StartDate: 2022-12-12 19:11:21+00:00 CpuId: 32x AMD EPYC (3rd Gen) (Milan) [Zen 3], 7nm (SMT disabled) CommitSHA: eb0d6eed04221145363480ad2019c815711cc597 CommitTime: 2022-12-12 18:30:27 +0100 CommitAuthor: Ole Schütt CommitSubject: Toolchain: Upgrade to ELPA 2022.11.001.rc2 Populating docker build cache... done. #################### Building Image cp2k-perf-openmp #################### Dockerfile: /tools/docker/Dockerfile.test_performance Build-Path: / Build-Args: GIT_COMMIT_SHA=eb0d6eed04221145363480ad2019c815711cc597 Sending build context to Docker daemon 366.6MB Step 1/42 : FROM ubuntu:22.04 22.04: Pulling from library/ubuntu 6e3729cf69e0: Already exists Digest: sha256:27cb6e6ccef575a4698b66f5de06c7ecd61589132d5a91d098f7f3f9285415a9 Status: Downloaded newer image for ubuntu:22.04 ---> 6b7dfa7e8fdb Step 2/42 : WORKDIR /opt/cp2k-toolchain ---> Using cache ---> e98199835f6f Step 3/42 : COPY ./tools/toolchain/install_requirements*.sh ./ ---> Using cache ---> ccd07bf8588a Step 4/42 : RUN ./install_requirements.sh ubuntu:22.04 ---> Using cache ---> 0aa7ad9d2809 Step 5/42 : RUN mkdir scripts ---> Using cache ---> e9459f85bb88 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 ---> 47c0caf3dab5 Step 7/42 : COPY ./tools/toolchain/install_cp2k_toolchain.sh . ---> Using cache ---> be8fa6fbcf37 Step 8/42 : RUN ./install_cp2k_toolchain.sh --install-all --with-gcc=system --dry-run ---> Using cache ---> f28a1025b264 Step 9/42 : COPY ./tools/toolchain/scripts/stage0/ ./scripts/stage0/ ---> Using cache ---> 0252f324567d Step 10/42 : RUN ./scripts/stage0/install_stage0.sh && rm -rf ./build ---> Using cache ---> 269f2a947f93 Step 11/42 : COPY ./tools/toolchain/scripts/stage1/ ./scripts/stage1/ ---> Using cache ---> 061ba8cf7fc2 Step 12/42 : RUN ./scripts/stage1/install_stage1.sh && rm -rf ./build ---> Using cache ---> b31df7664679 Step 13/42 : COPY ./tools/toolchain/scripts/stage2/ ./scripts/stage2/ ---> Using cache ---> b70891ce336e Step 14/42 : RUN ./scripts/stage2/install_stage2.sh && rm -rf ./build ---> Using cache ---> db931592a37e Step 15/42 : COPY ./tools/toolchain/scripts/stage3/ ./scripts/stage3/ ---> Using cache ---> 23d09c2dd880 Step 16/42 : RUN ./scripts/stage3/install_stage3.sh && rm -rf ./build ---> Using cache ---> bc6e476c4c25 Step 17/42 : COPY ./tools/toolchain/scripts/stage4/ ./scripts/stage4/ ---> Using cache ---> 299b55068007 Step 18/42 : RUN ./scripts/stage4/install_stage4.sh && rm -rf ./build ---> Using cache ---> ec36b4d4647d Step 19/42 : COPY ./tools/toolchain/scripts/stage5/ ./scripts/stage5/ ---> Using cache ---> 2646377ee1e0 Step 20/42 : RUN ./scripts/stage5/install_stage5.sh && rm -rf ./build ---> Using cache ---> 524fe93ee93b Step 21/42 : COPY ./tools/toolchain/scripts/stage6/ ./scripts/stage6/ ---> Using cache ---> 4080c51eaad7 Step 22/42 : RUN ./scripts/stage6/install_stage6.sh && rm -rf ./build ---> Using cache ---> 027f315ec9ee Step 23/42 : COPY ./tools/toolchain/scripts/stage7/ ./scripts/stage7/ ---> Using cache ---> 3e2ce927b62d Step 24/42 : RUN ./scripts/stage7/install_stage7.sh && rm -rf ./build ---> Using cache ---> c9dd09a8c151 Step 25/42 : COPY ./tools/toolchain/scripts/stage8/ ./scripts/stage8/ ---> Using cache ---> d5ec573f56b8 Step 26/42 : RUN ./scripts/stage8/install_stage8.sh && rm -rf ./build ---> Using cache ---> cefac058d908 Step 27/42 : COPY ./tools/toolchain/scripts/arch_base.tmpl ./tools/toolchain/scripts/generate_arch_files.sh ./scripts/ ---> Using cache ---> 3316cd590f0f Step 28/42 : RUN ./scripts/generate_arch_files.sh && rm -rf ./build ---> Using cache ---> 7d88c45bab28 Step 29/42 : WORKDIR /opt/cp2k ---> Using cache ---> 1d4550a038d5 Step 30/42 : COPY ./Makefile . ---> Using cache ---> f5070a46e4ea Step 31/42 : COPY ./src ./src ---> Using cache ---> 65774619736d Step 32/42 : COPY ./exts ./exts ---> Using cache ---> 70418d08fff8 Step 33/42 : COPY ./tools/build_utils ./tools/build_utils ---> Using cache ---> e1cbbe94c748 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 3eddeaee6802 './arch/local.psmp' -> '/opt/cp2k-toolchain/install/arch/local.psmp' Compiling cp2k... Removing intermediate container 3eddeaee6802 ---> f2c0f51dc200 Step 35/42 : COPY ./data ./data ---> 6e2bcaa1812a Step 36/42 : COPY ./tests ./tests ---> dc0905b63115 Step 37/42 : COPY ./tools/regtesting ./tools/regtesting ---> fdd4fab76ced Step 38/42 : COPY ./benchmarks ./benchmarks ---> 2e9ec98a1c34 Step 39/42 : COPY ./tools/docker/scripts/test_performance.sh ./tools/docker/scripts/plot_performance.py ./ ---> 1e34ad6fe93f Step 40/42 : RUN ./test_performance.sh "local" 2>&1 | tee report.log ---> Running in c984f9ce84dc ========== 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 0.029 0.029 86.487 86.487 qs_mol_dyn_low 1 2.0 0.003 0.003 85.873 85.873 qs_forces 11 3.9 0.001 0.001 85.833 85.833 qs_energies 11 4.9 0.001 0.001 79.912 79.912 scf_env_do_scf 11 5.9 0.001 0.001 69.347 69.347 velocity_verlet 10 3.0 0.002 0.002 56.441 56.441 scf_env_do_scf_inner_loop 108 6.5 0.011 0.011 52.994 52.994 rebuild_ks_matrix 119 8.3 0.001 0.001 19.702 19.702 qs_ks_build_kohn_sham_matrix 119 9.3 0.012 0.012 19.701 19.701 dbcsr_multiply_generic 2286 12.5 0.159 0.159 19.412 19.412 qs_scf_new_mos 108 7.5 0.001 0.001 19.391 19.391 qs_scf_loop_do_ot 108 8.5 0.001 0.001 19.391 19.391 qs_rho_update_rho_low 119 7.7 0.001 0.001 19.224 19.224 calculate_rho_elec 119 8.7 0.950 0.950 19.223 19.223 qs_ks_update_qs_env 119 7.6 0.001 0.001 18.088 18.088 ot_scf_mini 108 9.5 0.002 0.002 18.065 18.065 init_scf_loop 11 6.9 0.000 0.000 16.225 16.225 grid_collocate_task_list 119 9.7 14.847 14.847 14.847 14.847 prepare_preconditioner 11 7.9 0.000 0.000 13.832 13.832 make_preconditioner 11 8.9 0.000 0.000 13.832 13.832 sum_up_and_integrate 119 10.3 0.513 0.513 12.848 12.848 make_full_inverse_cholesky 11 9.9 0.000 0.000 12.698 12.698 integrate_v_rspace 119 11.3 0.103 0.103 12.335 12.335 ot_mini 108 10.5 0.001 0.001 11.804 11.804 make_m2s 4572 13.5 0.045 0.045 10.784 10.784 grid_integrate_task_list 119 12.3 10.409 10.409 10.409 10.409 qs_ot_get_derivative 108 11.5 0.001 0.001 6.228 6.228 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 6.208 6.208 pw_transfer 1439 11.6 0.062 0.062 5.902 5.902 dbcsr_make_dense_low 5837 15.5 0.079 0.079 5.863 5.863 make_dense_data 5837 16.5 5.202 5.202 5.770 5.770 fft_wrap_pw1pw2 1201 12.6 0.006 0.006 5.708 5.708 ot_diis_step 108 11.5 0.004 0.004 5.573 5.573 make_images 4572 14.5 2.140 2.140 5.385 5.385 dbcsr_make_images_dense 3978 14.8 0.018 0.018 5.095 5.095 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 5.055 5.055 apply_single 119 13.6 0.000 0.000 5.055 5.055 fft_wrap_pw1pw2_140 487 13.2 0.426 0.426 4.895 4.895 multiply_cannon 2286 13.5 0.172 0.172 4.744 4.744 cp_fm_cholesky_decompose 22 10.9 4.400 4.400 4.400 4.400 multiply_cannon_loop 2286 14.5 0.041 0.041 4.289 4.289 multiply_cannon_multrec 2286 15.5 4.197 4.197 4.247 4.247 cp_fm_cholesky_invert 11 10.9 4.138 4.138 4.138 4.138 init_scf_run 11 5.9 0.002 0.002 3.757 3.757 scf_env_initial_rho_setup 11 6.9 0.001 0.001 3.755 3.755 dbcsr_copy 2102 12.0 0.231 0.231 3.611 3.611 dbcsr_complete_redistribute 329 12.2 1.921 1.921 3.580 3.580 density_rs2pw 119 9.7 0.005 0.005 3.427 3.427 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 3.351 3.351 dbcsr_copy_into_existing 22 7.9 3.344 3.344 3.344 3.344 wfi_extrapolate 11 7.9 0.001 0.001 3.303 3.303 qs_env_update_s_mstruct 11 6.9 0.000 0.000 3.273 3.273 copy_dbcsr_to_fm 153 11.3 0.002 0.002 2.959 2.959 qs_ot_get_p 119 10.4 0.001 0.001 2.912 2.912 qs_create_task_list 11 7.9 0.000 0.000 2.894 2.894 generate_qs_task_list 11 8.9 1.969 1.969 2.894 2.894 fft3d_s 1202 14.6 2.807 2.807 2.811 2.811 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 2.567 2.567 build_core_hamiltonian_matrix 11 6.9 0.000 0.000 2.518 2.518 