StartDate: 2023-08-17 19:13:56+00:00 CpuId: 32x AMD EPYC (3rd Gen) (Milan) [Zen 3], 7nm (SMT disabled) CommitSHA: 627b89bbdc49bd82d8905e4d10d261ed7123330b CommitTime: 2023-08-17 17:36:08 +0200 CommitAuthor: Matthias Krack CommitSubject: Run checks for new python script #################### Building Image cp2k-perf-openmp #################### Dockerfile: /tools/docker/Dockerfile.test_performance Build-Path: / Build-Args: GIT_COMMIT_SHA=627b89bbdc49bd82d8905e4d10d261ed7123330b 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 383.7MB Step 1/42 : FROM ubuntu:22.04 22.04: Pulling from library/ubuntu b237fe92c417: Pulling fs layer b237fe92c417: Verifying Checksum b237fe92c417: Download complete b237fe92c417: Pull complete Digest: sha256:ec050c32e4a6085b423d36ecd025c0d3ff00c38ab93a3d71a460ff1c44fa6d77 Status: Downloaded newer image for ubuntu:22.04 ---> 01f29b872827 Step 2/42 : WORKDIR /opt/cp2k-toolchain ---> Using cache ---> ed64d4bb2bb3 Step 3/42 : COPY ./tools/toolchain/install_requirements*.sh ./ ---> Using cache ---> 6d64b6caa119 Step 4/42 : RUN ./install_requirements.sh ubuntu:22.04 ---> Using cache ---> 528403065b56 Step 5/42 : RUN mkdir scripts ---> Using cache ---> 2a7005b78c0e 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 ---> 79098f2a61a6 Step 7/42 : COPY ./tools/toolchain/install_cp2k_toolchain.sh . ---> Using cache ---> 016fb3bf205d Step 8/42 : RUN ./install_cp2k_toolchain.sh --install-all --with-gcc=system --dry-run ---> Using cache ---> ea5f28b1e1f8 Step 9/42 : COPY ./tools/toolchain/scripts/stage0/ ./scripts/stage0/ ---> Using cache ---> 767ac113086c Step 10/42 : RUN ./scripts/stage0/install_stage0.sh && rm -rf ./build ---> Using cache ---> 1d159a3113a2 Step 11/42 : COPY ./tools/toolchain/scripts/stage1/ ./scripts/stage1/ ---> Using cache ---> 837e9801a1b9 Step 12/42 : RUN ./scripts/stage1/install_stage1.sh && rm -rf ./build ---> Using cache ---> e44fec745045 Step 13/42 : COPY ./tools/toolchain/scripts/stage2/ ./scripts/stage2/ ---> Using cache ---> 720c06412111 Step 14/42 : RUN ./scripts/stage2/install_stage2.sh && rm -rf ./build ---> Using cache ---> 5373ea6abc17 Step 15/42 : COPY ./tools/toolchain/scripts/stage3/ ./scripts/stage3/ ---> Using cache ---> 68d9e0e398d7 Step 16/42 : RUN ./scripts/stage3/install_stage3.sh && rm -rf ./build ---> Using cache ---> 64760ac7a9c1 Step 17/42 : COPY ./tools/toolchain/scripts/stage4/ ./scripts/stage4/ ---> Using cache ---> ddc0d0908887 Step 18/42 : RUN ./scripts/stage4/install_stage4.sh && rm -rf ./build ---> Using cache ---> cdbd05e994b4 Step 19/42 : COPY ./tools/toolchain/scripts/stage5/ ./scripts/stage5/ ---> Using cache ---> d2e08907b5bb Step 20/42 : RUN ./scripts/stage5/install_stage5.sh && rm -rf ./build ---> Using cache ---> 336098c3bd03 Step 21/42 : COPY ./tools/toolchain/scripts/stage6/ ./scripts/stage6/ ---> Using cache ---> 1791da06b70f Step 22/42 : RUN ./scripts/stage6/install_stage6.sh && rm -rf ./build ---> Using cache ---> a44961f0b64e Step 23/42 : COPY ./tools/toolchain/scripts/stage7/ ./scripts/stage7/ ---> Using cache ---> 62be1a5cfe61 Step 24/42 : RUN ./scripts/stage7/install_stage7.sh && rm -rf ./build ---> Using cache ---> 4f87b58cf817 Step 25/42 : COPY ./tools/toolchain/scripts/stage8/ ./scripts/stage8/ ---> Using cache ---> 0458d246ac05 Step 26/42 : RUN ./scripts/stage8/install_stage8.sh && rm -rf ./build ---> Using cache ---> dbfdbc9c4cc4 Step 27/42 : COPY ./tools/toolchain/scripts/arch_base.tmpl ./tools/toolchain/scripts/generate_arch_files.sh ./scripts/ ---> Using cache ---> 9ed3ca8bf57b Step 28/42 : RUN ./scripts/generate_arch_files.sh && rm -rf ./build ---> Using cache ---> 2e4e5c6cfe05 Step 29/42 : WORKDIR /opt/cp2k ---> Using cache ---> 23ec3d61e2a7 Step 30/42 : COPY ./Makefile . ---> Using cache ---> 9dfe550d954d Step 31/42 : COPY ./src ./src ---> Using cache ---> 8f3e8e546f5d Step 32/42 : COPY ./exts ./exts ---> Using cache ---> 3113b047e804 Step 33/42 : COPY ./tools/build_utils ./tools/build_utils ---> Using cache ---> 355f355e62fb Step 34/42 : RUN /bin/bash -c " mkdir -p arch && ln -vs /opt/cp2k-toolchain/install/arch/local.psmp ./arch/ && echo 'Compiling cp2k...' && source /opt/cp2k-toolchain/install/setup && ( make -j ARCH=local VERSION=psmp &> /dev/null || true ) && rm -rf lib obj && ( [ ! -f ./exe/local/cp2k.psmp ] || ldd ./exe/local/cp2k.psmp | grep -q libmpi )" ---> Running in c35729ee596f './arch/local.psmp' -> '/opt/cp2k-toolchain/install/arch/local.psmp' Compiling cp2k... Removing intermediate container c35729ee596f ---> b7a7e6b0f8b2 Step 35/42 : COPY ./data ./data ---> f76f059003a8 Step 36/42 : COPY ./tests ./tests ---> d0d7e3e78398 Step 37/42 : COPY ./tools/regtesting ./tools/regtesting ---> 0b299ef60147 Step 38/42 : COPY ./benchmarks ./benchmarks ---> 080ffe39a944 Step 39/42 : COPY ./tools/docker/scripts/test_performance.sh ./tools/docker/scripts/plot_performance.py ./ ---> a9de159f291f Step 40/42 : RUN ./test_performance.sh "local" 2>&1 | tee report.log ---> Running in 9417460f1608 ========== Compiling CP2K ========== Compiling cp2k... done. Checking benchmark inputs... Found 70 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 0.041 0.041 114.241 114.241 qs_mol_dyn_low 1 2.0 0.003 0.003 113.633 113.633 qs_forces 11 3.9 0.002 0.002 113.583 113.583 qs_energies 11 4.9 0.001 0.001 105.416 105.416 scf_env_do_scf 11 5.9 0.002 0.002 90.905 90.905 velocity_verlet 10 3.0 0.002 0.002 75.974 75.974 scf_env_do_scf_inner_loop 108 6.5 0.014 0.014 70.075 70.075 rebuild_ks_matrix 119 8.3 0.001 0.001 28.133 28.133 qs_ks_build_kohn_sham_matrix 119 9.3 0.015 0.015 28.132 28.132 qs_ks_update_qs_env 119 7.6 0.001 0.001 27.342 27.342 qs_scf_new_mos 108 7.5 0.001 0.001 25.996 25.996 qs_scf_loop_do_ot 108 8.5 0.001 0.001 25.996 25.996 dbcsr_multiply_generic 2286 12.5 0.207 0.207 25.489 25.489 ot_scf_mini 108 9.5 0.003 0.003 24.155 24.155 qs_rho_update_rho_low 119 7.7 0.001 0.001 21.873 21.873 calculate_rho_elec 119 8.7 1.137 1.137 21.873 21.873 init_scf_loop 11 6.9 0.000 0.000 20.610 20.610 grid_collocate_task_list 119 9.7 16.767 16.767 16.767 16.767 prepare_preconditioner 11 7.9 0.000 0.000 16.711 16.711 make_preconditioner 11 8.9 0.000 0.000 16.711 16.711 sum_up_and_integrate 119 10.3 1.648 1.648 16.498 16.498 ot_mini 108 10.5 0.001 0.001 15.768 15.768 make_full_inverse_cholesky 11 9.9 0.035 0.035 14.948 14.948 integrate_v_rspace 119 11.3 0.137 0.137 14.850 14.850 make_m2s 4572 13.5 0.053 0.053 12.593 12.593 grid_integrate_task_list 119 12.3 12.143 12.143 12.143 12.143 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 8.568 8.568 qs_ot_get_derivative 108 11.5 0.001 0.001 8.258 8.258 multiply_cannon 2286 13.5 0.211 0.211 8.134 8.134 multiply_cannon_loop 2286 14.5 0.081 0.081 7.584 7.584 ot_diis_step 108 11.5 0.004 0.004 7.507 7.507 multiply_cannon_multrec 2286 15.5 7.437 7.437 7.502 7.502 pw_transfer 1439 11.6 0.075 0.075 7.285 7.285 make_images 4572 14.5 3.021 3.021 7.043 7.043 fft_wrap_pw1pw2 1201 12.6 0.007 0.007 6.954 6.954 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 6.209 6.209 apply_single 119 13.6 0.001 0.001 6.209 6.209 dbcsr_make_dense_low 5837 15.5 0.080 0.080 6.005 6.005 make_dense_data 5837 16.5 5.407 5.407 5.911 5.911 cp_fm_cholesky_decompose 22 10.9 5.908 5.908 5.908 5.908 fft_wrap_pw1pw2_140 487 13.2 0.603 0.603 5.881 5.881 dbcsr_complete_redistribute 329 12.2 3.147 3.147 5.394 5.394 qs_env_update_s_mstruct 11 6.9 0.000 0.000 5.141 5.141 dbcsr_make_images_dense 3978 14.8 0.019 0.019 5.104 5.104 init_scf_run 11 5.9 0.003 0.003 4.977 4.977 scf_env_initial_rho_setup 11 6.9 0.002 0.002 4.974 4.974 qs_create_task_list 11 7.9 0.000 0.000 4.661 4.661 generate_qs_task_list 11 8.9 2.316 2.316 4.661 4.661 dbcsr_dot_sd 1205 11.9 