StartDate: 2022-10-19 11:05:48+00:00 CpuId: 32x AMD EPYC (3rd Gen) (Milan) [Zen 3], 7nm (SMT disabled) CommitSHA: 4ad85c18327c325f09a4f0607fd2dd05986e0241 CommitTime: 2022-10-19 10:46:17 +0200 CommitAuthor: Matthias Krack CommitSubject: Update arch files (LIBXC 6.0.0) Populating docker build cache... done. #################### Building Image cp2k-perf-openmp #################### Dockerfile: /tools/docker/Dockerfile.test_performance Build-Path: / Build-Args: GIT_COMMIT_SHA=4ad85c18327c325f09a4f0607fd2dd05986e0241 Sending build context to Docker daemon 365.3MB Step 1/42 : FROM ubuntu:22.04 22.04: Pulling from library/ubuntu cf92e523b49e: Already exists Digest: sha256:35fb073f9e56eb84041b0745cb714eff0f7b225ea9e024f703cab56aaa5c7720 Status: Downloaded newer image for ubuntu:22.04 ---> 216c552ea5ba Step 2/42 : WORKDIR /opt/cp2k-toolchain ---> Using cache ---> 20d076db758f Step 3/42 : COPY ./tools/toolchain/install_requirements*.sh ./ ---> Using cache ---> 4b417da6a397 Step 4/42 : RUN ./install_requirements.sh ubuntu:22.04 ---> Using cache ---> 5f46925292ae Step 5/42 : RUN mkdir scripts ---> Using cache ---> 1d1e6363a04f 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 ---> 1bac43e64090 Step 7/42 : COPY ./tools/toolchain/install_cp2k_toolchain.sh . ---> Using cache ---> 7d17f6081efc Step 8/42 : RUN ./install_cp2k_toolchain.sh --install-all --mpi-mode=mpich --target-cpu=native --with-gcc=system --dry-run ---> Using cache ---> f50c614e95d1 Step 9/42 : COPY ./tools/toolchain/scripts/stage0/ ./scripts/stage0/ ---> Using cache ---> ddd6bdad2541 Step 10/42 : RUN ./scripts/stage0/install_stage0.sh && rm -rf ./build ---> Using cache ---> 682c93918026 Step 11/42 : COPY ./tools/toolchain/scripts/stage1/ ./scripts/stage1/ ---> Using cache ---> 0805ee19df5e Step 12/42 : RUN ./scripts/stage1/install_stage1.sh && rm -rf ./build ---> Using cache ---> d61920fb0b41 Step 13/42 : COPY ./tools/toolchain/scripts/stage2/ ./scripts/stage2/ ---> Using cache ---> fee9ef523de6 Step 14/42 : RUN ./scripts/stage2/install_stage2.sh && rm -rf ./build ---> Using cache ---> 015f01497548 Step 15/42 : COPY ./tools/toolchain/scripts/stage3/ ./scripts/stage3/ ---> Using cache ---> e35742fe7015 Step 16/42 : RUN ./scripts/stage3/install_stage3.sh && rm -rf ./build ---> Using cache ---> db343ce68093 Step 17/42 : COPY ./tools/toolchain/scripts/stage4/ ./scripts/stage4/ ---> Using cache ---> c0de3990182c Step 18/42 : RUN ./scripts/stage4/install_stage4.sh && rm -rf ./build ---> Using cache ---> c4e4ed3fd8bf Step 19/42 : COPY ./tools/toolchain/scripts/stage5/ ./scripts/stage5/ ---> Using cache ---> 1072b0b8b49a Step 20/42 : RUN ./scripts/stage5/install_stage5.sh && rm -rf ./build ---> Using cache ---> 03a3da6d3835 Step 21/42 : COPY ./tools/toolchain/scripts/stage6/ ./scripts/stage6/ ---> Using cache ---> 1838284d8a70 Step 22/42 : RUN ./scripts/stage6/install_stage6.sh && rm -rf ./build ---> Using cache ---> 4fc61a533649 Step 23/42 : COPY ./tools/toolchain/scripts/stage7/ ./scripts/stage7/ ---> Using cache ---> 7f9ad542b44b Step 24/42 : RUN ./scripts/stage7/install_stage7.sh && rm -rf ./build ---> Using cache ---> 6ec4a1c3ad47 Step 25/42 : COPY ./tools/toolchain/scripts/stage8/ ./scripts/stage8/ ---> Using cache ---> 70d40ab7bd48 Step 26/42 : RUN ./scripts/stage8/install_stage8.sh && rm -rf ./build ---> Using cache ---> a6b90ca8b207 Step 27/42 : COPY ./tools/toolchain/scripts/arch_base.tmpl ./tools/toolchain/scripts/generate_arch_files.sh ./scripts/ ---> Using cache ---> 65569800d45a Step 28/42 : RUN ./scripts/generate_arch_files.sh && rm -rf ./build ---> Using cache ---> 699085d14317 Step 29/42 : WORKDIR /opt/cp2k ---> Using cache ---> 1817006aa12a Step 30/42 : COPY ./Makefile . ---> Using cache ---> e7a5659c5cd3 Step 31/42 : COPY ./src ./src ---> Using cache ---> 0a20eff0ee1a Step 32/42 : COPY ./exts ./exts ---> Using cache ---> 8ae76d95ea6d Step 33/42 : COPY ./tools/build_utils ./tools/build_utils ---> Using cache ---> ed7edc7162af 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 ) && ( [ ! -f ./exe/local/cp2k.psmp ] || ldd ./exe/local/cp2k.psmp | grep -q libmpi )" ---> Using cache ---> 644fc61181c2 Step 35/42 : COPY ./data ./data ---> Using cache ---> 35d7f7908e19 Step 36/42 : COPY ./tests ./tests ---> Using cache ---> 0f6e555a087f Step 37/42 : COPY ./tools/regtesting ./tools/regtesting ---> Using cache ---> d09afb2c31d0 Step 38/42 : COPY ./benchmarks ./benchmarks ---> Using cache ---> 8351febd5cbc Step 39/42 : COPY ./tools/docker/scripts/test_performance.sh ./tools/docker/scripts/plot_performance.py ./ ---> Using cache ---> 8b5ef2a23134 Step 40/42 : RUN ./test_performance.sh "local" 2>&1 | tee report.log ---> Using cache ---> 918249192cda Step 41/42 : CMD cat $(find ./report.log -mmin +10) | sed '/^Summary:/ s/$/ (cached)/' ---> Using cache ---> 0e620bdccc0e Step 42/42 : ENTRYPOINT [] ---> Using cache ---> 1814488a702a [Warning] One or more build-args [GIT_COMMIT_SHA] were not consumed Successfully built 1814488a702a Successfully tagged gcr.io/cp2k-org-project/img_cp2k-perf-openmp-arch-be5:master Pushing new image... done. #################### Running Image cp2k-perf-openmp #################### ========== Compiling CP2K ========== Compiling cp2k... done. Checking benchmark inputs... Found 60 input files and 0 errors. ========== Running Performance Test ========== Running H2O-64.inp with 1 threads and 32 ranks... done. Running H2O-64.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/H2O-64_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.028 0.028 84.984 84.984 qs_mol_dyn_low 1 2.0 0.003 0.003 84.377 84.377 qs_forces 11 3.9 0.001 0.001 84.338 84.338 qs_energies 11 4.9 0.001 0.001 78.453 78.453 scf_env_do_scf 11 5.9 0.001 0.001 68.086 68.086 velocity_verlet 10 3.0 0.002 0.002 54.675 54.675 scf_env_do_scf_inner_loop 108 6.5 0.011 0.011 52.156 52.156 rebuild_ks_matrix 119 8.3 0.001 0.001 19.503 19.503 qs_ks_build_kohn_sham_matrix 119 9.3 0.012 0.012 19.502 19.502 qs_scf_new_mos 108 7.5 0.001 0.001 19.172 19.172 qs_scf_loop_do_ot 108 8.5 0.001 0.001 19.172 19.172 dbcsr_multiply_generic 2286 12.5 0.158 0.158 19.014 19.014 qs_rho_update_rho_low 119 7.7 0.001 0.001 18.706 18.706 calculate_rho_elec 119 8.7 0.949 0.949 18.705 18.705 qs_ks_update_qs_env 119 7.6 0.001 0.001 17.922 17.922 ot_scf_mini 108 9.5 0.002 0.002 17.881 17.881 init_scf_loop 11 6.9 0.000 0.000 15.800 15.800 grid_collocate_task_list 119 9.7 14.582 14.582 14.582 14.582 prepare_preconditioner 11 7.9 0.000 0.000 13.397 13.397 make_preconditioner 11 8.9 0.000 0.000 13.397 13.397 sum_up_and_integrate 119 10.3 0.502 0.502 12.715 12.715 make_full_inverse_cholesky 11 9.9 0.000 0.000 12.263 12.263 integrate_v_rspace 119 11.3 0.093 0.093 12.213 12.213 ot_mini 108 10.5 0.001 0.001 11.482 11.482 make_m2s 4572 13.5 0.045 0.045 10.635 10.635 grid_integrate_task_list 119 12.3 10.338 10.338 10.338 10.338 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 5.997 5.997 qs_ot_get_derivative 108 11.5 0.001 0.001 5.992 5.992 dbcsr_make_dense_low 5837 15.5 0.065 0.065 5.801 5.801 make_dense_data 5837 16.5 5.080 5.080 5.722 5.722 pw_transfer 1439 11.6 0.062 0.062 5.569 5.569 ot_diis_step 108 11.5 0.004 0.004 5.487 5.487 fft_wrap_pw1pw2 1201 12.6 0.006 0.006 5.370 5.370 make_images 4572 14.5 2.106 2.106 5.283 5.283 dbcsr_make_images_dense 3978 14.8 0.017 0.017 5.054 5.054 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 5.012 5.012 apply_single 119 13.6 0.000 0.000 5.012 5.012 fft_wrap_pw1pw2_140 487 13.2 0.366 0.366 4.563 