StartDate: 2022-12-05 19:05:48+00:00 CpuId: 32x AMD EPYC (3rd Gen) (Milan) [Zen 3], 7nm (SMT disabled) CommitSHA: 06cede5577ec193881931c2266652107c13fde17 CommitTime: 2022-12-05 17:33:25 +0100 CommitAuthor: hforbert CommitSubject: add missing xyz output format for helium and fixes of corner cases (#2432) Populating docker build cache... done. #################### Building Image cp2k-perf-openmp #################### Dockerfile: /tools/docker/Dockerfile.test_performance Build-Path: / Build-Args: GIT_COMMIT_SHA=06cede5577ec193881931c2266652107c13fde17 Sending build context to Docker daemon 366.6MB Step 1/42 : FROM ubuntu:22.04 22.04: Pulling from library/ubuntu e96e057aae67: Already exists Digest: sha256:4b1d0c4a2d2aaf63b37111f34eb9fa89fa1bf53dd6e4ca954d47caebca4005c2 Status: Downloaded newer image for ubuntu:22.04 ---> a8780b506fa4 Step 2/42 : WORKDIR /opt/cp2k-toolchain ---> Using cache ---> 456d88508063 Step 3/42 : COPY ./tools/toolchain/install_requirements*.sh ./ ---> Using cache ---> 196acfd778fb Step 4/42 : RUN ./install_requirements.sh ubuntu:22.04 ---> Using cache ---> 1c5721a94525 Step 5/42 : RUN mkdir scripts ---> Using cache ---> aa1c7bdf0e90 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 ---> 8641bd388b4f Step 7/42 : COPY ./tools/toolchain/install_cp2k_toolchain.sh . ---> Using cache ---> ae0fdf87c16d Step 8/42 : RUN ./install_cp2k_toolchain.sh --install-all --with-gcc=system --dry-run ---> Using cache ---> 6a351dfd8131 Step 9/42 : COPY ./tools/toolchain/scripts/stage0/ ./scripts/stage0/ ---> Using cache ---> 4d5dfef407b9 Step 10/42 : RUN ./scripts/stage0/install_stage0.sh && rm -rf ./build ---> Using cache ---> 0e445bb4268b Step 11/42 : COPY ./tools/toolchain/scripts/stage1/ ./scripts/stage1/ ---> Using cache ---> 1b8408d74bc3 Step 12/42 : RUN ./scripts/stage1/install_stage1.sh && rm -rf ./build ---> Using cache ---> 5017927aa877 Step 13/42 : COPY ./tools/toolchain/scripts/stage2/ ./scripts/stage2/ ---> Using cache ---> 395859d3f819 Step 14/42 : RUN ./scripts/stage2/install_stage2.sh && rm -rf ./build ---> Using cache ---> 9f2c788d8880 Step 15/42 : COPY ./tools/toolchain/scripts/stage3/ ./scripts/stage3/ ---> Using cache ---> 795b7ed39ee8 Step 16/42 : RUN ./scripts/stage3/install_stage3.sh && rm -rf ./build ---> Using cache ---> 5e9d69406f5e Step 17/42 : COPY ./tools/toolchain/scripts/stage4/ ./scripts/stage4/ ---> Using cache ---> 6dc7b086699e Step 18/42 : RUN ./scripts/stage4/install_stage4.sh && rm -rf ./build ---> Using cache ---> 11deb2698a87 Step 19/42 : COPY ./tools/toolchain/scripts/stage5/ ./scripts/stage5/ ---> Using cache ---> 95d6e3492171 Step 20/42 : RUN ./scripts/stage5/install_stage5.sh && rm -rf ./build ---> Using cache ---> db9b58fd1ae8 Step 21/42 : COPY ./tools/toolchain/scripts/stage6/ ./scripts/stage6/ ---> Using cache ---> f5a43d6a365d Step 22/42 : RUN ./scripts/stage6/install_stage6.sh && rm -rf ./build ---> Using cache ---> 50c376e2e5fa Step 23/42 : COPY ./tools/toolchain/scripts/stage7/ ./scripts/stage7/ ---> Using cache ---> a90470af2665 Step 24/42 : RUN ./scripts/stage7/install_stage7.sh && rm -rf ./build ---> Using cache ---> a0ec8a1f04bd Step 25/42 : COPY ./tools/toolchain/scripts/stage8/ ./scripts/stage8/ ---> Using cache ---> d0460bf5e769 Step 26/42 : RUN ./scripts/stage8/install_stage8.sh && rm -rf ./build ---> Using cache ---> 695570ad73ce Step 27/42 : COPY ./tools/toolchain/scripts/arch_base.tmpl ./tools/toolchain/scripts/generate_arch_files.sh ./scripts/ ---> Using cache ---> 0dbe548ceff1 Step 28/42 : RUN ./scripts/generate_arch_files.sh && rm -rf ./build ---> Using cache ---> f15c4981eaed Step 29/42 : WORKDIR /opt/cp2k ---> Using cache ---> 0d57826fcf2e Step 30/42 : COPY ./Makefile . ---> Using cache ---> 8bb1cb6bde6a Step 31/42 : COPY ./src ./src ---> Using cache ---> 90c61d4337e9 Step 32/42 : COPY ./exts ./exts ---> Using cache ---> bae7ad684f9b Step 33/42 : COPY ./tools/build_utils ./tools/build_utils ---> Using cache ---> a606df382218 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 )" ---> Running in 8af5f93a6d9a './arch/local.psmp' -> '/opt/cp2k-toolchain/install/arch/local.psmp' Compiling cp2k... Removing intermediate container 8af5f93a6d9a ---> 103415f9f0e1 Step 35/42 : COPY ./data ./data ---> e3174fca492d Step 36/42 : COPY ./tests ./tests ---> 5a0293e984e9 Step 37/42 : COPY ./tools/regtesting ./tools/regtesting ---> cc2d3bcb5d1a Step 38/42 : COPY ./benchmarks ./benchmarks ---> b8b84d12b8bc Step 39/42 : COPY ./tools/docker/scripts/test_performance.sh ./tools/docker/scripts/plot_performance.py ./ ---> 89e4245d95fa Step 40/42 : RUN ./test_performance.sh "local" 2>&1 | tee report.log ---> Running in ba7b879ef841 ========== 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 0.027 0.027 86.019 86.019 qs_mol_dyn_low 1 2.0 0.003 0.003 85.403 85.403 qs_forces 11 3.9 0.001 0.001 85.364 85.364 qs_energies 11 4.9 0.001 0.001 79.409 79.409 scf_env_do_scf 11 5.9 0.001 0.001 68.795 68.795 velocity_verlet 10 3.0 0.002 0.002 55.825 55.825 scf_env_do_scf_inner_loop 108 6.5 0.010 0.010 52.554 52.554 rebuild_ks_matrix 119 8.3 0.001 0.001 19.759 19.759 qs_ks_build_kohn_sham_matrix 119 9.3 0.011 0.011 19.758 19.758 dbcsr_multiply_generic 2286 12.5 0.166 0.166 19.331 19.331 qs_scf_new_mos 108 7.5 0.001 0.001 19.257 19.257 qs_scf_loop_do_ot 108 8.5 0.001 0.001 19.257 19.257 qs_rho_update_rho_low 119 7.7 0.000 0.000 18.844 18.844 calculate_rho_elec 119 8.7 0.944 0.944 18.843 18.843 qs_ks_update_qs_env 119 7.6 0.001 0.001 18.125 18.125 ot_scf_mini 108 9.5 0.002 0.002 17.903 17.903 init_scf_loop 11 6.9 0.000 0.000 16.110 16.110 grid_collocate_task_list 119 9.7 14.449 14.449 14.449 14.449 prepare_preconditioner 11 7.9 0.000 0.000 13.690 13.690 make_preconditioner 11 8.9 0.000 0.000 13.690 13.690 sum_up_and_integrate 119 10.3 0.511 0.511 12.797 12.797 make_full_inverse_cholesky 11 9.9 0.000 0.000 12.566 12.566 integrate_v_rspace 119 11.3 0.087 0.087 12.286 12.286 ot_mini 108 10.5 0.001 0.001 11.690 11.690 make_m2s 4572 13.5 0.044 0.044 10.971 10.971 grid_integrate_task_list 119 12.3 10.381 10.381 10.381 10.381 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 6.175 6.175 qs_ot_get_derivative 108 11.5 0.001 0.001 6.091 6.091 pw_transfer 1439 11.6 0.060 0.060 6.010 6.010 dbcsr_make_dense_low 5837 15.5 0.069 0.069 5.993 5.993 make_dense_data 5837 16.5 5.284 5.284 5.910 5.910 fft_wrap_pw1pw2 1201 12.6 0.006 0.006 5.821 5.821 ot_diis_step 108 11.5 0.004 0.004 5.597 5.597 make_images 4572 14.5 2.175 2.175 5.413 5.413 dbcsr_make_images_dense 3978 14.8 0.018 0.018 5.252 5.252 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 5.126 5.126 apply_single 119 13.6 0.000 0.000 5.126 5.126 fft_wrap_pw1pw2_140 487 13.2 0.443 0.443 5.008 5.008 multiply_cannon 2286 13.5 0.171 0.171 4.499 4.499 cp_fm_cholesky_decompose 22 10.9 4.412 4.412 4.412 4.412 multiply_cannon_loop 2286 14.5 0.050 0.050 4.053 4.053 multiply_cannon_multrec 2286 15.5 3.955 3.955 4.002 4.002 cp_fm_cholesky_invert 11 10.9 3.994 3.994 3.994 3.994 init_scf_run 11 5.9 0.002 0.002 3.846 3.846 scf_env_initial_rho_setup 11 6.9 0.000 0.000 3.844 3.844 dbcsr_complete_redistribute 329 12.2 1.921 1.921 3.658 3.658 dbcsr_copy 2102 12.0 0.215 0.215 3.578 3.578 density_rs2pw 119 9.7 0.004 0.004 3.450 3.450 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 3.379 3.379 wfi_extrapolate 11 7.9 0.001 0.001 3.334 3.334 dbcsr_copy_into_existing 22 7.9 3.332 3.332 3.332 3.332 qs_env_update_s_mstruct 11 6.9 0.000 0.000 