_wavefunction 2656 8.0 7.930 7.930 11.401 11.401 multiply_cannon 5322 9.0 0.454 0.454 11.133 11.133 multiply_cannon_loop 5322 10.0 0.189 0.189 9.735 9.735 get_2c_integrals 1 6.0 0.000 0.000 9.480 9.480 fft_wrap_pw1pw2_20 21271 11.4 1.047 1.047 8.821 8.821 make_m2s 10644 9.0 0.062 0.062 8.541 8.541 compute_2c_integrals 1 7.0 0.006 0.006 8.509 8.509 compute_2c_integrals_loop_lm 1 8.0 0.013 0.013 8.496 8.496 mp2_eri_2c_integrate_gpw 1 9.0 0.870 0.870 8.482 8.482 make_images 10644 10.0 3.415 3.415 8.234 8.234 multiply_cannon_multrec 5322 11.0 8.153 8.153 8.192 8.192 fft3d_s 53229 12.4 6.727 6.727 6.765 6.765 ao_to_mo_and_store_B_E_Ex_1 2656 7.0 2.287 2.287 6.344 6.344 mp2_ri_gpw_compute_en_ener 2080 7.0 5.617 5.617 5.617 5.617 potential_pw2rs 5322 10.0 0.145 0.145 4.666 4.666 copy_dbcsr_to_fm 2679 8.0 0.026 0.026 4.584 4.584 scf_env_do_scf 1 3.0 0.000 0.000 4.470 4.470 scf_env_do_scf_inner_loop 10 4.0 0.001 0.001 4.469 4.469 mp2_eri_2c_integrate_gpw_pot_l 2656 10.0 0.005 0.005 3.895 3.895 ------------------------------------------------------------------------------- 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 0.035 36.670 36.683 qs_energies 1 2.0 0.000 0.000 36.515 36.515 mp2_main 1 3.0 0.000 0.001 34.492 34.492 mp2_gpw_main 1 4.0 0.001 0.003 34.391 34.391 mp2_ri_gpw_compute_in 1 5.0 0.043 0.044 17.231 17.448 mp2_ri_gpw_compute_en 1 5.0 0.326 0.347 17.091 17.317 mp2_ri_gpw_compute_in_loop 1 6.0 0.001 0.001 15.894 16.113 mp2_ri_gpw_compute_en_RI_loop 1 6.0 2.332 2.661 15.906 15.919 mp2_eri_3c_integrate_gpw 83 7.0 0.001 0.001 13.668 13.882 integrate_v_rspace 93 8.1 0.106 0.117 13.535 13.751 grid_integrate_task_list 93 9.1 13.229 13.427 13.229 13.427 mp2_ri_gpw_compute_en_expansio 65 7.0 0.098 0.112 10.814 10.940 local_gemm 65 8.0 10.715 10.831 10.715 10.831 mp2_ri_gpw_compute_en_comm 17 7.0 0.088 0.122 2.424 3.139 mp_sendrecv_dm3 1054 8.0 1.872 2.640 1.872 2.640 dbcsr_multiply_generic 176 8.0 0.008 0.009 1.906 2.118 ao_to_mo_and_store_B_mult_1 83 7.0 0.001 0.001 1.890 2.102 scf_env_do_scf 1 3.0 0.000 0.000 1.884 1.884 scf_env_do_scf_inner_loop 10 4.0 0.000 0.002 1.884 1.884 get_2c_integrals 1 6.0 0.003 0.012 1.266 1.293 multiply_cannon 176 9.0 0.017 0.018 1.100 1.160 multiply_cannon_loop 176 10.0 0.002 0.006 1.042 1.101 multiply_cannon_multrec 246 11.0 0.886 0.921 0.891 0.927 compute_2c_integrals 1 7.0 0.003 0.005 0.910 0.919 make_m2s 352 9.0 0.003 0.003 0.769 0.918 make_images 352 10.0 0.051 0.053 0.756 0.906 qs_scf_new_mos 10 5.0 0.000 0.000 0.897 0.904 compute_2c_integrals_loop_lm 1 8.0 0.001 0.002 0.814 0.842 mp2_eri_2c_integrate_gpw 1 9.0 0.205 0.218 0.813 0.841 eigensolver 11 5.8 0.001 0.001 0.827 0.828 ------------------------------------------------------------------------------- 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=54.655, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=86.17, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="local_gemm", label="local_gemm", y=22.303, 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=9.646, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=8.153, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="calculate_wavefunction", label="calculate_wavefunction", y=7.93, 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=7.636000000000003, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.229, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="local_gemm", label="local_gemm", y=10.715, 