4.563 multiply_cannon 2286 13.5 0.170 0.170 4.555 4.555 cp_fm_cholesky_decompose 22 10.9 4.200 4.200 4.200 4.200 multiply_cannon_loop 2286 14.5 0.042 0.042 4.109 4.109 multiply_cannon_multrec 2286 15.5 4.024 4.024 4.066 4.066 cp_fm_cholesky_invert 11 10.9 3.948 3.948 3.948 3.948 init_scf_run 11 5.9 0.002 0.002 3.776 3.776 scf_env_initial_rho_setup 11 6.9 0.001 0.001 3.774 3.774 dbcsr_complete_redistribute 329 12.2 1.920 1.920 3.607 3.607 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 3.351 3.351 dbcsr_copy 2102 12.0 0.192 0.192 3.350 3.350 wfi_extrapolate 11 7.9 0.001 0.001 3.275 3.275 qs_env_update_s_mstruct 11 6.9 0.000 0.000 3.205 3.205 density_rs2pw 119 9.7 0.003 0.003 3.175 3.175 dbcsr_copy_into_existing 22 7.9 3.128 3.128 3.128 3.128 qs_ot_get_p 119 10.4 0.001 0.001 3.098 3.098 copy_dbcsr_to_fm 153 11.3 0.002 0.002 2.965 2.965 qs_create_task_list 11 7.9 0.000 0.000 2.850 2.850 generate_qs_task_list 11 8.9 1.959 1.959 2.850 2.850 fft3d_s 1202 14.6 2.637 2.637 2.641 2.641 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 2.532 2.532 build_core_hamiltonian_matrix 11 6.9 0.000 0.000 2.388 2.388 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.312 2.312 dbcsr_data_release 279534 16.0 1.969 1.969 1.969 1.969 pw_poisson_solve 119 10.3 0.330 0.330 1.947 1.947 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 1.922 1.922 qs_ot_p2m_diag 50 11.0 0.154 0.154 1.854 1.854 copy_fm_to_dbcsr 176 11.2 0.001 0.001 1.800 1.800 qs_ot_get_derivative_taylor 59 13.0 0.001 0.001 1.794 1.794 potential_pw2rs 119 12.3 0.045 0.045 1.782 1.782 cp_fm_upper_to_full 72 14.2 1.732 1.732 1.732 1.732 ------------------------------------------------------------------------------- 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 0.007 0.021 41.914 41.923 qs_mol_dyn_low 1 2.0 0.003 0.004 41.816 41.820 qs_forces 11 3.9 0.001 0.001 41.776 41.777 qs_energies 11 4.9 0.001 0.001 39.015 39.017 scf_env_do_scf 11 5.9 0.000 0.002 35.794 35.794 scf_env_do_scf_inner_loop 108 6.5 0.003 0.018 33.036 33.036 velocity_verlet 10 3.0 0.001 0.003 24.958 24.959 rebuild_ks_matrix 119 8.3 0.000 0.001 15.187 15.336 qs_ks_build_kohn_sham_matrix 119 9.3 0.014 0.015 15.187 15.335 qs_ks_update_qs_env 119 7.6 0.001 0.001 13.501 13.638 qs_rho_update_rho_low 119 7.7 0.001 0.001 12.426 12.435 calculate_rho_elec 119 8.7 0.029 0.031 12.425 12.434 dbcsr_multiply_generic 2286 12.5 0.068 0.072 12.059 12.345 sum_up_and_integrate 119 10.3 0.027 0.034 11.363 11.396 integrate_v_rspace 119 11.3 0.004 0.006 11.336 11.373 qs_scf_new_mos 108 7.5 0.001 0.001 9.630 9.777 qs_scf_loop_do_ot 108 8.5 0.001 0.001 9.629 9.777 multiply_cannon 2286 13.5 0.143 0.161 8.828 9.404 ot_scf_mini 108 9.5 0.002 0.002 9.030 9.158 grid_collocate_task_list 119 9.7 8.831 9.129 8.831 9.129 multiply_cannon_loop 2286 14.5 0.085 0.104 8.345 8.968 mp_waitall_1 169478 16.3 7.300 8.409 7.300 8.409 grid_integrate_task_list 119 12.3 7.914 8.154 7.914 8.154 multiply_cannon_metrocomm3 18288 15.5 0.035 0.040 4.762 5.833 ot_mini 108 10.5 0.001 0.001 5.223 5.362 rs_pw_transfer 974 11.9 0.010 0.012 3.863 4.307 density_rs2pw 119 9.7 0.005 0.006 3.261 3.698 pw_transfer 1439 11.6 0.094 0.117 3.233 3.321 fft_wrap_pw1pw2 1201 12.6 0.008 0.011 3.073 3.155 multiply_cannon_multrec 18288 15.5 2.811 3.079 2.820 3.092 potential_pw2rs 119 12.3 0.006 0.007 2.971 2.993 fft_wrap_pw1pw2_140 487 13.2 0.239 0.290 2.647 2.816 qs_ot_get_derivative 108 11.5 0.001 0.001 2.686 2.812 init_scf_loop 11 6.9 0.000 0.000 2.745 2.745 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 2.408 2.559 apply_single 119 13.6 0.000 0.000 2.408 2.559 ot_diis_step 108 11.5 0.003 0.003 2.513 2.513 fft3d_ps 1201 14.6 1.154 1.275 2.243 2.324 init_scf_run 11 5.9 0.000 0.004 2.270 2.270 scf_env_initial_rho_setup 11 6.9 0.000 0.003 2.269 2.270 make_m2s 4572 13.5 0.044 0.047 2.123 2.190 wfi_extrapolate 11 7.9 0.001 0.001 2.061 2.061 make_images 4572 14.5 0.113 0.115 1.814 1.886 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 1.813 1.825 mp_waitany 9880 13.7 1.195 1.665 1.195 1.665 qs_ot_get_p 119 10.4 0.001 0.001 1.223 1.364 multiply_cannon_metrocomm1 18288 15.5 0.017 0.020 0.496 1.312 rs_pw_transfer_RS2PW_140 130 11.5 0.175 0.207 0.861 1.307 rs_pw_transfer_PW2RS_140 130 13.9 0.322 0.398 1.128 1.179 make_images_data 4572 15.5 0.033 0.040 1.014 1.162 prepare_preconditioner 11 7.9 0.000 0.000 1.069 1.086 make_preconditioner 11 8.9 0.000 0.000 1.069 1.085 mp_alltoall_z22v 1201 16.6 0.862 1.082 0.862 1.082 mp_sum_l 11218 13.2 0.686 1.048 0.686 1.048 make_full_inverse_cholesky 11 9.9 0.000 0.000 0.962 0.981 hybrid_alltoall_any 4725 16.4 0.054 0.143 0.882 0.979 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 0.866 0.942 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 0.850 0.926 qs_ot_get_derivative_taylor 59 13.0 0.001 0.001 0.853 0.902 mp_alltoall_d11v 2130 13.8 0.639 0.842 0.639 0.842 cp_dbcsr_sm_fm_multiply 37 9.5 0.001 0.001 0.840 0.841 ------------------------------------------------------------------------------- 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=46.75999999999999, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=14.582, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=10.338, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="make_dense_data", label="make_dense_data", y=5.08, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=4.2, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=4.024, 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=13.863000000000003, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=8.831, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=7.914, 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="multiply_cannon_multrec", label="multiply_cannon_multrec", y=2.811, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitany", label="mp_waitany", y=1.195, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=7.3, 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 0.034 0.034 109.136 109.136 qs_mol_dyn_low 1 2.0 0.002 0.002 108.491 108.491 qs_forces 11 3.9 0.001 0.001 108.452 108.452 qs_energies 11 4.9 0.001 0.001 100.690 100.690 scf_env_do_scf 11 5.9 0.001 0.001 88.020 88.020 scf_env_do_scf_inner_loop 96 6.5 0.010 0.010 70.596 70.596 velocity_verlet 10 3.0 0.002 0.002 69.881 69.881 rebuild_ks_matrix 107 8.3 0.001 0.001 32.961 32.961 qs_ks_build_kohn_sham_matrix 107 9.3 0.011 0.011 32.960 32.960 qs_rho_update_rho_low 107 7.7 0.000 0.000 30.864 30.864 calculate_rho_elec 107 8.7 0.854 0.854 30.864 30.864 qs_ks_update_qs_env 107 7.6 0.001 0.001 29.704 29.704 grid_collocate_task_list 107 9.7 27.070 27.070 27.070 27.070 sum_up_and_integrate 107 10.3 0.448 0.448 26.392 26.392 integrate_v_rspace 107 11.3 0.077 0.077 25.944 25.944 grid_integrate_task_list 107 12.3 24.242 24.242 24.242 24.242 dbcsr_multiply_generic 1966 12.4 0.137 0.137 17.313 17.313 init_scf_loop 11 6.9 0.000 0.000 17.256 17.256 qs_scf_new_mos 96 7.5 0.001 0.001 16.671 16.671 qs_scf_loop_do_ot 96 8.5 0.001 0.001 16.671 16.671 ot_scf_mini 96 9.5 0.002 0.002 15.544 15.544 prepare_preconditioner 11 7.9 0.000 0.000 13.276 13.276 make_preconditioner 11 8.9 0.000 0.000 13.276 13.276 make_full_inverse_cholesky 11 9.9 0.000 0.000 12.175 12.175 ot_mini 96 10.5 0.001 0.001 10.118 10.118 make_m2s 3932 13.4 0.039 0.039 9.493 9.493 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 6.508 6.508 init_scf_run 11 5.9 0.002 0.002 5.443 5.443 scf_env_initial_rho_setup 11 6.9 0.001 0.001 5.441 5.441 qs_ot_get_derivative 96 11.5 0.001 0.001 