StartDate: 2023-04-05 20:31:09+00:00 CpuId: 32x AMD EPYC (3rd Gen) (Milan) [Zen 3], 7nm (SMT disabled) CommitSHA: a5f008ff72915fffd70f18d34c54035508798718 CommitTime: 2023-04-05 18:41:47 +0200 CommitAuthor: Matthias Krack CommitSubject: make pretty Populating docker build cache... done. #################### Building Image cp2k-perf-openmp #################### Dockerfile: /tools/docker/Dockerfile.test_performance Build-Path: / Build-Args: GIT_COMMIT_SHA=a5f008ff72915fffd70f18d34c54035508798718 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 367.9MB Step 1/42 : FROM ubuntu:22.04 22.04: Pulling from library/ubuntu 2ab09b027e7f: Pulling fs layer 2ab09b027e7f: Verifying Checksum 2ab09b027e7f: Download complete 2ab09b027e7f: Pull complete Digest: sha256:67211c14fa74f070d27cc59d69a7fa9aeff8e28ea118ef3babc295a0428a6d21 Status: Downloaded newer image for ubuntu:22.04 ---> 08d22c0ceb15 Step 2/42 : WORKDIR /opt/cp2k-toolchain ---> Using cache ---> 47a3542ef7e0 Step 3/42 : COPY ./tools/toolchain/install_requirements*.sh ./ ---> Using cache ---> e86e12710088 Step 4/42 : RUN ./install_requirements.sh ubuntu:22.04 ---> Using cache ---> 5ad7a46db6e4 Step 5/42 : RUN mkdir scripts ---> Using cache ---> 2ed50184e1de 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 ---> 2cfaec0caa31 Step 7/42 : COPY ./tools/toolchain/install_cp2k_toolchain.sh . ---> Using cache ---> e3c7243c9e7e Step 8/42 : RUN ./install_cp2k_toolchain.sh --install-all --with-gcc=system --dry-run ---> Using cache ---> f053587e71f2 Step 9/42 : COPY ./tools/toolchain/scripts/stage0/ ./scripts/stage0/ ---> Using cache ---> 27b6a69300c0 Step 10/42 : RUN ./scripts/stage0/install_stage0.sh && rm -rf ./build ---> Using cache ---> af05dc2abbcf Step 11/42 : COPY ./tools/toolchain/scripts/stage1/ ./scripts/stage1/ ---> Using cache ---> 72a9160365c6 Step 12/42 : RUN ./scripts/stage1/install_stage1.sh && rm -rf ./build ---> Using cache ---> 08767ccb9543 Step 13/42 : COPY ./tools/toolchain/scripts/stage2/ ./scripts/stage2/ ---> Using cache ---> c93c73c59c7d Step 14/42 : RUN ./scripts/stage2/install_stage2.sh && rm -rf ./build ---> Using cache ---> 46507f029160 Step 15/42 : COPY ./tools/toolchain/scripts/stage3/ ./scripts/stage3/ ---> Using cache ---> a3d4507934f4 Step 16/42 : RUN ./scripts/stage3/install_stage3.sh && rm -rf ./build ---> Using cache ---> 685c0a7bb753 Step 17/42 : COPY ./tools/toolchain/scripts/stage4/ ./scripts/stage4/ ---> Using cache ---> 92d27c56d5bc Step 18/42 : RUN ./scripts/stage4/install_stage4.sh && rm -rf ./build ---> Using cache ---> a334f9476c42 Step 19/42 : COPY ./tools/toolchain/scripts/stage5/ ./scripts/stage5/ ---> Using cache ---> c73b0452b2ef Step 20/42 : RUN ./scripts/stage5/install_stage5.sh && rm -rf ./build ---> Using cache ---> 202dd7cbf5a3 Step 21/42 : COPY ./tools/toolchain/scripts/stage6/ ./scripts/stage6/ ---> Using cache ---> 0c04ffdac443 Step 22/42 : RUN ./scripts/stage6/install_stage6.sh && rm -rf ./build ---> Using cache ---> 349fd42ea13a Step 23/42 : COPY ./tools/toolchain/scripts/stage7/ ./scripts/stage7/ ---> Using cache ---> d64eae5b05f8 Step 24/42 : RUN ./scripts/stage7/install_stage7.sh && rm -rf ./build ---> Using cache ---> 80648f9dff0f Step 25/42 : COPY ./tools/toolchain/scripts/stage8/ ./scripts/stage8/ ---> Using cache ---> 16bc772eed58 Step 26/42 : RUN ./scripts/stage8/install_stage8.sh && rm -rf ./build ---> Using cache ---> 02f5a0fdf6e7 Step 27/42 : COPY ./tools/toolchain/scripts/arch_base.tmpl ./tools/toolchain/scripts/generate_arch_files.sh ./scripts/ ---> Using cache ---> e8be50ed56f8 Step 28/42 : RUN ./scripts/generate_arch_files.sh && rm -rf ./build ---> Using cache ---> 9f357f320f08 Step 29/42 : WORKDIR /opt/cp2k ---> Using cache ---> 0daff3c95d21 Step 30/42 : COPY ./Makefile . ---> Using cache ---> 3528cfcca48d Step 31/42 : COPY ./src ./src ---> Using cache ---> 56983c35d81d Step 32/42 : COPY ./exts ./exts ---> Using cache ---> 795595a99fa0 Step 33/42 : COPY ./tools/build_utils ./tools/build_utils ---> Using cache ---> 1d40aff0b8b9 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 1e1b13e4c0fc './arch/local.psmp' -> '/opt/cp2k-toolchain/install/arch/local.psmp' Compiling cp2k... Removing intermediate container 1e1b13e4c0fc ---> 16c64588314b Step 35/42 : COPY ./data ./data ---> f929529a0f49 Step 36/42 : COPY ./tests ./tests ---> 595274b7be6c Step 37/42 : COPY ./tools/regtesting ./tools/regtesting ---> c7f369fdd77a Step 38/42 : COPY ./benchmarks ./benchmarks ---> d334914181c3 Step 39/42 : COPY ./tools/docker/scripts/test_performance.sh ./tools/docker/scripts/plot_performance.py ./ ---> d73695c59fc2 Step 40/42 : RUN ./test_performance.sh "local" 2>&1 | tee report.log ---> Running in d2c530e1581a ========== 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 0.037 0.037 86.438 86.438 qs_mol_dyn_low 1 2.0 0.003 0.003 85.809 85.809 qs_forces 11 3.9 0.001 0.001 85.770 85.770 qs_energies 11 4.9 0.001 0.001 79.753 79.753 scf_env_do_scf 11 5.9 0.001 0.001 69.270 69.270 velocity_verlet 10 3.0 0.002 0.002 55.815 55.815 scf_env_do_scf_inner_loop 108 6.5 0.011 0.011 52.929 52.929 rebuild_ks_matrix 119 8.3 0.001 0.001 20.106 20.106 qs_ks_build_kohn_sham_matrix 119 9.3 0.012 0.012 20.105 20.105 qs_rho_update_rho_low 119 7.7 0.001 0.001 19.255 19.255 calculate_rho_elec 119 8.7 0.950 0.950 19.254 19.254 dbcsr_multiply_generic 2286 12.5 0.149 0.149 18.975 18.975 qs_scf_new_mos 108 7.5 0.001 0.001 18.938 18.938 qs_scf_loop_do_ot 108 8.5 0.001 0.001 18.938 18.938 qs_ks_update_qs_env 119 7.6 0.001 0.001 18.470 18.470 ot_scf_mini 108 9.5 0.002 0.002 17.647 17.647 init_scf_loop 11 6.9 0.000 0.000 16.209 16.209 grid_collocate_task_list 119 9.7 14.838 14.838 14.838 14.838 prepare_preconditioner 11 7.9 0.000 0.000 13.789 13.789 make_preconditioner 11 8.9 0.000 0.000 13.789 13.789 sum_up_and_integrate 119 10.3 0.783 0.783 13.144 13.144 make_full_inverse_cholesky 11 9.9 0.000 0.000 12.675 12.675 integrate_v_rspace 119 11.3 0.106 0.106 12.361 12.361 ot_mini 108 10.5 0.001 0.001 11.600 11.600 make_m2s 4572 13.5 0.045 0.045 10.652 10.652 grid_integrate_task_list 119 12.3 10.445 10.445 10.445 10.445 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 6.132 6.132 qs_ot_get_derivative 108 11.5 0.001 0.001 5.967 5.967 pw_transfer 1439 11.6 0.066 0.066 5.957 5.957 dbcsr_make_dense_low 5837 15.5 0.080 0.080 5.779 5.779 fft_wrap_pw1pw2 1201 12.6 0.006 0.006 5.718 5.718 make_dense_data 5837 16.5 5.070 5.070 5.685 5.685 ot_diis_step 108 11.5 0.004 0.004 5.631 5.631 make_images 4572 14.5 2.116 2.116 5.268 5.268 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 5.144 5.144 apply_single 119 13.6 0.000 0.000 5.144 5.144 dbcsr_make_images_dense 3978 14.8 0.017 0.017 5.031 5.031 fft_wrap_pw1pw2_140 487 13.2 0.412 0.412 4.881 4.881 multiply_cannon 2286 13.5 0.210 0.210 4.664 4.664 cp_fm_cholesky_decompose 22 10.9 4.508 4.508 4.508 4.508 multiply_cannon_loop 2286 14.5 0.054 0.054 4.111 4.111 cp_fm_cholesky_invert 11 10.9 4.073 4.073 4.073 4.073 multiply_cannon_multrec 2286 15.5 4.002 4.002 4.056 4.056 init_scf_run 11 5.9 0.002 0.002 3.726 3.726 scf_env_initial_rho_setup 11 6.9 0.001 0.001 3.724 3.724 dbcsr_complete_redistribute 329 12.2 1.927 1.927 3.676 3.676 dbcsr_copy 2102 12.0 0.227 0.227 3.640 3.640 density_rs2pw 119 9.7 0.005 0.005 3.466 3.466 build_core_hamiltonian_matrix_ 11 4.9 0.001 0.001 3.432 3.432 dbcsr_copy_into_existing 22 7.9 3.363 3.363 3.364 3.364 qs_env_update_s_mstruct 11 6.9 0.000 0.000 3.228 3.228 wfi_extrapolate 11 7.9 0.001 0.001 3.225 3.225 copy_dbcsr_to_fm 153 11.3 0.002 0.002 2.997 2.997 fft3d_s 1202 14.6 2.859 2.859 2.876 2.876 qs_create_task_list 11 7.9 0.000 0.000 2.862 2.862 generate_qs_task_list 