4.629 4.629 4.632 4.632 pw_poisson_solve 119 10.3 1.101 1.101 4.421 4.421 wfi_extrapolate 11 7.9 0.001 0.001 4.398 4.398 copy_dbcsr_to_fm 153 11.3 0.003 0.003 4.249 4.249 build_core_hamiltonian_matrix_ 11 4.9 0.001 0.001 4.146 4.146 dbcsr_copy 2102 12.0 0.328 0.328 4.131 4.131 qs_ot_get_p 119 10.4 0.001 0.001 4.089 4.089 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 4.017 4.017 density_rs2pw 119 9.7 0.006 0.006 3.968 3.968 cp_fm_cholesky_invert 11 10.9 3.907 3.907 3.907 3.907 dbcsr_copy_into_existing 22 7.9 3.760 3.760 3.761 3.761 fft3d_s 1202 14.6 3.530 3.530 3.536 3.536 evaluate_core_matrix_traces 119 8.3 0.001 0.001 3.225 3.225 calculate_ptrace_kp 238 9.3 0.001 0.001 3.224 3.224 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 3.201 3.201 pw_integral_ab 119 11.3 3.041 3.041 3.041 3.041 build_core_hamiltonian_matrix 11 6.9 0.001 0.001 2.887 2.887 copy_fm_to_dbcsr 176 11.2 0.002 0.002 2.841 2.841 dbcsr_data_release 279532 16.0 2.635 2.635 2.635 2.635 potential_pw2rs 119 12.3 0.129 0.129 2.570 2.570 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 2.529 2.529 qs_ot_get_derivative_taylor 59 13.0 0.002 0.002 2.489 2.489 qs_ot_p2m_diag 50 11.0 0.157 0.157 2.357 2.357 dbcsr_finalize 5186 13.8 0.162 0.162 2.305 2.305 ------------------------------------------------------------------------------- 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 0.011 0.038 54.658 54.678 qs_mol_dyn_low 1 2.0 0.004 0.005 54.247 54.252 qs_forces 11 3.9 0.002 0.002 54.195 54.196 qs_energies 11 4.9 0.001 0.001 50.747 50.749 scf_env_do_scf 11 5.9 0.001 0.003 46.566 46.567 scf_env_do_scf_inner_loop 108 6.5 0.003 0.026 42.992 42.992 velocity_verlet 10 3.0 0.001 0.004 32.047 32.049 rebuild_ks_matrix 119 8.3 0.001 0.001 19.322 19.403 qs_ks_build_kohn_sham_matrix 119 9.3 0.018 0.022 19.322 19.402 qs_ks_update_qs_env 119 7.6 0.001 0.001 17.181 17.255 dbcsr_multiply_generic 2286 12.5 0.089 0.098 16.474 16.623 qs_rho_update_rho_low 119 7.7 0.001 0.001 15.570 15.580 calculate_rho_elec 119 8.7 0.034 0.042 15.569 15.580 sum_up_and_integrate 119 10.3 0.039 0.043 14.276 14.307 integrate_v_rspace 119 11.3 0.005 0.005 14.237 14.269 qs_scf_new_mos 108 7.5 0.001 0.001 13.443 13.645 qs_scf_loop_do_ot 108 8.5 0.001 0.004 13.443 13.645 ot_scf_mini 108 9.5 0.003 0.003 12.715 12.921 multiply_cannon 2286 13.5 0.160 0.194 12.004 12.458 multiply_cannon_loop 2286 14.5 0.111 0.123 11.310 11.633 grid_collocate_task_list 119 9.7 10.498 10.877 10.498 10.877 mp_waitall_1 158411 16.6 9.180 9.742 9.180 9.742 grid_integrate_task_list 119 12.3 9.434 9.628 9.434 9.628 ot_mini 108 10.5 0.001 0.001 7.519 7.742 multiply_cannon_metrocomm3 18288 15.5 0.049 0.053 6.998 7.502 density_rs2pw 119 9.7 0.006 0.007 4.554 5.046 pw_transfer 1439 11.6 0.075 0.083 4.777 4.867 fft_wrap_pw1pw2 1201 12.6 0.010 0.014 4.618 4.705 potential_pw2rs 119 12.3 0.007 0.007 4.191 4.224 multiply_cannon_multrec 18288 15.5 3.832 4.106 3.846 4.119 fft_wrap_pw1pw2_140 487 13.2 0.746 0.875 3.914 4.068 qs_ot_get_derivative 108 11.5 0.001 0.001 3.786 3.991 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 3.752 3.916 apply_single 119 13.6 0.000 0.001 3.752 3.916 ot_diis_step 108 11.5 0.004 0.004 3.709 3.710 init_scf_loop 11 6.9 0.000 0.000 3.555 3.555 fft3d_ps 1201 14.6 1.539 1.697 2.991 3.127 make_m2s 4572 13.5 0.053 0.058 2.985 3.083 init_scf_run 11 5.9 0.000 0.006 2.938 2.938 scf_env_initial_rho_setup 11 6.9 0.000 0.005 2.937 2.938 transfer_pw2rs 487 13.2 0.007 0.008 2.919 2.927 transfer_rs2pw 487 10.6 0.008 0.009 2.358 2.822 make_images 4572 14.5 0.129 0.135 2.604 2.695 wfi_extrapolate 11 7.9 0.001 0.001 2.650 2.654 mp_waitany 9880 13.7 1.847 2.308 1.847 2.308 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 2.293 2.305 qs_ot_get_p 119 10.4 0.001 0.001 1.781 2.047 transfer_rs2pw_140 130 11.5 0.277 0.338 1.355 1.824 mp_sum_l 11298 13.2 1.024 1.651 1.024 1.651 make_images_data 4572 15.5 0.042 0.049 1.445 1.574 transfer_pw2rs_140 130 13.9 0.455 0.514 1.524 1.564 prepare_preconditioner 11 7.9 0.000 0.000 1.414 1.430 make_preconditioner 11 8.9 0.000 0.000 1.413 1.430 hybrid_alltoall_any 4725 16.4 0.077 0.257 1.266 1.423 mp_alltoall_z22v 1201 16.6 1.127 1.409 1.127 1.409 make_full_inverse_cholesky 11 9.9 0.000 0.000 1.272 1.289 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 1.133 1.246 qs_ot_get_derivative_taylor 59 13.0 0.001 0.001 1.089 1.186 transfer_pw2rs_50 119 14.3 0.391 0.435 1.076 1.180 mp_sum_d 4135 12.0 0.738 1.177 0.738 1.177 mp_alltoall_d11v 2130 13.8 0.946 1.164 0.946 1.164 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.001 1.024 1.116 cp_dbcsr_sm_fm_multiply 37 9.5 0.001 0.001 1.099 1.104 ------------------------------------------------------------------------------- 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=66.579, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=16.767, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=12.143, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=7.437, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=5.908, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="make_dense_data", label="make_dense_data", y=5.407, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="mp_waitany", label="mp_waitany", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 Plot: name="H2O-64_timings_32mpi", title="Timings of H2O-64 with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="H2O-64_timings_32mpi", name="rest", label="rest", y=19.867000000000004, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=10.498, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=9.434, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=3.832, 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="make_dense_data", label="make_dense_data", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitany", label="mp_waitany", y=1.847, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=9.18, 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 0.038 0.038 131.368 131.368 qs_mol_dyn_low 1 2.0 0.003 0.003 130.693 130.693 qs_forces 11 3.9 0.002 0.002 130.648 130.648 qs_energies 11 4.9 0.001 0.001 121.525 121.525 scf_env_do_scf 11 5.9 0.002 0.002 106.687 106.687 scf_env_do_scf_inner_loop 96 6.5 0.013 0.013 85.801 85.801 velocity_verlet 10 3.0 0.002 0.002 84.311 84.311 rebuild_ks_matrix 107 8.3 0.001 0.001 39.663 39.663 qs_ks_build_kohn_sham_matrix 107 9.3 0.013 0.013 39.662 39.662 qs_rho_update_rho_low 107 7.7 0.001 0.001 37.109 37.109 calculate_rho_elec 107 8.7 0.910 0.910 37.108 37.108 qs_ks_update_qs_env 107 7.6 0.001 0.001 35.429 35.429 grid_collocate_task_list 107 9.7 32.305 32.305 32.305 32.305 sum_up_and_integrate 107 10.3 0.873 0.873 31.869 31.869 integrate_v_rspace 107 11.3 0.140 0.140 30.996 30.996 grid_integrate_task_list 107 12.3 28.526 28.526 28.526 28.526 dbcsr_multiply_generic 1966 12.4 0.165 0.165 21.582 21.582 qs_scf_new_mos 96 7.5 0.001 0.001 21.156 21.156 qs_scf_loop_do_ot 96 8.5 0.001 0.001 21.155 21.155 init_scf_loop 11 6.9 0.000 0.000 20.702 20.702 ot_scf_mini 96 9.5 0.003 0.003 19.766 19.766 prepare_preconditioner 11 7.9 0.000 0.000 15.990 15.990 make_preconditioner 11 8.9 0.000 0.000 15.990 15.990 make_full_inverse_cholesky 11 9.9 0.028 0.028 14.734 14.734 ot_mini 96 10.5 0.001 0.001 12.702 12.702 make_m2s 3932 13.4 0.046 0.046 11.086 11.086 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 7.922 7.922 pw_transfer 1295 11.6 0.070 0.070 7.135 7.135 fft_wrap_pw1pw2 1081 12.6 0.007 0.007 6.848 6.848 qs_ot_get_derivative 96 11.5 0.001 0.001 6.848 6.848 multiply_cannon 1966 13.4 0.256 0.256 6.586 6.586 init_scf_run 11 5.9 0.003 0.003 6.172 6.172 scf_env_initial_rho_setup 11 6.9 0.002 0.002 6.169 6.169 fft_wrap_pw1pw2_140 439 13.2 0.565 0.565 