StartDate: 2023-06-10 19:15:19+00:00 CpuId: 32x AMD EPYC (3rd Gen) (Milan) [Zen 3], 7nm (SMT disabled) CommitSHA: 7c12bb00fd46e0ed47181f56d61ed417c5f84a01 CommitTime: 2023-06-10 15:35:29 +0200 CommitAuthor: Ole Schütt CommitSubject: Docs: Turn Sphinx warnings into errors #################### Building Image cp2k-perf-openmp #################### Dockerfile: /tools/docker/Dockerfile.test_performance Build-Path: / Build-Args: GIT_COMMIT_SHA=7c12bb00fd46e0ed47181f56d61ed417c5f84a01 Build-Cache: Yes Populating docker build cache... done. DEPRECATED: The legacy builder is deprecated and will be removed in a future release. BuildKit is currently disabled; enable it by removing the DOCKER_BUILDKIT=0 environment-variable. Sending build context to Docker daemon 370.9MB Step 1/42 : FROM ubuntu:22.04 22.04: Pulling from library/ubuntu 837dd4791cdc: Already exists Digest: sha256:ac58ff7fe25edc58bdf0067ca99df00014dbd032e2246d30a722fa348fd799a5 Status: Downloaded newer image for ubuntu:22.04 ---> 1f6ddc1b2547 Step 2/42 : WORKDIR /opt/cp2k-toolchain ---> Using cache ---> 77485a061f07 Step 3/42 : COPY ./tools/toolchain/install_requirements*.sh ./ ---> Using cache ---> 7e80b6839af5 Step 4/42 : RUN ./install_requirements.sh ubuntu:22.04 ---> Using cache ---> 97ef01a73136 Step 5/42 : RUN mkdir scripts ---> Using cache ---> c54acc06979f 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 ---> 24fe50387362 Step 7/42 : COPY ./tools/toolchain/install_cp2k_toolchain.sh . ---> Using cache ---> 03cbc5f5aef2 Step 8/42 : RUN ./install_cp2k_toolchain.sh --install-all --with-gcc=system --dry-run ---> Using cache ---> 45fc70026992 Step 9/42 : COPY ./tools/toolchain/scripts/stage0/ ./scripts/stage0/ ---> Using cache ---> f0c4289cfbf8 Step 10/42 : RUN ./scripts/stage0/install_stage0.sh && rm -rf ./build ---> Using cache ---> 860559d0c1a2 Step 11/42 : COPY ./tools/toolchain/scripts/stage1/ ./scripts/stage1/ ---> Using cache ---> 9db7161a5804 Step 12/42 : RUN ./scripts/stage1/install_stage1.sh && rm -rf ./build ---> Using cache ---> 85112f7fc45c Step 13/42 : COPY ./tools/toolchain/scripts/stage2/ ./scripts/stage2/ ---> Using cache ---> 07e053f6a218 Step 14/42 : RUN ./scripts/stage2/install_stage2.sh && rm -rf ./build ---> Using cache ---> 5cf6daabab96 Step 15/42 : COPY ./tools/toolchain/scripts/stage3/ ./scripts/stage3/ ---> Using cache ---> a62c03b71343 Step 16/42 : RUN ./scripts/stage3/install_stage3.sh && rm -rf ./build ---> Using cache ---> b2ea66e03e0c Step 17/42 : COPY ./tools/toolchain/scripts/stage4/ ./scripts/stage4/ ---> Using cache ---> abe34da94d84 Step 18/42 : RUN ./scripts/stage4/install_stage4.sh && rm -rf ./build ---> Using cache ---> b31f8ffc3328 Step 19/42 : COPY ./tools/toolchain/scripts/stage5/ ./scripts/stage5/ ---> Using cache ---> 69bd13bfbeb6 Step 20/42 : RUN ./scripts/stage5/install_stage5.sh && rm -rf ./build ---> Using cache ---> 7425d448a8cf Step 21/42 : COPY ./tools/toolchain/scripts/stage6/ ./scripts/stage6/ ---> Using cache ---> 634800181c87 Step 22/42 : RUN ./scripts/stage6/install_stage6.sh && rm -rf ./build ---> Using cache ---> 7ad6cc5e6499 Step 23/42 : COPY ./tools/toolchain/scripts/stage7/ ./scripts/stage7/ ---> Using cache ---> c8429affbeee Step 24/42 : RUN ./scripts/stage7/install_stage7.sh && rm -rf ./build ---> Using cache ---> 1b923a782280 Step 25/42 : COPY ./tools/toolchain/scripts/stage8/ ./scripts/stage8/ ---> Using cache ---> 4a5b276b7479 Step 26/42 : RUN ./scripts/stage8/install_stage8.sh && rm -rf ./build ---> Using cache ---> d26f474fa12b Step 27/42 : COPY ./tools/toolchain/scripts/arch_base.tmpl ./tools/toolchain/scripts/generate_arch_files.sh ./scripts/ ---> Using cache ---> 6294243b6b32 Step 28/42 : RUN ./scripts/generate_arch_files.sh && rm -rf ./build ---> Using cache ---> c515ddd48f72 Step 29/42 : WORKDIR /opt/cp2k ---> Using cache ---> 1fda98fb0c53 Step 30/42 : COPY ./Makefile . ---> Using cache ---> 969045cae981 Step 31/42 : COPY ./src ./src ---> Using cache ---> 3eb2eec23fd8 Step 32/42 : COPY ./exts ./exts ---> Using cache ---> f80cc9a2b827 Step 33/42 : COPY ./tools/build_utils ./tools/build_utils ---> Using cache ---> 012123e48502 Step 34/42 : RUN /bin/bash -c " mkdir -p arch && ln -vs /opt/cp2k-toolchain/install/arch/local.psmp ./arch/ && echo 'Compiling cp2k...' && source /opt/cp2k-toolchain/install/setup && ( make -j ARCH=local VERSION=psmp &> /dev/null || true ) && rm -rf lib obj && ( [ ! -f ./exe/local/cp2k.psmp ] || ldd ./exe/local/cp2k.psmp | grep -q libmpi )" ---> Running in feca6e554c70 './arch/local.psmp' -> '/opt/cp2k-toolchain/install/arch/local.psmp' Compiling cp2k... Removing intermediate container feca6e554c70 ---> 4297a6a27745 Step 35/42 : COPY ./data ./data ---> d071e66a690d Step 36/42 : COPY ./tests ./tests ---> 1e1483d799b8 Step 37/42 : COPY ./tools/regtesting ./tools/regtesting ---> c6b99c9ac9f6 Step 38/42 : COPY ./benchmarks ./benchmarks ---> acc22c45f92a Step 39/42 : COPY ./tools/docker/scripts/test_performance.sh ./tools/docker/scripts/plot_performance.py ./ ---> 125b208300de Step 40/42 : RUN ./test_performance.sh "local" 2>&1 | tee report.log ---> Running in 4fb07fd1582c ========== Compiling CP2K ========== Compiling cp2k... done. Checking benchmark inputs... Found 70 input files and 0 errors. ========== Running Performance Test ========== Running H2O-64.inp with 1 threads and 32 ranks... done. Running H2O-64.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/H2O-64_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.030 0.030 85.840 85.840 qs_mol_dyn_low 1 2.0 0.003 0.003 85.207 85.207 qs_forces 11 3.9 0.001 0.001 85.168 85.168 qs_energies 11 4.9 0.001 0.001 79.113 79.113 scf_env_do_scf 11 5.9 0.001 0.001 68.377 68.377 velocity_verlet 10 3.0 0.002 0.002 55.967 55.967 scf_env_do_scf_inner_loop 108 6.5 0.011 0.011 52.142 52.142 rebuild_ks_matrix 119 8.3 0.001 0.001 20.306 20.306 qs_ks_build_kohn_sham_matrix 119 9.3 0.012 0.012 20.305 20.305 dbcsr_multiply_generic 2286 12.5 0.175 0.175 19.156 19.156 qs_scf_new_mos 108 7.5 0.001 0.001 18.983 18.983 qs_scf_loop_do_ot 108 8.5 0.001 0.001 18.983 18.983 qs_ks_update_qs_env 119 7.6 0.001 0.001 18.504 18.504 qs_rho_update_rho_low 119 7.7 0.001 0.001 18.365 18.365 calculate_rho_elec 119 8.7 0.946 0.946 18.364 18.364 ot_scf_mini 108 9.5 0.002 0.002 17.679 17.679 init_scf_loop 11 6.9 0.000 0.000 16.102 16.102 grid_collocate_task_list 119 9.7 14.322 14.322 14.322 14.322 prepare_preconditioner 11 7.9 0.000 0.000 13.670 13.670 make_preconditioner 11 8.9 0.000 0.000 13.670 13.670 sum_up_and_integrate 119 10.3 0.778 0.778 13.105 13.105 make_full_inverse_cholesky 11 9.9 0.031 0.031 12.492 12.492 integrate_v_rspace 119 11.3 0.116 0.116 12.327 12.327 ot_mini 108 10.5 0.001 0.001 11.481 11.481 make_m2s 4572 13.5 0.046 0.046 10.768 10.768 grid_integrate_task_list 119 12.3 10.413 10.413 10.413 10.413 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 6.454 6.454 qs_ot_get_derivative 108 11.5 0.001 0.001 6.029 6.029 dbcsr_make_dense_low 5837 15.5 0.068 0.068 5.736 5.736 make_dense_data 5837 16.5 5.101 5.101 5.653 5.653 pw_transfer 1439 11.6 0.067 0.067 5.612 5.612 make_images 4572 14.5 2.177 2.177 5.500 5.500 ot_diis_step 108 11.5 0.004 0.004 5.449 5.449 fft_wrap_pw1pw2 1201 12.6 0.006 0.006 5.394 5.394 dbcsr_make_images_dense 3978 14.8 0.017 0.017 4.976 4.976 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 4.951 4.951 apply_single 119 13.6 0.000 0.000 4.951 4.951 multiply_cannon 2286 13.5 0.175 0.175 4.600 4.600 fft_wrap_pw1pw2_140 487 13.2 0.464 0.464 4.576 4.576 cp_fm_cholesky_decompose 22 10.9 4.318 4.318 4.318 4.318 multiply_cannon_loop 2286 14.5 0.045 0.045 4.145 4.145 multiply_cannon_multrec 2286 15.5 4.044 4.044 4.099 4.099 cp_fm_cholesky_invert 