3.255 3.255 fft3d_s 1202 14.6 2.937 2.937 2.942 2.942 copy_dbcsr_to_fm 153 11.3 0.002 0.002 2.918 2.918 qs_ot_get_p 119 10.4 0.001 0.001 2.900 2.900 qs_create_task_list 11 7.9 0.000 0.000 2.899 2.899 generate_qs_task_list 11 8.9 1.974 1.974 2.899 2.899 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 2.574 2.574 build_core_hamiltonian_matrix 11 6.9 0.000 0.000 2.516 2.516 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.296 2.296 dbcsr_data_release 279534 16.0 2.169 2.169 2.169 2.169 pw_poisson_solve 119 10.3 0.329 0.329 1.970 1.970 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 1.921 1.921 copy_fm_to_dbcsr 176 11.2 0.001 0.001 1.882 1.882 qs_ot_get_derivative_taylor 59 13.0 0.001 0.001 1.850 1.850 potential_pw2rs 119 12.3 0.045 0.045 1.819 1.819 cp_fm_upper_to_full 72 14.2 1.783 1.783 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 0.007 0.022 41.629 41.638 qs_mol_dyn_low 1 2.0 0.003 0.004 41.524 41.528 qs_forces 11 3.9 0.001 0.001 41.483 41.483 qs_energies 11 4.9 0.001 0.001 38.693 38.694 scf_env_do_scf 11 5.9 0.000 0.002 35.487 35.488 scf_env_do_scf_inner_loop 108 6.5 0.003 0.020 32.754 32.755 velocity_verlet 10 3.0 0.001 0.003 24.798 24.799 rebuild_ks_matrix 119 8.3 0.000 0.001 15.087 15.194 qs_ks_build_kohn_sham_matrix 119 9.3 0.013 0.015 15.086 15.193 qs_ks_update_qs_env 119 7.6 0.001 0.001 13.411 13.504 qs_rho_update_rho_low 119 7.7 0.001 0.001 12.325 12.336 calculate_rho_elec 119 8.7 0.029 0.039 12.324 12.336 dbcsr_multiply_generic 2286 12.5 0.069 0.072 11.895 12.072 sum_up_and_integrate 119 10.3 0.027 0.032 11.349 11.367 integrate_v_rspace 119 11.3 0.004 0.005 11.322 11.343 qs_scf_new_mos 108 7.5 0.001 0.001 9.503 9.692 qs_scf_loop_do_ot 108 8.5 0.001 0.001 9.503 9.691 grid_collocate_task_list 119 9.7 8.798 9.123 8.798 9.123 ot_scf_mini 108 9.5 0.002 0.002 8.905 9.089 multiply_cannon 2286 13.5 0.138 0.153 8.637 8.983 multiply_cannon_loop 2286 14.5 0.085 0.096 8.125 8.548 grid_integrate_task_list 119 12.3 7.928 8.102 7.928 8.102 mp_waitall_1 169478 16.3 7.213 7.958 7.213 7.958 multiply_cannon_metrocomm3 18288 15.5 0.033 0.036 4.623 5.443 ot_mini 108 10.5 0.001 0.001 5.142 5.347 rs_pw_transfer 974 11.9 0.009 0.012 3.817 4.183 density_rs2pw 119 9.7 0.005 0.006 3.167 3.530 pw_transfer 1439 11.6 0.087 0.100 3.044 3.121 multiply_cannon_multrec 18288 15.5 2.715 3.033 2.723 3.043 fft_wrap_pw1pw2 1201 12.6 0.008 0.009 2.892 2.953 potential_pw2rs 119 12.3 0.006 0.007 2.893 2.919 qs_ot_get_derivative 108 11.5 0.001 0.001 2.680 2.872 init_scf_loop 11 6.9 0.000 0.000 2.720 2.720 fft_wrap_pw1pw2_140 487 13.2 0.232 0.277 2.460 2.575 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 2.339 2.438 apply_single 119 13.6 0.000 0.000 2.339 2.437 ot_diis_step 108 11.5 0.003 0.003 2.435 2.435 init_scf_run 11 5.9 0.000 0.004 2.239 2.239 scf_env_initial_rho_setup 11 6.9 0.000 0.004 2.238 2.239 make_m2s 4572 13.5 0.044 0.047 2.140 2.231 fft3d_ps 1201 14.6 1.096 1.226 2.071 2.156 wfi_extrapolate 11 7.9 0.001 0.001 2.026 2.026 make_images 4572 14.5 0.113 0.116 1.830 1.930 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 1.805 1.818 mp_waitany 9880 13.7 1.241 1.661 1.241 1.661 qs_ot_get_p 119 10.4 0.001 0.001 1.219 1.476 mp_sum_l 11218 13.2 0.703 1.347 0.703 1.347 multiply_cannon_metrocomm1 18288 15.5 0.016 0.019 0.513 1.290 rs_pw_transfer_RS2PW_140 130 11.5 0.168 0.192 0.896 1.260 rs_pw_transfer_PW2RS_140 130 13.9 0.313 0.395 1.108 1.169 make_images_data 4572 15.5 0.034 0.041 1.020 1.153 prepare_preconditioner 11 7.9 0.000 0.000 1.076 1.112 make_preconditioner 11 8.9 0.000 0.000 1.076 1.112 mp_alltoall_d11v 2130 13.8 0.694 1.021 0.694 1.021 mp_sum_d 4125 12.0 0.617 1.003 0.617 1.003 make_full_inverse_cholesky 11 9.9 0.000 0.000 0.976 1.003 hybrid_alltoall_any 4725 16.4 0.053 0.143 0.873 0.983 mp_alltoall_z22v 1201 16.6 0.752 0.966 0.752 0.966 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 0.868 0.957 qs_ot_get_derivative_taylor 59 13.0 0.001 0.001 0.860 0.954 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 0.852 0.930 rs_pw_transfer_PW2RS_50 119 14.3 0.235 0.288 0.721 0.877 ------------------------------------------------------------------------------- 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=43.54400000000001, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=14.449, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=10.381, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="make_dense_data", label="make_dense_data", y=5.284, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=4.412, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=3.994, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=3.955, 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=13.733999999999998, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=8.798, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=7.928, 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=2.715, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=7.213, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitany", label="mp_waitany", y=1.241, 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 0.027 0.027 109.526 109.526 qs_mol_dyn_low 1 2.0 0.003 0.003 108.874 108.874 qs_forces 11 3.9 0.001 0.001 108.835 108.835 qs_energies 11 4.9 0.001 0.001 101.310 101.310 scf_env_do_scf 11 5.9 0.001 0.001 88.803 88.803 scf_env_do_scf_inner_loop 96 6.5 0.009 0.009 70.942 70.942 velocity_verlet 10 3.0 0.002 0.002 70.238 70.238 rebuild_ks_matrix 107 8.3 0.001 0.001 33.027 33.027 qs_ks_build_kohn_sham_matrix 107 9.3 0.011 0.011 33.026 33.026 qs_rho_update_rho_low 107 7.7 0.000 0.000 30.938 30.938 calculate_rho_elec 107 8.7 0.849 0.849 30.938 30.938 qs_ks_update_qs_env 107 7.6 0.001 0.001 29.711 29.711 grid_collocate_task_list 107 9.7 26.849 26.849 26.849 26.849 sum_up_and_integrate 107 10.3 0.453 0.453 26.463 26.463 integrate_v_rspace 107 11.3 0.078 0.078 26.009 26.009 grid_integrate_task_list 107 12.3 24.280 24.280 24.280 24.280 init_scf_loop 11 6.9 0.000 0.000 17.724 17.724 dbcsr_multiply_generic 1966 12.4 0.141 0.141 17.480 17.480 qs_scf_new_mos 96 7.5 0.001 0.001 16.964 16.964 qs_scf_loop_do_ot 96 8.5 0.001 0.001 16.963 16.963 ot_scf_mini 96 9.5 0.002 0.002 15.781 15.781 prepare_preconditioner 11 7.9 0.000 0.000 13.730 13.730 make_preconditioner 11 8.9 0.000 0.000 13.730 13.730 make_full_inverse_cholesky 11 9.9 0.000 0.000 12.596 12.596 ot_mini 96 10.5 0.001 0.001 10.163 10.163 make_m2s 3932 13.4 0.039 0.039 9.724 9.724 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 6.557 6.557 pw_transfer 1295 11.6 0.055 0.055 5.598 5.598 fft_wrap_pw1pw2 1081 12.6 0.006 0.006 5.410 5.410 init_scf_run 11 5.9 0.002 0.002 5.339 5.339 scf_env_initial_rho_setup 11 6.9 0.000 0.000 5.337 5.337 qs_ot_get_derivative 96 11.5 0.001 0.001 5.294 5.294 dbcsr_make_dense_low 4961 15.5 0.056 0.056 5.204 5.204 make_dense_data 4961 16.5 4.599 4.599 5.137 5.137 make_images 3932 14.4 1.912 1.912 4.872 4.872 ot_diis_step 96 11.5 0.003 0.003 4.867 4.867 fft_wrap_pw1pw2_140 439 13.2 0.467 0.467 4.635 4.635 wfi_extrapolate 11 7.9 0.001 0.001 4.630 4.630 dbcsr_make_images_dense 3386 14.7 0.015 0.015 4.574 4.574 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 4.522 4.522 apply_single 107 13.6 0.000 0.000 4.522 4.522 cp_fm_cholesky_decompose 22 10.9 4.350 4.350 4.350 4.350 multiply_cannon 1966 13.4 0.150 0.150 4.190 4.190 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 4.160 4.160 cp_fm_cholesky_invert 11 10.9 3.994 3.994 3.994 3.994 