11 8.9 1.952 1.952 2.862 2.862 qs_ot_get_p 119 10.4 0.001 0.001 2.843 2.843 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 2.582 2.582 build_core_hamiltonian_matrix 11 6.9 0.001 0.001 2.491 2.491 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.353 2.353 dbcsr_data_release 279534 16.0 1.998 1.998 1.998 1.998 pw_poisson_solve 119 10.3 0.334 0.334 1.989 1.989 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 1.875 1.875 qs_ot_get_derivative_taylor 59 13.0 0.001 0.001 1.814 1.814 potential_pw2rs 119 12.3 0.045 0.045 1.811 1.811 copy_fm_to_dbcsr 176 11.2 0.001 0.001 1.783 1.783 ------------------------------------------------------------------------------- From /workspace/artifacts/H2O-64_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.008 0.023 49.437 49.446 qs_mol_dyn_low 1 2.0 0.003 0.004 49.307 49.312 qs_forces 11 3.9 0.001 0.002 49.267 49.267 qs_energies 11 4.9 0.001 0.001 45.838 45.842 scf_env_do_scf 11 5.9 0.000 0.002 42.024 42.025 scf_env_do_scf_inner_loop 108 6.5 0.003 0.020 38.982 38.983 velocity_verlet 10 3.0 0.002 0.003 29.171 29.172 rebuild_ks_matrix 119 8.3 0.000 0.001 17.825 17.935 qs_ks_build_kohn_sham_matrix 119 9.3 0.015 0.019 17.824 17.934 qs_ks_update_qs_env 119 7.6 0.001 0.001 15.739 15.838 qs_rho_update_rho_low 119 7.7 0.001 0.001 15.611 15.623 calculate_rho_elec 119 8.7 0.030 0.032 15.611 15.623 sum_up_and_integrate 119 10.3 0.033 0.040 13.618 13.660 integrate_v_rspace 119 11.3 0.004 0.005 13.585 13.631 dbcsr_multiply_generic 2286 12.5 0.072 0.075 13.274 13.567 qs_scf_new_mos 108 7.5 0.001 0.001 10.545 10.714 qs_scf_loop_do_ot 108 8.5 0.001 0.001 10.545 10.713 grid_collocate_task_list 119 9.7 9.165 10.178 9.165 10.178 multiply_cannon 2286 13.5 0.159 0.174 9.720 10.121 ot_scf_mini 108 9.5 0.002 0.002 9.883 10.028 multiply_cannon_loop 2286 14.5 0.087 0.104 9.181 9.588 grid_integrate_task_list 119 12.3 8.128 8.758 8.128 8.758 mp_waitall_1 158411 16.6 7.509 8.281 7.509 8.281 rs_pw_transfer 974 11.9 0.011 0.014 6.343 6.812 density_rs2pw 119 9.7 0.005 0.006 5.834 6.336 multiply_cannon_metrocomm3 18288 15.5 0.034 0.039 5.300 6.134 ot_mini 108 10.5 0.001 0.001 5.815 5.978 pw_transfer 1439 11.6 0.101 0.109 3.913 4.020 mp_waitany 9880 13.7 3.486 3.923 3.486 3.923 fft_wrap_pw1pw2 1201 12.6 0.008 0.010 3.743 3.837 rs_pw_transfer_RS2PW_140 130 11.5 0.211 0.255 3.169 3.639 fft_wrap_pw1pw2_140 487 13.2 0.614 0.764 3.162 3.336 potential_pw2rs 119 12.3 0.006 0.007 3.246 3.283 multiply_cannon_multrec 18288 15.5 3.025 3.228 3.035 3.239 qs_ot_get_derivative 108 11.5 0.001 0.001 3.027 3.173 init_scf_loop 11 6.9 0.000 0.000 3.030 3.042 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 2.674 2.804 apply_single 119 13.6 0.000 0.000 2.674 2.804 ot_diis_step 108 11.5 0.003 0.004 2.766 2.766 mp_alltoall_d11v 2130 13.8 2.375 2.752 2.375 2.752 init_scf_run 11 5.9 0.000 0.004 2.654 2.654 scf_env_initial_rho_setup 11 6.9 0.000 0.003 2.654 2.654 fft3d_ps 1201 14.6 1.226 1.400 2.382 2.607 rs_gather_matrices 119 12.3 0.107 0.121 2.152 2.535 wfi_extrapolate 11 7.9 0.001 0.001 2.421 2.421 make_m2s 4572 13.5 0.044 0.046 2.288 2.373 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 2.220 2.231 make_images 4572 14.5 0.115 0.118 1.971 2.057 multiply_cannon_metrocomm1 18288 15.5 0.018 0.021 0.570 1.671 qs_ot_get_p 119 10.4 0.001 0.001 1.268 1.469 mp_sum_l 11218 13.2 0.803 1.398 0.803 1.398 mp_sum_d 4135 12.0 0.910 1.319 0.910 1.319 mp_alltoall_z22v 1201 16.6 0.926 1.284 0.926 1.284 make_images_data 4572 15.5 0.033 0.037 1.085 1.236 rs_pw_transfer_PW2RS_140 130 13.9 0.320 0.402 1.154 1.211 prepare_preconditioner 11 7.9 0.000 0.000 1.175 1.210 make_preconditioner 11 8.9 0.000 0.000 1.175 1.210 qs_ot_get_derivative_taylor 59 13.0 0.001 0.001 1.029 1.122 make_full_inverse_cholesky 11 9.9 0.000 0.000 1.057 1.080 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 0.866 1.059 hybrid_alltoall_any 4725 16.4 0.055 0.133 0.937 1.053 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 0.945 0.998 ------------------------------------------------------------------------------- Plot: name="H2O-64_timings_32omp", title="Timings of H2O-64 with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="H2O-64_timings_32omp", name="rest", label="rest", y=43.501999999999995, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=14.838, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=10.445, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="make_dense_data", label="make_dense_data", y=5.07, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=4.508, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=4.073, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=4.002, 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=18.124, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=9.165, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=8.128, 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="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=3.025, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=7.509, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitany", label="mp_waitany", y=3.486, yerr=0.0 Running H2O-64_nonortho.inp with 1 threads and 32 ranks... done. Running H2O-64_nonortho.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/H2O-64_nonortho_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.037 0.037 111.126 111.126 qs_mol_dyn_low 1 2.0 0.003 0.003 110.445 110.445 qs_forces 11 3.9 0.001 0.001 110.405 110.405 qs_energies 11 4.9 0.001 0.001 102.810 102.810 scf_env_do_scf 11 5.9 0.001 0.001 89.953 89.953 scf_env_do_scf_inner_loop 96 6.5 0.010 0.010 71.935 71.935 velocity_verlet 10 3.0 0.002 0.002 71.206 71.206 rebuild_ks_matrix 107 8.3 0.001 0.001 33.433 33.433 qs_ks_build_kohn_sham_matrix 107 9.3 0.011 0.011 33.433 33.433 qs_rho_update_rho_low 107 7.7 0.001 0.001 31.448 31.448 calculate_rho_elec 107 8.7 0.860 0.860 31.448 31.448 qs_ks_update_qs_env 107 7.6 0.001 0.001 30.087 30.087 grid_collocate_task_list 107 9.7 27.480 27.480 27.480 27.480 sum_up_and_integrate 107 10.3 0.717 0.717 26.946 26.946 integrate_v_rspace 107 11.3 0.082 0.082 26.229 26.229 grid_integrate_task_list 107 12.3 24.432 24.432 24.432 24.432 init_scf_loop 11 6.9 0.000 0.000 17.876 17.876 dbcsr_multiply_generic 1966 12.4 0.137 0.137 17.715 17.715 qs_scf_new_mos 96 7.5 0.001 0.001 17.183 17.183 qs_scf_loop_do_ot 96 8.5 0.001 0.001 17.182 17.182 ot_scf_mini 96 9.5 0.002 0.002 15.954 15.954 prepare_preconditioner 11 7.9 0.000 0.000 13.832 13.832 make_preconditioner 11 8.9 0.000 0.000 13.832 13.832 make_full_inverse_cholesky 11 9.9 0.000 0.000 12.658 12.658 ot_mini 96 10.5 0.001 0.001 10.468 10.468 make_m2s 3932 13.4 0.040 0.040 9.734 9.734 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 6.564 6.564 init_scf_run 11 5.9 0.002 0.002 5.593 5.593 scf_env_initial_rho_setup 11 6.9 0.001 0.001 5.591 5.591 qs_ot_get_derivative 96 11.5 0.001 0.001 5.571 5.571 pw_transfer 1295 11.6 0.060 0.060 5.482 5.482 fft_wrap_pw1pw2 1081 12.6 0.006 0.006 5.292 5.292 dbcsr_make_dense_low 4961 15.5 0.084 0.084 5.258 5.258 make_dense_data 4961 16.5 4.540 4.540 5.163 5.163 wfi_extrapolate 11 7.9 0.001 0.001 5.007 5.007 ot_diis_step 96 11.5 0.003 0.003 4.895 4.895 make_images 3932 14.4 1.901 1.901 4.812 4.812 multiply_cannon 1966 13.4 0.211 0.211 4.611 4.611 dbcsr_make_images_dense 3386 14.7 0.015 0.015 4.611 4.611 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 4.569 4.569 apply_single 107 13.6 0.000 0.000 4.568 4.568 fft_wrap_pw1pw2_140 439 13.2 0.370 0.370 4.523 4.523 cp_fm_cholesky_decompose 22 10.9 4.421 4.421 4.421 4.421 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 4.222 4.222 multiply_cannon_loop 1966 14.4 0.066 