StartDate: 2022-12-06 11:06:09+00:00 CpuId: 32x AMD EPYC (3rd Gen) (Milan) [Zen 3], 7nm (SMT disabled) CommitSHA: b753bb93281c97fa8726a6c63af42b68d04a50bb CommitTime: 2022-12-06 10:37:19 +0100 CommitAuthor: Juerg Hutter CommitSubject: Remove unused parameter (#2433) Populating docker build cache... done. #################### Building Image cp2k-perf-openmp #################### Dockerfile: /tools/docker/Dockerfile.test_performance Build-Path: / Build-Args: GIT_COMMIT_SHA=b753bb93281c97fa8726a6c63af42b68d04a50bb 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 ---> b757dabde138 Step 32/42 : COPY ./exts ./exts ---> Using cache ---> bd8cf87a4749 Step 33/42 : COPY ./tools/build_utils ./tools/build_utils ---> Using cache ---> 00b38e9dd0c7 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 1543d3803a3b './arch/local.psmp' -> '/opt/cp2k-toolchain/install/arch/local.psmp' Compiling cp2k... Removing intermediate container 1543d3803a3b ---> 9dfd2f3988e6 Step 35/42 : COPY ./data ./data ---> 275bf1723c16 Step 36/42 : COPY ./tests ./tests ---> 4fa2a361e415 Step 37/42 : COPY ./tools/regtesting ./tools/regtesting ---> 7362748fb167 Step 38/42 : COPY ./benchmarks ./benchmarks ---> 6bc44bb0011f Step 39/42 : COPY ./tools/docker/scripts/test_performance.sh ./tools/docker/scripts/plot_performance.py ./ ---> c68a811c136f Step 40/42 : RUN ./test_performance.sh "local" 2>&1 | tee report.log ---> Running in 4fcf1d5fe814 ========== 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 0.036 0.036 91.752 91.752 qs_mol_dyn_low 1 2.0 0.003 0.003 91.116 91.116 qs_forces 11 3.9 0.001 0.001 91.077 91.077 qs_energies 11 4.9 0.001 0.001 84.896 84.896 scf_env_do_scf 11 5.9 0.001 0.001 73.843 73.843 velocity_verlet 10 3.0 0.002 0.002 59.258 59.258 scf_env_do_scf_inner_loop 108 6.5 0.012 0.012 56.338 56.338 rebuild_ks_matrix 119 8.3 0.001 0.001 21.208 21.208 qs_ks_build_kohn_sham_matrix 119 9.3 0.013 0.013 21.207 21.207 qs_rho_update_rho_low 119 7.7 0.001 0.001 20.659 20.659 calculate_rho_elec 119 8.7 0.957 0.957 20.658 20.658 dbcsr_multiply_generic 2286 12.5 0.168 0.168 20.265 20.265 qs_scf_new_mos 108 7.5 0.001 0.001 20.104 20.104 qs_scf_loop_do_ot 108 8.5 0.001 0.001 20.104 20.104 qs_ks_update_qs_env 119 7.6 0.001 0.001 19.510 19.510 ot_scf_mini 108 9.5 0.003 0.003 18.607 18.607 init_scf_loop 11 6.9 0.000 0.000 17.365 17.365 grid_collocate_task_list 119 9.7 15.938 15.938 15.938 15.938 prepare_preconditioner 11 7.9 0.000 0.000 14.815 14.815 make_preconditioner 11 8.9 0.000 0.000 14.815 14.815 sum_up_and_integrate 119 10.3 0.552 0.552 13.761 13.761 make_full_inverse_cholesky 11 9.9 0.000 0.000 13.692 13.692 integrate_v_rspace 119 11.3 0.102 0.102 13.209 13.209 ot_mini 108 10.5 0.001 0.001 11.985 11.985 grid_integrate_task_list 119 12.3 11.126 11.126 11.126 11.126 make_m2s 4572 13.5 0.047 0.047 10.841 10.841 pw_transfer 1439 11.6 0.071 0.071 6.534 6.534 qs_ot_get_derivative 108 11.5 0.001 0.001 6.507 6.507 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 6.345 6.345 fft_wrap_pw1pw2 1201 12.6 0.007 0.007 6.293 6.293 dbcsr_make_dense_low 5837 15.5 0.070 0.070 5.892 5.892 make_dense_data 5837 16.5 5.283 5.283 5.807 5.807 multiply_cannon 2286 13.5 0.188 0.188 5.495 5.495 ot_diis_step 108 11.5 0.004 0.004 5.474 5.474 fft_wrap_pw1pw2_140 487 13.2 0.469 0.469 5.450 5.450 make_images 4572 14.5 2.151 2.151 5.445 5.445 cp_fm_cholesky_decompose 22 10.9 5.098 5.098 5.098 5.098 dbcsr_make_images_dense 3978 14.8 0.018 0.018 5.080 5.080 multiply_cannon_loop 2286 14.5 0.055 0.055 5.011 5.011 multiply_cannon_multrec 2286 15.5 4.896 4.896 4.955 4.955 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 4.948 4.948 apply_single 119 13.6 0.000 0.000 4.947 4.947 cp_fm_cholesky_invert 11 10.9 4.442 4.442 4.442 4.442 init_scf_run 11 5.9 0.002 0.002 4.079 4.079 scf_env_initial_rho_setup 11 6.9 0.001 0.001 4.077 4.077 dbcsr_complete_redistribute 329 12.2 1.938 1.938 3.775 3.775 density_rs2pw 119 9.7 0.005 0.005 3.763 3.763 dbcsr_copy 2102 12.0 0.262 0.262 3.654 3.654 wfi_extrapolate 11 7.9 0.001 0.001 3.544 3.544 build_core_hamiltonian_matrix_ 11 4.9 0.001 0.001 3.507 3.507 dbcsr_copy_into_existing 22 7.9 3.357 3.357 3.357 3.357 qs_env_update_s_mstruct 11 6.9 0.000 0.000 3.354 3.354 fft3d_s 1202 14.6 3.201 3.201 3.206 3.206 qs_ot_get_p 119 10.4 0.001 0.001 3.118 3.118 copy_dbcsr_to_fm 153 11.3 0.002 0.002 3.099 3.099 qs_create_task_list 11 7.9 0.000 0.000 2.918 2.918 generate_qs_task_list 11 8.9 1.978 1.978 2.918 2.918 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 2.672 2.672 build_core_hamiltonian_matrix 11 6.9 0.001 0.001 2.579 2.579 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.357 2.357 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 2.050 2.050 pw_poisson_solve 119 10.3 0.361 0.361 2.029 2.029 qs_ot_get_derivative_taylor 59 13.0 0.002 0.002 1.994 1.994 potential_pw2rs 119 12.3 0.049 0.049 1.981 1.981 copy_fm_to_dbcsr 176 11.2 0.001 0.001 1.854 1.854 dbcsr_data_release 279534 16.0 1.849 1.849 1.849 1.849 ------------------------------------------------------------------------------- From /workspace/artifacts/H2O-64_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.008 0.030 47.644 47.655 qs_mol_dyn_low 1 2.0 0.004 0.004 47.533 47.538 qs_forces 11 3.9 0.001 0.001 47.491 47.492 qs_energies 11 4.9 0.001 0.001 44.368 44.370 scf_env_do_scf 11 5.9 0.000 0.002 40.656 40.657 scf_env_do_scf_inner_loop 108 6.5 0.003 0.021 37.524 37.525 velocity_verlet 10 3.0 0.001 0.003 28.367 28.368 rebuild_ks_matrix 119 8.3 0.001 0.001 17.262 17.336 qs_ks_build_kohn_sham_matrix 119 9.3 0.015 0.017 17.261 17.335 qs_ks_update_qs_env 119 7.6 0.001 0.001 15.351 15.421 dbcsr_multiply_generic 2286 12.5 0.078 0.082 14.140 14.266 qs_rho_update_rho_low 119 7.7 0.001 0.001 13.929 13.942 calculate_rho_elec 119 8.7 0.030 0.031 13.928 13.941 sum_up_and_integrate 119 10.3 0.034 0.042 12.801 12.830 integrate_v_rspace 119 11.3 0.004 0.005 12.767 12.806 qs_scf_new_mos 108 7.5 0.001 0.001 11.100 11.261 qs_scf_loop_do_ot 108 8.5 0.001 0.001 11.100 11.260 multiply_cannon 2286 13.5 0.141 0.155 10.466 10.716 ot_scf_mini 108 9.5 0.002 0.002 10.427 10.567 multiply_cannon_loop 2286 14.5 0.097 0.107 9.927 10.209 grid_collocate_task_list 119 9.7 9.802 10.070 9.802 10.070 mp_waitall_1 169478 16.3 8.890 9.510 8.890 9.510 grid_integrate_task_list 119 12.3 8.745 8.986 8.745 8.986 multiply_cannon_metrocomm3 18288 15.5 0.037 0.039 5.803 6.445 ot_mini 108 10.5 0.001 0.001 6.051 6.203 rs_pw_transfer 974 11.9 0.012 0.013 4.582 5.020 density_rs2pw 119 9.7 0.005 0.006 3.758 4.180 pw_transfer 1439 11.6 0.086 0.096 3.550 3.604 potential_pw2rs 119 12.3 0.007 0.008 3.445 3.477 multiply_cannon_multrec 18288 15.5 3.223 3.429 3.234 3.439 fft_wrap_pw1pw2 1201 12.6 0.009 0.010 3.389 3.434 qs_ot_get_derivative 108 11.5 0.001 0.001 3.051 3.187 init_scf_loop 11 6.9 0.000 0.000 3.118 3.118 fft_wrap_pw1pw2_140 487 13.2 0.273 0.322 2.880 2.986 ot_diis_step 108 11.5 0.004 0.004 2.974 2.974 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 2.882 2.974 apply_single 119 13.6 0.000 0.000 2.882 2.973 init_scf_run 11 5.9 0.000 0.004 2.650 2.650 scf_env_initial_rho_setup 11 6.9 0.000 0.004 2.650 2.650 fft3d_ps 1201 14.6 1.252 1.387 2.482 2.582 make_m2s 4572 13.5 0.047 0.052 2.472 2.539 wfi_extrapolate 11 7.9 0.001 0.001 2.386 2.387 make_images 