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.330 2.330 dbcsr_data_release 279534 16.0 2.007 2.007 2.007 2.007 pw_poisson_solve 119 10.3 0.335 0.335 1.969 1.969 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 1.954 1.954 qs_ot_get_derivative_taylor 59 13.0 0.001 0.001 1.936 1.936 potential_pw2rs 119 12.3 0.045 0.045 1.822 1.822 copy_fm_to_dbcsr 176 11.2 0.001 0.001 1.809 1.809 cp_fm_upper_to_full 72 14.2 1.751 1.751 1.751 1.751 ------------------------------------------------------------------------------- From /workspace/artifacts/H2O-64_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.007 0.024 42.930 42.939 qs_mol_dyn_low 1 2.0 0.003 0.004 42.825 42.830 qs_forces 11 3.9 0.001 0.001 42.785 42.786 qs_energies 11 4.9 0.001 0.001 39.982 39.984 scf_env_do_scf 11 5.9 0.000 0.002 36.642 36.643 scf_env_do_scf_inner_loop 108 6.5 0.003 0.018 33.798 33.799 velocity_verlet 10 3.0 0.002 0.003 25.569 25.570 rebuild_ks_matrix 119 8.3 0.000 0.001 15.445 15.550 qs_ks_build_kohn_sham_matrix 119 9.3 0.015 0.016 15.445 15.549 qs_ks_update_qs_env 119 7.6 0.001 0.001 13.738 13.831 dbcsr_multiply_generic 2286 12.5 0.072 0.075 12.767 12.946 qs_rho_update_rho_low 119 7.7 0.001 0.001 12.646 12.654 calculate_rho_elec 119 8.7 0.029 0.030 12.646 12.654 sum_up_and_integrate 119 10.3 0.030 0.032 11.443 11.459 integrate_v_rspace 119 11.3 0.004 0.005 11.413 11.430 qs_scf_new_mos 108 7.5 0.001 0.001 9.991 10.095 qs_scf_loop_do_ot 108 8.5 0.001 0.001 9.991 10.094 multiply_cannon 2286 13.5 0.146 0.154 9.486 9.906 ot_scf_mini 108 9.5 0.002 0.002 9.374 9.464 multiply_cannon_loop 2286 14.5 0.093 0.099 8.961 9.420 grid_collocate_task_list 119 9.7 8.912 9.204 8.912 9.204 mp_waitall_1 169478 16.3 7.858 8.379 7.858 8.379 grid_integrate_task_list 119 12.3 7.977 8.146 7.977 8.146 multiply_cannon_metrocomm3 18288 15.5 0.036 0.038 5.238 5.826 ot_mini 108 10.5 0.001 0.001 5.429 5.530 rs_pw_transfer 974 11.9 0.010 0.011 4.004 4.376 density_rs2pw 119 9.7 0.005 0.006 3.386 3.762 pw_transfer 1439 11.6 0.100 0.108 3.227 3.260 fft_wrap_pw1pw2 1201 12.6 0.009 0.010 3.060 3.098 multiply_cannon_multrec 18288 15.5 2.913 3.011 2.923 3.020 potential_pw2rs 119 12.3 0.007 0.007 2.993 3.000 qs_ot_get_derivative 108 11.5 0.001 0.001 2.763 2.852 init_scf_loop 11 6.9 0.000 0.000 2.831 2.831 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 2.596 2.713 apply_single 119 13.6 0.000 0.000 2.596 2.713 fft_wrap_pw1pw2_140 487 13.2 0.261 0.281 2.606 2.681 ot_diis_step 108 11.5 0.003 0.003 2.646 2.646 init_scf_run 11 5.9 0.000 0.004 2.365 2.365 scf_env_initial_rho_setup 11 6.9 0.000 0.003 2.365 2.365 make_m2s 4572 13.5 0.045 0.050 2.229 2.281 fft3d_ps 1201 14.6 1.184 1.232 2.188 2.226 wfi_extrapolate 11 7.9 0.001 0.001 2.139 2.139 make_images 4572 14.5 0.114 0.118 1.906 1.960 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 1.837 1.848 mp_waitany 9880 13.7 1.265 1.651 1.265 1.651 rs_pw_transfer_RS2PW_140 130 11.5 0.192 0.231 0.958 1.335 qs_ot_get_p 119 10.4 0.001 0.001 1.189 1.325 rs_pw_transfer_PW2RS_140 130 13.9 0.358 0.385 1.164 1.182 make_images_data 4572 15.5 0.035 0.041 1.046 1.129 prepare_preconditioner 11 7.9 0.000 0.000 1.103 1.125 make_preconditioner 11 8.9 0.000 0.000 1.103 1.125 make_full_inverse_cholesky 11 9.9 0.000 0.000 0.999 1.013 hybrid_alltoall_any 4725 16.4 0.063 0.185 0.924 1.011 mp_sum_l 11218 13.2 0.621 0.950 0.621 0.950 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 0.854 0.935 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 0.891 0.931 qs_ot_get_derivative_taylor 59 13.0 0.001 0.001 0.865 0.923 cp_dbcsr_sm_fm_multiply 37 9.5 0.001 0.001 0.899 0.900 multiply_cannon_metrocomm1 18288 15.5 0.018 0.019 0.510 0.868 ------------------------------------------------------------------------------- Plot: name="H2O-64_timings_32omp", title="Timings of H2O-64 with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="H2O-64_timings_32omp", name="rest", label="rest", y=47.431999999999995, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=14.847, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=10.409, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="make_dense_data", label="make_dense_data", y=5.202, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=4.4, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=4.197, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="mp_waitany", label="mp_waitany", y=0.0, yerr=0.0 Plot: name="H2O-64_timings_32mpi", title="Timings of H2O-64 with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="H2O-64_timings_32mpi", name="rest", label="rest", y=14.004999999999995, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=8.912, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=7.977, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="make_dense_data", label="make_dense_data", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=2.913, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=7.858, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitany", label="mp_waitany", y=1.265, 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 0.031 0.031 110.621 110.621 qs_mol_dyn_low 1 2.0 0.003 0.003 109.968 109.968 qs_forces 11 3.9 0.001 0.001 109.929 109.929 qs_energies 11 4.9 0.001 0.001 102.439 102.439 scf_env_do_scf 11 5.9 0.001 0.001 89.982 89.982 scf_env_do_scf_inner_loop 96 6.5 0.010 0.010 72.072 72.072 velocity_verlet 10 3.0 0.002 0.002 70.983 70.983 rebuild_ks_matrix 107 8.3 0.001 0.001 33.071 33.071 qs_ks_build_kohn_sham_matrix 107 9.3 0.011 0.011 33.070 33.070 qs_rho_update_rho_low 107 7.7 0.000 0.000 31.537 31.537 calculate_rho_elec 107 8.7 0.853 0.853 31.537 31.537 qs_ks_update_qs_env 107 7.6 0.001 0.001 29.757 29.757 grid_collocate_task_list 107 9.7 27.150 27.150 27.150 27.150 sum_up_and_integrate 107 10.3 0.453 0.453 26.564 26.564 integrate_v_rspace 107 11.3 0.101 0.101 26.110 26.110 grid_integrate_task_list 107 12.3 24.328 24.328 24.328 24.328 dbcsr_multiply_generic 1966 12.4 0.146 0.146 17.906 17.906 init_scf_loop 11 6.9 0.000 0.000 17.753 17.753 qs_scf_new_mos 96 7.5 0.000 0.000 17.488 17.488 qs_scf_loop_do_ot 96 8.5 0.001 0.001 17.488 17.488 ot_scf_mini 96 9.5 0.002 0.002 16.308 16.308 prepare_preconditioner 11 7.9 0.000 0.000 13.754 13.754 make_preconditioner 11 8.9 0.000 0.000 13.754 13.754 make_full_inverse_cholesky 11 9.9 0.000 0.000 12.611 12.611 ot_mini 96 10.5 0.001 0.001 10.513 10.513 make_m2s 3932 13.4 0.039 0.039 9.752 9.752 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 6.576 6.576 pw_transfer 1295 11.6 0.056 0.056 5.893 5.893 fft_wrap_pw1pw2 1081 12.6 0.005 0.005 5.667 5.667 qs_ot_get_derivative 96 11.5 0.001 0.001 5.324 5.324 init_scf_run 11 5.9 0.002 0.002 5.237 5.237 scf_env_initial_rho_setup 11 6.9 0.000 0.000 5.235 5.235 ot_diis_step 96 11.5 0.003 0.003 5.187 5.187 dbcsr_make_dense_low 4961 15.5 0.074 0.074 5.173 5.173 make_dense_data 4961 16.5 4.546 4.546 5.087 5.087 fft_wrap_pw1pw2_140 439 13.2 0.492 0.492 4.946 4.946 make_images 3932 14.4 1.933 1.933 4.870 4.870 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 4.706 4.706 apply_single 107 13.6 0.000 0.000 4.706 4.706 wfi_extrapolate 11 7.9 0.001 0.001 4.634 4.634 dbcsr_make_images_dense 3386 14.7 0.016 0.016 4.548 4.548 multiply_cannon 1966 13.4 0.190 0.190 4.515 4.515 cp_fm_cholesky_decompose 22 10.9 4.362 4.362 4.362 4.362 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 4.164 4.164 cp_fm_cholesky_invert 11 10.9 4.034 4.034 4.034 4.034 multiply_cannon_loop 1966 14.4 0.073 0.073 4.007 4.007 multiply_cannon_multrec 1966 15.4 3.888 3.888 3.933 3.933 qs_env_update_s_mstruct 11 6.9 0.000 0.000 3.665 3.665 dbcsr_complete_redistribute 317 12.2 1.883 1.883 3.605 3.605 dbcsr_copy 1855 11.9 0.190 0.190 3.539 3.539 density_rs2pw 107 9.7 0.004 0.004 3.533 3.533 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 