11 10.9 3.987 3.987 3.987 3.987 init_scf_run 11 5.9 0.002 0.002 3.682 3.682 scf_env_initial_rho_setup 11 6.9 0.001 0.001 3.680 3.680 dbcsr_complete_redistribute 329 12.2 1.889 1.889 3.594 3.594 qs_env_update_s_mstruct 11 6.9 0.000 0.000 3.578 3.578 dbcsr_copy 2102 12.0 0.242 0.242 3.538 3.538 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 3.298 3.298 dbcsr_copy_into_existing 22 7.9 3.236 3.236 3.236 3.236 qs_create_task_list 11 7.9 0.000 0.000 3.216 3.216 generate_qs_task_list 11 8.9 1.954 1.954 3.216 3.216 wfi_extrapolate 11 7.9 0.001 0.001 3.186 3.186 density_rs2pw 119 9.7 0.005 0.005 3.097 3.097 copy_dbcsr_to_fm 153 11.3 0.002 0.002 2.909 2.909 qs_ot_get_p 119 10.4 0.001 0.001 2.858 2.858 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 2.754 2.754 fft3d_s 1202 14.6 2.709 2.709 2.715 2.715 build_core_hamiltonian_matrix 11 6.9 0.001 0.001 2.456 2.456 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.289 2.289 dbcsr_data_release 279532 16.0 2.117 2.117 2.117 2.117 pw_poisson_solve 119 10.3 0.327 0.327 2.029 2.029 copy_fm_to_dbcsr 176 11.2 0.001 0.001 1.914 1.914 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 1.884 1.884 qs_ot_get_derivative_taylor 59 13.0 0.001 0.001 1.873 1.873 potential_pw2rs 119 12.3 0.045 0.045 1.798 1.798 cp_fm_upper_to_full 72 14.2 1.785 1.785 1.785 1.785 ------------------------------------------------------------------------------- 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 0.009 0.021 44.827 44.837 qs_mol_dyn_low 1 2.0 0.003 0.004 44.685 44.690 qs_forces 11 3.9 0.001 0.002 44.645 44.646 qs_energies 11 4.9 0.001 0.001 41.777 41.778 scf_env_do_scf 11 5.9 0.000 0.002 38.328 38.328 scf_env_do_scf_inner_loop 108 6.5 0.003 0.018 35.364 35.365 velocity_verlet 10 3.0 0.001 0.003 26.604 26.605 rebuild_ks_matrix 119 8.3 0.001 0.001 15.994 16.109 qs_ks_build_kohn_sham_matrix 119 9.3 0.015 0.019 15.993 16.109 qs_ks_update_qs_env 119 7.6 0.001 0.001 14.209 14.318 dbcsr_multiply_generic 2286 12.5 0.075 0.080 13.366 13.556 qs_rho_update_rho_low 119 7.7 0.001 0.001 12.916 12.921 calculate_rho_elec 119 8.7 0.030 0.032 12.916 12.921 sum_up_and_integrate 119 10.3 0.031 0.035 11.890 11.920 integrate_v_rspace 119 11.3 0.004 0.005 11.859 11.892 qs_scf_new_mos 108 7.5 0.001 0.001 10.894 11.101 qs_scf_loop_do_ot 108 8.5 0.001 0.001 10.893 11.101 ot_scf_mini 108 9.5 0.002 0.003 10.270 10.476 multiply_cannon 2286 13.5 0.161 0.180 9.910 10.438 multiply_cannon_loop 2286 14.5 0.104 0.126 9.378 9.836 grid_collocate_task_list 119 9.7 8.719 9.037 8.719 9.037 mp_waitall_1 158411 16.6 7.733 8.612 7.733 8.612 grid_integrate_task_list 119 12.3 7.890 8.204 7.890 8.204 multiply_cannon_metrocomm3 18288 15.5 0.046 0.057 5.929 6.743 ot_mini 108 10.5 0.001 0.001 5.834 6.065 rs_pw_transfer 974 11.9 0.011 0.016 4.226 4.685 density_rs2pw 119 9.7 0.005 0.006 3.591 3.999 pw_transfer 1439 11.6 0.084 0.095 3.754 3.892 fft_wrap_pw1pw2 1201 12.6 0.008 0.010 3.607 3.730 multiply_cannon_multrec 18288 15.5 3.020 3.407 3.032 3.418 potential_pw2rs 119 12.3 0.006 0.008 3.350 3.386 fft_wrap_pw1pw2_140 487 13.2 0.577 0.747 3.079 3.290 qs_ot_get_derivative 108 11.5 0.001 0.001 2.928 3.134 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 2.859 2.970 apply_single 119 13.6 0.000 0.001 2.859 2.970 init_scf_loop 11 6.9 0.000 0.000 2.948 2.949 ot_diis_step 108 11.5 0.003 0.003 2.889 2.889 fft3d_ps 1201 14.6 1.219 1.432 2.310 2.483 init_scf_run 11 5.9 0.000 0.004 2.445 2.445 scf_env_initial_rho_setup 11 6.9 0.000 0.003 2.444 2.445 make_m2s 4572 13.5 0.046 0.058 2.378 2.443 wfi_extrapolate 11 7.9 0.001 0.001 2.224 2.224 make_images 4572 14.5 0.115 0.124 2.049 2.111 mp_waitany 9880 13.7 1.421 2.058 1.421 2.058 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 1.907 1.917 qs_ot_get_p 119 10.4 0.001 0.001 1.537 1.874 rs_pw_transfer_RS2PW_140 130 11.5 0.181 0.262 0.977 1.435 mp_sum_l 11298 13.2 0.636 1.410 0.636 1.410 make_images_data 4572 15.5 0.034 0.045 1.175 1.338 rs_pw_transfer_PW2RS_140 130 13.9 0.350 0.456 1.210 1.254 mp_alltoall_d11v 2130 13.8 0.840 1.245 0.840 1.245 mp_sum_d 4135 12.0 0.599 1.223 0.599 1.223 prepare_preconditioner 11 7.9 0.000 0.000 1.166 1.193 make_preconditioner 11 8.9 0.000 0.000 1.166 1.193 hybrid_alltoall_any 4725 16.4 0.064 0.231 0.996 1.148 mp_alltoall_z22v 1201 16.6 0.859 1.146 0.859 1.146 rs_pw_transfer_PW2RS_50 119 14.3 0.327 0.415 0.908 1.121 make_full_inverse_cholesky 11 9.9 0.000 0.000 1.062 1.088 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 0.928 1.030 qs_ot_get_derivative_taylor 59 13.0 0.001 0.001 0.901 1.006 rs_gather_matrices 119 12.3 0.092 0.114 0.562 0.949 cp_dbcsr_sm_fm_multiply 37 9.5 0.001 0.001 0.941 0.942 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 0.852 0.934 ------------------------------------------------------------------------------- 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=47.64200000000001, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=14.322, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=10.413, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="make_dense_data", label="make_dense_data", y=5.101, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=4.318, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=4.044, 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=16.044, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=8.719, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=7.89, 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=3.02, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=7.733, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitany", label="mp_waitany", y=1.421, 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 0.033 109.921 109.921 qs_mol_dyn_low 1 2.0 0.002 0.002 109.258 109.258 qs_forces 11 3.9 0.001 0.001 109.219 109.219 qs_energies 11 4.9 0.001 0.001 101.536 101.536 scf_env_do_scf 11 5.9 0.001 0.001 88.718 88.718 velocity_verlet 10 3.0 0.002 0.002 70.898 70.898 scf_env_do_scf_inner_loop 96 6.5 0.010 0.010 70.382 70.382 rebuild_ks_matrix 107 8.3 0.001 0.001 33.303 33.303 qs_ks_build_kohn_sham_matrix 107 9.3 0.011 0.011 33.303 33.303 qs_rho_update_rho_low 107 7.7 0.000 0.000 30.438 30.438 calculate_rho_elec 107 8.7 0.850 0.850 30.437 30.437 qs_ks_update_qs_env 107 7.6 0.001 0.001 29.940 29.940 sum_up_and_integrate 107 10.3 0.699 0.699 26.858 26.858 grid_collocate_task_list 107 9.7 26.696 26.696 26.696 26.696 integrate_v_rspace 107 11.3 0.077 0.077 26.159 26.159 grid_integrate_task_list 107 12.3 24.395 24.395 24.395 24.395 init_scf_loop 11 6.9 0.000 0.000 18.181 18.181 dbcsr_multiply_generic 1966 12.4 0.138 0.138 17.008 17.008 qs_scf_new_mos 96 7.5 0.000 0.000 16.724 16.724 qs_scf_loop_do_ot 96 8.5 0.001 0.001 16.724 16.724 ot_scf_mini 96 9.5 0.002 0.002 15.523 15.523 prepare_preconditioner 11 7.9 0.000 0.000 14.087 14.087 make_preconditioner 11 8.9 0.000 0.000 14.087 14.087 make_full_inverse_cholesky 11 9.9 0.028 0.028 12.926 12.926 ot_mini 96 10.5 0.001 0.001 10.132 10.132 make_m2s 3932 13.4 0.040 0.040 9.475 9.475 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 6.915 6.915 qs_ot_get_derivative 96 11.5 0.001 0.001 5.347 5.347 pw_transfer 1295 11.6 0.057 0.057 5.310 5.310 init_scf_run 11 5.9 0.002 0.002 5.262 5.262 scf_env_initial_rho_setup 11 6.9 0.000 0.000 5.260 5.260 dbcsr_make_dense_low 4961 15.5 0.060 0.060 5.138 5.138 fft_wrap_pw1pw2 1081 12.6 0.005 0.005 5.117 5.117 make_dense_data 4961 16.5 4.524 4.524 5.066 5.066 ot_diis_step 96 11.5 0.003 0.003 4.782 4.782 make_images 3932 14.4 1.885 1.885 4.723 4.723 wfi_extrapolate 11 7.9 0.001 0.001 4.690 4.690 cp_fm_cholesky_decompose 22 10.9 4.550 4.550 4.550 4.550 dbcsr_make_images_dense 3386 14.7 0.015 0.015 4.490 4.490 