StartDate: 2022-06-30 11:11:18+00:00 CpuId: 32x AMD (unknown model) [Zen 3], 7nm (SMT disabled) CommitSHA: fb5b8f2570f6bb37b6305d8107202a4d22ff4053 CommitTime: 2022-06-30 12:19:34 +0200 CommitAuthor: Matthias Krack CommitSubject: Print input selection for PERIODIC_EFIELD in output Populating docker build cache... done. #################### Building Image cp2k-perf-openmp #################### Dockerfile: /tools/docker/Dockerfile.test_performance Build-Path: / Build-Args: GIT_COMMIT_SHA=fb5b8f2570f6bb37b6305d8107202a4d22ff4053 Sending build context to Docker daemon 363.2MB Step 1/42 : FROM ubuntu:22.04 22.04: Pulling from library/ubuntu 405f018f9d1d: Already exists Digest: sha256:b6b83d3c331794420340093eb706a6f152d9c1fa51b262d9bf34594887c2c7ac Status: Downloaded newer image for ubuntu:22.04 ---> 27941809078c Step 2/42 : WORKDIR /opt/cp2k-toolchain ---> Using cache ---> 92ee757f28a3 Step 3/42 : COPY ./tools/toolchain/install_requirements*.sh ./ ---> Using cache ---> a398cc4ae5b3 Step 4/42 : RUN ./install_requirements.sh ubuntu:22.04 ---> Using cache ---> e20712e9c254 Step 5/42 : RUN mkdir scripts ---> Using cache ---> c7b9413ca6be 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 ---> 5f4bcd2de9f5 Step 7/42 : COPY ./tools/toolchain/install_cp2k_toolchain.sh . ---> Using cache ---> c39d97839810 Step 8/42 : RUN ./install_cp2k_toolchain.sh --install-all --mpi-mode=mpich --with-gcc=system --dry-run ---> Using cache ---> d0b21d05b338 Step 9/42 : COPY ./tools/toolchain/scripts/stage0/ ./scripts/stage0/ ---> Using cache ---> 6e616c7670ff Step 10/42 : RUN ./scripts/stage0/install_stage0.sh && rm -rf ./build ---> Using cache ---> 5ba44cd61a38 Step 11/42 : COPY ./tools/toolchain/scripts/stage1/ ./scripts/stage1/ ---> Using cache ---> 1aa896c19a24 Step 12/42 : RUN ./scripts/stage1/install_stage1.sh && rm -rf ./build ---> Using cache ---> c7ccbf5e1b85 Step 13/42 : COPY ./tools/toolchain/scripts/stage2/ ./scripts/stage2/ ---> Using cache ---> 9cb6a1bd2cd3 Step 14/42 : RUN ./scripts/stage2/install_stage2.sh && rm -rf ./build ---> Using cache ---> 1eed70bdd06a Step 15/42 : COPY ./tools/toolchain/scripts/stage3/ ./scripts/stage3/ ---> Using cache ---> ac04ff4ae473 Step 16/42 : RUN ./scripts/stage3/install_stage3.sh && rm -rf ./build ---> Using cache ---> cd0e2369620a Step 17/42 : COPY ./tools/toolchain/scripts/stage4/ ./scripts/stage4/ ---> Using cache ---> 1b4ef27dc823 Step 18/42 : RUN ./scripts/stage4/install_stage4.sh && rm -rf ./build ---> Using cache ---> 8c2ce1cbdb23 Step 19/42 : COPY ./tools/toolchain/scripts/stage5/ ./scripts/stage5/ ---> Using cache ---> c08a0bc6f0ef Step 20/42 : RUN ./scripts/stage5/install_stage5.sh && rm -rf ./build ---> Using cache ---> 377bc99f74ae Step 21/42 : COPY ./tools/toolchain/scripts/stage6/ ./scripts/stage6/ ---> Using cache ---> 415f340401e7 Step 22/42 : RUN ./scripts/stage6/install_stage6.sh && rm -rf ./build ---> Using cache ---> 46d9c769ebc6 Step 23/42 : COPY ./tools/toolchain/scripts/stage7/ ./scripts/stage7/ ---> Using cache ---> 6aafee7e9835 Step 24/42 : RUN ./scripts/stage7/install_stage7.sh && rm -rf ./build ---> Using cache ---> 2e0fc7bba01b Step 25/42 : COPY ./tools/toolchain/scripts/stage8/ ./scripts/stage8/ ---> Using cache ---> dd31a4351cf1 Step 26/42 : RUN ./scripts/stage8/install_stage8.sh && rm -rf ./build ---> Using cache ---> a67db58bafbb Step 27/42 : COPY ./tools/toolchain/scripts/arch_base.tmpl ./tools/toolchain/scripts/generate_arch_files.sh ./scripts/ ---> Using cache ---> e7d1480e5889 Step 28/42 : RUN ./scripts/generate_arch_files.sh && rm -rf ./build ---> Using cache ---> f822acadf693 Step 29/42 : WORKDIR /opt/cp2k ---> Using cache ---> 0b0fdcc56471 Step 30/42 : COPY ./Makefile . ---> Using cache ---> a38c6462aef8 Step 31/42 : COPY ./src ./src ---> 526414a9a75c Step 32/42 : COPY ./exts ./exts ---> 811e0d878267 Step 33/42 : COPY ./tools/build_utils ./tools/build_utils ---> f96137474c53 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 c34c7844b9bb './arch/local.psmp' -> '/opt/cp2k-toolchain/install/arch/local.psmp' Compiling cp2k... Removing intermediate container c34c7844b9bb ---> eb872b56d3a0 Step 35/42 : COPY ./data ./data ---> b8fb3eeb574a Step 36/42 : COPY ./tests ./tests ---> 4054408d37e5 Step 37/42 : COPY ./tools/regtesting ./tools/regtesting ---> 26e14b349430 Step 38/42 : COPY ./benchmarks ./benchmarks ---> eb193a604267 Step 39/42 : COPY ./tools/docker/scripts/test_performance.sh ./tools/docker/scripts/plot_performance.py ./ ---> 8a3c9371e71c Step 40/42 : RUN ./test_performance.sh "local" 2>&1 | tee report.log ---> Running in 2c965868054c ========== Compiling CP2K ========== Compiling cp2k... done. Checking benchmark inputs... Found 60 input files and 0 errors. ========== Running Performance Test ========== Running H2O-64.inp with 1 threads and 32 ranks... done. Running H2O-64.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/H2O-64_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.028 0.028 196.668 196.668 qs_mol_dyn_low 1 2.0 0.003 0.003 196.022 196.022 qs_forces 11 3.9 0.001 0.001 195.983 195.983 qs_energies 11 4.9 0.001 0.001 189.628 189.628 scf_env_do_scf 11 5.9 0.001 0.001 176.947 176.947 velocity_verlet 10 3.0 0.002 0.002 137.531 137.531 init_scf_loop 11 6.9 0.000 0.000 95.874 95.874 prepare_preconditioner 11 7.9 0.000 0.000 93.301 93.301 make_preconditioner 11 8.9 0.000 0.000 93.301 93.301 make_full_inverse_cholesky 11 9.9 0.000 0.000 92.186 92.186 scf_env_do_scf_inner_loop 108 6.5 0.011 0.011 80.937 80.937 cp_fm_cholesky_invert 11 10.9 62.619 62.619 62.619 62.619 qs_scf_new_mos 108 7.5 0.001 0.001 43.268 43.268 qs_scf_loop_do_ot 108 8.5 0.001 0.001 43.267 43.267 ot_scf_mini 108 9.5 0.003 0.003 41.721 41.721 cp_fm_cholesky_decompose 22 10.9 25.686 25.686 25.686 25.686 qs_ot_get_p 119 10.4 0.001 0.001 23.108 23.108 rebuild_ks_matrix 119 8.3 0.001 0.001 22.102 22.102 qs_ks_build_kohn_sham_matrix 119 9.3 0.013 0.013 22.102 22.102 qs_ot_p2m_diag 50 11.0 0.156 0.156 21.660 21.660 qs_rho_update_rho 119 7.7 0.001 0.001 21.400 21.400 calculate_rho_elec 119 8.7 0.966 0.966 21.399 21.399 cp_dbcsr_syevd 50 12.0 0.003 0.003 21.248 21.248 dbcsr_multiply_generic 2286 12.5 0.178 0.178 21.084 21.084 qs_ks_update_qs_env 119 7.6 0.001 0.001 20.322 20.322 cp_fm_diag_elpa 50 13.0 0.000 0.000 19.913 19.913 cp_fm_diag_elpa_base 50 14.0 19.850 19.850 19.912 19.912 grid_collocate_task_list 119 9.7 16.676 16.676 16.676 16.676 ot_mini 108 10.5 0.001 0.001 14.841 14.841 sum_up_and_integrate 119 10.3 0.224 0.224 13.981 13.981 integrate_v_rspace 119 11.3 0.109 0.109 13.757 13.757 grid_integrate_task_list 119 12.3 11.538 11.538 11.538 11.538 make_m2s 4572 13.5 0.048 0.048 10.960 10.960 qs_ot_get_derivative 108 11.5 0.001 0.001 9.241 9.241 pw_transfer 1439 11.6 0.062 0.062 6.486 6.486 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 6.306 6.306 fft_wrap_pw1pw2 1201 12.6 0.007 0.007 6.237 6.237 dbcsr_make_dense_low 5837 15.5 0.070 0.070 5.937 5.937 multiply_cannon 2286 13.5 0.185 0.185 5.896 5.896 make_dense_data 5837 16.5 5.208 5.208 5.853 5.853 ot_diis_step 108 11.5 0.004 0.004 5.596 5.596 make_images 4572 14.5 2.110 2.110 5.463 5.463 init_scf_run 11 5.9 0.002 0.002 5.460 5.460 scf_env_initial_rho_setup 11 6.9 0.001 0.001 5.458 5.458 multiply_cannon_loop 2286 14.5 0.101 0.101 5.405 5.405 multiply_cannon_multrec 2286 15.5 5.250 5.250 5.303 5.303 fft_wrap_pw1pw2_140 487 13.2 0.464 0.464 5.193 5.193 dbcsr_make_images_dense 3978 14.8 0.019 0.019 5.158 5.158 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 5.060 5.060 apply_single 119 13.6 0.000 0.000 5.060 5.060 wfi_extrapolate 11 7.9 0.001 0.001 4.935 4.935 ------------------------------------------------------------------------------- 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 0.022 53.550 53.561 qs_mol_dyn_low 1 2.0 0.004 0.006 53.429 53.434 qs_forces 11 3.9 0.001 0.002 53.384 53.385 qs_energies 11 4.9 0.001 0.001 49.607 49.609 scf_env_do_scf 11 