StartDate: 2022-06-10 11:05:50+00:00 CpuId: 32x AMD (unknown model) [Zen 3], 7nm (SMT disabled) CommitSHA: da6a0b7d1e19bf450ab83ef34151de0df22295a8 CommitTime: 2022-06-10 11:11:28 +0200 CommitAuthor: abussy CommitSubject: RPA| low-scaling: change in batching strategy Populating docker build cache... done. #################### Building Image cp2k-perf-openmp #################### Dockerfile: /tools/docker/Dockerfile.test_performance Build-Path: / Build-Args: GIT_COMMIT_SHA=da6a0b7d1e19bf450ab83ef34151de0df22295a8 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 ---> 644fb72bd2a2 Step 24/42 : RUN ./scripts/stage7/install_stage7.sh && rm -rf ./build ---> Using cache ---> 6c6ae39cc95a Step 25/42 : COPY ./tools/toolchain/scripts/stage8/ ./scripts/stage8/ ---> Using cache ---> e6a1ecc8aad2 Step 26/42 : RUN ./scripts/stage8/install_stage8.sh && rm -rf ./build ---> Using cache ---> 87371125159a Step 27/42 : COPY ./tools/toolchain/scripts/arch_base.tmpl ./tools/toolchain/scripts/generate_arch_files.sh ./scripts/ ---> Using cache ---> ff89f8997806 Step 28/42 : RUN ./scripts/generate_arch_files.sh && rm -rf ./build ---> Using cache ---> a80648d1a85e Step 29/42 : WORKDIR /opt/cp2k ---> Using cache ---> 10306dcf3c6a Step 30/42 : COPY ./Makefile . ---> Using cache ---> 08c68107fb5d Step 31/42 : COPY ./src ./src ---> 62f206c058ce Step 32/42 : COPY ./exts ./exts ---> 856586526b08 Step 33/42 : COPY ./tools/build_utils ./tools/build_utils ---> 8bd37cc3685d 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 b49f4b4ffc28 './arch/local.psmp' -> '/opt/cp2k-toolchain/install/arch/local.psmp' Compiling cp2k... Removing intermediate container b49f4b4ffc28 ---> 707af76a56f6 Step 35/42 : COPY ./data ./data ---> 3afe8d5a8273 Step 36/42 : COPY ./tests ./tests ---> c90c17e34649 Step 37/42 : COPY ./tools/regtesting ./tools/regtesting ---> 992042a56466 Step 38/42 : COPY ./benchmarks ./benchmarks ---> e64343b466ce Step 39/42 : COPY ./tools/docker/scripts/test_performance.sh ./tools/docker/scripts/plot_performance.py ./ ---> 1e5348547840 Step 40/42 : RUN ./test_performance.sh "local" 2>&1 | tee report.log ---> Running in 84694d2d40ff ========== 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 0.034 0.034 185.343 185.343 qs_mol_dyn_low 1 2.0 0.002 0.002 184.746 184.746 qs_forces 11 3.9 0.001 0.001 184.698 184.698 qs_energies 11 4.9 0.001 0.001 178.611 178.611 scf_env_do_scf 11 5.9 0.001 0.001 166.323 166.323 velocity_verlet 10 3.0 0.002 0.002 127.811 127.811 init_scf_loop 11 6.9 0.000 0.000 90.790 90.790 prepare_preconditioner 11 7.9 0.000 0.000 88.327 88.327 make_preconditioner 11 8.9 0.000 0.000 88.327 88.327 make_full_inverse_cholesky 11 9.9 0.000 0.000 87.255 87.255 scf_env_do_scf_inner_loop 108 6.5 0.011 0.011 75.421 75.421 cp_fm_cholesky_invert 11 10.9 61.927 61.927 61.927 61.927 qs_scf_new_mos 108 7.5 0.001 0.001 40.981 40.981 qs_scf_loop_do_ot 108 8.5 0.001 0.001 40.981 40.981 ot_scf_mini 108 9.5 0.002 0.002 39.607 39.607 qs_ot_get_p 119 10.4 0.001 0.001 21.951 21.951 cp_fm_cholesky_decompose 22 10.9 21.555 21.555 21.555 21.555 qs_ot_p2m_diag 50 11.0 0.156 0.156 20.661 20.661 rebuild_ks_matrix 119 8.3 0.001 0.001 20.479 20.479 qs_ks_build_kohn_sham_matrix 119 9.3 0.012 0.012 20.478 20.478 cp_dbcsr_syevd 50 12.0 0.002 0.002 20.234 20.234 dbcsr_multiply_generic 2286 12.5 0.163 0.163 20.070 20.070 qs_rho_update_rho 119 7.7 0.001 0.001 19.395 19.395 calculate_rho_elec 119 8.7 0.971 0.971 19.395 19.395 cp_fm_diag_elpa 50 13.0 0.000 0.000 19.101 19.101 cp_fm_diag_elpa_base 50 14.0 19.039 19.039 19.100 19.100 qs_ks_update_qs_env 119 7.6 0.001 0.001 18.825 18.825 grid_collocate_task_list 119 9.7 15.068 15.068 15.068 15.068 ot_mini 108 10.5 0.001 0.001 14.086 14.086 sum_up_and_integrate 119 10.3 0.192 0.192 12.877 12.877 integrate_v_rspace 119 11.3 0.090 0.090 12.685 12.685 make_m2s 4572 13.5 0.047 0.047 10.847 10.847 grid_integrate_task_list 119 12.3 10.710 10.710 10.710 10.710 qs_ot_get_derivative 108 11.5 0.001 0.001 8.567 8.567 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 6.359 6.359 dbcsr_make_dense_low 5837 15.5 0.069 0.069 5.908 5.908 make_dense_data 5837 16.5 5.126 5.126 5.825 5.825 pw_transfer 1439 11.6 0.056 0.056 5.817 5.817 fft_wrap_pw1pw2 1201 12.6 0.006 0.006 5.617 5.617 ot_diis_step 108 11.5 0.004 0.004 5.516 5.516 make_images 4572 14.5 2.107 2.107 5.432 5.432 multiply_cannon 2286 13.5 0.181 0.181 5.161 5.161 dbcsr_make_images_dense 3978 14.8 0.018 0.018 5.078 5.078 init_scf_run 11 5.9 0.002 0.002 4.967 4.967 scf_env_initial_rho_setup 11 6.9 0.001 0.001 4.965 4.965 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 4.921 4.921 apply_single 119 13.6 0.000 0.000 4.921 4.921 fft_wrap_pw1pw2_140 487 13.2 0.410 0.410 4.757 4.757 multiply_cannon_loop 2286 14.5 0.129 0.129 4.688 4.688 multiply_cannon_multrec 2286 15.5 4.505 4.505 4.557 4.557 wfi_extrapolate 11 7.9 0.001 0.001 4.291 4.291 dbcsr_copy 2102 12.0 0.237 0.237 3.805 3.805 dbcsr_complete_redistribute 329 12.2 1.901 1.901 3.712 3.712 ------------------------------------------------------------------------------- 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 0.006 0.020 49.401 49.412 qs_mol_dyn_low 1 2.0 0.004 0.005 49.297 49.301 qs_forces 11 3.9 0.001 0.001 49.245 49.245 qs_energies 11 4.9 0.001 0.001 45.919 45.925 scf_env_do_scf 11 5.9 0.001 0.002 42.104 42.104 scf_env_do_scf_inner_loop 108 6.5 0.003 0.020 38.875 38.875 velocity_verlet 10 3.0 0.001 0.003 29.692 29.694 rebuild_ks_matrix 119 8.3 0.000 0.001 18.816 18.921 qs_ks_build_kohn_sham_matrix 119 9.3 0.014 0.021 18.815 18.921 qs_ks_update_qs_env 119 7.6 0.001 0.001 16.786 16.889 sum_up_and_integrate 119 10.3 0.018 0.020 14.494 14.519 qs_rho_update_rho 119 7.7 0.001 0.001 14.493 14.501 integrate_v_rspace 119 11.3 0.004 0.005 14.476 14.501 calculate_rho_elec 119 8.7 0.029 0.031 14.493 14.501 dbcsr_multiply_generic 2286 12.5 0.071 0.084 13.286 13.502 grid_collocate_task_list 119 9.7 9.011 11.078 9.011 11.078 grid_integrate_task_list 119 12.3 8.115 10.911 8.115 10.911 qs_scf_new_mos 108 7.5 0.001 0.001 10.682 10.824 qs_scf_loop_do_ot 108 8.5 0.001 0.001 10.681 10.823 ot_scf_mini 108 9.5 0.002 0.002 10.021 10.145 multiply_cannon 2286 13.5 0.131 0.147 9.421 9.856 multiply_cannon_loop 2286 14.5 0.088 0.113 8.828 9.258 mp_waitall_1 169478 16.3 7.958 8.605 7.958 8.605 rs_pw_transfer 974 11.9 0.010 0.013 6.121 6.604 ot_mini 108 10.5 0.001 0.001 5.906 6.039 multiply_cannon_metrocomm3 18288 15.5 0.037 0.049 5.096 5.752 density_rs2pw 119 9.7 0.005 0.006 5.114 5.602 mp_alltoall_d11v 2130 13.8 3.168 3.535 3.168 3.535 mp_waitany 9880 13.7 2.918 3.469 2.918 3.469 pw_transfer 1439 11.6 0.090 0.105 3.383 3.442 potential_pw2rs 119 12.3 0.006 0.008 3.389 3.416 rs_gather_matrices 119 12.3 0.084 0.095 2.930 3.324 qs_ot_get_derivative 108 11.5 0.001 0.001 3.199 3.322 fft_wrap_pw1pw2 1201 12.6 0.009 0.011 3.229 3.281 multiply_cannon_multrec 18288 15.5 2.918 3.255 2.927 3.267 init_scf_loop 11 6.9 0.000 0.000 3.215 3.216 rs_pw_transfer_RS2PW_140 130 11.5 0.258 0.312 2.646 3.124 fft_wrap_pw1pw2_140 487 13.2 0.255 0.317 2.719 2.834 ot_diis_step 108 11.5 0.004 0.013 2.680 2.681 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 2.550 2.673 apply_single 119 13.6 0.000 0.000 2.549 2.672 init_scf_run 11 5.9 0.000 0.004 2.656 2.657 scf_env_initial_rho_setup 11 6.9 0.000 0.003 2.656 2.656 make_m2s 4572 13.5 0.045 0.065 2.397 2.481 fft3d_ps 1201 14.6 1.173 1.295 2.361 2.449 