StartDate: 2023-03-21 11:38:06+00:00 CpuId: 32x AMD EPYC (3rd Gen) (Milan) [Zen 3], 7nm (SMT disabled) CommitSHA: 7f090fb11291b829076ec7a97d9530b1aff7c614 CommitTime: 2023-03-21 06:08:07 +0100 CommitAuthor: Matthias Krack CommitSubject: Update arch file Populating docker build cache... done. #################### Building Image cp2k-perf-openmp #################### Dockerfile: /tools/docker/Dockerfile.test_performance Build-Path: / Build-Args: GIT_COMMIT_SHA=7f090fb11291b829076ec7a97d9530b1aff7c614 DEPRECATED: The legacy builder is deprecated and will be removed in a future release. BuildKit is currently disabled; enable it by removing the DOCKER_BUILDKIT=0 environment-variable. Sending build context to Docker daemon 367.7MB Step 1/42 : FROM ubuntu:22.04 22.04: Pulling from library/ubuntu 2ab09b027e7f: Pulling fs layer 2ab09b027e7f: Download complete 2ab09b027e7f: Pull complete Digest: sha256:67211c14fa74f070d27cc59d69a7fa9aeff8e28ea118ef3babc295a0428a6d21 Status: Downloaded newer image for ubuntu:22.04 ---> 08d22c0ceb15 Step 2/42 : WORKDIR /opt/cp2k-toolchain ---> Using cache ---> 47a3542ef7e0 Step 3/42 : COPY ./tools/toolchain/install_requirements*.sh ./ ---> Using cache ---> e86e12710088 Step 4/42 : RUN ./install_requirements.sh ubuntu:22.04 ---> Using cache ---> 5ad7a46db6e4 Step 5/42 : RUN mkdir scripts ---> Using cache ---> 2ed50184e1de 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 ---> 2cfaec0caa31 Step 7/42 : COPY ./tools/toolchain/install_cp2k_toolchain.sh . ---> Using cache ---> e3c7243c9e7e Step 8/42 : RUN ./install_cp2k_toolchain.sh --install-all --with-gcc=system --dry-run ---> Using cache ---> f053587e71f2 Step 9/42 : COPY ./tools/toolchain/scripts/stage0/ ./scripts/stage0/ ---> Using cache ---> 27b6a69300c0 Step 10/42 : RUN ./scripts/stage0/install_stage0.sh && rm -rf ./build ---> Using cache ---> af05dc2abbcf Step 11/42 : COPY ./tools/toolchain/scripts/stage1/ ./scripts/stage1/ ---> Using cache ---> 72a9160365c6 Step 12/42 : RUN ./scripts/stage1/install_stage1.sh && rm -rf ./build ---> Using cache ---> 08767ccb9543 Step 13/42 : COPY ./tools/toolchain/scripts/stage2/ ./scripts/stage2/ ---> Using cache ---> c93c73c59c7d Step 14/42 : RUN ./scripts/stage2/install_stage2.sh && rm -rf ./build ---> Using cache ---> 46507f029160 Step 15/42 : COPY ./tools/toolchain/scripts/stage3/ ./scripts/stage3/ ---> Using cache ---> a3d4507934f4 Step 16/42 : RUN ./scripts/stage3/install_stage3.sh && rm -rf ./build ---> Using cache ---> 685c0a7bb753 Step 17/42 : COPY ./tools/toolchain/scripts/stage4/ ./scripts/stage4/ ---> Using cache ---> b6060b066447 Step 18/42 : RUN ./scripts/stage4/install_stage4.sh && rm -rf ./build ---> Using cache ---> 8aaf7d16b2e3 Step 19/42 : COPY ./tools/toolchain/scripts/stage5/ ./scripts/stage5/ ---> Using cache ---> 828b2697b61f Step 20/42 : RUN ./scripts/stage5/install_stage5.sh && rm -rf ./build ---> Using cache ---> 2f8752bf29da Step 21/42 : COPY ./tools/toolchain/scripts/stage6/ ./scripts/stage6/ ---> Using cache ---> cdd2991d30c3 Step 22/42 : RUN ./scripts/stage6/install_stage6.sh && rm -rf ./build ---> Using cache ---> de789914448a Step 23/42 : COPY ./tools/toolchain/scripts/stage7/ ./scripts/stage7/ ---> Using cache ---> e37c62bdb039 Step 24/42 : RUN ./scripts/stage7/install_stage7.sh && rm -rf ./build ---> Using cache ---> ac27a8f6f3ff Step 25/42 : COPY ./tools/toolchain/scripts/stage8/ ./scripts/stage8/ ---> Using cache ---> db4b485d3d1b Step 26/42 : RUN ./scripts/stage8/install_stage8.sh && rm -rf ./build ---> Using cache ---> a546f9c7d269 Step 27/42 : COPY ./tools/toolchain/scripts/arch_base.tmpl ./tools/toolchain/scripts/generate_arch_files.sh ./scripts/ ---> Using cache ---> dde9c44acf01 Step 28/42 : RUN ./scripts/generate_arch_files.sh && rm -rf ./build ---> Using cache ---> 33280a6a3dee Step 29/42 : WORKDIR /opt/cp2k ---> Using cache ---> 3d9a8a65d6c7 Step 30/42 : COPY ./Makefile . ---> Using cache ---> 10c6007874ff Step 31/42 : COPY ./src ./src ---> Using cache ---> 6a2e76326b16 Step 32/42 : COPY ./exts ./exts ---> Using cache ---> 5ed952ad204f Step 33/42 : COPY ./tools/build_utils ./tools/build_utils ---> Using cache ---> 1a346e3ae462 Step 34/42 : RUN /bin/bash -c " mkdir -p arch && ln -vs /opt/cp2k-toolchain/install/arch/local.psmp ./arch/ && echo 'Compiling cp2k...' && source /opt/cp2k-toolchain/install/setup && ( make -j ARCH=local VERSION=psmp &> /dev/null || true ) && rm -rf lib obj && ( [ ! -f ./exe/local/cp2k.psmp ] || ldd ./exe/local/cp2k.psmp | grep -q libmpi )" ---> Running in 7efbde341483 './arch/local.psmp' -> '/opt/cp2k-toolchain/install/arch/local.psmp' Compiling cp2k... Removing intermediate container 7efbde341483 ---> fa6a5dc15db7 Step 35/42 : COPY ./data ./data ---> 1392f47cc3e4 Step 36/42 : COPY ./tests ./tests ---> cf6b964cb4f0 Step 37/42 : COPY ./tools/regtesting ./tools/regtesting ---> ad682059dba8 Step 38/42 : COPY ./benchmarks ./benchmarks ---> 3b0e52aebc2c Step 39/42 : COPY ./tools/docker/scripts/test_performance.sh ./tools/docker/scripts/plot_performance.py ./ ---> 2582acb50762 Step 40/42 : RUN ./test_performance.sh "local" 2>&1 | tee report.log ---> Running in 9e3730199841 ========== Compiling CP2K ========== Compiling cp2k... done. Checking benchmark inputs... Found 70 input files and 0 errors. ========== Running Performance Test ========== Running H2O-64.inp with 1 threads and 32 ranks... done. Running H2O-64.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/H2O-64_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.034 0.034 87.424 87.424 qs_mol_dyn_low 1 2.0 0.003 0.003 86.776 86.776 qs_forces 11 3.9 0.001 0.001 86.736 86.736 qs_energies 11 4.9 0.001 0.001 80.613 80.613 scf_env_do_scf 11 5.9 0.001 0.001 70.027 70.027 velocity_verlet 10 3.0 0.002 0.002 56.554 56.554 scf_env_do_scf_inner_loop 108 6.5 0.011 0.011 53.757 53.757 rebuild_ks_matrix 119 8.3 0.001 0.001 20.208 20.208 qs_ks_build_kohn_sham_matrix 119 9.3 0.012 0.012 20.207 20.207 qs_rho_update_rho_low 119 7.7 0.001 0.001 19.674 19.674 calculate_rho_elec 119 8.7 0.951 0.951 19.673 19.673 dbcsr_multiply_generic 2286 12.5 0.157 0.157 19.381 19.381 qs_scf_new_mos 108 7.5 0.001 0.001 19.303 19.303 qs_scf_loop_do_ot 108 8.5 0.001 0.001 19.303 19.303 qs_ks_update_qs_env 119 7.6 0.001 0.001 18.483 18.483 ot_scf_mini 108 9.5 0.002 0.002 17.962 17.962 init_scf_loop 11 6.9 0.000 0.000 16.144 16.144 grid_collocate_task_list 119 9.7 15.003 15.003 15.003 15.003 prepare_preconditioner 11 7.9 0.000 0.000 13.750 13.750 make_preconditioner 11 8.9 0.000 0.000 13.749 13.749 sum_up_and_integrate 119 10.3 0.776 0.776 13.236 13.236 make_full_inverse_cholesky 11 9.9 0.000 0.000 12.641 12.641 integrate_v_rspace 119 11.3 0.087 0.087 12.460 12.460 ot_mini 108 10.5 0.001 0.001 11.592 11.592 grid_integrate_task_list 119 12.3 10.542 10.542 10.542 10.542 make_m2s 4572 13.5 0.045 0.045 10.513 10.513 qs_ot_get_derivative 108 11.5 0.001 0.001 6.164 6.164 pw_transfer 1439 11.6 0.067 0.067 6.133 6.133 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 6.096 6.096 fft_wrap_pw1pw2 1201 12.6 0.007 0.007 5.935 5.935 dbcsr_make_dense_low 5837 15.5 0.069 0.069 5.681 5.681 make_dense_data 5837 16.5 5.029 5.029 5.598 5.598 ot_diis_step 108 11.5 0.004 0.004 5.425 5.425 make_images 4572 14.5 2.119 2.119 5.260 5.260 multiply_cannon 2286 13.5 0.177 0.177 5.033 5.033 dbcsr_make_images_dense 3978 14.8 0.016 0.016 4.966 4.966 fft_wrap_pw1pw2_140 487 13.2 0.438 0.438 4.946 4.946 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 4.901 4.901 apply_single 119 13.6 0.000 0.000 4.901 4.901 multiply_cannon_loop 2286 14.5 0.056 0.056 4.570 4.570 multiply_cannon_multrec 2286 15.5 4.461 4.461 4.513 4.513 