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=2.332, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=0.886, 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="mp_sendrecv_dm3", label="mp_sendrecv_dm3", y=1.872, 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 0.097 0.097 133.747 133.747 qs_energies 1 2.0 0.000 0.000 132.405 132.405 scf_env_do_scf 1 3.0 0.000 0.000 124.446 124.446 scf_env_do_scf_inner_loop 15 4.0 0.001 0.001 124.445 124.445 qs_ks_update_qs_env 15 5.0 0.000 0.000 55.621 55.621 rebuild_ks_matrix 15 6.0 0.000 0.000 55.406 55.406 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.002 55.406 55.406 qs_scf_new_mos 15 5.0 0.000 0.000 43.523 43.523 qs_vxc_create 15 8.0 0.016 0.016 39.034 39.034 eigensolver 15 6.0 0.002 0.002 35.620 35.620 calculate_dispersion_nonloc 15 9.0 6.700 6.700 33.712 33.712 fft_wrap_pw1pw2 1086 10.0 0.015 0.015 28.898 28.898 cp_fm_diag_elpa 15 7.0 0.000 0.000 22.864 22.864 cp_fm_diag_elpa_base 15 8.0 20.387 20.387 22.864 22.864 qs_rho_update_rho_low 16 5.0 0.000 0.000 21.850 21.850 calculate_rho_elec 16 6.0 0.225 0.225 21.850 21.850 fft_wrap_pw1pw2_150 765 11.0 6.878 6.878 21.246 21.246 grid_collocate_task_list 16 7.0 20.207 20.207 20.207 20.207 sum_up_and_integrate 15 8.0 0.000 0.000 15.349 15.349 integrate_v_rspace 15 9.0 0.022 0.022 15.338 15.338 grid_integrate_task_list 15 10.0 14.623 14.623 14.623 14.623 fft3d_s 1087 12.0 11.125 11.125 11.133 11.133 cp_fm_cholesky_restore 45 7.0 10.484 10.484 10.484 10.484 fft_wrap_pw1pw2_200 197 11.3 1.667 1.667 7.406 7.406 pw_scatter_s 585 12.1 7.339 7.339 7.339 7.339 copy_dbcsr_to_fm 16 5.9 0.001 0.001 5.647 5.647 dbcsr_complete_redistribute 46 8.3 2.257 2.257 5.643 5.643 xc_vxc_pw_create 15 9.0 0.240 0.240 5.306 5.306 cp_fm_upper_to_full 30 8.0 4.747 4.747 4.747 4.747 gspace_mixing 14 5.0 0.171 0.171 4.621 4.621 vdW_energy 15 10.0 4.391 4.391 4.391 4.391 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 4.339 4.339 broyden_mixing 14 6.0 3.962 3.962 3.962 3.962 xc_pw_derive 90 11.0 0.001 0.001 3.764 3.764 init_scf_run 1 3.0 0.000 0.000 3.147 3.147 build_core_hamiltonian_matrix 1 4.0 0.000 0.000 3.136 3.136 ------------------------------------------------------------------------------- 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 61.852 61.865 qs_energies 1 2.0 0.000 0.000 61.519 61.527 scf_env_do_scf 1 3.0 0.000 0.001 57.251 57.251 scf_env_do_scf_inner_loop 15 4.0 0.001 0.004 57.250 57.251 qs_ks_update_qs_env 15 5.0 0.000 0.000 24.569 24.589 rebuild_ks_matrix 15 6.0 0.000 0.000 24.527 24.547 qs_ks_build_kohn_sham_matrix 15 7.0 0.003 0.003 24.527 24.547 qs_rho_update_rho_low 16 5.0 0.000 0.000 19.390 19.393 calculate_rho_elec 16 6.0 0.007 0.008 19.390 19.393 grid_collocate_task_list 16 7.0 18.300 18.479 18.300 18.479 sum_up_and_integrate 15 8.0 0.000 0.000 14.609 14.661 integrate_v_rspace 15 9.0 0.001 0.001 14.600 14.656 qs_scf_new_mos 15 5.0 0.000 0.000 13.819 13.998 grid_integrate_task_list 15 10.0 13.673 13.930 13.673 13.930 eigensolver 15 6.0 0.001 0.002 12.735 12.748 qs_vxc_create 15 8.0 0.001 0.001 9.500 9.512 cp_fm_diag_elpa 15 7.0 0.000 0.000 9.025 9.030 cp_fm_diag_elpa_base 15 8.0 8.881 8.895 9.022 9.023 calculate_dispersion_nonloc 15 9.0 0.933 0.944 7.631 7.646 fft_wrap_pw1pw2 1086 10.0 0.022 0.024 7.070 7.132 fft3d_ps 1086 12.0 2.690 2.845 5.175 5.269 fft_wrap_pw1pw2_150 765 11.0 0.136 0.146 4.565 4.592 cp_fm_cholesky_restore 45 7.0 3.547 3.582 3.547 3.582 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 2.709 2.709 