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 4.450 4.450 apply_single 107 13.6 0.000 0.000 4.450 4.450 fft_wrap_pw1pw2_140 439 13.2 0.442 0.442 4.386 4.386 multiply_cannon 1966 13.4 0.161 0.161 4.268 4.268 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 4.218 4.218 cp_fm_cholesky_invert 11 10.9 4.078 4.078 4.078 4.078 qs_env_update_s_mstruct 11 6.9 0.000 0.000 3.976 3.976 dbcsr_complete_redistribute 317 12.2 1.895 1.895 3.889 3.889 multiply_cannon_loop 1966 14.4 0.049 0.049 3.856 3.856 multiply_cannon_multrec 1966 15.4 3.760 3.760 3.807 3.807 qs_create_task_list 11 7.9 0.000 0.000 3.614 3.614 generate_qs_task_list 11 8.9 2.386 2.386 3.614 3.614 dbcsr_copy 1855 11.9 0.202 0.202 3.577 3.577 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 3.463 3.463 dbcsr_copy_into_existing 22 7.9 3.346 3.346 3.346 3.346 copy_dbcsr_to_fm 147 11.2 0.002 0.002 3.080 3.080 density_rs2pw 107 9.7 0.004 0.004 2.891 2.891 fft3d_s 1082 14.6 2.584 2.584 2.588 2.588 build_core_hamiltonian_matrix 11 6.9 0.000 0.000 2.524 2.524 qs_ot_get_p 107 10.4 0.001 0.001 2.510 2.510 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.429 2.429 ------------------------------------------------------------------------------- From /workspace/artifacts/H2O-64_nonortho_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.009 0.021 70.618 70.627 qs_mol_dyn_low 1 2.0 0.003 0.003 70.460 70.464 qs_forces 11 3.9 0.001 0.002 70.420 70.421 qs_energies 11 4.9 0.001 0.001 65.706 65.708 scf_env_do_scf 11 5.9 0.000 0.002 60.828 60.828 scf_env_do_scf_inner_loop 96 6.5 0.002 0.017 56.242 56.243 velocity_verlet 10 3.0 0.001 0.003 41.986 41.988 rebuild_ks_matrix 107 8.3 0.000 0.001 30.389 30.445 qs_ks_build_kohn_sham_matrix 107 9.3 0.014 0.017 30.388 30.444 qs_ks_update_qs_env 107 7.6 0.001 0.001 26.742 26.794 sum_up_and_integrate 107 10.3 0.031 0.036 26.594 26.618 integrate_v_rspace 107 11.3 0.004 0.005 26.563 26.589 qs_rho_update_rho_low 107 7.7 0.001 0.001 25.413 25.422 calculate_rho_elec 107 8.7 0.027 0.029 25.413 25.421 grid_integrate_task_list 107 12.3 22.647 23.184 22.647 23.184 grid_collocate_task_list 107 9.7 21.515 22.007 21.515 22.007 dbcsr_multiply_generic 1966 12.4 0.068 0.071 12.201 12.352 qs_scf_new_mos 96 7.5 0.001 0.001 9.747 9.874 qs_scf_loop_do_ot 96 8.5 0.001 0.001 9.747 9.874 multiply_cannon 1966 13.4 0.143 0.157 9.107 9.347 ot_scf_mini 96 9.5 0.002 0.002 9.194 9.325 multiply_cannon_loop 1966 14.4 0.097 0.117 8.594 8.867 mp_waitall_1 136719 16.5 6.998 7.700 6.998 7.700 multiply_cannon_metrocomm3 15728 15.4 0.042 0.052 5.434 5.973 ot_mini 96 10.5 0.001 0.001 5.245 5.389 rs_pw_transfer 878 11.9 0.010 0.013 3.932 4.598 init_scf_loop 11 6.9 0.000 0.000 4.570 4.570 density_rs2pw 107 9.7 0.005 0.006 3.340 3.973 init_scf_run 11 5.9 0.000 0.004 3.850 3.850 scf_env_initial_rho_setup 11 6.9 0.000 0.003 3.850 3.850 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 3.761 3.768 pw_transfer 1295 11.6 0.077 0.087 3.443 3.563 wfi_extrapolate 11 7.9 0.001 0.001 3.509 3.509 fft_wrap_pw1pw2 1081 12.6 0.008 0.009 3.311 3.426 multiply_cannon_multrec 15728 15.4 2.804 3.090 2.814 3.101 fft_wrap_pw1pw2_140 439 13.2 0.539 0.682 2.823 3.088 potential_pw2rs 107 12.3 0.006 0.007 3.056 3.079 qs_ot_get_derivative 96 11.5 0.001 0.001 2.608 2.740 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 2.640 2.731 apply_single 107 13.6 0.000 0.000 2.640 2.731 ot_diis_step 96 11.5 0.003 0.003 2.623 2.626 fft3d_ps 1081 14.6 1.109 1.270 2.102 2.246 make_m2s 3932 13.4 0.040 0.045 2.165 2.245 mp_waitany 8968 13.7 1.445 2.243 1.445 2.243 make_images 3932 14.4 0.104 0.107 1.871 1.938 mp_alltoall_d11v 1998 13.7 1.075 1.684 1.075 1.684 rs_pw_transfer_RS2PW_140 118 11.5 0.164 0.203 1.001 1.671 qs_ot_get_p 107 10.4 0.001 0.001 1.338 1.542 ------------------------------------------------------------------------------- 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=41.918000000000006, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=26.696, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=24.395, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=4.55, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="make_dense_data", label="make_dense_data", y=4.524, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=4.078, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=3.76, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="mp_waitany", label="mp_waitany", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 Plot: name="H2O-64_nonortho_timings_32mpi", title="Timings of H2O-64_nonortho with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="rest", label="rest", y=15.208999999999996, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=21.515, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=22.647, 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="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=2.804, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitany", label="mp_waitany", y=1.445, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=6.998, 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 0.205 0.205 104.451 104.451 qs_energies 1 2.0 0.000 0.000 103.606 103.606 scf_env_do_scf 1 3.0 0.000 0.000 102.449 102.449 qs_ks_update_qs_env 8 5.0 0.000 0.000 97.577 97.577 rebuild_ks_matrix 7 6.0 0.000 0.000 97.520 97.520 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.001 97.520 97.520 hfx_ks_matrix 7 8.0 0.000 0.000 88.813 88.813 integrate_four_center 7 9.0 1.743 1.743 88.785 88.785 integrate_four_center_main 7 10.0 0.733 0.733 81.123 81.123 integrate_four_center_bin 448 11.0 80.390 80.390 80.390 80.390 scf_env_do_scf_inner_loop 7 4.0 0.001 0.001 56.407 56.407 init_scf_loop 1 4.0 0.000 0.000 46.032 46.032 integrate_four_center_load 7 10.0 0.002 0.002 5.663 5.663 hfx_load_balance 1 11.0 0.001 0.001 5.661 5.661 qs_vxc_create 14 8.0 0.000 0.000 3.061 3.061 xc_vxc_pw_create 14 9.0 0.119 0.119 3.061 3.061 hfx_load_balance_bin 1 12.0 2.842 2.842 2.842 2.842 hfx_load_balance_count 1 12.0 2.802 2.802 2.802 2.802 calculate_rho_elec 15 7.4 0.117 0.117 2.371 2.371 xc_rho_set_and_dset_create 14 10.0 0.094 0.094 2.353 2.353 prepare_preconditioner 1 5.0 0.000 0.000 2.309 2.309 make_preconditioner 1 6.0 0.000 0.000 2.309 2.309 admm_mo_calc_rho_aux 7 8.0 0.000 0.000 2.103 2.103 ------------------------------------------------------------------------------- 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 0.220 0.241 95.146 95.157 qs_energies 1 2.0 0.000 0.000 94.736 94.743 scf_env_do_scf 1 3.0 0.000 0.000 94.396 94.397 qs_ks_update_qs_env 8 5.0 0.000 0.000 92.385 92.385 rebuild_ks_matrix 7 6.0 0.000 0.000 92.378 92.378 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.001 92.378 92.378 hfx_ks_matrix 7 8.0 0.000 0.000 86.791 86.793 integrate_four_center 7 9.0 0.051 0.333 86.782 86.784 integrate_four_center_main 7 10.0 0.003 0.003 78.896 79.770 integrate_four_center_bin 448 11.0 78.893 79.767 78.893 79.767 scf_env_do_scf_inner_loop 7 4.0 0.000 0.001 52.727 52.727 init_scf_loop 1 4.0 0.000 0.000 41.668 41.669 integrate_four_center_load 7 10.0 0.000 0.000 5.796 5.797 hfx_load_balance 1 11.0 0.001 0.001 5.796 5.797 hfx_load_balance_count 1 12.0 2.760 2.896 2.760 2.896 hfx_load_balance_bin 1 12.0 2.760 2.895 2.760 2.895 mp_sync 56 11.2 1.422 2.497 1.422 2.497 qs_vxc_create 14 8.0 0.000 0.000 2.434 2.434 xc_vxc_pw_create 14 9.0 0.007 0.007 2.434 2.434 xc_rho_set_and_dset_create 14 10.0 0.008 0.010 1.930 2.057 ------------------------------------------------------------------------------- Plot: name="H2O-hyb_timings_32omp", title="Timings of H2O-hyb