5.941 5.941 multiply_cannon_loop 1966 14.4 0.058 0.058 5.928 5.928 multiply_cannon_multrec 1966 15.4 5.818 5.818 5.869 5.869 ot_diis_step 96 11.5 0.003 0.003 5.851 5.851 make_images 3932 14.4 2.323 2.323 5.810 5.810 dbcsr_make_dense_low 4961 15.5 0.092 0.092 5.638 5.638 cp_fm_cholesky_decompose 22 10.9 5.568 5.568 5.568 5.568 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 5.554 5.554 apply_single 107 13.6 0.000 0.000 5.554 5.554 make_dense_data 4961 16.5 4.947 4.947 5.532 5.532 wfi_extrapolate 11 7.9 0.001 0.001 5.447 5.447 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 5.140 5.140 dbcsr_make_images_dense 3386 14.7 0.016 0.016 4.887 4.887 cp_fm_cholesky_invert 11 10.9 4.806 4.806 4.806 4.806 qs_env_update_s_mstruct 11 6.9 0.000 0.000 4.332 4.332 dbcsr_copy 1855 11.9 0.266 0.266 4.318 4.318 dbcsr_copy_into_existing 22 7.9 3.982 3.982 3.982 3.982 build_core_hamiltonian_matrix_ 11 4.9 0.001 0.001 3.980 3.980 dbcsr_complete_redistribute 317 12.2 2.034 2.034 3.939 3.939 density_rs2pw 107 9.7 0.005 0.005 3.894 3.894 qs_create_task_list 11 7.9 0.000 0.000 3.841 3.841 generate_qs_task_list 11 8.9 2.399 2.399 3.841 3.841 fft3d_s 1082 14.6 3.510 3.510 3.515 3.515 qs_ot_get_p 107 10.4 0.001 0.001 3.479 3.479 copy_dbcsr_to_fm 147 11.2 0.003 0.003 3.288 3.288 build_core_hamiltonian_matrix 11 6.9 0.001 0.001 3.136 3.136 ------------------------------------------------------------------------------- From /workspace/artifacts/H2O-64_nonortho_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.009 0.029 86.059 86.071 qs_mol_dyn_low 1 2.0 0.003 0.005 85.902 85.907 qs_forces 11 3.9 0.002 0.002 85.852 85.853 qs_energies 11 4.9 0.001 0.001 80.215 80.221 scf_env_do_scf 11 5.9 0.000 0.002 74.181 74.182 scf_env_do_scf_inner_loop 96 6.5 0.003 0.021 68.682 68.682 velocity_verlet 10 3.0 0.001 0.003 51.120 51.121 rebuild_ks_matrix 107 8.3 0.001 0.001 36.279 36.335 qs_ks_build_kohn_sham_matrix 107 9.3 0.017 0.020 36.278 36.334 qs_ks_update_qs_env 107 7.6 0.001 0.001 31.957 32.007 sum_up_and_integrate 107 10.3 0.041 0.045 31.529 31.545 integrate_v_rspace 107 11.3 0.005 0.005 31.488 31.512 qs_rho_update_rho_low 107 7.7 0.001 0.001 31.205 31.212 calculate_rho_elec 107 8.7 0.030 0.035 31.204 31.211 grid_integrate_task_list 107 12.3 26.462 26.825 26.462 26.825 grid_collocate_task_list 107 9.7 25.767 26.790 25.767 26.790 dbcsr_multiply_generic 1966 12.4 0.081 0.088 15.361 15.503 qs_scf_new_mos 96 7.5 0.001 0.001 12.441 12.505 qs_scf_loop_do_ot 96 8.5 0.001 0.001 12.440 12.504 ot_scf_mini 96 9.5 0.002 0.003 11.772 11.831 multiply_cannon 1966 13.4 0.146 0.165 11.172 11.637 multiply_cannon_loop 1966 14.4 0.104 0.118 10.544 10.905 mp_waitall_1 136719 16.5 8.522 8.856 8.522 8.856 ot_mini 96 10.5 0.001 0.001 7.015 7.079 multiply_cannon_metrocomm3 15728 15.4 0.045 0.049 6.511 6.804 density_rs2pw 107 9.7 0.006 0.007 4.973 5.708 init_scf_loop 11 6.9 0.000 0.000 5.480 5.481 init_scf_run 11 5.9 0.000 0.006 4.757 4.757 scf_env_initial_rho_setup 11 6.9 0.000 0.004 4.757 4.757 pw_transfer 1295 11.6 0.071 0.078 4.459 4.545 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 4.469 4.477 fft_wrap_pw1pw2 1081 12.6 0.009 0.010 4.310 4.388 wfi_extrapolate 11 7.9 0.001 0.001 4.344 4.344 potential_pw2rs 107 12.3 0.006 0.007 3.931 3.956 fft_wrap_pw1pw2_140 439 13.2 0.708 0.804 3.646 3.837 multiply_cannon_multrec 15728 15.4 3.614 3.786 3.626 3.797 transfer_rs2pw 439 10.6 0.007 0.008 2.931 3.721 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 3.553 3.658 apply_single 107 13.6 0.000 0.001 3.553 3.657 qs_ot_get_derivative 96 11.5 0.001 0.001 3.529 3.593 mp_waitany 8968 13.7 2.560 3.478 2.560 3.478 ot_diis_step 96 11.5 0.003 0.003 3.461 3.461 fft3d_ps 1081 14.6 1.427 1.575 2.776 2.955 make_m2s 3932 13.4 0.048 0.053 2.864 2.935 transfer_rs2pw_140 118 11.5 0.225 0.261 2.028 2.820 transfer_pw2rs 439 13.2 0.006 0.008 2.760 2.766 make_images 3932 14.4 0.117 0.121 2.517 2.580 mp_alltoall_d11v 1998 13.7 1.391 2.029 1.391 2.029 qs_ot_get_p 107 10.4 0.001 0.001 1.674 1.763 ------------------------------------------------------------------------------- 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=54.20399999999999, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=32.305, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=28.526, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=5.818, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=5.568, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="make_dense_data", label="make_dense_data", y=4.947, 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=19.134, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=25.767, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=26.462, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=3.614, 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=2.56, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=8.522, 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 0.240 0.240 158.721 158.721 qs_energies 1 2.0 0.000 0.000 157.850 157.850 scf_env_do_scf 1 3.0 0.000 0.000 156.557 156.557 qs_ks_update_qs_env 8 5.0 0.000 0.000 150.780 150.780 rebuild_ks_matrix 7 6.0 0.000 0.000 150.719 150.719 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.001 150.719 150.719 hfx_ks_matrix 7 8.0 0.000 0.000 140.351 140.351 integrate_four_center 7 9.0 2.142 2.142 140.155 140.155 integrate_four_center_main 7 10.0 0.588 0.588 123.670 123.670 integrate_four_center_bin 454 11.0 123.082 123.082 123.082 123.082 scf_env_do_scf_inner_loop 7 4.0 0.001 0.001 88.280 88.280 init_scf_loop 1 4.0 0.000 0.000 68.267 68.267 integrate_four_center_load 7 10.0 0.001 0.001 13.884 13.884 hfx_load_balance 1 11.0 0.001 0.001 13.884 13.884 hfx_load_balance_count 1 12.0 6.968 6.968 6.968 6.968 hfx_load_balance_bin 1 12.0 6.897 6.897 6.897 6.897 qs_vxc_create 14 8.0 0.000 0.000 3.812 3.812 xc_vxc_pw_create 14 9.0 0.161 0.161 3.811 3.811 ------------------------------------------------------------------------------- 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 0.275 0.304 152.532 152.546 qs_energies 1 2.0 0.000 0.000 152.054 152.067 scf_env_do_scf 1 3.0 0.000 0.000 151.659 151.660 qs_ks_update_qs_env 8 5.0 0.000 0.000 149.164 149.165 rebuild_ks_matrix 7 6.0 0.000 0.000 149.155 149.156 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.001 149.155 149.156 hfx_ks_matrix 7 8.0 0.000 0.000 142.761 142.764 integrate_four_center 7 9.0 0.062 0.383 142.750 142.753 integrate_four_center_main 7 10.0 0.004 0.005 119.996 128.000 integrate_four_center_bin 448 11.0 119.992 127.996 119.992 127.996 scf_env_do_scf_inner_loop 7 4.0 0.000 0.001 89.723 89.724 init_scf_loop 1 4.0 0.000 0.000 61.934 61.934 mp_sync 56 11.2 8.169 15.255 8.169 15.255 integrate_four_center_load 7 10.0 0.000 0.000 13.823 13.834 hfx_load_balance 1 11.0 0.001 0.001 13.823 13.834 hfx_load_balance_count 1 12.0 6.813 6.920 6.813 6.920 hfx_load_balance_bin 1 12.0 6.814 6.911 6.814 6.911 ------------------------------------------------------------------------------- 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=18.80400000000003, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_bin", label="integrate_four_center_bin", y=123.082, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_count", label="hfx_load_balance_count", y=6.968, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=6.897, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center", label="integrate_four_center", y=2.142, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_main", label="integrate_four_center_main", y=0.588, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="CP2K", label="CP2K", y=0.24, 