StartDate: 2023-06-16 13:03:41+00:00 CpuId: 32x AMD EPYC (3rd Gen) (Milan) [Zen 3], 7nm (SMT disabled) CommitSHA: 7e92e2ab9bf27c2a5bb388384f6c7748634383a1 CommitTime: 2023-06-16 11:01:01 +0200 CommitAuthor: Juerg Hutter CommitSubject: TDDFPT: Improved state following (#2827) #################### Building Image cp2k-perf-openmp #################### Dockerfile: /tools/docker/Dockerfile.test_performance Build-Path: / Build-Args: GIT_COMMIT_SHA=7e92e2ab9bf27c2a5bb388384f6c7748634383a1 Build-Cache: Yes Populating docker build cache... done. DEPRECATED: The legacy builder is deprecated and will be removed in a future release. BuildKit is currently disabled; enable it by removing the DOCKER_BUILDKIT=0 environment-variable. Sending build context to Docker daemon 371MB Step 1/42 : FROM ubuntu:22.04 22.04: Pulling from library/ubuntu 6b851dcae6ca: Pulling fs layer 6b851dcae6ca: Verifying Checksum 6b851dcae6ca: Download complete 6b851dcae6ca: Pull complete Digest: sha256:2a357c4bd54822267339e601ae86ee3966723bdbcae640a70ace622cc9470c83 Status: Downloaded newer image for ubuntu:22.04 ---> 99284ca6cea0 Step 2/42 : WORKDIR /opt/cp2k-toolchain ---> Using cache ---> a4b0c172f62f Step 3/42 : COPY ./tools/toolchain/install_requirements*.sh ./ ---> Using cache ---> 6bb3b047e99c Step 4/42 : RUN ./install_requirements.sh ubuntu:22.04 ---> Using cache ---> 73d80ef9e4a3 Step 5/42 : RUN mkdir scripts ---> Using cache ---> b7df9fba15d6 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 ---> 5c15e99590c4 Step 7/42 : COPY ./tools/toolchain/install_cp2k_toolchain.sh . ---> Using cache ---> d49e3391ce09 Step 8/42 : RUN ./install_cp2k_toolchain.sh --install-all --with-gcc=system --dry-run ---> Using cache ---> fda0d3a90bfc Step 9/42 : COPY ./tools/toolchain/scripts/stage0/ ./scripts/stage0/ ---> Using cache ---> 11c1a44a6047 Step 10/42 : RUN ./scripts/stage0/install_stage0.sh && rm -rf ./build ---> Using cache ---> c0966e1e9481 Step 11/42 : COPY ./tools/toolchain/scripts/stage1/ ./scripts/stage1/ ---> Using cache ---> 2ca131548388 Step 12/42 : RUN ./scripts/stage1/install_stage1.sh && rm -rf ./build ---> Using cache ---> e81a3481b9f8 Step 13/42 : COPY ./tools/toolchain/scripts/stage2/ ./scripts/stage2/ ---> Using cache ---> e4cc5157ace6 Step 14/42 : RUN ./scripts/stage2/install_stage2.sh && rm -rf ./build ---> Using cache ---> fce6a9f1c0f0 Step 15/42 : COPY ./tools/toolchain/scripts/stage3/ ./scripts/stage3/ ---> Using cache ---> 0eb272416f09 Step 16/42 : RUN ./scripts/stage3/install_stage3.sh && rm -rf ./build ---> Using cache ---> ab39849e6cd3 Step 17/42 : COPY ./tools/toolchain/scripts/stage4/ ./scripts/stage4/ ---> Using cache ---> 048080f34045 Step 18/42 : RUN ./scripts/stage4/install_stage4.sh && rm -rf ./build ---> Using cache ---> 0b08afc0fcfe Step 19/42 : COPY ./tools/toolchain/scripts/stage5/ ./scripts/stage5/ ---> Using cache ---> 6c655de08775 Step 20/42 : RUN ./scripts/stage5/install_stage5.sh && rm -rf ./build ---> Using cache ---> 1ee5494fa729 Step 21/42 : COPY ./tools/toolchain/scripts/stage6/ ./scripts/stage6/ ---> Using cache ---> 5a84c2e51c14 Step 22/42 : RUN ./scripts/stage6/install_stage6.sh && rm -rf ./build ---> Using cache ---> cc892a5b70ae Step 23/42 : COPY ./tools/toolchain/scripts/stage7/ ./scripts/stage7/ ---> Using cache ---> 588f1d001230 Step 24/42 : RUN ./scripts/stage7/install_stage7.sh && rm -rf ./build ---> Using cache ---> ccc47b63a296 Step 25/42 : COPY ./tools/toolchain/scripts/stage8/ ./scripts/stage8/ ---> Using cache ---> 5cd1606b56e2 Step 26/42 : RUN ./scripts/stage8/install_stage8.sh && rm -rf ./build ---> Using cache ---> 91dbd0c04011 Step 27/42 : COPY ./tools/toolchain/scripts/arch_base.tmpl ./tools/toolchain/scripts/generate_arch_files.sh ./scripts/ ---> Using cache ---> 7130f6458206 Step 28/42 : RUN ./scripts/generate_arch_files.sh && rm -rf ./build ---> Using cache ---> 977895808b97 Step 29/42 : WORKDIR /opt/cp2k ---> Using cache ---> ef198c6c6fd6 Step 30/42 : COPY ./Makefile . ---> Using cache ---> 7c8ed37bf246 Step 31/42 : COPY ./src ./src ---> Using cache ---> abdd344e950d Step 32/42 : COPY ./exts ./exts ---> Using cache ---> f005b6909d32 Step 33/42 : COPY ./tools/build_utils ./tools/build_utils ---> Using cache ---> b805dbdb3b84 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 8d2c9c865321 './arch/local.psmp' -> '/opt/cp2k-toolchain/install/arch/local.psmp' Compiling cp2k... Removing intermediate container 8d2c9c865321 ---> e7d0cd46dca9 Step 35/42 : COPY ./data ./data ---> 718e6a9d3848 Step 36/42 : COPY ./tests ./tests ---> 1a7e27ad80f0 Step 37/42 : COPY ./tools/regtesting ./tools/regtesting ---> 8fcede500aed Step 38/42 : COPY ./benchmarks ./benchmarks ---> e4d37c71e371 Step 39/42 : COPY ./tools/docker/scripts/test_performance.sh ./tools/docker/scripts/plot_performance.py ./ ---> 32053c86c004 Step 40/42 : RUN ./test_performance.sh "local" 2>&1 | tee report.log ---> Running in c40b384523c0 ========== 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 0.036 0.036 87.172 87.172 qs_mol_dyn_low 1 2.0 0.003 0.003 86.559 86.559 qs_forces 11 3.9 0.001 0.001 86.520 86.520 qs_energies 11 4.9 0.001 0.001 80.509 80.509 scf_env_do_scf 11 5.9 0.001 0.001 69.543 69.543 velocity_verlet 10 3.0 0.002 0.002 56.517 56.517 scf_env_do_scf_inner_loop 108 6.5 0.011 0.011 53.087 53.087 rebuild_ks_matrix 119 8.3 0.001 0.001 20.079 20.079 qs_ks_build_kohn_sham_matrix 119 9.3 0.012 0.012 20.079 20.079 qs_scf_new_mos 108 7.5 0.001 0.001 19.473 19.473 qs_scf_loop_do_ot 108 8.5 0.001 0.001 19.472 19.472 dbcsr_multiply_generic 2286 12.5 0.159 0.159 19.358 19.358 qs_rho_update_rho_low 119 7.7 0.001 0.001 18.900 18.900 calculate_rho_elec 119 8.7 0.946 0.946 18.899 18.899 qs_ks_update_qs_env 119 7.6 0.001 0.001 18.427 18.427 ot_scf_mini 108 9.5 0.002 0.002 18.185 18.185 init_scf_loop 11 6.9 0.000 0.000 16.300 16.300 grid_collocate_task_list 119 9.7 14.551 14.551 14.551 14.551 prepare_preconditioner 11 7.9 0.000 0.000 13.861 13.861 make_preconditioner 11 8.9 0.000 0.000 13.861 13.861 sum_up_and_integrate 119 10.3 0.782 0.782 13.195 13.195 make_full_inverse_cholesky 11 9.9 0.030 0.030 12.678 12.678 integrate_v_rspace 119 11.3 0.090 0.090 12.413 12.413 ot_mini 108 10.5 0.001 0.001 11.447 11.447 make_m2s 4572 13.5 0.045 0.045 10.788 10.788 grid_integrate_task_list 119 12.3 10.479 10.479 10.479 10.479 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 6.525 6.525 qs_ot_get_derivative 108 11.5 0.001 0.001 6.069 6.069 pw_transfer 1439 11.6 0.061 0.061 5.873 5.873 dbcsr_make_dense_low 5837 15.5 0.068 0.068 5.706 5.706 fft_wrap_pw1pw2 1201 12.6 0.006 0.006 5.676 5.676 make_dense_data 5837 16.5 5.142 5.142 5.624 5.624 make_images 4572 14.5 2.146 2.146 5.497 5.497 ot_diis_step 108 11.5 0.004 0.004 5.375 5.375 dbcsr_make_images_dense 3978 14.8 0.017 0.017 4.984 4.984 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 4.894 4.894 apply_single 119 13.6 0.000 0.000 4.894 4.894 fft_wrap_pw1pw2_140 487 13.2 0.437 0.437 4.857 4.857 multiply_cannon 2286 13.5 0.175 0.175 4.632 4.632 cp_fm_cholesky_decompose 22 10.9 4.356 4.356 4.356 4.356 multiply_cannon_loop 2286 14.5 0.046 0.046 4.166 4.166 cp_fm_cholesky_invert 11 10.9 4.138 4.138 4.138 4.138 multiply_cannon_multrec 2286 15.5 4.072 4.072 4.119 4.119 init_scf_run 11 5.9 0.002 0.002 3.829 3.829 scf_env_initial_rho_setup 11 6.9 0.000 0.000 3.827 3.827 dbcsr_complete_redistribute 329 12.2 1.918 1.918 3.681 3.681 dbcsr_copy 2102 12.0 0.224 0.224 3.660 3.660 qs_env_update_s_mstruct 11 6.9 0.000 0.000 3.593 3.593 qs_ot_get_p 119 10.4 0.001 0.001 3.407 3.407 density_rs2pw 119 9.7 0.005 0.005 3.402 3.402 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 3.402 3.402 dbcsr_copy_into_existing 22 7.9 3.379 3.379 3.380 3.380 wfi_extrapolate 11 7.9 0.001 0.001 3.361 3.361 qs_create_task_list 11 7.9 0.000 0.000 3.215 3.215 generate_qs_task_list 11 8.9 1.966 1.966 3.215 3.215 copy_dbcsr_to_fm 153 11.3 0.002 0.002 3.018 3.018 fft3d_s 1202 14.6 2.755 2.755 2.759 2.759 