cp_fm_cholesky_decompose 22 10.9 4.422 4.422 4.422 4.422 cp_fm_cholesky_invert 11 10.9 4.168 4.168 4.168 4.168 init_scf_run 11 5.9 0.002 0.002 3.880 3.880 scf_env_initial_rho_setup 11 6.9 0.001 0.001 3.878 3.878 dbcsr_complete_redistribute 329 12.2 1.910 1.910 3.725 3.725 density_rs2pw 119 9.7 0.005 0.005 3.719 3.719 dbcsr_copy 2102 12.0 0.209 0.209 3.530 3.530 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 3.448 3.448 wfi_extrapolate 11 7.9 0.001 0.001 3.355 3.355 dbcsr_copy_into_existing 22 7.9 3.286 3.286 3.286 3.286 qs_env_update_s_mstruct 11 6.9 0.000 0.000 3.216 3.216 copy_dbcsr_to_fm 153 11.3 0.002 0.002 3.003 3.003 qs_ot_get_p 119 10.4 0.001 0.001 2.966 2.966 fft3d_s 1202 14.6 2.954 2.954 2.958 2.958 qs_create_task_list 11 7.9 0.000 0.000 2.865 2.865 generate_qs_task_list 11 8.9 1.955 1.955 2.865 2.865 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 2.672 2.672 build_core_hamiltonian_matrix 11 6.9 0.000 0.000 2.462 2.462 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.326 2.326 dbcsr_data_release 279534 16.0 2.086 2.086 2.086 2.086 pw_poisson_solve 119 10.3 0.336 0.336 1.958 1.958 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 1.934 1.934 qs_ot_get_derivative_taylor 59 13.0 0.001 0.001 1.888 1.888 copy_fm_to_dbcsr 176 11.2 0.001 0.001 1.859 1.859 potential_pw2rs 119 12.3 0.047 0.047 1.832 1.832 dbcsr_finalize 5186 13.8 0.094 0.094 1.793 1.793 ------------------------------------------------------------------------------- From /workspace/artifacts/H2O-64_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.008 0.021 46.130 46.140 qs_mol_dyn_low 1 2.0 0.003 0.004 46.001 46.006 qs_forces 11 3.9 0.002 0.002 45.957 45.958 qs_energies 11 4.9 0.001 0.001 42.997 42.999 scf_env_do_scf 11 5.9 0.000 0.002 39.516 39.516 scf_env_do_scf_inner_loop 108 6.5 0.003 0.022 36.437 36.437 velocity_verlet 10 3.0 0.002 0.003 27.237 27.238 rebuild_ks_matrix 119 8.3 0.000 0.000 16.582 16.669 qs_ks_build_kohn_sham_matrix 119 9.3 0.017 0.019 16.582 16.669 qs_ks_update_qs_env 119 7.6 0.001 0.001 14.730 14.809 qs_rho_update_rho_low 119 7.7 0.001 0.001 13.946 13.951 calculate_rho_elec 119 8.7 0.031 0.032 13.945 13.950 dbcsr_multiply_generic 2286 12.5 0.074 0.076 13.291 13.445 sum_up_and_integrate 119 10.3 0.034 0.037 12.318 12.347 integrate_v_rspace 119 11.3 0.005 0.005 12.284 12.317 qs_scf_new_mos 108 7.5 0.001 0.001 10.493 10.561 qs_scf_loop_do_ot 108 8.5 0.001 0.001 10.492 10.560 multiply_cannon 2286 13.5 0.153 0.164 9.947 10.286 ot_scf_mini 108 9.5 0.002 0.002 9.830 9.893 multiply_cannon_loop 2286 14.5 0.095 0.102 9.420 9.767 grid_collocate_task_list 119 9.7 9.208 9.598 9.208 9.598 grid_integrate_task_list 119 12.3 8.210 8.470 8.210 8.470 mp_waitall_1 158411 16.6 7.587 7.966 7.587 7.966 ot_mini 108 10.5 0.001 0.001 5.713 5.780 multiply_cannon_metrocomm3 18288 15.5 0.037 0.039 5.451 5.777 rs_pw_transfer 974 11.9 0.011 0.012 4.545 4.953 density_rs2pw 119 9.7 0.006 0.006 4.146 4.526 pw_transfer 1439 11.6 0.104 0.110 4.046 4.107 fft_wrap_pw1pw2 1201 12.6 0.009 0.010 3.875 3.937 fft_wrap_pw1pw2_140 487 13.2 0.721 0.783 3.342 3.495 potential_pw2rs 119 12.3 0.006 0.006 3.354 3.367 multiply_cannon_multrec 18288 15.5 3.148 3.235 3.158 3.245 init_scf_loop 11 6.9 0.000 0.000 3.066 3.066 qs_ot_get_derivative 108 11.5 0.001 0.001 2.920 2.977 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 2.696 2.780 apply_single 119 13.6 0.000 0.000 2.696 2.780 ot_diis_step 108 11.5 0.003 0.004 2.773 2.773 init_scf_run 11 5.9 0.000 0.005 2.478 2.479 scf_env_initial_rho_setup 11 6.9 0.000 0.004 2.478 2.478 fft3d_ps 1201 14.6 1.315 1.394 2.367 2.471 make_m2s 4572 13.5 0.045 0.050 2.216 2.266 wfi_extrapolate 11 7.9 0.001 0.001 2.256 2.256 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 1.980 1.990 make_images 4572 14.5 0.116 0.118 1.892 1.947 mp_waitany 9880 13.7 1.384 1.848 1.384 1.848 rs_pw_transfer_RS2PW_140 130 11.5 0.183 0.205 1.070 1.479 qs_ot_get_p 119 10.4 0.001 0.001 1.217 1.307 prepare_preconditioner 11 7.9 0.000 0.000 1.268 1.283 make_preconditioner 11 8.9 0.000 0.000 1.268 1.283 rs_pw_transfer_PW2RS_140 130 13.9 0.367 0.388 1.182 1.203 mp_alltoall_d11v 2130 13.8 0.874 1.175 0.874 1.175 make_full_inverse_cholesky 11 9.9 0.000 0.000 1.162 1.175 make_images_data 4572 15.5 0.034 0.038 1.045 1.134 hybrid_alltoall_any 4725 16.4 0.060 0.174 0.921 1.007 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 0.955 1.007 multiply_cannon_metrocomm1 18288 15.5 0.019 0.020 0.512 0.974 rs_pw_transfer_RS2PW_50 119 11.7 0.260 0.283 0.906 0.961 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 0.876 0.953 rs_gather_matrices 119 12.3 0.101 0.113 0.660 0.929 qs_ot_get_derivative_taylor 59 13.0 0.001 0.001 0.897 0.923 ------------------------------------------------------------------------------- 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=47.967000000000006, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=15.003, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=10.542, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="make_dense_data", label="make_dense_data", y=5.029, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=4.461, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=4.422, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="mp_waitany", label="mp_waitany", y=0.0, yerr=0.0 Plot: name="H2O-64_timings_32mpi", title="Timings of H2O-64 with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="H2O-64_timings_32mpi", name="rest", label="rest", y=16.593000000000004, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=9.208, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=8.21, 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="multiply_cannon_multrec", label="multiply_cannon_multrec", y=3.148, 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="mp_waitall_1", label="mp_waitall_1", y=7.587, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitany", label="mp_waitany", y=1.384, yerr=0.0 Running H2O-64_nonortho.inp with 1 threads and 32 ranks... done. Running H2O-64_nonortho.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/H2O-64_nonortho_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.029 0.029 111.752 111.752 qs_mol_dyn_low 1 2.0 0.003 0.003 111.071 111.071 qs_forces 11 3.9 0.001 0.001 111.032 111.032 qs_energies 11 4.9 0.001 0.001 103.338 103.338 scf_env_do_scf 11 5.9 0.001 0.001 90.750 90.750 scf_env_do_scf_inner_loop 96 6.5 0.010 0.010 72.578 72.578 velocity_verlet 10 3.0 0.002 0.002 71.257 71.257 rebuild_ks_matrix 107 8.3 0.001 0.001 33.553 33.553 qs_ks_build_kohn_sham_matrix 107 9.3 0.011 0.011 33.553 33.553 qs_rho_update_rho_low 107 7.7 0.000 0.000 31.727 31.727 calculate_rho_elec 107 8.7 0.855 0.855 31.727 31.727 qs_ks_update_qs_env 107 7.6 0.001 0.001 30.216 30.216 grid_collocate_task_list 107 9.7 27.674 27.674 27.674 27.674 sum_up_and_integrate 107 10.3 0.709 0.709 27.082 27.082 integrate_v_rspace 107 11.3 0.099 0.099 26.373 26.373 grid_integrate_task_list 107 12.3 24.565 24.565 24.565 24.565 init_scf_loop 11 6.9 0.000 0.000 18.041 18.041 dbcsr_multiply_generic 1966 12.4 0.142 0.142 17.970 17.970 qs_scf_new_mos 96 7.5 0.001 0.001 17.487 17.487 qs_scf_loop_do_ot 96 8.5 0.001 0.001 17.487 17.487 ot_scf_mini 96 9.5 0.002 0.002 16.224 16.224 prepare_preconditioner 11 7.9 0.000 0.000 13.977 13.977 make_preconditioner 11 8.9 0.000 0.000 13.977 13.977 make_full_inverse_cholesky 11 9.9 0.000 0.000 12.832 12.832 ot_mini 96 10.5 0.001 0.001 10.698 10.698 make_m2s 3932 13.4 0.039 0.039 9.801 9.801 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 6.609 6.609 qs_ot_get_derivative 96 11.5 0.001 0.001 5.779 5.779 pw_transfer 1295 11.6 0.061 0.061 5.542 