5.303 5.303 pw_transfer 1295 11.6 0.058 0.058 5.259 5.259 fft_wrap_pw1pw2 1081 12.6 0.006 0.006 5.056 5.056 dbcsr_make_dense_low 4961 15.5 0.062 0.062 4.999 4.999 make_dense_data 4961 16.5 4.419 4.419 4.926 4.926 make_images 3932 14.4 1.895 1.895 4.842 4.842 ot_diis_step 96 11.5 0.003 0.003 4.813 4.813 wfi_extrapolate 11 7.9 0.001 0.001 4.769 4.769 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 4.491 4.491 apply_single 107 13.6 0.000 0.000 4.491 4.491 dbcsr_make_images_dense 3386 14.7 0.015 0.015 4.404 4.404 fft_wrap_pw1pw2_140 439 13.2 0.360 0.360 4.345 4.345 multiply_cannon 1966 13.4 0.147 0.147 4.185 4.185 cp_fm_cholesky_decompose 22 10.9 4.156 4.156 4.156 4.156 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 4.106 4.106 cp_fm_cholesky_invert 11 10.9 3.897 3.897 3.897 3.897 dbcsr_complete_redistribute 317 12.2 1.896 1.896 3.851 3.851 multiply_cannon_loop 1966 14.4 0.038 0.038 3.799 3.799 multiply_cannon_multrec 1966 15.4 3.717 3.717 3.759 3.759 dbcsr_copy 1855 11.9 0.220 0.220 3.691 3.691 qs_env_update_s_mstruct 11 6.9 0.000 0.000 3.667 3.667 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 3.654 3.654 dbcsr_copy_into_existing 22 7.9 3.383 3.383 3.383 3.383 qs_create_task_list 11 7.9 0.000 0.000 3.271 3.271 generate_qs_task_list 11 8.9 2.394 2.394 3.271 3.271 copy_dbcsr_to_fm 147 11.2 0.002 0.002 3.133 3.133 density_rs2pw 107 9.7 0.003 0.003 2.940 2.940 fft3d_s 1082 14.6 2.568 2.568 2.572 2.572 build_core_hamiltonian_matrix 11 6.9 0.000 0.000 2.414 2.414 qs_ot_get_p 107 10.4 0.001 0.001 2.383 2.383 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.381 2.381 ------------------------------------------------------------------------------- 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 0.019 69.394 69.404 qs_mol_dyn_low 1 2.0 0.003 0.004 69.299 69.303 qs_forces 11 3.9 0.001 0.001 69.259 69.259 qs_energies 11 4.9 0.001 0.001 64.567 64.569 scf_env_do_scf 11 5.9 0.000 0.002 59.806 59.806 scf_env_do_scf_inner_loop 96 6.5 0.002 0.017 55.328 55.328 velocity_verlet 10 3.0 0.002 0.003 41.212 41.213 rebuild_ks_matrix 107 8.3 0.000 0.001 30.047 30.216 qs_ks_build_kohn_sham_matrix 107 9.3 0.014 0.017 30.046 30.215 qs_ks_update_qs_env 107 7.6 0.001 0.001 26.432 26.595 sum_up_and_integrate 107 10.3 0.034 0.037 26.380 26.399 integrate_v_rspace 107 11.3 0.004 0.005 26.346 26.367 qs_rho_update_rho_low 107 7.7 0.000 0.001 25.333 25.343 calculate_rho_elec 107 8.7 0.027 0.028 25.333 25.342 grid_integrate_task_list 107 12.3 22.713 23.220 22.713 23.220 grid_collocate_task_list 107 9.7 21.728 22.247 21.728 22.247 dbcsr_multiply_generic 1966 12.4 0.063 0.067 11.732 12.003 qs_scf_new_mos 96 7.5 0.001 0.001 9.158 9.300 qs_scf_loop_do_ot 96 8.5 0.001 0.001 9.157 9.300 multiply_cannon 1966 13.4 0.126 0.147 8.646 9.246 multiply_cannon_loop 1966 14.4 0.088 0.104 8.203 8.822 ot_scf_mini 96 9.5 0.002 0.002 8.604 8.750 mp_waitall_1 146670 16.2 7.129 7.816 7.129 7.816 multiply_cannon_metrocomm3 15728 15.4 0.035 0.040 4.816 5.655 ot_mini 96 10.5 0.001 0.001 5.011 5.170 rs_pw_transfer 878 11.9 0.010 0.011 3.933 4.538 init_scf_loop 11 6.9 0.000 0.000 4.464 4.464 density_rs2pw 107 9.7 0.005 0.005 3.303 3.915 init_scf_run 11 5.9 0.000 0.004 3.763 3.763 scf_env_initial_rho_setup 11 6.9 0.000 0.003 3.763 3.763 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 3.735 3.749 wfi_extrapolate 11 7.9 0.001 0.001 3.420 3.421 pw_transfer 1295 11.6 0.099 0.109 3.039 3.094 fft_wrap_pw1pw2 1081 12.6 0.009 0.010 2.879 2.938 multiply_cannon_multrec 15728 15.4 2.650 2.903 2.659 2.915 potential_pw2rs 107 12.3 0.006 0.007 2.819 2.832 qs_ot_get_derivative 96 11.5 0.001 0.001 2.610 2.751 fft_wrap_pw1pw2_140 439 13.2 0.252 0.273 2.491 2.564 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 2.353 2.481 apply_single 107 13.6 0.000 0.000 2.353 2.481 ot_diis_step 96 11.5 0.003 0.003 2.383 2.383 fft3d_ps 1081 14.6 1.132 1.216 2.057 2.122 make_m2s 3932 13.4 0.040 0.045 2.011 2.045 mp_waitany 8968 13.7 1.426 2.005 1.426 2.005 make_images 3932 14.4 0.103 0.106 1.725 1.763 mp_alltoall_d11v 1998 13.7 0.998 1.745 0.998 1.745 rs_pw_transfer_RS2PW_140 118 11.5 0.155 0.167 1.124 1.731 rs_gather_matrices 107 12.3 0.065 0.076 0.777 1.492 ------------------------------------------------------------------------------- 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=41.635000000000005, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=27.07, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=24.242, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="make_dense_data", label="make_dense_data", y=4.419, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=4.156, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=3.897, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=3.717, 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=13.748000000000005, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=21.728, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=22.713, 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=2.65, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitany", label="mp_waitany", y=1.426, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=7.129, 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 0.188 0.188 103.321 103.321 qs_energies 1 2.0 0.000 0.000 102.511 102.511 scf_env_do_scf 1 3.0 0.000 0.000 101.375 101.375 qs_ks_update_qs_env 8 5.0 0.000 0.000 96.549 96.549 rebuild_ks_matrix 7 6.0 0.000 0.000 96.494 96.494 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.001 96.494 96.494 hfx_ks_matrix 7 8.0 0.000 0.000 87.734 87.734 integrate_four_center 7 9.0 1.854 1.854 87.715 87.715 integrate_four_center_main 7 10.0 0.660 0.660 79.984 79.984 integrate_four_center_bin 449 11.0 79.324 79.324 79.324 79.324 scf_env_do_scf_inner_loop 7 4.0 0.001 0.001 55.632 55.632 init_scf_loop 1 4.0 0.000 0.000 45.734 45.734 integrate_four_center_load 7 10.0 0.000 0.000 5.633 5.633 hfx_load_balance 1 11.0 0.001 0.001 5.633 5.633 qs_vxc_create 14 8.0 0.000 0.000 3.090 3.090 xc_vxc_pw_create 14 9.0 0.116 0.116 3.090 3.090 hfx_load_balance_bin 1 12.0 2.810 2.810 2.810 2.810 hfx_load_balance_count 1 12.0 2.806 2.806 2.806 2.806 calculate_rho_elec 15 7.4 0.118 0.118 2.418 2.418 xc_rho_set_and_dset_create 14 10.0 0.084 0.084 2.324 2.324 admm_mo_calc_rho_aux 7 8.0 0.000 0.000 2.302 2.302 prepare_preconditioner 1 5.0 0.000 0.000 2.269 2.269 make_preconditioner 1 6.0 0.000 0.000 2.269 2.269 ------------------------------------------------------------------------------- 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 0.208 0.228 94.505 94.516 qs_energies 1 2.0 0.000 0.000 94.181 94.187 scf_env_do_scf 1 3.0 0.000 0.000 93.850 93.851 qs_ks_update_qs_env 8 5.0 0.000 0.000 91.968 91.969 rebuild_ks_matrix 7 6.0 0.000 0.000 91.960 91.961 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.002 91.960 91.961 hfx_ks_matrix 7 8.0 0.000 0.001 86.838 86.839 integrate_four_center 7 9.0 0.051 0.327 86.829 86.830 integrate_four_center_main 7 10.0 0.003 0.003 78.008 79.507 integrate_four_center_bin 448 11.0 78.005 79.504 78.005 79.504 scf_env_do_scf_inner_loop 7 4.0 0.000 0.001 52.732 52.733 init_scf_loop 1 4.0 0.000 0.000 41.117 41.117 integrate_four_center_load 7 10.0 0.000 0.000 5.657 5.658 hfx_load_balance 1 11.0 0.001 0.001 5.657 5.658 mp_sync 70 11.3 2.507 4.091 2.507 4.091 hfx_load_balance_bin 1 12.0 2.765 2.826 2.765 2.826 hfx_load_balance_count 1 12.0 2.764 2.825 2.764 2.825 qs_vxc_create 14 8.0 0.000 0.000 2.354 2.354 xc_vxc_pw_create 14 9.0 0.006 0.007 2.354 