3.324 3.324 qs_create_task_list 11 7.9 0.000 0.000 3.300 3.300 generate_qs_task_list 11 8.9 2.397 2.397 3.299 3.299 dbcsr_copy_into_existing 22 7.9 3.269 3.269 3.270 3.270 copy_dbcsr_to_fm 147 11.2 0.002 0.002 2.997 2.997 fft3d_s 1082 14.6 2.849 2.849 2.854 2.854 build_core_hamiltonian_matrix 11 6.9 0.000 0.000 2.498 2.498 qs_ot_get_p 107 10.4 0.001 0.001 2.482 2.482 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.343 2.343 ------------------------------------------------------------------------------- From /workspace/artifacts/H2O-64_nonortho_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.007 0.025 69.737 69.746 qs_mol_dyn_low 1 2.0 0.003 0.004 69.542 69.547 qs_forces 11 3.9 0.001 0.002 69.502 69.503 qs_energies 11 4.9 0.001 0.001 64.803 64.805 scf_env_do_scf 11 5.9 0.000 0.002 59.959 59.959 scf_env_do_scf_inner_loop 96 6.5 0.002 0.016 55.466 55.466 velocity_verlet 10 3.0 0.002 0.003 41.278 41.279 rebuild_ks_matrix 107 8.3 0.000 0.001 30.092 30.183 qs_ks_build_kohn_sham_matrix 107 9.3 0.013 0.014 30.092 30.183 qs_ks_update_qs_env 107 7.6 0.001 0.001 26.483 26.563 sum_up_and_integrate 107 10.3 0.031 0.034 26.396 26.419 integrate_v_rspace 107 11.3 0.004 0.004 26.364 26.387 qs_rho_update_rho_low 107 7.7 0.000 0.001 25.455 25.459 calculate_rho_elec 107 8.7 0.027 0.027 25.454 25.458 grid_integrate_task_list 107 12.3 22.705 23.143 22.705 23.143 grid_collocate_task_list 107 9.7 21.796 22.261 21.796 22.261 dbcsr_multiply_generic 1966 12.4 0.064 0.066 11.786 11.970 qs_scf_new_mos 96 7.5 0.001 0.001 9.139 9.223 qs_scf_loop_do_ot 96 8.5 0.001 0.001 9.139 9.223 multiply_cannon 1966 13.4 0.130 0.135 8.740 9.163 ot_scf_mini 96 9.5 0.002 0.002 8.571 8.653 multiply_cannon_loop 1966 14.4 0.086 0.094 8.236 8.638 mp_waitall_1 146670 16.2 7.207 7.511 7.207 7.511 multiply_cannon_metrocomm3 15728 15.4 0.032 0.034 4.747 5.336 ot_mini 96 10.5 0.001 0.001 4.997 5.086 rs_pw_transfer 878 11.9 0.009 0.010 4.047 4.690 init_scf_loop 11 6.9 0.000 0.001 4.480 4.480 density_rs2pw 107 9.7 0.005 0.005 3.349 3.994 init_scf_run 11 5.9 0.000 0.004 3.830 3.830 scf_env_initial_rho_setup 11 6.9 0.000 0.003 3.829 3.829 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 3.731 3.743 wfi_extrapolate 11 7.9 0.001 0.001 3.484 3.484 pw_transfer 1295 11.6 0.089 0.095 2.936 2.972 multiply_cannon_multrec 15728 15.4 2.736 2.838 2.745 2.847 potential_pw2rs 107 12.3 0.006 0.007 2.825 2.838 fft_wrap_pw1pw2 1081 12.6 0.008 0.009 2.786 2.823 qs_ot_get_derivative 96 11.5 0.001 0.001 2.543 2.625 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 2.387 2.467 apply_single 107 13.6 0.000 0.000 2.386 2.467 fft_wrap_pw1pw2_140 439 13.2 0.234 0.253 2.393 2.444 ot_diis_step 96 11.5 0.003 0.003 2.434 2.434 mp_waitany 8968 13.7 1.470 2.112 1.470 2.112 make_m2s 3932 13.4 0.040 0.043 2.023 2.072 fft3d_ps 1081 14.6 1.066 1.133 1.988 2.033 rs_pw_transfer_RS2PW_140 118 11.5 0.164 0.180 1.134 1.786 make_images 3932 14.4 0.103 0.105 1.733 1.780 mp_alltoall_d11v 1998 13.7 1.011 1.667 1.011 1.667 rs_gather_matrices 107 12.3 0.076 0.085 0.797 1.425 ------------------------------------------------------------------------------- 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=42.31299999999999, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=27.15, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=24.328, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="make_dense_data", label="make_dense_data", y=4.546, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=4.362, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=4.034, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=3.888, 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=13.823, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=21.796, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=22.705, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="make_dense_data", label="make_dense_data", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=2.736, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitany", label="mp_waitany", y=1.47, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=7.207, 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 0.182 0.182 105.043 105.043 qs_energies 1 2.0 0.000 0.000 104.219 104.219 scf_env_do_scf 1 3.0 0.000 0.000 103.099 103.099 qs_ks_update_qs_env 8 5.0 0.000 0.000 97.941 97.941 rebuild_ks_matrix 7 6.0 0.000 0.000 97.887 97.887 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.001 97.887 97.887 hfx_ks_matrix 7 8.0 0.000 0.000 88.624 88.624 integrate_four_center 7 9.0 1.917 1.917 88.594 88.594 integrate_four_center_main 7 10.0 0.426 0.426 80.798 80.798 integrate_four_center_bin 447 11.0 80.372 80.372 80.372 80.372 scf_env_do_scf_inner_loop 7 4.0 0.001 0.001 56.703 56.703 init_scf_loop 1 4.0 0.000 0.000 46.384 46.384 integrate_four_center_load 7 10.0 0.000 0.000 5.632 5.632 hfx_load_balance 1 11.0 0.001 0.001 5.632 5.632 qs_vxc_create 14 8.0 0.000 0.000 3.193 3.193 xc_vxc_pw_create 14 9.0 0.153 0.153 3.192 3.192 hfx_load_balance_count 1 12.0 2.809 2.809 2.809 2.809 hfx_load_balance_bin 1 12.0 2.806 2.806 2.806 2.806 admm_mo_calc_rho_aux 7 8.0 0.000 0.000 2.449 2.449 calculate_rho_elec 15 7.4 0.118 0.118 2.417 2.417 prepare_preconditioner 1 5.0 0.000 0.000 2.403 2.403 make_preconditioner 1 6.0 0.000 0.000 2.403 2.403 xc_rho_set_and_dset_create 14 10.0 0.103 0.103 2.392 2.392 ------------------------------------------------------------------------------- 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 0.218 0.238 94.750 94.761 qs_energies 1 2.0 0.000 0.000 94.405 94.412 scf_env_do_scf 1 3.0 0.000 0.000 93.953 93.954 qs_ks_update_qs_env 8 5.0 0.000 0.000 92.057 92.058 rebuild_ks_matrix 7 6.0 0.000 0.000 92.049 92.050 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.001 92.049 92.050 hfx_ks_matrix 7 8.0 0.000 0.000 86.883 86.884 integrate_four_center 7 9.0 0.053 0.330 86.874 86.875 integrate_four_center_main 7 10.0 0.003 0.003 78.645 79.967 integrate_four_center_bin 448 11.0 78.642 79.965 78.642 79.965 scf_env_do_scf_inner_loop 7 4.0 0.000 0.001 52.682 52.682 init_scf_loop 1 4.0 0.000 0.000 41.270 41.270 integrate_four_center_load 7 10.0 0.000 0.000 5.852 5.853 hfx_load_balance 1 11.0 0.001 0.001 5.852 5.853 mp_sync 70 11.3 1.726 3.153 1.726 3.153 hfx_load_balance_count 1 12.0 2.769 2.923 2.769 2.923 hfx_load_balance_bin 1 12.0 2.768 2.922 2.768 2.922 qs_vxc_create 14 8.0 0.000 0.000 2.326 2.326 xc_vxc_pw_create 14 9.0 0.007 0.007 2.326 2.326 xc_rho_set_and_dset_create 14 10.0 0.009 0.010 1.889 1.999 ------------------------------------------------------------------------------- Plot: name="H2O-hyb_timings_32omp", title="Timings of H2O-hyb with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="H2O-hyb_timings_32omp", name="rest", label="rest", y=16.531000000000006, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_bin", label="integrate_four_center_bin", y=80.372, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_count", label="hfx_load_balance_count", y=2.809, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=2.806, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center", label="integrate_four_center", y=1.917, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_main", label="integrate_four_center_main", y=0.426, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="CP2K", label="CP2K", y=0.182, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="mp_sync", label="mp_sync", y=0.0, yerr=0.0 Plot: name="H2O-hyb_timings_32mpi", title="Timings of H2O-hyb with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="H2O-hyb_timings_32mpi", name="rest", label="rest", y=8.570999999999998, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center_bin", label="integrate_four_center_bin", y=78.642, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_count", label="hfx_load_balance_count", y=2.769, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=2.768, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center", label="integrate_four_center", y=0.053, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center_main", label="integrate_four_center_main", y=0.003, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="CP2K", label="CP2K", y=0.218, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="mp_sync", label="mp_sync", y=1.726, yerr=0.0 Running GW_PBE_4benzene.inp with 1 threads and 32 ranks... done. Running GW_PBE_4benzene.