multiply_cannon_loop 1966 14.4 0.059 0.059 3.799 3.799 multiply_cannon_multrec 1966 15.4 3.698 3.698 3.739 3.739 dbcsr_complete_redistribute 317 12.2 1.882 1.882 3.678 3.678 qs_env_update_s_mstruct 11 6.9 0.000 0.000 3.671 3.671 dbcsr_copy 1855 11.9 0.198 0.198 3.452 3.452 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 3.364 3.364 qs_create_task_list 11 7.9 0.000 0.000 3.302 3.302 generate_qs_task_list 11 8.9 2.401 2.401 3.302 3.302 density_rs2pw 107 9.7 0.004 0.004 3.239 3.239 dbcsr_copy_into_existing 22 7.9 3.226 3.226 3.226 3.226 copy_dbcsr_to_fm 147 11.2 0.002 0.002 3.036 3.036 fft3d_s 1082 14.6 2.697 2.697 2.701 2.701 qs_ot_get_p 107 10.4 0.001 0.001 2.558 2.558 build_core_hamiltonian_matrix 11 6.9 0.000 0.000 2.477 2.477 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.379 2.379 ------------------------------------------------------------------------------- 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 0.022 67.684 67.693 qs_mol_dyn_low 1 2.0 0.003 0.004 67.585 67.588 qs_forces 11 3.9 0.001 0.001 67.545 67.546 qs_energies 11 4.9 0.001 0.001 62.962 62.964 scf_env_do_scf 11 5.9 0.000 0.002 58.283 58.284 scf_env_do_scf_inner_loop 96 6.5 0.002 0.016 53.935 53.935 velocity_verlet 10 3.0 0.002 0.003 40.122 40.124 rebuild_ks_matrix 107 8.3 0.000 0.001 29.480 29.572 qs_ks_build_kohn_sham_matrix 107 9.3 0.013 0.015 29.480 29.572 sum_up_and_integrate 107 10.3 0.029 0.034 26.072 26.095 integrate_v_rspace 107 11.3 0.004 0.005 26.043 26.074 qs_ks_update_qs_env 107 7.6 0.001 0.001 25.972 26.058 qs_rho_update_rho_low 107 7.7 0.000 0.001 25.023 25.029 calculate_rho_elec 107 8.7 0.026 0.028 25.023 25.028 grid_integrate_task_list 107 12.3 22.587 22.989 22.587 22.989 grid_collocate_task_list 107 9.7 21.683 22.090 21.683 22.090 dbcsr_multiply_generic 1966 12.4 0.062 0.067 10.758 10.939 qs_scf_new_mos 96 7.5 0.000 0.001 8.476 8.540 qs_scf_loop_do_ot 96 8.5 0.001 0.001 8.475 8.540 multiply_cannon 1966 13.4 0.124 0.143 7.857 8.214 ot_scf_mini 96 9.5 0.002 0.002 7.954 8.028 multiply_cannon_loop 1966 14.4 0.081 0.090 7.421 7.809 mp_waitall_1 146670 16.2 6.465 6.947 6.465 6.947 multiply_cannon_metrocomm3 15728 15.4 0.031 0.034 4.203 4.793 ot_mini 96 10.5 0.001 0.001 4.660 4.743 init_scf_loop 11 6.9 0.000 0.000 4.335 4.336 rs_pw_transfer 878 11.9 0.009 0.011 3.648 4.213 init_scf_run 11 5.9 0.000 0.004 3.695 3.695 scf_env_initial_rho_setup 11 6.9 0.000 0.003 3.695 3.695 density_rs2pw 107 9.7 0.004 0.005 3.036 3.645 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 3.624 3.632 wfi_extrapolate 11 7.9 0.001 0.001 3.362 3.362 pw_transfer 1295 11.6 0.083 0.106 2.831 2.881 fft_wrap_pw1pw2 1081 12.6 0.008 0.012 2.690 2.727 multiply_cannon_multrec 15728 15.4 2.533 2.694 2.542 2.702 potential_pw2rs 107 12.3 0.006 0.007 2.663 2.691 qs_ot_get_derivative 96 11.5 0.001 0.001 2.435 2.509 fft_wrap_pw1pw2_140 439 13.2 0.223 0.265 2.295 2.383 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 2.130 2.248 apply_single 107 13.6 0.000 0.000 2.129 2.248 ot_diis_step 96 11.5 0.003 0.003 2.207 2.207 fft3d_ps 1081 14.6 1.022 1.117 1.914 1.986 make_m2s 3932 13.4 0.039 0.041 1.924 1.967 mp_waitany 8968 13.7 1.267 1.768 1.267 1.768 make_images 3932 14.4 0.101 0.103 1.648 1.698 mp_alltoall_d11v 1998 13.7 0.970 1.594 0.970 1.594 rs_pw_transfer_RS2PW_140 118 11.5 0.150 0.175 0.951 1.522 ------------------------------------------------------------------------------- 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=41.755999999999986, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=26.849, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=24.28, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="make_dense_data", label="make_dense_data", y=4.599, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=4.35, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=3.994, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=3.698, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="mp_waitany", label="mp_waitany", 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=13.148999999999994, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=21.683, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=22.587, 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=2.533, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=6.465, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitany", label="mp_waitany", y=1.267, 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 0.187 0.187 104.745 104.745 qs_energies 1 2.0 0.000 0.000 103.911 103.911 scf_env_do_scf 1 3.0 0.000 0.000 102.793 102.793 qs_ks_update_qs_env 8 5.0 0.000 0.000 97.768 97.768 rebuild_ks_matrix 7 6.0 0.000 0.000 97.713 97.713 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.001 97.713 97.713 hfx_ks_matrix 7 8.0 0.000 0.000 88.436 88.436 integrate_four_center 7 9.0 1.682 1.682 88.399 88.399 integrate_four_center_main 7 10.0 0.750 0.750 80.797 80.797 integrate_four_center_bin 449 11.0 80.047 80.047 80.047 80.047 scf_env_do_scf_inner_loop 7 4.0 0.001 0.001 56.620 56.620 init_scf_loop 1 4.0 0.000 0.000 46.155 46.155 integrate_four_center_load 7 10.0 0.001 0.001 5.672 5.672 hfx_load_balance 1 11.0 0.001 0.001 5.671 5.671 qs_vxc_create 14 8.0 0.000 0.000 3.292 3.292 xc_vxc_pw_create 14 9.0 0.172 0.172 3.291 3.291 hfx_load_balance_count 1 12.0 2.828 2.828 2.828 2.828 hfx_load_balance_bin 1 12.0 2.826 2.826 2.826 2.826 xc_rho_set_and_dset_create 14 10.0 0.091 0.091 2.412 2.412 calculate_rho_elec 15 7.4 0.117 0.117 2.411 2.411 admm_mo_calc_rho_aux 7 8.0 0.000 0.000 2.402 2.402 prepare_preconditioner 1 5.0 0.000 0.000 2.318 2.318 make_preconditioner 1 6.0 0.000 0.000 2.318 2.318 ------------------------------------------------------------------------------- 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 0.219 0.239 94.824 94.835 qs_energies 1 2.0 0.000 0.000 94.358 94.359 scf_env_do_scf 1 3.0 0.000 0.000 94.036 94.037 qs_ks_update_qs_env 8 5.0 0.000 0.000 92.227 92.228 rebuild_ks_matrix 7 6.0 0.000 0.000 92.219 92.220 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.001 92.219 92.220 hfx_ks_matrix 7 8.0 0.000 0.000 87.143 87.144 integrate_four_center 7 9.0 0.052 0.337 87.135 87.136 integrate_four_center_main 7 10.0 0.003 0.003 78.388 80.451 integrate_four_center_bin 448 11.0 78.385 80.448 78.385 80.448 scf_env_do_scf_inner_loop 7 4.0 0.000 0.001 52.308 52.308 init_scf_loop 1 4.0 0.000 0.000 41.728 41.728 integrate_four_center_load 7 10.0 0.000 0.000 5.800 5.800 hfx_load_balance 1 11.0 0.001 0.001 5.800 5.800 mp_sync 70 11.3 2.315 3.374 2.315 3.374 hfx_load_balance_count 1 12.0 2.768 2.899 2.768 2.899 hfx_load_balance_bin 1 12.0 2.768 2.897 2.768 2.897 qs_vxc_create 14 8.0 0.000 0.004 2.317 2.317 xc_vxc_pw_create 14 9.0 0.006 0.007 2.316 2.317 xc_rho_set_and_dset_create 14 10.0 0.008 0.010 1.882 1.996 ------------------------------------------------------------------------------- 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=16.42500000000001, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_bin", label="integrate_four_center_bin", y=80.047, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_count", label="hfx_load_balance_count", y=2.828, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=2.826, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center", label="integrate_four_center", y=1.682, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_main", label="integrate_four_center_main", y=0.75, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="CP2K", label="CP2K", y=0.187, 