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 2.607 2.607 build_core_hamiltonian_matrix 11 6.9 0.000 0.000 2.506 2.506 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.332 2.332 dbcsr_data_release 279532 16.0 2.096 2.096 2.096 2.096 pw_poisson_solve 119 10.3 0.331 0.331 1.974 1.974 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 1.913 1.913 copy_fm_to_dbcsr 176 11.2 0.001 0.001 1.879 1.879 qs_ot_get_derivative_taylor 59 13.0 0.001 0.001 1.852 1.852 potential_pw2rs 119 12.3 0.046 0.046 1.844 1.844 dbcsr_finalize 5186 13.8 0.092 0.092 1.765 1.765 ------------------------------------------------------------------------------- From /workspace/artifacts/H2O-64_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.009 0.025 46.895 46.904 qs_mol_dyn_low 1 2.0 0.003 0.004 46.749 46.753 qs_forces 11 3.9 0.001 0.001 46.709 46.709 qs_energies 11 4.9 0.001 0.001 43.779 43.780 scf_env_do_scf 11 5.9 0.000 0.002 40.134 40.134 scf_env_do_scf_inner_loop 108 6.5 0.003 0.019 37.065 37.065 velocity_verlet 10 3.0 0.002 0.003 27.495 27.496 rebuild_ks_matrix 119 8.3 0.001 0.001 16.853 16.943 qs_ks_build_kohn_sham_matrix 119 9.3 0.017 0.021 16.852 16.943 qs_ks_update_qs_env 119 7.6 0.001 0.001 15.009 15.092 dbcsr_multiply_generic 2286 12.5 0.076 0.081 13.776 13.948 qs_rho_update_rho_low 119 7.7 0.001 0.001 13.327 13.334 calculate_rho_elec 119 8.7 0.031 0.034 13.326 13.333 sum_up_and_integrate 119 10.3 0.033 0.036 12.480 12.513 integrate_v_rspace 119 11.3 0.004 0.005 12.446 12.479 qs_scf_new_mos 108 7.5 0.001 0.001 11.500 11.608 qs_scf_loop_do_ot 108 8.5 0.001 0.001 11.500 11.607 ot_scf_mini 108 9.5 0.002 0.002 10.865 10.970 multiply_cannon 2286 13.5 0.165 0.182 10.248 10.602 multiply_cannon_loop 2286 14.5 0.118 0.134 9.662 10.048 grid_collocate_task_list 119 9.7 8.787 9.140 8.787 9.140 grid_integrate_task_list 119 12.3 7.984 8.741 7.984 8.741 mp_waitall_1 158411 16.6 7.765 8.211 7.765 8.211 multiply_cannon_metrocomm3 18288 15.5 0.055 0.061 6.051 6.527 ot_mini 108 10.5 0.001 0.001 5.894 6.009 rs_pw_transfer 974 11.9 0.013 0.015 4.309 4.727 density_rs2pw 119 9.7 0.006 0.007 3.919 4.348 pw_transfer 1439 11.6 0.095 0.100 4.284 4.342 fft_wrap_pw1pw2 1201 12.6 0.009 0.010 4.123 4.184 fft_wrap_pw1pw2_140 487 13.2 0.694 0.737 3.607 3.745 potential_pw2rs 119 12.3 0.007 0.007 3.510 3.518 multiply_cannon_multrec 18288 15.5 3.207 3.416 3.218 3.430 qs_ot_get_derivative 108 11.5 0.001 0.001 2.989 3.095 init_scf_loop 11 6.9 0.000 0.001 3.052 3.052 apply_preconditioner_dbcsr 119 12.6 0.000 0.000 2.888 2.981 apply_single 119 13.6 0.000 0.001 2.888 2.981 ot_diis_step 108 11.5 0.003 0.004 2.890 2.890 fft3d_ps 1201 14.6 1.386 1.519 2.646 2.772 init_scf_run 11 5.9 0.000 0.004 2.597 2.597 scf_env_initial_rho_setup 11 6.9 0.000 0.003 2.596 2.597 make_m2s 4572 13.5 0.047 0.057 2.510 2.561 wfi_extrapolate 11 7.9 0.001 0.001 2.356 2.356 make_images 4572 14.5 0.118 0.125 2.164 2.215 qs_ot_get_p 119 10.4 0.001 0.001 1.973 2.093 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 1.967 1.976 mp_waitany 9880 13.7 1.339 1.773 1.339 1.773 mp_alltoall_d11v 2130 13.8 1.194 1.484 1.194 1.484 rs_pw_transfer_RS2PW_140 130 11.5 0.230 0.293 1.007 1.428 make_images_data 4572 15.5 0.037 0.043 1.228 1.319 rs_pw_transfer_PW2RS_140 130 13.9 0.425 0.447 1.240 1.297 prepare_preconditioner 11 7.9 0.000 0.000 1.200 1.216 make_preconditioner 11 8.9 0.000 0.000 1.200 1.216 hybrid_alltoall_any 4725 16.4 0.072 0.213 1.101 1.213 rs_gather_matrices 119 12.3 0.090 0.106 0.894 1.185 qs_ot_p2m_diag 50 11.0 0.006 0.006 1.158 1.159 make_full_inverse_cholesky 11 9.9 0.000 0.000 1.087 1.102 mp_alltoall_z22v 1201 16.6 0.993 1.081 0.993 1.081 cp_dbcsr_syevd 50 12.0 0.005 0.006 1.065 1.065 cp_fm_diag_elpa 50 13.0 0.000 0.000 1.028 1.030 cp_fm_diag_elpa_base 50 14.0 1.023 1.025 1.026 1.029 qs_ot_get_derivative_diag 49 12.0 0.001 0.001 0.968 1.026 qs_ot_get_derivative_taylor 59 13.0 0.001 0.001 0.933 0.992 cp_dbcsr_sm_fm_multiply 37 9.5 0.001 0.001 0.978 0.979 ------------------------------------------------------------------------------- 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=44.434, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=14.551, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=10.479, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="make_dense_data", label="make_dense_data", y=5.142, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=4.356, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=4.138, yerr=0.0 PlotPoint: plot="H2O-64_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=4.072, 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="fft3d_ps", label="fft3d_ps", 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=17.766000000000002, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=8.787, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=7.984, 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="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=0.0, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=3.207, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=7.765, yerr=0.0 PlotPoint: plot="H2O-64_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=1.386, yerr=0.0 Running H2O-64_nonortho.inp with 1 threads and 32 ranks... done. Running H2O-64_nonortho.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/H2O-64_nonortho_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.033 0.033 110.859 110.859 qs_mol_dyn_low 1 2.0 0.002 0.002 110.143 110.143 qs_forces 11 3.9 0.001 0.001 110.104 110.104 qs_energies 11 4.9 0.001 0.001 102.480 102.480 scf_env_do_scf 11 5.9 0.001 0.001 89.596 89.596 scf_env_do_scf_inner_loop 96 6.5 0.010 0.010 71.544 71.544 velocity_verlet 10 3.0 0.002 0.002 71.301 71.301 rebuild_ks_matrix 107 8.3 0.001 0.001 33.874 33.874 qs_ks_build_kohn_sham_matrix 107 9.3 0.011 0.011 33.873 33.873 qs_rho_update_rho_low 107 7.7 0.000 0.000 30.897 30.897 calculate_rho_elec 107 8.7 0.852 0.852 30.897 30.897 qs_ks_update_qs_env 107 7.6 0.001 0.001 30.512 30.512 sum_up_and_integrate 107 10.3 0.703 0.703 27.103 27.103 grid_collocate_task_list 107 9.7 26.835 26.835 26.835 26.835 integrate_v_rspace 107 11.3 0.080 0.080 26.399 26.399 grid_integrate_task_list 107 12.3 24.404 24.404 24.404 24.404 init_scf_loop 11 6.9 0.000 0.000 17.889 17.889 dbcsr_multiply_generic 1966 12.4 0.140 0.140 17.378 17.378 qs_scf_new_mos 96 7.5 0.001 0.001 16.852 16.852 qs_scf_loop_do_ot 96 8.5 0.000 0.000 16.851 16.851 ot_scf_mini 96 9.5 0.002 0.002 15.682 15.682 prepare_preconditioner 11 7.9 0.000 0.000 13.792 13.792 make_preconditioner 11 8.9 0.000 0.000 13.792 13.792 make_full_inverse_cholesky 11 9.9 0.031 0.031 12.628 12.628 ot_mini 96 10.5 0.001 0.001 10.117 10.117 make_m2s 3932 13.4 0.039 0.039 9.601 9.601 qs_energies_init_hamiltonians 11 5.9 0.000 0.000 7.035 7.035 pw_transfer 1295 11.6 0.056 0.056 5.863 5.863 fft_wrap_pw1pw2 1081 12.6 0.006 0.006 5.648 5.648 qs_ot_get_derivative 96 11.5 0.001 0.001 5.340 5.340 init_scf_run 11 5.9 0.002 0.002 5.220 5.220 scf_env_initial_rho_setup 11 6.9 0.000 0.000 5.218 5.218 dbcsr_make_dense_low 4961 15.5 0.059 0.059 5.044 5.044 make_dense_data 4961 16.5 4.524 4.524 4.974 4.974 make_images 3932 14.4 1.901 1.901 4.888 4.888 fft_wrap_pw1pw2_140 439 13.2 0.487 0.487 4.802 4.802 ot_diis_step 96 11.5 0.003 0.003 4.774 4.774 wfi_extrapolate 11 7.9 0.001 0.001 4.629 4.629 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 4.454 4.454 apply_single 107 13.6 0.000 0.000 4.454 4.454 dbcsr_make_images_dense 3386 14.7 0.014 0.014 4.451 4.451 cp_fm_cholesky_decompose 22 10.9 4.324 4.324 4.324 4.324 multiply_cannon 1966 13.4 0.152 0.152 4.234 4.234 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 4.224 4.224 cp_fm_cholesky_invert 11 10.9 4.047 4.047 4.047 4.047 qs_env_update_s_mstruct 11 6.9 0.000 0.000 4.026 4.026 multiply_cannon_loop 1966 14.4 0.043 0.043 3.838 3.838 multiply_cannon_multrec 1966 15.4 3.754 3.754 3.795 3.795 dbcsr_complete_redistribute 317 12.2 1.907 1.907 3.754 3.754 dbcsr_copy 1855 11.9 0.229 