build_core_hamiltonian_matrix 1 4.0 0.000 0.000 2.410 2.613 fft_wrap_pw1pw2_200 197 11.3 0.100 0.109 2.381 2.465 mp_alltoall_z22v 1086 14.0 1.837 2.124 1.837 2.124 xc_vxc_pw_create 15 9.0 0.016 0.020 1.868 1.897 build_core_ppnl 1 5.0 1.502 1.626 1.502 1.626 vdW_energy 15 10.0 1.353 1.396 1.353 1.396 x_to_yz 585 13.1 0.353 0.374 1.289 1.370 yz_to_x 501 12.9 0.271 0.324 1.172 1.356 init_scf_run 1 3.0 0.000 0.001 1.333 1.334 xc_pw_derive 90 11.0 0.001 0.002 1.245 1.325 ------------------------------------------------------------------------------- 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=56.92100000000002, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=20.387, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=20.207, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=14.623, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="fft3d_s", label="fft3d_s", y=11.125, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=10.484, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="fft3d_ps", label="fft3d_ps", y=0.0, yerr=0.0 Plot: name="diag_cu144_broy_timings_32mpi", title="Timings of diag_cu144_broy with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="rest", label="rest", y=14.761000000000003, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=8.881, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=18.3, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.673, 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=3.547, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=2.69, yerr=0.0 Running bench_dftb.inp with 1 threads and 32 ranks... done. Running bench_dftb.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/bench_dftb_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.080 0.080 344.042 344.042 qs_energies 1 2.0 0.000 0.000 343.903 343.903 ls_scf 1 3.0 0.000 0.000 342.616 342.616 ls_scf_main 1 4.0 0.002 0.002 333.732 333.732 density_matrix_trs4 11 5.0 0.013 0.013 240.916 240.916 arnoldi_extremal 12 6.1 0.000 0.000 154.525 154.525 arnoldi_normal_ev 12 7.1 0.031 0.031 154.525 154.525 dbcsr_matrix_vector_mult 652 9.0 0.207 0.207 152.340 152.340 build_subspace 23 8.1 0.077 0.077 151.820 151.820 dbcsr_matrix_vector_mult_local 652 10.0 150.606 150.606 150.615 150.615 ls_scf_dm_to_ks 11 5.0 0.000 0.000 87.460 87.460 matrix_ls_to_qs 11 6.0 0.000 0.000 84.199 84.199 dbcsr_multiply_generic 185 6.1 0.818 0.818 74.978 74.978 dbcsr_copy_into_existing 11 7.0 45.593 45.593 45.594 45.594 multiply_cannon 185 7.1 0.305 0.305 44.645 44.645 dbcsr_complete_redistribute 23 7.5 30.944 30.944 42.396 42.396 matrix_decluster 11 7.0 0.000 0.000 38.604 38.604 multiply_cannon_loop 185 8.1 0.226 0.226 32.335 32.335 make_m2s 370 7.1 0.038 0.038 25.693 25.693 make_images 370 8.1 10.854 10.854 24.072 24.072 multiply_cannon_multrec 185 9.1 23.880 23.880 23.915 23.915 dbcsr_finalize 646 7.5 0.271 0.271 15.308 15.308 dbcsr_merge_all 597 8.5 2.215 2.215 14.028 14.028 setup_rec_index_2d 370 8.1 11.913 11.913 11.913 11.913 dbcsr_sort_indices 1103 9.9 11.199 11.199 11.199 11.199 tree_to_linear_d 110 9.4 10.407 10.407 10.407 10.407 quick_finalize 395 10.0 0.321 0.321 9.602 9.602 dbcsr_special_finalize 370 9.1 0.002 0.002 8.850 8.850 calculate_norms 370 9.1 8.194 8.194 8.194 8.194 ls_scf_init_scf 1 4.0 0.000 0.000 8.193 8.193 ls_scf_init_matrix_S 1 5.0 0.000 0.000 7.861 7.861 matrix_sqrt_Newton_Schulz 1 6.0 0.001 0.001 7.202 7.202 ------------------------------------------------------------------------------- 