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=10.402999999999992, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center_bin", label="integrate_four_center_bin", y=119.992, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_count", label="hfx_load_balance_count", y=6.813, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=6.814, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center", label="integrate_four_center", y=0.062, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center_main", label="integrate_four_center_main", y=0.004, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="CP2K", label="CP2K", y=0.275, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="mp_sync", label="mp_sync", y=8.169, 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 0.018 0.018 79.181 79.181 qs_energies 1 2.0 0.000 0.000 78.776 78.776 mp2_main 1 3.0 0.000 0.000 75.802 75.802 mp2_gpw_main 1 4.0 0.000 0.000 75.689 75.689 rpa_ri_compute_en 1 5.0 0.000 0.000 72.005 72.005 rpa_num_int 1 6.0 0.002 0.002 71.999 71.999 compute_mat_P_omega 1 7.0 0.005 0.005 61.710 61.710 compute_mat_P_omega_contract 10 8.0 9.110 9.110 61.504 61.504 dbt_total 2336 9.6 0.014 0.014 47.419 47.419 dbt_contract 787 11.0 0.042 0.042 40.152 40.152 dbt_tas_total 1149 12.2 0.243 0.243 38.550 38.550 dbt_tas_multiply 807 12.1 0.002 0.002 37.358 37.358 dbt_tas_dbm 807 14.1 0.003 0.003 31.042 31.042 dbm_multiply 807 16.1 31.034 31.034 31.034 31.034 dbt_tas_mm_1N 524 15.1 0.002 0.002 23.478 23.478 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 22.344 22.344 compute_mat_P_omega_calc_M_occ 250 9.0 9.102 9.102 17.382 17.382 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 6.793 6.793 dbt_copy 1103 10.7 0.120 0.120 6.056 6.056 dbt_tas_mm_2 251 15.0 0.001 0.001 6.004 6.004 compute_QP_energies 1 7.0 0.000 0.000 5.141 5.141 compute_self_energy_cubic_gw 1 8.0 0.055 0.055 5.139 5.139 contract_cubic_gw 21 9.0 0.000 0.000 4.088 4.088 dbt_tas_reserve_blocks_index 3261 14.3 0.483 0.483 3.950 3.950 mp2_ri_gpw_compute_in 1 5.0 0.001 0.001 3.676 3.676 dbm_reserve_blocks 3628 15.3 3.542 3.542 3.542 3.542 dbt_reserve_blocks_index 2280 13.1 0.055 0.055 3.003 3.003 dbt_reserve_blocks_index_array 2222 12.2 0.008 0.008 2.949 2.949 scf_env_do_scf 1 3.0 0.000 0.000 2.849 2.849 scf_env_do_scf_inner_loop 17 4.0 0.002 0.002 2.849 2.849 dbt_crop 1042 12.0 1.553 1.553 2.674 2.674 dbt_tas_copy 574 11.4 1.351 1.351 2.378 2.378 convert_to_new_pgrid 2421 14.1 0.164 0.164 2.209 2.209 compute_W_cubic_GW 10 7.0 0.004 0.004 2.094 2.094 dbm_copy 1614 15.1 2.045 2.045 2.045 2.045 rpa_num_int_RPA_matrix_operati 10 7.0 0.000 0.000 2.036 2.036 dbt_reshape 278 11.9 1.130 1.130 2.026 2.026 dbt_tas_reshape 367 15.0 0.032 0.032 1.888 1.888 get_2c_integrals 1 6.0 0.000 0.000 1.720 1.720 compute_mat_P_omega_copy_M_occ 250 9.0 0.001 0.001 1.637 1.637 ------------------------------------------------------------------------------- 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 0.008 0.036 38.790 38.810 qs_energies 1 2.0 0.000 0.000 38.646 38.647 mp2_main 1 3.0 0.000 0.001 37.519 37.520 mp2_gpw_main 1 4.0 0.000 0.001 37.413 37.415 rpa_ri_compute_en 1 5.0 0.000 0.000 35.934 35.935 rpa_num_int 1 6.0 0.000 0.003 35.933 35.934 dbt_total 2336 9.6 0.017 0.018 31.965 32.043 compute_mat_P_omega 1 7.0 0.001 0.008 30.823 30.843 compute_mat_P_omega_contract 10 8.0 0.456 0.474 30.463 30.476 dbt_contract 787 11.0 0.045 0.046 23.531 23.539 dbt_tas_total 1149 12.2 0.089 0.099 20.854 20.858 dbt_tas_multiply 807 12.1 0.002 0.002 20.725 20.728 dbt_tas_dbm 807 14.1 0.003 0.004 15.171 15.186 dbm_multiply 807 16.1 11.924 12.743 11.924 12.743 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 9.068 9.071 compute_mat_P_omega_calc_M_occ 250 9.0 0.439 0.454 8.986 8.987 dbt_copy 1149 10.8 0.015 0.017 7.163 7.524 dbt_tas_mm_2 251 15.0 0.002 0.002 7.262 7.272 mp_sync 8688 11.6 5.848 7.247 5.848 7.247 dbt_reshape 1136 11.8 3.035 3.235 6.802 7.148 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 6.208 6.209 dbt_tas_mm_1N 524 15.1 0.002 0.002 5.247 6.111 compute_QP_energies 1 7.0 0.000 0.000 3.298 3.301 compute_self_energy_cubic_gw 1 8.0 0.003 0.003 3.297 3.298 mp_waitall_2 3812 15.3 2.811 3.060 2.811 3.060 dbt_communicate_buffer 1136 12.8 0.059 0.063 2.775 2.945 contract_cubic_gw 21 9.0 0.000 0.000 2.570 2.570 dbt_reserve_blocks_index 2887 13.1 0.076 0.084 2.017 2.285 dbt_reserve_blocks_index_array 2829 12.2 0.009 0.010 2.007 2.273 dbt_tas_reserve_blocks_index 3347 14.5 0.484 0.526 1.998 2.259 dbt_crop 1042 12.0 1.018 1.126 1.644 1.864 dbm_reserve_blocks 3752 15.4 1.621 1.851 1.621 1.851 mp2_ri_gpw_compute_in 1 5.0 0.003 0.004 1.474 1.475 dbt_tas_replicate 405 14.1 0.613 0.798 1.296 1.366 compute_mat_P_omega_copy_M_vir 250 9.0 0.001 0.001 1.275 1.278 compute_mat_P_omega_copy_M_occ 250 9.0 0.001 0.001 1.174 1.177 parallel_gemm_fm 105 8.4 0.000 0.000 1.110 1.118 parallel_gemm_fm_cosma 105 9.4 1.110 1.118 1.110 1.118 scf_env_do_scf 1 3.0 0.000 0.000 1.069 1.069 scf_env_do_scf_inner_loop 17 4.0 0.000 0.002 1.069 1.069 convert_to_new_pgrid 2421 14.1 0.028 0.032 0.874 1.024 dbm_copy 1608 15.1 0.840 0.990 0.840 0.990 mp_max_i 2004 9.8 0.766 0.976 0.766 0.976 compute_W_cubic_GW 10 7.0 0.001 0.001 0.830 0.838 mp_sum_l 6165 12.9 0.675 0.783 0.675 0.783 ------------------------------------------------------------------------------- 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=23.217999999999996, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=31.034, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=9.11, 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=9.102, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=3.542, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_copy", label="dbm_copy", y=2.045, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=1.13, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="mp_sync", label="mp_sync", y=0.0, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="mp_waitall_2", label="mp_waitall_2", y=0.0, yerr=0.0 Plot: name="GW_PBE_4benzene_timings_32mpi", title="Timings of GW_PBE_4benzene with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="rest", label="rest", y=11.816000000000003, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=11.924, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=0.456, 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=0.439, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=1.621, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_copy", label="dbm_copy", y=0.84, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=3.035, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_sync", label="mp_sync", y=5.848, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.811, 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 0.027 0.027 245.004 245.004 qs_forces 1 2.0 0.000 0.000 244.460 244.460 rebuild_ks_matrix 7 6.6 0.000 0.000 242.841 242.841 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.001 242.841 242.841 hfx_ks_matrix 7 8.6 0.000 0.000 240.762 240.762 hfx_ri_update_ks 7 9.6 0.000 0.000 196.575 196.575 hfx_ri_update_ks_Pmat 7 10.6 33.296 33.296 196.570 196.570 dbt_total 809 11.0 0.007 0.007 182.871 182.871 qs_energies 1 3.0 0.000 0.000 173.777 173.777 scf_env_do_scf 1 4.0 0.000 0.000 173.463 173.463 qs_ks_update_qs_env 8 6.0 0.000 0.000 172.219 172.219 dbt_contract 207 12.4 0.107 0.107 160.894 160.894 dbt_tas_total 343 13.7 1.340 1.340 158.291 158.291 dbt_tas_multiply 216 13.5 0.001 0.001 154.683 154.683 dbt_tas_dbm 216 15.5 0.001 0.001 142.494 142.494 dbm_multiply 216 17.5 142.490 142.490 142.490 142.490 hfx_ri_update_ks_Pmat_KS 63 11.6 0.001 0.001 136.149 136.149 dbt_tas_mm_2 91 16.5 0.001 0.001 127.018 127.018 scf_env_do_scf_inner_loop 6 5.0 0.001 0.001 109.279 109.279 