2.354 xc_rho_set_and_dset_create 14 10.0 0.009 0.010 1.904 2.013 ------------------------------------------------------------------------------- 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=15.679000000000002, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_bin", label="integrate_four_center_bin", y=79.324, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=2.81, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_count", label="hfx_load_balance_count", y=2.806, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center", label="integrate_four_center", y=1.854, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_main", label="integrate_four_center_main", y=0.66, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="CP2K", label="CP2K", y=0.188, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="mp_sync", label="mp_sync", y=0.0, yerr=0.0 Plot: name="H2O-hyb_timings_32mpi", title="Timings of H2O-hyb with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="H2O-hyb_timings_32mpi", name="rest", label="rest", y=8.201999999999998, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center_bin", label="integrate_four_center_bin", y=78.005, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=2.765, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_count", label="hfx_load_balance_count", y=2.764, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center", label="integrate_four_center", y=0.051, 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=0.208, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="mp_sync", label="mp_sync", y=2.507, 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 88.124 88.124 qs_energies 1 2.0 0.000 0.000 87.754 87.754 mp2_main 1 3.0 0.000 0.000 85.030 85.030 mp2_gpw_main 1 4.0 0.000 0.000 84.930 84.930 rpa_ri_compute_en 1 5.0 0.000 0.000 81.688 81.688 rpa_num_int 1 6.0 0.001 0.001 81.682 81.682 compute_mat_P_omega 1 7.0 0.003 0.003 71.927 71.927 compute_mat_P_omega_contract 10 8.0 8.808 8.808 71.725 71.725 dbt_total 2336 9.6 0.010 0.010 58.196 58.196 dbt_contract 787 11.0 0.035 0.035 51.604 51.604 dbt_tas_total 1149 12.2 0.186 0.186 50.884 50.884 dbt_tas_multiply 807 12.1 0.002 0.002 49.421 49.421 dbt_tas_dbm 807 14.1 0.003 0.003 43.096 43.096 dbm_multiply 807 16.1 43.088 43.088 43.088 43.088 dbt_tas_mm_1N 524 15.1 0.001 0.001 34.636 34.636 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 32.971 32.971 compute_mat_P_omega_calc_M_occ 250 9.0 8.843 8.843 16.694 16.694 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 7.815 7.815 dbt_tas_mm_2 251 15.0 0.001 0.001 6.869 6.869 dbt_copy 1103 10.7 0.067 0.067 5.114 5.114 compute_QP_energies 1 7.0 0.000 0.000 5.108 5.108 compute_self_energy_cubic_gw 1 8.0 0.054 0.054 5.107 5.107 contract_cubic_gw 21 9.0 0.000 0.000 4.156 4.156 mp2_ri_gpw_compute_in 1 5.0 0.001 0.001 3.236 3.236 dbt_tas_reserve_blocks_index 3261 14.3 0.145 0.145 3.132 3.132 dbm_reserve_blocks 3628 15.3 3.068 3.068 3.068 3.068 scf_env_do_scf 1 3.0 0.000 0.000 2.576 2.576 scf_env_do_scf_inner_loop 17 4.0 0.002 0.002 2.575 2.575 dbt_reserve_blocks_index 2280 13.1 0.047 0.047 2.361 2.361 dbt_reserve_blocks_index_array 2222 12.2 0.008 0.008 2.352 2.352 convert_to_new_pgrid 2421 14.1 0.067 0.067 2.196 2.196 dbt_tas_reshape 367 15.0 0.006 0.006 2.139 2.139 dbm_copy 1614 15.1 2.129 2.129 2.129 2.129 dbt_crop 1042 12.0 1.335 1.335 2.082 2.082 dbt_tas_copy 574 11.4 1.293 1.293 2.080 2.080 compute_W_cubic_GW 10 7.0 0.011 0.011 1.969 1.969 rpa_num_int_RPA_matrix_operati 10 7.0 0.000 0.000 1.828 1.828 ------------------------------------------------------------------------------- From /workspace/artifacts/GW_PBE_4benzene_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.005 0.021 30.345 30.355 qs_energies 1 2.0 0.000 0.001 30.274 30.275 mp2_main 1 3.0 0.000 0.004 29.354 29.355 mp2_gpw_main 1 4.0 0.000 0.000 29.316 29.317 rpa_ri_compute_en 1 5.0 0.000 0.000 28.035 28.036 rpa_num_int 1 6.0 0.000 0.002 28.034 28.035 dbt_total 2336 9.6 0.011 0.011 24.990 24.992 compute_mat_P_omega 1 7.0 0.001 0.005 23.921 23.946 compute_mat_P_omega_contract 10 8.0 0.411 0.425 23.797 23.799 dbt_contract 787 11.0 0.025 0.026 18.825 18.831 dbt_tas_total 1149 12.2 0.051 0.056 16.889 16.889 dbt_tas_multiply 807 12.1 0.002 0.002 16.836 16.838 dbt_tas_dbm 807 14.1 0.003 0.003 12.511 12.519 dbm_multiply 807 16.1 9.801 10.602 9.801 10.602 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 7.258 7.258 compute_mat_P_omega_calc_M_occ 250 9.0 0.392 0.406 6.941 6.941 dbt_tas_mm_2 251 15.0 0.001 0.001 6.040 6.043 dbt_copy 1111 10.7 0.011 0.012 5.489 5.664 dbt_reshape 1098 11.7 2.129 2.268 5.242 5.407 mp_sync 8706 11.6 4.221 5.374 4.221 5.374 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 5.004 5.004 dbt_tas_mm_1N 524 15.1 0.001 0.002 4.451 4.772 compute_QP_energies 1 7.0 0.000 0.000 2.640 2.641 compute_self_energy_cubic_gw 1 8.0 0.003 0.003 2.638 2.640 dbt_communicate_buffer 1098 12.7 0.053 0.057 2.463 2.561 mp_waitall_2 3776 15.3 2.405 2.548 2.405 2.548 contract_cubic_gw 21 9.0 0.000 0.000 2.111 2.111 dbt_reserve_blocks_index_array 2791 12.2 0.010 0.011 1.565 1.702 dbt_reserve_blocks_index 2849 13.1 0.061 0.066 1.564 1.702 dbt_tas_reserve_blocks_index 3300 14.5 0.115 0.124 1.537 1.669 dbm_reserve_blocks 3696 15.4 1.512 1.638 1.512 1.638 dbt_crop 1042 12.0 0.904 0.997 1.396 1.518 mp2_ri_gpw_compute_in 1 5.0 0.000 0.001 1.277 1.280 dbt_tas_replicate 396 14.1 0.527 0.690 1.061 1.113 convert_to_new_pgrid 2421 14.1 0.024 0.028 0.814 0.990 dbm_copy 1608 15.1 0.784 0.961 0.784 0.961 compute_mat_P_omega_copy_M_vir 250 9.0 0.001 0.001 0.954 0.957 scf_env_do_scf 1 3.0 0.000 0.000 0.884 0.884 scf_env_do_scf_inner_loop 17 4.0 0.000 0.002 0.884 0.884 compute_mat_P_omega_copy_M_occ 250 9.0 0.001 0.001 0.879 0.881 parallel_gemm_fm 105 8.4 0.000 0.000 0.867 0.876 parallel_gemm_fm_cosma 105 9.4 0.867 0.876 0.867 0.876 dbm_add 807 14.1 0.657 0.695 0.657 0.695 compute_W_cubic_GW 10 7.0 0.001 0.001 0.652 0.657 mp_max_i 1994 9.8 0.476 0.650 0.476 0.650 ------------------------------------------------------------------------------- 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=22.188000000000002, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=43.088, 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=8.843, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=8.808, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=3.068, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_copy", label="dbm_copy", y=2.129, 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="dbt_reshape", label="dbt_reshape", 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=8.689999999999994, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=9.801, 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=0.392, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=0.411, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=1.512, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_copy", label="dbm_copy", y=0.784, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_sync", label="mp_sync", y=4.221, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=2.129, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.405, 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 0.018 0.018 370.459 370.459 qs_forces 1 2.0 0.000 0.000 369.910 369.910 rebuild_ks_matrix 7 6.6 0.000 0.000 368.485 368.485 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.001 368.485 368.485 hfx_ks_matrix 7 8.6 0.000 0.000 366.522 366.522 hfx_ri_update_ks 7 9.6 