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=8.313999999999993, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center_bin", label="integrate_four_center_bin", y=78.385, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_count", label="hfx_load_balance_count", y=2.768, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=2.768, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center", label="integrate_four_center", y=0.052, 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=0.219, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="mp_sync", label="mp_sync", y=2.315, 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 76.270 76.270 qs_energies 1 2.0 0.000 0.000 75.893 75.893 mp2_main 1 3.0 0.000 0.000 73.044 73.044 mp2_gpw_main 1 4.0 0.000 0.000 72.926 72.926 rpa_ri_compute_en 1 5.0 0.000 0.000 69.325 69.325 rpa_num_int 1 6.0 0.001 0.001 69.320 69.320 compute_mat_P_omega 1 7.0 0.003 0.003 59.559 59.559 compute_mat_P_omega_contract 10 8.0 8.969 8.969 59.345 59.345 dbt_total 2336 9.6 0.011 0.011 45.462 45.462 dbt_contract 787 11.0 0.041 0.041 38.785 38.785 dbt_tas_total 1149 12.2 0.265 0.265 37.897 37.897 dbt_tas_multiply 807 12.1 0.003 0.003 36.582 36.582 dbt_tas_dbm 807 14.1 0.003 0.003 30.013 30.013 dbm_multiply 807 16.1 30.006 30.006 30.006 30.006 dbt_tas_mm_1N 524 15.1 0.001 0.001 22.815 22.815 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 21.607 21.607 compute_mat_P_omega_calc_M_occ 250 9.0 8.988 8.988 16.600 16.600 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 6.778 6.778 dbt_tas_mm_2 251 15.0 0.001 0.001 5.741 5.741 dbt_copy 1103 10.7 0.067 0.067 5.346 5.346 compute_QP_energies 1 7.0 0.000 0.000 4.961 4.961 compute_self_energy_cubic_gw 1 8.0 0.055 0.055 4.960 4.960 contract_cubic_gw 21 9.0 0.000 0.000 4.003 4.003 mp2_ri_gpw_compute_in 1 5.0 0.001 0.001 3.593 3.593 dbt_tas_reserve_blocks_index 3261 14.3 0.138 0.138 3.246 3.246 dbm_reserve_blocks 3628 15.3 3.175 3.175 3.175 3.175 scf_env_do_scf 1 3.0 0.000 0.000 2.644 2.644 scf_env_do_scf_inner_loop 17 4.0 0.002 0.002 2.644 2.644 dbt_reserve_blocks_index 2280 13.1 0.047 0.047 2.463 2.463 convert_to_new_pgrid 2421 14.1 0.065 0.065 2.442 2.442 dbt_reserve_blocks_index_array 2222 12.2 0.009 0.009 2.421 2.421 dbm_copy 1614 15.1 2.377 2.377 2.377 2.377 dbt_tas_copy 574 11.4 1.249 1.249 2.119 2.119 dbt_crop 1042 12.0 1.356 1.356 2.096 2.096 dbt_tas_reshape 367 15.0 0.006 0.006 2.002 2.002 compute_W_cubic_GW 10 7.0 0.011 0.011 1.989 1.989 rpa_num_int_RPA_matrix_operati 10 7.0 0.000 0.000 1.982 1.982 dbt_reshape 278 11.9 0.929 0.929 1.763 1.763 get_2c_integrals 1 6.0 0.000 0.000 1.706 1.706 ------------------------------------------------------------------------------- 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 0.021 29.540 29.551 qs_energies 1 2.0 0.000 0.000 29.372 29.375 mp2_main 1 3.0 0.000 0.000 28.463 28.466 mp2_gpw_main 1 4.0 0.000 0.000 28.429 28.431 rpa_ri_compute_en 1 5.0 0.000 0.000 27.215 27.218 rpa_num_int 1 6.0 0.000 0.002 27.214 27.217 dbt_total 2336 9.6 0.011 0.012 24.168 24.170 compute_mat_P_omega 1 7.0 0.001 0.005 23.216 23.238 compute_mat_P_omega_contract 10 8.0 0.379 0.400 23.107 23.112 dbt_contract 787 11.0 0.024 0.025 18.228 18.231 dbt_tas_total 1149 12.2 0.047 0.055 16.369 16.369 dbt_tas_multiply 807 12.1 0.002 0.002 16.317 16.320 dbt_tas_dbm 807 14.1 0.002 0.003 12.285 12.291 dbm_multiply 807 16.1 9.482 10.446 9.482 10.446 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 6.930 6.930 compute_mat_P_omega_calc_M_occ 250 9.0 0.370 0.390 6.774 6.774 dbt_tas_mm_2 251 15.0 0.001 0.001 5.800 5.802 mp_sync 8706 11.6 4.437 5.528 4.437 5.528 dbt_copy 1111 10.7 0.011 0.012 5.183 5.443 dbt_reshape 1098 11.7 1.971 2.154 4.943 5.200 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 4.957 4.958 dbt_tas_mm_1N 524 15.1 0.001 0.002 4.357 4.747 mp_waitall_2 3776 15.3 2.346 2.583 2.346 2.583 dbt_communicate_buffer 1098 12.7 0.051 0.056 2.388 2.524 compute_QP_energies 1 7.0 0.000 0.000 2.511 2.512 compute_self_energy_cubic_gw 1 8.0 0.002 0.003 2.511 2.511 contract_cubic_gw 21 9.0 0.000 0.000 1.999 1.999 dbt_reserve_blocks_index 2849 13.1 0.058 0.064 1.437 1.701 dbt_reserve_blocks_index_array 2791 12.2 0.008 0.011 1.428 1.693 dbt_tas_reserve_blocks_index 3300 14.5 0.109 0.117 1.409 1.670 dbm_reserve_blocks 3696 15.4 1.387 1.638 1.387 1.638 dbt_crop 1042 12.0 0.842 0.940 1.291 1.480 mp2_ri_gpw_compute_in 1 5.0 0.000 0.001 1.212 1.213 dbt_tas_replicate 396 14.1 0.519 0.679 1.043 1.116 convert_to_new_pgrid 2421 14.1 0.023 0.027 0.718 0.920 compute_mat_P_omega_copy_M_vir 250 9.0 0.001 0.001 0.909 0.911 parallel_gemm_fm 105 8.4 0.000 0.000 0.891 0.897 parallel_gemm_fm_cosma 105 9.4 0.890 0.897 0.890 0.897 dbm_copy 1608 15.1 0.689 0.894 0.689 0.894 scf_env_do_scf 1 3.0 0.000 0.000 0.875 0.875 scf_env_do_scf_inner_loop 17 4.0 0.000 0.002 0.875 0.875 compute_mat_P_omega_copy_M_occ 250 9.0 0.001 0.001 0.854 0.856 mp_max_i 1994 9.8 0.579 0.688 0.579 0.688 compute_W_cubic_GW 10 7.0 0.001 0.001 0.673 0.679 dbm_add 807 14.1 0.521 0.620 0.521 0.620 ------------------------------------------------------------------------------- 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=21.825999999999993, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=30.006, 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=8.988, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=8.969, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=3.175, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_copy", label="dbm_copy", y=2.377, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=0.929, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="mp_waitall_2", label="mp_waitall_2", y=0.0, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="mp_sync", label="mp_sync", y=0.0, yerr=0.0 Plot: name="GW_PBE_4benzene_timings_32mpi", title="Timings of GW_PBE_4benzene with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="rest", label="rest", y=8.479, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=9.482, 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=0.37, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=0.379, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=1.387, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_copy", label="dbm_copy", y=0.689, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=1.971, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.346, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_sync", label="mp_sync", y=4.437, 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 0.017 0.017 285.963 285.963 qs_forces 1 2.0 0.000 0.000 285.418 285.418 rebuild_ks_matrix 7 6.6 0.000 0.000 284.024 284.024 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.001 284.024 284.024 hfx_ks_matrix 7 8.6 0.000 0.000 282.226 282.226 hfx_ri_update_ks 7 9.6 0.000 0.000 240.864 240.864 hfx_ri_update_ks_Pmat 7 10.6 31.015 31.015 240.860 240.860 dbt_total 841 11.0 0.005 0.005 228.656 228.656 qs_energies 1 3.0 0.000 0.000 211.139 211.139 scf_env_do_scf 1 4.0 0.000 0.000 210.859 210.859 qs_ks_update_qs_env 8 6.0 0.000 0.000 209.796 209.796 dbt_contract 207 12.4 0.030 0.030 209.671 209.671 dbt_tas_total 375 13.4 1.753 1.753 208.892 208.892 dbt_tas_multiply 216 13.5 0.001 0.001 204.641 204.641 dbt_tas_dbm 216 15.5 0.001 0.001 191.149 191.149 dbm_multiply 216 17.5 191.146 191.146 191.146 191.146 hfx_ri_update_ks_Pmat_KS 63 11.6 0.000 0.000 186.009 186.009 