wfi_extrapolate 11 7.9 0.001 0.001 2.415 2.416 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 2.178 2.186 make_images 4572 14.5 0.116 0.139 2.080 2.156 qs_ot_get_p 119 10.4 0.001 0.001 1.367 1.537 mp_sum_d 4129 12.0 1.088 1.468 1.088 1.468 rs_pw_transfer_PW2RS_140 130 13.9 0.551 0.644 1.383 1.429 mp_sum_l 11218 13.2 1.011 1.418 1.011 1.418 make_images_data 4572 15.5 0.035 0.046 1.087 1.217 prepare_preconditioner 11 7.9 0.000 0.000 1.157 1.180 make_preconditioner 11 8.9 0.000 0.000 1.157 1.180 mp_alltoall_z22v 1201 16.6 0.948 1.180 0.948 1.180 multiply_cannon_metrocomm1 18288 15.5 0.018 0.026 0.528 1.143 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 0.867 1.122 qs_ot_get_derivative_taylor 59 13.0 0.001 0.001 1.000 1.081 hybrid_alltoall_any 4725 16.4 0.058 0.190 0.947 1.067 make_full_inverse_cholesky 11 9.9 0.000 0.000 1.045 1.062 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 0.965 1.029 ------------------------------------------------------------------------------- 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=57.04399999999998, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=61.927, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=21.555, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=19.039, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=15.068, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=10.71, 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_alltoall_d11v", label="mp_alltoall_d11v", 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=18.23100000000001, 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=9.011, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=8.115, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=7.958, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_alltoall_d11v", label="mp_alltoall_d11v", y=3.168, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitany", label="mp_waitany", y=2.918, 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 0.030 0.030 211.809 211.809 qs_mol_dyn_low 1 2.0 0.002 0.002 211.061 211.061 qs_forces 11 3.9 0.001 0.001 211.024 211.024 qs_energies 11 4.9 0.001 0.001 203.119 203.119 scf_env_do_scf 11 5.9 0.001 0.001 188.851 188.851 velocity_verlet 10 3.0 0.002 0.002 148.188 148.188 init_scf_loop 11 6.9 0.000 0.000 97.538 97.538 prepare_preconditioner 11 7.9 0.000 0.000 93.445 93.445 make_preconditioner 11 8.9 0.000 0.000 93.445 93.445 make_full_inverse_cholesky 11 9.9 0.000 0.000 92.290 92.290 scf_env_do_scf_inner_loop 96 6.5 0.010 0.010 91.176 91.176 cp_fm_cholesky_invert 11 10.9 64.152 64.152 64.152 64.152 qs_scf_new_mos 96 7.5 0.001 0.001 35.519 35.519 qs_scf_loop_do_ot 96 8.5 0.001 0.001 35.519 35.519 ot_scf_mini 96 9.5 0.002 0.002 34.179 34.179 rebuild_ks_matrix 107 8.3 0.001 0.001 33.986 33.986 qs_ks_build_kohn_sham_matrix 107 9.3 0.011 0.011 33.985 33.985 qs_rho_update_rho 107 7.7 0.001 0.001 31.784 31.784 calculate_rho_elec 107 8.7 0.855 0.855 31.783 31.783 qs_ks_update_qs_env 107 7.6 0.001 0.001 30.628 30.628 grid_collocate_task_list 107 9.7 27.625 27.625 27.625 27.625 sum_up_and_integrate 107 10.3 0.175 0.175 26.828 26.828 integrate_v_rspace 107 11.3 0.093 0.093 26.653 26.653 grid_integrate_task_list 107 12.3 24.749 24.749 24.749 24.749 cp_fm_cholesky_decompose 22 10.9 24.129 24.129 24.129 24.129 dbcsr_multiply_generic 1966 12.4 0.146 0.146 18.537 18.537 qs_ot_get_p 107 10.4 0.001 0.001 18.181 18.181 qs_ot_p2m_diag 44 11.0 0.136 0.136 16.999 16.999 cp_dbcsr_syevd 44 12.0 0.002 0.002 16.648 16.648 cp_fm_diag_elpa 44 13.0 0.000 0.000 15.623 15.623 cp_fm_diag_elpa_base 44 14.0 15.570 15.570 15.622 15.622 ot_mini 96 10.5 0.001 0.001 12.707 12.707 make_m2s 3932 13.4 0.041 0.041 9.915 9.915 qs_ot_get_derivative 96 11.5 0.001 0.001 7.751 7.751 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 7.184 7.184 init_scf_run 11 5.9 0.002 0.002 6.123 6.123 scf_env_initial_rho_setup 11 6.9 0.001 0.001 6.121 6.121 pw_transfer 1295 11.6 0.051 0.051 5.786 5.786 fft_wrap_pw1pw2 1081 12.6 0.006 0.006 5.594 5.594 wfi_extrapolate 11 7.9 0.001 0.001 5.475 5.475 dbcsr_make_dense_low 4961 15.5 0.064 0.064 5.308 5.308 make_dense_data 4961 16.5 4.600 4.600 5.232 5.232 ot_diis_step 96 11.5 0.003 0.003 4.952 4.952 make_images 3932 14.4 1.899 1.899 4.914 4.914 multiply_cannon 1966 13.4 0.155 0.155 4.869 4.869 fft_wrap_pw1pw2_140 439 13.2 0.492 0.492 4.764 4.764 dbcsr_make_images_dense 3386 14.7 0.016 0.016 4.626 4.626 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 4.588 4.588 apply_single 107 13.6 0.000 0.000 4.588 4.588 multiply_cannon_loop 1966 14.4 0.131 0.131 4.452 4.452 multiply_cannon_multrec 1966 15.4 4.272 4.272 4.321 4.321 qs_env_update_s_mstruct 11 6.9 0.000 0.000 4.243 4.243 ------------------------------------------------------------------------------- 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 0.005 0.020 83.751 83.761 qs_mol_dyn_low 1 2.0 0.003 0.004 83.636 83.641 qs_forces 11 3.9 0.001 0.002 83.596 83.596 qs_energies 11 4.9 0.001 0.001 78.015 78.017 scf_env_do_scf 11 5.9 0.000 0.002 72.274 72.274 scf_env_do_scf_inner_loop 96 6.5 0.002 0.017 66.940 66.940 velocity_verlet 10 3.0 0.001 0.003 49.731 49.732 rebuild_ks_matrix 107 8.3 0.000 0.001 37.072 37.141 qs_ks_build_kohn_sham_matrix 107 9.3 0.014 0.019 37.071 37.140 sum_up_and_integrate 107 10.3 0.018 0.020 32.993 33.040 integrate_v_rspace 107 11.3 0.004 0.005 32.975 33.024 qs_ks_update_qs_env 107 7.6 0.001 0.001 32.784 32.846 qs_rho_update_rho 107 7.7 0.001 0.001 31.462 31.471 calculate_rho_elec 107 8.7 0.026 0.027 31.462 31.471 grid_integrate_task_list 107 12.3 23.016 29.645 23.016 29.645 grid_collocate_task_list 107 9.7 22.020 28.383 22.020 28.383 dbcsr_multiply_generic 1966 12.4 0.064 0.077 12.379 12.544 rs_pw_transfer 878 11.9 0.010 0.013 10.195 10.879 density_rs2pw 107 9.7 0.005 0.006 9.116 9.796 qs_scf_new_mos 96 7.5 0.001 0.001 9.708 9.782 qs_scf_loop_do_ot 96 8.5 0.001 0.001 9.708 9.781 multiply_cannon 1966 13.4 0.124 0.143 9.038 9.360 ot_scf_mini 96 9.5 0.002 0.002 9.134 9.193 multiply_cannon_loop 1966 14.4 0.088 0.119 8.475 8.826 mp_waitall_1 146670 16.2 7.556 8.321 7.556 8.321 mp_waitany 8968 13.7 7.225 7.958 7.225 7.958 mp_alltoall_d11v 1998 13.7 6.945 7.732 6.945 7.732 rs_pw_transfer_RS2PW_140 118 11.5 0.227 0.255 6.918 7.604 rs_gather_matrices 107 12.3 0.075 0.090 6.729 7.487 multiply_cannon_metrocomm3 15728 15.4 0.035 0.049 4.957 5.691 ot_mini 96 10.5 0.001 0.001 5.436 5.507 init_scf_loop 11 6.9 0.000 0.001 5.321 5.322 init_scf_run 11 5.9 0.000 0.004 4.528 4.528 scf_env_initial_rho_setup 11 6.9 0.000 0.003 4.528 4.528 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 4.413 4.421 wfi_extrapolate 11 7.9 0.001 0.001 4.103 4.103 potential_pw2rs 107 12.3 0.006 0.008 3.193 3.227 pw_transfer 1295 11.6 0.084 0.094 3.080 3.169 multiply_cannon_multrec 15728 15.4 2.748 3.152 2.757 3.164 fft_wrap_pw1pw2 1081 12.6 0.008 0.011 2.937 3.010 qs_ot_get_derivative 96 11.5 0.001 0.001 2.910 2.971 fft_wrap_pw1pw2_140 439 13.2 0.242 0.293 2.498 2.623 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 2.456 2.561 apply_single 107 13.6 0.000 0.000 2.456 2.561 ot_diis_step 96 11.5 0.003 0.004 2.503 2.503 make_m2s 3932 13.4 0.040 0.050 2.176 2.246 fft3d_ps 1081 14.6 1.089 1.206 2.121 2.170 make_images 3932 14.4 0.104 0.127 1.887 1.955 ------------------------------------------------------------------------------- 