0.229 3.734 3.734 qs_create_task_list 11 7.9 0.000 0.000 3.642 3.642 generate_qs_task_list 11 8.9 2.385 2.385 3.642 3.642 dbcsr_copy_into_existing 22 7.9 3.471 3.471 3.471 3.471 build_core_hamiltonian_matrix_ 11 4.9 0.000 0.000 3.398 3.398 density_rs2pw 107 9.7 0.004 0.004 3.210 3.210 copy_dbcsr_to_fm 147 11.2 0.002 0.002 3.065 3.065 fft3d_s 1082 14.6 2.805 2.805 2.847 2.847 build_core_hamiltonian_matrix 11 6.9 0.000 0.000 2.590 2.590 qs_ot_get_p 107 10.4 0.001 0.001 2.507 2.507 transfer_dbcsr_to_fm 11 10.9 0.000 0.000 2.379 2.379 ------------------------------------------------------------------------------- From /workspace/artifacts/H2O-64_nonortho_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.009 0.022 71.724 71.734 qs_mol_dyn_low 1 2.0 0.003 0.003 71.586 71.590 qs_forces 11 3.9 0.001 0.002 71.546 71.547 qs_energies 11 4.9 0.001 0.001 66.718 66.720 scf_env_do_scf 11 5.9 0.000 0.002 61.395 61.395 scf_env_do_scf_inner_loop 96 6.5 0.002 0.016 56.747 56.747 velocity_verlet 10 3.0 0.001 0.003 42.633 42.634 rebuild_ks_matrix 107 8.3 0.000 0.001 30.653 30.724 qs_ks_build_kohn_sham_matrix 107 9.3 0.014 0.018 30.653 30.723 qs_ks_update_qs_env 107 7.6 0.001 0.001 26.911 26.977 sum_up_and_integrate 107 10.3 0.032 0.036 26.790 26.814 integrate_v_rspace 107 11.3 0.004 0.004 26.758 26.788 qs_rho_update_rho_low 107 7.7 0.001 0.001 25.693 25.701 calculate_rho_elec 107 8.7 0.028 0.036 25.693 25.700 grid_integrate_task_list 107 12.3 22.670 23.048 22.670 23.048 grid_collocate_task_list 107 9.7 21.547 21.901 21.547 21.901 dbcsr_multiply_generic 1966 12.4 0.068 0.074 12.244 12.395 qs_scf_new_mos 96 7.5 0.001 0.001 9.829 9.888 qs_scf_loop_do_ot 96 8.5 0.001 0.001 9.829 9.888 multiply_cannon 1966 13.4 0.145 0.159 9.131 9.365 ot_scf_mini 96 9.5 0.002 0.002 9.289 9.352 multiply_cannon_loop 1966 14.4 0.095 0.112 8.630 8.940 mp_waitall_1 136719 16.5 7.122 7.705 7.122 7.705 multiply_cannon_metrocomm3 15728 15.4 0.042 0.049 5.466 5.967 ot_mini 96 10.5 0.001 0.001 5.285 5.354 rs_pw_transfer 878 11.9 0.010 0.014 4.242 4.936 init_scf_loop 11 6.9 0.000 0.000 4.631 4.632 density_rs2pw 107 9.7 0.005 0.006 3.582 4.255 init_scf_run 11 5.9 0.000 0.004 3.941 3.941 scf_env_initial_rho_setup 11 6.9 0.000 0.003 3.940 3.941 qs_ks_update_qs_env_forces 11 4.9 0.000 0.000 3.857 3.864 pw_transfer 1295 11.6 0.077 0.085 3.607 3.731 fft_wrap_pw1pw2 1081 12.6 0.008 0.014 3.472 3.582 wfi_extrapolate 11 7.9 0.001 0.001 3.524 3.525 potential_pw2rs 107 12.3 0.005 0.006 3.211 3.232 fft_wrap_pw1pw2_140 439 13.2 0.535 0.645 2.979 3.148 multiply_cannon_multrec 15728 15.4 2.811 3.117 2.821 3.127 apply_preconditioner_dbcsr 107 12.6 0.000 0.000 2.663 2.744 apply_single 107 13.6 0.000 0.001 2.663 2.744 qs_ot_get_derivative 96 11.5 0.001 0.001 2.643 2.707 ot_diis_step 96 11.5 0.003 0.004 2.628 2.628 fft3d_ps 1081 14.6 1.153 1.346 2.257 2.438 mp_waitany 8968 13.7 1.592 2.433 1.592 2.433 make_m2s 3932 13.4 0.040 0.044 2.176 2.242 make_images 3932 14.4 0.104 0.107 1.883 1.944 rs_pw_transfer_RS2PW_140 118 11.5 0.177 0.223 1.156 1.852 mp_alltoall_d11v 1998 13.7 1.085 1.845 1.085 1.845 rs_gather_matrices 107 12.3 0.087 0.105 0.819 1.545 qs_ot_get_p 107 10.4 0.001 0.001 1.405 1.491 ------------------------------------------------------------------------------- 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=42.97099999999999, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=26.835, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=24.404, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="make_dense_data", label="make_dense_data", y=4.524, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_decompose", label="cp_fm_cholesky_decompose", y=4.324, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="cp_fm_cholesky_invert", label="cp_fm_cholesky_invert", y=4.047, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=3.754, 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=15.982000000000006, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=21.547, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=22.67, 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=2.811, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitany", label="mp_waitany", y=1.592, yerr=0.0 PlotPoint: plot="H2O-64_nonortho_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=7.122, 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 0.232 0.232 104.281 104.281 qs_energies 1 2.0 0.000 0.000 103.417 103.417 scf_env_do_scf 1 3.0 0.000 0.000 102.164 102.164 qs_ks_update_qs_env 8 5.0 0.000 0.000 97.259 97.259 rebuild_ks_matrix 7 6.0 0.000 0.000 97.205 97.205 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.001 97.205 97.205 hfx_ks_matrix 7 8.0 0.000 0.000 88.305 88.305 integrate_four_center 7 9.0 1.563 1.563 88.282 88.282 integrate_four_center_main 7 10.0 0.575 0.575 80.851 80.851 integrate_four_center_bin 448 11.0 80.276 80.276 80.276 80.276 scf_env_do_scf_inner_loop 7 4.0 0.001 0.001 56.612 56.612 init_scf_loop 1 4.0 0.000 0.000 45.542 45.542 integrate_four_center_load 7 10.0 0.000 0.000 5.626 5.626 hfx_load_balance 1 11.0 0.001 0.001 5.626 5.626 qs_vxc_create 14 8.0 0.000 0.000 3.161 3.161 xc_vxc_pw_create 14 9.0 0.117 0.117 3.161 3.161 hfx_load_balance_count 1 12.0 2.808 2.808 2.808 2.808 hfx_load_balance_bin 1 12.0 2.801 2.801 2.801 2.801 calculate_rho_elec 15 7.4 0.118 0.118 2.490 2.490 xc_rho_set_and_dset_create 14 10.0 0.090 0.090 2.432 2.432 prepare_preconditioner 1 5.0 0.000 0.000 2.261 2.261 make_preconditioner 1 6.0 0.000 0.000 2.261 2.261 admm_mo_calc_rho_aux 7 8.0 0.000 0.000 2.189 2.189 ------------------------------------------------------------------------------- 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 0.225 0.246 95.657 95.669 qs_energies 1 2.0 0.000 0.000 95.175 95.181 scf_env_do_scf 1 3.0 0.000 0.000 94.839 94.839 qs_ks_update_qs_env 8 5.0 0.000 0.000 92.827 92.827 rebuild_ks_matrix 7 6.0 0.000 0.000 92.819 92.819 qs_ks_build_kohn_sham_matrix 7 7.0 0.001 0.001 92.819 92.819 hfx_ks_matrix 7 8.0 0.000 0.000 87.320 87.321 integrate_four_center 7 9.0 0.052 0.332 87.312 87.313 integrate_four_center_main 7 10.0 0.003 0.003 78.612 79.983 integrate_four_center_bin 448 11.0 78.609 79.980 78.609 79.980 scf_env_do_scf_inner_loop 7 4.0 0.000 0.001 53.404 53.404 init_scf_loop 1 4.0 0.000 0.000 41.433 41.434 integrate_four_center_load 7 10.0 0.000 0.000 5.665 5.666 hfx_load_balance 1 11.0 0.001 0.001 5.665 5.666 mp_sync 56 11.2 2.378 3.636 2.378 3.636 hfx_load_balance_bin 1 12.0 2.761 2.833 2.761 2.833 hfx_load_balance_count 1 12.0 2.761 2.827 2.761 2.827 qs_vxc_create 14 8.0 0.000 0.000 2.453 2.453 xc_vxc_pw_create 14 9.0 0.007 0.007 2.452 2.452 xc_rho_set_and_dset_create 14 10.0 0.009 0.010 1.940 2.054 ------------------------------------------------------------------------------- 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=16.025999999999996, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_bin", label="integrate_four_center_bin", y=80.276, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_count", label="hfx_load_balance_count", y=2.808, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=2.801, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center", label="integrate_four_center", y=1.563, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="integrate_four_center_main", label="integrate_four_center_main", y=0.575, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32omp", name="CP2K", label="CP2K", y=0.232, 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=8.86800000000001, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center_bin", label="integrate_four_center_bin", y=78.609, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_count", label="hfx_load_balance_count", y=2.761, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="hfx_load_balance_bin", label="hfx_load_balance_bin", y=2.761, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="integrate_four_center", label="integrate_four_center", y=0.052, 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=0.225, yerr=0.0 PlotPoint: plot="H2O-hyb_timings_32mpi", name="mp_sync", label="mp_sync", y=2.378, yerr=0.0 Running GW_PBE_4benzene.inp with 1 threads and 32 ranks... done. Running GW_PBE_4benzene.inp with 32 threads and 1 ranks... done. From /workspace/artifacts/GW_PBE_4benzene_32omp.