with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="H2O-hyb_timings_32omp", name="rest", label="rest", y=15.73599999999999, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_bin", label="integrate_four_center_bin", y=80.39, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=2.842, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_count", label="hfx_load_balance_count", y=2.802, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center", label="integrate_four_center", y=1.743, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_main", label="integrate_four_center_main", y=0.733, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="CP2K", label="CP2K", y=0.205, 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=9.036999999999992, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center_bin", label="integrate_four_center_bin", y=78.893, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=2.76, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_count", label="hfx_load_balance_count", y=2.76, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center", label="integrate_four_center", y=0.051, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center_main", label="integrate_four_center_main", y=0.003, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="CP2K", label="CP2K", y=0.22, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="mp_sync", label="mp_sync", y=1.422, 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 0.014 0.014 76.943 76.943 qs_energies 1 2.0 0.000 0.000 76.535 76.535 mp2_main 1 3.0 0.000 0.000 73.748 73.748 mp2_gpw_main 1 4.0 0.000 0.000 73.642 73.642 rpa_ri_compute_en 1 5.0 0.000 0.000 70.003 70.003 rpa_num_int 1 6.0 0.001 0.001 69.997 69.997 compute_mat_P_omega 1 7.0 0.003 0.003 60.391 60.391 compute_mat_P_omega_contract 10 8.0 8.860 8.860 60.192 60.192 dbt_total 2336 9.6 0.014 0.014 46.549 46.549 dbt_contract 787 11.0 0.041 0.041 39.658 39.658 dbt_tas_total 1149 12.2 0.212 0.212 38.636 38.636 dbt_tas_multiply 807 12.1 0.002 0.002 37.312 37.312 dbt_tas_dbm 807 14.1 0.003 0.003 30.831 30.831 dbm_multiply 807 16.1 30.824 30.824 30.824 30.824 dbt_tas_mm_1N 524 15.1 0.001 0.001 23.601 23.601 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 22.288 22.288 compute_mat_P_omega_calc_M_occ 250 9.0 8.824 8.824 16.636 16.636 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 6.787 6.787 dbt_tas_mm_2 251 15.0 0.001 0.001 5.729 5.729 dbt_copy 1103 10.7 0.089 0.089 5.548 5.548 compute_QP_energies 1 7.0 0.000 0.000 4.966 4.966 compute_self_energy_cubic_gw 1 8.0 0.053 0.053 4.965 4.965 contract_cubic_gw 21 9.0 0.000 0.000 3.994 3.994 mp2_ri_gpw_compute_in 1 5.0 0.001 0.001 3.632 3.632 dbt_tas_reserve_blocks_index 3261 14.3 0.481 0.481 3.564 3.564 dbm_reserve_blocks 3628 15.3 3.158 3.158 3.158 3.158 dbt_reserve_blocks_index 2280 13.1 0.052 0.052 2.709 2.709 dbt_reserve_blocks_index_array 2222 12.2 0.009 0.009 2.659 2.659 scf_env_do_scf 1 3.0 0.000 0.000 2.628 2.628 scf_env_do_scf_inner_loop 17 4.0 0.002 0.002 2.628 2.628 convert_to_new_pgrid 2421 14.1 0.129 0.129 2.406 2.406 dbm_copy 1614 15.1 2.278 2.278 2.278 2.278 dbt_crop 1042 12.0 1.357 1.357 2.231 2.231 dbt_tas_copy 574 11.4 1.288 1.288 2.198 2.198 dbt_tas_reshape 367 15.0 0.007 0.007 2.026 2.026 compute_W_cubic_GW 10 7.0 0.007 0.007 1.936 1.936 dbt_reshape 278 11.9 1.028 1.028 1.886 1.886 rpa_num_int_RPA_matrix_operati 10 7.0 0.000 0.000 1.861 1.861 get_2c_integrals 1 6.0 0.000 0.000 1.742 1.742 ------------------------------------------------------------------------------- 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 0.023 32.616 32.627 qs_energies 1 2.0 0.000 0.000 32.495 32.496 mp2_main 1 3.0 0.000 0.000 31.463 31.464 mp2_gpw_main 1 4.0 0.000 0.000 31.429 31.430 rpa_ri_compute_en 1 5.0 0.000 0.000 30.183 30.184 rpa_num_int 1 6.0 0.000 0.002 30.183 30.184 dbt_total 2336 9.6 0.014 0.015 26.676 26.691 compute_mat_P_omega 1 7.0 0.001 0.005 25.754 25.779 compute_mat_P_omega_contract 10 8.0 0.376 0.406 25.538 25.543 dbt_contract 787 11.0 0.037 0.039 19.638 19.644 dbt_tas_total 1149 12.2 0.074 0.084 17.474 17.487 dbt_tas_multiply 807 12.1 0.002 0.002 17.178 17.182 dbt_tas_dbm 807 14.1 0.003 0.003 12.410 12.415 dbm_multiply 807 16.1 9.882 10.606 9.882 10.606 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 8.019 8.020 compute_mat_P_omega_calc_M_occ 250 9.0 0.369 0.394 7.140 7.142 mp_sync 8688 11.6 4.858 6.274 4.858 6.274 dbt_copy 1149 10.8 0.012 0.013 5.882 6.216 dbt_tas_mm_2 251 15.0 0.001 0.001 6.077 6.079 dbt_reshape 1136 11.8 2.522 2.698 5.581 5.901 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 4.996 4.997 dbt_tas_mm_1N 524 15.1 0.001 0.001 4.286 4.742 compute_QP_energies 1 7.0 0.000 0.000 2.785 2.786 compute_self_energy_cubic_gw 1 8.0 0.002 0.003 2.783 2.785 mp_waitall_2 3812 15.3 2.243 2.447 2.243 2.447 dbt_communicate_buffer 1136 12.8 0.051 0.057 2.231 2.397 contract_cubic_gw 21 9.0 0.000 0.000 2.104 2.104 dbt_reserve_blocks_index 2887 13.1 0.063 0.070 1.611 1.852 dbt_reserve_blocks_index_array 2829 12.2 0.008 0.010 1.602 1.841 dbt_tas_reserve_blocks_index 3347 14.5 0.431 0.467 1.595 1.831 dbt_crop 1042 12.0 0.860 0.942 1.365 1.542 dbm_reserve_blocks 3752 15.4 1.250 1.464 1.250 1.464 mp2_ri_gpw_compute_in 1 5.0 0.000 0.001 1.244 1.245 dbt_tas_replicate 405 14.1 0.532 0.703 1.080 1.155 compute_mat_P_omega_copy_M_occ 250 9.0 0.001 0.001 1.053 1.056 compute_mat_P_omega_copy_M_vir 250 9.0 0.001 0.001 1.047 1.049 scf_env_do_scf 1 3.0 0.000 0.000 0.990 0.990 scf_env_do_scf_inner_loop 17 4.0 0.000 0.002 0.990 0.990 parallel_gemm_fm 105 8.4 0.000 0.000 0.967 0.974 parallel_gemm_fm_cosma 105 9.4 0.967 0.974 0.967 0.974 mp_max_i 2002 9.8 0.774 0.956 0.774 0.956 convert_to_new_pgrid 2421 14.1 0.025 0.029 0.721 0.859 dbm_copy 1608 15.1 0.690 0.827 0.690 0.827 mp_sum_l 6165 12.9 0.608 0.759 0.608 0.759 compute_W_cubic_GW 10 7.0 0.001 0.001 0.738 0.745 ------------------------------------------------------------------------------- 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=21.971000000000004, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=30.824, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=8.86, 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=8.824, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=3.158, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_copy", label="dbm_copy", y=2.278, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=1.028, 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=10.426000000000002, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=9.882, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=0.376, 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=0.369, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=1.25, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_copy", label="dbm_copy", y=0.69, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=2.522, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_sync", label="mp_sync", y=4.858, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.243, yerr=0.0 Running RI-HFX_H2O-32.inp with 1 threads and 32 ranks... done. Running RI-HFX_H2O-32.