0.066 4.082 4.082 cp_fm_cholesky_invert 11 10.9 4.036 4.036 4.036 4.036 multiply_cannon_multrec 1966 15.4 3.967 3.967 4.015 4.015 dbcsr_complete_redistribute 317 12.2 1.938 1.938 3.914 3.914 qs_env_update_s_mstruct 11 6.9 0.000 0.000 3.673 3.673 dbcsr_copy 1855 11.9 0.210 0.210 3.582 3.582 build_core_hamiltonian_matrix_ 11 4.9 0.001 0.001 3.371 3.371 dbcsr_copy_into_existing 22 7.9 3.342 3.342 3.342 3.342 qs_create_task_list 11 7.9 0.000 0.000 3.303 3.303 generate_qs_task_list 11 8.9 2.388 2.388 3.303 3.303 copy_dbcsr_to_fm 147 11.2 0.002 0.002 3.136 3.136 density_rs2pw 107 9.7 0.004 0.004 3.108 3.108 fft3d_s 1082 14.6 2.648 2.648 2.653 2.653 qs_ot_get_p 107 10.4 0.001 0.001 2.498 2.498 build_core_hamiltonian_matrix 11 6.9 0.000 0.000 2.479 2.479 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.417 2.417 ------------------------------------------------------------------------------- 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 0.007 0.021 71.032 71.042 qs_mol_dyn_low 1 2.0 0.003 0.003 70.907 70.911 qs_forces 11 3.9 0.002 0.002 70.866 70.867 qs_energies 11 4.9 0.001 0.001 66.135 66.136 scf_env_do_scf 11 5.9 0.000 0.002 61.180 61.180 scf_env_do_scf_inner_loop 96 6.5 0.002 0.017 56.579 56.580 velocity_verlet 10 3.0 0.002 0.003 42.251 42.253 rebuild_ks_matrix 107 8.3 0.000 0.001 30.477 30.558 qs_ks_build_kohn_sham_matrix 107 9.3 0.016 0.020 30.476 30.558 qs_ks_update_qs_env 107 7.6 0.001 0.001 26.822 26.895 sum_up_and_integrate 107 10.3 0.034 0.038 26.516 26.526 integrate_v_rspace 107 11.3 0.004 0.005 26.482 26.497 qs_rho_update_rho_low 107 7.7 0.000 0.001 26.135 26.147 calculate_rho_elec 107 8.7 0.028 0.029 26.134 26.146 grid_integrate_task_list 107 12.3 22.690 23.008 22.690 23.008 grid_collocate_task_list 107 9.7 21.730 22.085 21.730 22.085 dbcsr_multiply_generic 1966 12.4 0.065 0.070 12.177 12.311 multiply_cannon 1966 13.4 0.141 0.160 9.219 9.608 qs_scf_new_mos 96 7.5 0.001 0.001 9.339 9.418 qs_scf_loop_do_ot 96 8.5 0.001 0.001 9.339 9.418 multiply_cannon_loop 1966 14.4 0.091 0.099 8.770 9.096 ot_scf_mini 96 9.5 0.002 0.002 8.777 8.860 mp_waitall_1 136719 16.5 7.206 7.605 7.206 7.605 multiply_cannon_metrocomm3 15728 15.4 0.034 0.037 5.282 5.799 ot_mini 96 10.5 0.001 0.001 5.113 5.202 rs_pw_transfer 878 11.9 0.010 0.012 4.255 4.860 init_scf_loop 11 6.9 0.000 0.000 4.588 4.588 density_rs2pw 107 9.7 0.005 0.006 3.870 4.477 init_scf_run 11 5.9 0.000 0.004 3.924 3.924 scf_env_initial_rho_setup 11 6.9 0.000 0.003 3.924 3.924 pw_transfer 1295 11.6 0.099 0.105 3.731 3.820 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 3.770 3.781 fft_wrap_pw1pw2 1081 12.6 0.008 0.010 3.572 3.651 wfi_extrapolate 11 7.9 0.001 0.001 3.566 3.566 fft_wrap_pw1pw2_140 439 13.2 0.681 0.756 3.114 3.280 potential_pw2rs 107 12.3 0.005 0.006 3.072 3.086 multiply_cannon_multrec 15728 15.4 2.747 2.880 2.756 2.892 qs_ot_get_derivative 96 11.5 0.001 0.001 2.581 2.663 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 2.511 2.597 apply_single 107 13.6 0.000 0.000 2.511 2.597 ot_diis_step 96 11.5 0.003 0.003 2.511 2.511 fft3d_ps 1081 14.6 1.204 1.322 2.152 2.339 mp_waitany 8968 13.7 1.445 2.131 1.445 2.131 make_m2s 3932 13.4 0.040 0.047 2.040 2.074 make_images 3932 14.4 0.103 0.109 1.754 1.795 rs_pw_transfer_RS2PW_140 118 11.5 0.204 0.241 1.170 1.779 mp_alltoall_d11v 1998 13.7 0.868 1.505 0.868 1.505 ------------------------------------------------------------------------------- Plot: name="H2O-64_nonortho_timings_32omp", title="Timings of H2O-64_nonortho with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="rest", label="rest", y=42.250000000000014, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=27.48, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=24.432, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="make_dense_data", label="make_dense_data", y=4.54, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=4.421, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=4.036, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=3.967, 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=15.213999999999992, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=21.73, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=22.69, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="make_dense_data", label="make_dense_data", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=2.747, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitany", label="mp_waitany", y=1.445, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=7.206, 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 0.189 0.189 106.701 106.701 qs_energies 1 2.0 0.000 0.000 105.798 105.798 scf_env_do_scf 1 3.0 0.000 0.000 104.605 104.605 qs_ks_update_qs_env 8 5.0 0.000 0.000 99.551 99.551 rebuild_ks_matrix 7 6.0 0.000 0.000 99.497 99.497 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.001 99.497 99.497 hfx_ks_matrix 7 8.0 0.000 0.000 90.604 90.604 integrate_four_center 7 9.0 1.713 1.713 90.580 90.580 integrate_four_center_main 7 10.0 0.396 0.396 82.938 82.938 integrate_four_center_bin 448 11.0 82.542 82.542 82.542 82.542 scf_env_do_scf_inner_loop 7 4.0 0.001 0.001 56.990 56.990 init_scf_loop 1 4.0 0.000 0.000 47.605 47.605 integrate_four_center_load 7 10.0 0.000 0.000 5.678 5.678 hfx_load_balance 1 11.0 0.009 0.009 5.678 5.678 qs_vxc_create 14 8.0 0.000 0.000 3.095 3.095 xc_vxc_pw_create 14 9.0 0.133 0.133 3.095 3.095 hfx_load_balance_count 1 12.0 2.829 2.829 2.829 2.829 hfx_load_balance_bin 1 12.0 2.823 2.823 2.823 2.823 calculate_rho_elec 15 7.4 0.119 0.119 2.544 2.544 prepare_preconditioner 1 5.0 0.000 0.000 2.439 2.439 make_preconditioner 1 6.0 0.000 0.000 2.439 2.439 xc_rho_set_and_dset_create 14 10.0 0.104 0.104 2.350 2.350 admm_mo_calc_rho_aux 7 8.0 0.000 0.000 2.236 2.236 ------------------------------------------------------------------------------- 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 0.221 0.240 97.603 97.613 qs_energies 1 2.0 0.000 0.000 97.190 97.196 scf_env_do_scf 1 3.0 0.000 0.000 96.833 96.834 qs_ks_update_qs_env 8 5.0 0.000 0.001 94.701 94.702 rebuild_ks_matrix 7 6.0 0.000 0.000 94.692 94.693 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.002 94.692 94.693 hfx_ks_matrix 7 8.0 0.000 0.000 88.991 88.992 integrate_four_center 7 9.0 0.056 0.345 88.982 88.983 integrate_four_center_main 7 10.0 0.003 0.003 80.537 82.543 integrate_four_center_bin 448 11.0 80.534 82.539 80.534 82.539 scf_env_do_scf_inner_loop 7 4.0 0.000 0.001 54.390 54.390 init_scf_loop 1 4.0 0.000 0.000 42.442 42.442 integrate_four_center_load 7 10.0 0.000 0.000 5.616 5.617 hfx_load_balance 1 11.0 0.001 0.001 5.616 5.617 mp_sync 56 11.2 2.130 3.563 2.130 3.563 hfx_load_balance_count 1 12.0 2.758 2.813 2.758 2.813 hfx_load_balance_bin 1 12.0 2.755 2.803 2.755 2.803 qs_vxc_create 14 8.0 0.000 0.000 2.553 2.553 xc_vxc_pw_create 14 9.0 0.008 0.009 2.553 2.553 xc_rho_set_and_dset_create 14 10.0 0.011 0.014 1.996 2.102 ------------------------------------------------------------------------------- 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=16.209000000000017, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_bin", label="integrate_four_center_bin", y=82.542, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_count", label="hfx_load_balance_count", y=2.829, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=2.823, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center", label="integrate_four_center", y=1.713, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_main", label="integrate_four_center_main", y=0.396, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="CP2K", label="CP2K", y=0.189, 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=9.146, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center_bin", label="integrate_four_center_bin", y=80.534, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_count", label="hfx_load_balance_count", y=2.758, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=2.755, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center", label="integrate_four_center", y=0.056, 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=0.221, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="mp_sync", label="mp_sync", y=2.13, yerr=0.0 Running GW_PBE_4benzene.inp with 1 threads and 32 ranks... done. Running GW_PBE_4benzene.