0.000 0.000 329.762 329.762 hfx_ri_update_ks_Pmat 7 10.6 30.813 30.813 329.758 329.758 dbt_total 841 11.0 0.005 0.005 313.658 313.658 dbt_contract 207 12.4 0.107 0.107 296.030 296.030 dbt_tas_total 375 13.4 1.481 1.481 295.789 295.789 dbt_tas_multiply 216 13.5 0.001 0.001 291.351 291.351 qs_energies 1 3.0 0.000 0.000 290.824 290.824 scf_env_do_scf 1 4.0 0.000 0.000 290.548 290.548 qs_ks_update_qs_env 8 6.0 0.000 0.000 289.445 289.445 dbt_tas_dbm 216 15.5 0.001 0.001 280.439 280.439 dbm_multiply 216 17.5 280.436 280.436 280.436 280.436 hfx_ri_update_ks_Pmat_KS 63 11.6 0.001 0.001 275.826 275.826 dbt_tas_mm_2 91 16.5 0.001 0.001 267.382 267.382 scf_env_do_scf_inner_loop 6 5.0 0.001 0.001 185.458 185.458 init_scf_loop 2 5.0 0.000 0.000 105.088 105.088 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 79.043 79.043 hfx_ri_update_forces 1 7.0 1.695 1.695 36.720 36.720 hfx_ri_forces_Pmat_3c 1 8.0 4.588 4.588 21.134 21.134 dbt_copy 409 11.7 0.024 0.024 13.182 13.182 precalc_derivatives 1 8.0 2.100 2.100 11.942 11.942 dbt_reshape 132 13.2 5.660 5.660 9.234 9.234 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 9.173 9.173 dbt_tas_mm_3T 77 17.1 0.000 0.000 8.969 8.969 ------------------------------------------------------------------------------- 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 0.006 0.021 42.949 42.959 qs_forces 1 2.0 0.000 0.000 42.847 42.848 rebuild_ks_matrix 7 6.6 0.000 0.000 42.211 42.211 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.002 42.211 42.211 hfx_ks_matrix 7 8.6 0.000 0.000 41.274 41.281 dbt_total 841 11.0 0.005 0.006 36.710 36.712 dbt_contract 207 12.4 0.020 0.021 29.085 29.094 dbt_tas_total 375 13.4 0.060 0.179 27.059 27.059 dbt_tas_multiply 216 13.5 0.001 0.001 26.123 26.123 hfx_ri_update_ks 7 9.6 0.000 0.001 24.136 24.136 hfx_ri_update_ks_Pmat 7 10.6 1.198 1.258 24.135 24.135 qs_energies 1 3.0 0.000 0.000 22.663 22.663 scf_env_do_scf 1 4.0 0.000 0.001 22.530 22.530 qs_ks_update_qs_env 8 6.0 0.000 0.000 22.036 22.037 dbt_tas_dbm 216 15.5 0.001 0.001 20.753 20.764 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 20.175 20.176 dbm_multiply 216 17.5 18.484 19.389 18.484 19.389 hfx_ri_update_forces 1 7.0 0.056 0.059 17.138 17.144 hfx_ri_forces_Pmat_3c 1 8.0 0.161 0.171 12.892 12.901 scf_env_do_scf_inner_loop 6 5.0 0.000 0.001 12.611 12.612 hfx_ri_update_ks_Pmat_KS 63 11.6 0.001 0.001 11.369 11.369 init_scf_loop 2 5.0 0.000 0.000 9.918 9.918 dbt_tas_mm_2 91 16.5 0.001 0.001 9.538 9.544 dbt_copy 421 11.8 0.010 0.012 6.438 6.583 mp_sync 2909 12.8 4.034 6.268 4.034 6.268 dbt_tas_mm_3T 77 17.1 0.000 0.000 5.784 6.170 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 4.899 4.899 dbt_reshape 252 12.8 2.264 2.315 4.350 4.442 dbt_tas_mm_3N 37 15.4 0.000 0.000 3.898 4.088 precalc_derivatives 1 8.0 0.079 0.084 3.222 3.222 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 3.092 3.092 dbm_reserve_blocks 1477 16.3 2.476 2.722 2.476 2.722 dbt_tas_reserve_blocks_index 1302 15.5 0.214 0.224 2.457 2.708 dbt_crop 372 13.7 1.696 1.777 2.301 2.418 mp_waitall_2 1204 16.3 2.076 2.155 2.076 2.155 dbt_reserve_blocks_index 938 14.4 0.087 0.093 1.928 2.112 dbt_reserve_blocks_index_array 915 13.4 0.005 0.006 1.906 2.085 build_3c_derivatives 3 9.0 0.219 0.235 1.780 1.790 dbt_tas_replicate 175 15.2 0.690 0.722 1.653 1.681 hfx_ri_pre_scf_Pmat_RIx3C 9 13.0 0.000 0.000 1.649 1.652 dbt_tas_copy 169 12.8 0.865 0.901 1.460 1.559 convert_to_new_pgrid 648 15.5 0.031 0.052 1.333 1.517 dbt_communicate_buffer 252 13.8 0.012 0.012 1.397 1.445 dbm_copy 452 16.3 1.154 1.354 1.154 1.354 hfx_ri_update_ks_Pmat_copy_2 63 11.6 0.000 0.000 1.332 1.333 dbt_tas_communicate_buffer 352 16.4 0.013 0.014 0.906 0.960 ------------------------------------------------------------------------------- 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=46.861999999999966, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=280.436, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=30.813, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=5.66, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_forces_Pmat_3c", label="hfx_ri_forces_Pmat_3c", y=4.588, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="precalc_derivatives", label="precalc_derivatives", y=2.1, 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 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", 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=12.176999999999996, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=18.484, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=1.198, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=2.264, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_forces_Pmat_3c", label="hfx_ri_forces_Pmat_3c", y=0.161, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="precalc_derivatives", label="precalc_derivatives", y=0.079, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.076, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_sync", label="mp_sync", y=4.034, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=2.476, 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 0.014 0.014 202.922 202.922 qs_energies 1 2.0 0.000 0.000 202.742 202.742 mp2_main 1 3.0 0.000 0.000 198.103 198.103 mp2_gpw_main 1 4.0 0.001 0.001 197.724 197.724 mp2_ri_gpw_compute_in 1 5.0 0.375 0.375 153.280 153.280 mp2_ri_gpw_compute_in_loop 1 6.0 0.009 0.009 142.460 142.460 mp2_eri_3c_integrate_gpw 2656 7.0 0.012 0.012 113.290 113.290 integrate_v_rspace 2666 8.0 0.583 0.583 100.468 100.468 grid_integrate_task_list 2666 9.0 97.922 97.922 97.922 97.922 mp2_ri_gpw_compute_en 1 5.0 0.092 0.092 44.419 44.419 mp2_ri_gpw_compute_en_RI_loop 1 6.0 9.354 9.354 42.602 42.602 mp2_ri_gpw_compute_en_expansio 2080 7.0 1.999 1.999 25.961 25.961 local_gemm 2080 8.0 23.962 23.962 23.962 23.962 dbcsr_multiply_generic 5322 8.0 0.172 0.172 19.779 19.779 ao_to_mo_and_store_B_mult_1 2656 7.0 0.009 0.009 19.745 19.745 pw_transfer 63872 10.6 1.016 1.016 11.466 11.466 calculate_wavefunction 2656 8.0 8.113 8.113 11.463 11.463 get_2c_integrals 1 6.0 0.000 0.000 10.444 10.444 fft_wrap_pw1pw2 53228 11.4 0.112 0.112 10.252 10.252 multiply_cannon 5322 9.0 0.429 0.429 10.036 10.036 compute_2c_integrals 1 7.0 0.006 0.006 9.626 9.626 compute_2c_integrals_loop_lm 1 8.0 0.014 0.014 9.607 9.607 mp2_eri_2c_integrate_gpw 1 9.0 3.085 3.085 9.593 9.593 ao_to_mo_and_store_B_E_Ex_1 2656 7.0 2.187 2.187 9.323 9.323 multiply_cannon_loop 5322 10.0 0.111 0.111 8.725 8.725 make_m2s 10644 9.0 0.062 0.062 7.652 7.652 copy_dbcsr_to_fm 2679 8.0 0.026 0.026 7.622 7.622 fft_wrap_pw1pw2_20 21271 12.4 0.468 0.468 7.397 7.397 make_images 10644 10.0 3.110 3.110 7.358 7.358 multiply_cannon_multrec 5322 11.0 7.251 7.251 7.289 7.289 fft3d_s 53229 13.4 6.357 6.357 6.396 6.396 dbcsr_complete_redistribute 2689 9.0 1.203 1.203 6.034 6.034 mp2_ri_gpw_compute_en_ener 2080 7.0 5.388 5.388 5.388 5.388 dbcsr_finalize 10708 9.5 0.139 0.139 5.100 5.100 dbcsr_merge_all 8011 10.3 3.177 3.177 4.515 4.515 scf_env_do_scf 1 3.0 0.000 0.000 4.196 4.196 scf_env_do_scf_inner_loop 10 4.0 0.001 0.001 4.196 4.196 ------------------------------------------------------------------------------- From /workspace/artifacts/RI-MP2_ammonia_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.005 0.021 34.056 34.066 qs_energies 1 2.0 0.000 0.000 33.988 33.989 mp2_main 1 3.0 0.000 0.001 31.953 31.954 mp2_gpw_main 1 4.0 0.001 0.002 31.839 31.839 mp2_ri_gpw_compute_in 1 5.0 0.049 0.051 17.064 17.363 mp2_ri_gpw_compute_in_loop 1 6.0 0.001 