5.542 fft_wrap_pw1pw2 1081 12.6 0.006 0.006 5.351 5.351 init_scf_run 11 5.9 0.002 0.002 5.312 5.312 scf_env_initial_rho_setup 11 6.9 0.001 0.001 5.310 5.310 dbcsr_make_dense_low 4961 15.5 0.071 0.071 5.278 5.278 make_dense_data 4961 16.5 4.594 4.594 5.196 5.196 ot_diis_step 96 11.5 0.003 0.003 4.916 4.916 make_images 3932 14.4 1.928 1.928 4.802 4.802 multiply_cannon 1966 13.4 0.168 0.168 4.775 4.775 wfi_extrapolate 11 7.9 0.001 0.001 4.680 4.680 dbcsr_make_images_dense 3386 14.7 0.014 0.014 4.679 4.679 fft_wrap_pw1pw2_140 439 13.2 0.393 0.393 4.585 4.585 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 4.567 4.567 apply_single 107 13.6 0.000 0.000 4.567 4.567 cp_fm_cholesky_decompose 22 10.9 4.464 4.464 4.464 4.464 multiply_cannon_loop 1966 14.4 0.054 0.054 4.349 4.349 multiply_cannon_multrec 1966 15.4 4.245 4.245 4.294 4.294 cp_fm_cholesky_invert 11 10.9 4.200 4.200 4.200 4.200 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 4.199 4.199 qs_env_update_s_mstruct 11 6.9 0.000 0.000 3.700 3.700 dbcsr_complete_redistribute 317 12.2 1.917 1.917 3.677 3.677 dbcsr_copy 1855 11.9 0.206 0.206 3.672 3.672 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 3.492 3.492 dbcsr_copy_into_existing 22 7.9 3.393 3.393 3.393 3.393 qs_create_task_list 11 7.9 0.000 0.000 3.304 3.304 generate_qs_task_list 11 8.9 2.385 2.385 3.304 3.304 density_rs2pw 107 9.7 0.004 0.004 3.198 3.198 copy_dbcsr_to_fm 147 11.2 0.002 0.002 3.031 3.031 fft3d_s 1082 14.6 2.650 2.650 2.655 2.655 qs_ot_get_p 107 10.4 0.001 0.001 2.509 2.509 build_core_hamiltonian_matrix 11 6.9 0.000 0.000 2.497 2.497 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.382 2.382 ------------------------------------------------------------------------------- From /workspace/artifacts/H2O-64_nonortho_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.008 0.024 72.273 72.283 qs_mol_dyn_low 1 2.0 0.003 0.004 72.140 72.144 qs_forces 11 3.9 0.002 0.002 72.099 72.100 qs_energies 11 4.9 0.001 0.001 67.165 67.167 scf_env_do_scf 11 5.9 0.000 0.002 62.095 62.095 scf_env_do_scf_inner_loop 96 6.5 0.003 0.019 57.435 57.435 velocity_verlet 10 3.0 0.002 0.003 43.131 43.132 rebuild_ks_matrix 107 8.3 0.000 0.001 30.938 31.054 qs_ks_build_kohn_sham_matrix 107 9.3 0.015 0.017 30.937 31.054 qs_ks_update_qs_env 107 7.6 0.001 0.001 27.123 27.230 sum_up_and_integrate 107 10.3 0.033 0.036 26.959 26.979 integrate_v_rspace 107 11.3 0.004 0.005 26.925 26.950 qs_rho_update_rho_low 107 7.7 0.001 0.001 26.722 26.730 calculate_rho_elec 107 8.7 0.028 0.029 26.722 26.729 grid_integrate_task_list 107 12.3 22.958 23.489 22.958 23.489 grid_collocate_task_list 107 9.7 22.345 22.870 22.345 22.870 dbcsr_multiply_generic 1966 12.4 0.066 0.069 12.207 12.401 multiply_cannon 1966 13.4 0.135 0.148 9.238 9.684 qs_scf_new_mos 96 7.5 0.001 0.001 9.469 9.588 qs_scf_loop_do_ot 96 8.5 0.001 0.001 9.469 9.588 multiply_cannon_loop 1966 14.4 0.088 0.093 8.774 9.256 ot_scf_mini 96 9.5 0.002 0.002 8.893 9.000 mp_waitall_1 136719 16.5 6.995 7.455 6.995 7.455 multiply_cannon_metrocomm3 15728 15.4 0.033 0.036 5.069 5.795 ot_mini 96 10.5 0.001 0.001 5.167 5.288 rs_pw_transfer 878 11.9 0.010 0.011 4.275 4.916 init_scf_loop 11 6.9 0.000 0.001 4.647 4.647 density_rs2pw 107 9.7 0.005 0.006 3.843 4.506 init_scf_run 11 5.9 0.000 0.004 4.044 4.045 scf_env_initial_rho_setup 11 6.9 0.000 0.004 4.044 4.045 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 3.935 3.945 pw_transfer 1295 11.6 0.097 0.102 3.706 3.786 wfi_extrapolate 11 7.9 0.001 0.001 3.664 3.664 fft_wrap_pw1pw2 1081 12.6 0.008 0.009 3.548 3.625 fft_wrap_pw1pw2_140 439 13.2 0.667 0.731 3.074 3.191 multiply_cannon_multrec 15728 15.4 2.949 3.108 2.959 3.118 potential_pw2rs 107 12.3 0.006 0.006 3.100 3.108 qs_ot_get_derivative 96 11.5 0.001 0.001 2.623 2.730 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 2.505 2.614 apply_single 107 13.6 0.000 0.000 2.504 2.614 ot_diis_step 96 11.5 0.003 0.005 2.524 2.524 fft3d_ps 1081 14.6 1.202 1.345 2.155 2.290 mp_waitany 8968 13.7 1.498 2.172 1.498 2.172 make_m2s 3932 13.4 0.040 0.045 1.996 2.039 rs_pw_transfer_RS2PW_140 118 11.5 0.156 0.173 1.173 1.822 make_images 3932 14.4 0.103 0.106 1.708 1.752 mp_alltoall_d11v 1998 13.7 1.018 1.720 1.018 1.720 rs_gather_matrices 107 12.3 0.091 0.098 0.808 1.495 ------------------------------------------------------------------------------- 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=46.209999999999994, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=27.674, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=24.565, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="make_dense_data", label="make_dense_data", y=4.594, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=4.464, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=4.245, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="mp_waitany", label="mp_waitany", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 Plot: name="H2O-64_nonortho_timings_32mpi", title="Timings of H2O-64_nonortho with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="rest", label="rest", y=15.528000000000006, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=22.345, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=22.958, 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="multiply_cannon_multrec", label="multiply_cannon_multrec", y=2.949, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitany", label="mp_waitany", y=1.498, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=6.995, 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 0.183 0.183 107.449 107.449 qs_energies 1 2.0 0.000 0.000 106.590 106.590 scf_env_do_scf 1 3.0 0.000 0.000 105.393 105.393 qs_ks_update_qs_env 8 5.0 0.000 0.000 100.480 100.480 rebuild_ks_matrix 7 6.0 0.000 0.000 100.426 100.426 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.001 100.426 100.426 hfx_ks_matrix 7 8.0 0.000 0.000 91.392 91.392 integrate_four_center 7 9.0 1.922 1.922 91.371 91.371 integrate_four_center_main 7 10.0 0.747 0.747 82.949 82.949 integrate_four_center_bin 440 11.0 82.202 82.202 82.202 82.202 scf_env_do_scf_inner_loop 7 4.0 0.001 0.001 57.077 57.077 init_scf_loop 1 4.0 0.000 0.000 48.307 48.307 integrate_four_center_load 7 10.0 0.000 0.000 6.251 6.251 hfx_load_balance 1 11.0 0.001 0.001 6.251 6.251 hfx_load_balance_count 1 12.0 3.120 3.120 3.120 3.120 hfx_load_balance_bin 1 12.0 3.114 3.114 3.114 3.114 qs_vxc_create 14 8.0 0.000 0.000 3.051 3.051 xc_vxc_pw_create 14 9.0 0.120 0.120 3.051 3.051 calculate_rho_elec 15 7.4 0.118 0.118 2.483 2.483 admm_mo_calc_rho_aux 7 8.0 0.000 0.000 2.406 2.406 prepare_preconditioner 1 5.0 0.000 0.000 2.345 2.345 make_preconditioner 1 6.0 0.000 0.000 2.345 2.345 xc_rho_set_and_dset_create 14 10.0 0.102 0.102 2.335 2.335 ------------------------------------------------------------------------------- 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 0.268 0.298 97.824 97.838 qs_energies 1 2.0 0.000 0.000 97.372 97.380 scf_env_do_scf 1 3.0 0.000 0.000 97.023 97.024 qs_ks_update_qs_env 8 5.0 0.000 0.000 94.991 94.991 rebuild_ks_matrix 7 6.0 0.000 0.000 94.983 94.983 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.002 94.983 94.983 hfx_ks_matrix 7 8.0 0.000 0.000 89.497 89.498 integrate_four_center 7 9.0 0.055 0.347 89.489 89.490 integrate_four_center_main 7 10.0 0.003 0.003 80.977 82.987 integrate_four_center_bin 448 11.0 80.974 82.984 80.974 82.984 scf_env_do_scf_inner_loop 7 4.0 0.000 0.001 53.727 53.728 init_scf_loop 1 4.0 0.000 0.000 43.294 43.295 integrate_four_center_load 7 10.0 0.000 0.000 5.720 5.721 hfx_load_balance 1 11.0 0.001 0.001 5.720 5.721 mp_sync 56 11.2 2.089 3.384 2.089 3.384 