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 70.626 70.626 init_scf_loop 2 5.0 0.000 0.000 64.181 64.181 hfx_ri_update_forces 1 7.0 1.710 1.710 44.183 44.183 hfx_ri_forces_Pmat_3c 1 8.0 4.990 4.990 24.791 24.791 dbt_copy 409 11.7 0.085 0.085 18.359 18.359 precalc_derivatives 1 8.0 2.360 2.360 14.919 14.919 dbt_reshape 132 13.2 8.025 8.025 12.717 12.717 dbt_tas_mm_3T 77 17.1 0.000 0.000 10.670 10.670 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 9.914 9.914 dbt_tas_reserve_blocks_index 1255 15.4 1.075 1.075 9.204 9.204 dbm_reserve_blocks 1397 16.3 8.320 8.320 8.320 8.320 build_3c_derivatives 3 9.0 3.005 3.005 8.216 8.216 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 7.846 7.846 dbt_reserve_blocks_index 818 14.4 0.126 0.126 7.193 7.193 dbt_reserve_blocks_index_array 795 13.4 0.008 0.008 7.052 7.052 dbt_crop 372 13.7 3.222 3.222 5.731 5.731 hfx_ri_update_ks_Pmat_copy_2 63 11.6 0.000 0.000 5.529 5.529 ------------------------------------------------------------------------------- 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 0.031 53.529 53.543 qs_forces 1 2.0 0.000 0.000 53.357 53.357 rebuild_ks_matrix 7 6.6 0.000 0.000 52.506 52.507 qs_ks_build_kohn_sham_matrix 7 7.6 0.002 0.002 52.506 52.507 hfx_ks_matrix 7 8.6 0.000 0.000 51.390 51.398 dbt_total 809 11.0 0.006 0.007 45.979 45.989 dbt_contract 207 12.4 0.027 0.028 35.687 35.698 dbt_tas_total 343 13.7 0.087 0.226 31.718 31.726 dbt_tas_multiply 216 13.5 0.001 0.001 31.371 31.375 hfx_ri_update_ks 7 9.6 0.000 0.000 31.299 31.300 hfx_ri_update_ks_Pmat 7 10.6 1.381 1.463 31.294 31.295 qs_energies 1 3.0 0.000 0.000 29.499 29.499 scf_env_do_scf 1 4.0 0.000 0.001 29.346 29.346 qs_ks_update_qs_env 8 6.0 0.000 0.000 28.661 28.662 dbt_tas_dbm 216 15.5 0.001 0.001 24.050 24.060 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 23.846 23.846 dbm_multiply 216 17.5 21.765 22.440 21.765 22.440 hfx_ri_update_forces 1 7.0 0.063 0.066 20.090 20.097 scf_env_do_scf_inner_loop 6 5.0 0.000 0.001 16.249 16.249 hfx_ri_forces_Pmat_3c 1 8.0 0.180 0.192 14.843 14.843 hfx_ri_update_ks_Pmat_KS 63 11.6 0.001 0.001 14.619 14.631 init_scf_loop 2 5.0 0.000 0.000 13.095 13.095 dbt_tas_mm_2 91 16.5 0.001 0.001 11.654 11.664 dbt_copy 497 12.3 0.012 0.013 9.292 9.579 dbt_reshape 365 13.6 3.892 3.977 7.257 7.498 dbt_tas_mm_3T 77 17.1 0.000 0.000 6.021 6.461 mp_sync 2769 12.9 4.981 6.219 4.981 6.219 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 6.103 6.104 dbt_tas_mm_3N 37 15.4 0.000 0.000 4.537 4.657 precalc_derivatives 1 8.0 0.095 0.101 3.949 3.949 dbt_tas_reserve_blocks_index 1380 15.8 0.984 1.019 3.363 3.667 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 3.345 3.345 mp_waitall_2 1234 16.4 3.045 3.223 3.045 3.223 dbt_reserve_blocks_index 1051 14.7 0.123 0.131 2.804 3.096 dbt_reserve_blocks_index_array 1028 13.8 0.005 0.007 2.778 3.069 dbm_reserve_blocks 1529 16.7 2.583 2.885 2.583 2.885 dbt_crop 372 13.7 1.908 1.980 2.753 2.849 dbt_communicate_buffer 365 14.6 0.013 0.014 2.187 2.339 build_3c_derivatives 3 9.0 0.258 0.277 2.225 2.234 hfx_ri_update_ks_Pmat_copy_2 63 11.6 0.000 0.000 1.913 1.913 dbt_tas_replicate 149 15.4 0.668 0.694 1.725 1.801 hfx_ri_pre_scf_Pmat_RIx3C 9 13.0 0.000 0.000 1.725 1.730 convert_to_new_pgrid 648 15.5 0.041 0.087 1.411 1.701 dbm_copy 452 16.3 1.229 1.526 1.229 1.526 dbt_tas_copy 132 12.5 0.658 0.685 1.284 1.400 mp_sum_l 6385 13.7 1.063 1.200 1.063 1.200 ------------------------------------------------------------------------------- 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=47.88299999999998, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=142.49, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=33.296, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=8.32, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=8.025, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_forces_Pmat_3c", label="hfx_ri_forces_Pmat_3c", y=4.99, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="mp_sync", label="mp_sync", y=0.0, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="mp_waitall_2", label="mp_waitall_2", y=0.0, yerr=0.0 Plot: name="RI-HFX_H2O-32_timings_32mpi", title="Timings of RI-HFX_H2O-32 with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="rest", label="rest", y=15.702000000000005, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=21.765, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=1.381, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=2.583, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=3.892, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_forces_Pmat_3c", label="hfx_ri_forces_Pmat_3c", y=0.18, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_sync", label="mp_sync", y=4.981, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=3.045, 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 0.018 0.018 184.164 184.164 qs_energies 1 2.0 0.000 0.000 183.969 183.969 mp2_main 1 3.0 0.000 0.000 178.316 178.316 mp2_gpw_main 1 4.0 0.001 0.001 177.856 177.856 mp2_ri_gpw_compute_in 1 5.0 0.398 0.398 126.987 126.987 mp2_ri_gpw_compute_in_loop 1 6.0 0.010 0.010 116.689 116.689 mp2_eri_3c_integrate_gpw 2656 7.0 0.014 0.014 85.178 85.178 integrate_v_rspace 2666 8.0 0.715 0.715 71.942 71.942 grid_integrate_task_list 2666 9.0 69.156 69.156 69.156 69.156 mp2_ri_gpw_compute_en 1 5.0 0.086 0.086 50.841 50.841 mp2_ri_gpw_compute_en_RI_loop 1 6.0 9.572 9.572 48.963 48.963 mp2_ri_gpw_compute_en_expansio 2080 7.0 1.951 1.951 31.980 31.980 local_gemm 2080 8.0 30.029 30.029 30.029 30.029 dbcsr_multiply_generic 5322 8.0 0.202 0.202 23.948 23.948 ao_to_mo_and_store_B_mult_1 2656 7.0 0.010 0.010 23.919 23.919 pw_transfer 63872 10.6 1.040 1.040 12.900 12.900 calculate_wavefunction 2656 8.0 7.996 7.996 11.814 11.814 multiply_cannon 5322 9.0 0.461 0.461 11.694 11.694 fft_wrap_pw1pw2 53228 11.4 0.115 0.115 11.617 11.617 multiply_cannon_loop 5322 10.0 0.177 0.177 10.268 10.268 get_2c_integrals 1 6.0 0.000 0.000 9.898 9.898 make_m2s 10644 9.0 0.069 0.069 9.880 9.880 make_images 10644 10.0 3.840 3.840 9.544 9.544 compute_2c_integrals 1 7.0 0.007 0.007 8.927 8.927 compute_2c_integrals_loop_lm 1 8.0 0.012 0.012 8.909 8.909 mp2_eri_2c_integrate_gpw 1 9.0 0.991 0.991 8.897 8.897 multiply_cannon_multrec 5322 11.0 8.556 8.556 8.599 8.599 fft_wrap_pw1pw2_20 21271 12.4 0.571 0.571 8.220 8.220 ao_to_mo_and_store_B_E_Ex_1 2656 7.0 2.391 2.391 7.474 7.474 fft3d_s 53229 13.4 7.061 7.061 7.102 7.102 copy_dbcsr_to_fm 2679 8.0 0.027 0.027 5.664 5.664 mp2_ri_gpw_compute_en_ener 2080 7.0 5.560 5.560 5.560 5.560 scf_env_do_scf 1 3.0 0.000 0.000 5.186 5.186 scf_env_do_scf_inner_loop 10 4.0 0.001 0.001 5.186 5.186 potential_pw2rs 5322 10.0 0.157 0.157 4.517 4.517 mp2_eri_2c_integrate_gpw_pot_l 2656 10.0 0.006 0.006 4.093 4.093 make_images_data 10644 11.0 0.085 0.085 3.953 3.953 hybrid_alltoall_any 13323 11.6 3.725 3.725 3.944 3.944 dbcsr_complete_redistribute 2689 9.0 1.260 1.260 3.927 3.927 qs_scf_new_mos 10 5.0 0.000 0.000 3.771 3.771 collocate_single_gaussian 2656 10.0 0.153 0.153 3.699 3.699 ------------------------------------------------------------------------------- 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 0.009 0.033 44.907 44.921 qs_energies 1 2.0 0.000 0.000 44.769 44.770 mp2_main 1 3.0 0.000 0.001 42.555 42.556 mp2_gpw_main 1 4.0 0.001 0.002 42.451 42.451 mp2_ri_gpw_compute_en 1 5.0 0.325 0.347 22.296 22.602 mp2_ri_gpw_compute_en_RI_loop 1 6.0 4.036 4.510 20.775 20.781 mp2_ri_gpw_compute_in 1 5.0 0.045 0.046 20.059 20.627 mp2_ri_gpw_compute_in_loop 1 6.0 0.001 0.001 18.605 19.174 mp2_eri_3c_integrate_gpw 83 7.0 0.001 0.001 16.113 16.373 integrate_v_rspace 93 8.1 0.119 0.126 15.966 16.194 grid_integrate_task_list 93 9.1 15.614 15.843 