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/GW_PBE_4benzene_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.013 0.013 85.273 85.273 qs_energies 1 2.0 0.000 0.000 84.867 84.867 mp2_main 1 3.0 0.000 0.000 82.051 82.051 mp2_gpw_main 1 4.0 0.000 0.000 81.949 81.949 rpa_ri_compute_en 1 5.0 0.000 0.000 78.256 78.256 rpa_num_int 1 6.0 0.001 0.001 78.250 78.250 compute_mat_P_omega 1 7.0 0.003 0.003 67.909 67.909 compute_mat_P_omega_contract 10 8.0 8.956 8.956 67.704 67.704 dbt_total 2336 9.6 0.013 0.013 54.155 54.155 dbt_contract 787 11.0 0.041 0.041 46.775 46.775 dbt_tas_total 1149 12.2 0.239 0.239 45.672 45.672 dbt_tas_multiply 807 12.1 0.002 0.002 44.278 44.278 dbt_tas_dbm 807 14.1 0.004 0.004 37.576 37.576 dbm_multiply 807 16.1 37.567 37.567 37.567 37.567 dbt_tas_mm_1N 524 15.1 0.002 0.002 29.808 29.808 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 28.344 28.344 compute_mat_P_omega_calc_M_occ 250 9.0 8.976 8.976 17.141 17.141 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 7.266 7.266 dbt_tas_mm_2 251 15.0 0.001 0.001 6.243 6.243 dbt_copy 1103 10.7 0.078 0.078 5.968 5.968 compute_QP_energies 1 7.0 0.000 0.000 5.457 5.457 compute_self_energy_cubic_gw 1 8.0 0.054 0.054 5.456 5.456 contract_cubic_gw 21 9.0 0.000 0.000 4.427 4.427 dbt_tas_reserve_blocks_index 3261 14.3 0.482 0.482 3.897 3.897 mp2_ri_gpw_compute_in 1 5.0 0.001 0.001 3.685 3.685 dbm_reserve_blocks 3628 15.3 3.505 3.505 3.505 3.505 dbt_reserve_blocks_index 2280 13.1 0.058 0.058 2.940 2.940 dbt_reserve_blocks_index_array 2222 12.2 0.009 0.009 2.891 2.891 scf_env_do_scf 1 3.0 0.000 0.000 2.700 2.700 scf_env_do_scf_inner_loop 17 4.0 0.002 0.002 2.700 2.700 dbt_tas_copy 574 11.4 1.399 1.399 2.405 2.405 dbt_crop 1042 12.0 1.440 1.440 2.378 2.378 convert_to_new_pgrid 2421 14.1 0.094 0.094 2.338 2.338 dbm_copy 1614 15.1 2.244 2.244 2.244 2.244 dbt_tas_reshape 367 15.0 0.007 0.007 2.089 2.089 compute_W_cubic_GW 10 7.0 0.004 0.004 2.046 2.046 dbt_reshape 278 11.9 1.079 1.079 1.994 1.994 rpa_num_int_RPA_matrix_operati 10 7.0 0.000 0.000 1.993 1.993 get_2c_integrals 1 6.0 0.000 0.000 1.726 1.726 ------------------------------------------------------------------------------- From /workspace/artifacts/GW_PBE_4benzene_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.006 0.026 34.503 34.514 qs_energies 1 2.0 0.000 0.000 34.399 34.400 mp2_main 1 3.0 0.000 0.000 33.451 33.453 mp2_gpw_main 1 4.0 0.000 0.000 33.396 33.398 rpa_ri_compute_en 1 5.0 0.000 0.000 32.112 32.114 rpa_num_int 1 6.0 0.000 0.002 32.112 32.113 dbt_total 2336 9.6 0.015 0.016 28.593 28.601 compute_mat_P_omega 1 7.0 0.001 0.005 26.533 26.560 compute_mat_P_omega_contract 10 8.0 0.441 0.459 26.411 26.415 dbt_contract 787 11.0 0.038 0.039 21.011 21.015 dbt_tas_total 1149 12.2 0.077 0.082 18.688 18.689 dbt_tas_multiply 807 12.1 0.002 0.002 18.630 18.631 dbt_tas_dbm 807 14.1 0.003 0.003 14.199 14.224 dbm_multiply 807 16.1 10.859 11.912 10.859 11.912 compute_mat_P_omega_calc_M_occ 250 9.0 0.415 0.429 7.896 7.897 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 7.468 7.468 dbt_copy 1149 10.8 0.014 0.014 6.702 6.899 dbt_reshape 1136 11.8 2.853 2.998 6.393 6.610 mp_sync 8688 11.6 5.195 6.268 5.195 6.268 dbt_tas_mm_2 251 15.0 0.001 0.001 6.174 6.182 dbt_tas_mm_1N 524 15.1 0.001 0.002 5.077 5.702 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 5.458 5.459 compute_QP_energies 1 7.0 0.000 0.000 3.928 3.929 compute_self_energy_cubic_gw 1 8.0 0.003 0.003 3.928 3.928 contract_cubic_gw 21 9.0 0.000 0.000 3.234 3.234 mp_waitall_2 3812 15.3 2.578 2.800 2.578 2.800 dbt_communicate_buffer 1136 12.8 0.052 0.057 2.609 2.738 dbt_reserve_blocks_index 2887 13.1 0.070 0.075 1.943 2.197 dbt_reserve_blocks_index_array 2829 12.2 0.009 0.010 1.933 2.182 dbt_tas_reserve_blocks_index 3347 14.5 0.435 0.478 1.925 2.176 dbm_reserve_blocks 3752 15.4 1.587 1.825 1.587 1.825 dbt_crop 1042 12.0 0.933 1.028 1.510 1.677 mp2_ri_gpw_compute_in 1 5.0 0.000 0.001 1.282 1.283 dbt_tas_replicate 405 14.1 0.556 0.740 1.151 1.236 compute_mat_P_omega_copy_M_vir 250 9.0 0.001 0.001 1.164 1.166 compute_mat_P_omega_copy_M_occ 250 9.0 0.001 0.001 1.056 1.058 parallel_gemm_fm 105 8.4 0.000 0.000 1.001 1.011 parallel_gemm_fm_cosma 105 9.4 1.001 1.011 1.001 1.011 convert_to_new_pgrid 2421 14.1 0.027 0.031 0.878 0.989 dbm_copy 1608 15.1 0.845 0.959 0.845 0.959 scf_env_do_scf 1 3.0 0.000 0.000 0.895 0.895 scf_env_do_scf_inner_loop 17 4.0 0.001 0.003 0.894 0.894 mp_max_i 2001 9.8 0.559 0.761 0.559 0.761 compute_W_cubic_GW 10 7.0 0.001 0.001 0.754 0.760 dbt_tas_mm_3N 22 15.1 0.000 0.000 0.524 0.737 ------------------------------------------------------------------------------- Plot: name="GW_PBE_4benzene_timings_32omp", title="Timings of GW_PBE_4benzene with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="rest", label="rest", y=22.945999999999998, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=37.567, 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=8.976, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=8.956, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=3.505, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_copy", label="dbm_copy", y=2.244, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=1.079, 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=9.73, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=10.859, 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=0.415, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=0.441, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=1.587, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_copy", label="dbm_copy", y=0.845, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=2.853, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_sync", label="mp_sync", y=5.195, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.578, yerr=0.0 Running RI-HFX_H2O-32.inp with 1 threads and 32 ranks... done. Running RI-HFX_H2O-32.