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/GW_PBE_4benzene_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.013 0.013 82.866 82.866 qs_energies 1 2.0 0.000 0.000 82.488 82.488 mp2_main 1 3.0 0.000 0.000 79.610 79.610 mp2_gpw_main 1 4.0 0.000 0.000 79.501 79.501 rpa_ri_compute_en 1 5.0 0.000 0.000 75.780 75.780 rpa_num_int 1 6.0 0.001 0.001 75.774 75.774 compute_mat_P_omega 1 7.0 0.003 0.003 65.622 65.622 compute_mat_P_omega_contract 10 8.0 8.839 8.839 65.072 65.072 dbt_total 2336 9.6 0.011 0.011 51.624 51.624 dbt_contract 787 11.0 0.034 0.034 44.618 44.618 dbt_tas_total 1149 12.2 0.196 0.196 43.657 43.657 dbt_tas_multiply 807 12.1 0.002 0.002 42.246 42.246 dbt_tas_dbm 807 14.1 0.003 0.003 35.747 35.747 dbm_multiply 807 16.1 35.738 35.738 35.738 35.738 dbt_tas_mm_1N 524 15.1 0.001 0.001 27.146 27.146 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 25.686 25.686 compute_mat_P_omega_calc_M_occ 250 9.0 8.875 8.875 16.930 16.930 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 7.879 7.879 dbt_tas_mm_2 251 15.0 0.001 0.001 7.023 7.023 dbt_copy 1103 10.7 0.068 0.068 5.578 5.578 compute_QP_energies 1 7.0 0.000 0.000 5.238 5.238 compute_self_energy_cubic_gw 1 8.0 0.052 0.052 5.237 5.237 contract_cubic_gw 21 9.0 0.000 0.000 4.253 4.253 mp2_ri_gpw_compute_in 1 5.0 0.001 0.001 3.714 3.714 dbt_tas_reserve_blocks_index 3261 14.3 0.144 0.144 3.511 3.511 dbm_reserve_blocks 3628 15.3 3.435 3.435 3.435 3.435 scf_env_do_scf 1 3.0 0.000 0.000 2.748 2.748 scf_env_do_scf_inner_loop 17 4.0 0.002 0.002 2.748 2.748 dbt_reserve_blocks_index 2280 13.1 0.053 0.053 2.698 2.698 dbt_reserve_blocks_index_array 2222 12.2 0.010 0.010 2.653 2.653 dbt_crop 1042 12.0 1.450 1.450 2.269 2.269 convert_to_new_pgrid 2421 14.1 0.088 0.088 2.184 2.184 dbt_tas_reshape 367 15.0 0.006 0.006 2.176 2.176 dbt_tas_copy 574 11.4 1.316 1.316 2.125 2.125 dbm_copy 1614 15.1 2.096 2.096 2.096 2.096 compute_W_cubic_GW 10 7.0 0.004 0.004 2.044 2.044 rpa_num_int_RPA_matrix_operati 10 7.0 0.000 0.000 2.029 2.029 dbt_reshape 278 11.9 0.995 0.995 1.883 1.883 get_2c_integrals 1 6.0 0.000 0.000 1.780 1.780 ------------------------------------------------------------------------------- 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 32.991 33.001 qs_energies 1 2.0 0.000 0.000 32.914 32.916 mp2_main 1 3.0 0.000 0.000 31.998 32.000 mp2_gpw_main 1 4.0 0.000 0.000 31.964 31.966 rpa_ri_compute_en 1 5.0 0.000 0.000 30.710 30.712 rpa_num_int 1 6.0 0.000 0.002 30.710 30.711 dbt_total 2336 9.6 0.012 0.014 27.062 27.072 compute_mat_P_omega 1 7.0 0.001 0.005 25.115 25.139 compute_mat_P_omega_contract 10 8.0 0.407 0.425 24.984 24.989 dbt_contract 787 11.0 0.025 0.026 20.449 20.452 dbt_tas_total 1149 12.2 0.051 0.058 18.456 18.457 dbt_tas_multiply 807 12.1 0.002 0.002 18.399 18.401 dbt_tas_dbm 807 14.1 0.003 0.003 13.982 14.005 dbm_multiply 807 16.1 10.440 11.629 10.440 11.629 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 7.423 7.423 compute_mat_P_omega_calc_M_occ 250 9.0 0.392 0.409 7.370 7.370 mp_sync 8706 11.6 5.350 6.706 5.350 6.706 dbt_tas_mm_2 251 15.0 0.001 0.001 6.164 6.177 dbt_copy 1111 10.7 0.012 0.012 5.781 5.977 dbt_reshape 1098 11.7 2.148 2.244 5.490 5.680 dbt_tas_mm_1N 524 15.1 0.001 0.002 4.974 5.501 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 5.339 5.339 compute_QP_energies 1 7.0 0.000 0.000 3.677 3.678 compute_self_energy_cubic_gw 1 8.0 0.003 0.004 3.676 3.677 contract_cubic_gw 21 9.0 0.000 0.000 3.014 3.014 mp_waitall_2 3776 15.3 2.560 2.761 2.560 2.761 dbt_communicate_buffer 1098 12.7 0.053 0.057 2.609 2.741 dbt_reserve_blocks_index 2849 13.1 0.064 0.069 1.594 1.799 dbt_reserve_blocks_index_array 2791 12.2 0.009 0.018 1.585 1.787 dbt_tas_reserve_blocks_index 3300 14.5 0.114 0.121 1.564 1.769 dbm_reserve_blocks 3696 15.4 1.545 1.746 1.545 1.746 dbt_crop 1042 12.0 0.894 0.984 1.389 1.497 mp2_ri_gpw_compute_in 1 5.0 0.000 0.001 1.253 1.253 parallel_gemm_fm 105 8.4 0.000 0.000 1.188 1.197 parallel_gemm_fm_cosma 105 9.4 1.188 1.197 1.188 1.197 dbt_tas_replicate 396 14.1 0.535 0.697 1.094 1.150 compute_mat_P_omega_copy_M_vir 250 9.0 0.001 0.001 0.992 0.994 compute_mat_P_omega_copy_M_occ 250 9.0 0.001 0.001 0.926 0.928 compute_W_cubic_GW 10 7.0 0.001 0.001 0.907 0.912 convert_to_new_pgrid 2421 14.1 0.025 0.029 0.806 0.911 scf_env_do_scf 1 3.0 0.000 0.000 0.879 0.879 scf_env_do_scf_inner_loop 17 4.0 0.000 0.002 0.879 0.879 dbm_copy 1608 15.1 0.775 0.879 0.775 0.879 dbt_tas_mm_3N 22 15.1 0.000 0.000 0.536 0.802 rpa_num_int_RPA_matrix_operati 10 7.0 0.000 0.000 0.755 0.755 ------------------------------------------------------------------------------- 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=22.887999999999998, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=35.738, 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=8.875, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=8.839, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=3.435, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_copy", label="dbm_copy", y=2.096, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=0.995, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="mp_sync", label="mp_sync", y=0.0, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="mp_waitall_2", label="mp_waitall_2", y=0.0, yerr=0.0 Plot: name="GW_PBE_4benzene_timings_32mpi", title="Timings of GW_PBE_4benzene with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="rest", label="rest", y=9.374000000000002, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=10.44, 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=0.392, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=0.407, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=1.545, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_copy", label="dbm_copy", y=0.775, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=2.148, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_sync", label="mp_sync", y=5.35, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.56, 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 0.018 269.075 269.075 qs_forces 1 2.0 0.000 0.000 268.523 268.523 rebuild_ks_matrix 7 6.6 0.000 0.000 267.078 267.078 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.001 267.078 267.078 hfx_ks_matrix 7 8.6 0.000 0.000 265.227 265.227 hfx_ri_update_ks 7 9.6 0.000 0.000 224.035 224.035 hfx_ri_update_ks_Pmat 7 10.6 31.646 31.646 224.031 224.031 dbt_total 841 11.0 0.005 0.005 210.762 210.762 qs_energies 1 3.0 0.000 0.000 197.882 197.882 scf_env_do_scf 1 4.0 0.000 0.000 197.596 197.596 qs_ks_update_qs_env 8 6.0 0.000 0.000 196.488 196.488 dbt_contract 207 12.4 0.054 0.054 191.911 191.911 dbt_tas_total 375 13.4 1.740 1.740 191.288 191.288 dbt_tas_multiply 216 13.5 0.001 0.001 186.900 186.900 dbt_tas_dbm 216 15.5 0.001 0.001 173.489 173.489 dbm_multiply 216 17.5 173.485 173.485 173.485 173.485 hfx_ri_update_ks_Pmat_KS 63 11.6 0.001 0.001 168.220 168.220 dbt_tas_mm_2 91 16.5 0.001 0.001 159.864 159.864 scf_env_do_scf_inner_loop 6 5.0 0.001 0.001 125.912 125.912 init_scf_loop 2 5.0 0.000 0.000 71.682 71.682 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 70.594 70.594 hfx_ri_update_forces 1 7.0 1.640 1.640 41.185 