15.614 15.843 mp2_ri_gpw_compute_en_expansio 65 7.0 0.167 0.183 12.443 12.608 local_gemm 65 8.0 12.276 12.442 12.276 12.442 mp2_ri_gpw_compute_en_comm 30 7.0 0.113 0.140 3.842 4.875 mp_sendrecv_dm3 1860 8.0 2.935 4.162 2.935 4.162 dbcsr_multiply_generic 176 8.0 0.009 0.010 2.122 2.418 ao_to_mo_and_store_B_mult_1 83 7.0 0.001 0.001 2.101 2.395 scf_env_do_scf 1 3.0 0.000 0.000 2.061 2.062 scf_env_do_scf_inner_loop 10 4.0 0.000 0.001 2.061 2.062 get_2c_integrals 1 6.0 0.004 0.012 1.380 1.407 multiply_cannon 176 9.0 0.018 0.023 1.225 1.308 multiply_cannon_loop 176 10.0 0.002 0.003 1.156 1.239 make_m2s 352 9.0 0.003 0.004 0.853 1.060 make_images 352 10.0 0.060 0.061 0.838 1.044 multiply_cannon_multrec 246 11.0 0.986 1.025 0.992 1.032 compute_2c_integrals 1 7.0 0.003 0.004 1.003 1.017 fill_local_i_aL 1920 8.0 0.847 0.971 0.847 0.971 qs_scf_new_mos 10 5.0 0.000 0.000 0.948 0.959 compute_2c_integrals_loop_lm 1 8.0 0.002 0.003 0.887 0.927 mp2_eri_2c_integrate_gpw 1 9.0 0.230 0.242 0.886 0.925 ------------------------------------------------------------------------------- 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=58.85499999999999, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=69.156, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="local_gemm", label="local_gemm", y=30.029, 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=9.572, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=8.556, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="calculate_wavefunction", label="calculate_wavefunction", y=7.996, 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=9.059999999999995, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=15.614, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="local_gemm", label="local_gemm", y=12.276, 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=4.036, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=0.986, 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=2.935, 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 0.096 0.096 129.399 129.399 qs_energies 1 2.0 0.000 0.000 128.080 128.080 scf_env_do_scf 1 3.0 0.000 0.000 119.765 119.765 scf_env_do_scf_inner_loop 15 4.0 0.002 0.002 119.764 119.764 qs_ks_update_qs_env 15 5.0 0.000 0.000 50.537 50.537 rebuild_ks_matrix 15 6.0 0.000 0.000 50.326 50.326 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.002 50.326 50.326 qs_scf_new_mos 15 5.0 0.000 0.000 44.453 44.453 eigensolver 15 6.0 0.002 0.002 36.405 36.405 qs_vxc_create 15 8.0 0.030 0.030 34.455 34.455 calculate_dispersion_nonloc 15 9.0 7.065 7.065 30.118 30.118 pw_transfer 1191 10.0 0.062 0.062 23.628 23.628 fft_wrap_pw1pw2 1086 11.0 0.009 0.009 23.452 23.452 cp_fm_diag_elpa 15 7.0 0.000 0.000 23.201 23.201 cp_fm_diag_elpa_base 15 8.0 20.701 20.701 23.200 23.200 qs_rho_update_rho_low 16 5.0 0.000 0.000 21.047 21.047 calculate_rho_elec 16 6.0 0.224 0.224 21.047 21.047 grid_collocate_task_list 16 7.0 19.697 19.697 19.697 19.697 fft_wrap_pw1pw2_150 765 12.0 3.601 3.601 17.282 17.282 sum_up_and_integrate 15 8.0 0.133 0.133 14.690 14.690 integrate_v_rspace 15 9.0 0.021 0.021 14.556 14.556 grid_integrate_task_list 15 10.0 14.014 14.014 14.014 14.014 fft3d_s 1087 13.0 11.055 11.055 11.062 11.062 cp_fm_cholesky_restore 45 7.0 10.949 10.949 10.949 10.949 pw_scatter_s 585 13.1 6.969 6.969 6.969 6.969 fft_wrap_pw1pw2_200 197 12.3 0.714 0.714 5.984 5.984 copy_dbcsr_to_fm 16 5.9 0.001 0.001 5.692 5.692 dbcsr_complete_redistribute 46 8.3 2.273 2.273 5.664 5.664 gspace_mixing 14 5.0 0.171 0.171 4.841 4.841 cp_fm_upper_to_full 30 8.0 4.752 4.752 4.752 4.752 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 4.646 4.646 vdW_energy 15 10.0 4.393 4.393 4.393 4.393 xc_vxc_pw_create 15 9.0 0.213 0.213 4.307 4.307 broyden_mixing 14 6.0 4.239 4.239 4.239 4.239 build_core_hamiltonian_matrix 1 4.0 0.000 0.000 3.460 3.460 init_scf_run 1 3.0 0.001 0.001 3.160 3.160 xc_pw_derive 90 11.0 0.001 0.001 2.806 2.806 calculate_dm_sparse 15 6.0 0.017 0.017 2.707 2.707 cp_dbcsr_plus_fm_fm_t_native 15 7.0 0.000 0.000 2.622 2.622 ------------------------------------------------------------------------------- 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 0.016 0.038 61.000 61.012 qs_energies 1 2.0 0.000 0.000 60.658 60.667 scf_env_do_scf 1 3.0 0.000 0.001 56.437 56.437 scf_env_do_scf_inner_loop 15 4.0 0.001 0.003 56.437 56.437 qs_ks_update_qs_env 15 5.0 0.000 0.000 25.075 25.087 rebuild_ks_matrix 15 6.0 0.000 0.000 25.042 25.055 qs_ks_build_kohn_sham_matrix 15 7.0 0.003 0.003 25.042 25.055 qs_rho_update_rho_low 16 5.0 0.000 0.000 18.933 18.938 calculate_rho_elec 16 6.0 0.007 0.007 18.933 18.938 grid_collocate_task_list 16 7.0 17.743 17.947 17.743 17.947 sum_up_and_integrate 15 8.0 0.015 0.019 14.070 14.113 integrate_v_rspace 15 9.0 0.001 0.001 14.055 14.101 grid_integrate_task_list 15 10.0 13.175 13.281 13.175 13.281 qs_scf_new_mos 15 5.0 0.000 0.000 12.924 12.988 eigensolver 15 6.0 0.001 0.002 11.705 11.736 qs_vxc_create 15 8.0 0.001 0.001 10.628 10.642 calculate_dispersion_nonloc 15 9.0 0.911 0.937 8.513 8.542 pw_transfer 1191 10.0 0.079 0.097 8.456 8.495 fft_wrap_pw1pw2 1086 11.0 0.012 0.014 8.294 8.352 cp_fm_diag_elpa 15 7.0 0.000 0.000 8.143 8.148 cp_fm_diag_elpa_base 15 8.0 8.005 8.017 8.140 8.142 fft3d_ps 1086 13.0 2.749 3.172 5.701 6.177 fft_wrap_pw1pw2_150 765 12.0 0.576 0.727 5.376 5.406 cp_fm_cholesky_restore 45 7.0 3.405 3.464 3.405 3.464 mp_alltoall_z22v 1086 15.0 2.354 3.192 2.354 3.192 fft_wrap_pw1pw2_200 197 12.3 0.446 0.549 2.788 2.828 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 2.674 2.674 build_core_hamiltonian_matrix 1 4.0 0.000 0.000 2.368 2.578 xc_vxc_pw_create 15 9.0 0.016 0.020 2.115 2.149 x_to_yz 585 14.1 0.342 0.368 1.510 1.887 yz_to_x 501 13.9 0.231 0.270 1.417 1.854 build_core_ppnl 1 5.0 1.474 1.604 1.474 1.604 xc_pw_derive 90 11.0 0.001 0.002 1.457 1.530 vdW_energy 15 10.0 1.331 1.436 1.331 1.436 init_scf_run 1 3.0 0.000 0.001 1.319 1.320 scf_env_initial_rho_setup 1 4.0 0.000 0.000 1.220 1.221 ------------------------------------------------------------------------------- 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=52.98300000000002, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=20.701, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=19.697, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=14.014, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="fft3d_s", label="fft3d_s", y=11.055, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=10.949, 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=15.922999999999995, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=8.005, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=17.743, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.175, 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=3.405, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=2.749, 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 0.127 0.127 309.541 309.541 qs_energies 1 2.0 0.000 0.000 309.353 309.353 ls_scf 1 3.0 0.000 0.000 308.026 308.026 ls_scf_main 1 4.0 0.003 0.003 297.667 297.667 density_matrix_trs4 11 5.0 0.016 0.016 185.067 185.067 ls_scf_dm_to_ks 11 5.0 0.000 0.000 105.386 105.386 matrix_ls_to_qs 11 6.0 0.000 0.000 101.138 101.138 dbcsr_multiply_generic 185 6.1 1.158 1.158 93.344 93.344 arnoldi_extremal 12 6.1 0.000 0.000 68.637 68.637 arnoldi_normal_ev 12 7.1 0.071 0.071 68.637 68.637 build_subspace 23 8.1 0.109 0.109 67.333 67.333 dbcsr_matrix_vector_mult 652 9.0 0.363 0.363 66.968 66.968 dbcsr_matrix_vector_mult_local 652 10.0 64.853 64.853 64.865 64.865 dbcsr_complete_redistribute 23 7.5 38.106 38.106 54.357 54.357 multiply_cannon 185 7.1 0.510 0.510 52.499 52.499 dbcsr_copy_into_existing 