dbt_tas_mm_2 91 16.5 0.001 0.001 177.914 177.914 scf_env_do_scf_inner_loop 6 5.0 0.001 0.001 133.408 133.408 init_scf_loop 2 5.0 0.000 0.000 77.449 77.449 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 74.231 74.231 hfx_ri_update_forces 1 7.0 1.579 1.579 41.359 41.359 hfx_ri_forces_Pmat_3c 1 8.0 4.685 4.685 24.438 24.438 dbt_copy 409 11.7 0.026 0.026 14.727 14.727 precalc_derivatives 1 8.0 2.205 2.205 12.899 12.899 dbt_reshape 132 13.2 6.349 6.349 10.419 10.419 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 9.621 9.621 dbt_tas_mm_3T 77 17.1 0.000 0.000 9.021 9.021 build_3c_derivatives 3 9.0 2.699 2.699 7.127 7.127 dbt_tas_reserve_blocks_index 1287 15.4 0.269 0.269 7.115 7.115 dbm_reserve_blocks 1461 16.2 7.085 7.085 7.085 7.085 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 6.757 6.757 ------------------------------------------------------------------------------- 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 0.022 42.174 42.184 qs_forces 1 2.0 0.000 0.000 42.065 42.065 rebuild_ks_matrix 7 6.6 0.000 0.000 41.428 41.428 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.001 41.428 41.428 hfx_ks_matrix 7 8.6 0.000 0.000 40.542 40.551 dbt_total 841 11.0 0.005 0.012 35.977 35.980 dbt_contract 207 12.4 0.019 0.021 28.227 28.248 dbt_tas_total 375 13.4 0.069 0.219 26.306 26.306 dbt_tas_multiply 216 13.5 0.001 0.001 25.301 25.301 hfx_ri_update_ks 7 9.6 0.000 0.000 23.728 23.728 hfx_ri_update_ks_Pmat 7 10.6 1.165 1.252 23.727 23.727 qs_energies 1 3.0 0.000 0.000 22.317 22.317 scf_env_do_scf 1 4.0 0.000 0.001 22.186 22.186 qs_ks_update_qs_env 8 6.0 0.000 0.000 21.691 21.691 dbt_tas_dbm 216 15.5 0.001 0.001 20.123 20.124 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 19.738 19.738 dbm_multiply 216 17.5 17.639 18.892 17.639 18.892 hfx_ri_update_forces 1 7.0 0.056 0.059 16.814 16.823 hfx_ri_forces_Pmat_3c 1 8.0 0.159 0.171 12.561 12.576 scf_env_do_scf_inner_loop 6 5.0 0.000 0.001 12.330 12.330 hfx_ri_update_ks_Pmat_KS 63 11.6 0.000 0.001 11.299 11.299 init_scf_loop 2 5.0 0.000 0.000 9.855 9.855 dbt_tas_mm_2 91 16.5 0.001 0.001 9.518 9.518 mp_sync 2909 12.8 4.614 8.201 4.614 8.201 dbt_copy 421 11.8 0.009 0.011 6.251 6.603 dbt_tas_mm_3T 77 17.1 0.000 0.000 5.160 5.778 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 4.601 4.601 dbt_reshape 252 12.8 2.133 2.259 4.216 4.399 dbt_tas_mm_3N 37 15.4 0.000 0.000 3.755 3.920 precalc_derivatives 1 8.0 0.075 0.083 3.255 3.255 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 3.126 3.126 dbm_reserve_blocks 1477 16.3 2.361 2.753 2.361 2.753 dbt_tas_reserve_blocks_index 1302 15.5 0.212 0.220 2.361 2.724 dbt_crop 372 13.7 1.659 1.749 2.237 2.407 mp_waitall_2 1204 16.3 2.108 2.198 2.108 2.198 dbt_reserve_blocks_index 938 14.4 0.084 0.093 1.848 2.137 dbt_reserve_blocks_index_array 915 13.4 0.004 0.006 1.826 2.114 build_3c_derivatives 3 9.0 0.222 0.238 1.847 1.856 dbt_tas_replicate 175 15.2 0.632 0.683 1.585 1.667 hfx_ri_pre_scf_Pmat_RIx3C 9 13.0 0.000 0.000 1.580 1.585 dbt_tas_copy 169 12.8 0.743 0.804 1.324 1.502 convert_to_new_pgrid 648 15.5 0.032 0.059 1.236 1.479 dbt_communicate_buffer 252 13.8 0.011 0.013 1.412 1.478 dbm_copy 452 16.3 1.073 1.315 1.073 1.315 hfx_ri_update_ks_Pmat_copy_2 63 11.6 0.000 0.000 1.312 1.314 dbt_tas_communicate_buffer 352 16.4 0.012 0.013 0.915 0.993 hfx_ri_pre_scf_Pmat_int 1 13.0 0.000 0.000 0.876 0.881 ------------------------------------------------------------------------------- Plot: name="RI-HFX_H2O-32_timings_32omp", title="Timings of RI-HFX_H2O-32 with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="rest", label="rest", y=45.68300000000002, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=191.146, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=31.015, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=7.085, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=6.349, 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_sync", label="mp_sync", y=0.0, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="mp_waitall_2", label="mp_waitall_2", y=0.0, yerr=0.0 Plot: name="RI-HFX_H2O-32_timings_32mpi", title="Timings of RI-HFX_H2O-32 with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="rest", label="rest", y=11.995000000000001, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=17.639, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=1.165, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=2.361, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=2.133, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_forces_Pmat_3c", label="hfx_ri_forces_Pmat_3c", y=0.159, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_sync", label="mp_sync", y=4.614, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.108, 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 0.014 183.783 183.783 qs_energies 1 2.0 0.000 0.000 183.599 183.599 mp2_main 1 3.0 0.000 0.000 178.880 178.880 mp2_gpw_main 1 4.0 0.001 0.001 178.464 178.464 mp2_ri_gpw_compute_in 1 5.0 0.374 0.374 129.310 129.310 mp2_ri_gpw_compute_in_loop 1 6.0 0.009 0.009 118.175 118.175 mp2_eri_3c_integrate_gpw 2656 7.0 0.012 0.012 88.531 88.531 integrate_v_rspace 2666 8.0 0.598 0.598 75.723 75.723 grid_integrate_task_list 2666 9.0 73.157 73.157 73.157 73.157 mp2_ri_gpw_compute_en 1 5.0 0.087 0.087 49.130 49.130 mp2_ri_gpw_compute_en_RI_loop 1 6.0 9.972 9.972 47.360 47.360 mp2_ri_gpw_compute_en_expansio 2080 7.0 2.130 2.130 29.798 29.798 local_gemm 2080 8.0 27.667 27.667 27.667 27.667 dbcsr_multiply_generic 5322 8.0 0.181 0.181 20.274 20.274 ao_to_mo_and_store_B_mult_1 2656 7.0 0.009 0.009 20.254 20.254 pw_transfer 63872 10.6 1.013 1.013 11.540 11.540 calculate_wavefunction 2656 8.0 8.093 8.093 11.501 11.501 get_2c_integrals 1 6.0 0.000 0.000 10.760 10.760 fft_wrap_pw1pw2 53228 11.4 0.112 0.112 10.317 10.317 multiply_cannon 5322 9.0 0.418 0.418 9.962 9.962 compute_2c_integrals 1 7.0 0.005 0.005 9.909 9.909 compute_2c_integrals_loop_lm 1 8.0 0.013 0.013 9.890 9.890 mp2_eri_2c_integrate_gpw 1 9.0 3.267 3.267 9.876 9.876 ao_to_mo_and_store_B_E_Ex_1 2656 7.0 2.235 2.235 9.285 9.285 multiply_cannon_loop 5322 10.0 0.115 0.115 8.638 8.638 make_m2s 10644 9.0 0.060 0.060 8.021 8.021 make_images 10644 10.0 3.203 3.203 7.739 7.739 copy_dbcsr_to_fm 2679 8.0 0.026 0.026 7.553 7.553 fft_wrap_pw1pw2_20 21271 12.4 0.428 0.428 7.401 7.401 multiply_cannon_multrec 5322 11.0 7.206 7.206 7.243 7.243 fft3d_s 53229 13.4 6.359 6.359 6.395 6.395 dbcsr_complete_redistribute 2689 9.0 1.214 1.214 6.021 6.021 mp2_ri_gpw_compute_en_ener 2080 7.0 5.777 5.777 5.777 5.777 dbcsr_finalize 10708 9.5 0.207 0.207 5.386 5.386 dbcsr_merge_all 8011 10.3 3.595 3.595 4.725 4.725 scf_env_do_scf 1 3.0 0.000 0.000 4.338 4.338 scf_env_do_scf_inner_loop 10 4.0 0.001 0.001 4.338 4.338 potential_pw2rs 5322 10.0 0.144 0.144 3.872 3.872 ------------------------------------------------------------------------------- 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 0.006 0.020 33.321 33.332 qs_energies 1 2.0 0.000 0.000 33.255 33.256 mp2_main 1 3.0 0.000 0.001 31.254 31.254 mp2_gpw_main 1 4.0 0.001 0.002 31.141 31.141 mp2_ri_gpw_compute_in 1 5.0 0.051 0.052 16.776 16.996 mp2_ri_gpw_compute_in_loop 1 6.0 0.001 0.001 15.626 15.840 mp2_ri_gpw_compute_en 1 5.0 0.169 0.176 14.279 14.536 mp2_eri_3c_integrate_gpw 83 7.0 0.001 0.001 13.658 13.846 integrate_v_rspace 93 8.1 0.097 0.103 13.516 13.704 grid_integrate_task_list 93 9.1 13.239 13.431 13.239 13.431 mp2_ri_gpw_compute_en_RI_loop 1 