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 0.014 0.038 73.975 73.994 qs_energies 1 2.0 0.000 0.000 73.846 73.847 ls_scf 1 3.0 0.000 0.000 73.792 73.793 ls_scf_main 1 4.0 0.001 0.013 71.019 71.021 density_matrix_trs4 11 5.0 0.007 0.022 67.906 67.969 dbcsr_multiply_generic 185 6.1 0.062 0.081 64.497 64.683 multiply_cannon 185 7.1 0.038 0.041 53.179 53.753 multiply_cannon_loop 185 8.1 0.128 0.139 50.531 51.188 multiply_cannon_multrec 1480 9.1 30.734 32.664 31.011 32.934 mp_waitall_1 11936 10.3 17.040 19.517 17.040 19.517 multiply_cannon_metrocomm3 1480 9.1 0.017 0.019 13.033 15.887 make_m2s 370 7.1 0.036 0.038 7.353 7.415 make_images 370 8.1 0.657 0.686 7.217 7.280 calculate_norms 2960 9.1 5.271 5.803 5.271 5.803 mp_sum_l 1199 5.3 3.008 4.159 3.008 4.159 make_images_data 370 9.1 0.012 0.013 3.269 3.486 dbcsr_multiply_generic_mpsum_f 137 7.1 0.000 0.000 2.037 3.019 hybrid_alltoall_any 393 9.9 0.253 1.473 2.864 3.017 ls_scf_dm_to_ks 11 5.0 0.000 0.000 2.737 2.864 arnoldi_extremal 12 6.1 0.001 0.001 2.619 2.628 arnoldi_normal_ev 12 7.1 0.002 0.008 2.618 2.628 build_subspace 23 8.1 0.022 0.026 2.519 2.521 dbcsr_complete_redistribute 23 7.5 1.268 1.354 2.185 2.309 matrix_ls_to_qs 11 6.0 0.000 0.000 2.115 2.238 dbcsr_matrix_vector_mult 652 9.0 0.014 0.053 2.140 2.202 ls_scf_init_scf 1 4.0 0.000 0.000 2.115 2.116 matrix_decluster 11 7.0 0.000 0.000 1.972 2.095 ls_scf_init_matrix_S 1 5.0 0.000 0.000 2.090 2.094 multiply_cannon_metrocomm1 1480 9.1 0.007 0.008 1.048 2.056 make_images_pack 370 9.1 1.769 1.949 1.773 1.953 matrix_sqrt_Newton_Schulz 1 6.0 0.000 0.002 1.893 1.895 dbcsr_matrix_vector_mult_local 652 10.0 1.761 1.831 1.763 1.833 buffer_matrices_ensure_size 370 8.1 1.482 1.579 1.482 1.579 dbcsr_finalize 646 7.5 0.008 0.009 1.381 1.490 ------------------------------------------------------------------------------- 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=72.91199999999998, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=150.606, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_copy_into_existing", label="dbcsr_copy_into_existing", y=45.593, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_complete_redistribute", label="dbcsr_complete_redistribute", y=30.944, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=23.88, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="setup_rec_index_2d", label="setup_rec_index_2d", y=11.913, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="calculate_norms", label="calculate_norms", y=8.194, 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 PlotPoint: plot="bench_dftb_timings_32omp", name="make_images_pack", label="make_images_pack", 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=13.123999999999988, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=1.761, 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=1.268, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=30.734, 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=5.271, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=3.008, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=17.04, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="make_images_pack", label="make_images_pack", y=1.769, 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 72.746 72.746 lib_test 1 2.0 0.000 0.000 72.736 72.736 dbcsr_run_tests 3 3.0 0.002 0.002 72.735 72.735 test_multiplies_multiproc 3 4.0 0.001 0.001 56.362 56.362 dbcsr_redistribute 9 5.0 36.137 36.137 37.791 