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/RI-HFX_H2O-32_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.020 0.020 321.832 321.832 qs_forces 1 2.0 0.000 0.000 321.260 321.260 rebuild_ks_matrix 7 6.6 0.000 0.000 319.775 319.775 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.001 319.775 319.775 hfx_ks_matrix 7 8.6 0.000 0.000 317.712 317.712 hfx_ri_update_ks 7 9.6 0.000 0.000 282.189 282.189 hfx_ri_update_ks_Pmat 7 10.6 31.534 31.534 282.179 282.179 dbt_total 783 11.1 0.005 0.005 263.147 263.147 qs_energies 1 3.0 0.000 0.000 247.715 247.715 scf_env_do_scf 1 4.0 0.000 0.000 247.423 247.423 qs_ks_update_qs_env 8 6.0 0.000 0.000 246.282 246.282 dbt_contract 207 12.4 0.096 0.096 244.213 244.213 dbt_tas_total 317 14.0 1.604 1.604 241.976 241.976 dbt_tas_multiply 216 13.5 0.001 0.001 238.419 238.419 dbt_tas_dbm 216 15.5 0.001 0.001 229.340 229.340 dbm_multiply 216 17.5 229.337 229.337 229.337 229.337 hfx_ri_update_ks_Pmat_KS 63 11.6 0.001 0.001 224.900 224.900 dbt_tas_mm_2 91 16.5 0.001 0.001 215.063 215.063 scf_env_do_scf_inner_loop 6 5.0 0.001 0.001 157.184 157.184 init_scf_loop 2 5.0 0.000 0.000 90.237 90.237 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 73.497 73.497 hfx_ri_update_forces 1 7.0 1.608 1.608 35.519 35.519 hfx_ri_forces_Pmat_3c 1 8.0 4.685 4.685 18.405 18.405 dbt_copy 409 11.7 0.050 0.050 15.370 15.370 precalc_derivatives 1 8.0 2.155 2.155 13.334 13.334 dbt_reshape 132 13.2 6.184 6.184 10.450 10.450 dbt_tas_mm_3T 77 17.1 0.000 0.000 9.842 9.842 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 9.666 9.666 dbt_tas_reserve_blocks_index 1229 15.4 1.060 1.060 8.461 8.461 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 7.655 7.655 build_3c_derivatives 3 9.0 2.387 2.387 7.599 7.599 dbm_reserve_blocks 1345 16.4 7.501 7.501 7.501 7.501 dbt_reserve_blocks_index 818 14.4 0.100 0.100 6.820 6.820 dbt_reserve_blocks_index_array 795 13.4 0.007 0.007 6.731 6.731 ------------------------------------------------------------------------------- From /workspace/artifacts/RI-HFX_H2O-32_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.007 0.025 47.949 47.959 qs_forces 1 2.0 0.000 0.000 47.809 47.810 rebuild_ks_matrix 7 6.6 0.000 0.000 47.089 47.090 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.002 47.089 47.090 hfx_ks_matrix 7 8.6 0.000 0.000 45.988 45.995 dbt_total 783 11.1 0.006 0.006 40.960 40.962 dbt_contract 207 12.4 0.025 0.026 31.604 31.615 hfx_ri_update_ks 7 9.6 0.000 0.000 28.166 28.167 hfx_ri_update_ks_Pmat 7 10.6 1.277 1.347 28.166 28.166 dbt_tas_total 317 14.0 0.044 0.056 27.830 27.830 dbt_tas_multiply 216 13.5 0.001 0.001 27.737 27.737 qs_energies 1 3.0 0.000 0.000 26.455 26.455 scf_env_do_scf 1 4.0 0.000 0.001 26.310 26.310 qs_ks_update_qs_env 8 6.0 0.000 0.000 25.746 25.746 dbt_tas_dbm 216 15.5 0.001 0.001 23.321 23.326 dbm_multiply 216 17.5 21.124 22.135 21.124 22.135 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 21.345 21.345 hfx_ri_update_forces 1 7.0 0.060 0.063 17.821 17.827 scf_env_do_scf_inner_loop 6 5.0 0.000 0.001 14.936 14.936 hfx_ri_forces_Pmat_3c 1 8.0 0.178 0.186 12.971 12.971 hfx_ri_update_ks_Pmat_KS 63 11.6 0.000 0.001 12.719 12.719 init_scf_loop 2 5.0 0.000 0.000 11.373 11.373 dbt_tas_mm_2 91 16.5 0.001 0.001 10.844 10.846 dbt_copy 497 12.3 0.012 0.013 8.913 9.265 dbt_reshape 365 13.6 3.749 3.886 6.912 7.157 dbt_tas_mm_3T 77 17.1 0.000 0.000 6.312 6.982 mp_sync 2665 13.0 4.136 5.861 4.136 5.861 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 5.301 5.302 dbt_tas_mm_3N 37 15.4 0.000 0.000 4.388 4.501 dbt_tas_reserve_blocks_index 1356 15.8 0.893 0.919 3.345 3.758 precalc_derivatives 1 8.0 0.080 0.087 3.672 3.672 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 3.364 3.364 dbt_reserve_blocks_index 1051 14.7 0.114 0.121 2.806 3.150 dbt_reserve_blocks_index_array 1028 13.8 0.005 0.006 2.778 3.124 dbm_reserve_blocks 1481 16.7 2.526 2.936 2.526 2.936 dbt_crop 372 13.7 1.805 1.851 2.636 2.779 mp_waitall_2 1138 16.4 2.252 2.351 2.252 2.351 dbt_communicate_buffer 365 14.6 0.013 0.014 2.023 2.121 build_3c_derivatives 3 9.0 0.225 0.244 2.056 2.062 hfx_ri_update_ks_Pmat_copy_2 63 11.6 0.000 0.000 1.768 1.769 hfx_ri_pre_scf_Pmat_RIx3C 9 13.0 0.000 0.000 1.741 1.745 convert_to_new_pgrid 648 15.5 0.038 0.084 1.411 1.611 dbt_tas_copy 132 12.5 0.669 0.710 1.278 1.426 dbm_copy 452 16.3 1.227 1.423 1.227 1.423 ------------------------------------------------------------------------------- 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=42.59100000000001, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=229.337, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=31.534, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=7.501, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=6.184, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_forces_Pmat_3c", label="hfx_ri_forces_Pmat_3c", y=4.685, 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=12.707, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=21.124, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=1.277, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=2.526, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=3.749, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_forces_Pmat_3c", label="hfx_ri_forces_Pmat_3c", y=0.178, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.252, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_sync", label="mp_sync", y=4.136, 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 0.015 0.015 209.000 209.000 qs_energies 1 2.0 0.000 0.000 208.811 208.811 mp2_main 1 3.0 0.000 0.000 203.650 203.650 mp2_gpw_main 1 4.0 0.001 0.001 203.255 203.255 mp2_ri_gpw_compute_in 1 5.0 0.389 0.389 149.756 149.756 mp2_ri_gpw_compute_in_loop 1 6.0 0.011 0.011 141.001 141.001 mp2_eri_3c_integrate_gpw 2656 7.0 0.015 0.015 108.633 108.633 integrate_v_rspace 2666 8.0 0.676 0.676 95.307 95.307 grid_integrate_task_list 2666 9.0 92.608 92.608 92.608 92.608 mp2_ri_gpw_compute_en 1 5.0 0.099 0.099 53.475 53.475 mp2_ri_gpw_compute_en_RI_loop 1 6.0 10.192 10.192 51.601 51.601 mp2_ri_gpw_compute_en_expansio 2080 7.0 2.209 2.209 33.849 33.849 local_gemm 2080 8.0 31.640 31.640 31.640 31.640 dbcsr_multiply_generic 5322 8.0 0.185 0.185 21.776 21.776 ao_to_mo_and_store_B_mult_1 2656 7.0 0.011 0.011 21.754 21.754 calculate_wavefunction 2656 8.0 8.185 8.185 12.053 12.053 pw_transfer 63872 10.6 1.052 1.052 11.942 11.942 multiply_cannon 5322 9.0 0.471 0.471 11.238 11.238 fft_wrap_pw1pw2 53228 11.4 0.118 0.118 10.664 10.664 ao_to_mo_and_store_B_E_Ex_1 2656 7.0 2.698 2.698 10.506 10.506 multiply_cannon_loop 5322 10.0 0.131 0.131 9.813 9.813 copy_dbcsr_to_fm 2679 8.0 0.029 0.029 8.543 8.543 make_m2s 10644 9.0 0.063 0.063 8.376 8.376 get_2c_integrals 1 6.0 0.000 0.000 8.328 8.328 multiply_cannon_multrec 5322 11.0 8.112 8.112 8.158 8.158 make_images 10644 10.0 3.457 3.457 8.070 8.070 fft_wrap_pw1pw2_20 21271 12.4 0.497 0.497 7.566 7.566 compute_2c_integrals 1 7.0 0.006 0.006 7.463 7.463 compute_2c_integrals_loop_lm 1 8.0 0.013 0.013 7.450 7.450 mp2_eri_2c_integrate_gpw 1 9.0 0.806 0.806 7.437 7.437 dbcsr_complete_redistribute 2689 9.0 1.170 1.170 6.764 6.764 fft3d_s 53229 13.4 6.554 6.554 6.589 6.589 dbcsr_finalize 10708 9.5 0.161 0.161 6.039 6.039 mp2_ri_gpw_compute_en_ener 2080 7.0 5.502 5.502 5.502 5.502 dbcsr_merge_all 8011 10.3 4.181 4.181 5.383 5.383 scf_env_do_scf 1 3.0 0.000 0.000 4.720 4.720 scf_env_do_scf_inner_loop 10 4.0 0.001 0.001 4.720 4.720 ------------------------------------------------------------------------------- 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 0.027 36.808 36.818 qs_energies 1 2.0 0.000 0.000 36.697 36.697 mp2_main 1 3.0 0.000 0.001 34.615 34.615 mp2_gpw_main 1 4.0 0.001 0.001 34.494 34.494 mp2_ri_gpw_compute_in 1 5.0 0.051 0.053 17.649 17.970 mp2_ri_gpw_compute_en 1 5.0 0.202 0.211 16.752 17.032 mp2_ri_gpw_compute_in_loop 1 6.0 0.001 0.001 16.410 16.709 mp2_ri_gpw_compute_en_RI_loop 1 6.0 1.643 1.835 15.688 15.693 mp2_eri_3c_integrate_gpw 83 7.0 0.001 0.001 14.161 14.373 integrate_v_rspace 93 8.1 0.110 0.119 14.032 14.247 grid_integrate_task_list 93 9.1 13.707 13.917 13.707 13.917 mp2_ri_gpw_compute_en_expansio 65 7.0 0.122 0.143 11.131 11.269 local_gemm 65 8.0 11.009 11.135 11.009 11.135 mp2_ri_gpw_compute_en_comm 20 7.0 0.086 0.110 2.518 3.701 mp_sendrecv_dm3 1240 8.0 1.923 3.322 1.923 3.322 dbcsr_multiply_generic 176 8.0 0.008 0.009 1.931 2.115 ao_to_mo_and_store_B_mult_1 83 7.0 0.001 0.001 1.915 2.096 scf_env_do_scf 1 3.0 0.000 0.000 1.957 1.957 scf_env_do_scf_inner_loop 10 4.0 0.000 0.002 1.957 1.957 get_2c_integrals 1 6.0 0.000 0.000 1.167 1.205 multiply_cannon 176 9.0 0.017 0.019 1.109 1.166 multiply_cannon_loop 176 10.0 0.002 0.002 1.048 1.108 multiply_cannon_multrec 