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.014 0.014 76.468 76.468 qs_energies 1 2.0 0.000 0.000 76.075 76.075 mp2_main 1 3.0 0.000 0.000 72.848 72.848 mp2_gpw_main 1 4.0 0.000 0.000 72.735 72.735 rpa_ri_compute_en 1 5.0 0.000 0.000 69.060 69.060 rpa_num_int 1 6.0 0.001 0.001 69.054 69.054 compute_mat_P_omega 1 7.0 0.003 0.003 59.490 59.490 compute_mat_P_omega_contract 10 8.0 8.857 8.857 59.290 59.290 dbt_total 2336 9.6 0.014 0.014 45.552 45.552 dbt_contract 787 11.0 0.042 0.042 38.748 38.748 dbt_tas_total 1149 12.2 0.210 0.210 37.727 37.727 dbt_tas_multiply 807 12.1 0.002 0.002 36.445 36.445 dbt_tas_dbm 807 14.1 0.003 0.003 30.185 30.185 dbm_multiply 807 16.1 30.178 30.178 30.178 30.178 dbt_tas_mm_1N 524 15.1 0.001 0.001 23.162 23.162 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 21.817 21.817 compute_mat_P_omega_calc_M_occ 250 9.0 8.882 8.882 16.717 16.717 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 6.441 6.441 dbt_tas_mm_2 251 15.0 0.001 0.001 5.546 5.546 dbt_copy 1103 10.7 0.071 0.071 5.502 5.502 compute_QP_energies 1 7.0 0.000 0.000 4.924 4.924 compute_self_energy_cubic_gw 1 8.0 0.055 0.055 4.923 4.923 contract_cubic_gw 21 9.0 0.000 0.000 3.936 3.936 mp2_ri_gpw_compute_in 1 5.0 0.001 0.001 3.668 3.668 dbt_tas_reserve_blocks_index 3261 14.3 0.480 0.480 3.570 3.570 dbm_reserve_blocks 3628 15.3 3.159 3.159 3.159 3.159 scf_env_do_scf 1 3.0 0.000 0.000 3.117 3.117 scf_env_do_scf_inner_loop 17 4.0 0.002 0.002 3.117 3.117 dbt_reserve_blocks_index 2280 13.1 0.051 0.051 2.709 2.709 dbt_reserve_blocks_index_array 2222 12.2 0.010 0.010 2.664 2.664 convert_to_new_pgrid 2421 14.1 0.105 0.105 2.201 2.201 dbt_crop 1042 12.0 1.350 1.350 2.193 2.193 dbt_tas_copy 574 11.4 1.273 1.273 2.169 2.169 dbm_copy 1614 15.1 2.096 2.096 2.096 2.096 dbt_tas_reshape 367 15.0 0.007 0.007 1.937 1.937 rpa_num_int_RPA_matrix_operati 10 7.0 0.000 0.000 1.905 1.905 compute_W_cubic_GW 10 7.0 0.004 0.004 1.897 1.897 dbt_reshape 278 11.9 1.019 1.019 1.840 1.840 get_2c_integrals 1 6.0 0.000 0.000 1.735 1.735 qs_scf_new_mos 17 5.0 0.000 0.000 1.589 1.589 ------------------------------------------------------------------------------- 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 0.007 0.025 33.217 33.231 qs_energies 1 2.0 0.000 0.000 32.957 32.958 mp2_main 1 3.0 0.000 0.000 31.885 31.887 mp2_gpw_main 1 4.0 0.000 0.000 31.852 31.853 rpa_ri_compute_en 1 5.0 0.000 0.000 30.600 30.601 rpa_num_int 1 6.0 0.000 0.002 30.599 30.600 dbt_total 2336 9.6 0.014 0.016 27.274 27.287 compute_mat_P_omega 1 7.0 0.001 0.005 26.024 26.049 compute_mat_P_omega_contract 10 8.0 0.386 0.401 25.880 25.883 dbt_contract 787 11.0 0.037 0.039 20.329 20.340 dbt_tas_total 1149 12.2 0.076 0.088 18.006 18.008 dbt_tas_multiply 807 12.1 0.002 0.002 17.926 17.929 dbt_tas_dbm 807 14.1 0.003 0.003 12.586 12.588 dbm_multiply 807 16.1 9.989 10.810 9.989 10.810 compute_mat_P_omega_calc_P_t 250 9.0 0.001 0.001 8.392 8.393 compute_mat_P_omega_calc_M_occ 250 9.0 0.377 0.393 7.339 7.341 dbt_copy 1149 10.8 0.013 0.014 5.915 6.235 dbt_tas_mm_2 251 15.0 0.001 0.001 6.077 6.079 mp_sync 8688 11.6 4.873 5.957 4.873 5.957 dbt_reshape 1136 11.8 2.554 2.748 5.619 5.929 compute_mat_P_omega_calc_M_vir 250 9.0 0.001 0.001 5.029 5.029 dbt_tas_mm_1N 524 15.1 0.001 0.001 4.383 4.874 compute_QP_energies 1 7.0 0.000 0.000 2.968 2.969 compute_self_energy_cubic_gw 1 8.0 0.002 0.003 2.968 2.968 mp_waitall_2 3812 15.3 2.287 2.522 2.287 2.522 dbt_communicate_buffer 1136 12.8 0.051 0.057 2.277 2.449 contract_cubic_gw 21 9.0 0.000 0.000 2.317 2.317 dbt_reserve_blocks_index 2887 13.1 0.063 0.070 1.653 1.874 dbt_reserve_blocks_index_array 2829 12.2 0.008 0.010 1.643 1.863 dbt_tas_reserve_blocks_index 3347 14.5 0.432 0.468 1.638 1.854 dbt_crop 1042 12.0 0.873 0.959 1.391 1.570 dbm_reserve_blocks 3752 15.4 1.292 1.480 1.292 1.480 mp2_ri_gpw_compute_in 1 5.0 0.000 0.001 1.250 1.251 dbt_tas_replicate 405 14.1 0.534 0.703 1.098 1.166 compute_mat_P_omega_copy_M_vir 250 9.0 0.001 0.001 1.074 1.077 mp_sum_l 6165 12.9 0.908 1.027 0.908 1.027 scf_env_do_scf 1 3.0 0.000 0.000 1.022 1.022 scf_env_do_scf_inner_loop 17 4.0 0.000 0.002 1.022 1.022 compute_mat_P_omega_copy_M_occ 250 9.0 0.001 0.001 1.006 1.019 parallel_gemm_fm 105 8.4 0.000 0.000 0.979 0.985 parallel_gemm_fm_cosma 105 9.4 0.978 0.985 0.978 0.985 convert_to_new_pgrid 2421 14.1 0.025 0.029 0.741 0.866 dbm_copy 1608 15.1 0.711 0.836 0.711 0.836 mp_max_i 2002 9.8 0.688 0.817 0.688 0.817 compute_W_cubic_GW 10 7.0 0.001 0.001 0.743 0.748 ------------------------------------------------------------------------------- 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=22.277000000000008, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=30.178, 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=8.882, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=8.857, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=3.159, 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=1.019, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="mp_waitall_2", label="mp_waitall_2", y=0.0, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32omp", name="mp_sync", label="mp_sync", y=0.0, yerr=0.0 Plot: name="GW_PBE_4benzene_timings_32mpi", title="Timings of GW_PBE_4benzene with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="rest", label="rest", y=10.747999999999998, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=9.989, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="compute_mat_P_omega_calc_M_occ", label="compute_mat_P_omega_calc_M_occ", y=0.377, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="compute_mat_P_omega_contract", label="compute_mat_P_omega_contract", y=0.386, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=1.292, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbm_copy", label="dbm_copy", y=0.711, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=2.554, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.287, yerr=0.0 PlotPoint: plot="GW_PBE_4benzene_timings_32mpi", name="mp_sync", label="mp_sync", y=4.873, 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 0.023 0.023 241.700 241.700 qs_forces 1 2.0 0.000 0.000 241.113 241.113 rebuild_ks_matrix 7 6.6 0.000 0.000 239.680 239.680 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.001 239.680 239.680 hfx_ks_matrix 7 8.6 0.000 0.000 237.396 237.396 hfx_ri_update_ks 7 9.6 0.000 0.000 195.796 195.796 hfx_ri_update_ks_Pmat 7 10.6 31.408 31.408 195.767 195.767 dbt_total 809 11.0 0.006 0.006 182.737 182.737 qs_energies 1 3.0 0.000 0.000 175.442 175.442 scf_env_do_scf 1 4.0 0.000 0.000 175.120 175.120 qs_ks_update_qs_env 8 6.0 0.000 0.000 174.060 174.060 dbt_contract 207 12.4 0.079 0.079 163.630 163.630 dbt_tas_total 343 13.7 1.529 1.529 161.953 161.953 dbt_tas_multiply 216 13.5 0.001 0.001 158.502 158.502 dbt_tas_dbm 216 15.5 0.001 0.001 146.569 146.569 dbm_multiply 216 17.5 146.566 146.566 146.566 146.566 hfx_ri_update_ks_Pmat_KS 63 11.6 0.000 0.000 140.402 140.402 dbt_tas_mm_2 91 16.5 0.001 0.001 132.375 132.375 scf_env_do_scf_inner_loop 6 5.0 0.001 0.001 107.432 107.432 init_scf_loop 2 5.0 0.000 0.000 67.686 67.686 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 65.623 65.623 hfx_ri_update_forces 1 7.0 1.658 1.658 41.581 41.581 hfx_ri_forces_Pmat_3c 1 8.0 4.855 4.855 24.113 24.113 dbt_copy 409 11.7 0.030 0.030 15.648 15.648 precalc_derivatives 1 8.0 2.231 2.231 13.391 13.391 dbt_reshape 132 13.2 6.944 6.944 11.103 11.103 dbt_tas_mm_3T 77 17.1 0.000 0.000 9.723 9.723 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 9.318 9.318 dbt_tas_reserve_blocks_index 1255 15.4 1.025 1.025 7.575 7.575 build_3c_derivatives 