41.185 hfx_ri_forces_Pmat_3c 1 8.0 4.721 4.721 24.584 24.584 dbt_copy 409 11.7 0.027 0.027 14.455 14.455 precalc_derivatives 1 8.0 2.224 2.224 12.698 12.698 dbt_reshape 132 13.2 6.213 6.213 10.182 10.182 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 9.805 9.805 dbt_tas_mm_3T 77 17.1 0.000 0.000 9.462 9.462 dbt_tas_reserve_blocks_index 1287 15.4 0.272 0.272 7.029 7.029 build_3c_derivatives 3 9.0 2.730 2.730 7.013 7.013 dbm_reserve_blocks 1461 16.2 6.968 6.968 6.968 6.968 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 6.879 6.879 dbt_reserve_blocks_index 818 14.4 0.088 0.088 5.490 5.490 dbt_reserve_blocks_index_array 795 13.4 0.007 0.007 5.392 5.392 ------------------------------------------------------------------------------- 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 0.006 0.019 43.874 43.883 qs_forces 1 2.0 0.000 0.000 43.768 43.768 rebuild_ks_matrix 7 6.6 0.000 0.000 43.108 43.108 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.002 43.107 43.108 hfx_ks_matrix 7 8.6 0.000 0.000 42.183 42.191 dbt_total 841 11.0 0.005 0.005 37.447 37.448 dbt_contract 207 12.4 0.020 0.021 29.476 29.490 dbt_tas_total 375 13.4 0.045 0.139 27.358 27.359 dbt_tas_multiply 216 13.5 0.001 0.001 26.444 26.444 hfx_ri_update_ks 7 9.6 0.000 0.000 24.578 24.578 hfx_ri_update_ks_Pmat 7 10.6 1.204 1.288 24.577 24.577 qs_energies 1 3.0 0.000 0.000 23.014 23.014 scf_env_do_scf 1 4.0 0.000 0.001 22.875 22.876 qs_ks_update_qs_env 8 6.0 0.000 0.000 22.367 22.367 dbt_tas_dbm 216 15.5 0.001 0.001 21.177 21.178 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 20.742 20.742 dbm_multiply 216 17.5 18.512 19.537 18.512 19.537 hfx_ri_update_forces 1 7.0 0.055 0.061 17.604 17.612 hfx_ri_forces_Pmat_3c 1 8.0 0.166 0.180 13.083 13.097 scf_env_do_scf_inner_loop 6 5.0 0.000 0.001 12.801 12.801 hfx_ri_update_ks_Pmat_KS 63 11.6 0.000 0.001 11.714 11.714 init_scf_loop 2 5.0 0.000 0.000 10.074 10.074 dbt_tas_mm_2 91 16.5 0.001 0.001 9.905 9.905 mp_sync 2909 12.8 4.826 7.206 4.826 7.206 dbt_copy 421 11.8 0.009 0.011 6.526 6.785 dbt_tas_mm_3T 77 17.1 0.000 0.000 5.441 5.793 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 4.810 4.810 dbt_reshape 252 12.8 2.236 2.324 4.485 4.627 dbt_tas_mm_3N 37 15.4 0.000 0.000 4.026 4.202 precalc_derivatives 1 8.0 0.079 0.086 3.449 3.449 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 3.092 3.092 dbm_reserve_blocks 1477 16.3 2.515 2.828 2.515 2.828 dbt_tas_reserve_blocks_index 1302 15.5 0.214 0.222 2.504 2.814 dbt_crop 372 13.7 1.713 1.809 2.320 2.479 mp_waitall_2 1204 16.3 2.234 2.369 2.234 2.369 dbt_reserve_blocks_index 938 14.4 0.094 0.101 1.965 2.174 dbt_reserve_blocks_index_array 915 13.4 0.005 0.005 1.943 2.151 build_3c_derivatives 3 9.0 0.221 0.238 1.950 1.962 dbt_tas_replicate 175 15.2 0.672 0.710 1.658 1.722 hfx_ri_pre_scf_Pmat_RIx3C 9 13.0 0.000 0.000 1.634 1.638 dbt_communicate_buffer 252 13.8 0.011 0.013 1.512 1.588 dbt_tas_copy 169 12.8 0.781 0.820 1.396 1.543 convert_to_new_pgrid 648 15.5 0.030 0.082 1.279 1.457 hfx_ri_update_ks_Pmat_copy_2 63 11.6 0.000 0.000 1.392 1.392 dbm_copy 452 16.3 1.107 1.272 1.107 1.272 dbt_tas_communicate_buffer 352 16.4 0.013 0.015 0.948 1.052 ------------------------------------------------------------------------------- Plot: name="RI-HFX_H2O-32_timings_32omp", title="Timings of RI-HFX_H2O-32 with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="rest", label="rest", y=46.04199999999997, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=173.485, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=31.646, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=6.968, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=6.213, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_forces_Pmat_3c", label="hfx_ri_forces_Pmat_3c", y=4.721, 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=12.180999999999997, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=18.512, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=1.204, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=2.515, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=2.236, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_forces_Pmat_3c", label="hfx_ri_forces_Pmat_3c", y=0.166, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.234, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_sync", label="mp_sync", y=4.826, 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 0.015 190.415 190.415 qs_energies 1 2.0 0.000 0.000 190.227 190.227 mp2_main 1 3.0 0.000 0.000 185.585 185.585 mp2_gpw_main 1 4.0 0.001 0.001 185.182 185.182 mp2_ri_gpw_compute_in 1 5.0 0.380 0.380 136.739 136.739 mp2_ri_gpw_compute_in_loop 1 6.0 0.010 0.010 125.095 125.095 mp2_eri_3c_integrate_gpw 2656 7.0 0.013 0.013 94.034 94.034 integrate_v_rspace 2666 8.0 0.652 0.652 80.730 80.730 grid_integrate_task_list 2666 9.0 78.079 78.079 78.079 78.079 mp2_ri_gpw_compute_en 1 5.0 0.087 0.087 48.421 48.421 mp2_ri_gpw_compute_en_RI_loop 1 6.0 9.866 9.866 46.563 46.563 mp2_ri_gpw_compute_en_expansio 2080 7.0 2.112 2.112 28.989 28.989 local_gemm 2080 8.0 26.877 26.877 26.877 26.877 dbcsr_multiply_generic 5322 8.0 0.195 0.195 21.642 21.642 ao_to_mo_and_store_B_mult_1 2656 7.0 0.010 0.010 21.622 21.622 pw_transfer 63872 10.6 1.044 1.044 12.002 12.002 calculate_wavefunction 2656 8.0 8.204 8.204 11.908 11.908 get_2c_integrals 1 6.0 0.000 0.000 11.262 11.262 multiply_cannon 5322 9.0 0.443 0.443 10.887 10.887 fft_wrap_pw1pw2 53228 11.4 0.114 0.114 10.745 10.745 compute_2c_integrals 1 7.0 0.006 0.006 10.440 10.440 compute_2c_integrals_loop_lm 1 8.0 0.007 0.007 10.416 10.416 mp2_eri_2c_integrate_gpw 1 9.0 3.529 3.529 10.409 10.409 multiply_cannon_loop 5322 10.0 0.113 0.113 9.467 9.467 ao_to_mo_and_store_B_E_Ex_1 2656 7.0 2.501 2.501 9.331 9.331 make_m2s 10644 9.0 0.062 0.062 8.506 8.506 make_images 10644 10.0 3.441 3.441 8.165 8.165 multiply_cannon_multrec 5322 11.0 7.960 7.960 7.997 7.997 fft_wrap_pw1pw2_20 21271 12.4 0.508 0.508 7.772 7.772 copy_dbcsr_to_fm 2679 8.0 0.028 0.028 7.339 7.339 fft3d_s 53229 13.4 6.569 6.569 6.602 6.602 mp2_ri_gpw_compute_en_ener 2080 7.0 5.832 5.832 5.832 5.832 dbcsr_complete_redistribute 2689 9.0 1.176 1.176 5.765 5.765 dbcsr_finalize 10708 9.5 0.176 0.176 5.156 5.156 dbcsr_merge_all 8011 10.3 3.335 3.335 4.519 4.519 scf_env_do_scf 1 3.0 0.000 0.000 4.255 4.255 scf_env_do_scf_inner_loop 10 4.0 0.001 0.001 4.254 4.254 potential_pw2rs 5322 10.0 0.145 0.145 3.969 3.969 ------------------------------------------------------------------------------- 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 0.008 0.022 34.096 34.107 qs_energies 1 2.0 0.000 0.000 33.966 33.966 mp2_main 1 3.0 0.000 0.001 31.985 31.985 mp2_gpw_main 1 4.0 0.001 0.001 31.876 31.876 mp2_ri_gpw_compute_in 1 5.0 0.051 0.053 16.799 17.182 mp2_ri_gpw_compute_in_loop 1 6.0 0.001 0.001 15.636 16.023 mp2_ri_gpw_compute_en 1 5.0 0.169 0.179 14.988 15.206 mp2_ri_gpw_compute_en_RI_loop 1 6.0 0.751 0.848 13.940 13.952 mp2_eri_3c_integrate_gpw 83 7.0 0.001 0.001 13.666 13.801 integrate_v_rspace 93 8.1 0.098 0.110 13.541 13.681 grid_integrate_task_list 93 9.1 13.247 13.388 13.247 13.388 mp2_ri_gpw_compute_en_expansio 65 7.0 0.093 0.111 10.496 10.661 local_gemm 65 8.0 10.403 10.550 10.403 10.550 mp2_ri_gpw_compute_en_comm 17 7.0 0.066 0.081 2.363 2.735 mp_sendrecv_dm3 1054 8.0 1.859 2.302 1.859 2.302 dbcsr_multiply_generic 176 8.0 0.007 0.008 1.692 1.966 ao_to_mo_and_store_B_mult_1 83 7.0 0.001 0.001 1.675 1.949 scf_env_do_scf 1 3.0 0.000 0.000 1.868 1.868 scf_env_do_scf_inner_loop 10 4.0 0.000 0.001 1.868 1.868 get_2c_integrals 1 6.0 0.000 0.000 1.086 1.115 multiply_cannon 176 9.0 0.015 0.016 1.008 1.107 multiply_cannon_loop 176 10.0 0.002 0.002 0.952 1.049 qs_scf_new_mos 10 5.0 0.000 0.000 0.923 0.931 eigensolver 11 5.8 0.001 0.001 0.902 0.903 