hfx_load_balance_count 1 12.0 2.815 2.871 2.815 2.871 hfx_load_balance_bin 1 12.0 2.786 2.844 2.786 2.844 qs_vxc_create 14 8.0 0.000 0.000 2.497 2.497 xc_vxc_pw_create 14 9.0 0.007 0.008 2.497 2.497 xc_rho_set_and_dset_create 14 10.0 0.011 0.012 1.967 2.083 ------------------------------------------------------------------------------- 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=16.160999999999987, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_bin", label="integrate_four_center_bin", y=82.202, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_count", label="hfx_load_balance_count", y=3.12, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=3.114, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center", label="integrate_four_center", y=1.922, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_main", label="integrate_four_center_main", y=0.747, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="CP2K", label="CP2K", y=0.183, 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=8.833999999999989, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center_bin", label="integrate_four_center_bin", y=80.974, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_count", label="hfx_load_balance_count", y=2.815, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=2.786, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center", label="integrate_four_center", y=0.055, 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=0.268, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="mp_sync", label="mp_sync", y=2.089, 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 86.115 86.115 qs_energies 1 2.0 0.000 0.000 85.707 85.707 mp2_main 1 3.0 0.000 0.000 82.893 82.893 mp2_gpw_main 1 4.0 0.000 0.000 82.777 82.777 rpa_ri_compute_en 1 5.0 0.000 0.000 79.125 79.125 rpa_num_int 1 6.0 0.001 0.001 79.119 79.119 compute_mat_P_omega 1 7.0 0.003 0.003 69.188 69.188 compute_mat_P_omega_contract 10 8.0 8.926 8.926 68.985 68.985 dbt_total 2336 9.6 0.013 0.013 55.217 55.217 dbt_contract 787 11.0 0.041 0.041 48.055 48.055 dbt_tas_total 1149 12.2 0.232 0.232 47.050 47.050 dbt_tas_multiply 807 12.1 0.002 0.002 45.638 45.638 dbt_tas_dbm 807 14.1 0.003 0.003 39.065 39.065 dbm_multiply 807 16.1 39.057 39.057 39.057 39.057 dbt_tas_mm_1N 524 15.1 0.001 0.001 31.597 31.597 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 30.157 30.157 compute_mat_P_omega_calc_M_occ 250 9.0 8.934 8.934 17.190 17.190 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 6.977 6.977 dbt_tas_mm_2 251 15.0 0.001 0.001 5.962 5.962 dbt_copy 1103 10.7 0.074 0.074 5.733 5.733 compute_QP_energies 1 7.0 0.000 0.000 5.106 5.106 compute_self_energy_cubic_gw 1 8.0 0.056 0.056 5.105 5.105 contract_cubic_gw 21 9.0 0.000 0.000 4.090 4.090 dbt_tas_reserve_blocks_index 3261 14.3 0.477 0.477 3.716 3.716 mp2_ri_gpw_compute_in 1 5.0 0.001 0.001 3.645 3.645 dbm_reserve_blocks 3628 15.3 3.302 3.302 3.302 3.302 dbt_reserve_blocks_index 2280 13.1 0.057 0.057 2.800 2.800 dbt_reserve_blocks_index_array 2222 12.2 0.009 0.009 2.757 2.757 scf_env_do_scf 1 3.0 0.000 0.000 2.705 2.705 scf_env_do_scf_inner_loop 17 4.0 0.002 0.002 2.704 2.704 convert_to_new_pgrid 2421 14.1 0.140 0.140 2.357 2.357 dbt_crop 1042 12.0 1.407 1.407 2.300 2.300 dbt_tas_copy 574 11.4 1.334 1.334 2.283 2.283 dbm_copy 1614 15.1 2.217 2.217 2.217 2.217 dbt_tas_reshape 367 15.0 0.007 0.007 2.115 2.115 compute_W_cubic_GW 10 7.0 0.011 0.011 2.018 2.018 rpa_num_int_RPA_matrix_operati 10 7.0 0.000 0.000 1.955 1.955 dbt_reshape 278 11.9 1.056 1.056 1.940 1.940 get_2c_integrals 1 6.0 0.000 0.000 1.726 1.726 ------------------------------------------------------------------------------- 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 0.021 32.191 32.202 qs_energies 1 2.0 0.000 0.000 32.075 32.076 mp2_main 1 3.0 0.000 0.000 31.148 31.149 mp2_gpw_main 1 4.0 0.000 0.000 31.115 31.117 rpa_ri_compute_en 1 5.0 0.000 0.000 29.875 29.876 rpa_num_int 1 6.0 0.001 0.002 29.874 29.875 dbt_total 2336 9.6 0.015 0.016 26.516 26.522 compute_mat_P_omega 1 7.0 0.001 0.005 25.468 25.514 compute_mat_P_omega_contract 10 8.0 0.427 0.440 25.346 25.349 dbt_contract 787 11.0 0.038 0.040 19.486 19.490 dbt_tas_total 1149 12.2 0.076 0.085 17.269 17.269 dbt_tas_multiply 807 12.1 0.002 0.002 17.215 17.217 dbt_tas_dbm 807 14.1 0.003 0.003 13.021 13.027 dbm_multiply 807 16.1 10.344 11.225 10.344 11.225 compute_mat_P_omega_calc_M_occ 250 9.0 0.403 0.418 7.432 7.433 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 7.326 7.327 dbt_copy 1149 10.8 0.013 0.014 6.306 6.448 dbt_reshape 1136 11.8 2.742 2.892 6.018 6.149 dbt_tas_mm_2 251 15.0 0.001 0.001 6.091 6.092 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 5.365 5.366 mp_sync 8688 11.6 4.243 5.236 4.243 5.236 dbt_tas_mm_1N 524 15.1 0.001 0.002 4.723 5.079 compute_QP_energies 1 7.0 0.000 0.000 2.763 2.764 compute_self_energy_cubic_gw 1 8.0 0.003 0.003 2.761 2.763 mp_waitall_2 3812 15.3 2.371 2.539 2.371 2.539 dbt_communicate_buffer 1136 12.8 0.051 0.056 2.399 2.521 contract_cubic_gw 21 9.0 0.000 0.000 2.166 2.167 dbt_reserve_blocks_index 2887 13.1 0.071 0.076 1.826 2.008 dbt_reserve_blocks_index_array 2829 12.2 0.009 0.010 1.815 1.996 dbt_tas_reserve_blocks_index 3347 14.5 0.437 0.471 1.805 1.986 dbm_reserve_blocks 3752 15.4 1.458 1.606 1.458 1.606 dbt_crop 1042 12.0 0.909 0.996 1.460 1.588 mp2_ri_gpw_compute_in 1 5.0 0.000 0.001 1.239 1.239 dbt_tas_replicate 405 14.1 0.549 0.751 1.132 1.190 compute_mat_P_omega_copy_M_vir 250 9.0 0.001 0.001 1.082 1.085 compute_mat_P_omega_copy_M_occ 250 9.0 0.001 0.001 1.008 1.012 parallel_gemm_fm 105 8.4 0.000 0.000 0.973 0.981 parallel_gemm_fm_cosma 105 9.4 0.973 0.981 0.973 0.981 convert_to_new_pgrid 2421 14.1 0.026 0.029 0.838 0.920 scf_env_do_scf 1 3.0 0.000 0.000 0.890 0.890 scf_env_do_scf_inner_loop 17 4.0 0.000 0.002 0.890 0.890 dbm_copy 1608 15.1 0.806 0.890 0.806 0.890 compute_W_cubic_GW 10 7.0 0.001 0.001 0.737 0.741 mp_max_i 2000 9.8 0.502 0.687 0.502 0.687 ------------------------------------------------------------------------------- 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=22.622999999999998, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=39.057, 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=8.934, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=8.926, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=3.302, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_copy", label="dbm_copy", y=2.217, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=1.056, 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=9.397000000000002, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=10.344, 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=0.403, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=0.427, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=1.458, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_copy", label="dbm_copy", y=0.806, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=2.742, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_sync", label="mp_sync", y=4.243, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.371, yerr=0.0 Running RI-HFX_H2O-32.inp with 1 threads and 32 ranks... done. Running RI-HFX_H2O-32.