4572 14.5 0.121 0.125 2.134 2.205 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 2.058 2.066 mp_waitany 9880 13.7 1.428 1.950 1.428 1.950 qs_ot_get_p 119 10.4 0.001 0.001 1.332 1.524 rs_pw_transfer_RS2PW_140 130 11.5 0.203 0.242 1.016 1.456 make_images_data 4572 15.5 0.036 0.042 1.200 1.395 rs_pw_transfer_PW2RS_140 130 13.9 0.367 0.436 1.328 1.369 prepare_preconditioner 11 7.9 0.000 0.000 1.202 1.219 make_preconditioner 11 8.9 0.000 0.000 1.202 1.219 multiply_cannon_metrocomm1 18288 15.5 0.018 0.020 0.587 1.211 mp_alltoall_z22v 1201 16.6 0.977 1.199 0.977 1.199 mp_sum_l 11218 13.2 0.739 1.195 0.739 1.195 hybrid_alltoall_any 4725 16.4 0.062 0.200 1.044 1.179 mp_alltoall_d11v 2130 13.8 0.776 1.106 0.776 1.106 make_full_inverse_cholesky 11 9.9 0.000 0.000 1.089 1.105 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 0.982 1.044 cp_dbcsr_sm_fm_multiply 37 9.5 0.001 0.001 1.026 1.027 qs_ot_get_derivative_taylor 59 13.0 0.001 0.001 0.950 1.026 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 0.933 1.020 rs_pw_transfer_PW2RS_50 119 14.3 0.290 0.352 0.891 0.986 mp_sum_d 4125 12.0 0.684 0.978 0.684 0.978 ------------------------------------------------------------------------------- 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=49.410999999999994, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=15.938, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=11.126, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="make_dense_data", label="make_dense_data", y=5.283, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=5.098, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=4.896, 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=15.556000000000004, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=9.802, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=8.745, 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=3.223, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitany", label="mp_waitany", y=1.428, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=8.89, 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 0.033 0.033 116.898 116.898 qs_mol_dyn_low 1 2.0 0.003 0.003 116.216 116.216 qs_forces 11 3.9 0.001 0.001 116.176 116.176 qs_energies 11 4.9 0.001 0.001 108.179 108.179 scf_env_do_scf 11 5.9 0.001 0.001 94.899 94.899 scf_env_do_scf_inner_loop 96 6.5 0.011 0.011 75.642 75.642 velocity_verlet 10 3.0 0.002 0.002 75.112 75.112 rebuild_ks_matrix 107 8.3 0.001 0.001 35.058 35.058 qs_ks_build_kohn_sham_matrix 107 9.3 0.012 0.012 35.057 35.057 qs_rho_update_rho_low 107 7.7 0.001 0.001 33.537 33.537 calculate_rho_elec 107 8.7 0.865 0.865 33.536 33.536 qs_ks_update_qs_env 107 7.6 0.001 0.001 31.481 31.481 grid_collocate_task_list 107 9.7 29.299 29.299 29.299 29.299 sum_up_and_integrate 107 10.3 0.498 0.498 28.263 28.263 integrate_v_rspace 107 11.3 0.091 0.091 27.765 27.765 grid_integrate_task_list 107 12.3 25.920 25.920 25.920 25.920 init_scf_loop 11 6.9 0.000 0.000 19.111 19.111 dbcsr_multiply_generic 1966 12.4 0.140 0.140 18.422 18.422 qs_scf_new_mos 96 7.5 0.001 0.001 17.839 17.839 qs_scf_loop_do_ot 96 8.5 0.001 0.001 17.838 17.838 ot_scf_mini 96 9.5 0.002 0.002 16.532 16.532 prepare_preconditioner 11 7.9 0.000 0.000 14.875 14.875 make_preconditioner 11 8.9 0.000 0.000 14.875 14.875 make_full_inverse_cholesky 11 9.9 0.000 0.000 13.697 13.697 ot_mini 96 10.5 0.001 0.001 10.644 10.644 make_m2s 3932 13.4 0.041 0.041 9.843 9.843 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 6.971 6.971 pw_transfer 1295 11.6 0.063 0.063 5.768 5.768 qs_ot_get_derivative 96 11.5 0.001 0.001 5.734 5.734 init_scf_run 11 5.9 0.002 0.002 5.636 5.636 scf_env_initial_rho_setup 11 6.9 0.001 0.001 5.634 5.634 fft_wrap_pw1pw2 1081 12.6 0.006 0.006 5.568 5.568 dbcsr_make_dense_low 4961 15.5 0.062 0.062 5.198 5.198 make_dense_data 4961 16.5 4.640 4.640 5.124 5.124 cp_fm_cholesky_decompose 22 10.9 5.103 5.103 5.103 5.103 multiply_cannon 1966 13.4 0.165 0.165 5.061 5.061 wfi_extrapolate 11 7.9 0.001 0.001 5.022 5.022 make_images 3932 14.4 1.967 1.967 5.002 5.002 ot_diis_step 96 11.5 0.003 0.003 4.907 4.907 fft_wrap_pw1pw2_140 439 13.2 0.466 0.466 4.794 4.794 multiply_cannon_loop 1966 14.4 0.034 0.034 4.618 4.618 multiply_cannon_multrec 1966 15.4 4.534 4.534 4.582 4.582 dbcsr_make_images_dense 3386 14.7 0.016 0.016 4.568 4.568 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 4.565 4.565 apply_single 107 13.6 0.000 0.000 4.565 4.565 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 4.470 4.470 cp_fm_cholesky_invert 11 10.9 4.369 4.369 4.369 4.369 dbcsr_copy 1855 11.9 0.236 0.236 3.799 3.799 qs_env_update_s_mstruct 11 6.9 0.000 0.000 3.792 3.792 dbcsr_complete_redistribute 317 12.2 1.952 1.952 3.777 3.777 dbcsr_copy_into_existing 22 7.9 3.533 3.533 3.533 3.533 build_core_hamiltonian_matrix_ 11 4.9 0.001 0.001 3.525 3.525 qs_create_task_list 11 7.9 0.000 0.000 3.380 3.380 generate_qs_task_list 11 8.9 2.411 2.411 3.379 3.379 density_rs2pw 107 9.7 0.005 0.005 3.372 3.372 copy_dbcsr_to_fm 147 11.2 0.002 0.002 3.073 3.073 build_core_hamiltonian_matrix 11 6.9 0.001 0.001 2.757 2.757 fft3d_s 1082 14.6 2.737 2.737 2.742 2.742 qs_ot_get_p 107 10.4 0.001 0.001 2.666 2.666 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.396 2.396 ------------------------------------------------------------------------------- From /workspace/artifacts/H2O-64_nonortho_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.008 0.021 76.041 76.052 qs_mol_dyn_low 1 2.0 0.003 0.004 75.937 75.942 qs_forces 11 3.9 0.001 0.001 75.883 75.885 qs_energies 11 4.9 0.001 0.001 70.789 70.791 scf_env_do_scf 11 5.9 0.000 0.002 65.556 65.560 scf_env_do_scf_inner_loop 96 6.5 0.003 0.018 60.791 60.792 velocity_verlet 10 3.0 0.002 0.003 44.398 44.399 rebuild_ks_matrix 107 8.3 0.000 0.001 32.386 32.450 qs_ks_build_kohn_sham_matrix 107 9.3 0.014 0.015 32.385 32.449 qs_rho_update_rho_low 107 7.7 0.001 0.001 28.747 28.762 calculate_rho_elec 107 8.7 0.027 0.028 28.746 28.761 qs_ks_update_qs_env 107 7.6 0.001 0.001 28.498 28.556 sum_up_and_integrate 107 10.3 0.033 0.039 28.407 28.439 integrate_v_rspace 107 11.3 0.004 0.005 28.374 28.410 grid_collocate_task_list 107 9.7 23.726 25.225 23.726 25.225 grid_integrate_task_list 107 12.3 24.239 24.706 24.239 24.706 dbcsr_multiply_generic 1966 12.4 0.069 0.071 12.280 12.407 qs_scf_new_mos 96 7.5 0.001 0.001 9.585 9.648 qs_scf_loop_do_ot 96 8.5 0.001 0.001 9.584 9.648 multiply_cannon 1966 13.4 0.125 0.133 9.012 9.378 ot_scf_mini 96 9.5 0.002 0.002 8.986 9.052 multiply_cannon_loop 1966 14.4 0.086 0.095 8.531 8.866 mp_waitall_1 146670 16.2 7.469 7.860 7.469 7.860 rs_pw_transfer 878 11.9 0.011 0.013 5.488 6.176 multiply_cannon_metrocomm3 15728 15.4 0.033 0.035 4.820 5.369 density_rs2pw 107 9.7 0.005 0.005 4.664 5.343 ot_mini 96 10.5 0.001 0.001 5.214 5.289 init_scf_loop 11 6.9 0.000 0.000 4.750 4.750 init_scf_run 11 5.9 0.000 0.004 4.082 4.082 scf_env_initial_rho_setup 11 6.9 0.000 0.004 4.081 4.082 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 4.044 4.052 wfi_extrapolate 11 7.9 0.001 0.001 3.713 3.713 mp_waitany 8968 13.7 2.757 3.528 2.757 3.528 pw_transfer 1295 11.6 0.078 0.091 3.262 3.350 fft_wrap_pw1pw2 1081 12.6 0.008 0.009 3.116 3.195 potential_pw2rs 107 12.3 0.007 0.007 3.163 3.190 multiply_cannon_multrec 15728 15.4 2.914 3.089 