5.9 0.001 0.002 45.516 45.517 scf_env_do_scf_inner_loop 108 6.5 0.003 0.022 42.015 42.015 velocity_verlet 10 3.0 0.002 0.004 32.090 32.091 rebuild_ks_matrix 119 8.3 0.001 0.001 20.843 20.938 qs_ks_build_kohn_sham_matrix 119 9.3 0.016 0.021 20.842 20.938 qs_ks_update_qs_env 119 7.6 0.001 0.001 18.574 18.661 sum_up_and_integrate 119 10.3 0.021 0.027 16.032 16.079 integrate_v_rspace 119 11.3 0.004 0.006 16.010 16.058 qs_rho_update_rho 119 7.7 0.001 0.001 15.524 15.530 calculate_rho_elec 119 8.7 0.031 0.040 15.524 15.530 dbcsr_multiply_generic 2286 12.5 0.078 0.090 14.222 14.409 grid_integrate_task_list 119 12.3 8.930 11.918 8.930 11.918 grid_collocate_task_list 119 9.7 9.956 11.794 9.956 11.794 qs_scf_new_mos 108 7.5 0.001 0.001 11.265 11.332 qs_scf_loop_do_ot 108 8.5 0.001 0.001 11.264 11.331 multiply_cannon 2286 13.5 0.144 0.158 10.323 10.739 ot_scf_mini 108 9.5 0.002 0.003 10.549 10.606 multiply_cannon_loop 2286 14.5 0.099 0.116 9.679 10.129 mp_waitall_1 169478 16.3 8.537 8.973 8.537 8.973 rs_pw_transfer 974 11.9 0.012 0.014 6.439 6.898 ot_mini 108 10.5 0.001 0.001 6.108 6.177 multiply_cannon_metrocomm3 18288 15.5 0.041 0.050 5.491 6.087 density_rs2pw 119 9.7 0.006 0.007 5.172 5.629 potential_pw2rs 119 12.3 0.007 0.009 3.896 3.917 pw_transfer 1439 11.6 0.099 0.109 3.758 3.831 mp_alltoall_d11v 2130 13.8 3.405 3.764 3.405 3.764 fft_wrap_pw1pw2 1201 12.6 0.010 0.013 3.581 3.656 multiply_cannon_multrec 18288 15.5 3.312 3.543 3.323 3.556 rs_gather_matrices 119 12.3 0.085 0.106 3.142 3.509 init_scf_loop 11 6.9 0.000 0.000 3.486 3.486 mp_waitany 9880 13.7 2.794 3.308 2.794 3.308 qs_ot_get_derivative 108 11.5 0.001 0.001 3.115 3.174 fft_wrap_pw1pw2_140 487 13.2 0.318 0.348 3.050 3.145 rs_pw_transfer_RS2PW_140 130 11.5 0.330 0.392 2.533 3.004 ot_diis_step 108 11.5 0.004 0.004 2.967 2.967 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 2.854 2.952 apply_single 119 13.6 0.000 0.001 2.854 2.951 init_scf_run 11 5.9 0.000 0.005 2.763 2.763 scf_env_initial_rho_setup 11 6.9 0.000 0.004 2.762 2.763 fft3d_ps 1201 14.6 1.352 1.440 2.603 2.663 make_m2s 4572 13.5 0.049 0.059 2.597 2.661 wfi_extrapolate 11 7.9 0.001 0.001 2.500 2.500 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 2.422 2.430 make_images 4572 14.5 0.124 0.146 2.245 2.313 rs_pw_transfer_PW2RS_140 130 13.9 0.685 0.736 1.641 1.687 qs_ot_get_p 119 10.4 0.001 0.001 1.385 1.504 mp_sum_d 4129 12.0 1.134 1.423 1.134 1.423 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 0.958 1.330 make_images_data 4572 15.5 0.037 0.043 1.183 1.300 prepare_preconditioner 11 7.9 0.000 0.000 1.231 1.251 make_preconditioner 11 8.9 0.000 0.000 1.231 1.251 hybrid_alltoall_any 4725 16.4 0.072 0.241 1.049 1.173 make_full_inverse_cholesky 11 9.9 0.000 0.000 1.113 1.132 qs_energies_init_hamiltonians 11 5.9 0.000 0.001 1.126 1.126 mp_sum_l 11218 13.2 0.812 1.087 0.812 1.087 ------------------------------------------------------------------------------- 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=55.04900000000001, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=62.619, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=25.686, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=19.85, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=16.676, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=11.538, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=5.25, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="mp_alltoall_d11v", label="mp_alltoall_d11v", 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=19.409999999999997, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=9.956, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=8.93, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=3.312, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_alltoall_d11v", label="mp_alltoall_d11v", y=3.405, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=8.537, 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 0.029 0.029 218.264 218.264 qs_mol_dyn_low 1 2.0 0.002 0.002 217.598 217.598 qs_forces 11 3.9 0.001 0.001 217.560 217.560 qs_energies 11 4.9 0.001 0.001 209.470 209.470 scf_env_do_scf 11 5.9 0.001 0.001 194.608 194.608 velocity_verlet 10 3.0 0.002 0.002 151.820 151.820 init_scf_loop 11 6.9 0.000 0.000 98.588 98.588 scf_env_do_scf_inner_loop 96 6.5 0.010 0.010 95.874 95.874 prepare_preconditioner 11 7.9 0.000 0.000 94.289 94.289 make_preconditioner 11 8.9 0.000 0.000 94.289 94.289 make_full_inverse_cholesky 11 9.9 0.000 0.000 93.127 93.127 cp_fm_cholesky_invert 11 10.9 64.906 64.906 64.906 64.906 qs_scf_new_mos 96 7.5 0.001 0.001 37.405 37.405 qs_scf_loop_do_ot 96 8.5 0.001 0.001 37.405 37.405 ot_scf_mini 96 9.5 0.002 0.002 36.072 36.072 rebuild_ks_matrix 107 8.3 0.001 0.001 35.606 35.606 qs_ks_build_kohn_sham_matrix 107 9.3 0.011 0.011 35.605 35.605 qs_rho_update_rho 107 7.7 0.001 0.001 33.717 33.717 calculate_rho_elec 107 8.7 0.878 0.878 33.717 33.717 qs_ks_update_qs_env 107 7.6 0.001 0.001 31.934 31.934 grid_collocate_task_list 107 9.7 29.491 29.491 29.491 29.491 sum_up_and_integrate 107 10.3 0.193 0.193 28.068 28.068 integrate_v_rspace 107 11.3 0.099 0.099 27.875 27.875 grid_integrate_task_list 107 12.3 25.930 25.930 25.930 25.930 cp_fm_cholesky_decompose 22 10.9 24.144 24.144 24.144 24.144 qs_ot_get_p 107 10.4 0.001 0.001 19.655 19.655 dbcsr_multiply_generic 1966 12.4 0.157 0.157 18.945 18.945 qs_ot_p2m_diag 44 11.0 0.138 0.138 18.481 18.481 cp_dbcsr_syevd 44 12.0 0.002 0.002 18.085 18.085 cp_fm_diag_elpa 44 13.0 0.000 0.000 16.983 16.983 cp_fm_diag_elpa_base 44 14.0 16.928 16.928 16.982 16.982 ot_mini 96 10.5 0.001 0.001 13.164 13.164 make_m2s 3932 13.4 0.041 0.041 10.060 10.060 qs_ot_get_derivative 96 11.5 0.001 0.001 8.156 8.156 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 7.290 7.290 init_scf_run 11 5.9 0.002 0.002 6.605 6.605 scf_env_initial_rho_setup 11 6.9 0.001 0.001 6.603 6.603 pw_transfer 1295 11.6 0.054 0.054 5.946 5.946 wfi_extrapolate 11 7.9 0.001 0.001 5.893 5.893 fft_wrap_pw1pw2 1081 12.6 0.006 0.006 5.707 5.707 dbcsr_make_dense_low 4961 15.5 0.058 0.058 5.297 5.297 make_dense_data 4961 16.5 4.664 4.664 5.228 5.228 multiply_cannon 1966 13.4 0.147 0.147 5.114 5.114 make_images 3932 14.4 1.896 1.896 5.033 5.033 ot_diis_step 96 11.5 0.003 0.003 5.005 5.005 fft_wrap_pw1pw2_140 439 13.2 0.552 0.552 4.917 4.917 multiply_cannon_loop 1966 14.4 0.058 0.058 4.700 4.700 dbcsr_make_images_dense 3386 14.7 0.016 0.016 4.682 4.682 multiply_cannon_multrec 1966 15.4 4.589 4.589 4.642 4.642 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 4.641 4.641 apply_single 107 13.6 0.000 0.000 4.641 4.641 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 4.516 4.516 ------------------------------------------------------------------------------- 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 0.022 93.234 93.245 qs_mol_dyn_low 1 2.0 0.003 0.004 93.130 93.135 qs_forces 11 3.9 0.001 0.002 93.089 93.089 qs_energies 11 4.9 0.001 0.001 86.870 86.872 scf_env_do_scf 11 5.9 0.001 0.002 80.523 80.523 scf_env_do_scf_inner_loop 96 6.5 0.002 0.018 74.697 74.697 velocity_verlet 10 3.0 0.002 0.003 55.137 55.138 rebuild_ks_matrix 107 8.3 0.001 0.001 41.482 41.543 qs_ks_build_kohn_sham_matrix 107 9.3 0.015 0.021 41.482 41.542 qs_ks_update_qs_env 107 7.6 0.001 0.001 36.689 36.739 sum_up_and_integrate 107 10.3 0.021 0.023 36.645 36.678 integrate_v_rspace 107 11.3 0.004 0.005 36.624 36.658 qs_rho_update_rho 107 7.7 0.001 0.001 34.870 34.891 calculate_rho_elec 107 8.7 0.028 0.030 34.869 34.890 grid_integrate_task_list 107 12.3 25.142 32.523 25.142 32.523 grid_collocate_task_list 107 9.7 24.520 31.248 24.520 31.248 dbcsr_multiply_generic 1966 12.4 0.070 0.082 14.123 14.291 rs_pw_transfer 878 11.9 0.012 0.014 11.352 12.271 qs_scf_new_mos 96 7.5 0.001 0.001 10.875 10.995 qs_scf_loop_do_ot 96 8.5 0.001 0.001 10.875 10.995 density_rs2pw 107 9.7 0.005 0.006 9.986 10.902 multiply_cannon 1966 13.4 0.132 0.142 