3 9.0 2.704 2.704 7.446 7.446 dbm_reserve_blocks 1397 16.3 6.786 6.786 6.786 6.786 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 6.705 6.705 dbt_reserve_blocks_index 818 14.4 0.095 0.095 5.862 5.862 dbt_reserve_blocks_index_array 795 13.4 0.007 0.007 5.764 5.764 ------------------------------------------------------------------------------- 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 0.008 0.026 49.571 49.581 qs_forces 1 2.0 0.000 0.000 49.386 49.387 rebuild_ks_matrix 7 6.6 0.000 0.000 48.501 48.502 qs_ks_build_kohn_sham_matrix 7 7.6 0.001 0.001 48.501 48.502 hfx_ks_matrix 7 8.6 0.000 0.000 47.491 47.497 dbt_total 809 11.0 0.006 0.006 42.469 42.481 dbt_contract 207 12.4 0.023 0.024 32.733 32.784 hfx_ri_update_ks 7 9.6 0.000 0.000 29.047 29.047 hfx_ri_update_ks_Pmat 7 10.6 1.172 1.260 29.043 29.044 dbt_tas_total 343 13.7 0.111 0.305 29.035 29.035 dbt_tas_multiply 216 13.5 0.001 0.001 28.569 28.572 qs_energies 1 3.0 0.000 0.000 27.119 27.119 scf_env_do_scf 1 4.0 0.000 0.001 26.847 26.847 qs_ks_update_qs_env 8 6.0 0.000 0.000 26.244 26.245 qs_ks_update_qs_env_forces 1 3.0 0.000 0.000 22.258 22.258 dbt_tas_dbm 216 15.5 0.001 0.002 21.290 21.303 dbm_multiply 216 17.5 19.039 20.028 19.039 20.028 hfx_ri_update_forces 1 7.0 0.057 0.063 18.443 18.449 scf_env_do_scf_inner_loop 6 5.0 0.000 0.001 15.438 15.438 hfx_ri_update_ks_Pmat_KS 63 11.6 0.001 0.001 13.931 13.943 hfx_ri_forces_Pmat_3c 1 8.0 0.155 0.168 13.755 13.755 init_scf_loop 2 5.0 0.000 0.000 11.408 11.408 dbt_tas_mm_2 91 16.5 0.001 0.001 10.094 10.107 dbt_copy 497 12.3 0.010 0.012 8.214 8.580 mp_sync 2769 12.9 5.885 7.443 5.885 7.443 dbt_reshape 365 13.6 3.463 3.632 6.445 6.693 dbt_tas_mm_3T 77 17.1 0.000 0.000 5.347 6.008 hfx_ri_update_ks_Pmat_Px3C 63 11.6 0.000 0.000 5.327 5.333 dbt_tas_mm_3N 37 15.4 0.000 0.000 4.027 4.198 precalc_derivatives 1 8.0 0.077 0.082 3.480 3.480 dbt_tas_reserve_blocks_index 1380 15.8 0.892 0.916 2.937 3.331 hfx_ri_pre_scf_Pmat 1 12.0 0.000 0.000 3.275 3.275 mp_waitall_2 1234 16.4 2.706 2.896 2.706 2.896 dbt_reserve_blocks_index 1051 14.7 0.103 0.109 2.454 2.760 dbt_reserve_blocks_index_array 1028 13.8 0.005 0.006 2.427 2.729 dbt_crop 372 13.7 1.688 1.789 2.442 2.647 dbm_reserve_blocks 1529 16.7 2.237 2.624 2.237 2.624 dbt_communicate_buffer 365 14.6 0.012 0.013 1.934 2.094 build_3c_derivatives 3 9.0 0.220 0.243 1.940 1.952 mp_sum_l 6385 13.7 1.566 1.742 1.566 1.742 hfx_ri_update_ks_Pmat_copy_2 63 11.6 0.000 0.000 1.732 1.735 dbt_tas_replicate 149 15.4 0.616 0.653 1.586 1.674 hfx_ri_pre_scf_Pmat_RIx3C 9 13.0 0.000 0.000 1.668 1.671 convert_to_new_pgrid 648 15.5 0.035 0.064 1.284 1.582 dbm_copy 452 16.3 1.121 1.418 1.121 1.418 dbt_tas_copy 132 12.5 0.557 0.605 1.091 1.210 ------------------------------------------------------------------------------- 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=45.14100000000002, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_multiply", label="dbm_multiply", y=146.566, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=31.408, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbt_reshape", label="dbt_reshape", y=6.944, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=6.786, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="hfx_ri_forces_Pmat_3c", label="hfx_ri_forces_Pmat_3c", y=4.855, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="mp_sync", label="mp_sync", y=0.0, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32omp", name="mp_waitall_2", label="mp_waitall_2", y=0.0, yerr=0.0 Plot: name="RI-HFX_H2O-32_timings_32mpi", title="Timings of RI-HFX_H2O-32 with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="rest", label="rest", y=14.913999999999994, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_multiply", label="dbm_multiply", y=19.039, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_update_ks_Pmat", label="hfx_ri_update_ks_Pmat", y=1.172, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbt_reshape", label="dbt_reshape", y=3.463, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="dbm_reserve_blocks", label="dbm_reserve_blocks", y=2.237, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="hfx_ri_forces_Pmat_3c", label="hfx_ri_forces_Pmat_3c", y=0.155, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_sync", label="mp_sync", y=5.885, yerr=0.0 PlotPoint: plot="RI-HFX_H2O-32_timings_32mpi", name="mp_waitall_2", label="mp_waitall_2", y=2.706, 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 0.015 180.643 180.643 qs_energies 1 2.0 0.000 0.000 180.449 180.449 mp2_main 1 3.0 0.000 0.000 174.879 174.879 mp2_gpw_main 1 4.0 0.001 0.001 174.452 174.452 mp2_ri_gpw_compute_in 1 5.0 0.399 0.399 127.828 127.828 mp2_ri_gpw_compute_in_loop 1 6.0 0.011 0.011 118.510 118.510 mp2_eri_3c_integrate_gpw 2656 7.0 0.016 0.016 85.645 85.645 integrate_v_rspace 2666 8.0 0.624 0.624 72.440 72.440 grid_integrate_task_list 2666 9.0 69.785 69.785 69.785 69.785 mp2_ri_gpw_compute_en 1 5.0 0.089 0.089 46.599 46.599 mp2_ri_gpw_compute_en_RI_loop 1 6.0 9.747 9.747 44.703 44.703 mp2_ri_gpw_compute_en_expansio 2080 7.0 2.089 2.089 27.223 27.223 local_gemm 2080 8.0 25.133 25.133 25.133 25.133 dbcsr_multiply_generic 5322 8.0 0.182 0.182 22.148 22.148 ao_to_mo_and_store_B_mult_1 2656 7.0 0.011 0.011 22.128 22.128 pw_transfer 63872 10.6 1.099 1.099 12.265 12.265 calculate_wavefunction 2656 8.0 8.043 8.043 11.869 11.869 multiply_cannon 5322 9.0 0.470 0.470 11.404 11.404 fft_wrap_pw1pw2 53228 11.4 0.118 0.118 10.937 10.937 ao_to_mo_and_store_B_E_Ex_1 2656 7.0 2.615 2.615 10.619 10.619 multiply_cannon_loop 5322 10.0 0.117 0.117 9.970 9.970 get_2c_integrals 1 6.0 0.000 0.000 8.918 8.918 copy_dbcsr_to_fm 2679 8.0 0.029 0.029 8.544 8.544 multiply_cannon_multrec 5322 11.0 8.330 8.330 8.373 8.373 make_m2s 10644 9.0 0.065 0.065 8.296 8.296 compute_2c_integrals 1 7.0 0.006 0.006 8.050 8.050 compute_2c_integrals_loop_lm 1 8.0 0.012 0.012 8.035 8.035 mp2_eri_2c_integrate_gpw 1 9.0 0.890 0.890 8.024 8.024 make_images 10644 10.0 3.255 3.255 7.979 7.979 fft_wrap_pw1pw2_20 21271 12.4 0.540 0.540 7.773 7.773 dbcsr_complete_redistribute 2689 9.0 1.233 1.233 6.917 6.917 fft3d_s 53229 13.4 6.610 6.610 6.651 6.651 dbcsr_finalize 10708 9.5 0.210 0.210 6.148 6.148 mp2_ri_gpw_compute_en_ener 2080 7.0 5.701 5.701 5.701 5.701 dbcsr_merge_all 8011 10.3 4.147 4.147 5.461 5.461 scf_env_do_scf 1 3.0 0.000 0.000 5.156 5.156 scf_env_do_scf_inner_loop 10 4.0 0.001 0.001 5.156 5.156 potential_pw2rs 5322 10.0 0.154 0.154 4.056 4.056 qs_scf_new_mos 10 5.0 0.000 0.000 3.846 3.846 ------------------------------------------------------------------------------- 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 0.030 42.961 42.972 qs_energies 1 2.0 0.000 0.001 42.801 42.802 mp2_main 1 3.0 0.000 0.001 40.640 40.640 mp2_gpw_main 1 4.0 0.001 0.002 40.541 40.541 mp2_ri_gpw_compute_en 1 5.0 0.293 0.306 21.847 22.117 mp2_ri_gpw_compute_en_RI_loop 1 6.0 4.043 4.551 20.404 20.411 mp2_ri_gpw_compute_in 1 5.0 0.054 0.054 18.601 19.069 mp2_ri_gpw_compute_in_loop 1 6.0 0.001 0.001 17.212 17.685 mp2_eri_3c_integrate_gpw 83 7.0 0.001 0.001 14.863 15.148 integrate_v_rspace 93 8.1 0.118 0.137 14.726 15.014 grid_integrate_task_list 93 9.1 14.389 14.684 14.389 14.684 mp2_ri_gpw_compute_en_expansio 65 7.0 0.176 0.215 11.806 11.978 local_gemm 65 8.0 11.629 11.816 11.629 11.816 mp2_ri_gpw_compute_en_comm 30 7.0 0.098 0.116 4.069 5.157 mp_sendrecv_dm3 1860 8.0 3.216 4.447 3.216 4.447 dbcsr_multiply_generic 176 8.0 0.009 0.010 1.993 2.375 ao_to_mo_and_store_B_mult_1 83 7.0 0.001 0.001 1.976 2.360 scf_env_do_scf 1 3.0 0.000 0.000 2.018 2.018 scf_env_do_scf_inner_loop 10 4.0 0.000 0.002 2.018 2.018 get_2c_integrals 1 6.0 0.004 0.015 1.307 1.338 multiply_cannon 176 9.0 0.018 0.019 1.141 1.280 multiply_cannon_loop 176 10.0 0.002 0.002 1.080 1.216 make_m2s 352 9.0 0.003 0.003 0.812 1.049 make_images 352 10.0 0.056 0.058 0.798 1.035 multiply_cannon_multrec 246 11.0 0.920 0.995 0.925 1.002 fill_local_i_aL 1920 8.0 0.807 