37.791 dbcsr_multiply_generic 9 5.0 0.001 0.001 17.096 17.096 dbcsr_make_random_matrix 9 4.0 13.208 13.208 16.255 16.255 multiply_cannon 9 6.0 0.002 0.002 12.048 12.048 multiply_cannon_loop 9 7.0 0.007 0.007 11.685 11.685 multiply_cannon_multrec 9 8.0 11.677 11.677 11.678 11.678 dbcsr_finalize 27 5.7 0.011 0.011 5.670 5.670 dbcsr_merge_all 18 6.5 2.049 2.049 4.911 4.911 dbcsr_data_release 975 7.6 2.950 2.950 2.950 2.950 tree_to_linear_d 9 7.0 1.971 1.971 1.971 1.971 make_m2s 18 6.0 0.001 0.001 1.760 1.760 make_images 18 7.0 0.614 0.614 1.709 1.709 ------------------------------------------------------------------------------- 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 0.004 0.019 19.643 19.649 lib_test 1 2.0 0.000 0.000 19.448 19.466 dbcsr_run_tests 3 3.0 0.000 0.001 19.442 19.461 test_multiplies_multiproc 3 4.0 0.000 0.002 18.566 18.618 dbcsr_multiply_generic 9 5.0 0.001 0.001 17.116 17.215 multiply_cannon 9 6.0 0.002 0.002 15.149 15.583 multiply_cannon_loop 9 7.0 0.002 0.002 14.869 15.299 multiply_cannon_multrec 72 8.0 11.353 11.622 11.353 11.623 mp_waitall_1 576 9.2 3.849 4.229 3.849 4.229 multiply_cannon_metrocomm1 72 8.0 0.001 0.001 3.432 3.804 mp_sum_l 470 2.5 0.783 1.089 0.783 1.089 dbcsr_multiply_generic_mpsum_f 9 6.0 0.000 0.000 0.685 0.991 dbcsr_make_random_matrix 9 4.0 0.686 0.695 0.839 0.860 make_m2s 18 6.0 0.001 0.001 0.718 0.752 make_images 18 7.0 0.021 0.023 0.714 0.749 dbcsr_data_release 444 7.6 0.640 0.718 0.640 0.718 dbcsr_finalize 27 5.7 0.000 0.000 0.581 0.686 dbcsr_destroy 111 5.9 0.004 0.056 0.556 0.636 dbcsr_redistribute 9 5.0 0.257 0.298 0.562 0.590 dbcsr_merge_all 18 6.5 0.087 0.099 0.491 0.580 make_images_data 18 8.0 0.001 0.001 0.375 0.453 ------------------------------------------------------------------------------- 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=6.724999999999994, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_redistribute", label="dbcsr_redistribute", y=36.137, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=13.208, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=11.677, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_data_release", label="dbcsr_data_release", y=2.95, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_merge_all", label="dbcsr_merge_all", y=2.049, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="mp_sum_l", label="mp_sum_l", y=0.0, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 Plot: name="dbcsr_timings_32mpi", title="Timings of dbcsr with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="dbcsr_timings_32mpi", name="rest", label="rest", y=1.9879999999999995, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_redistribute", label="dbcsr_redistribute", y=0.257, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=0.686, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=11.353, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_data_release", label="dbcsr_data_release", y=0.64, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_merge_all", label="dbcsr_merge_all", y=0.087, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=0.783, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=3.849, 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 0.062 0.062 135.038 135.038 qs_mol_dyn_low 1 2.0 0.004 0.004 133.624 133.624 velocity_verlet 5 3.0 0.003 0.003 108.820 108.820 qmmm_el_coupling 6 3.8 0.000 0.000 87.938 87.938 qmmm_elec_with_gaussian 6 4.8 0.013 0.013 87.929 87.929 