10.422 10.830 ot_scf_mini 96 9.5 0.002 0.002 10.216 10.331 multiply_cannon_loop 1966 14.4 0.097 0.124 9.817 10.260 mp_waitall_1 146670 16.2 8.846 9.328 8.846 9.328 mp_alltoall_d11v 1998 13.7 7.776 8.763 7.776 8.763 mp_waitany 8968 13.7 7.646 8.613 7.646 8.613 rs_gather_matrices 107 12.3 0.090 0.108 7.504 8.464 rs_pw_transfer_RS2PW_140 118 11.5 0.321 0.382 7.363 8.298 multiply_cannon_metrocomm3 15728 15.4 0.039 0.050 5.786 6.300 ot_mini 96 10.5 0.001 0.001 5.967 6.098 init_scf_loop 11 6.9 0.000 0.000 5.809 5.810 init_scf_run 11 5.9 0.000 0.004 5.002 5.002 scf_env_initial_rho_setup 11 6.9 0.000 0.004 5.001 5.002 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 4.945 4.957 wfi_extrapolate 11 7.9 0.001 0.001 4.546 4.546 potential_pw2rs 107 12.3 0.007 0.009 3.928 3.938 pw_transfer 1295 11.6 0.090 0.094 3.675 3.734 fft_wrap_pw1pw2 1081 12.6 0.009 0.011 3.512 3.565 multiply_cannon_multrec 15728 15.4 3.176 3.391 3.186 3.402 qs_ot_get_derivative 96 11.5 0.001 0.001 3.052 3.171 fft_wrap_pw1pw2_140 439 13.2 0.292 0.322 2.962 3.066 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 2.866 2.963 apply_single 107 13.6 0.000 0.000 2.866 2.963 ot_diis_step 96 11.5 0.004 0.004 2.892 2.892 fft3d_ps 1081 14.6 1.263 1.359 2.602 2.653 make_m2s 3932 13.4 0.044 0.056 2.502 2.574 make_images 3932 14.4 0.113 0.135 2.175 2.243 ------------------------------------------------------------------------------- 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=56.86500000000001, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=64.906, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=29.491, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=25.93, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=24.144, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=16.928, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="mp_alltoall_d11v", label="mp_alltoall_d11v", 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 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="mp_waitany", label="mp_waitany", y=0.0, yerr=0.0 Plot: name="H2O-64_nonortho_timings_32mpi", title="Timings of H2O-64_nonortho with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="rest", label="rest", y=19.303999999999988, 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="grid_collocate_task_list", label="grid_collocate_task_list", y=24.52, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=25.142, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_alltoall_d11v", label="mp_alltoall_d11v", y=7.776, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=8.846, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitany", label="mp_waitany", y=7.646, 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 0.179 0.179 158.897 158.897 qs_energies 1 2.0 0.000 0.000 158.072 158.072 scf_env_do_scf 1 3.0 0.000 0.000 156.549 156.549 qs_ks_update_qs_env 8 5.0 0.000 0.000 118.919 118.919 rebuild_ks_matrix 7 6.0 0.000 0.000 118.861 118.861 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.001 118.861 118.861 hfx_ks_matrix 7 8.0 0.000 0.000 101.211 101.211 integrate_four_center 7 9.0 1.301 1.301 101.191 101.191 integrate_four_center_main 7 10.0 0.584 0.584 89.013 89.013 integrate_four_center_bin 452 11.0 88.429 88.429 88.429 88.429 init_scf_loop 1 4.0 0.000 0.000 87.994 87.994 scf_env_do_scf_inner_loop 7 4.0 0.001 0.001 68.546 68.546 prepare_preconditioner 1 5.0 0.000 0.000 31.879 31.879 make_preconditioner 1 6.0 0.000 0.000 31.879 31.879 arnoldi_normal_ev 11 9.3 0.002 0.002 19.711 19.711 estimate_cond_num 1 7.0 0.000 0.000 19.659 19.659 build_subspace 28 9.5 0.009 0.009 19.070 19.070 integrate_four_center_load 7 10.0 0.001 0.001 10.627 10.627 hfx_load_balance 1 11.0 0.016 0.016 10.627 10.627 admm_mo_calc_rho_aux 7 8.0 0.000 0.000 10.002 10.002 dbcsr_sym_m_v_mult 562 10.0 0.017 0.017 9.764 9.764 admm_fit_mo_coeffs 7 9.0 0.000 0.000 8.717 8.717 cp_fm_cholesky_invert 2 9.5 8.498 8.498 8.498 8.498 make_full_inverse_cholesky 1 7.0 0.000 0.000 8.035 8.035 DGKS_ortho_d 673 10.6 7.224 7.224 7.226 7.226 hfx_load_balance_bin 1 12.0 5.983 5.983 5.983 5.983 Gram_Schmidt_ortho_d 673 10.6 5.812 5.812 5.812 5.812 dbcsr_copy 1318 10.8 1.327 1.327 5.047 5.047 purify_mo_diag 7 10.0 0.000 0.000 4.719 4.719 hfx_load_balance_count 1 12.0 4.611 4.611 4.611 4.611 qs_scf_new_mos 7 5.0 0.000 0.000 4.350 4.350 qs_scf_loop_do_ot 7 6.0 0.000 0.000 4.350 4.350 dbcsr_create_new 3176 12.1 2.790 2.790 4.266 4.266 ot_scf_mini 7 7.0 0.000 0.000 4.249 4.249 cp_fm_syevd 7 11.0 0.000 0.000 4.111 4.111 cp_fm_syevd_base 7 12.0 4.110 4.110 4.110 4.110 make_full_single_inverse 1 7.0 0.000 0.000 4.007 4.007 fit_mo_coeffs 7 10.0 0.000 0.000 3.998 3.998 arnoldi_generalized_ev 1 8.0 0.000 0.000 3.915 3.915 qs_vxc_create 14 8.0 0.000 0.000 3.849 3.849 xc_vxc_pw_create 14 9.0 0.117 0.117 3.849 3.849 gev_build_subspace 4 9.0 0.005 0.005 3.688 3.688 dbcsr_set 2825 11.8 0.003 0.003 3.530 3.530 dbcsr_zero 2837 12.8 3.528 3.528 3.528 3.528 ------------------------------------------------------------------------------- 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 0.198 0.225 140.379 140.393 qs_energies 1 2.0 0.000 0.000 140.026 140.033 scf_env_do_scf 1 3.0 0.000 0.001 139.606 139.606 qs_ks_update_qs_env 8 5.0 0.000 0.000 137.288 137.288 rebuild_ks_matrix 7 6.0 0.000 0.000 137.279 137.279 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.002 137.279 137.279 hfx_ks_matrix 7 8.0 0.000 0.000 130.732 130.734 integrate_four_center 7 9.0 0.057 0.346 130.722 130.723 integrate_four_center_main 7 10.0 0.003 0.004 84.688 118.646 integrate_four_center_bin 448 11.0 84.685 118.642 84.685 118.642 scf_env_do_scf_inner_loop 7 4.0 0.000 0.001 79.619 79.619 init_scf_loop 1 4.0 0.000 0.000 59.986 59.987 mp_sync 70 11.3 33.993 36.896 33.993 36.896 integrate_four_center_load 7 10.0 0.000 0.000 11.357 11.361 hfx_load_balance 1 11.0 0.001 0.001 11.357 11.361 mp_sum_l 1135 8.3 5.681 6.044 5.681 6.044 hfx_load_balance_dist 1 12.0 0.000 0.000 5.510 5.783 hfx_load_balance_bin 1 12.0 2.885 5.689 2.885 5.689 hfx_load_balance_count 1 12.0 2.881 5.587 2.881 5.587 qs_vxc_create 14 8.0 0.000 0.001 3.093 3.094 xc_vxc_pw_create 14 9.0 0.008 0.010 3.092 3.094 ------------------------------------------------------------------------------- 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=38.339999999999975, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_bin", label="integrate_four_center_bin", y=88.429, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=8.498, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="DGKS_ortho_d", label="DGKS_ortho_d", y=7.224, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=5.983, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="Gram_Schmidt_ortho_d", label="Gram_Schmidt_ortho_d", y=5.812, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_count", label="hfx_load_balance_count", y=4.611, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="mp_sum_l", label="mp_sum_l", y=0.0, 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=10.25399999999999, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center_bin", label="integrate_four_center_bin", y=84.685, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=0.0, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="DGKS_ortho_d", label="DGKS_ortho_d", y=0.0, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=2.885, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="Gram_Schmidt_ortho_d", label="Gram_Schmidt_ortho_d", y=0.0, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_count", label="hfx_load_balance_count", y=2.881, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=5.681, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="mp_sync", label="mp_sync", y=33.993, 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 0.014 158.501 158.501 qs_energies 1 2.0 0.000 0.000 158.091 158.091 mp2_main 1 3.0 0.000 0.000 133.765 133.765 mp2_gpw_main 1 4.0 0.000 0.000 132.615 