multiply_cannon_multrec 246 11.0 0.825 0.882 0.830 0.889 compute_2c_integrals 1 7.0 0.002 0.004 0.815 0.833 make_m2s 352 9.0 0.003 0.003 0.649 0.819 make_images 352 10.0 0.050 0.052 0.637 0.807 compute_2c_integrals_loop_lm 1 8.0 0.002 0.004 0.722 0.747 mp2_eri_2c_integrate_gpw 1 9.0 0.197 0.203 0.720 0.746 pw_transfer 2120 10.5 0.043 0.045 0.731 0.743 cp_fm_diag_elpa 11 6.8 0.000 0.000 0.738 0.740 cp_fm_redistribute_end 11 7.8 0.276 0.731 0.290 0.733 cp_fm_diag_elpa_base 11 7.8 0.428 0.689 0.440 0.706 fft_wrap_pw1pw2 1768 11.4 0.004 0.004 0.675 0.684 ------------------------------------------------------------------------------- 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=59.429, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=78.079, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="local_gemm", label="local_gemm", y=26.877, 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=9.866, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="calculate_wavefunction", label="calculate_wavefunction", y=8.204, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=7.96, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="mp_sendrecv_dm3", label="mp_sendrecv_dm3", y=0.0, yerr=0.0 Plot: name="RI-MP2_ammonia_timings_32mpi", title="Timings of RI-MP2_ammonia with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="rest", label="rest", y=7.010999999999996, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.247, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="local_gemm", label="local_gemm", y=10.403, 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=0.751, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="calculate_wavefunction", label="calculate_wavefunction", y=0.0, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=0.825, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="mp_sendrecv_dm3", label="mp_sendrecv_dm3", y=1.859, 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 0.103 0.103 125.434 125.434 qs_energies 1 2.0 0.000 0.000 124.027 124.027 scf_env_do_scf 1 3.0 0.000 0.000 117.283 117.283 scf_env_do_scf_inner_loop 15 4.0 0.002 0.002 117.283 117.283 qs_ks_update_qs_env 15 5.0 0.000 0.000 49.450 49.450 rebuild_ks_matrix 15 6.0 0.000 0.000 49.242 49.242 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.002 49.242 49.242 qs_scf_new_mos 15 5.0 0.000 0.000 42.691 42.691 eigensolver 15 6.0 0.001 0.001 34.720 34.720 qs_vxc_create 15 8.0 0.028 0.028 33.900 33.900 calculate_dispersion_nonloc 15 9.0 6.801 6.801 29.506 29.506 pw_transfer 1191 10.0 0.060 0.060 23.268 23.268 fft_wrap_pw1pw2 1086 11.0 0.008 0.008 23.093 23.093 qs_rho_update_rho_low 16 5.0 0.000 0.000 22.206 22.206 calculate_rho_elec 16 6.0 0.214 0.214 22.206 22.206 cp_fm_diag_elpa 15 7.0 0.000 0.000 22.177 22.177 cp_fm_diag_elpa_base 15 8.0 19.686 19.686 22.176 22.176 grid_collocate_task_list 16 7.0 20.832 20.832 20.832 20.832 fft_wrap_pw1pw2_150 765 12.0 3.611 3.611 16.737 16.737 sum_up_and_integrate 15 8.0 0.121 0.121 14.091 14.091 integrate_v_rspace 15 9.0 0.019 0.019 13.970 13.970 grid_integrate_task_list 15 10.0 13.439 13.439 13.439 13.439 cp_fm_cholesky_restore 45 7.0 10.267 10.267 10.267 10.267 fft3d_s 1087 13.0 10.066 10.066 10.074 10.074 pw_scatter_s 585 13.1 7.464 7.464 7.464 7.464 fft_wrap_pw1pw2_200 197 12.3 0.810 0.810 6.169 6.169 dbcsr_complete_redistribute 46 8.3 2.244 2.244 5.682 5.682 copy_dbcsr_to_fm 16 5.9 0.001 0.001 5.664 5.664 cp_fm_upper_to_full 30 8.0 4.765 4.765 4.765 4.765 vdW_energy 15 10.0 4.438 4.438 4.438 4.438 xc_vxc_pw_create 15 9.0 0.223 0.223 4.367 4.367 gspace_mixing 14 5.0 0.170 0.170 4.165 4.165 broyden_mixing 14 6.0 3.510 3.510 3.510 3.510 init_scf_run 1 3.0 0.000 0.000 3.167 3.167 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 3.066 3.066 xc_pw_derive 90 11.0 0.001 0.001 2.884 2.884 calculate_dm_sparse 15 6.0 0.016 0.016 2.660 2.660 cp_dbcsr_plus_fm_fm_t_native 15 7.0 0.000 0.000 2.584 2.584 ------------------------------------------------------------------------------- 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 0.033 65.210 65.221 qs_energies 1 2.0 0.000 0.000 64.940 64.945 scf_env_do_scf 1 3.0 0.000 0.000 60.788 60.789 scf_env_do_scf_inner_loop 15 4.0 0.001 0.003 60.788 60.789 qs_ks_update_qs_env 15 5.0 0.000 0.000 24.910 24.981 rebuild_ks_matrix 15 6.0 0.000 0.000 24.876 24.948 qs_ks_build_kohn_sham_matrix 15 7.0 0.003 0.005 24.876 24.948 qs_rho_update_rho_low 16 5.0 0.000 0.000 22.572 22.576 calculate_rho_elec 16 6.0 0.007 0.007 22.572 22.576 grid_collocate_task_list 16 7.0 19.602 20.194 19.602 20.194 sum_up_and_integrate 15 8.0 0.011 0.017 15.621 15.717 integrate_v_rspace 15 9.0 0.000 0.001 15.610 15.708 qs_scf_new_mos 15 5.0 0.000 0.000 14.009 14.311 grid_integrate_task_list 15 10.0 13.198 14.050 13.198 14.050 eigensolver 15 6.0 0.001 0.002 12.949 12.979 cp_fm_diag_elpa 15 7.0 0.000 0.000 9.141 9.145 cp_fm_diag_elpa_base 15 8.0 8.989 9.015 9.134 9.134 qs_vxc_create 15 8.0 0.001 0.001 8.972 8.986 calculate_dispersion_nonloc 15 9.0 0.908 0.943 7.207 7.224 pw_transfer 1191 10.0 0.087 0.096 6.642 6.683 fft_wrap_pw1pw2 1086 11.0 0.012 0.013 6.470 6.511 fft3d_ps 1086 13.0 2.394 2.595 4.825 5.003 fft_wrap_pw1pw2_150 765 12.0 0.270 0.312 4.138 4.174 cp_fm_cholesky_restore 45 7.0 3.660 3.700 3.660 3.700 density_rs2pw 16 7.0 0.001 0.001 2.851 3.197 rs_pw_transfer 158 9.4 0.001 0.002 2.852 3.178 mp_waitany 520 11.3 2.112 2.766 2.112 2.766 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 2.432 2.432 mp_alltoall_d11v 217 9.2 2.120 2.411 2.120 2.411 rs_pw_transfer_RS2PW_200 18 8.8 0.029 0.032 1.505 2.346 build_core_hamiltonian_matrix 1 4.0 0.000 0.000 2.140 2.335 mp_alltoall_z22v 1086 15.0 1.842 2.332 1.842 2.332 fft_wrap_pw1pw2_200 197 12.3 0.179 0.206 2.210 2.256 rs_gather_matrices 15 10.0 0.021 0.024 1.928 2.226 xc_vxc_pw_create 15 9.0 0.015 0.019 1.765 1.789 init_scf_run 1 3.0 0.000 0.001 1.496 1.496 x_to_yz 585 14.1 0.335 0.357 1.223 1.455 scf_env_initial_rho_setup 1 4.0 0.000 0.000 1.410 1.411 yz_to_x 501 13.9 0.230 0.295 1.184 1.393 build_core_ppnl 1 5.0 1.251 1.373 1.251 1.373 vdW_energy 15 10.0 1.296 1.351 1.296 1.351 ------------------------------------------------------------------------------- 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=51.14399999999999, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=20.832, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=19.686, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.439, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=10.267, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="fft3d_s", label="fft3d_s", y=10.066, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="fft3d_ps", label="fft3d_ps", y=0.0, yerr=0.0 Plot: name="diag_cu144_broy_timings_32mpi", title="Timings of diag_cu144_broy with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="rest", label="rest", y=17.366999999999997, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=19.602, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=8.989, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.198, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=3.66, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="fft3d_s", label="fft3d_s", y=0.0, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=2.394, 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 0.074 0.074 341.108 341.108 qs_energies 1 2.0 0.000 0.000 340.971 340.971 ls_scf 1 3.0 0.000 0.000 339.780 339.780 ls_scf_main 1 4.0 0.002 0.002 330.887 330.887 density_matrix_trs4 11 5.0 0.012 0.012 240.018 240.018 arnoldi_extremal 12 6.1 0.000 0.000 156.710 156.710 arnoldi_normal_ev 12 7.1 0.014 0.014 156.710 156.710 dbcsr_matrix_vector_mult 652 9.0 0.169 0.169 154.114 154.114 build_subspace 23 8.1 0.077 0.077 153.776 153.776 dbcsr_matrix_vector_mult_local 652 10.0 152.498 152.498 