246 11.0 0.892 0.931 0.898 0.937 qs_scf_new_mos 10 5.0 0.000 0.000 0.927 0.931 make_m2s 352 9.0 0.003 0.003 0.783 0.907 eigensolver 11 5.8 0.001 0.001 0.905 0.907 make_images 352 10.0 0.053 0.056 0.770 0.894 compute_2c_integrals 1 7.0 0.003 0.004 0.861 0.881 pw_transfer 2120 10.5 0.048 0.050 0.788 0.809 compute_2c_integrals_loop_lm 1 8.0 0.002 0.004 0.774 0.791 mp2_eri_2c_integrate_gpw 1 9.0 0.202 0.212 0.772 0.790 fft_wrap_pw1pw2 1768 11.4 0.004 0.005 0.726 0.745 ------------------------------------------------------------------------------- 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=58.263000000000005, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=92.608, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="local_gemm", label="local_gemm", y=31.64, 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=10.192, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="calculate_wavefunction", label="calculate_wavefunction", y=8.185, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=8.112, 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=7.634, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.707, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="local_gemm", label="local_gemm", y=11.009, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="mp2_ri_gpw_compute_en_RI_loop", label="mp2_ri_gpw_compute_en_RI_loop", y=1.643, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="calculate_wavefunction", label="calculate_wavefunction", y=0.0, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=0.892, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="mp_sendrecv_dm3", label="mp_sendrecv_dm3", y=1.923, 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 0.096 126.068 126.068 qs_energies 1 2.0 0.000 0.000 124.600 124.600 scf_env_do_scf 1 3.0 0.000 0.000 117.822 117.822 scf_env_do_scf_inner_loop 15 4.0 0.002 0.002 117.822 117.822 qs_ks_update_qs_env 15 5.0 0.000 0.000 49.560 49.560 rebuild_ks_matrix 15 6.0 0.000 0.000 49.350 49.350 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.002 49.350 49.350 qs_scf_new_mos 15 5.0 0.000 0.000 42.767 42.767 eigensolver 15 6.0 0.002 0.002 34.951 34.951 qs_vxc_create 15 8.0 0.028 0.028 33.797 33.797 calculate_dispersion_nonloc 15 9.0 6.757 6.757 29.358 29.358 pw_transfer 1191 10.0 0.065 0.065 23.509 23.509 fft_wrap_pw1pw2 1086 11.0 0.009 0.009 23.323 23.323 qs_rho_update_rho_low 16 5.0 0.000 0.000 22.539 22.539 calculate_rho_elec 16 6.0 0.216 0.216 22.539 22.539 cp_fm_diag_elpa 15 7.0 0.000 0.000 22.014 22.014 cp_fm_diag_elpa_base 15 8.0 19.344 19.344 22.014 22.014 grid_collocate_task_list 16 7.0 21.042 21.042 21.042 21.042 fft_wrap_pw1pw2_150 765 12.0 3.621 3.621 16.866 16.866 sum_up_and_integrate 15 8.0 0.160 0.160 14.298 14.298 integrate_v_rspace 15 9.0 0.019 0.019 14.137 14.137 grid_integrate_task_list 15 10.0 13.594 13.594 13.594 13.594 cp_fm_cholesky_restore 45 7.0 10.538 10.538 10.538 10.538 fft3d_s 1087 13.0 10.162 10.162 10.170 10.170 pw_scatter_s 585 13.1 7.494 7.494 7.494 7.494 fft_wrap_pw1pw2_200 197 12.3 0.825 0.825 6.268 6.268 copy_dbcsr_to_fm 16 5.9 0.001 0.001 5.623 5.623 dbcsr_complete_redistribute 46 8.3 2.252 2.252 5.597 5.597 cp_fm_upper_to_full 30 8.0 5.066 5.066 5.066 5.066 xc_vxc_pw_create 15 9.0 0.213 0.213 4.411 4.411 vdW_energy 15 10.0 4.356 4.356 4.356 4.356 gspace_mixing 14 5.0 0.171 0.171 4.203 4.203 broyden_mixing 14 6.0 3.557 3.557 3.558 3.558 init_scf_run 1 3.0 0.000 0.000 3.231 3.231 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 3.072 3.072 xc_pw_derive 90 11.0 0.001 0.001 2.926 2.926 calculate_dm_sparse 15 6.0 0.018 0.018 2.561 2.561 ------------------------------------------------------------------------------- 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 0.034 63.888 63.900 qs_energies 1 2.0 0.000 0.000 63.468 63.473 scf_env_do_scf 1 3.0 0.000 0.000 59.293 59.294 scf_env_do_scf_inner_loop 15 4.0 0.001 0.003 59.293 59.294 qs_ks_update_qs_env 15 5.0 0.000 0.000 25.663 25.675 rebuild_ks_matrix 15 6.0 0.000 0.000 25.629 25.640 qs_ks_build_kohn_sham_matrix 15 7.0 0.003 0.003 25.628 25.640 qs_rho_update_rho_low 16 5.0 0.000 0.000 21.730 21.734 calculate_rho_elec 16 6.0 0.007 0.007 21.730 21.734 grid_collocate_task_list 16 7.0 19.983 20.254 19.983 20.254 sum_up_and_integrate 15 8.0 0.016 0.020 14.212 14.258 integrate_v_rspace 15 9.0 0.001 0.001 14.196 14.244 grid_integrate_task_list 15 10.0 13.411 13.508 13.411 13.508 qs_scf_new_mos 15 5.0 0.000 0.000 12.464 12.507 eigensolver 15 6.0 0.001 0.002 11.409 11.454 qs_vxc_create 15 8.0 0.001 0.001 11.056 11.068 pw_transfer 1191 10.0 0.097 0.107 8.971 9.040 fft_wrap_pw1pw2 1086 11.0 0.013 0.015 8.779 8.872 calculate_dispersion_nonloc 15 9.0 0.922 0.943 8.839 8.863 cp_fm_diag_elpa 15 7.0 0.000 0.000 8.073 8.074 cp_fm_diag_elpa_base 15 8.0 7.919 7.945 8.070 8.071 fft3d_ps 1086 13.0 3.007 3.301 5.818 6.279 fft_wrap_pw1pw2_150 765 12.0 0.792 0.945 5.678 5.718 cp_fm_cholesky_restore 45 7.0 3.169 3.212 3.169 3.212 fft_wrap_pw1pw2_200 197 12.3 0.530 0.628 2.973 3.014 mp_alltoall_z22v 1086 15.0 2.161 2.939 2.161 2.939 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 2.490 2.490 build_core_hamiltonian_matrix 1 4.0 0.000 0.000 2.190 2.391 xc_vxc_pw_create 15 9.0 0.017 0.021 2.216 2.251 x_to_yz 585 14.1 0.377 0.400 1.497 1.892 density_rs2pw 16 7.0 0.001 0.001 1.523 1.702 rs_pw_transfer 158 9.4 0.002 0.002 1.421 1.644 yz_to_x 501 13.9 0.245 0.288 1.286 1.643 xc_pw_derive 90 11.0 0.001 0.001 1.539 1.609 init_scf_run 1 3.0 0.000 0.001 1.454 1.456 vdW_energy 15 10.0 1.344 1.415 1.344 1.415 build_core_ppnl 1 5.0 1.282 1.409 1.282 1.409 scf_env_initial_rho_setup 1 4.0 0.000 0.000 1.361 1.362 ------------------------------------------------------------------------------- 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=51.38799999999999, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=21.042, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=19.344, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.594, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=10.538, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="fft3d_s", label="fft3d_s", y=10.162, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="fft3d_ps", label="fft3d_ps", y=0.0, yerr=0.0 Plot: name="diag_cu144_broy_timings_32mpi", title="Timings of diag_cu144_broy with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="rest", label="rest", y=16.399, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=19.983, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=7.919, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.411, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=3.169, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="fft3d_s", label="fft3d_s", y=0.0, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=3.007, 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 0.073 0.073 334.977 334.977 qs_energies 1 2.0 0.000 0.000 334.842 334.842 ls_scf 1 3.0 0.000 0.000 333.592 333.592 ls_scf_main 1 4.0 0.002 0.002 324.320 324.320 density_matrix_trs4 11 5.0 0.012 0.012 230.607 230.607 arnoldi_extremal 12 6.1 0.000 0.000 145.929 145.929 arnoldi_normal_ev 12 7.1 0.032 0.032 145.929 145.929 dbcsr_matrix_vector_mult 652 9.0 0.212 0.212 143.571 143.571 build_subspace 23 8.1 0.080 0.080 143.299 143.299 dbcsr_matrix_vector_mult_local 652 10.0 142.010 142.010 142.020 142.020 ls_scf_dm_to_ks 11 5.0 0.000 0.000 88.472 88.472 matrix_ls_to_qs 11 6.0 0.000 0.000 85.234 85.234 dbcsr_multiply_generic 185 6.1 0.824 0.824 73.626 73.626 dbcsr_copy_into_existing 11 7.0 47.433 47.433 47.433 47.433 multiply_cannon 185 7.1 0.279 0.279 44.438 44.438 dbcsr_complete_redistribute 23 7.5 30.223 30.223 