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=55.584, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=64.152, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=27.625, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=24.749, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=24.129, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=15.57, 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_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=16.989000000000004, 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=22.02, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=23.016, 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=6.945, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitany", label="mp_waitany", y=7.225, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=7.556, 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 0.180 0.180 152.029 152.029 qs_energies 1 2.0 0.000 0.000 151.235 151.235 scf_env_do_scf 1 3.0 0.000 0.000 149.820 149.820 qs_ks_update_qs_env 8 5.0 0.000 0.000 112.707 112.707 rebuild_ks_matrix 7 6.0 0.000 0.000 112.651 112.651 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.001 112.651 112.651 hfx_ks_matrix 7 8.0 0.000 0.000 95.048 95.048 integrate_four_center 7 9.0 1.511 1.511 95.024 95.024 init_scf_loop 1 4.0 0.000 0.000 84.879 84.879 integrate_four_center_main 7 10.0 1.122 1.122 82.088 82.088 integrate_four_center_bin 449 11.0 80.966 80.966 80.966 80.966 scf_env_do_scf_inner_loop 7 4.0 0.001 0.001 64.932 64.932 prepare_preconditioner 1 5.0 0.000 0.000 31.491 31.491 make_preconditioner 1 6.0 0.000 0.000 31.491 31.491 arnoldi_normal_ev 11 9.3 0.001 0.001 18.928 18.928 estimate_cond_num 1 7.0 0.000 0.000 18.885 18.885 build_subspace 28 9.5 0.009 0.009 18.520 18.520 integrate_four_center_load 7 10.0 0.000 0.000 11.106 11.106 hfx_load_balance 1 11.0 0.005 0.005 11.105 11.105 admm_mo_calc_rho_aux 7 8.0 0.000 0.000 9.929 9.929 dbcsr_sym_m_v_mult 562 10.0 0.014 0.014 9.552 9.552 admm_fit_mo_coeffs 7 9.0 0.000 0.000 8.749 8.749 cp_fm_cholesky_invert 2 9.5 8.523 8.523 8.523 8.523 make_full_inverse_cholesky 1 7.0 0.000 0.000 8.420 8.420 DGKS_ortho_d 673 10.6 7.199 7.199 7.201 7.201 Gram_Schmidt_ortho_d 673 10.6 5.611 5.611 5.612 5.612 hfx_load_balance_bin 1 12.0 5.519 5.519 5.519 5.519 hfx_load_balance_count 1 12.0 5.515 5.515 5.515 5.515 dbcsr_copy 1318 10.8 1.485 1.485 5.276 5.276 purify_mo_diag 7 10.0 0.000 0.000 4.671 4.671 qs_scf_new_mos 7 5.0 0.000 0.000 4.282 4.282 qs_scf_loop_do_ot 7 6.0 0.000 0.000 4.281 4.281 ot_scf_mini 7 7.0 0.000 0.000 4.185 4.185 dbcsr_create_new 3176 12.1 2.664 2.664 4.175 4.175 fit_mo_coeffs 7 10.0 0.000 0.000 4.078 4.078 cp_fm_syevd 7 11.0 0.000 0.000 4.058 4.058 cp_fm_syevd_base 7 12.0 4.057 4.057 4.057 4.057 make_full_single_inverse 1 7.0 0.000 0.000 4.047 4.047 arnoldi_generalized_ev 1 8.0 0.000 0.000 3.966 3.966 gev_build_subspace 4 9.0 0.004 0.004 3.829 3.829 qs_vxc_create 14 8.0 0.000 0.000 3.762 3.762 xc_vxc_pw_create 14 9.0 0.116 0.116 3.762 3.762 dbcsr_set 2825 11.8 0.003 0.003 3.319 3.319 dbcsr_zero 2837 12.8 3.317 3.317 3.317 3.317 cp_fm_cholesky_decompose 3 8.7 3.205 3.205 3.205 3.205 qs_ot_get_p 8 7.8 0.000 0.000 3.119 3.119 ------------------------------------------------------------------------------- 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 0.196 0.227 133.995 134.012 qs_energies 1 2.0 0.000 0.000 133.662 133.670 scf_env_do_scf 1 3.0 0.000 0.000 133.263 133.263 qs_ks_update_qs_env 8 5.0 0.000 0.000 131.070 131.071 rebuild_ks_matrix 7 6.0 0.000 0.000 131.062 131.063 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.001 131.062 131.062 hfx_ks_matrix 7 8.0 0.000 0.000 124.612 124.613 integrate_four_center 7 9.0 0.051 0.335 124.603 124.604 integrate_four_center_main 7 10.0 0.003 0.004 80.141 112.620 integrate_four_center_bin 448 11.0 80.138 112.617 80.138 112.617 scf_env_do_scf_inner_loop 7 4.0 0.000 0.001 75.810 75.810 init_scf_loop 1 4.0 0.000 0.000 57.452 57.452 mp_sync 70 11.3 32.501 35.236 32.501 35.236 integrate_four_center_load 7 10.0 0.000 0.000 11.300 11.304 hfx_load_balance 1 11.0 0.001 0.001 11.300 11.304 mp_sum_l 1135 8.3 5.660 5.979 5.660 5.979 hfx_load_balance_dist 1 12.0 0.000 0.000 5.514 5.773 hfx_load_balance_bin 1 12.0 2.853 5.620 2.853 5.620 hfx_load_balance_count 1 12.0 2.853 5.600 2.853 5.600 qs_vxc_create 14 8.0 0.001 0.001 3.062 3.062 xc_vxc_pw_create 14 9.0 0.008 0.009 3.061 3.061 xc_rho_set_and_dset_create 14 10.0 0.009 0.011 1.923 2.724 ------------------------------------------------------------------------------- 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=38.696, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_bin", label="integrate_four_center_bin", y=80.966, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=8.523, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="DGKS_ortho_d", label="DGKS_ortho_d", y=7.199, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="Gram_Schmidt_ortho_d", label="Gram_Schmidt_ortho_d", y=5.611, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=5.519, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_count", label="hfx_load_balance_count", y=5.515, 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=9.990000000000009, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center_bin", label="integrate_four_center_bin", y=80.138, 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="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_bin", label="hfx_load_balance_bin", y=2.853, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_count", label="hfx_load_balance_count", y=2.853, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=5.66, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="mp_sync", label="mp_sync", y=32.501, 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 0.012 0.012 149.702 149.702 qs_energies 1 2.0 0.000 0.000 149.332 149.332 mp2_main 1 3.0 0.000 0.000 125.544 125.544 mp2_gpw_main 1 4.0 0.000 0.000 124.510 124.510 rpa_ri_compute_en 1 5.0 0.000 0.000 117.588 117.588 rpa_num_int 1 6.0 0.001 0.001 117.583 117.583 compute_mat_P_omega 1 7.0 0.003 0.003 68.441 68.441 compute_mat_P_omega_contract 10 8.0 8.406 8.406 68.212 68.212 dbt_total 2336 9.6 0.012 0.012 56.100 56.100 dbt_contract 787 11.0 0.040 0.040 49.583 49.583 dbt_tas_total 1149 12.2 0.200 0.200 48.311 48.311 dbt_tas_multiply 807 12.1 0.002 0.002 46.939 46.939 dbt_tas_dbm 807 14.1 0.003 0.003 40.137 40.137 dbm_multiply 807 16.1 40.127 40.127 40.127 40.127 GW_matrix_operations 10 7.0 0.004 0.004 31.354 31.354 cp_fm_cholesky_invert 10 8.0 30.550 30.550 30.550 30.550 dbt_tas_mm_1N 524 15.1 0.002 0.002 29.089 29.089 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 25.382 25.382 scf_env_do_scf 1 3.0 0.000 0.000 23.614 23.614 scf_env_do_scf_inner_loop 17 4.0 0.002 0.002 23.614 23.614 qs_scf_new_mos 17 5.0 0.000 0.000 21.982 21.982 eigensolver 18 5.9 0.001 0.001 20.407 20.407 compute_mat_P_omega_calc_M_occ 250 9.0 8.432 8.432 18.832 18.832 cp_fm_diag_elpa 18 6.9 0.000 0.000 13.380 13.380 cp_fm_diag_elpa_base 18 7.9 13.339 13.339 13.380 13.380 cp_fm_cholesky_decompose 14 8.1 12.210 12.210 12.210 12.210 rpa_num_int_RPA_matrix_operati 10 7.0 0.000 0.000 11.167 11.167 RPA_postprocessing_nokp 10 8.0 0.001 0.001 10.322 10.322 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 10.293 10.293 dbt_tas_mm_2 251 15.0 0.001 0.001 9.149 9.149 cp_fm_cholesky_restore 51 7.0 6.969 6.969 6.969 6.969 mp2_ri_gpw_compute_in 1 5.0 0.000 0.000 6.915 