152.508 152.508 ls_scf_dm_to_ks 11 5.0 0.000 0.000 85.422 85.422 matrix_ls_to_qs 11 6.0 0.000 0.000 82.141 82.141 dbcsr_multiply_generic 185 6.1 0.856 0.856 72.249 72.249 dbcsr_copy_into_existing 11 7.0 44.865 44.865 44.865 44.865 multiply_cannon 185 7.1 0.272 0.272 43.838 43.838 dbcsr_complete_redistribute 23 7.5 30.100 30.100 41.208 41.208 matrix_decluster 11 7.0 0.000 0.000 37.275 37.275 multiply_cannon_loop 185 8.1 0.219 0.219 31.555 31.555 make_m2s 370 7.1 0.038 0.038 24.075 24.075 make_images 370 8.1 10.379 10.379 22.537 22.537 multiply_cannon_multrec 185 9.1 22.146 22.146 22.171 22.171 dbcsr_finalize 646 7.5 0.190 0.190 14.376 14.376 dbcsr_merge_all 597 8.5 2.113 2.113 13.288 13.288 setup_rec_index_2d 370 8.1 11.925 11.925 11.925 11.925 dbcsr_sort_indices 1103 9.9 10.001 10.001 10.001 10.001 tree_to_linear_d 110 9.4 9.919 9.919 9.919 9.919 calculate_norms 370 9.1 9.164 9.164 9.164 9.164 quick_finalize 395 10.0 0.349 0.349 8.660 8.660 ls_scf_init_scf 1 4.0 0.000 0.000 8.226 8.226 dbcsr_special_finalize 370 9.1 0.002 0.002 8.007 8.007 ls_scf_init_matrix_S 1 5.0 0.000 0.000 7.887 7.887 matrix_sqrt_Newton_Schulz 1 6.0 0.001 0.001 7.233 7.233 ------------------------------------------------------------------------------- From /workspace/artifacts/bench_dftb_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.009 0.024 66.526 66.536 qs_energies 1 2.0 0.000 0.000 66.433 66.433 ls_scf 1 3.0 0.000 0.000 66.382 66.382 ls_scf_main 1 4.0 0.001 0.009 63.858 63.858 density_matrix_trs4 11 5.0 0.006 0.020 61.315 61.381 dbcsr_multiply_generic 185 6.1 0.058 0.069 57.722 57.975 multiply_cannon 185 7.1 0.033 0.037 48.107 48.498 multiply_cannon_loop 185 8.1 0.113 0.130 45.686 46.351 multiply_cannon_multrec 1480 9.1 28.065 30.404 28.336 30.685 mp_waitall_1 11936 10.3 15.076 18.619 15.076 18.619 multiply_cannon_metrocomm3 1480 9.1 0.013 0.016 8.816 12.777 make_m2s 370 7.1 0.034 0.037 6.714 6.790 make_images 370 8.1 0.630 0.669 6.585 6.661 calculate_norms 2960 9.1 4.820 5.720 4.820 5.720 multiply_cannon_metrocomm1 1480 9.1 0.008 0.009 3.544 5.464 make_images_data 370 9.1 0.009 0.010 2.947 3.225 hybrid_alltoall_any 393 9.9 0.179 0.890 2.551 2.877 mp_sum_l 1119 5.6 1.852 2.862 1.852 2.862 arnoldi_extremal 12 6.1 0.000 0.000 2.678 2.703 arnoldi_normal_ev 12 7.1 0.001 0.004 2.677 2.703 build_subspace 23 8.1 0.019 0.025 2.573 2.575 ls_scf_dm_to_ks 11 5.0 0.000 0.000 2.180 2.273 dbcsr_matrix_vector_mult 652 9.0 0.009 0.043 2.094 2.179 dbcsr_complete_redistribute 23 7.5 1.192 1.266 1.937 2.049 matrix_ls_to_qs 11 6.0 0.000 0.000 1.869 1.990 ls_scf_init_scf 1 4.0 0.000 0.000 1.950 1.951 ls_scf_init_matrix_S 1 5.0 0.000 0.000 1.923 1.932 matrix_decluster 11 7.0 0.000 0.000 1.727 1.842 make_images_pack 370 9.1 1.666 1.798 1.669 1.802 dbcsr_matrix_vector_mult_local 652 10.0 1.691 1.791 1.693 1.793 dbcsr_multiply_generic_mpsum_f 137 7.1 0.000 0.000 0.949 1.766 matrix_sqrt_Newton_Schulz 1 6.0 0.000 0.002 1.753 1.756 dbcsr_finalize 646 7.5 0.007 0.008 1.369 1.545 buffer_matrices_ensure_size 370 8.1 1.294 1.450 1.294 1.450 ------------------------------------------------------------------------------- Plot: name="bench_dftb_timings_32omp", title="Timings of bench_dftb with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="bench_dftb_timings_32omp", name="rest", label="rest", y=70.41000000000003, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=152.498, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_copy_into_existing", label="dbcsr_copy_into_existing", y=44.865, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_complete_redistribute", label="dbcsr_complete_redistribute", y=30.1, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=22.146, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="setup_rec_index_2d", label="setup_rec_index_2d", y=11.925, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="calculate_norms", label="calculate_norms", y=9.164, 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=13.829999999999998, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=1.691, 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=1.192, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=28.065, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="setup_rec_index_2d", label="setup_rec_index_2d", y=0.0, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="calculate_norms", label="calculate_norms", y=4.82, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=15.076, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=1.852, yerr=0.0 Running dbcsr.inp with 1 threads and 32 ranks... done. Running dbcsr.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/dbcsr_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.007 0.007 69.522 69.522 lib_test 1 2.0 0.000 0.000 69.514 69.514 dbcsr_run_tests 3 3.0 0.002 0.002 69.514 69.514 test_multiplies_multiproc 3 4.0 0.001 0.001 53.952 53.952 dbcsr_redistribute 9 5.0 35.445 35.445 37.016 37.016 dbcsr_multiply_generic 9 5.0 0.001 0.001 15.614 15.614 dbcsr_make_random_matrix 9 4.0 12.534 12.534 15.455 15.455 multiply_cannon 9 6.0 0.001 0.001 11.027 11.027 multiply_cannon_loop 9 7.0 0.002 0.002 10.673 10.673 multiply_cannon_multrec 9 8.0 10.670 10.670 10.671 10.671 dbcsr_finalize 27 5.7 0.017 0.017 5.390 5.390 dbcsr_merge_all 18 6.5 1.952 1.952 4.660 4.660 dbcsr_data_release 975 7.6 2.769 2.769 2.769 2.769 tree_to_linear_d 9 7.0 1.851 1.851 1.851 1.851 make_m2s 18 6.0 0.001 0.001 1.569 1.569 make_images 18 7.0 0.539 0.539 1.523 1.523 ------------------------------------------------------------------------------- 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 0.015 17.340 17.345 lib_test 1 2.0 0.000 0.000 17.301 17.319 dbcsr_run_tests 3 3.0 0.000 0.001 17.300 17.318 test_multiplies_multiproc 3 4.0 0.000 0.002 16.465 16.500 dbcsr_multiply_generic 9 5.0 0.001 0.001 15.152 15.249 multiply_cannon 9 6.0 0.001 0.002 13.419 13.722 multiply_cannon_loop 9 7.0 0.002 0.002 13.136 13.463 multiply_cannon_multrec 72 8.0 10.952 11.267 10.952 11.268 mp_waitall_1 576 9.2 2.495 2.981 2.495 2.981 multiply_cannon_metrocomm1 72 8.0 0.001 0.001 1.944 2.502 dbcsr_data_release 444 7.6 0.783 0.913 0.783 0.913 mp_sum_l 390 2.5 0.385 0.827 0.385 0.827 dbcsr_make_random_matrix 9 4.0 0.661 0.668 0.804 0.825 dbcsr_multiply_generic_mpsum_f 9 6.0 0.000 0.000 0.382 0.824 dbcsr_finalize 27 5.7 0.000 0.000 0.719 0.818 dbcsr_destroy 111 5.9 0.000 0.001 0.619 0.759 multiply_cannon_metrocomm3 72 8.0 0.000 0.000 0.232 0.755 make_m2s 18 6.0 0.001 0.001 0.659 0.692 make_images 18 7.0 0.021 0.021 0.656 0.689 dbcsr_merge_all 18 6.5 0.103 0.124 0.554 0.642 dbcsr_redistribute 9 5.0 0.234 0.280 0.391 0.417 dbcsr_data_copy_aa2 18 7.5 0.333 0.408 0.333 0.408 make_images_data 18 8.0 0.000 0.001 0.352 0.406 hybrid_alltoall_any 18 9.0 0.029 0.124 0.308 0.356 ------------------------------------------------------------------------------- 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=6.152000000000008, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_redistribute", label="dbcsr_redistribute", y=35.445, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=12.534, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=10.67, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_data_release", label="dbcsr_data_release", y=2.769, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_merge_all", label="dbcsr_merge_all", y=1.952, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="mp_sum_l", label="mp_sum_l", y=0.0, yerr=0.0 Plot: name="dbcsr_timings_32mpi", title="Timings of dbcsr with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="dbcsr_timings_32mpi", name="rest", label="rest", y=1.727000000000002, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_redistribute", label="dbcsr_redistribute", y=0.234, 