0.001 15.894 16.188 mp2_ri_gpw_compute_en 1 5.0 0.150 0.156 14.693 14.948 mp2_eri_3c_integrate_gpw 83 7.0 0.001 0.001 13.690 13.811 mp2_ri_gpw_compute_en_RI_loop 1 6.0 0.804 0.862 13.771 13.775 integrate_v_rspace 93 8.1 0.105 0.119 13.543 13.658 grid_integrate_task_list 93 9.1 13.252 13.372 13.252 13.372 mp2_ri_gpw_compute_en_expansio 65 7.0 0.099 0.117 10.383 10.558 local_gemm 65 8.0 10.284 10.448 10.284 10.448 mp2_ri_gpw_compute_en_comm 17 7.0 0.067 0.080 2.231 2.453 dbcsr_multiply_generic 176 8.0 0.008 0.009 1.909 2.228 ao_to_mo_and_store_B_mult_1 83 7.0 0.001 0.001 1.892 2.214 mp_sendrecv_dm3 1054 8.0 1.697 1.964 1.697 1.964 scf_env_do_scf 1 3.0 0.000 0.000 1.921 1.922 scf_env_do_scf_inner_loop 10 4.0 0.000 0.002 1.921 1.921 multiply_cannon 176 9.0 0.016 0.017 1.074 1.175 get_2c_integrals 1 6.0 0.000 0.000 1.107 1.132 multiply_cannon_loop 176 10.0 0.002 0.002 1.016 1.113 make_m2s 352 9.0 0.003 0.003 0.796 1.032 make_images 352 10.0 0.051 0.053 0.784 1.019 qs_scf_new_mos 10 5.0 0.000 0.000 1.011 1.017 eigensolver 11 5.8 0.001 0.001 0.998 1.000 multiply_cannon_multrec 246 11.0 0.853 0.904 0.859 0.910 cp_fm_diag_elpa 11 6.8 0.000 0.000 0.847 0.848 cp_fm_redistribute_end 11 7.8 0.321 0.840 0.331 0.842 compute_2c_integrals 1 7.0 0.002 0.003 0.806 0.822 cp_fm_diag_elpa_base 11 7.8 0.496 0.798 0.507 0.815 pw_transfer 2120 10.5 0.044 0.046 0.734 0.745 compute_2c_integrals_loop_lm 1 8.0 0.001 0.003 0.720 0.742 mp2_eri_2c_integrate_gpw 1 9.0 0.198 0.209 0.719 0.742 fft_wrap_pw1pw2 1768 11.4 0.004 0.005 0.677 0.685 ------------------------------------------------------------------------------- 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=56.31999999999999, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=97.922, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="local_gemm", label="local_gemm", y=23.962, 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=9.354, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="calculate_wavefunction", label="calculate_wavefunction", y=8.113, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=7.251, 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=7.165999999999997, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.252, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="local_gemm", label="local_gemm", y=10.284, 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=0.804, 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=0.853, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="mp_sendrecv_dm3", label="mp_sendrecv_dm3", y=1.697, 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 0.087 0.087 123.810 123.810 qs_energies 1 2.0 0.000 0.000 122.454 122.454 scf_env_do_scf 1 3.0 0.000 0.000 115.820 115.820 scf_env_do_scf_inner_loop 15 4.0 0.002 0.002 115.820 115.820 qs_ks_update_qs_env 15 5.0 0.000 0.000 48.321 48.321 rebuild_ks_matrix 15 6.0 0.000 0.000 48.114 48.114 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.002 48.114 48.114 qs_scf_new_mos 15 5.0 0.000 0.000 42.859 42.859 eigensolver 15 6.0 0.001 0.001 35.143 35.143 qs_vxc_create 15 8.0 0.040 0.040 33.186 33.186 calculate_dispersion_nonloc 15 9.0 6.736 6.736 29.018 29.018 cp_fm_diag_elpa 15 7.0 0.000 0.000 22.758 22.758 cp_fm_diag_elpa_base 15 8.0 20.118 20.118 22.758 22.758 pw_transfer 1191 10.0 0.060 0.060 22.657 22.657 fft_wrap_pw1pw2 1086 11.0 0.008 0.008 22.490 22.490 qs_rho_update_rho_low 16 5.0 0.000 0.000 21.835 21.835 calculate_rho_elec 16 6.0 0.219 0.219 21.834 21.834 grid_collocate_task_list 16 7.0 20.516 20.516 20.516 20.516 fft_wrap_pw1pw2_150 765 12.0 3.577 3.577 16.542 16.542 sum_up_and_integrate 15 8.0 0.103 0.103 13.829 13.829 integrate_v_rspace 15 9.0 0.020 0.020 13.726 13.726 grid_integrate_task_list 15 10.0 13.203 13.203 13.203 13.203 fft3d_s 1087 13.0 10.219 10.219 10.227 10.227 cp_fm_cholesky_restore 45 7.0 10.070 10.070 10.070 10.070 pw_scatter_s 585 13.1 6.804 6.804 6.804 6.804 fft_wrap_pw1pw2_200 197 12.3 0.695 0.695 5.765 5.765 copy_dbcsr_to_fm 16 5.9 0.001 0.001 5.636 5.636 dbcsr_complete_redistribute 46 8.3 2.235 2.235 5.523 5.523 cp_fm_upper_to_full 30 8.0 4.953 4.953 4.953 4.953 vdW_energy 15 10.0 4.293 4.293 4.293 4.293 xc_vxc_pw_create 15 9.0 0.218 0.218 4.128 4.128 gspace_mixing 14 5.0 0.171 0.171 4.026 4.026 broyden_mixing 14 6.0 3.427 3.427 3.428 3.428 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 3.061 3.061 init_scf_run 1 3.0 0.000 0.000 3.045 3.045 xc_pw_derive 90 11.0 0.001 0.001 2.709 2.709 ------------------------------------------------------------------------------- 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 0.013 0.030 59.697 59.707 qs_energies 1 2.0 0.001 0.012 59.430 59.435 scf_env_do_scf 1 3.0 0.000 0.001 55.302 55.302 scf_env_do_scf_inner_loop 15 4.0 0.001 0.003 55.301 55.302 qs_ks_update_qs_env 15 5.0 0.000 0.000 23.054 23.060 rebuild_ks_matrix 15 6.0 0.000 0.000 23.022 23.028 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.003 23.022 23.028 qs_rho_update_rho_low 16 5.0 0.000 0.000 20.517 20.520 calculate_rho_elec 16 6.0 0.007 0.007 20.517 20.520 grid_collocate_task_list 16 7.0 19.164 19.876 19.164 19.876 sum_up_and_integrate 15 8.0 0.011 0.017 13.426 13.470 integrate_v_rspace 15 9.0 0.001 0.001 13.414 13.463 grid_integrate_task_list 15 10.0 12.745 12.859 12.745 12.859 qs_scf_new_mos 15 5.0 0.000 0.000 12.444 12.469 eigensolver 15 6.0 0.001 0.002 11.516 11.535 qs_vxc_create 15 8.0 0.001 0.001 9.309 9.319 cp_fm_diag_elpa 15 7.0 0.000 0.000 8.413 8.417 cp_fm_diag_elpa_base 15 8.0 8.270 8.292 8.411 8.413 calculate_dispersion_nonloc 15 9.0 0.903 0.908 7.572 7.592 pw_transfer 1191 10.0 0.099 0.107 7.037 7.106 fft_wrap_pw1pw2 1086 11.0 0.013 0.015 6.854 6.925 fft3d_ps 1086 13.0 2.590 2.725 5.168 5.270 fft_wrap_pw1pw2_150 765 12.0 0.308 0.323 4.562 4.596 cp_fm_cholesky_restore 45 7.0 2.959 2.999 2.959 2.999 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 2.448 2.448 mp_alltoall_z22v 1086 15.0 1.980 2.385 1.980 2.385 build_core_hamiltonian_matrix 1 4.0 0.000 0.000 2.144 2.348 fft_wrap_pw1pw2_200 197 12.3 0.185 0.212 2.183 2.258 xc_vxc_pw_create 15 9.0 0.015 0.019 1.736 1.760 yz_to_x 501 13.9 0.229 0.322 1.385 1.597 rs_pw_transfer 158 9.4 0.001 0.002 1.255 1.518 density_rs2pw 16 7.0 0.001 0.001 1.240 1.423 init_scf_run 1 3.0 0.000 0.001 1.404 1.405 build_core_ppnl 1 5.0 1.253 1.381 1.253 1.381 vdW_energy 15 10.0 1.288 1.330 1.288 1.330 scf_env_initial_rho_setup 1 4.0 0.000 0.000 1.317 1.317 x_to_yz 585 14.1 0.339 0.373 1.164 1.302 mp_waitany 520 11.3 0.860 1.251 0.860 1.251 xc_pw_derive 90 11.0 0.001 0.002 1.143 1.217 ------------------------------------------------------------------------------- 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=49.684, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=20.516, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=20.118, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.203, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="fft3d_s", label="fft3d_s", y=10.219, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=10.07, 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=13.968999999999994, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=19.164, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=8.27, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=12.745, 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=2.959, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=2.59, 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 0.075 0.075 330.445 330.445 qs_energies 