6.0 0.772 0.905 13.397 13.405 mp2_ri_gpw_compute_en_expansio 65 7.0 0.093 0.114 10.016 10.187 local_gemm 65 8.0 9.923 10.074 9.923 10.074 mp2_ri_gpw_compute_en_comm 17 7.0 0.059 0.088 2.294 2.728 mp_sendrecv_dm3 1054 8.0 1.818 2.398 1.818 2.398 dbcsr_multiply_generic 176 8.0 0.007 0.008 1.691 1.927 ao_to_mo_and_store_B_mult_1 83 7.0 0.001 0.001 1.675 1.909 scf_env_do_scf 1 3.0 0.000 0.000 1.888 1.889 scf_env_do_scf_inner_loop 10 4.0 0.000 0.001 1.888 1.888 get_2c_integrals 1 6.0 0.000 0.000 1.081 1.111 multiply_cannon 176 9.0 0.015 0.016 0.997 1.083 multiply_cannon_loop 176 10.0 0.002 0.002 0.940 1.024 qs_scf_new_mos 10 5.0 0.000 0.000 0.984 0.988 eigensolver 11 5.8 0.001 0.001 0.974 0.975 multiply_cannon_multrec 246 11.0 0.813 0.853 0.818 0.858 cp_fm_diag_elpa 11 6.8 0.000 0.000 0.819 0.820 compute_2c_integrals 1 7.0 0.002 0.003 0.796 0.815 cp_fm_redistribute_end 11 7.8 0.306 0.809 0.319 0.814 make_m2s 352 9.0 0.003 0.003 0.659 0.806 make_images 352 10.0 0.050 0.052 0.647 0.793 cp_fm_diag_elpa_base 11 7.8 0.480 0.770 0.491 0.788 pw_transfer 2120 10.5 0.042 0.044 0.730 0.754 compute_2c_integrals_loop_lm 1 8.0 0.002 0.004 0.719 0.734 mp2_eri_2c_integrate_gpw 1 9.0 0.196 0.200 0.717 0.732 fft_wrap_pw1pw2 1768 11.4 0.004 0.005 0.676 0.696 ------------------------------------------------------------------------------- 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=57.68799999999999, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=73.157, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="local_gemm", label="local_gemm", y=27.667, 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=9.972, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="calculate_wavefunction", label="calculate_wavefunction", y=8.093, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=7.206, 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=6.756, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.239, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="local_gemm", label="local_gemm", y=9.923, 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=0.772, 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=0.813, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="mp_sendrecv_dm3", label="mp_sendrecv_dm3", y=1.818, 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 0.092 0.092 123.488 123.488 qs_energies 1 2.0 0.000 0.000 122.151 122.151 scf_env_do_scf 1 3.0 0.000 0.000 115.531 115.531 scf_env_do_scf_inner_loop 15 4.0 0.002 0.002 115.531 115.531 qs_ks_update_qs_env 15 5.0 0.000 0.000 48.451 48.451 rebuild_ks_matrix 15 6.0 0.000 0.000 48.242 48.242 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.002 48.242 48.242 qs_scf_new_mos 15 5.0 0.000 0.000 42.702 42.702 eigensolver 15 6.0 0.001 0.001 35.017 35.017 qs_vxc_create 15 8.0 0.033 0.033 33.297 33.297 calculate_dispersion_nonloc 15 9.0 6.899 6.899 29.160 29.160 cp_fm_diag_elpa 15 7.0 0.000 0.000 23.047 23.047 cp_fm_diag_elpa_base 15 8.0 20.468 20.468 23.047 23.047 pw_transfer 1191 10.0 0.053 0.053 22.556 22.556 fft_wrap_pw1pw2 1086 11.0 0.007 0.007 22.383 22.383 qs_rho_update_rho_low 16 5.0 0.000 0.000 21.608 21.608 calculate_rho_elec 16 6.0 0.215 0.215 21.608 21.608 grid_collocate_task_list 16 7.0 20.314 20.314 20.314 20.314 fft_wrap_pw1pw2_150 765 12.0 3.551 3.551 16.468 16.468 sum_up_and_integrate 15 8.0 0.098 0.098 13.870 13.870 integrate_v_rspace 15 9.0 0.018 0.018 13.772 13.772 grid_integrate_task_list 15 10.0 13.267 13.267 13.267 13.267 fft3d_s 1087 13.0 10.105 10.105 10.112 10.112 cp_fm_cholesky_restore 45 7.0 9.685 9.685 9.685 9.685 pw_scatter_s 585 13.1 6.971 6.971 6.971 6.971 fft_wrap_pw1pw2_200 197 12.3 0.636 0.636 5.738 5.738 dbcsr_complete_redistribute 46 8.3 2.259 2.259 5.565 5.565 copy_dbcsr_to_fm 16 5.9 0.001 0.001 5.540 5.540 cp_fm_upper_to_full 30 8.0 4.862 4.862 4.862 4.862 vdW_energy 15 10.0 4.276 4.276 4.276 4.276 xc_vxc_pw_create 15 9.0 0.211 0.211 4.103 4.103 gspace_mixing 14 5.0 0.170 0.170 3.962 3.962 broyden_mixing 14 6.0 3.378 3.378 3.378 3.378 init_scf_run 1 3.0 0.000 0.000 3.071 3.071 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 3.062 3.062 xc_pw_derive 90 11.0 0.000 0.000 2.673 2.673 calculate_dm_sparse 15 6.0 0.016 0.016 2.499 2.499 ------------------------------------------------------------------------------- From /workspace/artifacts/diag_cu144_broy_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.014 0.029 58.452 58.464 qs_energies 1 2.0 0.000 0.000 58.203 58.209 scf_env_do_scf 1 3.0 0.000 0.000 54.206 54.207 scf_env_do_scf_inner_loop 15 4.0 0.001 0.003 54.206 54.207 qs_ks_update_qs_env 15 5.0 0.000 0.000 22.858 22.879 rebuild_ks_matrix 15 6.0 0.000 0.000 22.826 22.847 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.003 22.826 22.847 qs_rho_update_rho_low 16 5.0 0.000 0.000 20.013 20.017 calculate_rho_elec 16 6.0 0.007 0.007 20.013 20.017 grid_collocate_task_list 16 7.0 19.047 19.210 19.047 19.210 sum_up_and_integrate 15 8.0 0.010 0.015 13.826 13.883 integrate_v_rspace 15 9.0 0.000 0.001 13.816 13.878 grid_integrate_task_list 15 10.0 12.764 13.320 12.764 13.320 qs_scf_new_mos 15 5.0 0.000 0.000 12.016 12.402 eigensolver 15 6.0 0.001 0.002 11.123 11.155 qs_vxc_create 15 8.0 0.001 0.001 8.729 8.738 cp_fm_diag_elpa 15 7.0 0.000 0.000 8.052 8.055 cp_fm_diag_elpa_base 15 8.0 7.910 7.951 8.050 8.050 calculate_dispersion_nonloc 15 9.0 0.904 0.948 7.027 7.053 pw_transfer 1191 10.0 0.080 0.097 6.457 6.559 fft_wrap_pw1pw2 1086 11.0 0.011 0.013 6.299 6.422 fft3d_ps 1086 13.0 2.288 2.550 4.751 5.055 fft_wrap_pw1pw2_150 765 12.0 0.240 0.277 4.090 4.149 cp_fm_cholesky_restore 45 7.0 2.930 2.992 2.930 2.992 mp_alltoall_z22v 1086 15.0 1.943 2.602 1.943 2.602 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 2.428 2.428 build_core_hamiltonian_matrix 1 4.0 0.000 0.000 2.134 2.329 fft_wrap_pw1pw2_200 197 12.3 0.162 0.196 2.107 2.193 xc_vxc_pw_create 15 9.0 0.014 0.018 1.702 1.730 yz_to_x 501 13.9 0.197 0.275 1.231 1.543 x_to_yz 585 14.1 0.301 0.334 1.210 1.476 build_core_ppnl 1 5.0 1.247 1.382 1.247 1.382 init_scf_run 1 3.0 0.000 0.000 1.348 1.349 vdW_energy 15 10.0 1.249 1.314 1.249 1.314 scf_env_initial_rho_setup 1 4.0 0.000 0.000 1.269 1.270 ------------------------------------------------------------------------------- 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=49.649, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=20.468, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=20.314, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.267, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="fft3d_s", label="fft3d_s", y=10.105, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=9.685, 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=13.512999999999998, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=7.91, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=19.047, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=12.764, 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=2.93, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=2.288, 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 0.072 0.072 352.119 352.119 qs_energies 1 2.0 0.000 0.000 351.986 351.986 ls_scf 1 3.0 0.000 0.000 350.792 350.792 ls_scf_main 1 4.0 0.002 0.002 341.728 341.728 density_matrix_trs4 11 5.0 0.012 0.012 252.370 252.370 arnoldi_extremal 12 6.1 0.000 0.000 169.442 169.442 arnoldi_normal_ev 12 7.1 0.013 0.013 169.442 169.442 dbcsr_matrix_vector_mult 652 9.0 0.154 0.154 166.839 166.839 