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=10.952, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_data_release", label="dbcsr_data_release", y=0.783, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_merge_all", label="dbcsr_merge_all", y=0.103, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=2.495, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=0.385, 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 0.050 0.050 132.901 132.901 qs_mol_dyn_low 1 2.0 0.003 0.003 131.524 131.524 velocity_verlet 5 3.0 0.003 0.003 107.546 107.546 qmmm_el_coupling 6 3.8 0.000 0.000 89.241 89.241 qmmm_elec_with_gaussian 6 4.8 0.012 0.012 89.237 89.237 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 88.603 88.603 qmmm_elec_gaussian_low_G 6 6.8 87.710 87.710 87.710 87.710 qs_forces 6 3.8 0.000 0.000 33.864 33.864 qs_energies 6 4.8 0.000 0.000 30.017 30.017 scf_env_do_scf 6 5.8 0.001 0.001 27.799 27.799 scf_env_do_scf_inner_loop 39 6.8 0.004 0.004 24.272 24.272 rebuild_ks_matrix 45 8.4 0.000 0.000 23.296 23.296 qs_ks_build_kohn_sham_matrix 45 9.4 0.005 0.005 23.296 23.296 qs_ks_update_qs_env 45 7.8 0.000 0.000 19.866 19.866 pw_transfer 966 12.3 0.051 0.051 16.824 16.824 fft_wrap_pw1pw2 801 13.6 0.006 0.006 16.627 16.627 fft_wrap_pw1pw2_150 507 15.2 2.179 2.179 16.212 16.212 qs_vxc_create 45 10.4 0.001 0.001 12.837 12.837 xc_vxc_pw_create 45 11.4 0.648 0.648 12.836 12.836 xc_pw_derive 270 13.4 0.002 0.002 9.072 9.072 fft3d_s 802 15.6 7.678 7.678 7.686 7.686 qs_rho_update_rho_low 45 7.9 0.000 0.000 7.048 7.048 calculate_rho_elec 45 8.9 0.562 0.562 7.048 7.048 xc_rho_set_and_dset_create 45 12.4 0.557 0.557 6.533 6.533 xc_pw_divergence 45 12.4 0.001 0.001 5.605 5.605 pw_scatter_s 429 15.8 5.522 5.522 5.522 5.522 qmmm_forces 6 3.8 0.002 0.002 5.320 5.320 qmmm_forces_with_gaussian 6 4.8 0.017 0.017 4.983 4.983 pw_integral_ab 2539 7.4 4.407 4.407 4.407 4.407 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 4.262 4.262 qs_ks_ddapc 45 10.4 0.001 0.001 4.084 4.084 qmmm_forces_gaussian_low_G 6 6.8 3.577 3.577 3.577 3.577 init_scf_loop 6 6.8 0.000 0.000 3.522 3.522 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 3.438 3.438 sum_up_and_integrate 45 10.4 0.325 0.325 3.321 3.321 density_rs2pw 45 9.9 0.002 0.002 3.253 3.253 grid_collocate_task_list 45 9.9 3.232 3.232 3.232 3.232 integrate_v_rspace 45 11.4 0.006 0.006 2.995 2.995 ------------------------------------------------------------------------------- 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 0.037 0.057 52.490 52.504 qs_mol_dyn_low 1 2.0 0.003 0.004 51.502 51.561 qs_forces 6 3.8 0.000 0.001 37.292 37.292 qs_energies 6 4.8 0.000 0.000 35.568 35.568 scf_env_do_scf 6 5.8 0.000 0.001 34.679 34.679 scf_env_do_scf_inner_loop 113 6.2 0.003 0.018 33.278 33.279 rebuild_ks_matrix 119 8.1 0.000 0.000 24.468 24.476 qs_ks_build_kohn_sham_matrix 119 9.1 0.015 0.016 24.467 24.476 qs_ks_update_qs_env 119 7.3 0.001 0.001 23.037 23.046 velocity_verlet 5 3.0 0.002 0.004 21.853 21.856 pw_transfer 2446 12.3 0.199 0.217 16.229 16.695 fft_wrap_pw1pw2 2059 13.4 0.024 0.027 15.792 16.288 fft_wrap_pw1pw2_150 1321 14.9 1.227 1.357 15.233 15.690 qs_vxc_create 119 10.1 0.002 0.003 12.812 12.815 xc_vxc_pw_create 119 11.1 0.146 0.208 12.810 12.813 fft3d_ps 2059 15.4 6.737 7.329 11.750 12.508 qs_rho_update_rho_low 119 7.3 0.000 0.000 10.018 10.020 calculate_rho_elec 119 8.3 0.048 0.055 10.017 10.020 xc_pw_derive 714 13.1 0.010 0.012 9.610 9.867 sum_up_and_integrate 119 10.1 0.080 0.090 8.506 8.535 integrate_v_rspace 119 11.1 0.003 0.003 8.426 8.460 qmmm_forces 6 3.8 0.002 0.002 7.181 7.182 qmmm_forces_with_gaussian 6 4.8 0.007 0.010 6.910 7.058 xc_pw_divergence 119 12.1 0.005 0.005 6.233 6.454 xc_rho_set_and_dset_create 119 12.1 0.354 0.427 6.247 6.397 qmmm_el_coupling 6 3.8 0.000 0.000 6.202 6.275 qmmm_elec_with_gaussian 6 4.8 0.003 0.003 6.201 6.274 rs_pw_transfer 988 11.5 0.010 0.013 5.869 6.088 density_rs2pw 119 9.3 0.005 0.007 5.569 5.808 potential_pw2rs 119 12.1 0.006 0.006 4.836 4.845 grid_collocate_task_list 119 9.3 4.311 4.541 4.311 4.541 mp_alltoall_z22v 2059 17.4 3.598 4.152 3.598 4.152 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 3.822 3.857 grid_integrate_task_list 119 12.1 3.344 3.527 3.344 3.527 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 3.401 3.474 qmmm_forces_gaussian_low_G 6 6.8 3.144 3.177 3.144 3.177 x_to_yz 1095 16.8 0.816 0.913 2.690 2.906 qmmm_elec_gaussian_low_G 6 6.8 2.812 2.878 2.812 2.878 pw_restrict_s3 18 5.8 1.334 1.381 2.479 2.596 yz_to_x 964 16.0 0.540 0.651 2.265 2.589 mp_waitany 4028 12.8 2.107 2.389 2.107 2.389 rs_pw_transfer_PW2RS_150 125 13.9 0.724 0.773 2.193 2.220 qmmm_elec_with_gaussian:spline 6 5.8 0.000 0.000 2.128 2.199 pw_prolongate_s3 18 6.8 1.136 1.161 2.128 2.199 qs_scf_new_mos 113 7.2 0.000 0.000 1.938 1.944 qs_scf_loop_do_ot 113 8.2 0.000 0.000 1.938 1.944 rs_pw_transfer_RS2PW_150 125 11.2 0.579 0.665 1.722 1.930 qs_ks_ddapc 119 10.1 0.002 0.002 1.816 1.882 ot_scf_mini 113 9.2 0.001 0.001 1.854 1.858 dbcsr_multiply_generic 2588 12.3 0.056 0.058 1.797 1.852 mp_waitall_1 188862 16.2 1.699 1.768 1.699 1.768 pw_gather_p 964 15.0 1.242 1.626 1.242 1.626 pw_integral_ab 2761 7.7 1.230 1.285 1.447 1.562 pw_scatter_p 1095 15.8 1.520 1.547 1.520 1.547 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 1.453 1.454 init_scf_loop 6 6.8 0.000 0.000 1.399 1.399 mp_sum_dm3 33 5.7 1.170 1.203 1.170 1.203 ot_mini 113 10.2 0.000 0.000 1.136 1.141 ------------------------------------------------------------------------------- Plot: name="MQAE_single_node_timings_32omp", title="Timings of MQAE_single_node with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="MQAE_single_node_timings_32omp", name="rest", label="rest", y=20.77500000000002, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=87.71, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_s", label="fft3d_s", y=7.678, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_scatter_s", label="pw_scatter_s", y=5.522, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_integral_ab", label="pw_integral_ab", y=4.407, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.577, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=3.232, 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="grid_integrate_task_list", label="grid_integrate_task_list", y=0.0, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=0.0, yerr=0.0 Plot: name="MQAE_single_node_timings_32mpi", title="Timings of MQAE_single_node with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="MQAE_single_node_timings_32mpi", name="rest", label="rest", y=27.314, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=2.812, 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=1.23, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.144, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=4.311, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=6.737, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=3.344, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=3.598, yerr=0.0 Summary: Performance test took 34 minutes. Status: OK Removing intermediate container c984f9ce84dc ---> fcf80d080697 Step 41/42 : CMD cat $(find ./report.log -mmin +10) | sed '/^Summary:/ s/$/ (cached)/' ---> Running in 435140c60977 Removing intermediate container 435140c60977 ---> 003b11775bc5 Step 42/42 : ENTRYPOINT [] ---> Running in 58779d5ed61d Removing intermediate container 58779d5ed61d ---> 1293584b6b6b [Warning] One or more build-args [GIT_COMMIT_SHA] were not consumed Successfully built 1293584b6b6b Successfully tagged us-central1-docker.pkg.dev/cp2k-org-project/cp2kci/img_cp2k-perf-openmp:master Pushing new image... done. #################### Running Image cp2k-perf-openmp #################### Uploading artifacts... done EndDate: 2022-12-12 19:56:59+00:00