132.615 rpa_ri_compute_en 1 5.0 0.000 0.000 125.354 125.354 rpa_num_int 1 6.0 0.001 0.001 125.348 125.348 compute_mat_P_omega 1 7.0 0.003 0.003 71.715 71.715 compute_mat_P_omega_contract 10 8.0 8.488 8.488 71.449 71.449 dbt_total 2336 9.6 0.012 0.012 59.253 59.253 dbt_contract 787 11.0 0.035 0.035 52.212 52.212 dbt_tas_total 1149 12.2 0.191 0.191 50.861 50.861 dbt_tas_multiply 807 12.1 0.002 0.002 49.468 49.468 dbt_tas_dbm 807 14.1 0.003 0.003 42.731 42.731 dbm_multiply 807 16.1 42.721 42.721 42.721 42.721 GW_matrix_operations 10 7.0 0.004 0.004 35.105 35.105 cp_fm_cholesky_invert 10 8.0 34.171 34.171 34.171 34.171 dbt_tas_mm_1N 524 15.1 0.002 0.002 31.414 31.414 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 27.528 27.528 scf_env_do_scf 1 3.0 0.000 0.000 24.122 24.122 scf_env_do_scf_inner_loop 17 4.0 0.002 0.002 24.122 24.122 qs_scf_new_mos 17 5.0 0.000 0.000 22.554 22.554 eigensolver 18 5.9 0.001 0.001 21.002 21.002 compute_mat_P_omega_calc_M_occ 250 9.0 8.524 8.524 19.226 19.226 cp_fm_diag_elpa 18 6.9 0.000 0.000 14.537 14.537 cp_fm_diag_elpa_base 18 7.9 14.484 14.484 14.537 14.537 cp_fm_cholesky_decompose 14 8.1 13.347 13.347 13.347 13.347 rpa_num_int_RPA_matrix_operati 10 7.0 0.000 0.000 11.666 11.666 RPA_postprocessing_nokp 10 8.0 0.001 0.001 10.768 10.768 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 10.447 10.447 dbt_tas_mm_2 251 15.0 0.001 0.001 9.342 9.342 mp2_ri_gpw_compute_in 1 5.0 0.000 0.000 7.254 7.254 cp_fm_cholesky_restore 51 7.0 6.390 6.390 6.390 6.390 compute_QP_energies 1 7.0 0.000 0.000 5.881 5.881 compute_self_energy_cubic_gw 1 8.0 0.048 0.048 5.881 5.881 dbt_copy 1103 10.7 0.091 0.091 5.631 5.631 get_2c_integrals 1 6.0 0.000 0.000 5.625 5.625 contract_cubic_gw 21 9.0 0.000 0.000 4.840 4.840 dbt_tas_reserve_blocks_index 3261 14.3 0.152 0.152 3.378 3.378 dbm_reserve_blocks 3628 15.3 3.293 3.293 3.293 3.293 ------------------------------------------------------------------------------- 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 0.022 34.661 34.672 qs_energies 1 2.0 0.000 0.001 34.578 34.579 mp2_main 1 3.0 0.000 0.000 33.526 33.527 mp2_gpw_main 1 4.0 0.000 0.000 33.486 33.487 rpa_ri_compute_en 1 5.0 0.000 0.000 32.220 32.220 rpa_num_int 1 6.0 0.000 0.002 32.219 32.220 dbt_total 2336 9.6 0.012 0.013 28.569 28.576 compute_mat_P_omega 1 7.0 0.001 0.005 27.379 27.405 compute_mat_P_omega_contract 10 8.0 0.431 0.460 27.222 27.224 dbt_contract 787 11.0 0.027 0.037 21.398 21.410 dbt_tas_total 1149 12.2 0.055 0.069 19.139 19.144 dbt_tas_multiply 807 12.1 0.002 0.002 19.067 19.069 dbt_tas_dbm 807 14.1 0.003 0.004 14.164 14.177 dbm_multiply 807 16.1 10.897 11.816 10.897 11.816 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 8.090 8.090 compute_mat_P_omega_calc_M_occ 250 9.0 0.413 0.445 8.072 8.073 dbt_tas_mm_2 251 15.0 0.001 0.002 6.681 6.687 dbt_copy 1111 10.7 0.012 0.013 6.159 6.567 mp_sync 8706 11.6 5.405 6.319 5.405 6.319 dbt_reshape 1098 11.7 2.252 2.820 5.875 6.243 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 5.747 5.750 dbt_tas_mm_1N 524 15.1 0.002 0.002 5.049 5.491 compute_QP_energies 1 7.0 0.000 0.000 3.093 3.094 compute_self_energy_cubic_gw 1 8.0 0.003 0.003 3.090 3.093 mp_waitall_2 3776 15.3 2.802 3.068 2.802 3.068 dbt_communicate_buffer 1098 12.7 0.056 0.075 2.868 3.048 contract_cubic_gw 21 9.0 0.000 0.000 2.423 2.425 dbt_crop 1042 12.0 0.955 1.286 1.510 1.892 dbt_reserve_blocks_index 2849 13.1 0.067 0.082 1.720 1.875 dbt_reserve_blocks_index_array 2791 12.2 0.009 0.010 1.720 1.874 dbt_tas_reserve_blocks_index 3300 14.5 0.117 0.153 1.690 1.839 dbm_reserve_blocks 3696 15.4 1.674 1.819 1.674 1.819 dbt_tas_replicate 396 14.1 0.560 0.738 1.162 1.310 mp2_ri_gpw_compute_in 1 5.0 0.000 0.001 1.263 1.265 compute_mat_P_omega_copy_M_vir 250 9.0 0.001 0.001 1.112 1.115 cp_gemm 105 8.4 0.000 0.000 1.036 1.047 cp_gemm_cosma 105 9.4 1.035 1.047 1.035 1.047 compute_mat_P_omega_copy_M_occ 250 9.0 0.001 0.001 1.025 1.031 scf_env_do_scf 1 3.0 0.000 0.000 0.999 1.000 scf_env_do_scf_inner_loop 17 4.0 0.000 0.001 0.999 0.999 convert_to_new_pgrid 2421 14.1 0.027 0.035 0.884 0.954 dbm_copy 1608 15.1 0.851 0.923 0.851 0.923 mp_max_i 1992 9.8 0.688 0.894 0.688 0.894 GW_matrix_operations 10 7.0 0.001 0.001 0.796 0.803 dbm_add 807 14.1 0.710 0.741 0.710 0.741 ------------------------------------------------------------------------------- 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=41.96100000000001, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=42.721, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=34.171, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=14.484, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=13.347, 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=8.524, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=3.293, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="mp_waitall_2", label="mp_waitall_2", y=0.0, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=0.0, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="mp_sync", label="mp_sync", y=0.0, yerr=0.0 Plot: name="GW_PBE_4benzene_timings_32mpi", title="Timings of GW_PBE_4benzene with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="rest", label="rest", y=11.218, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=10.897, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=0.0, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=0.0, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=0.0, 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=0.413, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=1.674, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.802, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=2.252, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_sync", label="mp_sync", y=5.405, yerr=0.0 Running RI-HFX_H2O-32.inp with 1 threads and 32 ranks... done. Running RI-HFX_H2O-32.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/RI-HFX_H2O-32_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.018 0.018 373.148 373.148 qs_forces 1 2.0 0.000 0.000 372.531 372.531 rebuild_ks_matrix 7 6.6 0.000 0.000 350.710 350.710 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.001 350.710 350.710 hfx_ks_matrix 7 8.6 0.000 0.000 348.481 348.481 hfx_ri_update_ks 7 9.6 0.000 0.000 296.498 296.498 hfx_ri_update_ks_Pmat 7 10.6 33.569 33.569 296.495 296.495 dbt_total 4939 11.6 0.028 0.028 291.417 291.417 qs_energies 1 3.0 0.000 0.000 282.181 282.181 scf_env_do_scf 1 4.0 0.000 0.000 281.735 281.735 dbt_tas_total 2391 14.1 0.948 0.948 262.575 262.575 qs_ks_update_qs_env 8 6.0 0.000 0.000 260.412 260.412 dbt_contract 1473 13.0 0.169 0.169 242.667 242.667 dbt_tas_multiply 1482 14.0 0.004 0.004 231.808 231.808 hfx_ri_update_ks_Pmat_KS 567 11.6 0.004 0.004 212.759 212.759 dbt_tas_dbm 1482 16.0 0.005 0.005 211.092 211.092 dbm_multiply 1482 18.0 211.074 211.074 211.074 211.074 dbt_tas_mm_2 649 17.1 0.004 0.004 181.680 181.680 scf_env_do_scf_inner_loop 6 5.0 0.001 0.001 161.833 161.833 init_scf_loop 2 5.0 0.000 0.000 119.900 119.900 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 90.302 90.302 hfx_ri_update_forces 1 7.0 0.000 0.000 51.980 51.980 hfx_ri_forces_Pmat_3c 1 8.0 0.002 0.002 36.017 36.017 dbt_tas_mm_3T 659 17.1 0.002 0.002 22.375 22.375 dbt_tas_reshape 906 14.4 0.010 0.010 22.315 22.315 hfx_ri_pre_scf_Pmat 1 12.0 0.001 0.001 20.979 20.979 hfx_ri_update_ks_Pmat_Px3C 567 11.6 0.002 0.002 19.961 19.961 prepare_preconditioner 2 6.0 0.000 0.000 18.732 18.732 make_preconditioner 2 7.0 0.000 0.000 18.285 18.285 dbt_copy 2411 12.3 0.267 0.267 17.942 17.942 cp_fm_syevd 12 10.7 0.000 0.000 17.903 17.903 cp_fm_syevd_base 12 11.7 17.902 17.902 17.902 17.902 make_full_all 2 8.0 0.000 0.000 17.847 17.847 dbt_tas_merge 649 14.1 13.403 13.403 14.435 14.435 dbt_tas_reshape_buffer_fill 906 15.4 13.307 13.307 13.307 13.307 precalc_derivatives 1 8.0 0.006 0.006 12.833 12.833 dbm_reserve_blocks 8383 16.8 11.180 