6.915 compute_QP_energies 1 7.0 0.000 0.000 5.641 5.641 compute_self_energy_cubic_gw 1 8.0 0.049 0.049 5.640 5.640 get_2c_integrals 1 6.0 0.000 0.000 5.349 5.349 dbt_copy 1103 10.7 0.100 0.100 5.128 5.128 contract_cubic_gw 21 9.0 0.000 0.000 4.633 4.633 dbt_tas_reserve_blocks_index 3261 14.3 0.147 0.147 3.045 3.045 ------------------------------------------------------------------------------- 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 0.004 0.022 32.819 32.829 qs_energies 1 2.0 0.000 0.000 32.737 32.742 mp2_main 1 3.0 0.000 0.000 31.749 31.754 mp2_gpw_main 1 4.0 0.000 0.000 31.712 31.717 rpa_ri_compute_en 1 5.0 0.000 0.001 30.480 30.485 rpa_num_int 1 6.0 0.001 0.002 30.479 30.484 dbt_total 2336 9.6 0.011 0.014 27.072 27.096 compute_mat_P_omega 1 7.0 0.001 0.005 25.779 25.807 compute_mat_P_omega_contract 10 8.0 0.389 0.443 25.615 25.627 dbt_contract 787 11.0 0.025 0.028 20.372 20.379 dbt_tas_total 1149 12.2 0.049 0.067 18.251 18.252 dbt_tas_multiply 807 12.1 0.002 0.002 18.197 18.199 dbt_tas_dbm 807 14.1 0.003 0.004 13.465 13.487 dbm_multiply 807 16.1 10.147 10.907 10.147 10.907 compute_mat_P_omega_calc_M_occ 250 9.0 0.377 0.432 7.602 7.606 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 7.576 7.576 mp_sync 8706 11.6 5.505 6.848 5.505 6.848 dbt_tas_mm_2 251 15.0 0.001 0.002 6.226 6.236 dbt_copy 1111 10.7 0.011 0.012 5.648 6.139 dbt_reshape 1098 11.7 2.082 2.819 5.375 5.828 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 5.454 5.455 dbt_tas_mm_1N 524 15.1 0.001 0.002 4.703 5.164 compute_QP_energies 1 7.0 0.000 0.000 3.043 3.045 compute_self_energy_cubic_gw 1 8.0 0.002 0.003 3.040 3.043 mp_waitall_2 3776 15.3 2.601 2.807 2.601 2.807 dbt_communicate_buffer 1098 12.7 0.053 0.080 2.640 2.775 contract_cubic_gw 21 9.0 0.000 0.000 2.421 2.421 dbt_crop 1042 12.0 0.889 1.239 1.374 1.809 dbt_reserve_blocks_index_array 2791 12.2 0.008 0.010 1.492 1.721 dbt_reserve_blocks_index 2849 13.1 0.063 0.081 1.491 1.719 dbt_tas_reserve_blocks_index 3300 14.5 0.115 0.157 1.463 1.678 dbm_reserve_blocks 3696 15.4 1.440 1.645 1.440 1.645 dbt_tas_replicate 396 14.1 0.540 0.720 1.141 1.302 mp2_ri_gpw_compute_in 1 5.0 0.000 0.000 1.228 1.230 compute_mat_P_omega_copy_M_vir 250 9.0 0.001 0.001 1.032 1.037 compute_mat_P_omega_copy_M_occ 250 9.0 0.001 0.001 0.968 0.971 cp_gemm 105 8.4 0.000 0.000 0.957 0.965 cp_gemm_cosma 105 9.4 0.957 0.964 0.957 0.964 scf_env_do_scf 1 3.0 0.000 0.000 0.949 0.949 scf_env_do_scf_inner_loop 17 4.0 0.000 0.003 0.949 0.949 convert_to_new_pgrid 2421 14.1 0.025 0.031 0.781 0.906 dbm_copy 1608 15.1 0.750 0.872 0.750 0.872 mp_max_i 1992 9.8 0.681 0.845 0.681 0.845 GW_matrix_operations 10 7.0 0.001 0.001 0.750 0.756 dbm_add 807 14.1 0.610 0.688 0.610 0.688 mp_sum_l 6085 13.0 0.548 0.667 0.548 0.667 ------------------------------------------------------------------------------- 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=45.044, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=40.127, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=30.55, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=13.339, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=12.21, 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=8.432, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", 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 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=10.667000000000002, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=10.147, 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=0.377, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=1.44, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.601, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=2.082, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_sync", label="mp_sync", y=5.505, yerr=0.0 Running RI-HFX_H2O-32.inp with 1 threads and 32 ranks... done. Running RI-HFX_H2O-32.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/RI-HFX_H2O-32_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.017 0.017 345.937 345.937 qs_forces 1 2.0 0.000 0.000 345.387 345.387 rebuild_ks_matrix 7 6.6 0.000 0.000 325.246 325.246 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.001 325.246 325.246 hfx_ks_matrix 7 8.6 0.000 0.000 323.332 323.332 dbt_total 4939 11.6 0.028 0.028 267.620 267.620 hfx_ri_update_ks 7 9.6 0.000 0.000 267.148 267.148 hfx_ri_update_ks_Pmat 7 10.6 32.771 32.771 267.145 267.145 qs_energies 1 3.0 0.000 0.000 253.518 253.518 scf_env_do_scf 1 4.0 0.000 0.000 253.066 253.066 dbt_tas_total 2391 14.1 1.065 1.065 238.843 238.843 qs_ks_update_qs_env 8 6.0 0.000 0.000 233.428 233.428 dbt_contract 1473 13.0 0.113 0.113 218.597 218.597 dbt_tas_multiply 1482 14.0 0.004 0.004 207.923 207.923 hfx_ri_update_ks_Pmat_KS 567 11.6 0.004 0.004 185.998 185.998 dbt_tas_dbm 1482 16.0 0.006 0.006 184.841 184.841 dbm_multiply 1482 18.0 184.822 184.822 184.822 184.822 dbt_tas_mm_2 649 17.1 0.004 0.004 156.686 156.686 scf_env_do_scf_inner_loop 6 5.0 0.001 0.001 144.930 144.930 init_scf_loop 2 5.0 0.000 0.000 108.134 108.134 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 91.821 91.821 hfx_ri_update_forces 1 7.0 0.000 0.000 56.181 56.181 hfx_ri_forces_Pmat_3c 1 8.0 0.002 0.002 41.161 41.161 dbt_tas_reshape 906 14.4 0.016 0.016 23.532 23.532 dbt_tas_mm_3T 659 17.1 0.002 0.002 21.499 21.499 hfx_ri_pre_scf_Pmat 1 12.0 0.001 0.001 19.949 19.949 hfx_ri_update_ks_Pmat_Px3C 567 11.6 0.002 0.002 18.639 18.639 dbt_copy 2411 12.3 0.175 0.175 18.062 18.062 prepare_preconditioner 2 6.0 0.000 0.000 17.210 17.210 make_preconditioner 2 7.0 0.000 0.000 16.804 16.804 cp_fm_syevd 12 10.7 0.000 0.000 16.700 16.700 cp_fm_syevd_base 12 11.7 16.699 16.699 16.699 16.699 make_full_all 2 8.0 0.000 0.000 16.299 16.299 dbt_tas_merge 649 14.1 13.192 13.192 14.653 14.653 dbt_tas_reshape_buffer_fill 906 15.4 13.517 13.517 13.517 13.517 precalc_derivatives 1 8.0 0.005 0.005 12.206 12.206 dbm_reserve_blocks 8383 16.8 11.886 11.886 11.886 11.886 dbt_tas_reserve_blocks_index 7477 16.0 0.348 0.348 11.396 11.396 dbt_crop 2763 14.2 6.854 6.854 10.454 10.454 dbt_reshape 856 13.9 5.608 5.608 9.897 9.897 dbt_reserve_blocks_index 4998 15.2 0.134 0.134 8.737 8.737 dbt_reserve_blocks_index_array 4963 14.3 0.019 0.019 8.681 8.681 hfx_ri_pre_scf_Pmat_2c 1 13.0 0.000 0.000 8.536 8.536 reshape_mm_small 906 15.6 0.136 0.136 7.517 7.517 dbt_tas_replicate 906 15.6 5.484 5.484 7.306 7.306 dbt_tas_reshape_buffer_obtain 906 15.4 6.499 6.499 7.177 7.177 ------------------------------------------------------------------------------- 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 0.004 0.019 56.872 56.882 qs_forces 1 2.0 0.000 0.000 56.688 56.688 rebuild_ks_matrix 7 6.6 0.000 0.000 56.006 56.007 qs_ks_build_kohn_sham_matrix 7 7.6 0.002 0.003 56.006 56.007 hfx_ks_matrix 7 8.6 0.000 0.000 55.010 55.017 dbt_total 4939 11.6 0.026 0.030 49.655 49.676 dbt_contract 1473 13.0 0.087 0.101 37.637 37.653 hfx_ri_update_ks 7 9.6 0.000 0.000 37.359 37.359 hfx_ri_update_ks_Pmat 7 10.6 1.386 1.909 37.358 37.359 dbt_tas_total 2391 14.1 0.111 0.144 35.575 35.586 qs_energies 1 3.0 0.000 0.000 34.300 34.300 scf_env_do_scf 1 4.0 0.000 0.001 34.140 34.140 qs_ks_update_qs_env 8 6.0 0.000 0.000 33.633 33.634 dbt_tas_multiply 1482 14.0 0.005 0.005 31.207 31.212 dbt_tas_dbm 1482 16.0 0.005 0.009 23.601 23.654 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 22.375 22.375 dbm_multiply 1482 18.0 16.451 20.200 16.451 