1 2.0 0.000 0.000 330.309 330.309 ls_scf 1 3.0 0.000 0.000 329.086 329.086 ls_scf_main 1 4.0 0.002 0.002 319.893 319.893 density_matrix_trs4 11 5.0 0.012 0.012 227.831 227.831 arnoldi_extremal 12 6.1 0.000 0.000 142.464 142.464 arnoldi_normal_ev 12 7.1 0.014 0.014 142.464 142.464 dbcsr_matrix_vector_mult 652 9.0 0.180 0.180 139.946 139.946 build_subspace 23 8.1 0.072 0.072 139.882 139.882 dbcsr_matrix_vector_mult_local 652 10.0 138.459 138.459 138.469 138.469 ls_scf_dm_to_ks 11 5.0 0.000 0.000 86.735 86.735 matrix_ls_to_qs 11 6.0 0.000 0.000 83.400 83.400 dbcsr_multiply_generic 185 6.1 0.875 0.875 74.234 74.234 multiply_cannon 185 7.1 0.338 0.338 45.131 45.131 dbcsr_copy_into_existing 11 7.0 45.095 45.095 45.095 45.095 dbcsr_complete_redistribute 23 7.5 30.711 30.711 42.120 42.120 matrix_decluster 11 7.0 0.000 0.000 38.304 38.304 multiply_cannon_loop 185 8.1 0.248 0.248 32.628 32.628 make_m2s 370 7.1 0.038 0.038 24.496 24.496 make_images 370 8.1 10.563 10.563 22.893 22.893 multiply_cannon_multrec 185 9.1 22.350 22.350 22.383 22.383 dbcsr_finalize 646 7.5 0.237 0.237 14.975 14.975 dbcsr_merge_all 597 8.5 2.417 2.417 13.747 13.747 setup_rec_index_2d 370 8.1 12.018 12.018 12.018 12.018 dbcsr_sort_indices 1103 9.9 10.094 10.094 10.094 10.094 tree_to_linear_d 110 9.4 10.085 10.085 10.085 10.085 calculate_norms 370 9.1 9.996 9.996 9.996 9.996 quick_finalize 395 10.0 0.386 0.386 8.759 8.759 ls_scf_init_scf 1 4.0 0.000 0.000 8.513 8.513 ls_scf_init_matrix_S 1 5.0 0.000 0.000 8.173 8.173 dbcsr_special_finalize 370 9.1 0.002 0.002 8.100 8.100 matrix_sqrt_Newton_Schulz 1 6.0 0.001 0.001 7.536 7.536 ------------------------------------------------------------------------------- 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 0.024 63.699 63.709 qs_energies 1 2.0 0.000 0.000 63.613 63.613 ls_scf 1 3.0 0.000 0.000 63.564 63.564 ls_scf_main 1 4.0 0.000 0.008 61.054 61.054 density_matrix_trs4 11 5.0 0.006 0.019 58.686 58.743 dbcsr_multiply_generic 185 6.1 0.057 0.074 55.505 55.804 multiply_cannon 185 7.1 0.032 0.036 46.355 46.996 multiply_cannon_loop 185 8.1 0.104 0.131 44.037 44.628 multiply_cannon_multrec 1480 9.1 26.840 30.294 27.090 30.570 mp_waitall_1 11936 10.3 14.932 18.817 14.932 18.817 multiply_cannon_metrocomm3 1480 9.1 0.012 0.016 9.023 14.869 multiply_cannon_metrocomm1 1480 9.1 0.007 0.010 3.353 9.276 make_m2s 370 7.1 0.034 0.038 6.392 6.470 make_images 370 8.1 0.621 0.648 6.269 6.347 calculate_norms 2960 9.1 4.414 5.783 4.414 5.783 mp_sum_l 1119 5.6 1.833 3.162 1.833 3.162 make_images_data 370 9.1 0.009 0.011 2.773 3.003 hybrid_alltoall_any 393 9.9 0.167 0.807 2.395 2.670 arnoldi_extremal 12 6.1 0.000 0.000 2.467 2.487 arnoldi_normal_ev 12 7.1 0.001 0.004 2.467 2.487 build_subspace 23 8.1 0.019 0.026 2.365 2.367 dbcsr_multiply_generic_mpsum_f 137 7.1 0.000 0.000 0.991 2.114 ls_scf_dm_to_ks 11 5.0 0.000 0.000 2.050 2.113 dbcsr_matrix_vector_mult 652 9.0 0.009 0.042 1.995 2.067 ls_scf_init_scf 1 4.0 0.000 0.000 1.936 1.936 ls_scf_init_matrix_S 1 5.0 0.000 0.000 1.910 1.918 dbcsr_complete_redistribute 23 7.5 1.156 1.210 1.841 1.893 matrix_ls_to_qs 11 6.0 0.000 0.000 1.797 1.854 make_images_pack 370 9.1 1.590 1.829 1.593 1.834 matrix_sqrt_Newton_Schulz 1 6.0 0.000 0.001 1.749 1.752 matrix_decluster 11 7.0 0.000 0.000 1.658 1.714 dbcsr_matrix_vector_mult_local 652 10.0 1.601 1.675 1.603 1.677 dbcsr_finalize 646 7.5 0.007 0.008 1.277 1.576 buffer_matrices_ensure_size 370 8.1 1.246 1.496 1.246 1.496 ------------------------------------------------------------------------------- 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=71.81600000000003, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=138.459, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_copy_into_existing", label="dbcsr_copy_into_existing", y=45.095, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_complete_redistribute", label="dbcsr_complete_redistribute", y=30.711, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=22.35, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="setup_rec_index_2d", label="setup_rec_index_2d", y=12.018, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="calculate_norms", label="calculate_norms", y=9.996, 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=12.922999999999995, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=1.601, 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=1.156, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=26.84, 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=4.414, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=14.932, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=1.833, 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 71.013 71.013 lib_test 1 2.0 0.000 0.000 71.005 71.005 dbcsr_run_tests 3 3.0 0.002 0.002 71.005 71.005 test_multiplies_multiproc 3 4.0 0.001 0.001 55.273 55.273 dbcsr_redistribute 9 5.0 36.493 36.493 38.073 38.073 dbcsr_multiply_generic 9 5.0 0.001 0.001 15.851 15.851 dbcsr_make_random_matrix 9 4.0 12.697 12.697 15.621 15.621 multiply_cannon 9 6.0 0.001 0.001 11.136 11.136 multiply_cannon_loop 9 7.0 0.038 0.038 10.779 10.779 multiply_cannon_multrec 9 8.0 10.740 10.740 10.741 10.741 dbcsr_finalize 27 5.7 0.018 0.018 5.490 5.490 dbcsr_merge_all 18 6.5 1.985 1.985 4.734 4.734 dbcsr_data_release 975 7.6 2.872 2.872 2.872 2.872 tree_to_linear_d 9 7.0 1.855 1.855 1.855 1.855 make_m2s 18 6.0 0.001 0.001 1.582 1.582 make_images 18 7.0 0.544 0.544 1.536 1.536 ------------------------------------------------------------------------------- From /workspace/artifacts/dbcsr_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.004 0.014 17.093 17.098 lib_test 1 2.0 0.000 0.000 17.058 17.079 dbcsr_run_tests 3 3.0 0.000 0.001 17.053 17.074 test_multiplies_multiproc 3 4.0 0.000 0.002 16.224 16.281 dbcsr_multiply_generic 9 5.0 0.001 0.001 14.813 14.916 multiply_cannon 9 6.0 0.001 0.002 13.144 13.390 multiply_cannon_loop 9 7.0 0.002 0.002 12.860 13.119 multiply_cannon_multrec 72 8.0 10.751 11.449 10.752 11.450 mp_waitall_1 576 9.2 2.387 3.325 2.387 3.325 multiply_cannon_metrocomm1 72 8.0 0.001 0.001 1.859 2.746 multiply_cannon_metrocomm3 72 8.0 0.000 0.000 0.243 1.054 mp_sum_l 390 2.5 0.413 0.895 0.413 0.895 dbcsr_multiply_generic_mpsum_f 9 6.0 0.000 0.000 0.409 0.891 dbcsr_data_release 444 7.6 0.734 0.856 0.734 0.856 dbcsr_make_random_matrix 9 4.0 0.659 0.673 0.800 0.832 dbcsr_finalize 27 5.7 0.000 0.000 0.673 0.761 dbcsr_destroy 111 5.9 0.000 0.000 0.590 0.718 make_m2s 18 6.0 0.001 0.001 0.616 0.663 make_images 18 7.0 0.021 0.021 0.613 0.660 dbcsr_merge_all 18 6.5 0.096 0.121 0.527 0.635 dbcsr_redistribute 9 5.0 0.228 0.276 0.501 0.538 dbcsr_data_copy_aa2 18 7.5 0.317 0.408 0.317 0.408 make_images_data 18 8.0 0.000 0.001 0.316 0.376 hybrid_alltoall_any 18 9.0 0.027 0.142 0.276 0.342 ------------------------------------------------------------------------------- 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=6.225999999999999, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_redistribute", label="dbcsr_redistribute", y=36.493, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=12.697, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=10.74, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_data_release", label="dbcsr_data_release", y=2.872, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_merge_all", label="dbcsr_merge_all", y=1.985, 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=1.8249999999999993, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_redistribute", label="dbcsr_redistribute", y=0.228, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=0.659, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=10.751, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_data_release", label="dbcsr_data_release", y=0.734, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_merge_all", label="dbcsr_merge_all", y=0.096, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=0.413, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=2.387, yerr=0.0 Running MQAE_single_node.inp with 1 threads and 32 ranks... done. Running MQAE_single_node.