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/RI-HFX_H2O-32_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.018 0.018 249.156 249.156 qs_forces 1 2.0 0.000 0.000 248.591 248.591 rebuild_ks_matrix 7 6.6 0.000 0.000 247.178 247.178 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.001 247.178 247.178 hfx_ks_matrix 7 8.6 0.000 0.000 245.378 245.378 hfx_ri_update_ks 7 9.6 0.000 0.000 207.209 207.209 hfx_ri_update_ks_Pmat 7 10.6 30.850 30.850 207.205 207.205 dbt_total 809 11.0 0.005 0.005 192.032 192.032 qs_energies 1 3.0 0.000 0.000 184.172 184.172 scf_env_do_scf 1 4.0 0.001 0.001 183.843 183.843 qs_ks_update_qs_env 8 6.0 0.000 0.000 182.811 182.811 dbt_contract 207 12.4 0.081 0.081 173.712 173.712 dbt_tas_total 343 13.7 1.413 1.413 171.785 171.785 dbt_tas_multiply 216 13.5 0.001 0.001 168.479 168.479 dbt_tas_dbm 216 15.5 0.001 0.001 157.339 157.339 dbm_multiply 216 17.5 157.336 157.336 157.336 157.336 hfx_ri_update_ks_Pmat_KS 63 11.6 0.001 0.001 152.596 152.596 dbt_tas_mm_2 91 16.5 0.001 0.001 144.092 144.092 scf_env_do_scf_inner_loop 6 5.0 0.001 0.001 114.424 114.424 init_scf_loop 2 5.0 0.000 0.000 69.417 69.417 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 64.370 64.370 hfx_ri_update_forces 1 7.0 1.599 1.599 38.166 38.166 hfx_ri_forces_Pmat_3c 1 8.0 4.761 4.761 21.596 21.596 dbt_copy 409 11.7 0.046 0.046 15.006 15.006 precalc_derivatives 1 8.0 2.135 2.135 12.855 12.855 dbt_reshape 132 13.2 6.356 6.356 10.497 10.497 dbt_tas_mm_3T 77 17.1 0.000 0.000 9.228 9.228 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 8.934 8.934 dbt_tas_reserve_blocks_index 1255 15.4 1.075 1.075 7.826 7.826 build_3c_derivatives 3 9.0 2.848 2.848 7.175 7.175 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 7.009 7.009 dbm_reserve_blocks 1397 16.3 6.944 6.944 6.944 6.944 dbt_reserve_blocks_index 818 14.4 0.093 0.093 6.151 6.151 dbt_reserve_blocks_index_array 795 13.4 0.007 0.007 6.069 6.069 ------------------------------------------------------------------------------- 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 48.215 48.224 qs_forces 1 2.0 0.000 0.000 47.617 47.617 rebuild_ks_matrix 7 6.6 0.000 0.000 46.849 46.850 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.001 46.849 46.850 hfx_ks_matrix 7 8.6 0.000 0.000 45.880 45.888 dbt_total 809 11.0 0.006 0.006 40.642 40.679 dbt_contract 207 12.4 0.023 0.024 31.225 31.233 hfx_ri_update_ks 7 9.6 0.000 0.000 27.758 27.758 hfx_ri_update_ks_Pmat 7 10.6 1.138 1.192 27.755 27.756 dbt_tas_total 343 13.7 0.107 0.289 27.441 27.460 dbt_tas_multiply 216 13.5 0.001 0.001 26.959 26.963 qs_energies 1 3.0 0.000 0.000 25.935 25.935 scf_env_do_scf 1 4.0 0.000 0.001 25.786 25.786 qs_ks_update_qs_env 8 6.0 0.000 0.000 25.177 25.178 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 21.673 21.673 dbt_tas_dbm 216 15.5 0.001 0.001 20.658 20.670 dbm_multiply 216 17.5 18.594 19.549 18.594 19.549 hfx_ri_update_forces 1 7.0 0.056 0.060 18.121 18.129 scf_env_do_scf_inner_loop 6 5.0 0.000 0.001 14.420 14.420 hfx_ri_forces_Pmat_3c 1 8.0 0.149 0.161 13.394 13.394 hfx_ri_update_ks_Pmat_KS 63 11.6 0.000 0.001 12.924 12.946 init_scf_loop 2 5.0 0.000 0.000 11.365 11.365 dbt_tas_mm_2 91 16.5 0.001 0.001 9.984 9.997 dbt_copy 497 12.3 0.010 0.012 8.118 8.447 mp_sync 2769 12.9 5.320 7.420 5.320 7.420 dbt_reshape 365 13.6 3.394 3.518 6.235 6.457 dbt_tas_mm_3T 77 17.1 0.000 0.000 5.099 5.589 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 5.065 5.069 dbt_tas_mm_3N 37 15.4 0.000 0.000 3.942 4.077 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 3.468 3.468 precalc_derivatives 1 8.0 0.075 0.082 3.455 3.455 dbt_tas_reserve_blocks_index 1380 15.8 0.895 0.919 2.881 3.150 mp_waitall_2 1234 16.4 2.573 2.771 2.573 2.771 dbt_reserve_blocks_index 1051 14.7 0.103 0.108 2.405 2.635 dbt_reserve_blocks_index_array 1028 13.8 0.005 0.006 2.379 2.610 dbt_crop 372 13.7 1.660 1.721 2.391 2.512 dbm_reserve_blocks 1529 16.7 2.177 2.434 2.177 2.434 dbt_communicate_buffer 365 14.6 0.013 0.014 1.828 1.996 mp_sum_l 6385 13.7 1.709 1.953 1.709 1.953 build_3c_derivatives 3 9.0 0.220 0.235 1.929 1.937 hfx_ri_update_ks_Pmat_copy_2 63 11.6 0.000 0.000 1.651 1.652 dbt_tas_replicate 149 15.4 0.617 0.649 1.558 1.632 hfx_ri_pre_scf_Pmat_RIx3C 9 13.0 0.000 0.000 1.525 1.529 convert_to_new_pgrid 648 15.5 0.035 0.079 1.249 1.508 dbm_copy 452 16.3 1.091 1.354 1.091 1.354 dbt_tas_copy 132 12.5 0.555 0.595 1.082 1.193 hfx_ri_pre_scf_Pmat_int 1 13.0 0.000 0.000 1.049 1.055 hfx_ri_pre_scf_calc_tensors 1 14.0 0.001 0.001 0.973 0.974 ------------------------------------------------------------------------------- Plot: name="RI-HFX_H2O-32_timings_32omp", title="Timings of RI-HFX_H2O-32 with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="rest", label="rest", y=42.90900000000002, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=157.336, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=30.85, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=6.944, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=6.356, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_forces_Pmat_3c", label="hfx_ri_forces_Pmat_3c", y=4.761, 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=14.870000000000005, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=18.594, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=1.138, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=2.177, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=3.394, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_forces_Pmat_3c", label="hfx_ri_forces_Pmat_3c", y=0.149, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.573, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_sync", label="mp_sync", y=5.32, 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 0.015 178.696 178.696 qs_energies 1 2.0 0.000 0.000 178.509 178.509 mp2_main 1 3.0 0.000 0.000 173.871 173.871 mp2_gpw_main 1 4.0 0.001 0.001 173.418 173.418 mp2_ri_gpw_compute_in 1 5.0 0.385 0.385 122.647 122.647 mp2_ri_gpw_compute_in_loop 1 6.0 0.009 0.009 113.851 113.851 mp2_eri_3c_integrate_gpw 2656 7.0 0.013 0.013 82.954 82.954 integrate_v_rspace 2666 8.0 0.584 0.584 69.830 69.830 grid_integrate_task_list 2666 9.0 67.279 67.279 67.279 67.279 mp2_ri_gpw_compute_en 1 5.0 0.089 0.089 50.746 50.746 mp2_ri_gpw_compute_en_RI_loop 1 6.0 9.522 9.522 48.943 48.943 mp2_ri_gpw_compute_en_expansio 2080 7.0 2.095 2.095 32.156 32.156 local_gemm 2080 8.0 30.061 30.061 30.061 30.061 dbcsr_multiply_generic 5322 8.0 0.188 0.188 20.385 20.385 ao_to_mo_and_store_B_mult_1 2656 7.0 0.009 0.009 20.365 20.365 calculate_wavefunction 2656 8.0 7.987 7.987 11.809 11.809 pw_transfer 63872 10.6 1.028 1.028 11.806 11.806 fft_wrap_pw1pw2 53228 11.4 0.118 0.118 10.568 10.568 ao_to_mo_and_store_B_E_Ex_1 2656 7.0 2.364 2.364 10.418 10.418 multiply_cannon 5322 9.0 0.471 0.471 10.327 10.327 multiply_cannon_loop 5322 10.0 0.122 0.122 8.884 8.884 copy_dbcsr_to_fm 2679 8.0 0.026 0.026 8.606 8.606 get_2c_integrals 1 6.0 0.000 0.000 8.410 8.410 make_m2s 10644 9.0 0.063 0.063 7.907 7.907 make_images 10644 10.0 3.165 3.165 7.610 7.610 compute_2c_integrals 1 7.0 0.005 0.005 7.579 7.579 compute_2c_integrals_loop_lm 1 8.0 0.011 0.011 7.567 7.567 mp2_eri_2c_integrate_gpw 1 9.0 0.792 0.792 7.556 7.556 fft_wrap_pw1pw2_20 21271 12.4 0.483 0.483 7.503 7.503 multiply_cannon_multrec 5322 11.0 7.394 7.394 7.430 7.430 dbcsr_complete_redistribute 2689 9.0 1.154 1.154 6.966 6.966 fft3d_s 53229 13.4 6.420 6.420 6.460 6.460 dbcsr_finalize 10708 9.5 0.187 0.187 6.352 6.352 dbcsr_merge_all 8011 10.3 4.492 4.492 5.695 5.695 mp2_ri_gpw_compute_en_ener 2080 7.0 5.392 5.392 5.392 5.392 scf_env_do_scf 1 3.0 0.000 0.000 4.237 4.237 scf_env_do_scf_inner_loop 10 4.0 0.001 0.001 4.237 4.237 potential_pw2rs 5322 10.0 0.153 0.153 3.903 3.903 ------------------------------------------------------------------------------- From /workspace/artifacts/RI-MP2_ammonia_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.007 0.027 37.465 37.475 qs_energies 1 2.0 0.000 0.001 37.228 37.229 mp2_main 1 3.0 0.000 0.001 35.413 35.413 mp2_gpw_main 1 4.0 0.001 0.004 35.321 35.322 mp2_ri_gpw_compute_en 1 5.0 0.289 0.297 18.441 18.781 mp2_ri_gpw_compute_in 1 5.0 0.051 0.051 16.795 17.171 mp2_ri_gpw_compute_en_RI_loop 1 6.0 3.212 3.586 17.135 17.144 mp2_ri_gpw_compute_in_loop 1 6.0 0.001 0.001 15.585 15.965 mp2_eri_3c_integrate_gpw 83 7.0 0.001 0.001 13.561 13.749 