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/RI-HFX_H2O-32_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.019 0.019 356.655 356.655 qs_forces 1 2.0 0.000 0.000 356.059 356.059 rebuild_ks_matrix 7 6.6 0.000 0.000 354.560 354.560 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.001 354.560 354.560 hfx_ks_matrix 7 8.6 0.000 0.000 352.426 352.426 hfx_ri_update_ks 7 9.6 0.000 0.000 316.143 316.143 hfx_ri_update_ks_Pmat 7 10.6 36.148 36.148 316.136 316.136 dbt_total 783 11.1 0.005 0.005 293.056 293.056 qs_energies 1 3.0 0.000 0.000 276.575 276.575 scf_env_do_scf 1 4.0 0.000 0.000 276.284 276.284 qs_ks_update_qs_env 8 6.0 0.000 0.000 275.130 275.130 dbt_contract 207 12.4 0.033 0.033 273.990 273.990 dbt_tas_total 317 14.0 1.609 1.609 271.825 271.825 dbt_tas_multiply 216 13.5 0.001 0.001 268.292 268.292 dbt_tas_dbm 216 15.5 0.001 0.001 259.391 259.391 dbm_multiply 216 17.5 259.388 259.388 259.388 259.388 hfx_ri_update_ks_Pmat_KS 63 11.6 0.001 0.001 255.094 255.094 dbt_tas_mm_2 91 16.5 0.001 0.001 245.791 245.791 scf_env_do_scf_inner_loop 6 5.0 0.001 0.001 178.762 178.762 init_scf_loop 2 5.0 0.000 0.000 97.520 97.520 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 79.436 79.436 hfx_ri_update_forces 1 7.0 1.640 1.640 36.280 36.280 hfx_ri_forces_Pmat_3c 1 8.0 4.860 4.860 19.094 19.094 dbt_copy 409 11.7 0.049 0.049 15.525 15.525 precalc_derivatives 1 8.0 2.164 2.164 13.221 13.221 dbt_reshape 132 13.2 6.694 6.694 10.876 10.876 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 9.416 9.416 dbt_tas_mm_3T 77 17.1 0.000 0.000 9.324 9.324 dbt_tas_reserve_blocks_index 1229 15.4 1.032 1.032 7.929 7.929 build_3c_derivatives 3 9.0 2.793 2.793 7.507 7.507 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 7.201 7.201 ------------------------------------------------------------------------------- From /workspace/artifacts/RI-HFX_H2O-32_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.007 0.027 45.483 45.493 qs_forces 1 2.0 0.000 0.000 45.348 45.349 rebuild_ks_matrix 7 6.6 0.000 0.000 44.658 44.659 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.002 44.658 44.659 hfx_ks_matrix 7 8.6 0.000 0.000 43.651 43.656 dbt_total 783 11.1 0.005 0.006 38.775 38.778 dbt_contract 207 12.4 0.024 0.027 29.986 29.997 hfx_ri_update_ks 7 9.6 0.000 0.000 27.094 27.095 hfx_ri_update_ks_Pmat 7 10.6 1.233 1.294 27.092 27.094 dbt_tas_total 317 14.0 0.044 0.060 26.388 26.389 dbt_tas_multiply 216 13.5 0.001 0.001 26.296 26.297 qs_energies 1 3.0 0.000 0.000 25.385 25.385 scf_env_do_scf 1 4.0 0.000 0.001 25.244 25.244 qs_ks_update_qs_env 8 6.0 0.000 0.000 24.706 24.706 dbt_tas_dbm 216 15.5 0.001 0.001 22.109 22.111 dbm_multiply 216 17.5 20.021 20.672 20.021 20.672 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 19.954 19.954 hfx_ri_update_forces 1 7.0 0.058 0.062 16.556 16.561 scf_env_do_scf_inner_loop 6 5.0 0.000 0.001 14.486 14.486 hfx_ri_update_ks_Pmat_KS 63 11.6 0.000 0.001 12.538 12.538 hfx_ri_forces_Pmat_3c 1 8.0 0.159 0.169 11.871 11.871 init_scf_loop 2 5.0 0.000 0.000 10.758 10.758 dbt_tas_mm_2 91 16.5 0.001 0.002 10.678 10.680 dbt_copy 497 12.3 0.011 0.013 8.389 8.577 dbt_reshape 365 13.6 3.590 3.667 6.490 6.666 dbt_tas_mm_3T 77 17.1 0.000 0.000 5.850 6.300 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 5.088 5.088 mp_sync 2665 13.0 3.917 4.829 3.917 4.829 dbt_tas_mm_3N 37 15.4 0.000 0.000 3.942 4.067 precalc_derivatives 1 8.0 0.079 0.084 3.577 3.577 dbt_tas_reserve_blocks_index 1356 15.8 0.893 0.922 3.152 3.369 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 3.110 3.110 dbt_reserve_blocks_index 1051 14.7 0.114 0.118 2.652 2.856 dbt_reserve_blocks_index_array 1028 13.8 0.005 0.006 2.624 2.830 dbt_crop 372 13.7 1.734 1.778 2.525 2.606 dbm_reserve_blocks 1481 16.7 2.328 2.536 2.328 2.536 mp_waitall_2 1138 16.4 2.034 2.124 2.034 2.124 build_3c_derivatives 3 9.0 0.226 0.243 1.995 2.004 dbt_communicate_buffer 365 14.6 0.012 0.018 1.808 1.876 hfx_ri_update_ks_Pmat_copy_2 63 11.6 0.000 0.000 1.643 1.644 hfx_ri_pre_scf_Pmat_RIx3C 9 13.0 0.000 0.000 1.554 1.558 convert_to_new_pgrid 648 15.5 0.037 0.068 1.310 1.436 dbt_tas_copy 132 12.5 0.634 0.659 1.208 1.322 dbm_copy 452 16.3 1.141 1.254 1.141 1.254 ------------------------------------------------------------------------------- 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=46.771999999999935, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=259.388, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=36.148, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=6.694, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_forces_Pmat_3c", label="hfx_ri_forces_Pmat_3c", y=4.86, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="build_3c_derivatives", label="build_3c_derivatives", y=2.793, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", 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 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=11.975000000000001, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=20.021, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=1.233, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=3.59, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_forces_Pmat_3c", label="hfx_ri_forces_Pmat_3c", y=0.159, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="build_3c_derivatives", label="build_3c_derivatives", y=0.226, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=2.328, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.034, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_sync", label="mp_sync", y=3.917, 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 0.015 208.782 208.782 qs_energies 1 2.0 0.000 0.000 208.590 208.590 mp2_main 1 3.0 0.000 0.000 203.783 203.783 mp2_gpw_main 1 4.0 0.001 0.001 203.370 203.370 mp2_ri_gpw_compute_in 1 5.0 0.392 0.392 157.065 157.065 mp2_ri_gpw_compute_in_loop 1 6.0 0.010 0.010 148.285 148.285 mp2_eri_3c_integrate_gpw 2656 7.0 0.016 0.016 116.368 116.368 integrate_v_rspace 2666 8.0 0.649 0.649 103.416 103.416 grid_integrate_task_list 2666 9.0 100.779 100.779 100.779 100.779 mp2_ri_gpw_compute_en 1 5.0 0.089 0.089 46.280 46.280 mp2_ri_gpw_compute_en_RI_loop 1 6.0 9.735 9.735 44.382 44.382 mp2_ri_gpw_compute_en_expansio 2080 7.0 2.204 2.204 26.902 26.902 local_gemm 2080 8.0 24.697 24.697 24.697 24.697 dbcsr_multiply_generic 5322 8.0 0.190 0.190 21.653 21.653 ao_to_mo_and_store_B_mult_1 2656 7.0 0.009 0.009 21.631 21.631 pw_transfer 63872 10.6 1.068 1.068 11.662 11.662 calculate_wavefunction 2656 8.0 8.149 8.149 11.589 11.589 multiply_cannon 5322 9.0 0.455 0.455 11.197 11.197 fft_wrap_pw1pw2 53228 11.4 0.111 0.111 10.378 10.378 ao_to_mo_and_store_B_E_Ex_1 2656 7.0 2.427 2.427 10.180 10.180 multiply_cannon_loop 5322 10.0 0.127 0.127 9.798 9.798 get_2c_integrals 1 6.0 0.000 0.000 8.387 8.387 copy_dbcsr_to_fm 2679 8.0 0.027 0.027 8.320 8.320 multiply_cannon_multrec 5322 11.0 8.251 8.251 8.291 8.291 make_m2s 10644 9.0 0.061 0.061 8.204 8.204 make_images 10644 10.0 3.312 3.312 7.895 7.895 compute_2c_integrals 1 7.0 0.005 0.005 7.549 7.549 compute_2c_integrals_loop_lm 1 8.0 0.010 0.010 7.538 7.538 mp2_eri_2c_integrate_gpw 1 9.0 0.817 0.817 7.527 7.527 fft_wrap_pw1pw2_20 21271 12.4 0.479 0.479 7.399 7.399 dbcsr_complete_redistribute 2689 9.0 1.088 1.088 6.695 6.695 fft3d_s 53229 13.4 6.288 6.288 6.327 6.327 dbcsr_finalize 10708 9.5 0.172 0.172 6.186 6.186 mp2_ri_gpw_compute_en_ener 2080 7.0 5.708 5.708 5.708 5.708 dbcsr_merge_all 8011 10.3 4.223 4.223 5.544 5.544 scf_env_do_scf 1 3.0 0.000 0.000 4.413 4.413 scf_env_do_scf_inner_loop 10 4.0 0.001 0.001 4.413 4.413 ------------------------------------------------------------------------------- From /workspace/artifacts/RI-MP2_ammonia_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.007 0.027 36.348 36.358 qs_energies 1 2.0 0.000 0.002 36.128 36.129 mp2_main 1 3.0 0.000 0.001 34.292 34.293 mp2_gpw_main 1 4.0 0.001 0.002 34.202 34.202 mp2_ri_gpw_compute_in 1 5.0 0.051 0.052 17.568 17.921 mp2_ri_gpw_compute_en 1 5.0 0.205 0.218 16.541 16.760 mp2_ri_gpw_compute_in_loop 1 6.0 0.001 0.001 16.367 16.722 