2.923 3.098 rs_pw_transfer_RS2PW_140 118 11.5 0.164 0.173 2.316 3.019 fft_wrap_pw1pw2_140 439 13.2 0.245 0.285 2.624 2.782 qs_ot_get_derivative 96 11.5 0.001 0.001 2.645 2.709 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 2.501 2.575 apply_single 107 13.6 0.000 0.000 2.501 2.575 ot_diis_step 96 11.5 0.003 0.003 2.548 2.548 fft3d_ps 1081 14.6 1.128 1.303 2.291 2.368 make_m2s 3932 13.4 0.042 0.047 2.225 2.277 make_images 3932 14.4 0.107 0.110 1.927 1.982 mp_alltoall_d11v 1998 13.7 1.158 1.829 1.158 1.829 rs_gather_matrices 107 12.3 0.080 0.088 0.930 1.585 ------------------------------------------------------------------------------- Plot: name="H2O-64_nonortho_timings_32omp", title="Timings of H2O-64_nonortho with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="rest", label="rest", y=47.40199999999999, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=29.299, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=25.92, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=5.103, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="make_dense_data", label="make_dense_data", y=4.64, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=4.534, 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=14.935999999999993, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=23.726, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=24.239, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="make_dense_data", label="make_dense_data", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=2.914, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitany", label="mp_waitany", y=2.757, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=7.469, 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 0.206 0.206 120.013 120.013 qs_energies 1 2.0 0.000 0.000 119.120 119.120 scf_env_do_scf 1 3.0 0.000 0.000 117.864 117.864 qs_ks_update_qs_env 8 5.0 0.000 0.000 111.921 111.921 rebuild_ks_matrix 7 6.0 0.000 0.000 111.863 111.863 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.001 111.863 111.863 hfx_ks_matrix 7 8.0 0.000 0.000 101.507 101.507 integrate_four_center 7 9.0 1.687 1.687 101.459 101.459 integrate_four_center_main 7 10.0 1.019 1.019 93.146 93.146 integrate_four_center_bin 449 11.0 92.127 92.127 92.127 92.127 scf_env_do_scf_inner_loop 7 4.0 0.001 0.001 64.465 64.465 init_scf_loop 1 4.0 0.000 0.000 53.385 53.385 integrate_four_center_load 7 10.0 0.000 0.000 6.383 6.383 hfx_load_balance 1 11.0 0.008 0.008 6.382 6.382 qs_vxc_create 14 8.0 0.000 0.000 3.529 3.529 xc_vxc_pw_create 14 9.0 0.146 0.146 3.529 3.529 hfx_load_balance_count 1 12.0 3.183 3.183 3.183 3.183 hfx_load_balance_bin 1 12.0 3.175 3.175 3.175 3.175 prepare_preconditioner 1 5.0 0.000 0.000 2.915 2.915 make_preconditioner 1 6.0 0.000 0.000 2.915 2.915 calculate_rho_elec 15 7.4 0.121 0.121 2.899 2.899 admm_mo_calc_rho_aux 7 8.0 0.000 0.000 2.840 2.840 xc_rho_set_and_dset_create 14 10.0 0.123 0.123 2.628 2.628 ------------------------------------------------------------------------------- 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 0.281 0.307 105.647 105.662 qs_energies 1 2.0 0.000 0.000 105.229 105.237 scf_env_do_scf 1 3.0 0.000 0.000 104.872 104.872 qs_ks_update_qs_env 8 5.0 0.000 0.000 102.655 102.656 rebuild_ks_matrix 7 6.0 0.000 0.000 102.645 102.646 qs_ks_build_kohn_sham_matrix 7 7.0 0.002 0.002 102.645 102.646 hfx_ks_matrix 7 8.0 0.000 0.000 96.672 96.673 integrate_four_center 7 9.0 0.061 0.367 96.661 96.663 integrate_four_center_main 7 10.0 0.004 0.004 87.968 89.848 integrate_four_center_bin 448 11.0 87.964 89.844 87.964 89.844 scf_env_do_scf_inner_loop 7 4.0 0.000 0.002 59.693 59.694 init_scf_loop 1 4.0 0.000 0.000 45.177 45.177 integrate_four_center_load 7 10.0 0.000 0.000 5.903 5.904 hfx_load_balance 1 11.0 0.001 0.001 5.903 5.904 mp_sync 70 11.3 2.052 3.594 2.052 3.594 hfx_load_balance_bin 1 12.0 2.904 2.955 2.904 2.955 hfx_load_balance_count 1 12.0 2.905 2.946 2.905 2.946 qs_vxc_create 14 8.0 0.000 0.000 2.596 2.596 xc_vxc_pw_create 14 9.0 0.008 0.009 2.596 2.596 xc_rho_set_and_dset_create 14 10.0 0.013 0.015 2.028 2.174 ------------------------------------------------------------------------------- Plot: name="H2O-hyb_timings_32omp", title="Timings of H2O-hyb with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="H2O-hyb_timings_32omp", name="rest", label="rest", y=18.616, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_bin", label="integrate_four_center_bin", y=92.127, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_count", label="hfx_load_balance_count", y=3.183, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=3.175, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center", label="integrate_four_center", y=1.687, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_main", label="integrate_four_center_main", y=1.019, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="CP2K", label="CP2K", y=0.206, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="mp_sync", label="mp_sync", y=0.0, yerr=0.0 Plot: name="H2O-hyb_timings_32mpi", title="Timings of H2O-hyb with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="H2O-hyb_timings_32mpi", name="rest", label="rest", y=9.475999999999985, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center_bin", label="integrate_four_center_bin", y=87.964, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_count", label="hfx_load_balance_count", y=2.905, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=2.904, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center", label="integrate_four_center", y=0.061, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center_main", label="integrate_four_center_main", y=0.004, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="CP2K", label="CP2K", y=0.281, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="mp_sync", label="mp_sync", y=2.052, 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 0.019 0.019 87.298 87.298 qs_energies 1 2.0 0.000 0.000 86.863 86.863 mp2_main 1 3.0 0.000 0.000 83.567 83.567 mp2_gpw_main 1 4.0 0.000 0.000 83.436 83.436 rpa_ri_compute_en 1 5.0 0.000 0.000 79.285 79.285 rpa_num_int 1 6.0 0.001 0.001 79.279 79.279 compute_mat_P_omega 1 7.0 0.003 0.003 67.816 67.816 compute_mat_P_omega_contract 10 8.0 9.767 9.767 67.586 67.586 dbt_total 2336 9.6 0.015 0.015 52.667 52.667 dbt_contract 787 11.0 0.042 0.042 44.534 44.534 dbt_tas_total 1149 12.2 0.317 0.317 42.963 42.963 dbt_tas_multiply 807 12.1 0.003 0.003 41.640 41.640 dbt_tas_dbm 807 14.1 0.004 0.004 34.659 34.659 dbm_multiply 807 16.1 34.646 34.646 34.646 34.646 dbt_tas_mm_1N 524 15.1 0.002 0.002 25.885 25.885 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 24.055 24.055 compute_mat_P_omega_calc_M_occ 250 9.0 9.744 9.744 19.137 19.137 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 8.221 8.221 dbt_tas_mm_2 251 15.0 0.002 0.002 7.084 7.084 dbt_copy 1103 10.7 0.100 0.100 6.786 6.786 compute_QP_energies 1 7.0 0.000 0.000 5.559 5.559 compute_self_energy_cubic_gw 1 8.0 0.055 0.055 5.558 5.558 contract_cubic_gw 21 9.0 0.000 0.000 4.439 4.439 dbt_tas_reserve_blocks_index 3261 14.3 0.157 0.157 4.155 4.155 mp2_ri_gpw_compute_in 1 5.0 0.001 0.001 4.143 4.143 dbm_reserve_blocks 3628 15.3 4.076 4.076 4.076 4.076 scf_env_do_scf 1 3.0 0.000 0.000 3.146 3.146 