11.180 11.180 11.180 dbt_tas_reserve_blocks_index 7477 16.0 0.361 0.361 10.767 10.767 dbt_crop 2763 14.2 7.336 7.336 10.605 10.605 dbt_reshape 856 13.9 5.516 5.516 9.745 9.745 hfx_ri_pre_scf_Pmat_2c 1 13.0 0.000 0.000 8.926 8.926 dbt_reserve_blocks_index 4998 15.2 0.141 0.141 8.223 8.223 dbt_reserve_blocks_index_array 4963 14.3 0.020 0.020 8.177 8.177 ------------------------------------------------------------------------------- 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 0.024 64.066 64.077 qs_forces 1 2.0 0.000 0.000 63.877 63.877 rebuild_ks_matrix 7 6.6 0.000 0.000 63.149 63.150 qs_ks_build_kohn_sham_matrix 7 7.6 0.002 0.003 63.149 63.150 hfx_ks_matrix 7 8.6 0.000 0.000 61.992 62.000 dbt_total 4939 11.6 0.029 0.034 56.189 56.204 dbt_contract 1473 13.0 0.103 0.114 43.285 43.303 hfx_ri_update_ks 7 9.6 0.000 0.000 42.393 42.394 hfx_ri_update_ks_Pmat 7 10.6 1.532 1.998 42.392 42.393 dbt_tas_total 2391 14.1 0.128 0.159 40.753 40.760 qs_energies 1 3.0 0.000 0.001 38.899 38.900 scf_env_do_scf 1 4.0 0.000 0.001 38.756 38.756 qs_ks_update_qs_env 8 6.0 0.000 0.000 38.188 38.189 dbt_tas_multiply 1482 14.0 0.005 0.006 36.385 36.387 dbt_tas_dbm 1482 16.0 0.005 0.006 28.069 28.120 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 24.963 24.963 dbm_multiply 1482 18.0 19.205 23.806 19.205 23.806 hfx_ri_update_ks_Pmat_KS 567 11.6 0.004 0.005 23.293 23.293 scf_env_do_scf_inner_loop 6 5.0 0.000 0.001 22.831 22.832 hfx_ri_update_forces 1 7.0 0.001 0.011 19.598 19.606 dbt_tas_mm_2 649 17.1 0.003 0.004 16.585 16.621 init_scf_loop 2 5.0 0.000 0.000 15.924 15.924 mp_sync 17669 13.5 13.233 15.858 13.233 15.858 hfx_ri_forces_Pmat_3c 1 8.0 0.002 0.002 13.641 13.664 hfx_ri_update_ks_Pmat_Px3C 567 11.6 0.002 0.002 8.921 8.921 dbt_copy 2429 12.3 0.034 0.038 7.259 7.636 dbt_tas_mm_3T 659 17.1 0.002 0.002 4.822 5.851 dbt_crop 2763 14.2 3.203 4.435 3.993 5.261 dbt_reshape 1257 13.5 2.319 2.861 5.033 5.247 precalc_derivatives 1 8.0 0.002 0.002 4.578 4.578 dbt_tas_mm_3N 163 16.5 0.001 0.001 4.438 4.519 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.001 4.233 4.233 dbt_tas_merge 649 14.1 1.705 2.266 2.988 3.527 mp_waitall_2 5988 16.5 3.206 3.486 3.206 3.486 dbm_reserve_blocks 8417 16.9 2.466 2.711 2.466 2.711 dbt_tas_reserve_blocks_index 7508 16.1 0.266 0.354 2.355 2.643 mp_max_i 3372 12.5 2.127 2.478 2.127 2.478 dbt_tas_communicate_buffer 1825 16.3 0.064 0.084 2.179 2.470 hfx_ri_pre_scf_Pmat_RIx3C 81 13.0 0.000 0.000 2.432 2.440 dbt_tas_replicate 909 15.6 0.648 0.823 2.318 2.380 dbt_reserve_blocks_index 5399 15.2 0.127 0.159 1.988 2.213 dbt_reserve_blocks_index_array 5364 14.2 0.014 0.017 1.985 2.210 build_3c_derivatives 9 9.0 0.243 0.381 2.132 2.135 dbt_communicate_buffer 1257 14.5 0.047 0.063 1.810 1.942 mp_alltoall_i 4341 15.3 1.647 1.836 1.647 1.836 dbt_tas_reshape 916 14.4 0.009 0.013 1.750 1.832 hfx_ri_update_ks_Pmat_copy_2 567 11.6 0.002 0.002 1.620 1.631 convert_to_new_pgrid 4446 16.0 0.044 0.054 1.475 1.579 dbm_copy 3043 16.9 1.431 1.536 1.431 1.536 mp_sum_l 38201 15.3 1.135 1.391 1.135 1.391 ------------------------------------------------------------------------------- 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=65.37699999999995, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=211.074, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=33.569, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="cp_fm_syevd_base", label="cp_fm_syevd_base", y=17.902, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_tas_merge", label="dbt_tas_merge", y=13.403, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_tas_reshape_buffer_fill", label="dbt_tas_reshape_buffer_fill", y=13.307, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=11.18, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_crop", label="dbt_crop", y=7.336, 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=19.516000000000005, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=19.205, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=1.532, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="cp_fm_syevd_base", label="cp_fm_syevd_base", y=0.0, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_tas_merge", label="dbt_tas_merge", y=1.705, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_tas_reshape_buffer_fill", label="dbt_tas_reshape_buffer_fill", y=0.0, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=2.466, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_crop", label="dbt_crop", y=3.203, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=3.206, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_sync", label="mp_sync", y=13.233, 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 0.015 248.286 248.286 qs_energies 1 2.0 0.000 0.000 248.077 248.077 mp2_main 1 3.0 0.000 0.000 212.666 212.666 mp2_gpw_main 1 4.0 0.001 0.001 208.817 208.817 mp2_ri_gpw_compute_in 1 5.0 0.375 0.375 162.844 162.844 mp2_ri_gpw_compute_in_loop 1 6.0 0.010 0.010 137.731 137.731 mp2_eri_3c_integrate_gpw 2656 7.0 0.014 0.014 107.414 107.414 integrate_v_rspace 2666 8.0 0.794 0.794 94.051 94.051 grid_integrate_task_list 2666 9.0 91.225 91.225 91.225 91.225 mp2_ri_gpw_compute_en 1 5.0 0.075 0.075 45.949 45.949 mp2_ri_gpw_compute_en_RI_loop 1 6.0 10.193 10.193 44.130 44.130 scf_env_do_scf 1 3.0 0.000 0.000 34.267 34.267 scf_env_do_scf_inner_loop 10 4.0 0.001 0.001 34.266 34.266 qs_scf_new_mos 10 5.0 0.000 0.000 32.893 32.893 mp2_ri_gpw_compute_en_expansio 2080 7.0 2.077 2.077 26.276 26.276 eigensolver 11 5.8 0.001 0.001 24.902 24.902 get_2c_integrals 1 6.0 0.000 0.000 24.638 24.638 offload_gemm 2080 8.0 24.199 24.199 24.199 24.199 calculate_wavefunction 5312 9.0 16.102 16.102 23.749 23.749 dbcsr_multiply_generic 5322 8.0 0.196 0.196 23.204 23.204 ao_to_mo_and_store_B_mult_1 2656 7.0 0.010 0.010 23.183 23.183 cp_fm_diag_elpa 11 6.8 0.000 0.000 22.319 22.319 cp_fm_diag_elpa_base 11 7.8 22.153 22.153 22.319 22.319 compute_2c_integrals 1 7.0 0.006 0.006 18.573 18.573 compute_2c_integrals_loop_lm 1 8.0 0.012 0.012 18.553 18.553 mp2_eri_2c_integrate_gpw 1 9.0 3.403 3.403 18.542 18.542 multiply_cannon 5322 9.0 0.525 0.525 11.737 11.737 pw_transfer 63872 10.6 0.885 0.885 11.727 11.727 fft_wrap_pw1pw2 53228 11.4 0.109 0.109 10.570 10.570 multiply_cannon_loop 5322 10.0 0.303 0.303 10.228 10.228 qs_diis_b_step 9 6.0 0.000 0.000 9.670 9.670 make_m2s 10644 9.0 0.064 0.064 9.036 9.036 make_images 10644 10.0 3.321 3.321 8.663 8.663 multiply_cannon_multrec 5322 11.0 8.374 8.374 8.415 8.415 cp_fm_symm 18 7.0 8.337 8.337 8.337 8.337 fft_wrap_pw1pw2_20 21271 12.4 0.585 0.585 7.514 7.514 ao_to_mo_and_store_B_E_Ex_1 2656 7.0 2.529 2.529 7.026 7.026 fft3d_s 53229 13.4 6.753 6.753 6.808 6.808 mp2_ri_gpw_compute_en_ener 2080 7.0 5.662 5.662 5.662 5.662 copy_dbcsr_to_fm 2679 8.0 0.030 0.030 5.548 5.548 cp_fm_triangular_invert 2 6.0 5.452 5.452 5.452 5.452 ------------------------------------------------------------------------------- From /workspace/artifacts/RI-MP2_ammonia_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.006 0.023 45.035 45.048 qs_energies 1 2.0 0.000 0.001 44.959 44.959 mp2_main 1 3.0 0.000 0.001 42.539 42.540 mp2_gpw_main 1 4.0 0.001 0.002 42.414 42.415 mp2_ri_gpw_compute_in 1 5.0 0.043 0.044 19.400 25.498 mp2_ri_gpw_compute_in_loop 1 6.0 0.001 0.001 17.538 23.634 mp2_ri_gpw_compute_en 1 5.0 0.168 0.173 22.930 23.323 mp2_eri_3c_integrate_gpw 83 7.0 0.001 0.001 15.307 21.426 integrate_v_rspace 93 8.1 0.111 0.120 15.210 21.217 grid_integrate_task_list 93 9.1 14.822 20.887 14.822 20.887 mp2_ri_gpw_compute_en_RI_loop 1 6.0 1.009 1.086 15.725 15.734 mp2_ri_gpw_compute_en_expansio 65 7.0 0.097 0.111 11.653 11.855 offload_gemm 65 8.0 11.556 11.760 11.556 11.760 mp_min_d 2 7.0 6.144 6.537 6.144 6.537 mp2_ri_get_integ_group_size 1 6.0 0.000 0.000 6.096 6.489 mp2_ri_gpw_compute_en_comm 17 7.0 0.127 0.182 2.622 2.829 scf_env_do_scf 1 3.0 0.000 0.000 2.271 2.272 scf_env_do_scf_inner_loop 10 4.0 0.000 