mp2_ri_gpw_compute_en_RI_loop 1 6.0 1.536 1.631 15.421 15.426 mp2_eri_3c_integrate_gpw 83 7.0 0.001 0.001 14.291 14.667 integrate_v_rspace 93 8.1 0.101 0.112 14.141 14.519 grid_integrate_task_list 93 9.1 13.849 14.223 13.849 14.223 mp2_ri_gpw_compute_en_expansio 65 7.0 0.111 0.120 11.172 11.372 local_gemm 65 8.0 11.061 11.261 11.061 11.261 mp2_ri_gpw_compute_en_comm 20 7.0 0.080 0.089 2.354 2.651 mp_sendrecv_dm3 1240 8.0 1.802 2.147 1.802 2.147 dbcsr_multiply_generic 176 8.0 0.008 0.008 1.779 1.941 ao_to_mo_and_store_B_mult_1 83 7.0 0.001 0.001 1.764 1.928 scf_env_do_scf 1 3.0 0.000 0.000 1.715 1.716 scf_env_do_scf_inner_loop 10 4.0 0.000 0.001 1.715 1.716 get_2c_integrals 1 6.0 0.000 0.000 1.135 1.163 multiply_cannon 176 9.0 0.016 0.018 1.070 1.137 multiply_cannon_loop 176 10.0 0.002 0.002 1.010 1.075 multiply_cannon_multrec 246 11.0 0.874 0.913 0.879 0.919 compute_2c_integrals 1 7.0 0.003 0.004 0.837 0.855 pw_transfer 2120 10.5 0.048 0.050 0.769 0.780 compute_2c_integrals_loop_lm 1 8.0 0.002 0.004 0.757 0.771 mp2_eri_2c_integrate_gpw 1 9.0 0.202 0.207 0.755 0.770 make_m2s 352 9.0 0.003 0.003 0.673 0.765 qs_scf_new_mos 10 5.0 0.000 0.000 0.760 0.763 make_images 352 10.0 0.053 0.054 0.660 0.752 ------------------------------------------------------------------------------- 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=57.17099999999999, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=100.779, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="local_gemm", label="local_gemm", y=24.697, 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=9.735, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=8.251, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="calculate_wavefunction", label="calculate_wavefunction", y=8.149, 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=7.225999999999999, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.849, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="local_gemm", label="local_gemm", y=11.061, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="mp2_ri_gpw_compute_en_RI_loop", label="mp2_ri_gpw_compute_en_RI_loop", y=1.536, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=0.874, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="calculate_wavefunction", label="calculate_wavefunction", y=0.0, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="mp_sendrecv_dm3", label="mp_sendrecv_dm3", y=1.802, 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 0.088 0.088 127.366 127.366 qs_energies 1 2.0 0.000 0.000 125.873 125.873 scf_env_do_scf 1 3.0 0.000 0.000 119.157 119.157 scf_env_do_scf_inner_loop 15 4.0 0.002 0.002 119.157 119.157 qs_ks_update_qs_env 15 5.0 0.000 0.000 49.718 49.718 rebuild_ks_matrix 15 6.0 0.000 0.000 49.509 49.509 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.002 49.509 49.509 qs_scf_new_mos 15 5.0 0.000 0.000 43.628 43.628 eigensolver 15 6.0 0.002 0.002 35.631 35.631 qs_vxc_create 15 8.0 0.045 0.045 33.488 33.488 calculate_dispersion_nonloc 15 9.0 6.880 6.880 29.300 29.300 qs_rho_update_rho_low 16 5.0 0.000 0.000 23.110 23.110 calculate_rho_elec 16 6.0 0.223 0.223 23.110 23.110 cp_fm_diag_elpa 15 7.0 0.000 0.000 22.658 22.658 cp_fm_diag_elpa_base 15 8.0 20.147 20.147 22.658 22.658 pw_transfer 1191 10.0 0.071 0.071 22.654 22.654 fft_wrap_pw1pw2 1086 11.0 0.009 0.009 22.456 22.456 grid_collocate_task_list 16 7.0 21.818 21.818 21.818 21.818 fft_wrap_pw1pw2_150 765 12.0 3.575 3.575 16.651 16.651 sum_up_and_integrate 15 8.0 0.122 0.122 14.990 14.990 integrate_v_rspace 15 9.0 0.019 0.019 14.868 14.868 grid_integrate_task_list 15 10.0 14.347 14.347 14.347 14.347 cp_fm_cholesky_restore 45 7.0 10.625 10.625 10.625 10.625 fft3d_s 1087 13.0 10.351 10.351 10.359 10.359 pw_scatter_s 585 13.1 6.742 6.742 6.742 6.742 copy_dbcsr_to_fm 16 5.9 0.001 0.001 5.740 5.740 dbcsr_complete_redistribute 46 8.3 2.321 2.321 5.721 5.721 fft_wrap_pw1pw2_200 197 12.3 0.595 0.595 5.613 5.613 cp_fm_upper_to_full 30 8.0 4.856 4.856 4.856 4.856 vdW_energy 15 10.0 4.388 4.388 4.388 4.388 xc_vxc_pw_create 15 9.0 0.240 0.240 4.143 4.143 gspace_mixing 14 5.0 0.171 0.171 3.972 3.972 broyden_mixing 14 6.0 3.406 3.406 3.406 3.406 init_scf_run 1 3.0 0.000 0.000 3.197 3.197 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 3.047 3.047 xc_pw_derive 90 11.0 0.001 0.001 2.640 2.640 calculate_dm_sparse 15 6.0 0.019 0.019 2.617 2.617 ------------------------------------------------------------------------------- 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 0.016 0.030 63.954 63.966 qs_energies 1 2.0 0.000 0.000 63.666 63.672 scf_env_do_scf 1 3.0 0.000 0.000 59.256 59.257 scf_env_do_scf_inner_loop 15 4.0 0.001 0.004 59.256 59.257 qs_ks_update_qs_env 15 5.0 0.000 0.000 25.736 25.744 rebuild_ks_matrix 15 6.0 0.000 0.000 25.702 25.712 qs_ks_build_kohn_sham_matrix 15 7.0 0.003 0.003 25.702 25.712 qs_rho_update_rho_low 16 5.0 0.000 0.000 22.114 22.118 calculate_rho_elec 16 6.0 0.007 0.007 22.113 22.118 grid_collocate_task_list 16 7.0 20.734 21.163 20.734 21.163 sum_up_and_integrate 15 8.0 0.015 0.020 14.824 14.873 integrate_v_rspace 15 9.0 0.001 0.001 14.809 14.860 grid_integrate_task_list 15 10.0 14.091 14.205 14.091 14.205 qs_scf_new_mos 15 5.0 0.000 0.000 12.145 12.166 eigensolver 15 6.0 0.001 0.002 11.164 11.193 qs_vxc_create 15 8.0 0.001 0.001 10.537 10.549 calculate_dispersion_nonloc 15 9.0 0.948 0.958 8.427 8.449 pw_transfer 1191 10.0 0.101 0.112 8.326 8.405 fft_wrap_pw1pw2 1086 11.0 0.013 0.015 8.144 8.249 cp_fm_diag_elpa 15 7.0 0.000 0.000 7.867 7.871 cp_fm_diag_elpa_base 15 8.0 7.710 7.750 7.862 7.862 fft3d_ps 1086 13.0 2.832 3.097 5.472 5.970 fft_wrap_pw1pw2_150 765 12.0 0.690 0.808 5.245 5.273 cp_fm_cholesky_restore 45 7.0 3.133 3.197 3.133 3.197 fft_wrap_pw1pw2_200 197 12.3 0.458 0.558 2.786 2.846 mp_alltoall_z22v 1086 15.0 2.045 2.765 2.045 2.765 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 2.673 2.674 build_core_hamiltonian_matrix 1 4.0 0.000 0.000 2.323 2.571 xc_vxc_pw_create 15 9.0 0.016 0.021 2.110 2.149 x_to_yz 585 14.1 0.359 0.384 1.404 1.743 yz_to_x 501 13.9 0.207 0.246 1.207 1.587 xc_pw_derive 90 11.0 0.001 0.002 1.453 1.531 build_core_ppnl 1 5.0 1.367 1.514 1.367 1.514 init_scf_run 1 3.0 0.000 0.001 1.512 1.513 scf_env_initial_rho_setup 1 4.0 0.000 0.000 1.422 1.422 vdW_energy 15 10.0 1.356 1.412 1.356 1.412 rs_pw_transfer 158 9.4 0.002 0.002 1.106 1.381 density_rs2pw 16 7.0 0.001 0.001 1.162 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=50.07799999999999, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=21.818, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=20.147, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=14.347, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=10.625, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="fft3d_s", label="fft3d_s", y=10.351, 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=15.453999999999994, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=20.734, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=7.71, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=14.091, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=3.133, 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=2.832, 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 0.089 0.089 322.710 322.710 qs_energies 1 2.0 0.000 0.000 322.556 322.556 ls_scf 1 3.0 0.000 0.000 321.262 321.262 ls_scf_main 1 4.0 0.002 0.002 312.132 312.132 density_matrix_trs4 11 5.0 0.013 0.013 210.375 210.375 arnoldi_extremal 12 6.1 0.000 0.000 116.204 116.204 arnoldi_normal_ev 12 7.1 0.048 0.048 116.203 116.203 build_subspace 23 8.1 0.084 0.084 114.541 114.541 dbcsr_matrix_vector_mult 652 9.0 