20.200 hfx_ri_update_ks_Pmat_KS 567 11.6 0.004 0.005 19.964 19.965 scf_env_do_scf_inner_loop 6 5.0 0.000 0.001 19.958 19.958 hfx_ri_update_forces 1 7.0 0.000 0.000 17.650 17.656 mp_sync 17669 13.5 11.514 14.223 11.514 14.223 init_scf_loop 2 5.0 0.000 0.000 14.181 14.181 dbt_tas_mm_2 649 17.1 0.003 0.004 13.262 13.296 hfx_ri_forces_Pmat_3c 1 8.0 0.002 0.002 12.468 12.499 hfx_ri_update_ks_Pmat_Px3C 567 11.6 0.002 0.002 8.016 8.016 dbt_copy 2429 12.3 0.030 0.034 6.311 6.767 dbt_tas_mm_3T 659 17.1 0.002 0.002 4.212 4.917 dbt_reshape 1257 13.5 2.097 2.609 4.377 4.669 dbt_crop 2763 14.2 2.985 3.848 3.730 4.634 dbt_tas_mm_3N 163 16.5 0.000 0.001 4.092 4.133 precalc_derivatives 1 8.0 0.001 0.002 3.976 3.976 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 3.828 3.828 dbt_tas_merge 649 14.1 1.641 2.113 2.773 3.438 mp_waitall_2 5988 16.5 2.856 3.231 2.856 3.231 dbm_reserve_blocks 8417 16.9 2.263 2.615 2.263 2.615 dbt_tas_reserve_blocks_index 7508 16.1 0.251 0.315 2.104 2.514 mp_max_i 3372 12.5 1.984 2.351 1.984 2.351 dbt_tas_replicate 909 15.6 0.590 0.764 2.164 2.268 hfx_ri_pre_scf_Pmat_RIx3C 81 13.0 0.000 0.000 2.180 2.190 dbt_tas_communicate_buffer 1825 16.3 0.059 0.077 1.975 2.173 dbt_tas_reshape 916 14.4 0.008 0.010 1.940 2.120 dbt_reserve_blocks_index 5399 15.2 0.116 0.140 1.791 2.119 dbt_reserve_blocks_index_array 5364 14.2 0.013 0.016 1.789 2.118 mp_alltoall_i 4341 15.3 1.774 2.001 1.774 2.001 build_3c_derivatives 9 9.0 0.225 0.372 1.913 1.921 dbt_communicate_buffer 1257 14.5 0.043 0.061 1.529 1.643 hfx_ri_update_ks_Pmat_copy_2 567 11.6 0.001 0.002 1.427 1.431 convert_to_new_pgrid 4446 16.0 0.033 0.045 1.222 1.430 dbm_copy 3043 16.9 1.189 1.398 1.189 1.398 mp_sum_l 38201 15.3 1.103 1.391 1.103 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=66.19599999999997, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=184.822, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=32.771, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="cp_fm_syevd_base", label="cp_fm_syevd_base", y=16.699, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_tas_reshape_buffer_fill", label="dbt_tas_reshape_buffer_fill", y=13.517, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_tas_merge", label="dbt_tas_merge", y=13.192, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=11.886, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_crop", label="dbt_crop", y=6.854, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="mp_sync", label="mp_sync", y=0.0, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="mp_waitall_2", label="mp_waitall_2", y=0.0, yerr=0.0 Plot: name="RI-HFX_H2O-32_timings_32mpi", title="Timings of RI-HFX_H2O-32 with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="rest", label="rest", y=17.776000000000003, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=16.451, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=1.386, 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_reshape_buffer_fill", label="dbt_tas_reshape_buffer_fill", y=0.0, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_tas_merge", label="dbt_tas_merge", y=1.641, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=2.263, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_crop", label="dbt_crop", y=2.985, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_sync", label="mp_sync", y=11.514, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.856, yerr=0.0 Running RI-MP2_ammonia.inp with 1 threads and 32 ranks... done. Running RI-MP2_ammonia.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/RI-MP2_ammonia_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.014 0.014 242.164 242.164 qs_energies 1 2.0 0.000 0.000 241.984 241.984 mp2_main 1 3.0 0.000 0.000 205.199 205.199 mp2_gpw_main 1 4.0 0.001 0.001 201.253 201.253 mp2_ri_gpw_compute_in 1 5.0 0.368 0.368 150.423 150.423 mp2_ri_gpw_compute_in_loop 1 6.0 0.010 0.010 124.306 124.306 mp2_eri_3c_integrate_gpw 2656 7.0 0.013 0.013 94.466 94.466 integrate_v_rspace 2666 8.0 0.725 0.725 80.687 80.687 grid_integrate_task_list 2666 9.0 77.840 77.840 77.840 77.840 mp2_ri_gpw_compute_en 1 5.0 0.076 0.076 50.810 50.810 mp2_ri_gpw_compute_en_RI_loop 1 6.0 9.673 9.673 49.072 49.072 scf_env_do_scf 1 3.0 0.000 0.000 35.769 35.769 scf_env_do_scf_inner_loop 10 4.0 0.005 0.005 35.769 35.769 qs_scf_new_mos 10 5.0 0.000 0.000 34.492 34.492 mp2_ri_gpw_compute_en_expansio 2080 7.0 2.128 2.128 32.467 32.467 offload_gemm 2080 8.0 30.339 30.339 30.339 30.339 eigensolver 11 5.8 0.001 0.001 26.839 26.839 get_2c_integrals 1 6.0 0.000 0.000 25.696 25.696 calculate_wavefunction 5312 9.0 16.321 16.321 24.449 24.449 cp_fm_diag_elpa 11 6.8 0.000 0.000 24.268 24.268 cp_fm_diag_elpa_base 11 7.8 24.119 24.119 24.268 24.268 dbcsr_multiply_generic 5322 8.0 0.178 0.178 22.517 22.517 ao_to_mo_and_store_B_mult_1 2656 7.0 0.009 0.009 22.485 22.485 compute_2c_integrals 1 7.0 0.006 0.006 19.244 19.244 compute_2c_integrals_loop_lm 1 8.0 0.011 0.011 19.225 19.225 mp2_eri_2c_integrate_gpw 1 9.0 3.671 3.671 19.214 19.214 pw_transfer 63872 10.6 0.906 0.906 12.117 12.117 multiply_cannon 5322 9.0 0.441 0.441 11.335 11.335 fft_wrap_pw1pw2 53228 11.4 0.117 0.117 10.910 10.910 multiply_cannon_loop 5322 10.0 0.307 0.307 9.942 9.942 qs_diis_b_step 9 6.0 0.000 0.000 9.410 9.410 make_m2s 10644 9.0 0.066 0.066 8.809 8.809 make_images 10644 10.0 3.244 3.244 8.475 8.475 multiply_cannon_multrec 5322 11.0 8.071 8.071 8.110 8.110 cp_fm_symm 18 7.0 7.989 7.989 7.989 7.989 fft_wrap_pw1pw2_20 21271 12.4 0.628 0.628 7.650 7.650 ao_to_mo_and_store_B_E_Ex_1 2656 7.0 2.346 2.346 7.255 7.255 fft3d_s 53229 13.4 6.994 6.994 7.027 7.027 copy_dbcsr_to_fm 2679 8.0 0.035 0.035 5.908 5.908 cp_fm_triangular_invert 2 6.0 5.017 5.017 5.017 5.017 mp2_ri_gpw_compute_en_ener 2080 7.0 4.990 4.990 4.990 4.990 ------------------------------------------------------------------------------- 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 0.004 0.021 41.059 41.070 qs_energies 1 2.0 0.000 0.000 40.971 40.971 mp2_main 1 3.0 0.000 0.001 38.712 38.713 mp2_gpw_main 1 4.0 0.001 0.001 38.596 38.596 mp2_ri_gpw_compute_in 1 5.0 0.043 0.043 17.879 23.252 mp2_ri_gpw_compute_in_loop 1 6.0 0.001 0.001 16.173 21.548 mp2_ri_gpw_compute_en 1 5.0 0.154 0.163 20.637 21.126 mp2_eri_3c_integrate_gpw 83 7.0 0.001 0.001 14.027 19.493 integrate_v_rspace 93 8.1 0.107 0.127 13.966 19.332 grid_integrate_task_list 93 9.1 13.575 18.995 13.575 18.995 mp2_ri_gpw_compute_en_RI_loop 1 6.0 0.694 0.870 14.194 14.205 mp2_ri_gpw_compute_en_expansio 65 7.0 0.075 0.095 10.658 10.950 offload_gemm 65 8.0 10.582 10.880 10.582 10.880 mp_min_d 2 7.0 5.415 5.965 5.415 5.965 mp2_ri_get_integ_group_size 1 6.0 0.000 0.000 5.375 5.864 mp2_ri_gpw_compute_en_comm 17 7.0 0.099 0.166 2.496 2.969 mp_sendrecv_dm3 510 8.0 1.905 2.453 1.905 2.453 dbcsr_multiply_generic 176 8.0 0.008 0.009 1.854 2.251 ao_to_mo_and_store_B_mult_1 83 7.0 0.001 0.001 1.838 2.235 scf_env_do_scf 1 3.0 0.000 0.000 2.114 2.115 scf_env_do_scf_inner_loop 10 4.0 0.000 0.002 2.114 2.114 get_2c_integrals 1 6.0 0.000 0.001 1.639 1.667 compute_2c_integrals 1 7.0 0.002 0.004 1.360 1.376 compute_2c_integrals_loop_lm 1 8.0 0.001 0.003 0.982 1.293 mp2_eri_2c_integrate_gpw 1 9.0 0.204 0.318 0.981 1.293 multiply_cannon 176 9.0 0.015 0.017 1.078 1.192 multiply_cannon_loop 176 10.0 0.002 0.002 1.022 1.135 calculate_wavefunction 166 9.0 0.487 0.689 0.849 1.095 qs_scf_new_mos 10 5.0 0.000 0.000 