0.002 2.271 2.272 mp_sendrecv_dm3 510 8.0 1.885 2.129 1.885 2.129 dbcsr_multiply_generic 176 8.0 0.008 0.009 1.915 2.104 ao_to_mo_and_store_B_mult_1 83 7.0 0.001 0.001 1.896 2.084 get_2c_integrals 1 6.0 0.000 0.000 1.804 1.821 compute_2c_integrals 1 7.0 0.002 0.004 1.487 1.502 compute_2c_integrals_loop_lm 1 8.0 0.001 0.003 1.073 1.416 mp2_eri_2c_integrate_gpw 1 9.0 0.219 0.351 1.072 1.413 multiply_cannon 176 9.0 0.016 0.017 1.131 1.216 calculate_wavefunction 166 9.0 0.530 0.757 0.921 1.204 qs_scf_new_mos 10 5.0 0.000 0.000 1.112 1.178 multiply_cannon_loop 176 10.0 0.002 0.002 1.070 1.157 eigensolver 11 5.8 0.001 0.001 1.092 1.092 multiply_cannon_multrec 246 11.0 0.918 0.969 0.923 0.975 pw_transfer 2120 10.5 0.042 0.056 0.834 0.934 cp_fm_diag_elpa 11 6.8 0.000 0.000 0.919 0.921 cp_fm_redistribute_end 11 7.8 0.347 0.914 0.357 0.914 ------------------------------------------------------------------------------- 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=84.41399999999999, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=91.225, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="offload_gemm", label="offload_gemm", y=24.199, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=22.153, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="calculate_wavefunction", label="calculate_wavefunction", y=16.102, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="mp2_ri_gpw_compute_en_RI_loop", label="mp2_ri_gpw_compute_en_RI_loop", y=10.193, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="mp_min_d", label="mp_min_d", y=0.0, 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=9.088999999999999, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=14.822, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="offload_gemm", label="offload_gemm", y=11.556, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=0.0, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="calculate_wavefunction", label="calculate_wavefunction", y=0.53, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="mp2_ri_gpw_compute_en_RI_loop", label="mp2_ri_gpw_compute_en_RI_loop", y=1.009, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="mp_min_d", label="mp_min_d", y=6.144, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="mp_sendrecv_dm3", label="mp_sendrecv_dm3", y=1.885, 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 0.081 0.081 219.575 219.575 qs_energies 1 2.0 0.000 0.000 218.208 218.208 scf_env_do_scf 1 3.0 0.000 0.000 208.663 208.663 scf_env_do_scf_inner_loop 15 4.0 0.002 0.002 208.662 208.662 qs_scf_new_mos 15 5.0 0.000 0.000 130.416 130.416 eigensolver 15 6.0 0.001 0.001 122.593 122.593 cp_fm_diag_elpa 15 7.0 0.000 0.000 109.475 109.475 cp_fm_diag_elpa_base 15 8.0 106.939 106.939 109.475 109.475 qs_ks_update_qs_env 15 5.0 0.000 0.000 51.361 51.361 rebuild_ks_matrix 15 6.0 0.000 0.000 51.150 51.150 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.002 51.150 51.150 qs_vxc_create 15 8.0 0.020 0.020 34.371 34.371 calculate_dispersion_nonloc 15 9.0 7.098 7.098 29.875 29.875 qs_rho_update_rho 16 5.0 0.000 0.000 23.598 23.598 calculate_rho_elec 16 6.0 0.227 0.227 23.598 23.598 pw_transfer 1191 10.0 0.058 0.058 23.228 23.228 fft_wrap_pw1pw2 1086 11.0 0.009 0.009 23.015 23.015 grid_collocate_task_list 16 7.0 22.214 22.214 22.214 22.214 fft_wrap_pw1pw2_150 765 12.0 3.224 3.224 16.423 16.423 sum_up_and_integrate 15 8.0 0.043 0.043 15.307 15.307 integrate_v_rspace 15 9.0 0.021 0.021 15.264 15.264 grid_integrate_task_list 15 10.0 14.671 14.671 14.671 14.671 cp_fm_cholesky_restore 45 7.0 10.878 10.878 10.878 10.878 fft3d_s 1087 13.0 10.656 10.656 10.664 10.664 pw_scatter_s 585 13.1 7.066 7.066 7.066 7.066 fft_wrap_pw1pw2_200 197 12.3 0.740 0.740 6.397 6.397 init_scf_run 1 3.0 0.000 0.000 5.952 5.952 dbcsr_complete_redistribute 46 8.3 2.226 2.226 5.554 5.554 copy_dbcsr_to_fm 16 5.9 0.001 0.001 5.537 5.537 cp_fm_upper_to_full 30 8.0 4.774 4.774 4.774 4.774 gspace_mixing 14 5.0 0.170 0.170 4.619 4.619 vdW_energy 15 10.0 4.584 4.584 4.584 4.584 xc_vxc_pw_create 15 9.0 0.215 0.215 4.475 4.475 ------------------------------------------------------------------------------- From /workspace/artifacts/diag_cu144_broy_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.014 0.027 66.851 66.861 qs_energies 1 2.0 0.000 0.001 66.550 66.555 scf_env_do_scf 1 3.0 0.000 0.000 62.032 62.032 scf_env_do_scf_inner_loop 15 4.0 0.001 0.003 62.032 62.032 qs_ks_update_qs_env 15 5.0 0.000 0.000 27.257 27.305 rebuild_ks_matrix 15 6.0 0.000 0.000 27.213 27.261 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.003 27.213 27.261 qs_rho_update_rho 16 5.0 0.000 0.000 22.080 22.086 calculate_rho_elec 16 6.0 0.007 0.007 22.080 22.086 grid_collocate_task_list 16 7.0 20.478 20.977 20.478 20.977 sum_up_and_integrate 15 8.0 0.008 0.010 15.734 15.821 integrate_v_rspace 15 9.0 0.001 0.001 15.726 15.817 grid_integrate_task_list 15 10.0 13.979 15.148 13.979 15.148 qs_scf_new_mos 15 5.0 0.000 0.000 13.484 14.048 eigensolver 15 6.0 0.001 0.002 12.390 12.420 qs_vxc_create 15 8.0 0.001 0.001 11.142 11.152 calculate_dispersion_nonloc 15 9.0 1.004 1.567 9.129 9.144 cp_fm_diag_elpa 15 7.0 0.000 0.000 9.011 9.016 cp_fm_diag_elpa_base 15 8.0 8.846 8.871 8.999 9.001 pw_transfer 1191 10.0 0.083 0.090 8.629 8.721 fft_wrap_pw1pw2 1086 11.0 0.013 0.014 8.441 8.536 fft3d_ps 1086 13.0 2.692 2.886 6.639 6.793 fft_wrap_pw1pw2_150 765 12.0 0.312 0.334 5.771 5.832 mp_alltoall_z22v 1086 15.0 3.300 3.714 3.300 3.714 cp_fm_cholesky_restore 45 7.0 3.209 3.257 3.209 3.257 yz_to_x 501 13.9 0.267 0.312 2.456 2.707 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 2.681 2.681 fft_wrap_pw1pw2_200 197 12.3 0.210 0.235 2.532 2.609 build_core_hamiltonian_matrix 1 4.0 0.000 0.000 2.333 2.554 xc_vxc_pw_create 15 9.0 0.016 0.020 2.012 2.036 rs_pw_transfer 158 9.4 0.002 0.002 1.529 1.876 density_rs2pw 16 7.0 0.001 0.001 1.461 1.647 init_scf_run 1 3.0 0.000 0.001 1.609 1.610 mp_alltoall_d11v 217 9.2 1.377 1.605 1.377 1.605 x_to_yz 585 14.1 0.353 0.370 1.463 1.586 build_core_ppnl 1 5.0 1.365 1.510 1.365 1.510 vdW_energy 15 10.0 1.443 1.500 1.443 1.500 scf_env_initial_rho_setup 1 4.0 0.001 0.013 1.494 1.495 mp_waitany 520 11.3 1.061 1.468 1.061 1.468 xc_pw_derive 90 11.0 0.001 0.001 1.375 1.461 rs_gather_matrices 15 10.0 0.019 0.026 1.161 1.388 ------------------------------------------------------------------------------- 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=54.216999999999985, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=106.939, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=22.214, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=14.671, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=10.878, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="fft3d_s", label="fft3d_s", y=10.656, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="mp_alltoall_z22v", label="mp_alltoall_z22v", 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=17.039, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=8.846, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=20.478, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.979, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=3.209, 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="mp_alltoall_z22v", label="mp_alltoall_z22v", y=3.3, 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 0.077 0.077 365.078 365.078 qs_energies 1 2.0 0.000 0.000 364.939 364.939 ls_scf 1 3.0 0.000 0.000 363.681 363.681 ls_scf_main 1 4.0 0.002 0.002 351.662 351.662 density_matrix_trs4 11 5.0 0.012 0.012 257.310 257.310 arnoldi_extremal 12 6.1 0.000 0.000 172.028 172.028 arnoldi_normal_ev 12 7.1 0.018 0.018 172.028 172.028 build_subspace 23 8.1 0.085 0.085 169.160 169.160 dbcsr_matrix_vector_mult 652 9.0 0.201 0.201 146.365 146.365 dbcsr_matrix_vector_mult_local 652 10.0 135.570 135.570 135.575 135.575 ls_scf_dm_to_ks 11 5.0 0.000 0.000 88.897 88.897 matrix_ls_to_qs 