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/MQAE_single_node_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.048 0.048 127.962 127.962 qs_mol_dyn_low 1 2.0 0.003 0.003 126.589 126.589 velocity_verlet 5 3.0 0.003 0.003 102.819 102.819 qmmm_el_coupling 6 3.8 0.000 0.000 84.467 84.467 qmmm_elec_with_gaussian 6 4.8 0.012 0.012 84.463 84.463 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 83.841 83.841 qmmm_elec_gaussian_low_G 6 6.8 82.938 82.938 82.938 82.938 qs_forces 6 3.8 0.000 0.000 33.940 33.940 qs_energies 6 4.8 0.000 0.000 30.099 30.099 scf_env_do_scf 6 5.8 0.001 0.001 27.784 27.784 scf_env_do_scf_inner_loop 39 6.8 0.004 0.004 24.258 24.258 rebuild_ks_matrix 45 8.4 0.000 0.000 23.308 23.308 qs_ks_build_kohn_sham_matrix 45 9.4 0.005 0.005 23.308 23.308 qs_ks_update_qs_env 45 7.8 0.000 0.000 19.912 19.912 pw_transfer 966 12.3 0.051 0.051 16.858 16.858 fft_wrap_pw1pw2 801 13.6 0.006 0.006 16.660 16.660 fft_wrap_pw1pw2_150 507 15.2 2.231 2.231 16.259 16.259 qs_vxc_create 45 10.4 0.001 0.001 12.774 12.774 xc_vxc_pw_create 45 11.4 0.635 0.635 12.773 12.773 xc_pw_derive 270 13.4 0.002 0.002 9.102 9.102 fft3d_s 802 15.6 7.680 7.680 7.687 7.687 qs_rho_update_rho_low 45 7.9 0.000 0.000 7.025 7.025 calculate_rho_elec 45 8.9 0.563 0.563 7.025 7.025 xc_rho_set_and_dset_create 45 12.4 0.560 0.560 6.543 6.543 xc_pw_divergence 45 12.4 0.001 0.001 5.548 5.548 pw_scatter_s 429 15.8 5.497 5.497 5.497 5.497 qmmm_forces 6 3.8 0.002 0.002 5.153 5.153 qmmm_forces_with_gaussian 6 4.8 0.029 0.029 4.830 4.830 pw_integral_ab 2539 7.4 4.459 4.459 4.459 4.459 qs_ks_ddapc 45 10.4 0.001 0.001 4.174 4.174 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 4.105 4.105 init_scf_loop 6 6.8 0.000 0.000 3.519 3.519 qmmm_forces_gaussian_low_G 6 6.8 3.418 3.418 3.418 3.418 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 3.404 3.404 density_rs2pw 45 9.9 0.001 0.001 3.277 3.277 sum_up_and_integrate 45 10.4 0.330 0.330 3.274 3.274 grid_collocate_task_list 45 9.9 3.186 3.186 3.186 3.186 integrate_v_rspace 45 11.4 0.006 0.006 2.945 2.945 ------------------------------------------------------------------------------- From /workspace/artifacts/MQAE_single_node_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.034 0.051 51.231 51.242 qs_mol_dyn_low 1 2.0 0.003 0.004 50.268 50.325 qs_forces 6 3.8 0.000 0.001 36.379 36.380 qs_energies 6 4.8 0.000 0.001 34.686 34.686 scf_env_do_scf 6 5.8 0.000 0.001 33.815 33.815 scf_env_do_scf_inner_loop 113 6.2 0.002 0.016 32.447 32.447 rebuild_ks_matrix 119 8.1 0.000 0.000 23.829 23.835 qs_ks_build_kohn_sham_matrix 119 9.1 0.014 0.015 23.828 23.835 qs_ks_update_qs_env 119 7.3 0.001 0.001 22.419 22.426 velocity_verlet 5 3.0 0.002 0.003 21.450 21.453 pw_transfer 2446 12.3 0.188 0.225 15.695 16.177 fft_wrap_pw1pw2 2059 13.4 0.021 0.026 15.301 15.889 fft_wrap_pw1pw2_150 1321 14.9 1.106 1.355 14.750 15.239 fft3d_ps 2059 15.4 6.272 7.406 11.481 12.558 qs_vxc_create 119 10.1 0.002 0.003 12.442 12.445 xc_vxc_pw_create 119 11.1 0.137 0.218 12.440 12.443 qs_rho_update_rho_low 119 7.3 0.000 0.001 9.785 9.787 calculate_rho_elec 119 8.3 0.048 0.054 9.784 9.787 xc_pw_derive 714 13.1 0.009 0.011 9.347 9.648 sum_up_and_integrate 119 10.1 0.074 0.092 8.403 8.415 integrate_v_rspace 119 11.1 0.003 0.003 8.329 8.363 qmmm_forces 6 3.8 0.002 0.002 7.101 7.101 qmmm_forces_with_gaussian 6 4.8 0.010 0.013 6.747 6.977 xc_rho_set_and_dset_create 119 12.1 0.338 0.432 6.079 6.301 xc_pw_divergence 119 12.1 0.004 0.005 6.024 6.271 rs_pw_transfer 988 11.5 0.010 0.013 5.829 6.118 qmmm_el_coupling 6 3.8 0.000 0.000 5.902 6.069 qmmm_elec_with_gaussian 6 4.8 0.003 0.003 5.900 6.068 mp_alltoall_z22v 2059 17.4 3.963 6.021 3.963 6.021 density_rs2pw 119 9.3 0.005 0.007 5.380 5.577 potential_pw2rs 119 12.1 0.005 0.006 4.756 4.785 grid_collocate_task_list 119 9.3 4.230 4.527 4.230 4.527 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 3.828 3.913 yz_to_x 964 16.0 0.466 0.704 2.409 3.622 grid_integrate_task_list 119 12.1 3.338 3.528 3.338 3.528 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 3.297 3.378 x_to_yz 1095 16.8 0.726 0.850 2.746 3.352 qmmm_forces_gaussian_low_G 6 6.8 3.151 3.234 3.151 3.234 mp_waitany 4028 12.8 2.202 2.913 2.202 2.913 qmmm_elec_gaussian_low_G 6 6.8 2.708 2.776 2.708 2.776 pw_restrict_s3 18 5.8 1.295 1.370 2.308 2.521 rs_pw_transfer_PW2RS_150 125 13.9 0.652 0.818 2.176 2.248 qmmm_elec_with_gaussian:spline 6 5.8 0.000 0.000 1.947 2.120 pw_prolongate_s3 18 6.8 1.084 1.132 1.947 2.120 mp_waitall_1 188862 16.2 1.690 1.968 1.690 1.968 rs_pw_transfer_RS2PW_150 125 11.2 0.521 0.675 1.688 1.966 qs_scf_new_mos 113 7.2 0.000 0.000 1.921 1.927 qs_scf_loop_do_ot 113 8.2 0.000 0.000 1.921 1.927 ot_scf_mini 113 9.2 0.001 0.001 1.836 1.841 qs_ks_ddapc 119 10.1 0.002 0.002 1.726 1.838 dbcsr_multiply_generic 2588 12.3 0.056 0.058 1.735 1.766 pw_scatter_p 1095 15.8 1.501 1.530 1.501 1.530 pw_integral_ab 2761 7.7 1.043 1.219 1.343 1.496 pw_gather_p 964 15.0 1.165 1.464 1.165 1.464 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 1.421 1.421 mp_sum_d 5820 12.2 0.792 1.412 0.792 1.412 init_scf_loop 6 6.8 0.000 0.000 1.366 1.366 mp_sum_dm3 33 5.7 1.163 1.227 1.163 1.227 ot_mini 113 10.2 0.000 0.001 1.137 1.144 rs_pw_transfer_PW2RS_40 119 14.1 0.211 0.275 0.911 1.105 ------------------------------------------------------------------------------- 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=20.784000000000006, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=82.938, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_s", label="fft3d_s", y=7.68, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_scatter_s", label="pw_scatter_s", y=5.497, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_integral_ab", label="pw_integral_ab", y=4.459, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.418, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=3.186, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=0.0, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_ps", label="fft3d_ps", y=0.0, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=0.0, yerr=0.0 Plot: name="MQAE_single_node_timings_32mpi", title="Timings of MQAE_single_node with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="MQAE_single_node_timings_32mpi", name="rest", label="rest", y=26.525999999999996, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=2.708, 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=1.043, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.151, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=4.23, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=3.963, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=6.272, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=3.338, yerr=0.0 Summary: Performance test took 35 minutes. (cached) Status: OK Uploading artifacts... done EndDate: 2022-10-19 11:07:42+00:00