1.019 1.093 make_m2s 352 9.0 0.003 0.003 0.739 1.018 eigensolver 11 5.8 0.001 0.001 1.008 1.010 make_images 352 10.0 0.051 0.060 0.727 1.005 multiply_cannon_multrec 246 11.0 0.872 0.932 0.877 0.939 pw_transfer 2120 10.5 0.039 0.050 0.775 0.855 cp_fm_diag_elpa 11 6.8 0.000 0.000 0.841 0.843 cp_fm_redistribute_end 11 7.8 0.323 0.828 0.330 0.830 ------------------------------------------------------------------------------- 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=75.80099999999999, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=77.84, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="offload_gemm", label="offload_gemm", y=30.339, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=24.119, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="calculate_wavefunction", label="calculate_wavefunction", y=16.321, 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=9.673, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=8.071, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="mp_sendrecv_dm3", label="mp_sendrecv_dm3", y=0.0, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="mp_min_d", label="mp_min_d", 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=7.528999999999996, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.575, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="offload_gemm", label="offload_gemm", y=10.582, 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=0.487, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="mp2_ri_gpw_compute_en_RI_loop", label="mp2_ri_gpw_compute_en_RI_loop", y=0.694, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=0.872, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="mp_sendrecv_dm3", label="mp_sendrecv_dm3", y=1.905, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="mp_min_d", label="mp_min_d", y=5.415, 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 0.073 0.073 218.963 218.963 qs_energies 1 2.0 0.000 0.000 217.658 217.658 scf_env_do_scf 1 3.0 0.000 0.000 208.392 208.392 scf_env_do_scf_inner_loop 15 4.0 0.002 0.002 208.392 208.392 qs_scf_new_mos 15 5.0 0.000 0.000 132.964 132.964 eigensolver 15 6.0 0.001 0.001 125.274 125.274 cp_fm_diag_elpa 15 7.0 0.000 0.000 112.270 112.270 cp_fm_diag_elpa_base 15 8.0 109.792 109.792 112.270 112.270 qs_ks_update_qs_env 15 5.0 0.000 0.000 50.129 50.129 rebuild_ks_matrix 15 6.0 0.000 0.000 49.919 49.919 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.002 49.919 49.919 qs_vxc_create 15 8.0 0.029 0.029 34.397 34.397 calculate_dispersion_nonloc 15 9.0 7.330 7.330 29.965 29.965 pw_transfer 1191 10.0 0.059 0.059 23.038 23.038 fft_wrap_pw1pw2 1086 11.0 0.009 0.009 22.844 22.844 qs_rho_update_rho 16 5.0 0.000 0.000 21.931 21.931 calculate_rho_elec 16 6.0 0.215 0.215 21.931 21.931 grid_collocate_task_list 16 7.0 20.584 20.584 20.584 20.584 fft_wrap_pw1pw2_150 765 12.0 3.192 3.192 16.327 16.327 sum_up_and_integrate 15 8.0 0.042 0.042 14.106 14.106 integrate_v_rspace 15 9.0 0.024 0.024 14.064 14.064 grid_integrate_task_list 15 10.0 13.501 13.501 13.501 13.501 cp_fm_cholesky_restore 45 7.0 10.796 10.796 10.796 10.796 fft3d_s 1087 13.0 10.525 10.525 10.532 10.532 pw_scatter_s 585 13.1 7.127 7.127 7.127 7.127 fft_wrap_pw1pw2_200 197 12.3 0.737 0.737 6.306 6.306 init_scf_run 1 3.0 0.000 0.000 5.821 5.821 dbcsr_complete_redistribute 46 8.3 2.249 2.249 5.527 5.527 copy_dbcsr_to_fm 16 5.9 0.001 0.001 5.471 5.471 cp_fm_upper_to_full 30 8.0 4.685 4.685 4.685 4.685 gspace_mixing 14 5.0 0.170 0.170 4.567 4.567 vdW_energy 15 10.0 4.524 4.524 4.524 4.524 xc_vxc_pw_create 15 9.0 0.218 0.218 4.402 4.402 ------------------------------------------------------------------------------- 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 0.012 0.026 63.084 63.095 qs_energies 1 2.0 0.000 0.001 62.826 62.831 scf_env_do_scf 1 3.0 0.000 0.001 58.629 58.629 scf_env_do_scf_inner_loop 15 4.0 0.001 0.004 58.629 58.629 qs_ks_update_qs_env 15 5.0 0.000 0.000 24.946 24.965 rebuild_ks_matrix 15 6.0 0.000 0.000 24.912 24.932 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.004 24.912 24.932 qs_rho_update_rho 16 5.0 0.000 0.000 20.906 20.911 calculate_rho_elec 16 6.0 0.007 0.008 20.906 20.911 grid_collocate_task_list 16 7.0 19.313 19.773 19.313 19.773 sum_up_and_integrate 15 8.0 0.006 0.009 14.214 14.278 integrate_v_rspace 15 9.0 0.001 0.001 14.208 14.275 qs_scf_new_mos 15 5.0 0.000 0.000 13.462 13.547 grid_integrate_task_list 15 10.0 13.054 13.541 13.054 13.541 eigensolver 15 6.0 0.001 0.002 12.415 12.454 qs_vxc_create 15 8.0 0.001 0.001 10.379 10.387 cp_fm_diag_elpa 15 7.0 0.000 0.000 8.988 8.993 cp_fm_diag_elpa_base 15 8.0 8.837 8.859 8.985 8.989 calculate_dispersion_nonloc 15 9.0 0.967 1.799 8.504 8.527 pw_transfer 1191 10.0 0.077 0.094 7.978 8.086 fft_wrap_pw1pw2 1086 11.0 0.011 0.014 7.813 7.951 fft3d_ps 1086 13.0 2.392 2.924 6.186 6.479 fft_wrap_pw1pw2_150 765 12.0 0.249 0.293 5.333 5.414 mp_alltoall_z22v 1086 15.0 3.218 3.918 3.218 3.918 cp_fm_cholesky_restore 45 7.0 3.276 3.336 3.276 3.336 yz_to_x 501 13.9 0.214 0.320 2.448 2.837 qs_energies_init_hamiltonians 1 3.0 0.000 0.001 2.521 2.522 fft_wrap_pw1pw2_200 197 12.3 0.175 0.211 2.370 2.438 build_core_hamiltonian_matrix 1 4.0 0.000 0.000 2.148 2.394 xc_vxc_pw_create 15 9.0 0.014 0.018 1.875 1.906 rs_pw_transfer 158 9.4 0.001 0.002 1.548 1.884 density_rs2pw 16 7.0 0.001 0.001 1.471 1.692 x_to_yz 585 14.1 0.338 0.394 1.322 1.564 mp_waitany 520 11.3 1.131 1.453 1.131 1.453 init_scf_run 1 3.0 0.000 0.001 1.419 1.420 vdW_energy 15 10.0 1.334 1.397 1.334 1.397 build_core_ppnl 1 5.0 1.250 1.383 1.250 1.383 xc_pw_derive 90 11.0 0.001 0.002 1.278 1.356 scf_env_initial_rho_setup 1 4.0 0.000 0.001 1.333 1.333 rs_pw_transfer_RS2PW_200 18 8.8 0.033 0.038 0.868 1.321 ------------------------------------------------------------------------------- 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=53.764999999999986, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=109.792, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=20.584, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.501, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=10.796, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="fft3d_s", label="fft3d_s", y=10.525, 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=15.385999999999996, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=8.837, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=19.313, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.054, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=3.276, 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=3.218, 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 0.088 0.088 310.289 310.289 qs_energies 1 2.0 0.000 0.000 310.140 310.140 ls_scf 1 3.0 0.000 0.000 308.916 308.916 ls_scf_main 1 4.0 0.002 0.002 296.142 296.142 density_matrix_trs4 11 5.0 0.012 0.012 202.271 202.271 arnoldi_extremal 12 6.1 0.000 0.000 118.972 118.972 arnoldi_normal_ev 12 7.1 0.017 0.017 118.972 118.972 build_subspace 23 8.1 0.084 0.084 117.205 117.205 dbcsr_matrix_vector_mult 652 9.0 0.190 0.190 92.939 92.939 ls_scf_dm_to_ks 11 5.0 0.000 0.000 88.659 88.659 matrix_ls_to_qs 11 6.0 0.000 0.000 85.410 85.410 dbcsr_matrix_vector_mult_local 652 10.0 81.782 81.782 81.787 81.787 dbcsr_multiply_generic 185 6.1 0.841 0.841 75.323 75.323 dbcsr_copy_into_existing 11 7.0 47.573 47.573 47.573 47.573 multiply_cannon 185 7.1 0.289 0.289 46.190 