scf_env_do_scf_inner_loop 17 4.0 0.002 0.002 3.145 3.145 dbt_reserve_blocks_index 2280 13.1 0.069 0.069 3.130 3.130 dbt_reserve_blocks_index_array 2222 12.2 0.013 0.013 3.076 3.076 dbt_crop 1042 12.0 1.819 1.819 2.821 2.821 dbt_tas_copy 574 11.4 1.660 1.660 2.774 2.774 rpa_num_int_RPA_matrix_operati 10 7.0 0.000 0.000 2.570 2.570 compute_W_cubic_GW 10 7.0 0.017 0.017 2.404 2.404 convert_to_new_pgrid 2421 14.1 0.106 0.106 2.373 2.373 dbm_copy 1614 15.1 2.267 2.267 2.267 2.267 dbt_reshape 278 11.9 1.173 1.173 2.184 2.184 dbt_tas_reshape 367 15.0 0.008 0.008 2.084 2.084 get_2c_integrals 1 6.0 0.000 0.000 1.923 1.923 cp_fm_cholesky_decompose 14 8.1 1.896 1.896 1.896 1.896 compute_mat_P_omega_copy_M_occ 250 9.0 0.001 0.001 1.778 1.778 ------------------------------------------------------------------------------- From /workspace/artifacts/GW_PBE_4benzene_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.007 0.026 39.389 39.401 qs_energies 1 2.0 0.000 0.001 39.297 39.300 mp2_main 1 3.0 0.000 0.001 38.054 38.058 mp2_gpw_main 1 4.0 0.000 0.000 38.005 38.008 rpa_ri_compute_en 1 5.0 0.000 0.000 36.521 36.525 rpa_num_int 1 6.0 0.000 0.002 36.521 36.524 dbt_total 2336 9.6 0.016 0.017 32.400 32.403 compute_mat_P_omega 1 7.0 0.001 0.006 31.299 31.328 compute_mat_P_omega_contract 10 8.0 0.499 0.525 31.146 31.152 dbt_contract 787 11.0 0.034 0.036 23.914 23.920 dbt_tas_total 1149 12.2 0.068 0.074 21.383 21.385 dbt_tas_multiply 807 12.1 0.002 0.003 21.334 21.337 dbt_tas_dbm 807 14.1 0.004 0.005 15.996 16.002 dbm_multiply 807 16.1 12.432 13.393 12.432 13.393 compute_mat_P_omega_calc_M_occ 250 9.0 0.479 0.502 9.203 9.203 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 9.177 9.178 dbt_tas_mm_2 251 15.0 0.002 0.002 7.577 7.580 dbt_copy 1111 10.7 0.016 0.017 7.297 7.513 dbt_reshape 1098 11.7 2.741 2.868 6.965 7.199 mp_sync 8706 11.6 5.927 7.005 5.927 7.005 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 6.461 6.462 dbt_tas_mm_1N 524 15.1 0.002 0.002 5.781 6.221 dbt_communicate_buffer 1098 12.7 0.060 0.064 3.334 3.520 mp_waitall_2 3776 15.3 3.246 3.495 3.246 3.495 compute_QP_energies 1 7.0 0.000 0.000 3.283 3.285 compute_self_energy_cubic_gw 1 8.0 0.003 0.003 3.283 3.283 contract_cubic_gw 21 9.0 0.000 0.000 2.580 2.581 dbt_reserve_blocks_index 2849 13.1 0.076 0.084 2.055 2.299 dbt_reserve_blocks_index_array 2791 12.2 0.010 0.012 2.044 2.284 dbt_tas_reserve_blocks_index 3300 14.5 0.121 0.138 2.021 2.264 dbm_reserve_blocks 3696 15.4 2.012 2.251 2.012 2.251 dbt_crop 1042 12.0 1.083 1.211 1.717 1.868 mp2_ri_gpw_compute_in 1 5.0 0.000 0.001 1.481 1.482 dbt_tas_replicate 396 14.1 0.594 0.768 1.240 1.310 compute_mat_P_omega_copy_M_vir 250 9.0 0.001 0.001 1.245 1.247 scf_env_do_scf 1 3.0 0.000 0.000 1.198 1.198 scf_env_do_scf_inner_loop 17 4.0 0.001 0.003 1.197 1.198 compute_mat_P_omega_copy_M_occ 250 9.0 0.001 0.001 1.162 1.167 parallel_gemm_fm 105 8.4 0.000 0.000 1.153 1.165 parallel_gemm_fm_cosma 105 9.4 1.152 1.164 1.152 1.164 convert_to_new_pgrid 2421 14.1 0.028 0.032 1.013 1.152 dbm_copy 1608 15.1 0.978 1.116 0.978 1.116 mp_max_i 1994 9.8 0.706 0.937 0.706 0.937 compute_W_cubic_GW 10 7.0 0.001 0.001 0.889 0.897 dbm_add 807 14.1 0.755 0.827 0.755 0.827 ------------------------------------------------------------------------------- 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=25.625, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=34.646, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=9.767, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="compute_mat_P_omega_calc_M_occ", label="compute_mat_P_omega_calc_M_occ", y=9.744, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=4.076, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_copy", label="dbm_copy", y=2.267, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=1.173, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="mp_sync", label="mp_sync", y=0.0, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="mp_waitall_2", label="mp_waitall_2", y=0.0, yerr=0.0 Plot: name="GW_PBE_4benzene_timings_32mpi", title="Timings of GW_PBE_4benzene with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="rest", label="rest", y=11.075000000000003, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=12.432, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=0.499, 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=0.479, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=2.012, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_copy", label="dbm_copy", y=0.978, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=2.741, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_sync", label="mp_sync", y=5.927, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=3.246, 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 0.019 0.019 236.338 236.338 qs_forces 1 2.0 0.000 0.000 235.769 235.769 rebuild_ks_matrix 7 6.6 0.000 0.000 234.290 234.290 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.001 234.290 234.290 hfx_ks_matrix 7 8.6 0.000 0.000 232.342 232.342 hfx_ri_update_ks 7 9.6 0.000 0.000 190.263 190.263 hfx_ri_update_ks_Pmat 7 10.6 31.798 31.798 190.258 190.258 dbt_total 841 11.0 0.005 0.005 177.163 177.163 qs_energies 1 3.0 0.000 0.000 169.893 169.893 scf_env_do_scf 1 4.0 0.000 0.000 169.597 169.597 qs_ks_update_qs_env 8 6.0 0.000 0.000 168.465 168.465 dbt_contract 207 12.4 0.031 0.031 157.524 157.524 dbt_tas_total 375 13.4 1.524 1.524 156.440 156.440 dbt_tas_multiply 216 13.5 0.001 0.001 152.308 152.308 dbt_tas_dbm 216 15.5 0.001 0.001 139.475 139.475 dbm_multiply 216 17.5 139.471 139.471 139.471 139.471 hfx_ri_update_ks_Pmat_KS 63 11.6 0.001 0.001 133.251 133.251 dbt_tas_mm_2 91 16.5 0.001 0.001 124.665 124.665 scf_env_do_scf_inner_loop 6 5.0 0.001 0.001 106.117 106.117 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 65.829 65.829 init_scf_loop 2 5.0 0.000 0.000 63.477 63.477 hfx_ri_update_forces 1 7.0 1.707 1.707 42.075 42.075 hfx_ri_forces_Pmat_3c 1 8.0 4.788 4.788 24.513 24.513 dbt_copy 409 11.7 0.051 0.051 15.498 15.498 precalc_derivatives 1 8.0 2.191 2.191 13.497 13.497 dbt_reshape 132 13.2 6.580 6.580 10.766 10.766 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 10.099 10.099 dbt_tas_mm_3T 77 17.1 0.000 0.000 10.074 10.074 build_3c_derivatives 3 9.0 2.854 2.854 7.607 7.607 dbt_tas_reserve_blocks_index 1287 15.4 0.291 0.291 7.424 7.424 dbm_reserve_blocks 1461 16.2 7.366 7.366 7.366 7.366 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 7.225 7.225 dbt_reserve_blocks_index 818 14.4 0.102 0.102 5.828 5.828 dbt_reserve_blocks_index_array 795 13.4 0.008 0.008 5.751 5.751 dbt_tas_reshape 174 14.6 0.003 0.003 4.945 4.945 dbt_crop 372 13.7 2.978 2.978 4.907 4.907 ------------------------------------------------------------------------------- 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 48.613 48.621 qs_forces 1 2.0 0.000 0.000 48.464 48.464 rebuild_ks_matrix 7 6.6 0.000 0.000 47.747 47.748 qs_ks_build_kohn_sham_matrix 7 7.6 0.002 0.010 47.747 47.748 hfx_ks_matrix 7 8.6 0.000 0.000 46.742 46.748 dbt_total 841 11.0 0.006 0.006 41.448 41.450 dbt_contract 207 12.4 0.022 0.023 32.562 32.630 dbt_tas_total 375 13.4 0.052 0.175 30.233 30.234 dbt_tas_multiply 216 13.5 0.001 0.001 29.217 29.217 hfx_ri_update_ks 7 9.6 0.000 0.000 27.303 27.303 hfx_ri_update_ks_Pmat 7 10.6 