41.502 41.502 matrix_decluster 11 7.0 0.000 0.000 37.800 37.800 multiply_cannon_loop 185 8.1 0.236 0.236 32.289 32.289 make_m2s 370 7.1 0.038 0.038 24.664 24.664 multiply_cannon_multrec 185 9.1 23.200 23.200 23.235 23.235 make_images 370 8.1 10.589 10.589 23.081 23.081 dbcsr_finalize 646 7.5 0.163 0.163 14.993 14.993 dbcsr_merge_all 597 8.5 2.379 2.379 13.806 13.806 setup_rec_index_2d 370 8.1 11.779 11.779 11.779 11.779 dbcsr_sort_indices 1103 9.9 10.155 10.155 10.155 10.155 tree_to_linear_d 110 9.4 10.072 10.072 10.072 10.072 calculate_norms 370 9.1 8.817 8.817 8.817 8.817 quick_finalize 395 10.0 0.345 0.345 8.774 8.774 ls_scf_init_scf 1 4.0 0.000 0.000 8.608 8.608 ls_scf_init_matrix_S 1 5.0 0.000 0.000 8.276 8.276 dbcsr_special_finalize 370 9.1 0.002 0.002 8.115 8.115 matrix_sqrt_Newton_Schulz 1 6.0 0.001 0.001 7.630 7.630 ------------------------------------------------------------------------------- From /workspace/artifacts/bench_dftb_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.007 0.020 66.521 66.531 qs_energies 1 2.0 0.000 0.000 66.416 66.416 ls_scf 1 3.0 0.000 0.000 66.366 66.366 ls_scf_main 1 4.0 0.001 0.011 63.830 63.831 density_matrix_trs4 11 5.0 0.007 0.021 61.388 61.438 dbcsr_multiply_generic 185 6.1 0.060 0.077 58.169 58.389 multiply_cannon 185 7.1 0.035 0.036 48.514 49.354 multiply_cannon_loop 185 8.1 0.116 0.130 46.055 47.289 multiply_cannon_multrec 1480 9.1 28.594 31.405 28.873 31.669 mp_waitall_1 11936 10.3 14.763 16.453 14.763 16.453 multiply_cannon_metrocomm3 1480 9.1 0.014 0.018 8.689 11.606 make_m2s 370 7.1 0.035 0.037 6.747 6.832 make_images 370 8.1 0.628 0.669 6.615 6.702 calculate_norms 2960 9.1 4.963 5.608 4.963 5.608 multiply_cannon_metrocomm1 1480 9.1 0.008 0.009 3.356 5.328 make_images_data 370 9.1 0.009 0.010 2.964 3.207 hybrid_alltoall_any 393 9.9 0.190 0.999 2.585 2.793 mp_sum_l 1119 5.6 1.856 2.401 1.856 2.401 arnoldi_extremal 12 6.1 0.000 0.001 2.321 2.341 arnoldi_normal_ev 12 7.1 0.001 0.008 2.321 2.340 build_subspace 23 8.1 0.020 0.025 2.228 2.230 ls_scf_dm_to_ks 11 5.0 0.000 0.000 2.119 2.172 dbcsr_matrix_vector_mult 652 9.0 0.014 0.049 1.934 1.996 dbcsr_complete_redistribute 23 7.5 1.183 1.237 1.914 1.990 matrix_ls_to_qs 11 6.0 0.000 0.000 1.867 1.951 ls_scf_init_scf 1 4.0 0.000 0.000 1.929 1.929 ls_scf_init_matrix_S 1 5.0 0.000 0.000 1.904 1.911 make_images_pack 370 9.1 1.681 1.869 1.685 1.873 matrix_decluster 11 7.0 0.000 0.000 1.730 1.811 matrix_sqrt_Newton_Schulz 1 6.0 0.000 0.001 1.744 1.746 dbcsr_matrix_vector_mult_local 652 10.0 1.610 1.666 1.612 1.667 dbcsr_finalize 646 7.5 0.008 0.008 1.418 1.532 buffer_matrices_ensure_size 370 8.1 1.375 1.511 1.375 1.511 dbcsr_multiply_generic_mpsum_f 137 7.1 0.000 0.000 1.043 1.393 ------------------------------------------------------------------------------- Plot: name="bench_dftb_timings_32omp", title="Timings of bench_dftb with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="bench_dftb_timings_32omp", name="rest", label="rest", y=71.51499999999999, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=142.01, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_copy_into_existing", label="dbcsr_copy_into_existing", y=47.433, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_complete_redistribute", label="dbcsr_complete_redistribute", y=30.223, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=23.2, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="setup_rec_index_2d", label="setup_rec_index_2d", y=11.779, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="calculate_norms", label="calculate_norms", y=8.817, 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 PlotPoint: plot="bench_dftb_timings_32omp", name="mp_sum_l", label="mp_sum_l", y=0.0, yerr=0.0 Plot: name="bench_dftb_timings_32mpi", title="Timings of bench_dftb with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="bench_dftb_timings_32mpi", name="rest", label="rest", y=11.871000000000002, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=1.61, 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=1.183, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=28.594, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="setup_rec_index_2d", label="setup_rec_index_2d", y=0.0, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="calculate_norms", label="calculate_norms", y=4.963, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="make_images_pack", label="make_images_pack", y=1.681, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=14.763, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=1.856, yerr=0.0 Running dbcsr.inp with 1 threads and 32 ranks... done. Running dbcsr.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/dbcsr_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.007 0.007 71.404 71.404 lib_test 1 2.0 0.000 0.000 71.395 71.395 dbcsr_run_tests 3 3.0 0.002 0.002 71.395 71.395 test_multiplies_multiproc 3 4.0 0.001 0.001 55.948 55.948 dbcsr_redistribute 9 5.0 36.862 36.862 38.740 38.740 dbcsr_multiply_generic 9 5.0 0.001 0.001 15.890 15.890 dbcsr_make_random_matrix 9 4.0 12.386 12.386 15.338 15.338 multiply_cannon 9 6.0 0.002 0.002 11.253 11.253 multiply_cannon_loop 9 7.0 0.020 0.020 10.901 10.901 multiply_cannon_multrec 9 8.0 10.881 10.881 10.882 10.882 dbcsr_finalize 27 5.7 0.016 0.016 5.465 5.465 dbcsr_merge_all 18 6.5 1.949 1.949 4.718 4.718 dbcsr_data_release 975 7.6 2.824 2.824 2.824 2.824 tree_to_linear_d 9 7.0 1.880 1.880 1.880 1.880 make_m2s 18 6.0 0.001 0.001 1.571 1.571 make_images 18 7.0 0.542 0.542 1.525 1.525 mp_alltoall_d11v 27 6.0 1.511 1.511 1.511 1.511 ------------------------------------------------------------------------------- From /workspace/artifacts/dbcsr_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.003 0.011 17.453 17.458 lib_test 1 2.0 0.000 0.000 17.427 17.444 dbcsr_run_tests 3 3.0 0.000 0.001 17.426 17.443 test_multiplies_multiproc 3 4.0 0.000 0.002 16.586 16.632 dbcsr_multiply_generic 9 5.0 0.001 0.002 15.160 15.250 multiply_cannon 9 6.0 0.002 0.002 13.434 13.652 multiply_cannon_loop 9 7.0 0.002 0.002 13.144 13.390 multiply_cannon_multrec 72 8.0 10.977 11.228 10.977 11.229 mp_waitall_1 576 9.2 2.465 3.012 2.465 3.012 multiply_cannon_metrocomm1 72 8.0 0.001 0.001 1.930 2.428 dbcsr_make_random_matrix 9 4.0 0.666 0.878 0.810 0.945 dbcsr_data_release 444 7.6 0.809 0.925 0.809 0.925 dbcsr_finalize 27 5.7 0.000 0.000 0.736 0.835 dbcsr_destroy 111 5.9 0.000 0.000 0.634 0.775 multiply_cannon_metrocomm3 72 8.0 0.000 0.000 0.229 0.773 mp_sum_l 390 2.5 0.367 0.725 0.367 0.725 dbcsr_multiply_generic_mpsum_f 9 6.0 0.000 0.000 0.362 0.720 make_m2s 18 6.0 0.001 0.001 0.642 0.673 make_images 18 7.0 0.021 0.022 0.638 0.670 dbcsr_merge_all 18 6.5 0.104 0.124 0.559 0.668 dbcsr_data_copy_aa2 18 7.5 0.338 0.438 0.338 0.438 dbcsr_redistribute 9 5.0 0.233 0.271 0.389 0.419 make_images_data 18 8.0 0.000 0.001 0.335 0.412 hybrid_alltoall_any 18 9.0 0.025 0.112 0.299 0.360 ------------------------------------------------------------------------------- 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=6.501999999999995, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_redistribute", label="dbcsr_redistribute", y=36.862, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=12.386, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=10.881, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_data_release", label="dbcsr_data_release", y=2.824, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_merge_all", label="dbcsr_merge_all", y=1.949, 