46.190 dbcsr_complete_redistribute 23 7.5 30.117 30.117 41.493 41.493 matrix_decluster 11 7.0 0.000 0.000 37.836 37.836 multiply_cannon_loop 185 8.1 0.263 0.263 33.860 33.860 make_m2s 370 7.1 0.037 0.037 24.721 24.721 multiply_cannon_multrec 185 9.1 23.947 23.947 24.066 24.066 make_images 370 8.1 10.644 10.644 23.113 23.113 dbcsr_finalize 646 7.5 0.249 0.249 15.057 15.057 dbcsr_merge_all 597 8.5 2.296 2.296 13.784 13.784 DGKS_ortho_d 702 9.1 12.838 12.838 12.842 12.842 ls_scf_init_scf 1 4.0 0.000 0.000 12.037 12.037 setup_rec_index_2d 370 8.1 11.949 11.949 11.949 11.949 ls_scf_init_matrix_S 1 5.0 0.000 0.000 11.708 11.708 matrix_sqrt_Newton_Schulz 1 6.0 0.001 0.001 11.071 11.071 Gram_Schmidt_ortho_d 702 9.1 10.759 10.759 10.761 10.761 tree_to_linear_d 110 9.4 10.219 10.219 10.219 10.219 dbcsr_sort_indices 1103 9.9 10.084 10.084 10.084 10.084 calculate_norms 370 9.1 9.530 9.530 9.530 9.530 quick_finalize 395 10.0 0.390 0.390 8.757 8.757 dbcsr_special_finalize 370 9.1 0.002 0.002 8.107 8.107 ------------------------------------------------------------------------------- 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 0.023 0.037 68.861 68.872 qs_energies 1 2.0 0.000 0.000 68.724 68.725 ls_scf 1 3.0 0.000 0.000 68.638 68.639 ls_scf_main 1 4.0 0.000 0.007 65.798 65.798 density_matrix_trs4 11 5.0 0.006 0.017 63.096 63.183 dbcsr_multiply_generic 185 6.1 0.058 0.068 59.129 59.344 multiply_cannon 185 7.1 0.033 0.037 49.313 50.498 multiply_cannon_loop 185 8.1 0.113 0.129 46.856 47.799 multiply_cannon_multrec 1480 9.1 28.895 33.380 29.170 33.718 mp_waitall_1 11936 10.3 15.225 20.184 15.225 20.184 multiply_cannon_metrocomm3 1480 9.1 0.014 0.016 8.961 16.254 make_m2s 370 7.1 0.035 0.038 6.789 6.844 calculate_norms 2960 9.1 5.030 6.721 5.030 6.721 make_images 370 8.1 0.631 0.730 6.661 6.720 multiply_cannon_metrocomm1 1480 9.1 0.008 0.010 3.521 6.647 arnoldi_extremal 12 6.1 0.000 0.000 3.245 3.265 arnoldi_normal_ev 12 7.1 0.001 0.004 3.245 3.265 make_images_data 370 9.1 0.009 0.013 2.975 3.191 build_subspace 23 8.1 0.020 0.025 3.134 3.136 hybrid_alltoall_any 393 9.9 0.178 0.801 2.665 2.919 dbcsr_matrix_vector_mult 652 9.0 0.009 0.043 2.287 2.867 mp_sum_l 1119 5.6 2.072 2.747 2.072 2.747 dbcsr_matrix_vector_mult_local 652 10.0 1.683 2.527 1.684 2.529 ls_scf_dm_to_ks 11 5.0 0.000 0.000 2.358 2.459 ls_scf_init_scf 1 4.0 0.000 0.000 2.220 2.221 ls_scf_init_matrix_S 1 5.0 0.000 0.000 2.191 2.198 dbcsr_complete_redistribute 23 7.5 1.218 1.586 1.957 2.116 matrix_ls_to_qs 11 6.0 0.000 0.000 1.896 2.069 matrix_sqrt_Newton_Schulz 1 6.0 0.000 0.001 1.919 1.925 matrix_decluster 11 7.0 0.000 0.000 1.758 1.891 make_images_pack 370 9.1 1.636 1.884 1.640 1.888 dbcsr_multiply_generic_mpsum_f 137 7.1 0.000 0.000 1.236 1.805 buffer_matrices_ensure_size 370 8.1 1.341 1.544 1.341 1.544 dbcsr_finalize 646 7.5 0.008 0.010 1.321 1.429 ------------------------------------------------------------------------------- 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=104.50200000000001, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=81.782, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_copy_into_existing", label="dbcsr_copy_into_existing", y=47.573, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_complete_redistribute", label="dbcsr_complete_redistribute", y=30.117, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=23.947, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="DGKS_ortho_d", label="DGKS_ortho_d", y=12.838, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="calculate_norms", label="calculate_norms", y=9.53, 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=14.738, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=1.683, 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=1.218, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=28.895, 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=5.03, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=15.225, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=2.072, 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 0.014 0.014 71.402 71.402 lib_test 1 2.0 0.000 0.000 71.387 71.387 dbcsr_run_tests 3 3.0 0.002 0.002 71.387 71.387 test_multiplies_multiproc 3 4.0 0.001 0.001 56.122 56.122 dbcsr_redistribute 9 5.0 36.422 36.422 37.964 37.964 dbcsr_multiply_generic 9 5.0 0.001 0.001 16.524 16.524 dbcsr_make_random_matrix 9 4.0 12.149 12.149 15.164 15.164 multiply_cannon 9 6.0 0.001 0.001 11.987 11.987 multiply_cannon_loop 9 7.0 0.025 0.025 11.630 11.630 multiply_cannon_multrec 9 8.0 11.605 11.605 11.605 11.605 dbcsr_finalize 27 5.7 0.018 0.018 5.503 5.503 dbcsr_merge_all 18 6.5 1.973 1.973 4.818 4.818 dbcsr_data_release 975 7.6 2.528 2.528 2.528 2.528 tree_to_linear_d 9 7.0 1.904 1.904 1.904 1.904 make_m2s 18 6.0 0.001 0.001 1.520 1.520 make_images 18 7.0 0.524 0.524 1.463 1.463 ------------------------------------------------------------------------------- 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 0.002 0.013 18.343 18.347 lib_test 1 2.0 0.000 0.000 18.308 18.324 dbcsr_run_tests 3 3.0 0.000 0.001 18.305 18.320 test_multiplies_multiproc 3 4.0 0.001 0.003 17.476 17.534 dbcsr_multiply_generic 9 5.0 0.001 0.001 15.672 15.723 multiply_cannon 9 6.0 0.002 0.002 13.937 14.282 multiply_cannon_loop 9 7.0 0.002 0.003 13.641 13.960 multiply_cannon_multrec 72 8.0 11.407 12.369 11.408 12.370 mp_waitall_1 576 9.2 2.561 3.303 2.561 3.303 multiply_cannon_metrocomm1 72 8.0 0.001 0.001 1.952 2.794 mp_sum_l 390 2.5 0.437 1.103 0.437 1.103 dbcsr_multiply_generic_mpsum_f 9 6.0 0.000 0.000 0.431 1.096 dbcsr_make_random_matrix 9 4.0 0.661 0.916 0.799 1.001 multiply_cannon_metrocomm3 72 8.0 0.000 0.000 0.273 0.885 make_m2s 18 6.0 0.001 0.001 0.701 0.731 dbcsr_finalize 27 5.7 0.000 0.000 0.638 0.731 make_images 18 7.0 0.021 0.025 0.697 0.728 dbcsr_data_release 444 7.6 0.630 0.706 0.630 0.706 dbcsr_merge_all 18 6.5 0.095 0.116 0.519 0.608 dbcsr_destroy 111 5.9 0.000 0.001 0.513 0.601 dbcsr_checksum 6 5.0 0.158 0.527 0.527 0.527 dbcsr_redistribute 9 5.0 0.238 0.275 0.416 0.449 make_images_data 18 8.0 0.001 0.001 0.368 0.422 dbcsr_data_copy_aa2 18 7.5 0.310 0.395 0.310 0.395 mp_sum_d 191 1.2 0.370 0.389 0.370 0.389 hybrid_alltoall_any 18 9.0 0.028 0.136 0.321 0.384 ------------------------------------------------------------------------------- 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=6.724999999999994, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_redistribute", label="dbcsr_redistribute", y=36.422, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=12.149, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=11.605, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_data_release", label="dbcsr_data_release", y=2.528, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_merge_all", label="dbcsr_merge_all", y=1.973, 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=2.3139999999999965, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_redistribute", label="dbcsr_redistribute", y=0.238, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=0.661, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=11.407, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_data_release", label="dbcsr_data_release", y=0.63, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_merge_all", label="dbcsr_merge_all", y=0.095, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=0.437, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=2.561, 