11 7.0 51.723 51.723 51.723 51.723 matrix_decluster 11 7.0 0.000 0.000 49.412 49.412 multiply_cannon_loop 185 8.1 0.278 0.278 39.024 39.024 make_m2s 370 7.1 0.042 0.042 34.663 34.663 make_images 370 8.1 15.009 15.009 30.897 30.897 multiply_cannon_multrec 185 9.1 28.371 28.371 28.439 28.439 dbcsr_finalize 646 7.5 0.571 0.571 21.746 21.746 dbcsr_merge_all 597 8.5 3.257 3.257 19.738 19.738 tree_to_linear_d 110 9.4 14.515 14.515 14.515 14.515 dbcsr_sort_indices 1103 9.9 13.219 13.219 13.219 13.219 setup_rec_index_2d 370 8.1 12.826 12.826 12.826 12.826 quick_finalize 395 10.0 0.621 0.621 11.597 11.597 dbcsr_special_finalize 370 9.1 0.002 0.002 10.691 10.691 dbcsr_dot_sd 144 6.3 10.585 10.585 10.586 10.586 calculate_norms 370 9.1 10.307 10.307 10.307 10.307 ls_scf_init_scf 1 4.0 0.000 0.000 9.221 9.221 ls_scf_init_matrix_S 1 5.0 0.000 0.000 8.880 8.880 matrix_sqrt_Newton_Schulz 1 6.0 0.001 0.001 8.209 8.209 dbcsr_frobenius_norm 142 6.1 7.655 7.655 7.657 7.657 matrix_qs_to_ls 12 5.1 0.000 0.000 7.288 7.288 matrix_cluster 12 6.1 0.000 0.000 7.288 7.288 ------------------------------------------------------------------------------- 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 0.009 0.025 74.437 74.450 qs_energies 1 2.0 0.000 0.000 74.329 74.330 ls_scf 1 3.0 0.000 0.000 74.277 74.278 ls_scf_main 1 4.0 0.001 0.008 71.493 71.494 density_matrix_trs4 11 5.0 0.006 0.019 68.872 68.949 dbcsr_multiply_generic 185 6.1 0.060 0.066 65.507 65.762 multiply_cannon 185 7.1 0.034 0.037 54.176 55.089 multiply_cannon_loop 185 8.1 0.121 0.129 51.640 53.269 multiply_cannon_multrec 1480 9.1 31.178 33.573 31.439 33.827 mp_waitall_1 11936 10.3 18.038 22.617 18.038 22.617 multiply_cannon_metrocomm3 1480 9.1 0.016 0.018 13.654 18.321 make_m2s 370 7.1 0.036 0.040 7.509 7.568 make_images 370 8.1 0.639 0.665 7.375 7.431 calculate_norms 2960 9.1 5.187 5.570 5.187 5.570 mp_sum_l 1199 5.3 2.950 3.783 2.950 3.783 make_images_data 370 9.1 0.010 0.013 3.497 3.764 hybrid_alltoall_any 393 9.9 0.261 1.388 3.049 3.412 dbcsr_multiply_generic_mpsum_f 137 7.1 0.000 0.000 2.067 2.822 arnoldi_extremal 12 6.1 0.000 0.001 2.609 2.623 arnoldi_normal_ev 12 7.1 0.001 0.008 2.608 2.623 build_subspace 23 8.1 0.020 0.026 2.495 2.497 ls_scf_dm_to_ks 11 5.0 0.000 0.000 2.258 2.333 multiply_cannon_metrocomm1 1480 9.1 0.006 0.008 1.200 2.247 dbcsr_matrix_vector_mult 652 9.0 0.014 0.053 2.129 2.178 dbcsr_complete_redistribute 23 7.5 1.222 1.304 2.057 2.145 ls_scf_init_scf 1 4.0 0.000 0.000 2.106 2.107 ls_scf_init_matrix_S 1 5.0 0.000 0.000 2.076 2.085 matrix_ls_to_qs 11 6.0 0.000 0.000 1.972 2.058 make_images_pack 370 9.1 1.795 1.979 1.798 1.982 matrix_decluster 11 7.0 0.000 0.000 1.847 1.933 matrix_sqrt_Newton_Schulz 1 6.0 0.000 0.001 1.881 1.882 dbcsr_matrix_vector_mult_local 652 10.0 1.723 1.821 1.725 1.823 buffer_matrices_ensure_size 370 8.1 1.454 1.671 1.454 1.671 ------------------------------------------------------------------------------- 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=101.172, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=64.853, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_copy_into_existing", label="dbcsr_copy_into_existing", y=51.723, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_complete_redistribute", label="dbcsr_complete_redistribute", y=38.106, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=28.371, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="make_images", label="make_images", y=15.009, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="calculate_norms", label="calculate_norms", y=10.307, 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="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=11.704999999999984, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=1.723, 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=1.222, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=31.178, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="make_images", label="make_images", y=0.639, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="calculate_norms", label="calculate_norms", y=5.187, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=2.95, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="make_images_pack", label="make_images_pack", y=1.795, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=18.038, 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 0.010 0.010 87.251 87.251 lib_test 1 2.0 0.000 0.000 87.240 87.240 dbcsr_run_tests 3 3.0 0.002 0.002 87.240 87.240 test_multiplies_multiproc 3 4.0 0.001 0.001 69.061 69.061 dbcsr_redistribute 9 5.0 41.125 41.125 43.343 43.343 dbcsr_multiply_generic 9 5.0 0.002 0.002 23.389 23.389 dbcsr_make_random_matrix 9 4.0 13.561 13.561 18.004 18.004 multiply_cannon 9 6.0 0.003 0.003 16.080 16.080 multiply_cannon_loop 9 7.0 0.037 0.037 15.653 15.653 multiply_cannon_multrec 9 8.0 15.614 15.614 15.616 15.616 dbcsr_finalize 27 5.7 0.044 0.044 8.086 8.086 dbcsr_merge_all 18 6.5 2.714 2.714 6.839 6.839 dbcsr_data_release 975 7.6 4.583 4.583 4.583 4.583 tree_to_linear_d 9 7.0 3.006 3.006 3.006 3.006 make_m2s 18 6.0 0.001 0.001 2.646 2.646 make_images 18 7.0 0.904 0.904 2.427 2.427 dbcsr_destroy 93 5.8 0.001 0.001 2.253 2.253 ------------------------------------------------------------------------------- From /workspace/artifacts/dbcsr_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.005 0.016 26.144 26.151 lib_test 1 2.0 0.000 0.000 26.109 26.127 dbcsr_run_tests 3 3.0 0.000 0.001 26.108 26.126 test_multiplies_multiproc 3 4.0 0.000 0.003 25.199 25.271 dbcsr_multiply_generic 9 5.0 0.001 0.001 23.497 23.594 multiply_cannon 9 6.0 0.001 0.002 20.887 21.592 multiply_cannon_loop 9 7.0 0.002 0.002 20.584 21.306 multiply_cannon_multrec 72 8.0 15.223 15.849 15.226 15.852 mp_waitall_1 576 9.2 5.717 6.666 5.717 6.666 multiply_cannon_metrocomm1 72 8.0 0.001 0.001 5.246 6.256 mp_sum_l 470 2.5 1.199 2.164 1.199 2.164 dbcsr_multiply_generic_mpsum_f 9 6.0 0.000 0.000 1.182 2.147 dbcsr_make_random_matrix 9 4.0 0.694 0.702 0.863 0.893 make_m2s 18 6.0 0.001 0.001 0.815 0.868 make_images 18 7.0 0.030 0.033 0.810 0.863 dbcsr_finalize 27 5.7 0.000 0.000 0.539 0.641 dbcsr_redistribute 9 5.0 0.272 0.303 0.598 0.631 dbcsr_data_release 444 7.6 0.539 0.618 0.539 0.618 dbcsr_merge_all 18 6.5 0.078 0.090 0.470 0.564 dbcsr_destroy 111 5.9 0.003 0.047 0.476 0.546 ------------------------------------------------------------------------------- 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=9.361999999999995, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_redistribute", label="dbcsr_redistribute", y=41.125, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=15.614, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=13.561, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_data_release", label="dbcsr_data_release", y=4.583, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="tree_to_linear_d", label="tree_to_linear_d", y=3.006, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="mp_sum_l", label="mp_sum_l", y=0.0, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 Plot: name="dbcsr_timings_32mpi", title="Timings of dbcsr with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="dbcsr_timings_32mpi", name="rest", label="rest", y=2.4999999999999964, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_redistribute", label="dbcsr_redistribute", y=0.272, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=15.223, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=0.694, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_data_release", label="dbcsr_data_release", y=0.539, 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_sum_l", label="mp_sum_l", y=1.199, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=5.717, 