1.311 1.408 27.302 27.302 qs_energies 1 3.0 0.000 0.000 25.643 25.643 scf_env_do_scf 1 4.0 0.000 0.001 25.488 25.488 qs_ks_update_qs_env 8 6.0 0.000 0.000 24.939 24.939 dbt_tas_dbm 216 15.5 0.001 0.001 23.347 23.350 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 22.810 22.810 dbm_multiply 216 17.5 20.317 21.930 20.317 21.930 hfx_ri_update_forces 1 7.0 0.061 0.064 19.439 19.445 hfx_ri_forces_Pmat_3c 1 8.0 0.189 0.201 14.522 14.537 scf_env_do_scf_inner_loop 6 5.0 0.000 0.001 14.172 14.172 hfx_ri_update_ks_Pmat_KS 63 11.6 0.001 0.001 12.888 12.888 init_scf_loop 2 5.0 0.000 0.000 11.315 11.315 dbt_tas_mm_2 91 16.5 0.001 0.001 10.769 10.769 mp_sync 2909 12.8 5.583 8.287 5.583 8.287 dbt_copy 421 11.8 0.011 0.013 7.216 7.531 dbt_tas_mm_3T 77 17.1 0.000 0.000 6.146 6.806 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 5.316 5.316 dbt_reshape 252 12.8 2.479 2.565 4.946 5.118 dbt_tas_mm_3N 37 15.4 0.000 0.000 4.372 4.597 precalc_derivatives 1 8.0 0.084 0.091 3.762 3.762 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 3.555 3.555 dbm_reserve_blocks 1477 16.3 2.816 3.260 2.816 3.260 dbt_tas_reserve_blocks_index 1302 15.5 0.221 0.246 2.788 3.211 dbt_crop 372 13.7 1.876 2.006 2.538 2.752 mp_waitall_2 1204 16.3 2.443 2.577 2.443 2.577 dbt_reserve_blocks_index 938 14.4 0.102 0.111 2.177 2.476 dbt_reserve_blocks_index_array 915 13.4 0.005 0.005 2.152 2.450 build_3c_derivatives 3 9.0 0.238 0.254 2.116 2.121 dbt_tas_replicate 175 15.2 0.717 0.765 1.785 1.852 hfx_ri_pre_scf_Pmat_RIx3C 9 13.0 0.000 0.000 1.828 1.832 dbt_communicate_buffer 252 13.8 0.012 0.012 1.657 1.732 dbt_tas_copy 169 12.8 0.865 0.897 1.558 1.731 convert_to_new_pgrid 648 15.5 0.034 0.068 1.440 1.721 hfx_ri_update_ks_Pmat_copy_2 63 11.6 0.000 0.000 1.550 1.550 dbm_copy 452 16.3 1.257 1.522 1.257 1.522 dbt_tas_communicate_buffer 352 16.4 0.013 0.014 1.028 1.086 ------------------------------------------------------------------------------- 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=46.33499999999998, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=139.471, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=31.798, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=7.366, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=6.58, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_forces_Pmat_3c", label="hfx_ri_forces_Pmat_3c", y=4.788, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="mp_waitall_2", label="mp_waitall_2", y=0.0, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="mp_sync", label="mp_sync", y=0.0, yerr=0.0 Plot: name="RI-HFX_H2O-32_timings_32mpi", title="Timings of RI-HFX_H2O-32 with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="rest", label="rest", y=13.475000000000001, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=20.317, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=1.311, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=2.816, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=2.479, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_forces_Pmat_3c", label="hfx_ri_forces_Pmat_3c", y=0.189, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.443, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_sync", label="mp_sync", y=5.583, yerr=0.0 Running RI-MP2_ammonia.inp with 1 threads and 32 ranks... done. Running RI-MP2_ammonia.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/RI-MP2_ammonia_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.015 0.015 178.091 178.091 qs_energies 1 2.0 0.000 0.000 177.899 177.899 mp2_main 1 3.0 0.000 0.000 172.760 172.760 mp2_gpw_main 1 4.0 0.001 0.001 172.300 172.300 mp2_ri_gpw_compute_in 1 5.0 0.389 0.389 125.785 125.785 mp2_ri_gpw_compute_in_loop 1 6.0 0.014 0.014 114.229 114.229 mp2_eri_3c_integrate_gpw 2656 7.0 0.016 0.016 81.339 81.339 integrate_v_rspace 2666 8.0 0.692 0.692 67.973 67.973 grid_integrate_task_list 2666 9.0 65.206 65.206 65.206 65.206 mp2_ri_gpw_compute_en 1 5.0 0.087 0.087 46.490 46.490 mp2_ri_gpw_compute_en_RI_loop 1 6.0 9.890 9.890 44.597 44.597 mp2_ri_gpw_compute_en_expansio 2080 7.0 2.302 2.302 26.656 26.656 local_gemm 2080 8.0 24.355 24.355 24.355 24.355 dbcsr_multiply_generic 5322 8.0 0.211 0.211 22.602 22.602 ao_to_mo_and_store_B_mult_1 2656 7.0 0.012 0.012 22.583 22.583 pw_transfer 63872 10.6 1.097 1.097 12.348 12.348 calculate_wavefunction 2656 8.0 8.244 8.244 12.032 12.032 multiply_cannon 5322 9.0 0.491 0.491 11.655 11.655 get_2c_integrals 1 6.0 0.000 0.000 11.165 11.165 fft_wrap_pw1pw2 53228 11.4 0.121 0.121 10.996 10.996 compute_2c_integrals 1 7.0 0.006 0.006 10.240 10.240 compute_2c_integrals_loop_lm 1 8.0 0.011 0.011 10.219 10.219 mp2_eri_2c_integrate_gpw 1 9.0 3.033 3.033 10.208 10.208 ao_to_mo_and_store_B_E_Ex_1 2656 7.0 2.793 2.793 10.196 10.196 multiply_cannon_loop 5322 10.0 0.122 0.122 10.187 10.187 make_m2s 10644 9.0 0.067 0.067 8.576 8.576 multiply_cannon_multrec 5322 11.0 8.468 8.468 8.511 8.511 make_images 10644 10.0 3.254 3.254 8.233 8.233 copy_dbcsr_to_fm 2679 8.0 0.031 0.031 7.953 7.953 fft_wrap_pw1pw2_20 21271 12.4 0.495 0.495 7.771 7.771 fft3d_s 53229 13.4 6.715 6.715 6.753 6.753 dbcsr_complete_redistribute 2689 9.0 1.245 1.245 6.190 6.190 mp2_ri_gpw_compute_en_ener 2080 7.0 5.970 5.970 5.970 5.970 dbcsr_finalize 10708 9.5 0.208 0.208 5.552 5.552 dbcsr_merge_all 8011 10.3 3.719 3.719 4.856 4.856 scf_env_do_scf 1 3.0 0.000 0.000 4.696 4.696 scf_env_do_scf_inner_loop 10 4.0 0.001 0.001 4.696 4.696 potential_pw2rs 5322 10.0 0.152 0.152 4.123 4.123 ------------------------------------------------------------------------------- From /workspace/artifacts/RI-MP2_ammonia_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.007 0.022 37.737 37.749 qs_energies 1 2.0 0.000 0.000 37.501 37.502 mp2_main 1 3.0 0.000 0.001 35.297 35.297 mp2_gpw_main 1 4.0 0.001 0.002 35.174 35.174 mp2_ri_gpw_compute_in 1 5.0 0.053 0.053 18.498 18.855 mp2_ri_gpw_compute_in_loop 1 6.0 0.001 0.001 17.247 17.588 mp2_ri_gpw_compute_en 1 5.0 0.154 0.166 16.586 16.845 mp2_ri_gpw_compute_en_RI_loop 1 6.0 0.901 1.092 15.585 15.591 mp2_eri_3c_integrate_gpw 83 7.0 0.001 0.001 15.034 15.309 integrate_v_rspace 93 8.1 0.111 0.119 14.881 15.159 grid_integrate_task_list 93 9.1 14.568 14.844 14.568 14.844 mp2_ri_gpw_compute_en_expansio 65 7.0 0.111 0.135 11.703 11.829 local_gemm 65 8.0 11.593 11.712 11.593 11.712 mp2_ri_gpw_compute_en_comm 17 7.0 0.070 0.084 2.583 3.162 mp_sendrecv_dm3 1054 8.0 2.032 2.732 2.032 2.732 dbcsr_multiply_generic 176 8.0 0.009 0.010 1.904 2.092 scf_env_do_scf 1 3.0 0.000 0.000 2.083 2.084 scf_env_do_scf_inner_loop 10 4.0 0.000 0.001 2.083 2.084 ao_to_mo_and_store_B_mult_1 83 7.0 0.001 0.001 1.886 2.075 get_2c_integrals 1 6.0 0.000 0.000 1.180 1.207 multiply_cannon 176 9.0 0.018 0.019 1.131 1.191 multiply_cannon_loop 176 10.0 0.002 0.002 1.067 1.127 qs_scf_new_mos 10 5.0 0.000 0.000 1.081 1.086 eigensolver 11 5.8 0.001 0.001 1.057 1.058 multiply_cannon_multrec 246 11.0 0.915 0.949 0.920 0.954 compute_2c_integrals 1 7.0 0.002 0.004 0.886 0.901 cp_fm_diag_elpa 11 6.8 0.000 0.000 0.884 0.886 cp_fm_redistribute_end 11 7.8 0.331 0.876 0.342 0.879 make_m2s 352 9.0 0.003 0.004 0.732 0.862 cp_fm_diag_elpa_base 11 7.8 0.520 0.836 0.531 0.852 make_images 352 10.0 0.056 0.061 0.718 0.848 compute_2c_integrals_loop_lm 1 8.0 0.002 0.004 0.790 0.816 