0.254 0.254 113.961 113.961 dbcsr_matrix_vector_mult_local 652 10.0 112.363 112.363 112.374 112.374 ls_scf_dm_to_ks 11 5.0 0.000 0.000 95.435 95.435 matrix_ls_to_qs 11 6.0 0.000 0.000 91.793 91.793 dbcsr_multiply_generic 185 6.1 0.895 0.895 79.468 79.468 dbcsr_complete_redistribute 23 7.5 34.287 34.287 48.254 48.254 dbcsr_copy_into_existing 11 7.0 47.985 47.985 47.985 47.985 multiply_cannon 185 7.1 0.372 0.372 46.260 46.260 matrix_decluster 11 7.0 0.000 0.000 43.807 43.807 multiply_cannon_loop 185 8.1 0.273 0.273 33.452 33.452 make_m2s 370 7.1 0.039 0.039 28.077 28.077 make_images 370 8.1 12.431 12.431 25.783 25.783 multiply_cannon_multrec 185 9.1 23.667 23.667 23.714 23.714 dbcsr_finalize 646 7.5 0.248 0.248 18.038 18.038 dbcsr_merge_all 597 8.5 2.608 2.608 16.751 16.751 tree_to_linear_d 110 9.4 12.568 12.568 12.568 12.568 setup_rec_index_2d 370 8.1 12.332 12.332 12.332 12.332 dbcsr_sort_indices 1103 9.9 11.428 11.428 11.428 11.428 quick_finalize 395 10.0 0.412 0.412 9.839 9.839 calculate_norms 370 9.1 9.465 9.465 9.465 9.465 dbcsr_special_finalize 370 9.1 0.002 0.002 9.068 9.068 ls_scf_init_scf 1 4.0 0.000 0.000 8.410 8.410 ls_scf_init_matrix_S 1 5.0 0.000 0.000 8.080 8.080 matrix_sqrt_Newton_Schulz 1 6.0 0.001 0.001 7.416 7.416 dbcsr_dot_sd 144 6.3 6.625 6.625 6.625 6.625 matrix_qs_to_ls 12 5.1 0.000 0.000 6.505 6.505 matrix_cluster 12 6.1 0.000 0.000 6.505 6.505 ------------------------------------------------------------------------------- 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 0.021 65.825 65.835 qs_energies 1 2.0 0.000 0.000 65.716 65.716 ls_scf 1 3.0 0.000 0.000 65.662 65.662 ls_scf_main 1 4.0 0.001 0.008 63.072 63.073 density_matrix_trs4 11 5.0 0.006 0.019 60.583 60.650 dbcsr_multiply_generic 185 6.1 0.058 0.070 57.312 57.635 multiply_cannon 185 7.1 0.035 0.037 47.927 48.344 multiply_cannon_loop 185 8.1 0.112 0.129 45.494 46.153 multiply_cannon_multrec 1480 9.1 28.322 31.168 28.593 31.451 mp_waitall_1 11936 10.3 14.601 17.122 14.601 17.122 multiply_cannon_metrocomm3 1480 9.1 0.014 0.017 8.545 12.249 make_m2s 370 7.1 0.035 0.038 6.562 6.625 make_images 370 8.1 0.644 0.678 6.432 6.496 multiply_cannon_metrocomm1 1480 9.1 0.008 0.009 3.449 5.767 calculate_norms 2960 9.1 4.736 5.467 4.736 5.467 make_images_data 370 9.1 0.009 0.010 2.833 3.125 mp_sum_l 1119 5.6 1.796 2.858 1.796 2.858 hybrid_alltoall_any 393 9.9 0.173 0.904 2.458 2.740 arnoldi_extremal 12 6.1 0.000 0.000 2.447 2.467 arnoldi_normal_ev 12 7.1 0.002 0.008 2.446 2.467 build_subspace 23 8.1 0.020 0.024 2.350 2.352 ls_scf_dm_to_ks 11 5.0 0.000 0.000 2.154 2.208 dbcsr_matrix_vector_mult 652 9.0 0.014 0.052 2.029 2.085 dbcsr_complete_redistribute 23 7.5 1.224 1.263 1.945 2.029 ls_scf_init_scf 1 4.0 0.000 0.000 1.991 1.992 matrix_ls_to_qs 11 6.0 0.000 0.000 1.898 1.989 ls_scf_init_matrix_S 1 5.0 0.000 0.000 1.964 1.970 dbcsr_multiply_generic_mpsum_f 137 7.1 0.000 0.000 0.988 1.920 matrix_decluster 11 7.0 0.000 0.000 1.756 1.844 matrix_sqrt_Newton_Schulz 1 6.0 0.001 0.001 1.793 1.795 dbcsr_matrix_vector_mult_local 652 10.0 1.701 1.744 1.703 1.746 make_images_pack 370 9.1 1.629 1.720 1.633 1.725 buffer_matrices_ensure_size 370 8.1 1.350 1.551 1.350 1.551 dbcsr_finalize 646 7.5 0.008 0.009 1.401 1.549 ------------------------------------------------------------------------------- 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=82.37499999999994, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=112.363, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_copy_into_existing", label="dbcsr_copy_into_existing", y=47.985, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_complete_redistribute", label="dbcsr_complete_redistribute", y=34.287, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=23.667, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="tree_to_linear_d", label="tree_to_linear_d", y=12.568, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="calculate_norms", label="calculate_norms", y=9.465, 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=13.445000000000007, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=1.701, 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=1.224, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=28.322, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="tree_to_linear_d", label="tree_to_linear_d", y=0.0, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="calculate_norms", label="calculate_norms", y=4.736, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=14.601, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=1.796, 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 0.008 0.008 74.648 74.648 lib_test 1 2.0 0.000 0.000 74.639 74.639 dbcsr_run_tests 3 3.0 0.002 0.002 74.639 74.639 test_multiplies_multiproc 3 4.0 0.001 0.001 58.365 58.365 dbcsr_redistribute 9 5.0 38.580 38.580 40.220 40.220 dbcsr_multiply_generic 9 5.0 0.001 0.001 16.783 16.783 dbcsr_make_random_matrix 9 4.0 13.098 13.098 16.161 16.161 multiply_cannon 9 6.0 0.002 0.002 11.975 11.975 multiply_cannon_loop 9 7.0 0.020 0.020 11.610 11.610 multiply_cannon_multrec 9 8.0 11.590 11.590 11.590 11.590 dbcsr_finalize 27 5.7 0.009 0.009 5.636 5.636 dbcsr_merge_all 18 6.5 1.998 1.998 4.877 4.877 dbcsr_data_release 975 7.6 2.871 2.871 2.871 2.871 tree_to_linear_d 9 7.0 2.000 2.000 2.000 2.000 make_m2s 18 6.0 0.001 0.001 1.662 1.662 make_images 18 7.0 0.558 0.558 1.596 1.596 ------------------------------------------------------------------------------- From /workspace/artifacts/dbcsr_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.004 0.011 18.461 18.466 lib_test 1 2.0 0.000 0.000 18.431 18.451 dbcsr_run_tests 3 3.0 0.000 0.001 18.430 18.450 test_multiplies_multiproc 3 4.0 0.000 0.002 17.565 17.633 dbcsr_multiply_generic 9 5.0 0.001 0.001 16.031 16.078 multiply_cannon 9 6.0 0.002 0.002 14.285 14.603 multiply_cannon_loop 9 7.0 0.002 0.002 13.972 14.285 multiply_cannon_multrec 72 8.0 11.636 12.074 11.637 12.075 mp_waitall_1 576 9.2 2.641 3.791 2.641 3.791 multiply_cannon_metrocomm1 72 8.0 0.001 0.001 2.084 3.333 mp_sum_l 390 2.5 0.366 1.075 0.366 1.075 dbcsr_multiply_generic_mpsum_f 9 6.0 0.000 0.000 0.363 1.071 dbcsr_make_random_matrix 9 4.0 0.688 0.981 0.831 1.033 dbcsr_data_release 444 7.6 0.782 0.899 0.782 0.899 dbcsr_finalize 27 5.7 0.000 0.000 0.750 0.829 multiply_cannon_metrocomm3 72 8.0 0.000 0.000 0.244 0.773 dbcsr_destroy 111 5.9 0.000 0.000 0.611 0.711 make_m2s 18 6.0 0.001 0.001 0.667 0.699 make_images 18 7.0 0.021 0.022 0.664 0.696 dbcsr_merge_all 18 6.5 0.111 0.130 0.577 0.677 dbcsr_redistribute 9 5.0 0.248 0.301 0.430 0.462 dbcsr_data_copy_aa2 18 7.5 0.350 0.441 0.350 0.441 make_images_data 18 8.0 0.000 0.001 0.348 0.415 hybrid_alltoall_any 18 9.0 0.032 0.147 0.307 0.380 ------------------------------------------------------------------------------- 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=6.509, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_redistribute", label="dbcsr_redistribute", y=38.58, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=13.098, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=11.59, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_data_release", label="dbcsr_data_release", y=2.871, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="tree_to_linear_d", label="tree_to_linear_d", y=2.0, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="mp_sum_l", label="mp_sum_l", y=0.0, yerr=0.0 Plot: name="dbcsr_timings_32mpi", title="Timings of dbcsr