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 87.308 87.308 qmmm_elec_gaussian_low_G 6 6.8 86.402 86.402 86.402 86.402 qs_forces 6 3.8 0.001 0.001 37.107 37.107 qs_energies 6 4.8 0.000 0.000 33.006 33.006 scf_env_do_scf 6 5.8 0.001 0.001 30.495 30.495 scf_env_do_scf_inner_loop 39 6.8 0.004 0.004 26.594 26.594 rebuild_ks_matrix 45 8.4 0.000 0.000 25.463 25.463 qs_ks_build_kohn_sham_matrix 45 9.4 0.005 0.005 25.463 25.463 qs_ks_update_qs_env 45 7.8 0.000 0.000 21.819 21.819 fft_wrap_pw1pw2 801 12.6 0.010 0.010 20.937 20.937 fft_wrap_pw1pw2_150 507 14.2 5.313 5.313 20.479 20.479 qs_vxc_create 45 10.4 0.001 0.001 15.486 15.486 xc_vxc_pw_create 45 11.4 0.641 0.641 15.485 15.485 xc_pw_derive 270 13.4 0.002 0.002 11.575 11.575 fft3d_s 802 14.6 8.299 8.299 8.307 8.307 qs_rho_update_rho_low 45 7.9 0.000 0.000 7.875 7.875 calculate_rho_elec 45 8.9 0.563 0.563 7.875 7.875 xc_pw_divergence 45 12.4 0.001 0.001 7.873 7.873 xc_rho_set_and_dset_create 45 12.4 0.602 0.602 6.893 6.893 pw_scatter_s 429 14.8 5.611 5.611 5.611 5.611 qmmm_forces 6 3.8 0.001 0.001 5.479 5.479 qmmm_forces_with_gaussian 6 4.8 0.017 0.017 5.157 5.157 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 4.378 4.378 sum_up_and_integrate 45 10.4 0.000 0.000 3.916 3.916 density_rs2pw 45 9.9 0.002 0.002 3.898 3.898 init_scf_loop 6 6.8 0.000 0.000 3.896 3.896 integrate_v_rspace 45 11.4 0.007 0.007 3.857 3.857 qs_ks_ddapc 45 10.4 0.001 0.001 3.673 3.673 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 3.651 3.651 qmmm_forces_gaussian_low_G 6 6.8 3.649 3.649 3.649 3.649 grid_collocate_task_list 45 9.9 3.414 3.414 3.414 3.414 pw_integral_ab 2539 7.4 2.796 2.796 2.796 2.796 ------------------------------------------------------------------------------- From /workspace/artifacts/MQAE_single_node_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.034 0.060 58.479 58.498 qs_mol_dyn_low 1 2.0 0.003 0.004 57.326 57.387 qs_forces 6 3.8 0.001 0.001 42.062 42.062 qs_energies 6 4.8 0.000 0.000 40.177 40.177 scf_env_do_scf 6 5.8 0.000 0.001 39.201 39.202 scf_env_do_scf_inner_loop 113 6.2 0.002 0.017 37.575 37.576 rebuild_ks_matrix 119 8.1 0.000 0.000 27.473 27.484 qs_ks_build_kohn_sham_matrix 119 9.1 0.016 0.021 27.473 27.484 qs_ks_update_qs_env 119 7.3 0.001 0.001 25.891 25.901 velocity_verlet 5 3.0 0.002 0.004 23.843 23.846 fft_wrap_pw1pw2 2059 12.4 0.040 0.044 17.293 17.745 fft_wrap_pw1pw2_150 1321 13.9 0.671 0.709 16.566 16.988 qs_vxc_create 119 10.1 0.002 0.002 13.824 13.829 xc_vxc_pw_create 119 11.1 0.156 0.216 13.823 13.828 fft3d_ps 2059 14.4 7.306 7.969 12.777 13.399 qs_rho_update_rho_low 119 7.3 0.001 0.001 10.859 10.863 calculate_rho_elec 119 8.3 0.049 0.056 10.858 10.863 xc_pw_derive 714 13.1 0.013 0.015 10.384 10.708 sum_up_and_integrate 119 10.1 0.002 0.002 9.404 9.416 integrate_v_rspace 119 11.1 0.004 0.004 9.347 9.367 qmmm_forces 6 3.8 0.002 0.002 7.737 7.737 qmmm_forces_with_gaussian 6 4.8 0.008 0.009 7.397 7.544 xc_pw_divergence 119 12.1 0.005 0.006 6.808 7.084 xc_rho_set_and_dset_create 119 12.1 0.370 0.465 6.656 6.844 qmmm_el_coupling 6 3.8 0.000 0.000 6.491 6.568 qmmm_elec_with_gaussian 6 4.8 0.003 0.005 6.489 6.567 density_rs2pw 119 9.3 0.006 0.007 6.089 6.412 potential_pw2rs 119 12.1 0.006 0.007 5.507 5.522 grid_collocate_task_list 119 9.3 4.627 4.945 4.627 4.945 mp_alltoall_z22v 2059 16.4 3.921 4.789 3.921 4.789 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 4.070 4.131 transfer_pw2rs 500 12.8 0.006 0.007 3.816 3.827 grid_integrate_task_list 