mp2_eri_2c_integrate_gpw 1 9.0 0.213 0.226 0.788 0.815 pw_transfer 2120 10.5 0.045 0.046 0.800 0.808 ------------------------------------------------------------------------------- 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=61.928, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=65.206, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="local_gemm", label="local_gemm", y=24.355, 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=9.89, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=8.468, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="calculate_wavefunction", label="calculate_wavefunction", y=8.244, 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=7.7280000000000015, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=14.568, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="local_gemm", label="local_gemm", y=11.593, 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=0.901, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=0.915, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="calculate_wavefunction", label="calculate_wavefunction", y=0.0, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="mp_sendrecv_dm3", label="mp_sendrecv_dm3", y=2.032, 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 0.106 0.106 133.021 133.021 qs_energies 1 2.0 0.000 0.000 131.583 131.583 scf_env_do_scf 1 3.0 0.000 0.000 124.515 124.515 scf_env_do_scf_inner_loop 15 4.0 0.002 0.002 124.515 124.515 qs_ks_update_qs_env 15 5.0 0.000 0.000 51.637 51.637 rebuild_ks_matrix 15 6.0 0.000 0.000 51.420 51.420 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.002 51.420 51.420 qs_scf_new_mos 15 5.0 0.000 0.000 46.140 46.140 eigensolver 15 6.0 0.002 0.002 37.978 37.978 qs_vxc_create 15 8.0 0.032 0.032 34.944 34.944 calculate_dispersion_nonloc 15 9.0 7.106 7.106 30.509 30.509 cp_fm_diag_elpa 15 7.0 0.000 0.000 24.935 24.935 cp_fm_diag_elpa_base 15 8.0 22.495 22.495 24.934 24.934 pw_transfer 1191 10.0 0.068 0.068 23.946 23.946 qs_rho_update_rho_low 16 5.0 0.000 0.000 23.756 23.756 calculate_rho_elec 16 6.0 0.217 0.217 23.756 23.756 fft_wrap_pw1pw2 1086 11.0 0.009 0.009 23.755 23.755 grid_collocate_task_list 16 7.0 22.293 22.293 22.293 22.293 fft_wrap_pw1pw2_150 765 12.0 3.682 3.682 17.393 17.393 sum_up_and_integrate 15 8.0 0.115 0.115 15.289 15.289 integrate_v_rspace 15 9.0 0.020 0.020 15.175 15.175 grid_integrate_task_list 15 10.0 14.636 14.636 14.636 14.636 cp_fm_cholesky_restore 45 7.0 10.787 10.787 10.787 10.787 fft3d_s 1087 13.0 10.639 10.639 10.648 10.648 pw_scatter_s 585 13.1 7.343 7.343 7.343 7.343 fft_wrap_pw1pw2_200 197 12.3 0.766 0.766 6.160 6.160 dbcsr_complete_redistribute 46 8.3 2.276 2.276 5.806 5.806 copy_dbcsr_to_fm 16 5.9 0.001 0.001 5.752 5.752 cp_fm_upper_to_full 30 8.0 4.694 4.694 4.694 4.694 vdW_energy 15 10.0 4.452 4.452 4.452 4.452 xc_vxc_pw_create 15 9.0 0.217 0.217 4.403 4.403 gspace_mixing 14 5.0 0.171 0.171 4.291 4.291 broyden_mixing 14 6.0 3.657 3.657 3.657 3.657 init_scf_run 1 3.0 0.000 0.000 3.368 3.368 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 3.151 3.151 xc_pw_derive 90 11.0 0.001 0.001 2.847 2.847 calculate_dm_sparse 15 6.0 0.019 0.019 2.774 2.774 cp_dbcsr_plus_fm_fm_t_native 15 7.0 0.000 0.000 2.687 2.687 ------------------------------------------------------------------------------- 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 0.015 0.030 64.076 64.088 qs_energies 1 2.0 0.000 0.001 63.799 63.804 scf_env_do_scf 1 3.0 0.000 0.001 59.450 59.451 scf_env_do_scf_inner_loop 15 4.0 0.001 0.004 59.450 59.451 qs_ks_update_qs_env 15 5.0 0.000 0.000 24.905 24.911 rebuild_ks_matrix 15 6.0 0.000 0.000 24.867 24.874 qs_ks_build_kohn_sham_matrix 15 7.0 0.003 0.003 24.867 24.874 qs_rho_update_rho_low 16 5.0 0.000 0.000 21.812 21.817 calculate_rho_elec 16 6.0 0.007 0.007 21.812 21.817 grid_collocate_task_list 16 7.0 20.785 21.025 20.785 21.025 sum_up_and_integrate 15 8.0 0.013 0.019 15.019 15.062 integrate_v_rspace 15 9.0 0.001 0.001 15.005 15.054 grid_integrate_task_list 15 10.0 14.170 14.288 14.170 14.288 qs_scf_new_mos 15 5.0 0.000 0.001 13.451 13.468 eigensolver 15 6.0 0.001 0.002 12.444 12.486 qs_vxc_create 15 8.0 0.001 0.001 9.543 9.561 cp_fm_diag_elpa 15 7.0 0.000 0.000 8.979 8.982 cp_fm_diag_elpa_base 15 8.0 8.822 8.852 8.976 8.976 calculate_dispersion_nonloc 15 9.0 0.957 0.970 7.619 7.637 pw_transfer 1191 10.0 0.088 0.099 7.099 7.198 fft_wrap_pw1pw2 1086 11.0 0.012 0.014 6.917 7.043 fft3d_ps 1086 13.0 2.531 2.769 5.190 5.452 fft_wrap_pw1pw2_150 765 12.0 0.276 0.322 4.380 4.413 cp_fm_cholesky_restore 45 7.0 3.285 3.341 3.285 3.341 mp_alltoall_z22v 1086 15.0 2.076 2.718 2.076 2.718 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 2.634 2.634 build_core_hamiltonian_matrix 1 4.0 0.000 0.000 2.311 2.531 fft_wrap_pw1pw2_200 197 12.3 0.197 0.244 2.414 2.514 xc_vxc_pw_create 15 9.0 0.015 0.020 1.923 1.957 x_to_yz 585 14.1 0.342 0.367 1.411 1.698 yz_to_x 501 13.9 0.217 0.263 1.223 1.554 init_scf_run 1 3.0 0.000 0.001 1.492 1.492 build_core_ppnl 1 5.0 1.346 1.478 1.346 1.478 vdW_energy 15 10.0 1.388 1.461 1.388 1.461 scf_env_initial_rho_setup 1 4.0 0.000 0.000 1.392 1.392 xc_pw_derive 90 11.0 0.001 0.001 1.289 1.371 ------------------------------------------------------------------------------- Plot: name="diag_cu144_broy_timings_32omp", title="Timings of diag_cu144_broy with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="diag_cu144_broy_timings_32omp", name="rest", label="rest", y=52.17099999999999, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=22.495, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=22.293, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=14.636, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=10.787, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="fft3d_s", label="fft3d_s", y=10.639, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="fft3d_ps", label="fft3d_ps", y=0.0, yerr=0.0 Plot: name="diag_cu144_broy_timings_32mpi", title="Timings of diag_cu144_broy with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="rest", label="rest", y=14.482999999999997, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=8.822, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=20.785, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=14.17, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=3.285, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="fft3d_s", label="fft3d_s", y=0.0, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=2.531, 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 0.075 270.643 270.643 qs_energies 1 2.0 0.000 0.000 270.506 270.506 ls_scf 1 3.0 0.000 0.000 269.245 269.245 ls_scf_main 1 4.0 0.002 0.002 259.658 259.658 density_matrix_trs4 11 5.0 0.013 0.013 162.509 162.509 ls_scf_dm_to_ks 11 5.0 0.000 0.000 91.757 91.757 matrix_ls_to_qs 11 6.0 0.000 0.000 88.362 88.362 dbcsr_multiply_generic 185 6.1 0.850 0.850 78.584 78.584 arnoldi_extremal 12 6.1 0.000 0.000 72.500 72.500 arnoldi_normal_ev 12 7.1 0.015 0.015 72.500 72.500 build_subspace 23 8.1 0.078 0.078 70.993 70.993 dbcsr_matrix_vector_mult 652 9.0 0.179 0.179 70.432 70.432 dbcsr_matrix_vector_mult_local 652 10.0 68.907 68.907 68.917 68.917 dbcsr_copy_into_existing 11 7.0 48.583 48.583 48.584 48.584 multiply_cannon 185 7.1 0.305 0.305 48.172 48.172 