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 0.080 0.080 139.306 139.306 qs_mol_dyn_low 1 2.0 0.004 0.004 137.811 137.811 velocity_verlet 5 3.0 0.005 0.005 112.660 112.660 qmmm_el_coupling 6 3.8 0.000 0.000 86.779 86.779 qmmm_elec_with_gaussian 6 4.8 0.033 0.033 86.775 86.775 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 85.620 85.620 qmmm_elec_gaussian_low_G 6 6.8 84.622 84.622 84.622 84.622 qs_forces 6 3.8 0.001 0.001 41.744 41.744 qs_energies 6 4.8 0.000 0.000 36.906 36.906 scf_env_do_scf 6 5.8 0.001 0.001 34.414 34.414 rebuild_ks_matrix 45 8.4 0.000 0.000 29.987 29.987 qs_ks_build_kohn_sham_matrix 45 9.4 0.005 0.005 29.987 29.987 scf_env_do_scf_inner_loop 39 6.8 0.005 0.005 29.747 29.747 qs_ks_update_qs_env 45 7.8 0.000 0.000 25.587 25.587 pw_transfer 966 12.3 0.056 0.056 18.346 18.346 fft_wrap_pw1pw2 801 13.6 0.006 0.006 18.097 18.097 fft_wrap_pw1pw2_150 507 15.2 2.756 2.756 17.611 17.611 qs_vxc_create 45 10.4 0.001 0.001 15.188 15.188 xc_vxc_pw_create 45 11.4 0.791 0.791 15.188 15.188 xc_pw_derive 270 13.4 0.002 0.002 9.925 9.925 xc_rho_set_and_dset_create 45 12.4 1.183 1.183 8.210 8.210 fft3d_s 802 15.6 8.092 8.092 8.101 8.101 qs_rho_update_rho_low 45 7.9 0.000 0.000 7.826 7.826 calculate_rho_elec 45 8.9 0.638 0.638 7.826 7.826 pw_integral_ab 2539 7.4 7.156 7.156 7.156 7.156 xc_pw_divergence 45 12.4 0.001 0.001 6.085 6.085 pw_scatter_s 429 15.8 6.034 6.034 6.034 6.034 qmmm_forces 6 3.8 0.003 0.003 6.004 6.004 qmmm_forces_with_gaussian 6 4.8 0.043 0.043 5.593 5.593 qs_ks_ddapc 45 10.4 0.001 0.001 5.249 5.249 init_scf_loop 6 6.8 0.000 0.000 4.661 4.661 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 4.416 4.416 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 4.398 4.398 sum_up_and_integrate 45 10.4 0.909 0.909 4.314 4.314 qmmm_forces_gaussian_low_G 6 6.8 3.673 3.673 3.673 3.673 density_rs2pw 45 9.9 0.002 0.002 3.627 3.627 grid_collocate_task_list 45 9.9 3.561 3.561 3.561 3.561 cp_ddapc_apply_CD 45 11.4 0.006 0.006 3.500 3.500 pw_poisson_solve 51 9.9 0.741 0.741 3.446 3.446 integrate_v_rspace 45 11.4 0.007 0.007 3.405 3.405 ------------------------------------------------------------------------------- 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 0.038 0.055 71.480 71.491 qs_mol_dyn_low 1 2.0 0.003 0.005 70.214 70.286 qs_forces 6 3.8 0.001 0.001 51.472 51.473 qs_energies 6 4.8 0.000 0.000 49.159 49.160 scf_env_do_scf 6 5.8 0.000 0.001 47.968 47.968 scf_env_do_scf_inner_loop 113 6.2 0.003 0.022 45.935 45.936 rebuild_ks_matrix 119 8.1 0.000 0.000 34.772 34.783 qs_ks_build_kohn_sham_matrix 119 9.1 0.014 0.015 34.771 34.783 qs_ks_update_qs_env 119 7.3 0.001 0.001 32.778 32.790 velocity_verlet 5 3.0 0.002 0.005 29.559 29.562 pw_transfer 2446 12.3 0.130 0.139 24.668 25.467 fft_wrap_pw1pw2 2059 13.4 0.018 0.019 24.266 25.039 fft_wrap_pw1pw2_150 1321 14.9 4.220 4.637 23.474 24.287 qs_vxc_create 119 10.1 0.002 0.002 20.017 20.030 xc_vxc_pw_create 119 11.1 0.326 0.393 20.015 20.028 fft3d_ps 2059 15.4 7.899 8.411 14.454 15.582 xc_pw_derive 714 13.1 0.006 0.006 14.491 15.128 qs_rho_update_rho_low 119 7.3 0.001 0.001 12.834 12.838 calculate_rho_elec 119 8.3 0.053 0.064 12.833 12.838 sum_up_and_integrate 119 10.1 0.145 0.162 10.439 10.477 integrate_v_rspace 119 11.1 0.003 0.004 10.294 10.328 xc_rho_set_and_dset_create 119 12.1 0.661 0.799 9.737 10.248 xc_pw_divergence 119 12.1 0.003 0.004 9.682 10.215 qmmm_forces 6 3.8 0.003 0.004 9.807 9.807 qmmm_forces_with_gaussian 6 4.8 0.008 0.010 8.922 9.271 density_rs2pw 119 9.3 0.005 0.006 7.910 8.329 qmmm_el_coupling 6 3.8 0.000 0.000 7.824 8.035 qmmm_elec_with_gaussian 6 4.8 0.004 0.006 7.822 8.032 potential_pw2rs 119 12.1 0.006 0.006 6.322 6.344 mp_alltoall_z22v 2059 17.4 4.710 6.043 4.710 6.043 grid_collocate_task_list 119 9.3 4.711 5.081 4.711 5.081 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 4.361 4.540 pw_restrict_s3 18 5.8 2.007 2.225 3.797 4.123 yz_to_x 964 16.0 0.801 0.954 3.177 4.101 x_to_yz 1095 16.8 0.995 1.109 3.330 4.006 transfer_pw2rs 500 12.8 0.005 0.005 3.887 3.901 grid_integrate_task_list 119 12.1 3.606 3.854 3.606 3.854 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 3.669 3.785 transfer_rs2pw 488 10.2 0.006 0.007 3.311 3.724 qmmm_forces_gaussian_low_G 6 6.8 3.585 3.720 3.585 3.720 mp_waitany 4028 12.8 2.686 3.347 2.686 3.347 qmmm_elec_with_gaussian:spline 6 5.8 0.000 0.000 3.070 3.278 pw_prolongate_s3 18 6.8 1.636 1.732 3.070 3.278 qmmm_elec_gaussian_low_G 6 6.8 3.026 3.085 3.026 3.085 pw_scatter_p 1095 15.8 2.918 2.974 2.918 2.974 transfer_rs2pw_150 125 11.2 0.947 1.177 2.380 2.790 transfer_pw2rs_150 125 13.9 1.051 1.153 2.712 2.759 qs_ks_ddapc 119 10.1 0.002 0.002 2.651 2.727 qs_scf_new_mos 113 7.2 0.000 0.001 2.718 2.726 qs_scf_loop_do_ot 113 8.2 0.000 0.001 2.718 2.725 pw_gather_p 964 15.0 2.585 2.709 2.585 2.709 ot_scf_mini 113 9.2 0.001 0.002 2.628 2.634 pw_integral_ab 2761 7.7 1.831 1.971 2.120 2.219 dbcsr_multiply_generic 2588 12.3 0.063 0.066 2.037 2.103 init_scf_loop 6 6.8 0.000 0.000 2.029 2.029 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 2.013 2.014 xc_functional_eval 238 13.1 0.002 0.002 1.577 1.987 mp_sum_dm3 33 5.7 1.721 1.760 1.721 1.760 ------------------------------------------------------------------------------- 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=23.412000000000006, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=84.622, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_s", label="fft3d_s", y=8.092, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_integral_ab", label="pw_integral_ab", y=7.156, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_scatter_s", label="pw_scatter_s", y=6.034, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.673, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=3.561, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft_wrap_pw1pw2_150", label="fft_wrap_pw1pw2_150", y=2.756, 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="mp_alltoall_z22v", label="mp_alltoall_z22v", y=0.0, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=0.0, yerr=0.0 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=37.892, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=3.026, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="fft3d_s", label="fft3d_s", y=0.0, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="pw_integral_ab", label="pw_integral_ab", y=1.831, 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="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.585, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=4.711, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="fft_wrap_pw1pw2_150", label="fft_wrap_pw1pw2_150", y=4.22, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=7.899, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=4.71, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=3.606, yerr=0.0 Summary: Performance test took 37 minutes. Status: OK Removing intermediate container 9417460f1608 ---> ceab05cda000 Step 41/42 : CMD cat $(find ./report.log -mmin +10) | sed '/^Summary:/ s/$/ (cached)/' ---> Running in 6366977b397c Removing intermediate container 6366977b397c ---> 48b98dc8a1cc Step 42/42 : ENTRYPOINT [] ---> Running in eab14786ef34 Removing intermediate container eab14786ef34 ---> 9c2f1584abce [Warning] One or more build-args [GIT_COMMIT_SHA] were not consumed Successfully built 9c2f1584abce Successfully tagged us-central1-docker.pkg.dev/cp2k-org-project/cp2kci/img_cp2k-perf-openmp:master Pushing new image... done. #################### Running Image cp2k-perf-openmp #################### Uploading artifacts... done EndDate: 2023-08-17 20:10:28+00:00