0.967 0.807 0.967 qs_scf_new_mos 10 5.0 0.000 0.000 0.960 0.965 compute_2c_integrals 1 7.0 0.003 0.006 0.947 0.964 eigensolver 11 5.8 0.001 0.001 0.906 0.908 compute_2c_integrals_loop_lm 1 8.0 0.002 0.003 0.833 0.863 mp2_eri_2c_integrate_gpw 1 9.0 0.214 0.231 0.832 0.861 ------------------------------------------------------------------------------- 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=59.60500000000002, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=69.785, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="local_gemm", label="local_gemm", y=25.133, 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=9.747, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=8.33, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32omp", name="calculate_wavefunction", label="calculate_wavefunction", y=8.043, 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=8.763999999999996, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=14.389, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="local_gemm", label="local_gemm", y=11.629, 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=4.043, yerr=0.0 PlotPoint: plot="RI-MP2_ammonia_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=0.92, 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=3.216, 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 0.106 0.106 122.092 122.092 qs_energies 1 2.0 0.000 0.000 120.611 120.611 scf_env_do_scf 1 3.0 0.000 0.000 113.933 113.933 scf_env_do_scf_inner_loop 15 4.0 0.002 0.002 113.932 113.932 qs_ks_update_qs_env 15 5.0 0.000 0.000 48.583 48.583 rebuild_ks_matrix 15 6.0 0.000 0.000 48.372 48.372 qs_ks_build_kohn_sham_matrix 15 7.0 0.002 0.002 48.372 48.372 qs_scf_new_mos 15 5.0 0.000 0.000 42.391 42.391 eigensolver 15 6.0 0.002 0.002 34.533 34.533 qs_vxc_create 15 8.0 0.031 0.031 33.077 33.077 calculate_dispersion_nonloc 15 9.0 6.684 6.684 28.962 28.962 pw_transfer 1191 10.0 0.063 0.063 22.677 22.677 fft_wrap_pw1pw2 1086 11.0 0.008 0.008 22.483 22.483 cp_fm_diag_elpa 15 7.0 0.000 0.000 22.161 22.161 cp_fm_diag_elpa_base 15 8.0 19.583 19.583 22.161 22.161 qs_rho_update_rho_low 16 5.0 0.000 0.000 20.074 20.074 calculate_rho_elec 16 6.0 0.223 0.223 20.074 20.074 grid_collocate_task_list 16 7.0 18.555 18.555 18.555 18.555 fft_wrap_pw1pw2_150 765 12.0 3.522 3.522 16.450 16.450 sum_up_and_integrate 15 8.0 0.137 0.137 14.223 14.223 integrate_v_rspace 15 9.0 0.020 0.020 14.086 14.086 grid_integrate_task_list 15 10.0 13.558 13.558 13.558 13.558 fft3d_s 1087 13.0 10.267 10.267 10.274 10.274 cp_fm_cholesky_restore 45 7.0 10.096 10.096 10.096 10.096 pw_scatter_s 585 13.1 6.760 6.760 6.760 6.760 fft_wrap_pw1pw2_200 197 12.3 0.668 0.668 5.739 5.739 copy_dbcsr_to_fm 16 5.9 0.000 0.000 5.636 5.636 dbcsr_complete_redistribute 46 8.3 2.273 2.273 5.594 5.594 cp_fm_upper_to_full 30 8.0 4.852 4.852 4.852 4.852 vdW_energy 15 10.0 4.467 4.467 4.467 4.467 xc_vxc_pw_create 15 9.0 0.213 0.213 4.084 4.084 gspace_mixing 14 5.0 0.170 0.170 3.976 3.976 broyden_mixing 14 6.0 3.401 3.401 3.401 3.401 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 3.153 3.153 init_scf_run 1 3.0 0.000 0.000 3.052 3.052 xc_pw_derive 90 11.0 0.001 0.001 2.658 2.658 calculate_dm_sparse 15 6.0 0.017 0.017 2.596 2.596 cp_dbcsr_plus_fm_fm_t_native 15 7.0 0.000 0.000 2.515 2.515 ------------------------------------------------------------------------------- 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 0.018 0.026 63.970 63.980 qs_energies 1 2.0 0.000 0.001 63.650 63.650 scf_env_do_scf 1 3.0 0.000 0.001 59.109 59.110 scf_env_do_scf_inner_loop 15 4.0 0.001 0.003 59.109 59.110 qs_ks_update_qs_env 15 5.0 0.000 0.000 25.997 26.010 rebuild_ks_matrix 15 6.0 0.000 0.000 25.964 25.977 qs_ks_build_kohn_sham_matrix 15 7.0 0.003 0.003 25.964 25.977 qs_rho_update_rho_low 16 5.0 0.000 0.000 19.808 19.813 calculate_rho_elec 16 6.0 0.007 0.008 19.808 19.812 grid_collocate_task_list 16 7.0 17.584 17.835 17.584 17.835 sum_up_and_integrate 15 8.0 0.017 0.021 14.418 14.472 integrate_v_rspace 15 9.0 0.001 0.001 14.401 14.457 qs_scf_new_mos 15 5.0 0.000 0.001 14.043 14.208 grid_integrate_task_list 15 10.0 13.334 13.442 13.334 13.442 eigensolver 15 6.0 0.001 0.002 12.924 12.947 qs_vxc_create 15 8.0 0.001 0.001 11.196 11.210 cp_fm_diag_elpa 15 7.0 0.000 0.000 9.208 9.215 cp_fm_diag_elpa_base 15 8.0 9.057 9.073 9.203 9.206 pw_transfer 1191 10.0 0.098 0.108 9.029 9.072 calculate_dispersion_nonloc 15 9.0 0.926 1.011 8.987 9.006 fft_wrap_pw1pw2 1086 11.0 0.014 0.016 8.840 8.894 fft3d_ps 1086 13.0 3.096 3.303 5.914 6.125 fft_wrap_pw1pw2_150 765 12.0 0.796 0.878 5.797 5.822 cp_fm_cholesky_restore 45 7.0 3.546 3.599 3.546 3.599 fft_wrap_pw1pw2_200 197 12.3 0.510 0.577 2.925 2.952 mp_alltoall_z22v 1086 15.0 2.157 2.713 2.157 2.713 qs_energies_init_hamiltonians 1 3.0 0.000 0.000 2.616 2.616 build_core_hamiltonian_matrix 1 4.0 0.000 0.000 2.211 2.489 rs_pw_transfer 158 9.4 0.002 0.002 1.978 2.336 xc_vxc_pw_create 15 9.0 0.016 0.021 2.209 2.247 density_rs2pw 16 7.0 0.001 0.001 1.981 2.169 mp_waitany 520 11.3 1.378 1.858 1.378 1.858 x_to_yz 585 14.1 0.368 0.385 1.458 1.700 yz_to_x 501 13.9 0.264 0.300 1.331 1.681 init_scf_run 1 3.0 0.000 0.000 1.648 1.649 xc_pw_derive 90 11.0 0.001 0.002 1.527 1.610 scf_env_initial_rho_setup 1 4.0 0.000 0.000 1.521 1.522 rs_pw_transfer_RS2PW_200 18 8.8 0.035 0.040 0.987 1.512 build_core_ppnl 1 5.0 1.295 1.423 1.295 1.423 vdW_energy 15 10.0 1.358 1.413 1.358 1.413 ------------------------------------------------------------------------------- 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=50.033, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=19.583, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=18.555, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.558, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="fft3d_s", label="fft3d_s", y=10.267, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32omp", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=10.096, 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=17.35300000000001, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_diag_elpa_base", label="cp_fm_diag_elpa_base", y=9.057, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=17.584, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=13.334, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="fft3d_s", label="fft3d_s", y=0.0, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="cp_fm_cholesky_restore", label="cp_fm_cholesky_restore", y=3.546, yerr=0.0 PlotPoint: plot="diag_cu144_broy_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=3.096, 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 0.081 0.081 274.859 274.859 qs_energies 1 2.0 0.000 0.000 274.674 274.674 ls_scf 1 3.0 0.000 0.000 273.436 273.436 ls_scf_main 1 4.0 0.002 0.002 264.044 264.044 density_matrix_trs4 11 5.0 0.012 0.012 166.117 166.117 ls_scf_dm_to_ks 11 5.0 0.000 0.000 91.716 91.716 matrix_ls_to_qs 11 6.0 0.000 0.000 88.061 88.061 dbcsr_multiply_generic 185 6.1 0.980 0.980 79.619 79.619 arnoldi_extremal 12 6.1 0.000 0.000 70.517 70.517 arnoldi_normal_ev 12 7.1 0.051 0.051 70.517 70.517 build_subspace 23 8.1 0.085 0.085 69.278 69.278 dbcsr_matrix_vector_mult 652 9.0 0.246 0.246 68.819 68.819 dbcsr_matrix_vector_mult_local 652 10.0 67.232 67.232 67.242 67.242 dbcsr_complete_redistribute 23 7.5 33.945 33.945 47.440 47.440 multiply_cannon 185 7.1 0.378 0.378 46.168 46.168 dbcsr_copy_into_existing 11 7.0 44.953 44.953 44.953 44.953 matrix_decluster 11 7.0 0.000 0.000 43.107 43.107 multiply_cannon_loop 185 8.1 0.293 0.293 33.487 33.487 make_m2s 370 7.1 0.039 0.039 28.296 28.296 make_images 370 8.1 12.606 12.606 26.026 26.026 multiply_cannon_multrec 185 9.1 23.979 23.979 24.128 24.128 dbcsr_finalize 646 7.5 0.256 0.256 17.717 17.717 dbcsr_merge_all 597 8.5 2.665 2.665 16.398 16.398 tree_to_linear_d 110 9.4 12.223 12.223 12.223 12.223 setup_rec_index_2d 370 8.1 12.193 12.193 12.193 12.193 dbcsr_sort_indices 1103 9.9 11.591 11.591 