dbcsr_complete_redistribute 23 7.5 31.500 31.500 43.617 43.617 matrix_decluster 11 7.0 0.000 0.000 39.777 39.777 multiply_cannon_loop 185 8.1 0.252 0.252 35.472 35.472 make_m2s 370 7.1 0.038 0.038 25.605 25.605 multiply_cannon_multrec 185 9.1 24.598 24.598 24.629 24.629 make_images 370 8.1 10.739 10.739 23.877 23.877 dbcsr_finalize 646 7.5 0.206 0.206 16.023 16.023 dbcsr_merge_all 597 8.5 2.605 2.605 14.861 14.861 setup_rec_index_2d 370 8.1 12.292 12.292 12.292 12.292 tree_to_linear_d 110 9.4 10.953 10.953 10.953 10.953 dbcsr_sort_indices 1103 9.9 10.645 10.645 10.645 10.645 calculate_norms 370 9.1 10.591 10.591 10.591 10.591 quick_finalize 395 10.0 0.396 0.396 9.222 9.222 ls_scf_init_scf 1 4.0 0.000 0.000 8.850 8.850 dbcsr_special_finalize 370 9.1 0.002 0.002 8.528 8.528 ls_scf_init_matrix_S 1 5.0 0.000 0.000 8.508 8.508 matrix_sqrt_Newton_Schulz 1 6.0 0.001 0.001 7.823 7.823 matrix_qs_to_ls 12 5.1 0.000 0.000 5.619 5.619 matrix_cluster 12 6.1 0.000 0.000 5.619 5.619 ------------------------------------------------------------------------------- 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 0.008 0.022 71.860 71.872 qs_energies 1 2.0 0.000 0.000 71.761 71.761 ls_scf 1 3.0 0.000 0.000 71.707 71.707 ls_scf_main 1 4.0 0.001 0.010 68.909 68.910 density_matrix_trs4 11 5.0 0.007 0.022 66.218 66.323 dbcsr_multiply_generic 185 6.1 0.064 0.085 62.683 62.893 multiply_cannon 185 7.1 0.036 0.039 52.317 52.908 multiply_cannon_loop 185 8.1 0.124 0.139 49.729 50.671 multiply_cannon_multrec 1480 9.1 30.733 33.483 31.038 33.790 mp_waitall_1 11936 10.3 15.960 18.763 15.960 18.763 multiply_cannon_metrocomm3 1480 9.1 0.014 0.018 9.182 13.716 make_m2s 370 7.1 0.035 0.037 7.269 7.346 make_images 370 8.1 0.657 0.691 7.135 7.215 multiply_cannon_metrocomm1 1480 9.1 0.008 0.010 3.861 7.179 calculate_norms 2960 9.1 5.461 6.170 5.461 6.170 make_images_data 370 9.1 0.009 0.011 3.174 3.444 hybrid_alltoall_any 393 9.9 0.201 0.958 2.745 2.922 arnoldi_extremal 12 6.1 0.000 0.000 2.699 2.720 arnoldi_normal_ev 12 7.1 0.001 0.004 2.699 2.720 build_subspace 23 8.1 0.021 0.026 2.590 2.592 mp_sum_l 1119 5.6 1.973 2.559 1.973 2.559 ls_scf_dm_to_ks 11 5.0 0.000 0.000 2.324 2.387 dbcsr_matrix_vector_mult 652 9.0 0.010 0.047 2.188 2.253 dbcsr_complete_redistribute 23 7.5 1.274 1.330 2.084 2.188 matrix_ls_to_qs 11 6.0 0.000 0.000 2.027 2.133 ls_scf_init_scf 1 4.0 0.000 0.000 2.120 2.121 ls_scf_init_matrix_S 1 5.0 0.000 0.000 2.095 2.101 matrix_decluster 11 7.0 0.000 0.000 1.877 1.986 make_images_pack 370 9.1 1.792 1.922 1.796 1.925 matrix_sqrt_Newton_Schulz 1 6.0 0.000 0.001 1.918 1.921 dbcsr_matrix_vector_mult_local 652 10.0 1.790 1.894 1.792 1.896 buffer_matrices_ensure_size 370 8.1 1.433 1.671 1.433 1.671 dbcsr_finalize 646 7.5 0.008 0.009 1.523 1.648 dbcsr_multiply_generic_mpsum_f 137 7.1 0.000 0.000 1.076 1.530 ------------------------------------------------------------------------------- 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=74.17199999999994, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=68.907, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_copy_into_existing", label="dbcsr_copy_into_existing", y=48.583, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_complete_redistribute", label="dbcsr_complete_redistribute", y=31.5, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=24.598, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="setup_rec_index_2d", label="setup_rec_index_2d", y=12.292, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="calculate_norms", label="calculate_norms", y=10.591, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="make_images_pack", label="make_images_pack", y=0.0, yerr=0.0 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=12.877000000000002, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=1.79, 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=1.274, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=30.733, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="setup_rec_index_2d", label="setup_rec_index_2d", y=0.0, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="calculate_norms", label="calculate_norms", y=5.461, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=15.96, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="make_images_pack", label="make_images_pack", y=1.792, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=1.973, 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 74.050 74.050 lib_test 1 2.0 0.000 0.000 74.041 74.041 dbcsr_run_tests 3 3.0 0.002 0.002 74.041 74.041 test_multiplies_multiproc 3 4.0 0.001 0.001 57.573 57.573 dbcsr_redistribute 9 5.0 36.942 36.942 38.572 38.572 dbcsr_multiply_generic 9 5.0 0.003 0.003 17.611 17.611 dbcsr_make_random_matrix 9 4.0 13.106 13.106 16.359 16.359 multiply_cannon 9 6.0 0.002 0.002 12.568 12.568 multiply_cannon_loop 9 7.0 0.033 0.033 12.204 12.204 multiply_cannon_multrec 9 8.0 12.171 12.171 12.172 12.172 dbcsr_finalize 27 5.7 0.044 0.044 6.007 6.007 dbcsr_merge_all 18 6.5 2.129 2.129 5.207 5.207 dbcsr_data_release 975 7.6 2.836 2.836 2.836 2.836 tree_to_linear_d 9 7.0 2.031 2.031 2.031 2.031 make_m2s 18 6.0 0.001 0.001 1.700 1.700 make_images 18 7.0 0.576 0.576 1.640 1.640 ------------------------------------------------------------------------------- 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 0.011 19.392 19.396 lib_test 1 2.0 0.000 0.000 19.359 19.378 dbcsr_run_tests 3 3.0 0.000 0.001 19.358 19.378 test_multiplies_multiproc 3 4.0 0.000 0.003 18.482 18.564 dbcsr_multiply_generic 9 5.0 0.001 0.001 17.079 17.183 multiply_cannon 9 6.0 0.002 0.002 15.086 15.480 multiply_cannon_loop 9 7.0 0.002 0.003 14.770 15.211 multiply_cannon_multrec 72 8.0 12.297 12.959 12.298 12.960 mp_waitall_1 576 9.2 2.822 3.410 2.822 3.410 multiply_cannon_metrocomm1 72 8.0 0.001 0.001 2.203 2.845 mp_sum_l 390 2.5 0.513 0.945 0.513 0.945 dbcsr_multiply_generic_mpsum_f 9 6.0 0.000 0.000 0.508 0.940 dbcsr_make_random_matrix 9 4.0 0.694 0.706 0.843 0.878 dbcsr_data_release 444 7.6 0.763 0.862 0.763 0.862 dbcsr_finalize 27 5.7 0.000 0.000 0.761 0.860 make_m2s 18 6.0 0.001 0.001 0.739 0.777 make_images 18 7.0 0.022 0.024 0.736 0.773 dbcsr_destroy 111 5.9 0.000 0.001 0.609 0.736 multiply_cannon_metrocomm3 72 8.0 0.000 0.000 0.261 0.714 dbcsr_merge_all 18 6.5 0.115 0.137 0.605 0.712 dbcsr_redistribute 9 5.0 0.252 0.301 0.441 0.478 make_images_data 18 8.0 0.001 0.001 0.393 0.475 dbcsr_data_copy_aa2 18 7.5 0.366 0.449 0.366 0.449 hybrid_alltoall_any 18 9.0 0.031 0.157 0.348 0.435 ------------------------------------------------------------------------------- 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=6.8659999999999854, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_redistribute", label="dbcsr_redistribute", y=36.942, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=13.106, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=12.171, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_data_release", label="dbcsr_data_release", y=2.836, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_merge_all", label="dbcsr_merge_all", y=2.129, 