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=1.8320000000000007, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_redistribute", label="dbcsr_redistribute", y=0.233, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=0.666, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=10.977, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_data_release", label="dbcsr_data_release", y=0.809, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_merge_all", label="dbcsr_merge_all", y=0.104, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=0.367, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=2.465, 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 0.052 0.052 130.505 130.505 qs_mol_dyn_low 1 2.0 0.003 0.003 128.918 128.918 velocity_verlet 5 3.0 0.003 0.003 105.172 105.172 qmmm_el_coupling 6 3.8 0.000 0.000 86.198 86.198 qmmm_elec_with_gaussian 6 4.8 0.012 0.012 86.189 86.189 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 85.578 85.578 qmmm_elec_gaussian_low_G 6 6.8 84.684 84.684 84.684 84.684 qs_forces 6 3.8 0.001 0.001 34.338 34.338 qs_energies 6 4.8 0.000 0.000 30.510 30.510 scf_env_do_scf 6 5.8 0.001 0.001 28.208 28.208 scf_env_do_scf_inner_loop 39 6.8 0.004 0.004 24.625 24.625 rebuild_ks_matrix 45 8.4 0.000 0.000 23.725 23.725 qs_ks_build_kohn_sham_matrix 45 9.4 0.005 0.005 23.725 23.725 qs_ks_update_qs_env 45 7.8 0.000 0.000 20.315 20.315 pw_transfer 966 12.3 0.053 0.053 16.953 16.953 fft_wrap_pw1pw2 801 13.6 0.006 0.006 16.760 16.760 fft_wrap_pw1pw2_150 507 15.2 2.283 2.283 16.363 16.363 qs_vxc_create 45 10.4 0.001 0.001 13.100 13.100 xc_vxc_pw_create 45 11.4 0.689 0.689 13.099 13.099 xc_pw_derive 270 13.4 0.002 0.002 9.216 9.216 fft3d_s 802 15.6 7.550 7.550 7.558 7.558 qs_rho_update_rho_low 45 7.9 0.000 0.000 7.057 7.057 calculate_rho_elec 45 8.9 0.563 0.563 7.056 7.056 xc_rho_set_and_dset_create 45 12.4 0.596 0.596 6.769 6.769 pw_scatter_s 429 15.8 5.676 5.676 5.676 5.676 xc_pw_divergence 45 12.4 0.001 0.001 5.592 5.592 qmmm_forces 6 3.8 0.002 0.002 5.253 5.253 qmmm_forces_with_gaussian 6 4.8 0.016 0.016 4.915 4.915 pw_integral_ab 2539 7.4 4.454 4.454 4.454 4.454 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 4.213 4.213 qs_ks_ddapc 45 10.4 0.001 0.001 4.106 4.106 init_scf_loop 6 6.8 0.000 0.000 3.578 3.578 qmmm_forces_gaussian_low_G 6 6.8 3.477 3.477 3.477 3.477 sum_up_and_integrate 45 10.4 0.486 0.486 3.435 3.435 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 3.417 3.417 density_rs2pw 45 9.9 0.002 0.002 3.260 3.260 grid_collocate_task_list 45 9.9 3.233 3.233 3.233 3.233 integrate_v_rspace 45 11.4 0.006 0.006 2.949 2.949 ------------------------------------------------------------------------------- From /workspace/artifacts/MQAE_single_node_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.039 0.061 55.566 55.581 qs_mol_dyn_low 1 2.0 0.003 0.004 54.474 54.534 qs_forces 6 3.8 0.001 0.001 40.152 40.152 qs_energies 6 4.8 0.000 0.000 38.329 38.329 scf_env_do_scf 6 5.8 0.000 0.001 37.329 37.330 scf_env_do_scf_inner_loop 113 6.2 0.002 0.019 35.801 35.801 rebuild_ks_matrix 119 8.1 0.000 0.000 26.644 26.652 qs_ks_build_kohn_sham_matrix 119 9.1 0.015 0.017 26.643 26.652 qs_ks_update_qs_env 119 7.3 0.001 0.001 25.103 25.111 velocity_verlet 5 3.0 0.002 0.004 22.739 22.742 pw_transfer 2446 12.3 0.210 0.233 19.415 19.974 fft_wrap_pw1pw2 2059 13.4 0.024 0.028 18.968 19.526 fft_wrap_pw1pw2_150 1321 14.9 3.126 3.428 18.427 19.015 qs_vxc_create 119 10.1 0.002 0.003 14.654 14.658 xc_vxc_pw_create 119 11.1 0.149 0.218 14.652 14.656 fft3d_ps 2059 15.4 7.484 8.401 12.299 13.384 xc_pw_derive 714 13.1 0.011 0.013 11.241 11.541 qs_rho_update_rho_low 119 7.3 0.000 0.001 10.636 10.637 calculate_rho_elec 119 8.3 0.050 0.058 10.635 10.636 sum_up_and_integrate 119 10.1 0.069 0.078 8.630 8.648 integrate_v_rspace 119 11.1 0.003 0.003 8.561 8.586 xc_pw_divergence 119 12.1 0.006 0.007 7.390 7.616 qmmm_forces 6 3.8 0.002 0.002 7.331 7.331 xc_rho_set_and_dset_create 119 12.1 0.320 0.403 6.900 7.110 qmmm_forces_with_gaussian 6 4.8 0.008 0.010 6.928 7.080 density_rs2pw 119 9.3 0.006 0.008 6.179 6.398 qmmm_el_coupling 6 3.8 0.000 0.000 6.168 6.246 qmmm_elec_with_gaussian 6 4.8 0.003 0.003 6.166 6.245 rs_pw_transfer 988 11.5 0.011 0.015 5.685 5.884 mp_alltoall_z22v 2059 17.4 3.393 5.153 3.393 5.153 potential_pw2rs 119 12.1 0.005 0.006 4.997 5.012 grid_collocate_task_list 119 9.3 4.286 4.540 4.286 4.540 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 3.831 4.007 grid_integrate_task_list 119 12.1 3.339 3.539 3.339 3.539 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 3.408 3.467 x_to_yz 1095 16.8 0.833 0.949 2.564 3.385 qmmm_forces_gaussian_low_G 6 6.8 3.148 3.298 3.148 3.298 yz_to_x 964 16.0 0.518 0.653 2.181 3.018 qmmm_elec_gaussian_low_G 6 6.8 2.818 2.873 2.818 2.873 pw_restrict_s3 18 5.8 1.351 1.411 2.513 2.600 mp_waitany 4028 12.8 2.045 2.386 2.045 2.386 pw_gather_p 964 15.0 1.947 2.365 1.947 2.365 qs_ks_ddapc 119 10.1 0.002 0.003 2.102 2.185 qmmm_elec_with_gaussian:spline 6 5.8 0.000 0.000 2.099 2.176 pw_prolongate_s3 18 6.8 1.127 1.200 2.099 2.176 rs_pw_transfer_PW2RS_150 125 13.9 0.712 0.799 2.144 2.176 qs_scf_new_mos 113 7.2 0.000 0.000 1.948 1.954 qs_scf_loop_do_ot 113 8.2 0.000 0.000 1.947 1.954 rs_pw_transfer_RS2PW_150 125 11.2 0.594 0.713 1.704 1.876 ot_scf_mini 113 9.2 0.001 0.001 1.866 1.870 dbcsr_multiply_generic 2588 12.3 0.056 0.057 1.749 1.799 pw_integral_ab 2761 7.7 1.257 1.355 1.467 1.627 pw_scatter_p 1095 15.8 1.527 1.559 1.527 1.559 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 1.550 1.551 init_scf_loop 6 6.8 0.000 0.000 1.526 1.526 mp_sum_d 5822 12.2 0.623 1.236 0.623 1.236 mp_sum_dm3 33 5.7 1.135 1.198 1.135 1.198 ot_mini 113 10.2 0.000 0.001 1.135 1.139 ------------------------------------------------------------------------------- Plot: name="MQAE_single_node_timings_32omp", title="Timings of MQAE_single_node with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="MQAE_single_node_timings_32omp", name="rest", label="rest", y=21.430999999999997, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=84.684, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_s", label="fft3d_s", y=7.55, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_scatter_s", label="pw_scatter_s", y=5.676, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_integral_ab", label="pw_integral_ab", y=4.454, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.477, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=3.233, 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=29.841, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=2.818, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="fft3d_s", label="fft3d_s", y=0.0, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="pw_scatter_s", label="pw_scatter_s", y=0.0, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="pw_integral_ab", label="pw_integral_ab", y=1.257, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.148, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=4.286, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=7.484, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=3.393, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=3.339, yerr=0.0 Summary: Performance test took 35 minutes. Status: OK Removing intermediate container d2c530e1581a ---> 3b08491bf051 Step 41/42 : CMD cat $(find ./report.log -mmin +10) | sed '/^Summary:/ s/$/ (cached)/' ---> Running in c0f8038a89a5 Removing intermediate container c0f8038a89a5 ---> 792c0de7bd7e Step 42/42 : ENTRYPOINT [] ---> Running in 8b58a54b245b Removing intermediate container 8b58a54b245b ---> 446e4cb3b056 [Warning] One or more build-args [GIT_COMMIT_SHA] were not consumed Successfully built 446e4cb3b056 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: 2023-04-05 21:24:39+00:00