11.591 11.591 quick_finalize 395 10.0 0.401 0.401 9.979 9.979 dbcsr_special_finalize 370 9.1 0.002 0.002 9.204 9.204 calculate_norms 370 9.1 9.067 9.067 9.067 9.067 ls_scf_init_scf 1 4.0 0.000 0.000 8.714 8.714 ls_scf_init_matrix_S 1 5.0 0.000 0.000 8.377 8.377 matrix_sqrt_Newton_Schulz 1 6.0 0.001 0.001 7.716 7.716 dbcsr_dot_sd 144 6.3 7.328 7.328 7.329 7.329 matrix_qs_to_ls 12 5.1 0.000 0.000 6.383 6.383 matrix_cluster 12 6.1 0.000 0.000 6.383 6.383 dbcsr_frobenius_norm 142 6.1 5.739 5.739 5.741 5.741 ------------------------------------------------------------------------------- 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 0.008 0.021 72.153 72.163 qs_energies 1 2.0 0.000 0.000 72.024 72.024 ls_scf 1 3.0 0.000 0.000 71.968 71.969 ls_scf_main 1 4.0 0.001 0.009 69.317 69.318 density_matrix_trs4 11 5.0 0.006 0.021 66.653 66.734 dbcsr_multiply_generic 185 6.1 0.060 0.074 63.176 63.567 multiply_cannon 185 7.1 0.034 0.038 52.055 53.081 multiply_cannon_loop 185 8.1 0.114 0.129 49.596 50.476 multiply_cannon_multrec 1480 9.1 30.080 32.961 30.340 33.223 mp_waitall_1 11936 10.3 17.197 20.627 17.197 20.627 multiply_cannon_metrocomm3 1480 9.1 0.015 0.017 12.945 17.127 make_m2s 370 7.1 0.035 0.037 7.245 7.309 make_images 370 8.1 0.636 0.662 7.113 7.175 calculate_norms 2960 9.1 4.963 5.458 4.963 5.458 mp_sum_l 1199 5.3 2.946 4.366 2.946 4.366 make_images_data 370 9.1 0.010 0.012 3.353 3.583 hybrid_alltoall_any 393 9.9 0.248 1.115 2.920 3.201 dbcsr_multiply_generic_mpsum_f 137 7.1 0.000 0.000 2.007 3.130 arnoldi_extremal 12 6.1 0.000 0.001 2.530 2.550 arnoldi_normal_ev 12 7.1 0.002 0.008 2.530 2.549 build_subspace 23 8.1 0.020 0.026 2.430 2.432 ls_scf_dm_to_ks 11 5.0 0.000 0.000 2.310 2.394 multiply_cannon_metrocomm1 1480 9.1 0.006 0.007 1.197 2.278 dbcsr_complete_redistribute 23 7.5 1.221 1.291 2.084 2.201 dbcsr_matrix_vector_mult 652 9.0 0.014 0.050 2.036 2.196 matrix_ls_to_qs 11 6.0 0.000 0.000 2.023 2.139 matrix_decluster 11 7.0 0.000 0.000 1.881 1.997 ls_scf_init_scf 1 4.0 0.000 0.000 1.976 1.976 ls_scf_init_matrix_S 1 5.0 0.000 0.000 1.950 1.956 make_images_pack 370 9.1 1.718 1.908 1.721 1.912 dbcsr_matrix_vector_mult_local 652 10.0 1.649 1.896 1.651 1.898 matrix_sqrt_Newton_Schulz 1 6.0 0.000 0.001 1.770 1.773 buffer_matrices_ensure_size 370 8.1 1.394 1.598 1.394 1.598 ------------------------------------------------------------------------------- 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=83.077, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=67.232, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_copy_into_existing", label="dbcsr_copy_into_existing", y=44.953, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="dbcsr_complete_redistribute", label="dbcsr_complete_redistribute", y=33.945, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=23.979, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="make_images", label="make_images", y=12.606, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="calculate_norms", label="calculate_norms", y=9.067, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="mp_sum_l", label="mp_sum_l", y=0.0, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="make_images_pack", label="make_images_pack", y=0.0, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32omp", name="mp_waitall_1", label="mp_waitall_1", y=0.0, yerr=0.0 Plot: name="bench_dftb_timings_32mpi", title="Timings of bench_dftb with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="bench_dftb_timings_32mpi", name="rest", label="rest", y=11.74300000000001, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="dbcsr_matrix_vector_mult_local", label="dbcsr_matrix_vector_mult_local", y=1.649, 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=1.221, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=30.08, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="make_images", label="make_images", y=0.636, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="calculate_norms", label="calculate_norms", y=4.963, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=2.946, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="make_images_pack", label="make_images_pack", y=1.718, yerr=0.0 PlotPoint: plot="bench_dftb_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=17.197, 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 70.268 70.268 lib_test 1 2.0 0.000 0.000 70.260 70.260 dbcsr_run_tests 3 3.0 0.002 0.002 70.260 70.260 test_multiplies_multiproc 3 4.0 0.001 0.001 54.988 54.988 dbcsr_redistribute 9 5.0 36.243 36.243 37.841 37.841 dbcsr_multiply_generic 9 5.0 0.001 0.001 15.803 15.803 dbcsr_make_random_matrix 9 4.0 12.183 12.183 15.162 15.162 multiply_cannon 9 6.0 0.001 0.001 11.081 11.081 multiply_cannon_loop 9 7.0 0.017 0.017 10.728 10.728 multiply_cannon_multrec 9 8.0 10.710 10.710 10.711 10.711 dbcsr_finalize 27 5.7 0.023 0.023 5.506 5.506 dbcsr_merge_all 18 6.5 1.972 1.972 4.772 4.772 dbcsr_data_release 975 7.6 2.822 2.822 2.822 2.822 tree_to_linear_d 9 7.0 1.859 1.859 1.859 1.859 make_m2s 18 6.0 0.001 0.001 1.615 1.615 make_images 18 7.0 0.556 0.556 1.567 1.567 ------------------------------------------------------------------------------- From /workspace/artifacts/dbcsr_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.004 0.010 18.822 18.827 lib_test 1 2.0 0.000 0.000 18.676 18.697 dbcsr_run_tests 3 3.0 0.000 0.001 18.675 18.696 test_multiplies_multiproc 3 4.0 0.000 0.002 17.839 17.919 dbcsr_multiply_generic 9 5.0 0.001 0.001 16.327 16.430 multiply_cannon 9 6.0 0.001 0.002 14.351 14.800 multiply_cannon_loop 9 7.0 0.002 0.002 14.072 14.505 multiply_cannon_multrec 72 8.0 10.531 11.057 10.531 11.057 mp_waitall_1 576 9.2 3.861 4.658 3.861 4.658 multiply_cannon_metrocomm1 72 8.0 0.001 0.001 3.427 4.225 mp_sum_l 470 2.5 0.744 1.131 0.744 1.131 dbcsr_multiply_generic_mpsum_f 9 6.0 0.000 0.000 0.730 1.117 dbcsr_data_release 444 7.6 0.755 0.863 0.755 0.863 dbcsr_make_random_matrix 9 4.0 0.652 0.665 0.791 0.818 dbcsr_destroy 111 5.9 0.003 0.074 0.646 0.757 make_m2s 18 6.0 0.001 0.001 0.691 0.740 make_images 18 7.0 0.021 0.021 0.688 0.737 dbcsr_finalize 27 5.7 0.000 0.000 0.564 0.644 dbcsr_redistribute 9 5.0 0.240 0.282 0.530 0.562 dbcsr_merge_all 18 6.5 0.083 0.097 0.450 0.527 multiply_cannon_metrocomm3 72 8.0 0.000 0.000 0.110 0.512 make_images_data 18 8.0 0.000 0.001 0.359 0.421 ------------------------------------------------------------------------------- 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=6.337999999999994, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_redistribute", label="dbcsr_redistribute", y=36.243, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=12.183, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=10.71, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_data_release", label="dbcsr_data_release", y=2.822, yerr=0.0 PlotPoint: plot="dbcsr_timings_32omp", name="dbcsr_merge_all", label="dbcsr_merge_all", y=1.972, 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=1.9559999999999995, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_redistribute", label="dbcsr_redistribute", y=0.24, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_make_random_matrix", label="dbcsr_make_random_matrix", y=0.652, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="multiply_cannon_multrec", label="multiply_cannon_multrec", y=10.531, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_data_release", label="dbcsr_data_release", y=0.755, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="dbcsr_merge_all", label="dbcsr_merge_all", y=0.083, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_waitall_1", label="mp_waitall_1", y=3.861, yerr=0.0 PlotPoint: plot="dbcsr_timings_32mpi", name="mp_sum_l", label="mp_sum_l", y=0.744, 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 0.053 0.053 132.781 132.781 qs_mol_dyn_low 1 2.0 0.003 0.003 131.382 131.382 velocity_verlet 5 3.0 0.003 0.003 107.366 107.366 qmmm_el_coupling 6 3.8 0.000 0.000 