integrate_v_rspace 93 8.1 0.099 0.108 13.428 13.621 grid_integrate_task_list 93 9.1 13.142 13.333 13.142 13.333 mp2_ri_gpw_compute_en_expansio 65 7.0 0.132 0.150 10.429 10.557 local_gemm 65 8.0 10.297 10.407 10.297 10.407 mp2_ri_gpw_compute_en_comm 30 7.0 0.114 0.167 3.128 4.270 mp_sendrecv_dm3 1860 8.0 2.392 3.817 2.392 3.817 dbcsr_multiply_generic 176 8.0 0.008 0.009 1.728 2.104 ao_to_mo_and_store_B_mult_1 83 7.0 0.001 0.001 1.713 2.091 scf_env_do_scf 1 3.0 0.000 0.000 1.685 1.686 scf_env_do_scf_inner_loop 10 4.0 0.000 0.002 1.685 1.685 get_2c_integrals 1 6.0 0.004 0.010 1.133 1.166 multiply_cannon 176 9.0 0.016 0.017 1.014 1.129 multiply_cannon_loop 176 10.0 0.002 0.002 0.959 1.072 make_m2s 352 9.0 0.003 0.004 0.679 0.953 make_images 352 10.0 0.050 0.052 0.666 0.940 multiply_cannon_multrec 246 11.0 0.827 0.884 0.832 0.890 fill_local_i_aL 1920 8.0 0.665 0.859 0.665 0.859 compute_2c_integrals 1 7.0 0.003 0.005 0.832 0.847 qs_scf_new_mos 10 5.0 0.000 0.000 0.775 0.779 compute_2c_integrals_loop_lm 1 8.0 0.002 0.003 0.739 0.768 mp2_eri_2c_integrate_gpw 1 9.0 0.196 0.201 0.737 0.767 mp_min_d 2 7.0 0.401 0.750 0.401 0.750 ------------------------------------------------------------------------------- Plot: name="RI-MP2_ammonia_timings_32omp", title="Timings of RI-MP2_ammonia with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="rest", label="rest", y=56.45299999999999, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=67.279, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="local_gemm", label="local_gemm", y=30.061, 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=9.522, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="calculate_wavefunction", label="calculate_wavefunction", y=7.987, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=7.394, 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=7.595000000000002, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.142, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="local_gemm", label="local_gemm", y=10.297, 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=3.212, 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=0.827, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="mp_sendrecv_dm3", label="mp_sendrecv_dm3", y=2.392, 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 0.083 0.083 119.574 119.574 qs_energies 1 2.0 0.000 0.000 118.142 118.142 scf_env_do_scf 1 3.0 0.000 0.000 111.638 111.638 scf_env_do_scf_inner_loop 15 4.0 0.002 0.002 111.637 111.637 qs_ks_update_qs_env 15 5.0 0.000 0.000 48.225 48.225 rebuild_ks_matrix 15 6.0 0.000 0.000 48.017 48.017 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.002 48.017 48.017 qs_scf_new_mos 15 5.0 0.000 0.000 40.990 40.990 eigensolver 15 6.0 0.002 0.002 33.339 33.339 qs_vxc_create 15 8.0 0.046 0.046 32.952 32.952 calculate_dispersion_nonloc 15 9.0 6.910 6.910 28.671 28.671 pw_transfer 1191 10.0 0.060 0.060 22.295 22.295 fft_wrap_pw1pw2 1086 11.0 0.008 0.008 22.110 22.110 cp_fm_diag_elpa 15 7.0 0.000 0.000 21.550 21.550 cp_fm_diag_elpa_base 15 8.0 18.957 18.957 21.550 21.550 qs_rho_update_rho_low 16 5.0 0.000 0.000 19.476 19.476 calculate_rho_elec 16 6.0 0.214 0.214 19.475 19.475 grid_collocate_task_list 16 7.0 18.133 18.133 18.133 18.133 fft_wrap_pw1pw2_150 765 12.0 3.507 3.507 16.097 16.097 sum_up_and_integrate 15 8.0 0.138 0.138 14.002 14.002 integrate_v_rspace 15 9.0 0.017 0.017 13.864 13.864 grid_integrate_task_list 15 10.0 13.335 13.335 13.335 13.335 fft3d_s 1087 13.0 9.921 9.921 9.927 9.927 cp_fm_cholesky_restore 45 7.0 9.526 9.526 9.526 9.526 pw_scatter_s 585 13.1 6.878 6.878 6.878 6.878 fft_wrap_pw1pw2_200 197 12.3 0.687 0.687 5.812 5.812 copy_dbcsr_to_fm 16 5.9 0.000 0.000 5.554 5.554 dbcsr_complete_redistribute 46 8.3 2.273 2.273 5.481 5.481 cp_fm_upper_to_full 30 8.0 4.854 4.854 4.854 4.854 vdW_energy 15 10.0 4.244 4.244 4.244 4.244 xc_vxc_pw_create 15 9.0 0.257 0.257 4.235 4.235 gspace_mixing 14 5.0 0.171 0.171 4.006 4.006 broyden_mixing 14 6.0 3.427 3.427 3.427 3.427 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 3.071 3.071 init_scf_run 1 3.0 0.000 0.000 2.963 2.963 xc_pw_derive 90 11.0 0.001 0.001 2.756 2.756 calculate_dm_sparse 15 6.0 0.016 0.016 2.452 2.452 ------------------------------------------------------------------------------- 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 0.023 57.892 57.903 qs_energies 1 2.0 0.000 0.000 57.507 57.508 scf_env_do_scf 1 3.0 0.000 0.000 53.606 53.607 scf_env_do_scf_inner_loop 15 4.0 0.001 0.003 53.606 53.607 qs_ks_update_qs_env 15 5.0 0.000 0.000 23.276 23.287 rebuild_ks_matrix 15 6.0 0.000 0.000 23.247 23.258 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.003 23.247 23.258 qs_rho_update_rho_low 16 5.0 0.000 0.000 18.015 18.020 calculate_rho_elec 16 6.0 0.007 0.007 18.015 18.019 grid_collocate_task_list 16 7.0 16.812 17.043 16.812 17.043 sum_up_and_integrate 15 8.0 0.014 0.022 13.473 13.521 integrate_v_rspace 15 9.0 0.001 0.001 13.458 13.512 grid_integrate_task_list 15 10.0 12.781 12.902 12.781 12.902 qs_scf_new_mos 15 5.0 0.000 0.000 12.761 12.802 eigensolver 15 6.0 0.001 0.002 11.785 11.814 qs_vxc_create 15 8.0 0.001 0.001 9.475 9.488 cp_fm_diag_elpa 15 7.0 0.000 0.000 8.247 8.252 cp_fm_diag_elpa_base 15 8.0 8.118 8.134 8.244 8.247 calculate_dispersion_nonloc 15 9.0 0.892 0.903 7.592 7.618 pw_transfer 1191 10.0 0.084 0.109 7.377 7.422 fft_wrap_pw1pw2 1086 11.0 0.011 0.014 7.222 7.293 fft3d_ps 1086 13.0 2.523 2.869 4.885 5.457 fft_wrap_pw1pw2_150 765 12.0 0.579 0.719 4.644 4.677 cp_fm_cholesky_restore 45 7.0 3.396 3.467 3.396 3.467 mp_alltoall_z22v 1086 15.0 1.850 2.912 1.850 2.912 fft_wrap_pw1pw2_200 197 12.3 0.371 0.484 2.473 2.508 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 2.418 2.418 build_core_hamiltonian_matrix 1 4.0 0.000 0.000 2.130 2.322 xc_vxc_pw_create 15 9.0 0.014 0.019 1.883 1.920 x_to_yz 585 14.1 0.311 0.354 1.268 1.788 yz_to_x 501 13.9 0.176 0.202 1.069 1.619 build_core_ppnl 1 5.0 1.243 1.355 1.243 1.355 xc_pw_derive 90 11.0 0.001 0.002 1.273 1.343 vdW_energy 15 10.0 1.241 1.327 1.241 1.327 init_scf_run 1 3.0 0.000 0.001 1.238 1.239 rs_pw_transfer 158 9.4 0.002 0.002 0.993 1.238 density_rs2pw 16 7.0 0.001 0.001 0.998 1.182 ------------------------------------------------------------------------------- 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=49.702, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=18.957, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=18.133, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.335, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="fft3d_s", label="fft3d_s", y=9.921, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=9.526, 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=14.262, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=8.118, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=16.812, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=12.781, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="fft3d_s", label="fft3d_s", y=0.0, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=3.396, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=2.523, yerr=0.0 Running bench_dftb.inp with 1 threads and 32 ranks... done. Running bench_dftb.