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=1.9359999999999964, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_redistribute", label="dbcsr_redistribute", y=0.252, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=0.694, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=12.297, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_data_release", label="dbcsr_data_release", y=0.763, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_merge_all", label="dbcsr_merge_all", y=0.115, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=2.822, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=0.513, 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 0.054 0.054 133.627 133.627 qs_mol_dyn_low 1 2.0 0.003 0.003 132.188 132.188 velocity_verlet 5 3.0 0.004 0.004 107.665 107.665 qmmm_el_coupling 6 3.8 0.000 0.000 87.672 87.672 qmmm_elec_with_gaussian 6 4.8 0.014 0.014 87.668 87.668 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 87.009 87.009 qmmm_elec_gaussian_low_G 6 6.8 86.094 86.094 86.094 86.094 qs_forces 6 3.8 0.000 0.000 35.797 35.797 qs_energies 6 4.8 0.000 0.000 31.798 31.798 scf_env_do_scf 6 5.8 0.001 0.001 29.483 29.483 scf_env_do_scf_inner_loop 39 6.8 0.004 0.004 25.714 25.714 rebuild_ks_matrix 45 8.4 0.000 0.000 24.568 24.568 qs_ks_build_kohn_sham_matrix 45 9.4 0.005 0.005 24.568 24.568 qs_ks_update_qs_env 45 7.8 0.000 0.000 21.007 21.007 pw_transfer 966 12.3 0.056 0.056 17.630 17.630 fft_wrap_pw1pw2 801 13.6 0.006 0.006 17.409 17.409 fft_wrap_pw1pw2_150 507 15.2 2.333 2.333 16.971 16.971 qs_vxc_create 45 10.4 0.001 0.001 13.588 13.588 xc_vxc_pw_create 45 11.4 0.659 0.659 13.587 13.587 xc_pw_derive 270 13.4 0.002 0.002 9.675 9.675 fft3d_s 802 15.6 8.034 8.034 8.043 8.043 qs_rho_update_rho_low 45 7.9 0.000 0.000 7.481 7.481 calculate_rho_elec 45 8.9 0.563 0.563 7.481 7.481 xc_rho_set_and_dset_create 45 12.4 0.546 0.546 6.746 6.746 xc_pw_divergence 45 12.4 0.001 0.001 6.093 6.093 pw_scatter_s 429 15.8 5.615 5.615 5.615 5.615 qmmm_forces 6 3.8 0.001 0.001 5.535 5.535 qmmm_forces_with_gaussian 6 4.8 0.019 0.019 5.203 5.203 pw_integral_ab 2539 7.4 4.525 4.525 4.525 4.525 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 4.455 4.455 qs_ks_ddapc 45 10.4 0.001 0.001 4.251 4.251 init_scf_loop 6 6.8 0.000 0.000 3.764 3.764 qmmm_forces_gaussian_low_G 6 6.8 3.691 3.691 3.691 3.691 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 3.569 3.569 sum_up_and_integrate 45 10.4 0.361 0.361 3.556 3.556 grid_collocate_task_list 45 9.9 3.526 3.526 3.526 3.526 density_rs2pw 45 9.9 0.002 0.002 3.392 3.392 integrate_v_rspace 45 11.4 0.007 0.007 3.195 3.195 ------------------------------------------------------------------------------- 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 0.062 57.284 57.673 qs_mol_dyn_low 1 2.0 0.003 0.004 56.250 56.630 qs_forces 6 3.8 0.001 0.001 40.909 41.187 qs_energies 6 4.8 0.000 0.000 39.057 39.323 scf_env_do_scf 6 5.8 0.000 0.001 38.085 38.343 scf_env_do_scf_inner_loop 113 6.2 0.003 0.021 36.548 36.797 rebuild_ks_matrix 119 8.1 0.000 0.000 26.780 26.956 qs_ks_build_kohn_sham_matrix 119 9.1 0.016 0.020 26.779 26.956 qs_ks_update_qs_env 119 7.3 0.001 0.001 25.236 25.402 velocity_verlet 5 3.0 0.002 0.004 23.771 23.935 pw_transfer 2446 12.3 0.180 0.199 17.833 18.336 fft_wrap_pw1pw2 2059 13.4 0.023 0.026 17.423 17.963 fft_wrap_pw1pw2_150 1321 14.9 1.315 1.592 16.718 17.164 qs_vxc_create 119 10.1 0.003 0.004 14.098 14.193 xc_vxc_pw_create 119 11.1 0.151 0.216 14.095 14.190 fft3d_ps 2059 15.4 6.891 7.882 13.153 14.167 qs_rho_update_rho_low 119 7.3 0.001 0.001 11.115 11.190 calculate_rho_elec 119 8.3 0.049 0.055 11.114 11.190 xc_pw_derive 714 13.1 0.008 0.009 10.636 10.920 sum_up_and_integrate 119 10.1 0.088 0.123 9.343 9.385 integrate_v_rspace 119 11.1 0.003 0.004 9.255 9.299 qmmm_forces 6 3.8 0.002 0.002 7.904 7.958 qmmm_forces_with_gaussian 6 4.8 0.008 0.010 7.479 7.700 xc_pw_divergence 119 12.1 0.004 0.005 6.878 7.114 xc_rho_set_and_dset_create 119 12.1 0.366 0.467 6.845 7.019 rs_pw_transfer 988 11.5 0.012 0.014 6.496 6.683 qmmm_el_coupling 6 3.8 0.000 0.000 6.467 6.639 qmmm_elec_with_gaussian 6 4.8 0.003 0.004 6.465 6.637 density_rs2pw 119 9.3 0.006 0.007 6.106 6.298 mp_alltoall_z22v 2059 17.4 4.856 6.211 4.856 6.211 potential_pw2rs 119 12.1 0.007 0.007 5.328 5.364 grid_collocate_task_list 119 9.3 4.823 5.072 4.823 5.072 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 4.201 4.247 x_to_yz 1095 16.8 0.815 0.923 3.341 4.027 grid_integrate_task_list 119 12.1 3.667 3.872 3.667 3.872 yz_to_x 964 16.0 0.536 0.693 2.867 3.662 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 3.560 3.583 qmmm_forces_gaussian_low_G 6 6.8 3.450 3.492 3.450 3.492 qmmm_elec_gaussian_low_G 6 6.8 2.953 2.976 2.953 2.976 mp_waitany 4028 12.8 2.540 2.865 2.540 2.865 pw_restrict_s3 18 5.8 1.431 1.499 2.629 2.858 rs_pw_transfer_PW2RS_150 125 13.9 0.733 0.882 2.471 2.533 qmmm_elec_with_gaussian:spline 6 5.8 0.000 0.000 2.178 2.348 pw_prolongate_s3 18 6.8 1.192 1.237 2.178 2.348 rs_pw_transfer_RS2PW_150 125 11.2 0.615 0.745 1.976 2.157 qs_scf_new_mos 113 7.2 0.000 0.001 2.078 2.097 qs_scf_loop_do_ot 113 8.2 0.000 0.001 2.078 2.096 ot_scf_mini 113 9.2 0.001 0.001 1.993 2.011 qs_ks_ddapc 119 10.1 0.002 0.002 1.920 2.009 mp_waitall_1 188862 16.2 1.764 1.955 1.764 1.955 dbcsr_multiply_generic 2588 12.3 0.060 0.065 1.882 1.910 pw_gather_p 964 15.0 1.347 1.898 1.347 1.898 pw_integral_ab 2761 7.7 1.143 1.298 1.489 1.637 pw_scatter_p 1095 15.8 1.556 1.596 1.556 1.596 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 1.559 1.569 init_scf_loop 6 6.8 0.000 0.000 1.534 1.544 mp_sum_d 5814 12.2 0.907 1.308 0.907 1.308 mp_sum_dm3 33 5.7 1.255 1.305 1.255 1.305 ot_mini 113 10.2 0.000 0.001 1.221 1.234 pw_copy 1670 12.6 0.984 1.157 0.984 1.157 ------------------------------------------------------------------------------- Plot: name="MQAE_single_node_timings_32omp", title="Timings of MQAE_single_node with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="MQAE_single_node_timings_32omp", name="rest", label="rest", y=22.14200000000001, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=86.094, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_s", label="fft3d_s", y=8.034, 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=4.525, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.691, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=3.526, 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=29.500999999999998, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=2.953, 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=1.143, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.45, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=4.823, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=4.856, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=3.667, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=6.891, yerr=0.0 Summary: Performance test took 33 minutes. Status: OK Removing intermediate container 4fcf1d5fe814 ---> dedb3da76402 Step 41/42 : CMD cat $(find ./report.log -mmin +10) | sed '/^Summary:/ s/$/ (cached)/' ---> Running in 5f2e2f4b0f2d Removing intermediate container 5f2e2f4b0f2d ---> 579be217cc70 Step 42/42 : ENTRYPOINT [] ---> Running in 059d50f918ae Removing intermediate container 059d50f918ae ---> c766d00601f2 [Warning] One or more build-args [GIT_COMMIT_SHA] were not consumed Successfully built c766d00601f2 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: 2022-12-06 11:51:18+00:00