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 0.044 0.044 137.050 137.050 qs_mol_dyn_low 1 2.0 0.003 0.003 135.660 135.660 velocity_verlet 5 3.0 0.003 0.003 111.092 111.092 qmmm_el_coupling 6 3.8 0.000 0.000 83.073 83.073 qmmm_elec_with_gaussian 6 4.8 0.072 0.072 83.065 83.065 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 82.356 82.356 qmmm_elec_gaussian_low_G 6 6.8 81.429 81.429 81.429 81.429 qs_forces 6 3.8 0.001 0.001 43.999 43.999 qs_energies 6 4.8 0.000 0.000 39.584 39.584 scf_env_do_scf 6 5.8 0.001 0.001 36.300 36.300 scf_env_do_scf_inner_loop 39 6.8 0.004 0.004 25.958 25.958 rebuild_ks_matrix 45 8.4 0.000 0.000 25.198 25.198 qs_ks_build_kohn_sham_matrix 45 9.4 0.005 0.005 25.198 25.198 qs_ks_update_qs_env 45 7.8 0.000 0.000 21.226 21.226 pw_transfer 966 12.3 0.049 0.049 17.199 17.199 fft_wrap_pw1pw2 801 13.6 0.006 0.006 16.978 16.978 fft_wrap_pw1pw2_150 507 15.2 2.084 2.084 16.546 16.546 qs_vxc_create 45 10.4 0.001 0.001 13.619 13.619 xc_vxc_pw_create 45 11.4 0.662 0.662 13.618 13.618 init_scf_loop 6 6.8 0.000 0.000 10.338 10.338 xc_pw_derive 270 13.4 0.002 0.002 9.332 9.332 fft3d_s 802 15.6 7.850 7.850 7.858 7.858 qs_rho_update_rho 45 7.9 0.000 0.000 7.274 7.274 calculate_rho_elec 45 8.9 0.562 0.562 7.273 7.273 xc_rho_set_and_dset_create 45 12.4 0.695 0.695 7.187 7.187 prepare_preconditioner 6 7.8 0.000 0.000 6.969 6.969 make_preconditioner 6 8.8 0.000 0.000 6.762 6.762 make_full_all 6 9.8 0.001 0.001 6.386 6.386 xc_pw_divergence 45 12.4 0.001 0.001 5.701 5.701 pw_scatter_s 429 15.8 5.659 5.659 5.659 5.659 qmmm_forces 6 3.8 0.002 0.002 5.433 5.433 qmmm_forces_with_gaussian 6 4.8 0.083 0.083 5.087 5.087 pw_integral_ab 2539 7.4 4.366 4.366 4.366 4.366 qs_ks_ddapc 45 10.4 0.001 0.001 4.317 4.317 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 4.254 4.254 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 3.979 3.979 cp_fm_diag_elpa 18 11.2 0.000 0.000 3.596 3.596 cp_fm_diag_elpa_base 18 12.2 3.588 3.588 3.596 3.596 qmmm_forces_gaussian_low_G 6 6.8 3.554 3.554 3.554 3.554 grid_collocate_task_list 45 9.9 3.378 3.378 3.378 3.378 density_rs2pw 45 9.9 0.001 0.001 3.333 3.333 sum_up_and_integrate 45 10.4 0.125 0.125 3.201 3.201 integrate_v_rspace 45 11.4 0.006 0.006 3.075 3.075 pw_poisson_solve 51 9.9 1.282 1.282 3.027 3.027 ------------------------------------------------------------------------------- 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 0.030 0.053 59.303 59.318 qs_mol_dyn_low 1 2.0 0.003 0.004 58.119 58.174 qs_forces 6 3.8 0.001 0.001 41.911 41.911 qs_energies 6 4.8 0.000 0.000 40.005 40.005 scf_env_do_scf 6 5.8 0.000 0.001 38.987 38.987 scf_env_do_scf_inner_loop 113 6.2 0.002 0.019 37.432 37.433 rebuild_ks_matrix 119 8.1 0.000 0.000 27.456 27.469 qs_ks_build_kohn_sham_matrix 119 9.1 0.015 0.019 27.455 27.468 qs_ks_update_qs_env 119 7.3 0.001 0.001 25.846 25.858 velocity_verlet 5 3.0 0.002 0.004 24.430 24.433 pw_transfer 2446 12.3 0.178 0.209 17.599 18.025 fft_wrap_pw1pw2 2059 13.4 0.022 0.026 17.193 17.661 fft_wrap_pw1pw2_150 1321 14.9 1.253 1.578 16.430 16.929 fft3d_ps 2059 15.4 6.858 8.227 13.105 13.956 qs_vxc_create 119 10.1 0.002 0.002 13.842 13.849 xc_vxc_pw_create 119 11.1 0.147 0.210 13.839 13.847 qs_rho_update_rho 119 7.3 0.001 0.001 11.221 11.225 calculate_rho_elec 119 8.3 0.049 0.060 11.221 11.224 xc_pw_derive 714 13.1 0.009 0.012 10.391 10.699 sum_up_and_integrate 119 10.1 0.055 0.072 9.750 10.063 integrate_v_rspace 119 11.1 0.003 0.005 9.695 10.020 qmmm_forces 6 3.8 0.002 0.002 8.122 8.122 qmmm_forces_with_gaussian 6 4.8 0.326 0.387 7.428 8.032 rs_pw_transfer 988 11.5 0.011 0.017 7.649 7.941 xc_rho_set_and_dset_create 119 12.1 0.355 0.615 6.606 7.368 qmmm_el_coupling 6 3.8 0.000 0.000 7.063 7.239 qmmm_elec_with_gaussian 6 4.8 0.323 0.385 7.061 7.237 xc_pw_divergence 119 12.1 0.004 0.005 6.810 7.054 density_rs2pw 119 9.3 0.005 0.007 6.569 6.844 mp_alltoall_z22v 2059 17.4 4.798 6.540 4.798 6.540 potential_pw2rs 119 12.1 0.006 0.009 5.918 5.941 grid_collocate_task_list 119 9.3 4.412 5.043 4.412 5.043 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 3.881 4.103 x_to_yz 1095 16.8 0.844 1.027 3.300 4.064 grid_integrate_task_list 119 12.1 3.431 3.970 3.431 3.970 yz_to_x 964 16.0 0.550 0.747 2.893 3.831 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 3.337 3.598 mp_waitany 4028 12.8 2.739 3.524 2.739 3.524 qmmm_forces_gaussian_low_G 6 6.8 3.196 3.424 3.196 3.424 rs_pw_transfer_PW2RS_150 125 13.9 1.234 1.508 2.987 3.057 qmmm_elec_gaussian_low_G 6 6.8 2.746 2.996 2.746 2.996 pw_restrict_s3 18 5.8 1.387 1.690 2.529 2.862 rs_pw_transfer_RS2PW_150 125 11.2 0.904 1.161 2.446 2.766 dbcsr_multiply_generic 2588 12.3 0.057 0.070 2.414 2.538 qmmm_elec_with_gaussian:spline 6 5.8 0.000 0.000 2.133 2.354 pw_prolongate_s3 18 6.8 1.156 1.384 2.133 2.354 qs_scf_new_mos 113 7.2 0.000 0.001 2.288 2.293 qs_scf_loop_do_ot 113 8.2 0.000 0.001 2.288 2.293 mp_waitall_1 188862 16.2 1.999 2.272 1.999 2.272 ot_scf_mini 113 9.2 0.001 0.001 2.196 2.201 mp_sum_dm3 33 5.7 1.860 2.077 1.860 2.077 qs_ks_ddapc 119 10.1 0.002 0.002 1.934 2.074 mp_sum_d 5820 12.2 1.114 1.772 1.114 1.772 pw_gather_p 964 15.0 1.216 1.721 1.216 1.721 pw_integral_ab 2761 7.7 1.123 1.268 1.511 1.681 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 1.623 1.624 pw_scatter_p 1095 15.8 1.567 1.617 1.567 1.617 init_scf_loop 6 6.8 0.000 0.000 1.552 1.552 ot_mini 113 10.2 0.000 0.001 1.371 1.377 ------------------------------------------------------------------------------- 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=27.226000000000013, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=81.429, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_s", label="fft3d_s", y=7.85, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_scatter_s", label="pw_scatter_s", y=5.659, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_integral_ab", label="pw_integral_ab", y=4.366, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=3.588, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.554, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=3.378, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_ps", label="fft3d_ps", y=0.0, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="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 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=32.73899999999999, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=2.746, 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=1.123, 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=3.196, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=4.412, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=6.858, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=4.798, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=3.431, yerr=0.0 Summary: Performance test took 44 minutes. Status: OK Removing intermediate container 84694d2d40ff ---> bb0b8f38b4c9 Step 41/42 : CMD cat $(find ./report.log -mmin +10) | sed '/^Summary:/ s/$/ (cached)/' ---> Running in f9e7f9d22341 Removing intermediate container f9e7f9d22341 ---> 2994928800f2 Step 42/42 : ENTRYPOINT [] ---> Running in 6a15b8c8c17f Removing intermediate container 6a15b8c8c17f ---> 5a18562383c4 [Warning] One or more build-args [GIT_COMMIT_SHA] were not consumed Successfully built 5a18562383c4 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: 2022-06-10 12:00:19+00:00