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/bench_dftb_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.073 0.073 271.013 271.013 qs_energies 1 2.0 0.000 0.000 270.878 270.878 ls_scf 1 3.0 0.000 0.000 269.654 269.654 ls_scf_main 1 4.0 0.002 0.002 260.582 260.582 density_matrix_trs4 11 5.0 0.012 0.012 169.161 169.161 ls_scf_dm_to_ks 11 5.0 0.000 0.000 86.229 86.229 arnoldi_extremal 12 6.1 0.000 0.000 85.554 85.554 arnoldi_normal_ev 12 7.1 0.031 0.031 85.554 85.554 build_subspace 23 8.1 0.075 0.075 84.009 84.009 dbcsr_matrix_vector_mult 652 9.0 0.189 0.189 83.254 83.254 matrix_ls_to_qs 11 6.0 0.000 0.000 82.961 82.961 dbcsr_matrix_vector_mult_local 652 10.0 81.830 81.830 81.840 81.840 dbcsr_multiply_generic 185 6.1 0.855 0.855 72.564 72.564 dbcsr_copy_into_existing 11 7.0 45.661 45.661 45.661 45.661 multiply_cannon 185 7.1 0.315 0.315 43.503 43.503 dbcsr_complete_redistribute 23 7.5 30.126 30.126 40.938 40.938 matrix_decluster 11 7.0 0.000 0.000 37.299 37.299 multiply_cannon_loop 185 8.1 0.230 0.230 30.982 30.982 make_m2s 370 7.1 0.038 0.038 24.603 24.603 make_images 370 8.1 10.509 10.509 23.105 23.105 multiply_cannon_multrec 185 9.1 21.666 21.666 21.692 21.692 dbcsr_finalize 646 7.5 0.188 0.188 14.558 14.558 dbcsr_merge_all 597 8.5 2.384 2.384 13.427 13.427 setup_rec_index_2d 370 8.1 12.113 12.113 12.113 12.113 dbcsr_sort_indices 1103 9.9 10.743 10.743 10.743 10.743 tree_to_linear_d 110 9.4 9.847 9.847 9.847 9.847 quick_finalize 395 10.0 0.338 0.338 9.247 9.247 calculate_norms 370 9.1 9.060 9.060 9.060 9.060 dbcsr_special_finalize 370 9.1 0.002 0.002 8.552 8.552 ls_scf_init_scf 1 4.0 0.000 0.000 8.408 8.408 ls_scf_init_matrix_S 1 5.0 0.000 0.000 8.078 8.078 matrix_sqrt_Newton_Schulz 1 6.0 0.001 0.001 7.447 7.447 ------------------------------------------------------------------------------- From /workspace/artifacts/bench_dftb_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.007 0.021 64.713 64.723 qs_energies 1 2.0 0.000 0.000 64.593 64.594 ls_scf 1 3.0 0.000 0.000 64.545 64.546 ls_scf_main 1 4.0 0.000 0.007 62.072 62.073 density_matrix_trs4 11 5.0 0.006 0.017 59.609 59.682 dbcsr_multiply_generic 185 6.1 0.055 0.068 56.583 56.808 multiply_cannon 185 7.1 0.032 0.036 46.389 47.359 multiply_cannon_loop 185 8.1 0.102 0.117 44.118 44.947 multiply_cannon_multrec 1480 9.1 26.923 29.944 27.152 30.190 mp_waitall_1 11936 10.3 15.251 18.113 15.251 18.113 multiply_cannon_metrocomm3 1480 9.1 0.013 0.016 11.613 15.022 make_m2s 370 7.1 0.034 0.035 6.398 6.469 make_images 370 8.1 0.617 0.644 6.271 6.342 calculate_norms 2960 9.1 4.179 4.823 4.179 4.823 mp_sum_l 1199 5.3 2.879 4.151 2.879 4.151 dbcsr_multiply_generic_mpsum_f 137 7.1 0.000 0.000 1.997 3.132 make_images_data 370 9.1 0.010 0.012 2.853 3.106 hybrid_alltoall_any 393 9.9 0.207 0.993 2.478 2.810 arnoldi_extremal 12 6.1 0.000 0.001 2.217 2.256 arnoldi_normal_ev 12 7.1 0.001 0.007 2.217 2.255 ls_scf_dm_to_ks 11 5.0 0.000 0.000 2.122 2.252 build_subspace 23 8.1 0.019 0.024 2.131 2.133 dbcsr_complete_redistribute 23 7.5 1.164 1.234 1.912 1.985 multiply_cannon_metrocomm1 1480 9.1 0.005 0.007 1.038 1.981 matrix_ls_to_qs 11 6.0 0.000 0.000 1.856 1.931 dbcsr_matrix_vector_mult 652 9.0 0.013 0.047 1.860 1.919 ls_scf_init_scf 1 4.0 0.000 0.000 1.897 1.898 ls_scf_init_matrix_S 1 5.0 0.000 0.000 1.870 1.878 matrix_decluster 11 7.0 0.000 0.000 1.716 1.790 make_images_pack 370 9.1 1.553 1.752 1.556 1.757 matrix_sqrt_Newton_Schulz 1 6.0 0.000 0.001 1.703 1.703 dbcsr_matrix_vector_mult_local 652 10.0 1.560 1.642 1.562 1.644 buffer_matrices_ensure_size 370 8.1 1.228 1.462 1.228 1.462 dbcsr_finalize 646 7.5 0.007 0.008 1.167 1.312 ------------------------------------------------------------------------------- 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=70.55699999999999, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=81.83, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_copy_into_existing", label="dbcsr_copy_into_existing", y=45.661, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_complete_redistribute", label="dbcsr_complete_redistribute", y=30.126, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=21.666, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="setup_rec_index_2d", label="setup_rec_index_2d", y=12.113, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="calculate_norms", label="calculate_norms", y=9.06, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="mp_sum_l", label="mp_sum_l", y=0.0, yerr=0.0 Plot: name="bench_dftb_timings_32mpi", title="Timings of bench_dftb with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="bench_dftb_timings_32mpi", name="rest", label="rest", y=12.756999999999998, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=1.56, 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=1.164, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=26.923, 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=4.179, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=15.251, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=2.879, 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 69.572 69.572 lib_test 1 2.0 0.000 0.000 69.564 69.564 dbcsr_run_tests 3 3.0 0.002 0.002 69.564 69.564 test_multiplies_multiproc 3 4.0 0.001 0.001 54.290 54.290 dbcsr_redistribute 9 5.0 35.888 35.888 37.470 37.470 dbcsr_multiply_generic 9 5.0 0.001 0.001 15.495 15.495 dbcsr_make_random_matrix 9 4.0 12.287 12.287 15.165 15.165 multiply_cannon 9 6.0 0.002 0.002 10.861 10.861 multiply_cannon_loop 9 7.0 0.014 0.014 10.503 10.503 multiply_cannon_multrec 9 8.0 10.488 10.488 10.489 10.489 dbcsr_finalize 27 5.7 0.009 0.009 5.337 5.337 dbcsr_merge_all 18 6.5 1.919 1.919 4.614 4.614 dbcsr_data_release 975 7.6 2.808 2.808 2.808 2.808 tree_to_linear_d 9 7.0 1.867 1.867 1.867 1.867 make_m2s 18 6.0 0.001 0.001 1.602 1.602 make_images 18 7.0 0.549 0.549 1.547 1.547 ------------------------------------------------------------------------------- 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 0.010 18.425 18.430 lib_test 1 2.0 0.000 0.000 18.388 18.410 dbcsr_run_tests 3 3.0 0.000 0.001 18.387 18.409 test_multiplies_multiproc 3 4.0 0.000 0.002 17.552 17.604 dbcsr_multiply_generic 9 5.0 0.001 0.001 15.895 16.002 multiply_cannon 9 6.0 0.001 0.002 13.953 14.307 multiply_cannon_loop 9 7.0 0.002 0.002 13.683 14.065 multiply_cannon_multrec 72 8.0 10.357 10.905 10.358 10.906 mp_waitall_1 576 9.2 3.644 4.458 3.644 4.458 multiply_cannon_metrocomm1 72 8.0 0.001 0.001 3.219 3.962 mp_sum_l 470 2.5 0.728 1.205 0.728 1.205 dbcsr_multiply_generic_mpsum_f 9 6.0 0.000 0.000 0.719 1.197 dbcsr_data_release 444 7.6 0.741 0.819 0.741 0.819 dbcsr_make_random_matrix 9 4.0 0.653 0.668 0.790 0.818 make_m2s 18 6.0 0.001 0.001 0.684 0.727 make_images 18 7.0 0.021 0.023 0.680 0.724 dbcsr_destroy 111 5.9 0.003 0.074 0.657 0.722 dbcsr_finalize 27 5.7 0.000 0.000 0.498 0.610 dbcsr_redistribute 9 5.0 0.230 0.273 0.512 0.549 dbcsr_merge_all 18 6.5 0.072 0.086 0.411 0.492 make_images_data 18 8.0 0.000 0.001 0.357 0.442 hybrid_alltoall_any 18 9.0 0.032 0.156 0.298 0.371 ------------------------------------------------------------------------------- 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=6.182000000000009, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_redistribute", label="dbcsr_redistribute", y=35.888, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=12.287, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=10.488, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_data_release", label="dbcsr_data_release", y=2.808, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_merge_all", label="dbcsr_merge_all", y=1.919, 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=2.0000000000000036, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_redistribute", label="dbcsr_redistribute", y=0.23, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=0.653, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=10.357, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_data_release", label="dbcsr_data_release", y=0.741, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_merge_all", label="dbcsr_merge_all", y=0.072, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=3.644, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=0.728, yerr=0.0 Running MQAE_single_node.inp with 1 threads and 32 ranks... done. Running MQAE_single_node.