with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="dbcsr_timings_32mpi", name="rest", label="rest", y=2.099999999999998, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_redistribute", label="dbcsr_redistribute", y=0.248, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=0.688, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=11.636, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_data_release", label="dbcsr_data_release", y=0.782, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="tree_to_linear_d", label="tree_to_linear_d", y=0.0, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=2.641, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=0.366, 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 0.058 0.058 133.529 133.529 qs_mol_dyn_low 1 2.0 0.003 0.003 132.011 132.011 velocity_verlet 5 3.0 0.003 0.003 107.583 107.583 qmmm_el_coupling 6 3.8 0.000 0.000 88.000 88.000 qmmm_elec_with_gaussian 6 4.8 0.013 0.013 87.991 87.991 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 87.301 87.301 qmmm_elec_gaussian_low_G 6 6.8 86.385 86.385 86.385 86.385 qs_forces 6 3.8 0.001 0.001 35.343 35.343 qs_energies 6 4.8 0.000 0.000 31.363 31.363 scf_env_do_scf 6 5.8 0.001 0.001 29.049 29.049 scf_env_do_scf_inner_loop 39 6.8 0.004 0.004 25.331 25.331 rebuild_ks_matrix 45 8.4 0.000 0.000 24.265 24.265 qs_ks_build_kohn_sham_matrix 45 9.4 0.005 0.005 24.265 24.265 qs_ks_update_qs_env 45 7.8 0.000 0.000 20.718 20.718 pw_transfer 966 12.3 0.058 0.058 17.331 17.331 fft_wrap_pw1pw2 801 13.6 0.006 0.006 17.113 17.113 fft_wrap_pw1pw2_150 507 15.2 2.313 2.313 16.696 16.696 qs_vxc_create 45 10.4 0.001 0.001 13.278 13.278 xc_vxc_pw_create 45 11.4 0.682 0.682 13.277 13.277 xc_pw_derive 270 13.4 0.002 0.002 9.392 9.392 fft3d_s 802 15.6 7.769 7.769 7.777 7.777 qs_rho_update_rho_low 45 7.9 0.000 0.000 7.334 7.334 calculate_rho_elec 45 8.9 0.563 0.563 7.334 7.334 xc_rho_set_and_dset_create 45 12.4 0.577 0.577 6.758 6.758 xc_pw_divergence 45 12.4 0.001 0.001 5.760 5.760 pw_scatter_s 429 15.8 5.683 5.683 5.683 5.683 qmmm_forces 6 3.8 0.001 0.001 5.538 5.538 qmmm_forces_with_gaussian 6 4.8 0.018 0.018 5.200 5.200 pw_integral_ab 2539 7.4 4.540 4.540 4.540 4.540 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 4.443 4.443 qs_ks_ddapc 45 10.4 0.001 0.001 4.211 4.211 init_scf_loop 6 6.8 0.000 0.000 3.707 3.707 qmmm_forces_gaussian_low_G 6 6.8 3.668 3.668 3.668 3.668 sum_up_and_integrate 45 10.4 0.510 0.510 3.624 3.624 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 3.554 3.554 grid_collocate_task_list 45 9.9 3.387 3.387 3.387 3.387 density_rs2pw 45 9.9 0.002 0.002 3.383 3.383 integrate_v_rspace 45 11.4 0.007 0.007 3.114 3.114 ------------------------------------------------------------------------------- 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 0.040 0.061 58.283 58.297 qs_mol_dyn_low 1 2.0 0.003 0.004 57.161 57.221 qs_forces 6 3.8 0.001 0.001 42.383 42.384 qs_energies 6 4.8 0.000 0.000 40.458 40.460 scf_env_do_scf 6 5.8 0.000 0.001 39.461 39.461 scf_env_do_scf_inner_loop 113 6.2 0.002 0.018 37.849 37.850 rebuild_ks_matrix 119 8.1 0.000 0.000 28.204 28.213 qs_ks_build_kohn_sham_matrix 119 9.1 0.016 0.018 28.204 28.212 qs_ks_update_qs_env 119 7.3 0.001 0.001 26.582 26.591 velocity_verlet 5 3.0 0.002 0.004 23.688 23.692 pw_transfer 2446 12.3 0.207 0.229 20.475 21.019 fft_wrap_pw1pw2 2059 13.4 0.024 0.028 20.024 20.572 fft_wrap_pw1pw2_150 1321 14.9 3.280 3.825 19.404 19.957 qs_vxc_create 119 10.1 0.002 0.003 15.464 15.471 xc_vxc_pw_create 119 11.1 0.149 0.217 15.462 15.469 fft3d_ps 2059 15.4 7.627 8.626 13.084 14.712 xc_pw_derive 714 13.1 0.010 0.012 11.909 12.185 qs_rho_update_rho_low 119 7.3 0.000 0.001 11.223 11.228 calculate_rho_elec 119 8.3 0.049 0.058 11.222 11.227 sum_up_and_integrate 119 10.1 0.075 0.086 9.237 9.251 integrate_v_rspace 119 11.1 0.003 0.004 9.162 9.189 xc_pw_divergence 119 12.1 0.005 0.006 7.781 8.020 qmmm_forces 6 3.8 0.002 0.002 7.580 7.580 xc_rho_set_and_dset_create 119 12.1 0.327 0.408 7.300 7.515 qmmm_forces_with_gaussian 6 4.8 0.008 0.010 7.215 7.426 density_rs2pw 119 9.3 0.006 0.008 6.418 6.685 qmmm_el_coupling 6 3.8 0.000 0.000 6.234 6.403 qmmm_elec_with_gaussian 6 4.8 0.003 0.004 6.233 6.401 mp_alltoall_z22v 2059 17.4 4.052 6.372 4.052 6.372 rs_pw_transfer 988 11.5 0.011 0.014 6.017 6.362 potential_pw2rs 119 12.1 0.006 0.007 5.360 5.377 grid_collocate_task_list 119 9.3 4.621 4.992 4.621 4.992 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 4.079 4.151 yz_to_x 964 16.0 0.534 0.701 2.488 3.798 grid_integrate_task_list 119 12.1 3.568 3.766 3.568 3.766 x_to_yz 1095 16.8 0.808 0.889 2.905 3.754 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 3.482 3.518 qmmm_forces_gaussian_low_G 6 6.8 3.356 3.427 3.356 3.427 qmmm_elec_gaussian_low_G 6 6.8 2.886 2.915 2.886 2.915 mp_waitany 4028 12.8 2.241 2.895 2.241 2.895 pw_restrict_s3 18 5.8 1.491 1.593 2.557 2.716 pw_gather_p 964 15.0 2.036 2.363 2.036 2.363 rs_pw_transfer_PW2RS_150 125 13.9 0.726 0.830 2.298 2.355 qs_ks_ddapc 119 10.1 0.002 0.003 2.164 2.268 qmmm_elec_with_gaussian:spline 6 5.8 0.000 0.000 2.097 2.264 pw_prolongate_s3 18 6.8 1.162 1.221 2.097 2.263 rs_pw_transfer_RS2PW_150 125 11.2 0.554 0.662 1.745 2.086 qs_scf_new_mos 113 7.2 0.000 0.000 2.022 2.028 qs_scf_loop_do_ot 113 8.2 0.000 0.000 2.021 2.027 ot_scf_mini 113 9.2 0.001 0.001 1.938 1.943 dbcsr_multiply_generic 2588 12.3 0.058 0.059 1.822 1.850 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 1.639 1.639 init_scf_loop 6 6.8 0.000 0.000 1.609 1.609 pw_scatter_p 1095 15.8 1.552 1.589 1.552 1.589 pw_integral_ab 2761 7.7 1.163 1.308 1.427 1.560 mp_sum_d 5822 12.2 0.774 1.515 0.774 1.515 mp_waitall_1 177795 16.4 1.041 1.264 1.041 1.264 ot_mini 113 10.2 0.000 0.000 1.186 1.192 mp_sum_dm3 33 5.7 1.120 1.185 1.120 1.185 ------------------------------------------------------------------------------- Plot: name="MQAE_single_node_timings_32omp", title="Timings of MQAE_single_node with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="MQAE_single_node_timings_32omp", name="rest", label="rest", y=22.096999999999966, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=86.385, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_s", label="fft3d_s", y=7.769, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_scatter_s", label="pw_scatter_s", y=5.683, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_integral_ab", label="pw_integral_ab", y=4.54, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.668, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=3.387, 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=31.01, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=2.886, 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=1.163, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.356, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=4.621, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=7.627, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=4.052, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=3.568, yerr=0.0 Summary: Performance test took 36 minutes. Status: OK Removing intermediate container 9e3730199841 ---> 8fefd27a9f00 Step 41/42 : CMD cat $(find ./report.log -mmin +10) | sed '/^Summary:/ s/$/ (cached)/' ---> Running in f450215ebc1b Removing intermediate container f450215ebc1b ---> fa7415459061 Step 42/42 : ENTRYPOINT [] ---> Running in ac58b98868dc Removing intermediate container ac58b98868dc ---> 919291c72318 [Warning] One or more build-args [GIT_COMMIT_SHA] were not consumed Successfully built 919291c72318 Successfully tagged us-central1-docker.pkg.dev/cp2k-org-project/cp2kci/img_cp2k-perf-openmp:master Pushing new image... done. #################### Running Image cp2k-perf-openmp #################### Uploading artifacts... done EndDate: 2023-03-21 12:32:22+00:00