88.121 88.121 qmmm_elec_with_gaussian 6 4.8 0.012 0.012 88.117 88.117 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 87.498 87.498 qmmm_elec_gaussian_low_G 6 6.8 86.595 86.595 86.595 86.595 qs_forces 6 3.8 0.001 0.001 34.960 34.960 qs_energies 6 4.8 0.000 0.000 31.086 31.086 scf_env_do_scf 6 5.8 0.001 0.001 28.653 28.653 scf_env_do_scf_inner_loop 39 6.8 0.004 0.004 24.691 24.691 rebuild_ks_matrix 45 8.4 0.000 0.000 24.088 24.088 qs_ks_build_kohn_sham_matrix 45 9.4 0.005 0.005 24.088 24.088 qs_ks_update_qs_env 45 7.8 0.000 0.000 20.665 20.665 pw_transfer 966 12.3 0.053 0.053 17.262 17.262 fft_wrap_pw1pw2 801 13.6 0.006 0.006 17.029 17.029 fft_wrap_pw1pw2_150 507 15.2 2.318 2.318 16.625 16.625 qs_vxc_create 45 10.4 0.001 0.001 13.170 13.170 xc_vxc_pw_create 45 11.4 0.634 0.634 13.170 13.170 xc_pw_derive 270 13.4 0.002 0.002 9.366 9.366 fft3d_s 802 15.6 7.750 7.750 7.757 7.757 qs_rho_update_rho_low 45 7.9 0.000 0.000 7.028 7.028 calculate_rho_elec 45 8.9 0.563 0.563 7.028 7.028 xc_rho_set_and_dset_create 45 12.4 0.606 0.606 6.905 6.905 pw_scatter_s 429 15.8 5.707 5.707 5.707 5.707 xc_pw_divergence 45 12.4 0.001 0.001 5.584 5.584 qmmm_forces 6 3.8 0.001 0.001 5.196 5.196 qmmm_forces_with_gaussian 6 4.8 0.017 0.017 4.854 4.854 pw_integral_ab 2539 7.4 4.496 4.496 4.496 4.496 qs_ks_ddapc 45 10.4 0.001 0.001 4.216 4.216 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 4.142 4.142 init_scf_loop 6 6.8 0.000 0.000 3.957 3.957 sum_up_and_integrate 45 10.4 0.468 0.468 3.486 3.486 qmmm_forces_gaussian_low_G 6 6.8 3.451 3.451 3.451 3.451 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 3.431 3.431 density_rs2pw 45 9.9 0.002 0.002 3.312 3.312 grid_collocate_task_list 45 9.9 3.153 3.153 3.153 3.153 integrate_v_rspace 45 11.4 0.006 0.006 3.019 3.019 ------------------------------------------------------------------------------- From /workspace/artifacts/MQAE_single_node_32mpi.out: ------------------------------------------------------------------------------- - - - T I M I N G - - - ------------------------------------------------------------------------------- SUBROUTINE CALLS ASD SELF TIME TOTAL TIME MAXIMUM AVERAGE MAXIMUM AVERAGE MAXIMUM CP2K 1 1.0 0.041 0.061 55.908 55.922 qs_mol_dyn_low 1 2.0 0.003 0.004 54.794 54.852 qs_forces 6 3.8 0.001 0.001 40.666 40.666 qs_energies 6 4.8 0.000 0.000 38.836 38.837 scf_env_do_scf 6 5.8 0.000 0.001 37.863 37.863 scf_env_do_scf_inner_loop 113 6.2 0.002 0.019 36.206 36.206 rebuild_ks_matrix 119 8.1 0.000 0.000 26.503 26.514 qs_ks_build_kohn_sham_matrix 119 9.1 0.014 0.016 26.503 26.513 qs_ks_update_qs_env 119 7.3 0.001 0.001 24.952 24.962 velocity_verlet 5 3.0 0.002 0.003 22.663 22.666 pw_transfer 2446 12.3 0.177 0.209 18.966 19.456 fft_wrap_pw1pw2 2059 13.4 0.022 0.026 18.585 19.038 fft_wrap_pw1pw2_150 1321 14.9 2.729 3.302 17.950 18.528 qs_vxc_create 119 10.1 0.002 0.002 14.341 14.343 xc_vxc_pw_create 119 11.1 0.139 0.203 14.339 14.342 fft3d_ps 2059 15.4 6.870 7.999 12.435 13.824 xc_pw_derive 714 13.1 0.010 0.012 11.006 11.245 qs_rho_update_rho_low 119 7.3 0.000 0.001 10.499 10.499 calculate_rho_elec 119 8.3 0.049 0.056 10.498 10.499 sum_up_and_integrate 119 10.1 0.066 0.082 8.907 8.920 integrate_v_rspace 119 11.1 0.003 0.003 8.840 8.862 xc_pw_divergence 119 12.1 0.004 0.006 7.146 7.377 qmmm_forces 6 3.8 0.002 0.002 7.083 7.083 xc_rho_set_and_dset_create 119 12.1 0.310 0.382 6.815 7.044 qmmm_forces_with_gaussian 6 4.8 0.006 0.008 6.753 6.953 rs_pw_transfer 988 11.5 0.012 0.014 6.163 6.425 density_rs2pw 119 9.3 0.006 0.011 6.167 6.386 mp_alltoall_z22v 2059 17.4 4.381 6.360 4.381 6.360 qmmm_el_coupling 6 3.8 0.000 0.000 6.142 6.316 qmmm_elec_with_gaussian 6 4.8 0.003 0.003 6.140 6.313 potential_pw2rs 119 12.1 0.005 0.006 5.275 5.289 grid_collocate_task_list 119 9.3 4.127 4.402 4.127 4.402 x_to_yz 1095 16.8 0.675 0.763 2.965 3.921 qmmm_force_with_gaussian_low 6 5.8 0.000 0.000 3.821 3.873 yz_to_x 964 16.0 0.450 0.593 2.541 3.647 qmmm_elec_with_gaussian_low 6 5.8 0.000 0.000 3.407 3.499 grid_integrate_task_list 119 12.1 3.324 3.498 3.324 3.498 mp_waitany 4028 12.8 2.529 3.253 2.529 3.253 qmmm_forces_gaussian_low_G 6 6.8 3.143 3.194 3.143 3.194 qmmm_elec_gaussian_low_G 6 6.8 2.821 2.915 2.821 2.915 qs_scf_new_mos 113 7.2 0.000 0.001 2.613 2.619 qs_scf_loop_do_ot 113 8.2 0.000 0.001 2.612 2.618 pw_restrict_s3 18 5.8 1.302 1.358 2.401 2.604 ot_scf_mini 113 9.2 0.001 0.001 2.527 2.532 rs_pw_transfer_PW2RS_150 125 13.9 0.744 0.914 2.323 2.363 pw_gather_p 964 15.0 1.837 2.213 1.837 2.213 qmmm_elec_with_gaussian:spline 6 5.8 0.000 0.000 1.997 2.174 pw_prolongate_s3 18 6.8 1.098 1.152 1.997 2.174 rs_pw_transfer_RS2PW_150 125 11.2 0.608 0.778 1.903 2.155 qs_ks_ddapc 119 10.1 0.002 0.003 1.985 2.104 dbcsr_multiply_generic 2588 12.3 0.057 0.059 1.846 1.870 init_scf_loop 6 6.8 0.000 0.000 1.654 1.655 pw_scatter_p 1095 15.8 1.521 1.629 1.521 1.629 pw_integral_ab 2761 7.7 1.105 1.290 1.406 1.562 qs_ks_update_qs_env_forces 6 4.8 0.000 0.000 1.560 1.561 mp_sum_d 5822 12.2 0.840 1.516 0.840 1.516 ot_mini 113 10.2 0.000 0.000 1.207 1.214 mp_sum_dm3 33 5.7 1.171 1.214 1.171 1.214 ------------------------------------------------------------------------------- Plot: name="MQAE_single_node_timings_32omp", title="Timings of MQAE_single_node with 32 OpenMP Threads", ylabel="time [s]" PlotPoint: plot="MQAE_single_node_timings_32omp", name="rest", label="rest", y=21.62900000000002, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=86.595, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_s", label="fft3d_s", y=7.75, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_scatter_s", label="pw_scatter_s", y=5.707, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="pw_integral_ab", label="pw_integral_ab", y=4.496, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.451, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="grid_collocate_task_list", label="grid_collocate_task_list", y=3.153, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=0.0, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="grid_integrate_task_list", label="grid_integrate_task_list", y=0.0, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32omp", name="fft3d_ps", label="fft3d_ps", y=0.0, yerr=0.0 Plot: name="MQAE_single_node_timings_32mpi", title="Timings of MQAE_single_node with 32 MPI Ranks", ylabel="time [s]" PlotPoint: plot="MQAE_single_node_timings_32mpi", name="rest", label="rest", y=30.137, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_elec_gaussian_low_G", label="qmmm_elec_gaussian_low_G", y=2.821, 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=1.105, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="qmmm_forces_gaussian_low_G", label="qmmm_forces_gaussian_low_G", y=3.143, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_collocate_task_list", label="grid_collocate_task_list", y=4.127, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="mp_alltoall_z22v", label="mp_alltoall_z22v", y=4.381, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="grid_integrate_task_list", label="grid_integrate_task_list", y=3.324, yerr=0.0 PlotPoint: plot="MQAE_single_node_timings_32mpi", name="fft3d_ps", label="fft3d_ps", y=6.87, yerr=0.0 Summary: Performance test took 32 minutes. Status: OK Removing intermediate container c40b384523c0 ---> 59c0a745cff7 Step 41/42 : CMD cat $(find ./report.log -mmin +10) | sed '/^Summary:/ s/$/ (cached)/' ---> Running in 5e1bc55b517a Removing intermediate container 5e1bc55b517a ---> 15f64dc41537 Step 42/42 : ENTRYPOINT [] ---> Running in f4b4f6855389 Removing intermediate container f4b4f6855389 ---> 84f7f1f11632 [Warning] One or more build-args [GIT_COMMIT_SHA] were not consumed Successfully built 84f7f1f11632 Successfully tagged us-central1-docker.pkg.dev/cp2k-org-project/cp2kci/img_cp2k-perf-openmp:master Pushing new image... done. #################### Running Image cp2k-perf-openmp #################### Uploading artifacts... done EndDate: 2023-06-16 13:54:09+00:00