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/MQAE_single_node_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.052 0.052 129.380 129.380 qs_mol_dyn_low 1 2.0 0.003 0.003 127.982 127.982 velocity_verlet 5 3.0 0.003 0.003 104.528 104.528 qmmm_el_coupling 6 3.8 0.000 0.000 84.909 84.909 qmmm_elec_with_gaussian 6 4.8 0.011 0.011 84.905 84.905 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 84.291 84.291 qmmm_elec_gaussian_low_G 6 6.8 83.401 83.401 83.401 83.401 qs_forces 6 3.8 0.001 0.001 34.812 34.812 qs_energies 6 4.8 0.000 0.000 30.927 30.927 scf_env_do_scf 6 5.8 0.001 0.001 28.667 28.667 scf_env_do_scf_inner_loop 39 6.8 0.004 0.004 24.939 24.939 rebuild_ks_matrix 45 8.4 0.000 0.000 24.147 24.147 qs_ks_build_kohn_sham_matrix 45 9.4 0.005 0.005 24.147 24.147 qs_ks_update_qs_env 45 7.8 0.000 0.000 20.684 20.684 pw_transfer 966 12.3 0.052 0.052 17.380 17.380 fft_wrap_pw1pw2 801 13.6 0.006 0.006 17.193 17.193 fft_wrap_pw1pw2_150 507 15.2 2.309 2.309 16.791 16.791 qs_vxc_create 45 10.4 0.001 0.001 13.239 13.239 xc_vxc_pw_create 45 11.4 0.697 0.697 13.238 13.238 xc_pw_derive 270 13.4 0.002 0.002 9.319 9.319 fft3d_s 802 15.6 7.905 7.905 7.912 7.912 qs_rho_update_rho_low 45 7.9 0.000 0.000 6.966 6.966 calculate_rho_elec 45 8.9 0.563 0.563 6.965 6.965 xc_rho_set_and_dset_create 45 12.4 0.601 0.601 6.748 6.748 xc_pw_divergence 45 12.4 0.001 0.001 5.727 5.727 pw_scatter_s 429 15.8 5.722 5.722 5.722 5.722 qmmm_forces 6 3.8 0.002 0.002 5.170 5.170 qmmm_forces_with_gaussian 6 4.8 0.017 0.017 4.835 4.835 pw_integral_ab 2539 7.4 4.510 4.510 4.510 4.510 qs_ks_ddapc 45 10.4 0.001 0.001 4.217 4.217 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 4.120 4.120 init_scf_loop 6 6.8 0.000 0.000 3.723 3.723 sum_up_and_integrate 45 10.4 0.481 0.481 3.569 3.569 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 3.471 3.471 qmmm_forces_gaussian_low_G 6 6.8 3.425 3.425 3.425 3.425 density_rs2pw 45 9.9 0.002 0.002 3.278 3.278 grid_collocate_task_list 45 9.9 3.125 3.125 3.125 3.125 integrate_v_rspace 45 11.4 0.006 0.006 3.088 3.088 ------------------------------------------------------------------------------- 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 0.041 0.062 55.530 55.545 qs_mol_dyn_low 1 2.0 0.003 0.003 54.455 54.514 qs_forces 6 3.8 0.001 0.001 40.509 40.509 qs_energies 6 4.8 0.000 0.000 38.712 38.712 scf_env_do_scf 6 5.8 0.000 0.001 37.759 37.760 scf_env_do_scf_inner_loop 113 6.2 0.002 0.016 36.215 36.216 rebuild_ks_matrix 119 8.1 0.000 0.000 26.246 26.254 qs_ks_build_kohn_sham_matrix 119 9.1 0.014 0.017 26.246 26.254 qs_ks_update_qs_env 119 7.3 0.001 0.001 24.728 24.735 velocity_verlet 5 3.0 0.002 0.003 22.566 22.569 pw_transfer 2446 12.3 0.180 0.209 18.538 19.078 fft_wrap_pw1pw2 2059 13.4 0.022 0.027 18.156 18.755 fft_wrap_pw1pw2_150 1321 14.9 2.680 3.262 17.522 18.079 qs_vxc_create 119 10.1 0.002 0.002 14.054 14.061 xc_vxc_pw_create 119 11.1 0.141 0.210 14.052 14.059 fft3d_ps 2059 15.4 6.758 7.752 12.127 13.692 xc_pw_derive 714 13.1 0.010 0.012 10.751 10.994 qs_rho_update_rho_low 119 7.3 0.000 0.001 10.339 10.340 calculate_rho_elec 119 8.3 0.049 0.057 10.339 10.340 sum_up_and_integrate 119 10.1 0.065 0.077 8.919 8.941 integrate_v_rspace 119 11.1 0.003 0.003 8.854 8.878 xc_pw_divergence 119 12.1 0.004 0.006 6.982 7.218 qmmm_forces 6 3.8 0.002 0.002 7.123 7.123 qmmm_forces_with_gaussian 6 4.8 0.006 0.006 6.725 7.000 xc_rho_set_and_dset_create 119 12.1 0.307 0.379 6.683 6.891 rs_pw_transfer 988 11.5 0.011 0.015 6.106 6.240 density_rs2pw 119 9.3 0.006 0.008 6.011 6.205 qmmm_el_coupling 6 3.8 0.000 0.000 5.898 6.053 qmmm_elec_with_gaussian 6 4.8 0.003 0.003 5.897 6.052 mp_alltoall_z22v 2059 17.4 4.179 5.897 4.179 5.897 potential_pw2rs 119 12.1 0.006 0.006 5.261 5.286 grid_collocate_task_list 119 9.3 4.122 4.334 4.122 4.334 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 3.826 3.877 x_to_yz 1095 16.8 0.685 0.788 2.872 3.695 grid_integrate_task_list 119 12.1 3.334 3.506 3.334 3.506 yz_to_x 964 16.0 0.447 0.581 2.439 3.388 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 3.295 3.319 qmmm_forces_gaussian_low_G 6 6.8 3.145 3.197 3.145 3.197 qs_scf_new_mos 113 7.2 0.000 0.000 2.964 2.968 qs_scf_loop_do_ot 113 8.2 0.000 0.001 2.963 2.968 mp_waitany 4028 12.8 2.434 2.951 2.434 2.951 ot_scf_mini 113 9.2 0.001 0.001 2.878 2.882 qmmm_elec_gaussian_low_G 6 6.8 2.706 2.729 2.706 2.729 pw_restrict_s3 18 5.8 1.267 1.321 2.322 2.565 rs_pw_transfer_PW2RS_150 125 13.9 0.738 0.911 2.288 2.354 qmmm_elec_with_gaussian:spline 6 5.8 0.000 0.000 1.957 2.112 pw_prolongate_s3 18 6.8 1.087 1.124 1.957 2.112 qs_ks_ddapc 119 10.1 0.002 0.003 1.945 2.076 rs_pw_transfer_RS2PW_150 125 11.2 0.656 0.842 1.881 2.050 pw_gather_p 964 15.0 1.768 2.012 1.768 2.012 dbcsr_multiply_generic 2588 12.3 0.058 0.059 1.936 1.984 pw_scatter_p 1095 15.8 1.517 1.545 1.517 1.545 init_scf_loop 6 6.8 0.000 0.000 1.541 1.541 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 1.527 1.528 pw_integral_ab 2761 7.7 1.076 1.278 1.377 1.481 qs_ot_get_p 119 10.2 0.000 0.000 1.415 1.424 mp_sum_d 5822 12.2 0.838 1.373 0.838 1.373 ot_mini 113 10.2 0.000 0.001 1.237 1.241 mp_waitall_1 177795 16.4 1.004 1.224 1.004 1.224 mp_sum_dm3 33 5.7 1.125 1.172 1.125 1.172 qs_ot_p2m_diag 86 11.0 0.002 0.006 1.142 1.148 ------------------------------------------------------------------------------- Plot: name="MQAE_single_node_timings_32omp", title="Timings of MQAE_single_node with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="MQAE_single_node_timings_32omp", name="rest", label="rest", y=21.292, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=83.401, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_s", label="fft3d_s", y=7.905, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_scatter_s", label="pw_scatter_s", y=5.722, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_integral_ab", label="pw_integral_ab", y=4.51, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.425, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=3.125, 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="mp_alltoall_z22v", label="mp_alltoall_z22v", y=0.0, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_ps", label="fft3d_ps", y=0.0, yerr=0.0 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=30.210000000000004, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=2.706, 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=1.076, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.145, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=4.122, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=3.334, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=4.179, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=6.758, yerr=0.0 Summary: Performance test took 32 minutes. Status: OK Removing intermediate container 4fb07fd1582c ---> 94733c511604 Step 41/42 : CMD cat $(find ./report.log -mmin +10) | sed '/^Summary:/ s/$/ (cached)/' ---> Running in e9a75ae27e3d Removing intermediate container e9a75ae27e3d ---> b4a522b440bb Step 42/42 : ENTRYPOINT [] ---> Running in 734854cc7085 Removing intermediate container 734854cc7085 ---> d1c46819fce7 [Warning] One or more build-args [GIT_COMMIT_SHA] were not consumed Successfully built d1c46819fce7 Successfully tagged us-central1-docker.pkg.dev/cp2k-org-project/cp2kci/img_cp2k-perf-openmp:master Pushing new image... done. #################### Running Image cp2k-perf-openmp #################### Uploading artifacts... done EndDate: 2023-06-10 20:04:39+00:00