119 12.1 3.560 3.781 3.560 3.781 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 3.482 3.521 qmmm_forces_gaussian_low_G 6 6.8 3.347 3.413 3.347 3.413 x_to_yz 1095 15.8 0.827 0.897 2.970 3.247 transfer_rs2pw 488 10.2 0.007 0.010 2.871 3.184 mp_waitany 4028 12.8 2.562 3.080 2.562 3.080 yz_to_x 964 15.0 0.668 0.823 2.447 2.987 qmmm_elec_gaussian_low_G 6 6.8 2.889 2.930 2.889 2.930 pw_restrict_s3 18 5.8 1.433 1.488 2.725 2.817 qs_scf_new_mos 113 7.2 0.000 0.000 2.732 2.737 qs_scf_loop_do_ot 113 8.2 0.000 0.001 2.731 2.737 ot_scf_mini 113 9.2 0.001 0.001 2.647 2.651 transfer_pw2rs_150 125 13.9 0.935 1.014 2.556 2.600 qmmm_elec_with_gaussian:spline 6 5.8 0.000 0.000 2.267 2.342 pw_prolongate_s3 18 6.8 1.213 1.254 2.267 2.342 transfer_rs2pw_150 125 11.2 0.692 0.867 2.006 2.323 qs_ks_ddapc 119 10.1 0.003 0.007 2.058 2.147 dbcsr_multiply_generic 2588 12.3 0.060 0.063 1.898 1.930 pw_scatter_p 1095 14.8 1.685 1.725 1.685 1.725 pw_gather_p 964 14.0 1.364 1.637 1.364 1.637 init_scf_loop 6 6.8 0.000 0.000 1.623 1.623 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 1.600 1.600 pw_integral_ab 2761 7.7 1.242 1.297 1.538 1.598 pw_poisson_solve 125 9.9 0.003 0.004 1.488 1.528 pw_derive 1089 13.4 1.405 1.512 1.405 1.512 pw_copy 2027 12.4 1.326 1.444 1.326 1.444 mp_sum_dm3 33 5.7 1.237 1.264 1.237 1.264 ot_mini 113 10.2 0.001 0.001 1.242 1.247 qs_ot_get_p 119 10.2 0.000 0.000 1.179 1.186 ------------------------------------------------------------------------------- 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=22.35000000000001, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=86.402, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_s", label="fft3d_s", y=8.299, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_scatter_s", label="pw_scatter_s", y=5.611, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft_wrap_pw1pw2_150", label="fft_wrap_pw1pw2_150", y=5.313, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.649, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=3.414, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_ps", label="fft3d_ps", y=0.0, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=0.0, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=0.0, yerr=0.0 Plot: name="MQAE_single_node_timings_32mpi", title="Timings of MQAE_single_node with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="MQAE_single_node_timings_32mpi", name="rest", label="rest", y=32.158, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=2.889, 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=0.671, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.347, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=4.627, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=7.306, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=3.56, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=3.921, yerr=0.0 Summary: Performance test took 36 minutes. Status: OK Removing intermediate container f4761db22d98 ---> fff1bd2e5ba7 Step 41/42 : CMD cat $(find ./report.log -mmin +10) | sed '/^Summary:/ s/$/ (cached)/' ---> Running in a06ce82ea73c Removing intermediate container a06ce82ea73c ---> ca65136cad50 Step 42/42 : ENTRYPOINT [] ---> Running in 6393c4645e36 Removing intermediate container 6393c4645e36 ---> 638db34f4a8e [Warning] One or more build-args [GIT_COMMIT_SHA] were not consumed Successfully built 638db34f4a8e 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: 2024-02-14 08:54:02+00:00