build_subspace 23 8.1 0.073 0.073 166.605 166.605 dbcsr_matrix_vector_mult_local 652 10.0 165.403 165.403 165.412 165.412 ls_scf_dm_to_ks 11 5.0 0.000 0.000 84.237 84.237 matrix_ls_to_qs 11 6.0 0.000 0.000 81.005 81.005 dbcsr_multiply_generic 185 6.1 0.828 0.828 72.246 72.246 multiply_cannon 185 7.1 0.287 0.287 43.820 43.820 dbcsr_copy_into_existing 11 7.0 43.727 43.727 43.728 43.728 dbcsr_complete_redistribute 23 7.5 29.959 29.959 40.890 40.890 matrix_decluster 11 7.0 0.000 0.000 37.277 37.277 multiply_cannon_loop 185 8.1 0.223 0.223 31.412 31.412 make_m2s 370 7.1 0.037 0.037 24.032 24.032 make_images 370 8.1 10.421 10.421 22.541 22.541 multiply_cannon_multrec 185 9.1 22.093 22.093 22.118 22.118 dbcsr_finalize 646 7.5 0.150 0.150 14.491 14.491 dbcsr_merge_all 597 8.5 2.253 2.253 13.461 13.461 setup_rec_index_2d 370 8.1 12.036 12.036 12.036 12.036 dbcsr_sort_indices 1103 9.9 10.054 10.054 10.054 10.054 tree_to_linear_d 110 9.4 9.888 9.888 9.888 9.888 calculate_norms 370 9.1 9.071 9.071 9.071 9.071 quick_finalize 395 10.0 0.349 0.349 8.693 8.693 ls_scf_init_scf 1 4.0 0.000 0.000 8.394 8.394 ls_scf_init_matrix_S 1 5.0 0.000 0.000 8.065 8.065 dbcsr_special_finalize 370 9.1 0.002 0.002 8.036 8.036 matrix_sqrt_Newton_Schulz 1 6.0 0.001 0.001 7.425 7.425 ------------------------------------------------------------------------------- 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 62.835 62.845 qs_energies 1 2.0 0.000 0.000 62.748 62.749 ls_scf 1 3.0 0.000 0.000 62.699 62.700 ls_scf_main 1 4.0 0.000 0.008 60.203 60.205 density_matrix_trs4 11 5.0 0.006 0.017 57.808 57.870 dbcsr_multiply_generic 185 6.1 0.057 0.084 54.785 55.140 multiply_cannon 185 7.1 0.032 0.036 45.476 45.995 multiply_cannon_loop 185 8.1 0.105 0.138 43.169 43.660 multiply_cannon_multrec 1480 9.1 26.752 30.082 27.006 30.366 mp_waitall_1 11936 10.3 14.215 17.267 14.215 17.267 multiply_cannon_metrocomm3 1480 9.1 0.012 0.017 8.093 13.626 multiply_cannon_metrocomm1 1480 9.1 0.007 0.010 3.517 7.052 make_m2s 370 7.1 0.034 0.036 6.400 6.500 make_images 370 8.1 0.614 0.643 6.276 6.378 calculate_norms 2960 9.1 4.393 5.499 4.393 5.499 make_images_data 370 9.1 0.008 0.010 2.808 3.030 mp_sum_l 1119 5.6 1.915 2.789 1.915 2.789 hybrid_alltoall_any 393 9.9 0.154 0.723 2.428 2.658 arnoldi_extremal 12 6.1 0.000 0.000 2.251 2.273 arnoldi_normal_ev 12 7.1 0.001 0.003 2.250 2.273 build_subspace 23 8.1 0.018 0.023 2.162 2.164 ls_scf_dm_to_ks 11 5.0 0.000 0.000 2.076 2.135 dbcsr_matrix_vector_mult 652 9.0 0.009 0.042 1.888 1.941 dbcsr_complete_redistribute 23 7.5 1.158 1.225 1.855 1.926 ls_scf_init_scf 1 4.0 0.000 0.000 1.922 1.923 ls_scf_init_matrix_S 1 5.0 0.000 0.000 1.897 1.903 matrix_ls_to_qs 11 6.0 0.000 0.000 1.813 1.890 make_images_pack 370 9.1 1.586 1.764 1.590 1.768 matrix_decluster 11 7.0 0.000 0.000 1.673 1.749 dbcsr_multiply_generic_mpsum_f 137 7.1 0.000 0.000 0.995 1.738 matrix_sqrt_Newton_Schulz 1 6.0 0.000 0.001 1.736 1.737 dbcsr_matrix_vector_mult_local 652 10.0 1.587 1.636 1.589 1.638 dbcsr_finalize 646 7.5 0.007 0.008 1.314 1.484 buffer_matrices_ensure_size 370 8.1 1.229 1.453 1.229 1.453 ------------------------------------------------------------------------------- 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=69.82999999999998, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=165.403, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_copy_into_existing", label="dbcsr_copy_into_existing", y=43.727, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_complete_redistribute", label="dbcsr_complete_redistribute", y=29.959, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=22.093, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="setup_rec_index_2d", label="setup_rec_index_2d", y=12.036, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="calculate_norms", label="calculate_norms", y=9.071, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="mp_sum_l", label="mp_sum_l", y=0.0, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 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=12.815000000000005, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=1.587, 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=1.158, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=26.752, 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=4.393, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=1.915, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=14.215, 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 68.995 68.995 lib_test 1 2.0 0.000 0.000 68.988 68.988 dbcsr_run_tests 3 3.0 0.002 0.002 68.988 68.988 test_multiplies_multiproc 3 4.0 0.001 0.001 53.464 53.464 dbcsr_redistribute 9 5.0 34.829 34.829 36.386 36.386 dbcsr_multiply_generic 9 5.0 0.001 0.001 15.724 15.724 dbcsr_make_random_matrix 9 4.0 12.384 12.384 15.417 15.417 multiply_cannon 9 6.0 0.001 0.001 11.100 11.100 multiply_cannon_loop 9 7.0 0.014 0.014 10.747 10.747 multiply_cannon_multrec 9 8.0 10.733 10.733 10.733 10.733 dbcsr_finalize 27 5.7 0.004 0.004 5.512 5.512 dbcsr_merge_all 18 6.5 1.953 1.953 4.790 4.790 dbcsr_data_release 975 7.6 2.775 2.775 2.775 2.775 tree_to_linear_d 9 7.0 1.848 1.848 1.848 1.848 make_m2s 18 6.0 0.001 0.001 1.585 1.585 make_images 18 7.0 0.543 0.543 1.538 1.538 ------------------------------------------------------------------------------- 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 17.144 17.149 lib_test 1 2.0 0.000 0.000 17.116 17.135 dbcsr_run_tests 3 3.0 0.000 0.001 17.115 17.134 test_multiplies_multiproc 3 4.0 0.000 0.002 16.283 16.344 dbcsr_multiply_generic 9 5.0 0.001 0.001 14.978 15.058 multiply_cannon 9 6.0 0.001 0.002 13.255 13.559 multiply_cannon_loop 9 7.0 0.002 0.002 12.974 13.284 multiply_cannon_multrec 72 8.0 10.845 11.237 10.845 11.237 mp_waitall_1 576 9.2 2.417 3.456 2.417 3.456 multiply_cannon_metrocomm1 72 8.0 0.001 0.001 1.868 2.947 dbcsr_data_release 444 7.6 0.784 0.938 0.784 0.938 mp_sum_l 390 2.5 0.405 0.837 0.405 0.837 dbcsr_multiply_generic_mpsum_f 9 6.0 0.000 0.000 0.402 0.834 dbcsr_make_random_matrix 9 4.0 0.665 0.675 0.804 0.830 dbcsr_finalize 27 5.7 0.000 0.000 0.710 0.819 multiply_cannon_metrocomm3 72 8.0 0.000 0.000 0.254 0.764 dbcsr_destroy 111 5.9 0.000 0.000 0.623 0.747 make_m2s 18 6.0 0.001 0.001 0.631 0.656 make_images 18 7.0 0.021 0.021 0.627 0.653 dbcsr_merge_all 18 6.5 0.101 0.123 0.547 0.603 dbcsr_redistribute 9 5.0 0.225 0.256 0.377 0.401 make_images_data 18 8.0 0.000 0.001 0.325 0.392 dbcsr_data_copy_aa2 18 7.5 0.334 0.380 0.334 0.380 ------------------------------------------------------------------------------- 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=6.321000000000005, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_redistribute", label="dbcsr_redistribute", y=34.829, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=12.384, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=10.733, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_data_release", label="dbcsr_data_release", y=2.775, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_merge_all", label="dbcsr_merge_all", y=1.953, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="mp_sum_l", label="mp_sum_l", y=0.0, yerr=0.0 Plot: name="dbcsr_timings_32mpi", title="Timings of dbcsr