11 6.0 0.000 0.000 85.568 85.568 dbcsr_multiply_generic 185 6.1 0.833 0.833 76.945 76.945 dbcsr_copy_into_existing 11 7.0 47.380 47.380 47.380 47.380 multiply_cannon 185 7.1 0.275 0.275 46.932 46.932 dbcsr_complete_redistribute 23 7.5 30.622 30.622 42.069 42.069 matrix_decluster 11 7.0 0.000 0.000 38.187 38.187 multiply_cannon_loop 185 8.1 0.240 0.240 34.430 34.430 make_m2s 370 7.1 0.038 0.038 25.459 25.459 multiply_cannon_multrec 185 9.1 25.310 25.310 25.347 25.347 make_images 370 8.1 10.718 10.718 23.718 23.718 dbcsr_finalize 646 7.5 0.174 0.174 15.012 15.012 dbcsr_merge_all 597 8.5 2.253 2.253 13.895 13.895 DGKS_ortho_d 702 9.1 12.891 12.891 12.894 12.894 setup_rec_index_2d 370 8.1 12.129 12.129 12.129 12.129 ls_scf_init_scf 1 4.0 0.000 0.000 11.311 11.311 ls_scf_init_matrix_S 1 5.0 0.000 0.000 10.973 10.973 Gram_Schmidt_ortho_d 702 9.1 10.737 10.737 10.739 10.739 dbcsr_sort_indices 1103 9.9 10.476 10.476 10.476 10.476 matrix_sqrt_Newton_Schulz 1 6.0 0.001 0.001 10.326 10.326 tree_to_linear_d 110 9.4 10.317 10.317 10.317 10.317 quick_finalize 395 10.0 0.379 0.379 9.067 9.067 calculate_norms 370 9.1 8.844 8.844 8.844 8.844 dbcsr_special_finalize 370 9.1 0.002 0.002 8.382 8.382 ------------------------------------------------------------------------------- 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 0.017 0.035 74.087 74.099 qs_energies 1 2.0 0.000 0.000 73.991 73.991 ls_scf 1 3.0 0.000 0.000 73.927 73.928 ls_scf_main 1 4.0 0.001 0.009 70.990 70.991 density_matrix_trs4 11 5.0 0.007 0.021 68.022 68.071 dbcsr_multiply_generic 185 6.1 0.062 0.075 63.695 63.971 multiply_cannon 185 7.1 0.035 0.048 53.406 54.494 multiply_cannon_loop 185 8.1 0.131 0.143 50.722 51.812 multiply_cannon_multrec 1480 9.1 30.930 34.043 31.237 34.387 mp_waitall_1 11936 10.3 16.390 19.123 16.390 19.123 multiply_cannon_metrocomm3 1480 9.1 0.015 0.018 9.775 14.449 calculate_norms 2960 9.1 5.776 7.568 5.776 7.568 make_m2s 370 7.1 0.036 0.038 7.236 7.351 make_images 370 8.1 0.653 0.748 7.101 7.212 multiply_cannon_metrocomm1 1480 9.1 0.009 0.011 3.740 6.879 arnoldi_extremal 12 6.1 0.000 0.000 3.585 3.602 arnoldi_normal_ev 12 7.1 0.001 0.004 3.585 3.602 build_subspace 23 8.1 0.023 0.028 3.472 3.474 make_images_data 370 9.1 0.010 0.018 3.149 3.441 dbcsr_matrix_vector_mult 652 9.0 0.010 0.048 2.395 3.165 hybrid_alltoall_any 393 9.9 0.216 1.163 2.740 2.944 dbcsr_matrix_vector_mult_local 652 10.0 1.797 2.798 1.799 2.800 ls_scf_dm_to_ks 11 5.0 0.000 0.000 2.590 2.651 mp_sum_l 1119 5.6 2.034 2.583 2.034 2.583 dbcsr_complete_redistribute 23 7.5 1.269 1.760 2.108 2.421 matrix_ls_to_qs 11 6.0 0.000 0.000 2.028 2.355 ls_scf_init_scf 1 4.0 0.000 0.000 2.295 2.296 ls_scf_init_matrix_S 1 5.0 0.000 0.000 2.269 2.274 matrix_decluster 11 7.0 0.000 0.000 1.886 2.169 matrix_sqrt_Newton_Schulz 1 6.0 0.001 0.001 2.078 2.080 make_images_pack 370 9.1 1.760 1.937 1.763 1.941 buffer_matrices_ensure_size 370 8.1 1.517 1.638 1.517 1.638 dbcsr_multiply_generic_mpsum_f 137 7.1 0.000 0.000 1.164 1.612 dbcsr_finalize 646 7.5 0.008 0.009 1.441 1.548 ------------------------------------------------------------------------------- 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=104.46099999999996, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=135.57, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_copy_into_existing", label="dbcsr_copy_into_existing", y=47.38, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_complete_redistribute", label="dbcsr_complete_redistribute", y=30.622, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=25.31, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="DGKS_ortho_d", label="DGKS_ortho_d", y=12.891, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="calculate_norms", label="calculate_norms", y=8.844, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="mp_sum_l", label="mp_sum_l", y=0.0, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 Plot: name="bench_dftb_timings_32mpi", title="Timings of bench_dftb with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="bench_dftb_timings_32mpi", name="rest", label="rest", y=15.890999999999998, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=1.797, 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=1.269, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=30.93, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="DGKS_ortho_d", label="DGKS_ortho_d", y=0.0, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="calculate_norms", label="calculate_norms", y=5.776, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=2.034, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=16.39, yerr=0.0 Running dbcsr.inp with 1 threads and 32 ranks... done. Running dbcsr.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/dbcsr_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.007 0.007 71.537 71.537 lib_test 1 2.0 0.000 0.000 71.529 71.529 dbcsr_run_tests 3 3.0 0.003 0.003 71.529 71.529 test_multiplies_multiproc 3 4.0 0.001 0.001 55.770 55.770 dbcsr_redistribute 9 5.0 35.303 35.303 36.850 36.850 dbcsr_multiply_generic 9 5.0 0.001 0.001 17.323 17.323 dbcsr_make_random_matrix 9 4.0 12.724 12.724 15.662 15.662 multiply_cannon 9 6.0 0.001 0.001 12.711 12.711 multiply_cannon_loop 9 7.0 0.012 0.012 12.341 12.341 multiply_cannon_multrec 9 8.0 12.329 12.329 12.329 12.329 dbcsr_finalize 27 5.7 0.010 0.010 5.492 5.492 dbcsr_merge_all 18 6.5 2.066 2.066 4.834 4.834 dbcsr_data_release 975 7.6 2.495 2.495 2.495 2.495 tree_to_linear_d 9 7.0 1.915 1.915 1.915 1.915 make_m2s 18 6.0 0.001 0.001 1.518 1.518 make_images 18 7.0 0.530 0.530 1.466 1.466 ------------------------------------------------------------------------------- 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 19.357 19.361 lib_test 1 2.0 0.000 0.000 19.328 19.345 dbcsr_run_tests 3 3.0 0.000 0.001 19.327 19.345 test_multiplies_multiproc 3 4.0 0.000 0.003 18.462 18.515 dbcsr_multiply_generic 9 5.0 0.002 0.013 16.529 16.617 multiply_cannon 9 6.0 0.002 0.002 14.738 15.036 multiply_cannon_loop 9 7.0 0.002 0.002 14.442 14.701 multiply_cannon_multrec 72 8.0 12.123 12.602 12.124 12.603 mp_waitall_1 576 9.2 2.644 3.178 2.644 3.178 multiply_cannon_metrocomm1 72 8.0 0.001 0.002 2.035 2.526 dbcsr_make_random_matrix 9 4.0 0.690 0.965 0.835 1.057 mp_sum_l 390 2.5 0.435 1.014 0.435 1.014 dbcsr_multiply_generic_mpsum_f 9 6.0 0.000 0.000 0.411 0.990 multiply_cannon_metrocomm3 72 8.0 0.000 0.000 0.276 0.965 dbcsr_finalize 27 5.7 0.000 0.000 0.673 0.779 make_m2s 18 6.0 0.001 0.001 0.717 0.746 dbcsr_data_release 444 7.6 0.660 0.744 0.660 0.744 make_images 18 7.0 0.022 0.027 0.714 0.743 dbcsr_destroy 111 5.9 0.000 0.000 0.542 0.656 dbcsr_merge_all 18 6.5 0.100 0.121 0.552 0.656 dbcsr_checksum 6 5.0 0.168 0.562 0.565 0.566 dbcsr_redistribute 9 5.0 0.256 0.307 0.448 0.484 dbcsr_data_copy_aa2 18 7.5 0.331 0.427 0.331 0.427 make_images_data 18 8.0 0.001 0.001 0.370 0.425 mp_sum_d 191 1.2 0.398 0.416 0.398 0.416 ------------------------------------------------------------------------------- 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=6.6200000000000045, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_redistribute", label="dbcsr_redistribute", y=35.303, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=12.724, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=12.329, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_data_release", label="dbcsr_data_release", y=2.495, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_merge_all", label="dbcsr_merge_all", y=2.066, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="mp_sum_l", label="mp_sum_l", y=0.0, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 Plot: name="dbcsr_timings_32mpi", title="Timings of dbcsr