with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="dbcsr_timings_32mpi", name="rest", label="rest", y=1.7019999999999964, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_redistribute", label="dbcsr_redistribute", y=0.225, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=0.665, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=10.845, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_data_release", label="dbcsr_data_release", y=0.784, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_merge_all", label="dbcsr_merge_all", y=0.101, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=2.417, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=0.405, 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 0.053 0.053 126.945 126.945 qs_mol_dyn_low 1 2.0 0.003 0.003 125.596 125.596 velocity_verlet 5 3.0 0.003 0.003 102.471 102.471 qmmm_el_coupling 6 3.8 0.000 0.000 83.170 83.170 qmmm_elec_with_gaussian 6 4.8 0.012 0.012 83.166 83.166 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 82.545 82.545 qmmm_elec_gaussian_low_G 6 6.8 81.665 81.665 81.665 81.665 qs_forces 6 3.8 0.000 0.000 34.098 34.098 qs_energies 6 4.8 0.000 0.000 30.298 30.298 scf_env_do_scf 6 5.8 0.001 0.001 28.103 28.103 scf_env_do_scf_inner_loop 39 6.8 0.004 0.004 24.297 24.297 rebuild_ks_matrix 45 8.4 0.000 0.000 23.502 23.502 qs_ks_build_kohn_sham_matrix 45 9.4 0.005 0.005 23.501 23.501 qs_ks_update_qs_env 45 7.8 0.000 0.000 20.149 20.149 pw_transfer 966 12.3 0.051 0.051 16.934 16.934 fft_wrap_pw1pw2 801 13.6 0.006 0.006 16.740 16.740 fft_wrap_pw1pw2_150 507 15.2 2.209 2.209 16.339 16.339 qs_vxc_create 45 10.4 0.001 0.001 13.110 13.110 xc_vxc_pw_create 45 11.4 0.661 0.661 13.109 13.109 xc_pw_derive 270 13.4 0.002 0.002 9.284 9.284 fft3d_s 802 15.6 7.656 7.656 7.664 7.664 qs_rho_update_rho_low 45 7.9 0.000 0.000 7.012 7.012 calculate_rho_elec 45 8.9 0.563 0.563 7.012 7.012 xc_rho_set_and_dset_create 45 12.4 0.558 0.558 6.624 6.624 xc_pw_divergence 45 12.4 0.001 0.001 5.753 5.753 pw_scatter_s 429 15.8 5.615 5.615 5.615 5.615 qmmm_forces 6 3.8 0.001 0.001 5.178 5.178 qmmm_forces_with_gaussian 6 4.8 0.017 0.017 4.863 4.863 pw_integral_ab 2539 7.4 4.438 4.438 4.438 4.438 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 4.154 4.154 qs_ks_ddapc 45 10.4 0.001 0.001 4.108 4.108 init_scf_loop 6 6.8 0.000 0.000 3.800 3.800 qmmm_forces_gaussian_low_G 6 6.8 3.443 3.443 3.443 3.443 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 3.360 3.360 density_rs2pw 45 9.9 0.002 0.002 3.259 3.259 sum_up_and_integrate 45 10.4 0.323 0.323 3.245 3.245 grid_collocate_task_list 45 9.9 3.190 3.190 3.190 3.190 integrate_v_rspace 45 11.4 0.006 0.006 2.922 2.922 fist_calc_energy_force 6 3.8 0.001 0.001 2.543 2.543 cp_ddapc_apply_CD 45 11.4 0.004 0.004 2.540 2.540 ------------------------------------------------------------------------------- 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 0.059 52.241 52.255 qs_mol_dyn_low 1 2.0 0.003 0.004 51.260 51.317 qs_forces 6 3.8 0.000 0.001 36.830 36.831 qs_energies 6 4.8 0.000 0.000 35.118 35.118 scf_env_do_scf 6 5.8 0.000 0.001 34.237 34.237 scf_env_do_scf_inner_loop 113 6.2 0.002 0.018 32.849 32.850 rebuild_ks_matrix 119 8.1 0.000 0.000 24.183 24.192 qs_ks_build_kohn_sham_matrix 119 9.1 0.015 0.016 24.183 24.192 qs_ks_update_qs_env 119 7.3 0.001 0.001 22.749 22.758 velocity_verlet 5 3.0 0.002 0.004 21.713 21.716 pw_transfer 2446 12.3 0.196 0.236 16.063 16.641 fft_wrap_pw1pw2 2059 13.4 0.024 0.029 15.624 16.205 fft_wrap_pw1pw2_150 1321 14.9 1.263 1.396 15.117 15.618 qs_vxc_create 119 10.1 0.002 0.003 12.753 12.757 xc_vxc_pw_create 119 11.1 0.147 0.218 12.751 12.755 fft3d_ps 2059 15.4 6.779 7.488 11.591 12.392 qs_rho_update_rho_low 119 7.3 0.000 0.000 9.893 9.893 calculate_rho_elec 119 8.3 0.049 0.057 9.892 9.893 xc_pw_derive 714 13.1 0.011 0.012 9.565 9.810 sum_up_and_integrate 119 10.1 0.081 0.092 8.360 8.372 integrate_v_rspace 119 11.1 0.003 0.003 8.279 8.295 qmmm_forces 6 3.8 0.002 0.002 7.151 7.152 qmmm_forces_with_gaussian 6 4.8 0.008 0.011 6.893 7.035 qmmm_el_coupling 6 3.8 0.000 0.000 6.446 6.522 qmmm_elec_with_gaussian 6 4.8 0.003 0.004 6.445 6.520 xc_pw_divergence 119 12.1 0.005 0.006 6.225 6.446 xc_rho_set_and_dset_create 119 12.1 0.351 0.435 6.193 6.358 rs_pw_transfer 988 11.5 0.010 0.013 5.750 5.958 density_rs2pw 119 9.3 0.006 0.007 5.479 5.684 potential_pw2rs 119 12.1 0.006 0.006 4.729 4.743 mp_alltoall_z22v 2059 17.4 3.412 4.574 3.412 4.574 grid_collocate_task_list 119 9.3 4.273 4.434 4.273 4.434 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 3.829 3.861 grid_integrate_task_list 119 12.1 3.347 3.505 3.347 3.505 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 3.299 3.431 qmmm_forces_gaussian_low_G 6 6.8 3.141 3.171 3.141 3.171 x_to_yz 1095 16.8 0.808 0.909 2.582 3.146 qmmm_elec_gaussian_low_G 6 6.8 2.710 2.784 2.710 2.784 yz_to_x 964 16.0 0.530 0.650 2.168 2.721 pw_restrict_s3 18 5.8 1.320 1.362 2.479 2.599 mp_waitany 4028 12.8 2.069 2.406 2.069 2.406 rs_pw_transfer_PW2RS_150 125 13.9 0.731 0.788 2.189 2.227 qmmm_elec_with_gaussian:spline 6 5.8 0.000 0.000 2.110 2.177 pw_prolongate_s3 18 6.8 1.129 1.149 2.110 2.177 qs_scf_new_mos 113 7.2 0.000 0.000 1.913 1.919 qs_scf_loop_do_ot 113 8.2 0.000 0.000 1.913 1.918 rs_pw_transfer_RS2PW_150 125 11.2 0.596 0.693 1.708 1.911 qs_ks_ddapc 119 10.1 0.002 0.002 1.806 1.864 ot_scf_mini 113 9.2 0.001 0.001 1.818 1.828 mp_waitall_1 188862 16.2 1.610 1.804 1.610 1.804 dbcsr_multiply_generic 2588 12.3 0.056 0.057 1.740 1.769 mp_sum_dm3 33 5.7 1.518 1.569 1.518 1.569 pw_integral_ab 2761 7.7 1.248 1.338 1.436 1.567 pw_scatter_p 1095 15.8 1.512 1.559 1.512 1.559 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 1.443 1.443 pw_gather_p 964 15.0 1.205 1.434 1.205 1.434 init_scf_loop 6 6.8 0.000 0.000 1.385 1.385 ot_mini 113 10.2 0.000 0.000 1.126 1.131 ------------------------------------------------------------------------------- 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=20.937999999999988, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=81.665, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_s", label="fft3d_s", y=7.656, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_scatter_s", label="pw_scatter_s", y=5.615, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_integral_ab", label="pw_integral_ab", y=4.438, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.443, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=3.19, 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 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_ps", label="fft3d_ps", 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=27.331, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=2.71, 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=1.248, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.141, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=4.273, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=3.412, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=3.347, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=6.779, yerr=0.0 Summary: Performance test took 33 minutes. Status: OK Removing intermediate container ba7b879ef841 ---> d940ae84536d Step 41/42 : CMD cat $(find ./report.log -mmin +10) | sed '/^Summary:/ s/$/ (cached)/' ---> Running in 8a77a77da76e Removing intermediate container 8a77a77da76e ---> dec44edc847c Step 42/42 : ENTRYPOINT [] ---> Running in d8d06a18bb80 Removing intermediate container d8d06a18bb80 ---> 0c6e4ec1ef87 [Warning] One or more build-args [GIT_COMMIT_SHA] were not consumed Successfully built 0c6e4ec1ef87 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: 2022-12-05 19:50:35+00:00