with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="dbcsr_timings_32mpi", name="rest", label="rest", y=2.448999999999998, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_redistribute", label="dbcsr_redistribute", y=0.256, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=0.69, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=12.123, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_data_release", label="dbcsr_data_release", y=0.66, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_merge_all", label="dbcsr_merge_all", y=0.1, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=0.435, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=2.644, 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 0.061 0.061 142.869 142.869 qs_mol_dyn_low 1 2.0 0.003 0.003 141.298 141.298 velocity_verlet 5 3.0 0.003 0.003 115.566 115.566 qmmm_el_coupling 6 3.8 0.000 0.000 87.619 87.619 qmmm_elec_with_gaussian 6 4.8 0.087 0.087 87.616 87.616 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 86.872 86.872 qmmm_elec_gaussian_low_G 6 6.8 85.981 85.981 85.981 85.981 qs_forces 6 3.8 0.001 0.001 44.824 44.824 qs_energies 6 4.8 0.000 0.000 40.506 40.506 scf_env_do_scf 6 5.8 0.001 0.001 37.387 37.387 scf_env_do_scf_inner_loop 39 6.8 0.004 0.004 26.316 26.316 rebuild_ks_matrix 45 8.4 0.000 0.000 25.290 25.290 qs_ks_build_kohn_sham_matrix 45 9.4 0.005 0.005 25.290 25.290 qs_ks_update_qs_env 45 7.8 0.000 0.000 21.433 21.433 pw_transfer 966 12.3 0.050 0.050 17.153 17.153 fft_wrap_pw1pw2 801 13.6 0.006 0.006 16.905 16.905 fft_wrap_pw1pw2_150 507 15.2 2.125 2.125 16.475 16.475 qs_vxc_create 45 10.4 0.001 0.001 13.523 13.523 xc_vxc_pw_create 45 11.4 0.645 0.645 13.522 13.522 init_scf_loop 6 6.8 0.000 0.000 11.066 11.066 xc_pw_derive 270 13.4 0.002 0.002 9.321 9.321 fft3d_s 802 15.6 7.728 7.728 7.736 7.736 prepare_preconditioner 6 7.8 0.000 0.000 7.711 7.711 make_preconditioner 6 8.8 0.000 0.000 7.455 7.455 qs_rho_update_rho 45 7.9 0.000 0.000 7.430 7.430 calculate_rho_elec 45 8.9 0.563 0.563 7.430 7.430 xc_rho_set_and_dset_create 45 12.4 0.705 0.705 7.156 7.156 make_full_all 6 9.8 0.001 0.001 7.087 7.087 pw_scatter_s 429 15.8 5.708 5.708 5.708 5.708 qmmm_forces 6 3.8 0.001 0.001 5.678 5.678 xc_pw_divergence 45 12.4 0.001 0.001 5.664 5.664 qmmm_forces_with_gaussian 6 4.8 0.109 0.109 5.351 5.351 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 4.482 4.482 pw_integral_ab 2539 7.4 4.460 4.460 4.460 4.460 qs_ks_ddapc 45 10.4 0.001 0.001 4.351 4.351 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 3.865 3.865 cp_fm_diag_elpa 18 11.2 0.000 0.000 3.803 3.803 cp_fm_diag_elpa_base 18 12.2 3.795 3.795 3.803 3.803 qmmm_forces_gaussian_low_G 6 6.8 3.735 3.735 3.735 3.735 grid_collocate_task_list 45 9.9 3.571 3.571 3.571 3.571 density_rs2pw 45 9.9 0.002 0.002 3.296 3.296 sum_up_and_integrate 45 10.4 0.127 0.127 3.270 3.270 integrate_v_rspace 45 11.4 0.015 0.015 3.143 3.143 pw_poisson_solve 51 9.9 1.304 1.304 3.094 3.094 ------------------------------------------------------------------------------- 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 0.033 0.053 62.087 62.097 qs_mol_dyn_low 1 2.0 0.003 0.004 60.810 60.871 qs_forces 6 3.8 0.001 0.001 43.763 43.763 qs_energies 6 4.8 0.000 0.000 41.695 41.695 scf_env_do_scf 6 5.8 0.000 0.001 40.650 40.650 scf_env_do_scf_inner_loop 113 6.2 0.002 0.017 39.038 39.039 rebuild_ks_matrix 119 8.1 0.000 0.000 28.802 28.811 qs_ks_build_kohn_sham_matrix 119 9.1 0.015 0.022 28.802 28.811 qs_ks_update_qs_env 119 7.3 0.001 0.001 27.092 27.101 velocity_verlet 5 3.0 0.002 0.004 25.593 25.597 pw_transfer 2446 12.3 0.184 0.204 18.386 18.846 fft_wrap_pw1pw2 2059 13.4 0.023 0.028 17.947 18.423 fft_wrap_pw1pw2_150 1321 14.9 1.409 1.567 17.199 17.648 qs_vxc_create 119 10.1 0.002 0.004 14.556 14.559 xc_vxc_pw_create 119 11.1 0.157 0.211 14.554 14.556 fft3d_ps 2059 15.4 7.328 8.096 13.491 14.181 qs_rho_update_rho 119 7.3 0.001 0.001 11.759 11.760 calculate_rho_elec 119 8.3 0.050 0.056 11.758 11.760 xc_pw_derive 714 13.1 0.009 0.011 10.959 11.262 sum_up_and_integrate 119 10.1 0.060 0.072 10.250 10.520 integrate_v_rspace 119 11.1 0.004 0.004 10.190 10.458 qmmm_forces 6 3.8 0.002 0.002 8.603 8.603 qmmm_forces_with_gaussian 6 4.8 0.357 0.396 7.871 8.393 rs_pw_transfer 988 11.5 0.012 0.016 7.976 8.280 xc_rho_set_and_dset_create 119 12.1 0.383 0.741 6.977 7.942 qmmm_el_coupling 6 3.8 0.000 0.000 7.460 7.571 qmmm_elec_with_gaussian 6 4.8 0.336 0.369 7.459 7.569 xc_pw_divergence 119 12.1 0.004 0.005 7.192 7.442 density_rs2pw 119 9.3 0.006 0.008 6.820 7.141 potential_pw2rs 119 12.1 0.007 0.008 6.203 6.218 mp_alltoall_z22v 2059 17.4 4.638 5.321 4.638 5.321 grid_collocate_task_list 119 9.3 4.762 5.292 4.762 5.292 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 4.127 4.364 grid_integrate_task_list 119 12.1 3.702 4.225 3.702 4.225 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 3.512 3.766 x_to_yz 1095 16.8 0.841 0.946 3.285 3.746 qmmm_forces_gaussian_low_G 6 6.8 3.395 3.640 3.395 3.640 yz_to_x 964 16.0 0.628 0.729 2.822 3.274 mp_waitany 4028 12.8 2.773 3.261 2.773 3.261 rs_pw_transfer_PW2RS_150 125 13.9 1.404 1.461 3.190 3.236 qmmm_elec_gaussian_low_G 6 6.8 2.905 3.153 2.905 3.153 pw_restrict_s3 18 5.8 1.452 1.737 2.697 2.946 rs_pw_transfer_RS2PW_150 125 11.2 1.015 1.150 2.587 2.876 dbcsr_multiply_generic 2588 12.3 0.060 0.073 2.345 2.419 qmmm_elec_with_gaussian:spline 6 5.8 0.000 0.000 2.301 2.395 pw_prolongate_s3 18 6.8 1.237 1.418 2.301 2.395 qs_scf_new_mos 113 7.2 0.000 0.001 2.220 2.226 qs_scf_loop_do_ot 113 8.2 0.000 0.001 2.220 2.225 ot_scf_mini 113 9.2 0.001 0.001 2.134 2.140 qs_ks_ddapc 119 10.1 0.002 0.002 2.013 2.082 mp_waitall_1 188862 16.2 1.919 2.063 1.919 2.063 mp_sum_dm3 33 5.7 1.893 2.019 1.893 2.019 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 1.730 1.730 pw_scatter_p 1095 15.8 1.608 1.661 1.608 1.661 pw_integral_ab 2761 7.7 1.228 1.294 1.543 1.660 init_scf_loop 6 6.8 0.000 0.000 1.609 1.609 pw_gather_p 964 15.0 1.385 1.563 1.385 1.563 xc_functional_eval 238 13.1 0.003 0.004 0.761 1.405 ot_mini 113 10.2 0.000 0.001 1.323 1.329 mp_sum_d 5820 12.2 0.942 1.300 0.942 1.300 ------------------------------------------------------------------------------- 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=27.89100000000002, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=85.981, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_s", label="fft3d_s", y=7.728, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_scatter_s", label="pw_scatter_s", y=5.708, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_integral_ab", label="pw_integral_ab", y=4.46, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=3.795, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.735, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=3.571, 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=34.129000000000005, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=2.905, 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=1.228, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=0.0, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.395, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=4.762, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=4.638, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=3.702, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=7.328, yerr=0.0 Summary: Performance test took 47 minutes. Status: OK Removing intermediate container 2c965868054c ---> 669b01bb5f4f Step 41/42 : CMD cat $(find ./report.log -mmin +10) | sed '/^Summary:/ s/$/ (cached)/' ---> Running in b469d2fc0396 Removing intermediate container b469d2fc0396 ---> 25414b52df1d Step 42/42 : ENTRYPOINT [] ---> Running in a884e7cbd9d4 Removing intermediate container a884e7cbd9d4 ---> fd282c06aed7 [Warning] One or more build-args [GIT_COMMIT_SHA] were not consumed Successfully built fd282c06aed7 Successfully tagged gcr.io/cp2k-org-project/img_cp2k-perf-openmp-arch-14b:master Pushing new image... done. #################### Running Image cp2k-perf-openmp #################### Uploading artifacts... done EndDate: 2022-06-30 12:09:17+00:00